From 9b6b7bab0ea6fa2a5c0180cd02368f661962929b Mon Sep 17 00:00:00 2001 From: chenghao xiao <85804993+gowitheflow-1998@users.noreply.github.com> Date: Fri, 12 Jul 2024 00:59:27 +0800 Subject: [PATCH] RAR-b results (#7) * rarb results * rarb results * rarb results model-level diff * rarb results model-level diff --- .../no_revision_available/ARCChallenge.json | 42 +++++ .../no_revision_available/AlphaNLI.json | 42 +++++ .../no_revision_available/HellaSwag.json | 42 +++++ .../no_revision_available/PIQA.json | 42 +++++ .../no_revision_available/Quail.json | 42 +++++ .../no_revision_available/RARbCode.json | 42 +++++ .../no_revision_available/RARbMath.json | 42 +++++ .../no_revision_available/SIQA.json | 42 +++++ .../no_revision_available/SpartQA.json | 42 +++++ .../no_revision_available/TempReasonL1.json | 42 +++++ .../TempReasonL2Fact.json | 42 +++++ .../TempReasonL2Pure.json | 42 +++++ .../TempReasonL3Fact.json | 42 +++++ .../TempReasonL3Pure.json | 42 +++++ .../no_revision_available/WinoGrande.json | 42 +++++ .../no_revision_available/ARCChallenge.json | 42 +++++ .../no_revision_available/AlphaNLI.json | 42 +++++ .../no_revision_available/HellaSwag.json | 42 +++++ .../no_revision_available/PIQA.json | 42 +++++ .../no_revision_available/Quail.json | 42 +++++ .../no_revision_available/RARbCode.json | 42 +++++ .../no_revision_available/RARbMath.json | 42 +++++ .../no_revision_available/SIQA.json | 42 +++++ .../no_revision_available/SpartQA.json | 42 +++++ .../no_revision_available/TempReasonL1.json | 42 +++++ .../TempReasonL2Fact.json | 42 +++++ .../TempReasonL2Pure.json | 42 +++++ .../TempReasonL3Fact.json | 42 +++++ .../TempReasonL3Pure.json | 42 +++++ .../no_revision_available/WinoGrande.json | 42 +++++ .../ARCChallenge.json | 158 ++++++++++++++++++ .../AlphaNLI.json | 158 ++++++++++++++++++ .../HellaSwag.json | 158 ++++++++++++++++++ .../PIQA.json | 158 ++++++++++++++++++ .../Quail.json | 158 ++++++++++++++++++ .../RARbCode.json | 158 ++++++++++++++++++ .../RARbMath.json | 158 ++++++++++++++++++ .../SIQA.json | 158 ++++++++++++++++++ .../SpartQA.json | 158 ++++++++++++++++++ .../TempReasonL1.json | 158 ++++++++++++++++++ .../TempReasonL2Fact.json | 158 ++++++++++++++++++ .../TempReasonL2Pure.json | 158 ++++++++++++++++++ .../TempReasonL3Fact.json | 158 ++++++++++++++++++ .../TempReasonL3Pure.json | 158 ++++++++++++++++++ .../WinoGrande.json | 158 ++++++++++++++++++ .../model_meta.json | 1 + .../ARCChallenge.json | 158 ++++++++++++++++++ .../AlphaNLI.json | 158 ++++++++++++++++++ .../HellaSwag.json | 158 ++++++++++++++++++ .../PIQA.json | 158 ++++++++++++++++++ .../Quail.json | 158 ++++++++++++++++++ .../RARbCode.json | 158 ++++++++++++++++++ .../RARbMath.json | 158 ++++++++++++++++++ .../SIQA.json | 158 ++++++++++++++++++ .../SpartQA.json | 158 ++++++++++++++++++ .../TempReasonL1.json | 158 ++++++++++++++++++ .../TempReasonL2Fact.json | 158 ++++++++++++++++++ .../TempReasonL2Pure.json | 158 ++++++++++++++++++ .../TempReasonL3Fact.json | 158 ++++++++++++++++++ .../TempReasonL3Pure.json | 158 ++++++++++++++++++ .../WinoGrande.json | 158 ++++++++++++++++++ .../ARCChallenge.json | 158 ++++++++++++++++++ .../AlphaNLI.json | 158 ++++++++++++++++++ .../HellaSwag.json | 158 ++++++++++++++++++ .../PIQA.json | 158 ++++++++++++++++++ .../Quail.json | 158 ++++++++++++++++++ .../RARbCode.json | 158 ++++++++++++++++++ .../RARbMath.json | 158 ++++++++++++++++++ .../SIQA.json | 158 ++++++++++++++++++ .../SpartQA.json | 158 ++++++++++++++++++ .../TempReasonL1.json | 158 ++++++++++++++++++ .../TempReasonL2Fact.json | 158 ++++++++++++++++++ .../TempReasonL2Pure.json | 158 ++++++++++++++++++ .../TempReasonL3Fact.json | 158 ++++++++++++++++++ .../TempReasonL3Pure.json | 158 ++++++++++++++++++ .../WinoGrande.json | 158 ++++++++++++++++++ .../model_metaInstruct.json | 1 + .../ARCChallenge.json | 158 ++++++++++++++++++ .../AlphaNLI.json | 158 ++++++++++++++++++ .../HellaSwag.json | 158 ++++++++++++++++++ .../PIQA.json | 158 ++++++++++++++++++ .../Quail.json | 158 ++++++++++++++++++ .../RARbCode.json | 158 ++++++++++++++++++ .../RARbMath.json | 158 ++++++++++++++++++ .../SIQA.json | 158 ++++++++++++++++++ .../SpartQA.json | 158 ++++++++++++++++++ .../TempReasonL1.json | 158 ++++++++++++++++++ .../TempReasonL2Fact.json | 158 ++++++++++++++++++ .../TempReasonL2Pure.json | 158 ++++++++++++++++++ .../TempReasonL3Fact.json | 158 ++++++++++++++++++ .../TempReasonL3Pure.json | 158 ++++++++++++++++++ .../WinoGrande.json | 158 ++++++++++++++++++ .../ARCChallenge.json | 158 ++++++++++++++++++ .../AlphaNLI.json | 158 ++++++++++++++++++ .../HellaSwag.json | 158 ++++++++++++++++++ .../PIQA.json | 158 ++++++++++++++++++ .../Quail.json | 158 ++++++++++++++++++ .../RARbCode.json | 158 ++++++++++++++++++ .../RARbMath.json | 158 ++++++++++++++++++ .../SIQA.json | 158 ++++++++++++++++++ .../SpartQA.json | 158 ++++++++++++++++++ .../TempReasonL1.json | 158 ++++++++++++++++++ .../TempReasonL2Fact.json | 158 ++++++++++++++++++ .../TempReasonL2Pure.json | 158 ++++++++++++++++++ .../TempReasonL3Fact.json | 158 ++++++++++++++++++ .../TempReasonL3Pure.json | 158 ++++++++++++++++++ .../WinoGrande.json | 158 ++++++++++++++++++ .../ARCChallenge.json | 158 ++++++++++++++++++ .../AlphaNLI.json | 158 ++++++++++++++++++ .../HellaSwag.json | 158 ++++++++++++++++++ .../PIQA.json | 158 ++++++++++++++++++ .../Quail.json | 158 ++++++++++++++++++ .../RARbCode.json | 158 ++++++++++++++++++ .../RARbMath.json | 158 ++++++++++++++++++ .../SIQA.json | 158 ++++++++++++++++++ .../SpartQA.json | 158 ++++++++++++++++++ .../TempReasonL1.json | 158 ++++++++++++++++++ .../TempReasonL2Fact.json | 158 ++++++++++++++++++ .../TempReasonL2Pure.json | 158 ++++++++++++++++++ .../TempReasonL3Fact.json | 158 ++++++++++++++++++ .../TempReasonL3Pure.json | 158 ++++++++++++++++++ .../WinoGrande.json | 158 ++++++++++++++++++ .../ARCChallenge.json | 158 ++++++++++++++++++ .../AlphaNLI.json | 158 ++++++++++++++++++ .../HellaSwag.json | 158 ++++++++++++++++++ .../PIQA.json | 158 ++++++++++++++++++ .../Quail.json | 158 ++++++++++++++++++ .../RARbCode.json | 158 ++++++++++++++++++ .../RARbMath.json | 158 ++++++++++++++++++ .../SIQA.json | 158 ++++++++++++++++++ .../SpartQA.json | 158 ++++++++++++++++++ .../TempReasonL1.json | 158 ++++++++++++++++++ .../TempReasonL2Fact.json | 158 ++++++++++++++++++ .../TempReasonL2Pure.json | 158 ++++++++++++++++++ .../TempReasonL3Fact.json | 158 ++++++++++++++++++ .../TempReasonL3Pure.json | 158 ++++++++++++++++++ .../WinoGrande.json | 158 ++++++++++++++++++ .../model_metaInstruct.json | 1 + .../ARCChallengeInstruct.json | 158 ++++++++++++++++++ .../AlphaNLIInstruct.json | 158 ++++++++++++++++++ .../HellaSwagInstruct.json | 158 ++++++++++++++++++ .../PIQAInstruct.json | 158 ++++++++++++++++++ .../QuailInstruct.json | 158 ++++++++++++++++++ .../RARbCodeInstruct.json | 158 ++++++++++++++++++ .../RARbMathInstruct.json | 158 ++++++++++++++++++ .../SIQAInstruct.json | 158 ++++++++++++++++++ .../SpartQAInstruct.json | 158 ++++++++++++++++++ .../TempReasonL1Instruct.json | 158 ++++++++++++++++++ .../TempReasonL2FactInstruct.json | 158 ++++++++++++++++++ .../TempReasonL2PureInstruct.json | 158 ++++++++++++++++++ .../TempReasonL3FactInstruct.json | 158 ++++++++++++++++++ .../TempReasonL3PureInstruct.json | 158 ++++++++++++++++++ .../WinoGrandeInstruct.json | 158 ++++++++++++++++++ .../ARCChallenge.json | 158 ++++++++++++++++++ .../AlphaNLI.json | 158 ++++++++++++++++++ .../HellaSwag.json | 158 ++++++++++++++++++ .../PIQA.json | 158 ++++++++++++++++++ .../Quail.json | 158 ++++++++++++++++++ .../RARbCode.json | 158 ++++++++++++++++++ .../RARbMath.json | 158 ++++++++++++++++++ .../SIQA.json | 158 ++++++++++++++++++ .../SpartQA.json | 158 ++++++++++++++++++ .../TempReasonL1.json | 158 ++++++++++++++++++ .../TempReasonL2Fact.json | 158 ++++++++++++++++++ .../TempReasonL2Pure.json | 158 ++++++++++++++++++ .../TempReasonL3Fact.json | 158 ++++++++++++++++++ .../TempReasonL3Pure.json | 158 ++++++++++++++++++ .../WinoGrande.json | 158 ++++++++++++++++++ .../ARCChallenge.json | 158 ++++++++++++++++++ .../AlphaNLI.json | 158 ++++++++++++++++++ .../HellaSwag.json | 158 ++++++++++++++++++ .../PIQA.json | 158 ++++++++++++++++++ .../Quail.json | 158 ++++++++++++++++++ .../RARbCode.json | 158 ++++++++++++++++++ .../RARbMath.json | 158 ++++++++++++++++++ .../SIQA.json | 158 ++++++++++++++++++ .../SpartQA.json | 158 ++++++++++++++++++ .../TempReasonL1.json | 158 ++++++++++++++++++ .../TempReasonL2Fact.json | 158 ++++++++++++++++++ .../TempReasonL2Pure.json | 158 ++++++++++++++++++ .../TempReasonL3Fact.json | 158 ++++++++++++++++++ .../TempReasonL3Pure.json | 158 ++++++++++++++++++ .../WinoGrande.json | 158 ++++++++++++++++++ .../ARCChallenge.json | 158 ++++++++++++++++++ .../AlphaNLI.json | 158 ++++++++++++++++++ .../HellaSwag.json | 158 ++++++++++++++++++ .../PIQA.json | 158 ++++++++++++++++++ .../Quail.json | 158 ++++++++++++++++++ .../RARbCode.json | 158 ++++++++++++++++++ .../RARbMath.json | 158 ++++++++++++++++++ .../SIQA.json | 158 ++++++++++++++++++ .../SpartQA.json | 158 ++++++++++++++++++ .../TempReasonL1.json | 158 ++++++++++++++++++ .../TempReasonL2Fact.json | 158 ++++++++++++++++++ .../TempReasonL2Pure.json | 158 ++++++++++++++++++ .../TempReasonL3Fact.json | 158 ++++++++++++++++++ .../TempReasonL3Pure.json | 158 ++++++++++++++++++ .../WinoGrande.json | 158 ++++++++++++++++++ .../ARCChallenge.json | 158 ++++++++++++++++++ .../AlphaNLI.json | 158 ++++++++++++++++++ .../PIQA.json | 158 ++++++++++++++++++ .../Quail.json | 158 ++++++++++++++++++ .../RARbCode.json | 158 ++++++++++++++++++ .../RARbMath.json | 158 ++++++++++++++++++ .../SIQA.json | 158 ++++++++++++++++++ .../SpartQA.json | 158 ++++++++++++++++++ .../TempReasonL1.json | 158 ++++++++++++++++++ .../TempReasonL2Fact.json | 158 ++++++++++++++++++ .../TempReasonL2Pure.json | 158 ++++++++++++++++++ .../TempReasonL3Fact.json | 158 ++++++++++++++++++ .../TempReasonL3Pure.json | 158 ++++++++++++++++++ .../WinoGrande.json | 158 ++++++++++++++++++ .../ARCChallenge.json | 158 ++++++++++++++++++ .../AlphaNLI.json | 158 ++++++++++++++++++ .../HellaSwag.json | 158 ++++++++++++++++++ .../HellaSwagInstruct.json | 158 ++++++++++++++++++ .../PIQA.json | 158 ++++++++++++++++++ .../Quail.json | 158 ++++++++++++++++++ .../RARbCode.json | 158 ++++++++++++++++++ .../RARbMath.json | 158 ++++++++++++++++++ .../SIQA.json | 158 ++++++++++++++++++ .../SpartQA.json | 158 ++++++++++++++++++ .../TempReasonL1.json | 158 ++++++++++++++++++ .../TempReasonL2Fact.json | 158 ++++++++++++++++++ .../TempReasonL2Pure.json | 158 ++++++++++++++++++ .../TempReasonL3Fact.json | 158 ++++++++++++++++++ .../TempReasonL3Pure.json | 158 ++++++++++++++++++ .../WinoGrande.json | 158 ++++++++++++++++++ .../no_revision_available/ARCChallenge.json | 158 ++++++++++++++++++ .../no_revision_available/AlphaNLI.json | 158 ++++++++++++++++++ .../no_revision_available/HellaSwag.json | 158 ++++++++++++++++++ .../no_revision_available/PIQA.json | 158 ++++++++++++++++++ .../no_revision_available/Quail.json | 158 ++++++++++++++++++ .../no_revision_available/RARbCode.json | 158 ++++++++++++++++++ .../no_revision_available/RARbMath.json | 158 ++++++++++++++++++ .../no_revision_available/SIQA.json | 158 ++++++++++++++++++ .../no_revision_available/SpartQA.json | 158 ++++++++++++++++++ .../no_revision_available/TempReasonL1.json | 158 ++++++++++++++++++ .../TempReasonL2Fact.json | 158 ++++++++++++++++++ .../TempReasonL2Pure.json | 158 ++++++++++++++++++ .../TempReasonL3Fact.json | 158 ++++++++++++++++++ .../TempReasonL3Pure.json | 158 ++++++++++++++++++ .../no_revision_available/WinoGrande.json | 158 ++++++++++++++++++ .../no_revision_available/ARCChallenge.json | 158 ++++++++++++++++++ .../no_revision_available/AlphaNLI.json | 158 ++++++++++++++++++ .../no_revision_available/HellaSwag.json | 158 ++++++++++++++++++ .../no_revision_available/PIQA.json | 158 ++++++++++++++++++ .../no_revision_available/Quail.json | 158 ++++++++++++++++++ .../no_revision_available/RARbCode.json | 158 ++++++++++++++++++ .../no_revision_available/RARbMath.json | 158 ++++++++++++++++++ .../no_revision_available/SIQA.json | 158 ++++++++++++++++++ .../no_revision_available/SpartQA.json | 158 ++++++++++++++++++ .../no_revision_available/TempReasonL1.json | 158 ++++++++++++++++++ .../TempReasonL2Fact.json | 158 ++++++++++++++++++ .../TempReasonL2Pure.json | 158 ++++++++++++++++++ .../TempReasonL3Fact.json | 158 ++++++++++++++++++ .../TempReasonL3Pure.json | 158 ++++++++++++++++++ .../no_revision_available/WinoGrande.json | 158 ++++++++++++++++++ .../ARCChallenge.json | 158 ++++++++++++++++++ .../AlphaNLI.json | 158 ++++++++++++++++++ .../HellaSwag.json | 158 ++++++++++++++++++ .../PIQA.json | 158 ++++++++++++++++++ .../Quail.json | 158 ++++++++++++++++++ .../RARbCode.json | 158 ++++++++++++++++++ .../RARbMath.json | 158 ++++++++++++++++++ .../SIQA.json | 158 ++++++++++++++++++ .../SpartQA.json | 158 ++++++++++++++++++ .../TempReasonL1.json | 158 ++++++++++++++++++ .../TempReasonL2Fact.json | 158 ++++++++++++++++++ .../TempReasonL2Pure.json | 158 ++++++++++++++++++ .../TempReasonL3Fact.json | 158 ++++++++++++++++++ .../TempReasonL3Pure.json | 158 ++++++++++++++++++ .../WinoGrande.json | 158 ++++++++++++++++++ .../ARCChallenge.json | 158 ++++++++++++++++++ .../AlphaNLI.json | 158 ++++++++++++++++++ .../HellaSwag.json | 158 ++++++++++++++++++ .../PIQA.json | 158 ++++++++++++++++++ .../Quail.json | 158 ++++++++++++++++++ .../RARbCode.json | 158 ++++++++++++++++++ .../RARbMath.json | 158 ++++++++++++++++++ .../SIQA.json | 158 ++++++++++++++++++ .../SpartQA.json | 158 ++++++++++++++++++ .../TempReasonL1.json | 158 ++++++++++++++++++ .../TempReasonL2Fact.json | 158 ++++++++++++++++++ .../TempReasonL2Pure.json | 158 ++++++++++++++++++ .../TempReasonL3Fact.json | 158 ++++++++++++++++++ .../TempReasonL3Pure.json | 158 ++++++++++++++++++ .../WinoGrande.json | 158 ++++++++++++++++++ .../no_revision_available/ARCChallenge.json | 42 +++++ .../no_revision_available/AlphaNLI.json | 42 +++++ .../no_revision_available/HellaSwag.json | 42 +++++ .../no_revision_available/PIQA.json | 42 +++++ .../no_revision_available/Quail.json | 42 +++++ .../no_revision_available/RARbCode.json | 42 +++++ .../no_revision_available/RARbMath.json | 42 +++++ .../no_revision_available/SIQA.json | 42 +++++ .../no_revision_available/SpartQA.json | 42 +++++ .../no_revision_available/TempReasonL1.json | 42 +++++ .../TempReasonL2Fact.json | 42 +++++ .../TempReasonL2Pure.json | 42 +++++ .../TempReasonL3Fact.json | 42 +++++ .../TempReasonL3Pure.json | 42 +++++ .../no_revision_available/WinoGrande.json | 42 +++++ .../no_revision_available/ARCChallenge.json | 42 +++++ .../no_revision_available/AlphaNLI.json | 42 +++++ .../no_revision_available/HellaSwag.json | 42 +++++ .../no_revision_available/PIQA.json | 42 +++++ .../no_revision_available/Quail.json | 42 +++++ .../no_revision_available/RARbCode.json | 42 +++++ .../no_revision_available/RARbMath.json | 42 +++++ .../no_revision_available/SIQA.json | 42 +++++ .../no_revision_available/SpartQA.json | 42 +++++ .../no_revision_available/TempReasonL1.json | 42 +++++ .../TempReasonL2Fact.json | 42 +++++ .../TempReasonL2Pure.json | 42 +++++ .../TempReasonL3Fact.json | 42 +++++ .../TempReasonL3Pure.json | 42 +++++ .../no_revision_available/WinoGrande.json | 42 +++++ .../no_revision_available/ARCChallenge.json | 42 +++++ .../no_revision_available/AlphaNLI.json | 42 +++++ .../no_revision_available/HellaSwag.json | 42 +++++ .../no_revision_available/PIQA.json | 42 +++++ .../no_revision_available/Quail.json | 42 +++++ .../no_revision_available/RARbCode.json | 42 +++++ .../no_revision_available/RARbMath.json | 42 +++++ .../no_revision_available/SIQA.json | 42 +++++ .../no_revision_available/SpartQA.json | 42 +++++ .../no_revision_available/TempReasonL1.json | 42 +++++ .../TempReasonL2Fact.json | 42 +++++ .../TempReasonL2Pure.json | 42 +++++ .../TempReasonL3Fact.json | 42 +++++ .../TempReasonL3Pure.json | 42 +++++ .../no_revision_available/WinoGrande.json | 42 +++++ .../no_revision_available/ARCChallenge.json | 42 +++++ .../no_revision_available/AlphaNLI.json | 42 +++++ .../no_revision_available/HellaSwag.json | 42 +++++ .../no_revision_available/PIQA.json | 42 +++++ .../no_revision_available/Quail.json | 42 +++++ .../no_revision_available/RARbCode.json | 42 +++++ .../no_revision_available/RARbMath.json | 42 +++++ .../no_revision_available/SIQA.json | 42 +++++ .../no_revision_available/SpartQA.json | 42 +++++ .../no_revision_available/TempReasonL1.json | 42 +++++ .../TempReasonL2Fact.json | 42 +++++ .../TempReasonL2Pure.json | 42 +++++ .../TempReasonL3Fact.json | 42 +++++ .../TempReasonL3Pure.json | 42 +++++ .../no_revision_available/WinoGrande.json | 42 +++++ .../no_revision_available/ARCChallenge.json | 42 +++++ .../no_revision_available/AlphaNLI.json | 42 +++++ .../no_revision_available/HellaSwag.json | 42 +++++ .../no_revision_available/PIQA.json | 42 +++++ .../no_revision_available/Quail.json | 42 +++++ .../no_revision_available/RARbCode.json | 42 +++++ .../no_revision_available/RARbMath.json | 42 +++++ .../no_revision_available/SIQA.json | 42 +++++ .../no_revision_available/SpartQA.json | 42 +++++ .../no_revision_available/TempReasonL1.json | 42 +++++ .../TempReasonL2Fact.json | 42 +++++ .../TempReasonL2Pure.json | 42 +++++ .../TempReasonL3Fact.json | 42 +++++ .../TempReasonL3Pure.json | 42 +++++ .../no_revision_available/WinoGrande.json | 42 +++++ .../no_revision_available/ARCChallenge.json | 42 +++++ .../no_revision_available/AlphaNLI.json | 42 +++++ .../no_revision_available/HellaSwag.json | 42 +++++ .../no_revision_available/PIQA.json | 42 +++++ .../no_revision_available/Quail.json | 42 +++++ .../no_revision_available/RARbCode.json | 42 +++++ .../no_revision_available/RARbMath.json | 42 +++++ .../no_revision_available/SIQA.json | 42 +++++ .../no_revision_available/SpartQA.json | 42 +++++ .../no_revision_available/TempReasonL1.json | 42 +++++ .../TempReasonL2Fact.json | 42 +++++ .../TempReasonL2Pure.json | 42 +++++ .../TempReasonL3Fact.json | 42 +++++ .../TempReasonL3Pure.json | 42 +++++ .../no_revision_available/WinoGrande.json | 42 +++++ 378 files changed, 45333 insertions(+) create mode 100644 results/Cohere-embed-english-v3.0-instruct/no_revision_available/ARCChallenge.json create mode 100644 results/Cohere-embed-english-v3.0-instruct/no_revision_available/AlphaNLI.json create mode 100644 results/Cohere-embed-english-v3.0-instruct/no_revision_available/HellaSwag.json create mode 100644 results/Cohere-embed-english-v3.0-instruct/no_revision_available/PIQA.json create mode 100644 results/Cohere-embed-english-v3.0-instruct/no_revision_available/Quail.json create mode 100644 results/Cohere-embed-english-v3.0-instruct/no_revision_available/RARbCode.json create mode 100644 results/Cohere-embed-english-v3.0-instruct/no_revision_available/RARbMath.json create mode 100644 results/Cohere-embed-english-v3.0-instruct/no_revision_available/SIQA.json create mode 100644 results/Cohere-embed-english-v3.0-instruct/no_revision_available/SpartQA.json create mode 100644 results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL1.json create mode 100644 results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL2Fact.json create mode 100644 results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL2Pure.json create mode 100644 results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL3Fact.json create mode 100644 results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL3Pure.json create mode 100644 results/Cohere-embed-english-v3.0-instruct/no_revision_available/WinoGrande.json create mode 100644 results/Cohere-embed-english-v3.0/no_revision_available/ARCChallenge.json create mode 100644 results/Cohere-embed-english-v3.0/no_revision_available/AlphaNLI.json create mode 100644 results/Cohere-embed-english-v3.0/no_revision_available/HellaSwag.json create mode 100644 results/Cohere-embed-english-v3.0/no_revision_available/PIQA.json create mode 100644 results/Cohere-embed-english-v3.0/no_revision_available/Quail.json create mode 100644 results/Cohere-embed-english-v3.0/no_revision_available/RARbCode.json create mode 100644 results/Cohere-embed-english-v3.0/no_revision_available/RARbMath.json create mode 100644 results/Cohere-embed-english-v3.0/no_revision_available/SIQA.json create mode 100644 results/Cohere-embed-english-v3.0/no_revision_available/SpartQA.json create mode 100644 results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL1.json create mode 100644 results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL2Fact.json create mode 100644 results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL2Pure.json create mode 100644 results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL3Fact.json create mode 100644 results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL3Pure.json create mode 100644 results/Cohere-embed-english-v3.0/no_revision_available/WinoGrande.json create mode 100644 results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/ARCChallenge.json create mode 100644 results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/AlphaNLI.json create mode 100644 results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/HellaSwag.json create mode 100644 results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/PIQA.json create mode 100644 results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/Quail.json create mode 100644 results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/RARbCode.json create mode 100644 results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/RARbMath.json create mode 100644 results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/SIQA.json create mode 100644 results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/SpartQA.json create mode 100644 results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL1.json create mode 100644 results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL2Fact.json create mode 100644 results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL2Pure.json create mode 100644 results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL3Fact.json create mode 100644 results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL3Pure.json create mode 100644 results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/WinoGrande.json create mode 100644 results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/model_meta.json create mode 100644 results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/ARCChallenge.json create mode 100644 results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/AlphaNLI.json create mode 100644 results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/HellaSwag.json create mode 100644 results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/PIQA.json create mode 100644 results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/Quail.json create mode 100644 results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/RARbCode.json create mode 100644 results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/RARbMath.json create mode 100644 results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/SIQA.json create mode 100644 results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/SpartQA.json create mode 100644 results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL1.json create mode 100644 results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL2Fact.json create mode 100644 results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL2Pure.json create mode 100644 results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL3Fact.json create mode 100644 results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL3Pure.json create mode 100644 results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/WinoGrande.json create mode 100644 results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/ARCChallenge.json create mode 100644 results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/AlphaNLI.json create mode 100644 results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/HellaSwag.json create mode 100644 results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/PIQA.json create mode 100644 results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/Quail.json create mode 100644 results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/RARbCode.json create mode 100644 results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/RARbMath.json create mode 100644 results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/SIQA.json create mode 100644 results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/SpartQA.json create mode 100644 results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL1.json create mode 100644 results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL2Fact.json create mode 100644 results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL2Pure.json create mode 100644 results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL3Fact.json create mode 100644 results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL3Pure.json create mode 100644 results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/WinoGrande.json create mode 100644 results/all-mpnet-base-v2/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/model_metaInstruct.json create mode 100644 results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/ARCChallenge.json create mode 100644 results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/AlphaNLI.json create mode 100644 results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/HellaSwag.json create mode 100644 results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/PIQA.json create mode 100644 results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/Quail.json create mode 100644 results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/RARbCode.json create mode 100644 results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/RARbMath.json create mode 100644 results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/SIQA.json create mode 100644 results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/SpartQA.json create mode 100644 results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL1.json create mode 100644 results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL2Fact.json create mode 100644 results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL2Pure.json create mode 100644 results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL3Fact.json create mode 100644 results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL3Pure.json create mode 100644 results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/WinoGrande.json create mode 100644 results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/ARCChallenge.json create mode 100644 results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/AlphaNLI.json create mode 100644 results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/HellaSwag.json create mode 100644 results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/PIQA.json create mode 100644 results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/Quail.json create mode 100644 results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/RARbCode.json create mode 100644 results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/RARbMath.json create mode 100644 results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/SIQA.json create mode 100644 results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/SpartQA.json create mode 100644 results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL1.json create mode 100644 results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL2Fact.json create mode 100644 results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL2Pure.json create mode 100644 results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL3Fact.json create mode 100644 results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL3Pure.json create mode 100644 results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/WinoGrande.json create mode 100644 results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/ARCChallenge.json create mode 100644 results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/AlphaNLI.json create mode 100644 results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/HellaSwag.json create mode 100644 results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/PIQA.json create mode 100644 results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/Quail.json create mode 100644 results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/RARbCode.json create mode 100644 results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/RARbMath.json create mode 100644 results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/SIQA.json create mode 100644 results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/SpartQA.json create mode 100644 results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL1.json create mode 100644 results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL2Fact.json create mode 100644 results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL2Pure.json create mode 100644 results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL3Fact.json create mode 100644 results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL3Pure.json create mode 100644 results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/WinoGrande.json create mode 100644 results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/ARCChallenge.json create mode 100644 results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/AlphaNLI.json create mode 100644 results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/HellaSwag.json create mode 100644 results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/PIQA.json create mode 100644 results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/Quail.json create mode 100644 results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/RARbCode.json create mode 100644 results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/RARbMath.json create mode 100644 results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/SIQA.json create mode 100644 results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/SpartQA.json create mode 100644 results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL1.json create mode 100644 results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL2Fact.json create mode 100644 results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL2Pure.json create mode 100644 results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL3Fact.json create mode 100644 results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL3Pure.json create mode 100644 results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/WinoGrande.json create mode 100644 results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/model_metaInstruct.json create mode 100644 results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/ARCChallengeInstruct.json create mode 100644 results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/AlphaNLIInstruct.json create mode 100644 results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/HellaSwagInstruct.json create mode 100644 results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/PIQAInstruct.json create mode 100644 results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/QuailInstruct.json create mode 100644 results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/RARbCodeInstruct.json create mode 100644 results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/RARbMathInstruct.json create mode 100644 results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/SIQAInstruct.json create mode 100644 results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/SpartQAInstruct.json create mode 100644 results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL1Instruct.json create mode 100644 results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL2FactInstruct.json create mode 100644 results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL2PureInstruct.json create mode 100644 results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL3FactInstruct.json create mode 100644 results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL3PureInstruct.json create mode 100644 results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/WinoGrandeInstruct.json create mode 100644 results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/ARCChallenge.json create mode 100644 results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/AlphaNLI.json create mode 100644 results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/HellaSwag.json create mode 100644 results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/PIQA.json create mode 100644 results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/Quail.json create mode 100644 results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/RARbCode.json create mode 100644 results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/RARbMath.json create mode 100644 results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/SIQA.json create mode 100644 results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/SpartQA.json create mode 100644 results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL1.json create mode 100644 results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL2Fact.json create mode 100644 results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL2Pure.json create mode 100644 results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL3Fact.json create mode 100644 results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL3Pure.json create mode 100644 results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/WinoGrande.json create mode 100644 results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/ARCChallenge.json create mode 100644 results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/AlphaNLI.json create mode 100644 results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/HellaSwag.json create mode 100644 results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/PIQA.json create mode 100644 results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/Quail.json create mode 100644 results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/RARbCode.json create mode 100644 results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/RARbMath.json create mode 100644 results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/SIQA.json create mode 100644 results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/SpartQA.json create mode 100644 results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL1.json create mode 100644 results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL2Fact.json create mode 100644 results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL2Pure.json create mode 100644 results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL3Fact.json create mode 100644 results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL3Pure.json create mode 100644 results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/WinoGrande.json create mode 100644 results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/ARCChallenge.json create mode 100644 results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/AlphaNLI.json create mode 100644 results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/HellaSwag.json create mode 100644 results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/PIQA.json create mode 100644 results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/Quail.json create mode 100644 results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/RARbCode.json create mode 100644 results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/RARbMath.json create mode 100644 results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/SIQA.json create mode 100644 results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/SpartQA.json create mode 100644 results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL1.json create mode 100644 results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL2Fact.json create mode 100644 results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL2Pure.json create mode 100644 results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL3Fact.json create mode 100644 results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL3Pure.json create mode 100644 results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/WinoGrande.json create mode 100644 results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/ARCChallenge.json create mode 100644 results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/AlphaNLI.json create mode 100644 results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/PIQA.json create mode 100644 results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/Quail.json create mode 100644 results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/RARbCode.json create mode 100644 results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/RARbMath.json create mode 100644 results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/SIQA.json create mode 100644 results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/SpartQA.json create mode 100644 results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL1.json create mode 100644 results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL2Fact.json create mode 100644 results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL2Pure.json create mode 100644 results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL3Fact.json create mode 100644 results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL3Pure.json create mode 100644 results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/WinoGrande.json create mode 100644 results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/ARCChallenge.json create mode 100644 results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/AlphaNLI.json create mode 100644 results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/HellaSwag.json create mode 100644 results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/HellaSwagInstruct.json create mode 100644 results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/PIQA.json create mode 100644 results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/Quail.json create mode 100644 results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/RARbCode.json create mode 100644 results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/RARbMath.json create mode 100644 results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/SIQA.json create mode 100644 results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/SpartQA.json create mode 100644 results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL1.json create mode 100644 results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL2Fact.json create mode 100644 results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL2Pure.json create mode 100644 results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL3Fact.json create mode 100644 results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL3Pure.json create mode 100644 results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/WinoGrande.json create mode 100644 results/dragon-plus-instruct/no_revision_available/ARCChallenge.json create mode 100644 results/dragon-plus-instruct/no_revision_available/AlphaNLI.json create mode 100644 results/dragon-plus-instruct/no_revision_available/HellaSwag.json create mode 100644 results/dragon-plus-instruct/no_revision_available/PIQA.json create mode 100644 results/dragon-plus-instruct/no_revision_available/Quail.json create mode 100644 results/dragon-plus-instruct/no_revision_available/RARbCode.json create mode 100644 results/dragon-plus-instruct/no_revision_available/RARbMath.json create mode 100644 results/dragon-plus-instruct/no_revision_available/SIQA.json create mode 100644 results/dragon-plus-instruct/no_revision_available/SpartQA.json create mode 100644 results/dragon-plus-instruct/no_revision_available/TempReasonL1.json create mode 100644 results/dragon-plus-instruct/no_revision_available/TempReasonL2Fact.json create mode 100644 results/dragon-plus-instruct/no_revision_available/TempReasonL2Pure.json create mode 100644 results/dragon-plus-instruct/no_revision_available/TempReasonL3Fact.json create mode 100644 results/dragon-plus-instruct/no_revision_available/TempReasonL3Pure.json create mode 100644 results/dragon-plus-instruct/no_revision_available/WinoGrande.json create mode 100644 results/dragon-plus/no_revision_available/ARCChallenge.json create mode 100644 results/dragon-plus/no_revision_available/AlphaNLI.json create mode 100644 results/dragon-plus/no_revision_available/HellaSwag.json create mode 100644 results/dragon-plus/no_revision_available/PIQA.json create mode 100644 results/dragon-plus/no_revision_available/Quail.json create mode 100644 results/dragon-plus/no_revision_available/RARbCode.json create mode 100644 results/dragon-plus/no_revision_available/RARbMath.json create mode 100644 results/dragon-plus/no_revision_available/SIQA.json create mode 100644 results/dragon-plus/no_revision_available/SpartQA.json create mode 100644 results/dragon-plus/no_revision_available/TempReasonL1.json create mode 100644 results/dragon-plus/no_revision_available/TempReasonL2Fact.json create mode 100644 results/dragon-plus/no_revision_available/TempReasonL2Pure.json create mode 100644 results/dragon-plus/no_revision_available/TempReasonL3Fact.json create mode 100644 results/dragon-plus/no_revision_available/TempReasonL3Pure.json create mode 100644 results/dragon-plus/no_revision_available/WinoGrande.json create mode 100644 results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/ARCChallenge.json create mode 100644 results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/AlphaNLI.json create mode 100644 results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/HellaSwag.json create mode 100644 results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/PIQA.json create mode 100644 results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/Quail.json create mode 100644 results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/RARbCode.json create mode 100644 results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/RARbMath.json create mode 100644 results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/SIQA.json create mode 100644 results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/SpartQA.json create mode 100644 results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL1.json create mode 100644 results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL2Fact.json create mode 100644 results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL2Pure.json create mode 100644 results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL3Fact.json create mode 100644 results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL3Pure.json create mode 100644 results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/WinoGrande.json create mode 100644 results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/ARCChallenge.json create mode 100644 results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/AlphaNLI.json create mode 100644 results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/HellaSwag.json create mode 100644 results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/PIQA.json create mode 100644 results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/Quail.json create mode 100644 results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/RARbCode.json create mode 100644 results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/RARbMath.json create mode 100644 results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/SIQA.json create mode 100644 results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/SpartQA.json create mode 100644 results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL1.json create mode 100644 results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL2Fact.json create mode 100644 results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL2Pure.json create mode 100644 results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL3Fact.json create mode 100644 results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL3Pure.json create mode 100644 results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/WinoGrande.json create mode 100644 results/text-embedding-3-large-instruct/no_revision_available/ARCChallenge.json create mode 100644 results/text-embedding-3-large-instruct/no_revision_available/AlphaNLI.json create mode 100644 results/text-embedding-3-large-instruct/no_revision_available/HellaSwag.json create mode 100644 results/text-embedding-3-large-instruct/no_revision_available/PIQA.json create mode 100644 results/text-embedding-3-large-instruct/no_revision_available/Quail.json create mode 100644 results/text-embedding-3-large-instruct/no_revision_available/RARbCode.json create mode 100644 results/text-embedding-3-large-instruct/no_revision_available/RARbMath.json create mode 100644 results/text-embedding-3-large-instruct/no_revision_available/SIQA.json create mode 100644 results/text-embedding-3-large-instruct/no_revision_available/SpartQA.json create mode 100644 results/text-embedding-3-large-instruct/no_revision_available/TempReasonL1.json create mode 100644 results/text-embedding-3-large-instruct/no_revision_available/TempReasonL2Fact.json create mode 100644 results/text-embedding-3-large-instruct/no_revision_available/TempReasonL2Pure.json create mode 100644 results/text-embedding-3-large-instruct/no_revision_available/TempReasonL3Fact.json create mode 100644 results/text-embedding-3-large-instruct/no_revision_available/TempReasonL3Pure.json create mode 100644 results/text-embedding-3-large-instruct/no_revision_available/WinoGrande.json create mode 100644 results/text-embedding-3-large/no_revision_available/ARCChallenge.json create mode 100644 results/text-embedding-3-large/no_revision_available/AlphaNLI.json create mode 100644 results/text-embedding-3-large/no_revision_available/HellaSwag.json create mode 100644 results/text-embedding-3-large/no_revision_available/PIQA.json create mode 100644 results/text-embedding-3-large/no_revision_available/Quail.json create mode 100644 results/text-embedding-3-large/no_revision_available/RARbCode.json create mode 100644 results/text-embedding-3-large/no_revision_available/RARbMath.json create mode 100644 results/text-embedding-3-large/no_revision_available/SIQA.json create mode 100644 results/text-embedding-3-large/no_revision_available/SpartQA.json create mode 100644 results/text-embedding-3-large/no_revision_available/TempReasonL1.json create mode 100644 results/text-embedding-3-large/no_revision_available/TempReasonL2Fact.json create mode 100644 results/text-embedding-3-large/no_revision_available/TempReasonL2Pure.json create mode 100644 results/text-embedding-3-large/no_revision_available/TempReasonL3Fact.json create mode 100644 results/text-embedding-3-large/no_revision_available/TempReasonL3Pure.json create mode 100644 results/text-embedding-3-large/no_revision_available/WinoGrande.json create mode 100644 results/text-embedding-3-small-instruct/no_revision_available/ARCChallenge.json create mode 100644 results/text-embedding-3-small-instruct/no_revision_available/AlphaNLI.json create mode 100644 results/text-embedding-3-small-instruct/no_revision_available/HellaSwag.json create mode 100644 results/text-embedding-3-small-instruct/no_revision_available/PIQA.json create mode 100644 results/text-embedding-3-small-instruct/no_revision_available/Quail.json create mode 100644 results/text-embedding-3-small-instruct/no_revision_available/RARbCode.json create mode 100644 results/text-embedding-3-small-instruct/no_revision_available/RARbMath.json create mode 100644 results/text-embedding-3-small-instruct/no_revision_available/SIQA.json create mode 100644 results/text-embedding-3-small-instruct/no_revision_available/SpartQA.json create mode 100644 results/text-embedding-3-small-instruct/no_revision_available/TempReasonL1.json create mode 100644 results/text-embedding-3-small-instruct/no_revision_available/TempReasonL2Fact.json create mode 100644 results/text-embedding-3-small-instruct/no_revision_available/TempReasonL2Pure.json create mode 100644 results/text-embedding-3-small-instruct/no_revision_available/TempReasonL3Fact.json create mode 100644 results/text-embedding-3-small-instruct/no_revision_available/TempReasonL3Pure.json create mode 100644 results/text-embedding-3-small-instruct/no_revision_available/WinoGrande.json create mode 100644 results/text-embedding-3-small/no_revision_available/ARCChallenge.json create mode 100644 results/text-embedding-3-small/no_revision_available/AlphaNLI.json create mode 100644 results/text-embedding-3-small/no_revision_available/HellaSwag.json create mode 100644 results/text-embedding-3-small/no_revision_available/PIQA.json create mode 100644 results/text-embedding-3-small/no_revision_available/Quail.json create mode 100644 results/text-embedding-3-small/no_revision_available/RARbCode.json create mode 100644 results/text-embedding-3-small/no_revision_available/RARbMath.json create mode 100644 results/text-embedding-3-small/no_revision_available/SIQA.json create mode 100644 results/text-embedding-3-small/no_revision_available/SpartQA.json create mode 100644 results/text-embedding-3-small/no_revision_available/TempReasonL1.json create mode 100644 results/text-embedding-3-small/no_revision_available/TempReasonL2Fact.json create mode 100644 results/text-embedding-3-small/no_revision_available/TempReasonL2Pure.json create mode 100644 results/text-embedding-3-small/no_revision_available/TempReasonL3Fact.json create mode 100644 results/text-embedding-3-small/no_revision_available/TempReasonL3Pure.json create mode 100644 results/text-embedding-3-small/no_revision_available/WinoGrande.json create mode 100644 results/text-embedding-ada-002-instruct/no_revision_available/ARCChallenge.json create mode 100644 results/text-embedding-ada-002-instruct/no_revision_available/AlphaNLI.json create mode 100644 results/text-embedding-ada-002-instruct/no_revision_available/HellaSwag.json create mode 100644 results/text-embedding-ada-002-instruct/no_revision_available/PIQA.json create mode 100644 results/text-embedding-ada-002-instruct/no_revision_available/Quail.json create mode 100644 results/text-embedding-ada-002-instruct/no_revision_available/RARbCode.json create mode 100644 results/text-embedding-ada-002-instruct/no_revision_available/RARbMath.json create mode 100644 results/text-embedding-ada-002-instruct/no_revision_available/SIQA.json create mode 100644 results/text-embedding-ada-002-instruct/no_revision_available/SpartQA.json create mode 100644 results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL1.json create mode 100644 results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL2Fact.json create mode 100644 results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL2Pure.json create mode 100644 results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL3Fact.json create mode 100644 results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL3Pure.json create mode 100644 results/text-embedding-ada-002-instruct/no_revision_available/WinoGrande.json create mode 100644 results/text-embedding-ada-002/no_revision_available/ARCChallenge.json create mode 100644 results/text-embedding-ada-002/no_revision_available/AlphaNLI.json create mode 100644 results/text-embedding-ada-002/no_revision_available/HellaSwag.json create mode 100644 results/text-embedding-ada-002/no_revision_available/PIQA.json create mode 100644 results/text-embedding-ada-002/no_revision_available/Quail.json create mode 100644 results/text-embedding-ada-002/no_revision_available/RARbCode.json create mode 100644 results/text-embedding-ada-002/no_revision_available/RARbMath.json create mode 100644 results/text-embedding-ada-002/no_revision_available/SIQA.json create mode 100644 results/text-embedding-ada-002/no_revision_available/SpartQA.json create mode 100644 results/text-embedding-ada-002/no_revision_available/TempReasonL1.json create mode 100644 results/text-embedding-ada-002/no_revision_available/TempReasonL2Fact.json create mode 100644 results/text-embedding-ada-002/no_revision_available/TempReasonL2Pure.json create mode 100644 results/text-embedding-ada-002/no_revision_available/TempReasonL3Fact.json create mode 100644 results/text-embedding-ada-002/no_revision_available/TempReasonL3Pure.json create mode 100644 results/text-embedding-ada-002/no_revision_available/WinoGrande.json diff --git a/results/Cohere-embed-english-v3.0-instruct/no_revision_available/ARCChallenge.json b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/ARCChallenge.json new file mode 100644 index 000000000..b336dc598 --- /dev/null +++ b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/ARCChallenge.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.10099, + "ndcg_at_1": 0.03413, + "ndcg_at_3": 0.07297, + "ndcg_at_5": 0.08373, + "ndcg_at_10": 0.10099, + "ndcg_at_100": 0.1587, + "ndcg_at_1000": 0.20125, + "map_at_1": 0.03413, + "map_at_3": 0.06314, + "map_at_5": 0.06903, + "map_at_10": 0.07608, + "map_at_100": 0.08626, + "map_at_1000": 0.08762, + "recall_at_1": 0.03413, + "recall_at_3": 0.10154, + "recall_at_5": 0.12799, + "recall_at_10": 0.18174, + "recall_at_100": 0.47014, + "recall_at_1000": 0.81911, + "precision_at_1": 0.03413, + "precision_at_3": 0.03385, + "precision_at_5": 0.0256, + "precision_at_10": 0.01817, + "precision_at_100": 0.0047, + "precision_at_1000": 0.00082 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0-instruct/no_revision_available/AlphaNLI.json b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/AlphaNLI.json new file mode 100644 index 000000000..875c63502 --- /dev/null +++ b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/AlphaNLI.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.18746, + "ndcg_at_1": 0.11227, + "ndcg_at_3": 0.15844, + "ndcg_at_5": 0.17072, + "ndcg_at_10": 0.18746, + "ndcg_at_100": 0.22967, + "ndcg_at_1000": 0.25717, + "map_at_1": 0.11227, + "map_at_3": 0.1473, + "map_at_5": 0.15406, + "map_at_10": 0.161, + "map_at_100": 0.16853, + "map_at_1000": 0.16943, + "recall_at_1": 0.11227, + "recall_at_3": 0.1906, + "recall_at_5": 0.22063, + "recall_at_10": 0.27219, + "recall_at_100": 0.48238, + "recall_at_1000": 0.70692, + "precision_at_1": 0.11227, + "precision_at_3": 0.06353, + "precision_at_5": 0.04413, + "precision_at_10": 0.02722, + "precision_at_100": 0.00482, + "precision_at_1000": 0.00071 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0-instruct/no_revision_available/HellaSwag.json b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/HellaSwag.json new file mode 100644 index 000000000..6e31dc14b --- /dev/null +++ b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/HellaSwag.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.29021, + "ndcg_at_1": 0.15475, + "ndcg_at_3": 0.23843, + "ndcg_at_5": 0.26644, + "ndcg_at_10": 0.29021, + "ndcg_at_100": 0.33659, + "ndcg_at_1000": 0.36032, + "map_at_1": 0.15475, + "map_at_3": 0.21744, + "map_at_5": 0.233, + "map_at_10": 0.24284, + "map_at_100": 0.25153, + "map_at_1000": 0.25233, + "recall_at_1": 0.15475, + "recall_at_3": 0.29934, + "recall_at_5": 0.36726, + "recall_at_10": 0.44065, + "recall_at_100": 0.6672, + "recall_at_1000": 0.85929, + "precision_at_1": 0.15475, + "precision_at_3": 0.09978, + "precision_at_5": 0.07345, + "precision_at_10": 0.04406, + "precision_at_100": 0.00667, + "precision_at_1000": 0.00086 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0-instruct/no_revision_available/PIQA.json b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/PIQA.json new file mode 100644 index 000000000..a7dae3c2a --- /dev/null +++ b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/PIQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.27891, + "ndcg_at_1": 0.14799, + "ndcg_at_3": 0.23451, + "ndcg_at_5": 0.25608, + "ndcg_at_10": 0.27891, + "ndcg_at_100": 0.32027, + "ndcg_at_1000": 0.34195, + "map_at_1": 0.14799, + "map_at_3": 0.21409, + "map_at_5": 0.22609, + "map_at_10": 0.23538, + "map_at_100": 0.24327, + "map_at_1000": 0.24398, + "recall_at_1": 0.14799, + "recall_at_3": 0.29325, + "recall_at_5": 0.34548, + "recall_at_10": 0.41676, + "recall_at_100": 0.61643, + "recall_at_1000": 0.79271, + "precision_at_1": 0.14799, + "precision_at_3": 0.09775, + "precision_at_5": 0.0691, + "precision_at_10": 0.04168, + "precision_at_100": 0.00616, + "precision_at_1000": 0.00079 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0-instruct/no_revision_available/Quail.json b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/Quail.json new file mode 100644 index 000000000..ffa275bb9 --- /dev/null +++ b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/Quail.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07773, + "ndcg_at_1": 0.03088, + "ndcg_at_3": 0.0509, + "ndcg_at_5": 0.0634, + "ndcg_at_10": 0.07773, + "ndcg_at_100": 0.11673, + "ndcg_at_1000": 0.15158, + "map_at_1": 0.03088, + "map_at_3": 0.04577, + "map_at_5": 0.05276, + "map_at_10": 0.05864, + "map_at_100": 0.06539, + "map_at_1000": 0.06647, + "recall_at_1": 0.03088, + "recall_at_3": 0.06581, + "recall_at_5": 0.09596, + "recall_at_10": 0.14044, + "recall_at_100": 0.3375, + "recall_at_1000": 0.62574, + "precision_at_1": 0.03088, + "precision_at_3": 0.02194, + "precision_at_5": 0.01919, + "precision_at_10": 0.01404, + "precision_at_100": 0.00337, + "precision_at_1000": 0.00063 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0-instruct/no_revision_available/RARbCode.json b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/RARbCode.json new file mode 100644 index 000000000..f6a3383d7 --- /dev/null +++ b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/RARbCode.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.56557, + "ndcg_at_1": 0.41173, + "ndcg_at_3": 0.50591, + "ndcg_at_5": 0.53865, + "ndcg_at_10": 0.56557, + "ndcg_at_100": 0.6047, + "ndcg_at_1000": 0.6117, + "map_at_1": 0.41173, + "map_at_3": 0.48259, + "map_at_5": 0.50075, + "map_at_10": 0.51181, + "map_at_100": 0.51956, + "map_at_1000": 0.51982, + "recall_at_1": 0.41173, + "recall_at_3": 0.57345, + "recall_at_5": 0.65296, + "recall_at_10": 0.73652, + "recall_at_100": 0.92318, + "recall_at_1000": 0.97844, + "precision_at_1": 0.41173, + "precision_at_3": 0.19115, + "precision_at_5": 0.13059, + "precision_at_10": 0.07365, + "precision_at_100": 0.00923, + "precision_at_1000": 0.00098 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0-instruct/no_revision_available/RARbMath.json b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/RARbMath.json new file mode 100644 index 000000000..d8ccf98d0 --- /dev/null +++ b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/RARbMath.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.72054, + "ndcg_at_1": 0.65928, + "ndcg_at_3": 0.69838, + "ndcg_at_5": 0.70861, + "ndcg_at_10": 0.72054, + "ndcg_at_100": 0.74543, + "ndcg_at_1000": 0.75439, + "map_at_1": 0.65928, + "map_at_3": 0.6889, + "map_at_5": 0.69457, + "map_at_10": 0.69954, + "map_at_100": 0.7043, + "map_at_1000": 0.70463, + "recall_at_1": 0.65928, + "recall_at_3": 0.72575, + "recall_at_5": 0.75059, + "recall_at_10": 0.78731, + "recall_at_100": 0.90758, + "recall_at_1000": 0.97832, + "precision_at_1": 0.65928, + "precision_at_3": 0.24192, + "precision_at_5": 0.15012, + "precision_at_10": 0.07873, + "precision_at_100": 0.00908, + "precision_at_1000": 0.00098 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0-instruct/no_revision_available/SIQA.json b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/SIQA.json new file mode 100644 index 000000000..c60c56ff5 --- /dev/null +++ b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/SIQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.05028, + "ndcg_at_1": 0.02456, + "ndcg_at_3": 0.03796, + "ndcg_at_5": 0.04441, + "ndcg_at_10": 0.05028, + "ndcg_at_100": 0.07972, + "ndcg_at_1000": 0.11983, + "map_at_1": 0.02456, + "map_at_3": 0.03463, + "map_at_5": 0.03816, + "map_at_10": 0.04053, + "map_at_100": 0.04526, + "map_at_1000": 0.04646, + "recall_at_1": 0.02456, + "recall_at_3": 0.04759, + "recall_at_5": 0.06346, + "recall_at_10": 0.08188, + "recall_at_100": 0.2349, + "recall_at_1000": 0.56909, + "precision_at_1": 0.02456, + "precision_at_3": 0.01586, + "precision_at_5": 0.01269, + "precision_at_10": 0.00819, + "precision_at_100": 0.00235, + "precision_at_1000": 0.00057 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0-instruct/no_revision_available/SpartQA.json b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/SpartQA.json new file mode 100644 index 000000000..80e187c64 --- /dev/null +++ b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/SpartQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.03332, + "ndcg_at_1": 0.0039, + "ndcg_at_3": 0.0105, + "ndcg_at_5": 0.01986, + "ndcg_at_10": 0.03332, + "ndcg_at_100": 0.09939, + "ndcg_at_1000": 0.15276, + "map_at_1": 0.00185, + "map_at_3": 0.00713, + "map_at_5": 0.01202, + "map_at_10": 0.01749, + "map_at_100": 0.02849, + "map_at_1000": 0.03015, + "recall_at_1": 0.00185, + "recall_at_3": 0.01512, + "recall_at_5": 0.03561, + "recall_at_10": 0.07355, + "recall_at_100": 0.36765, + "recall_at_1000": 0.74968, + "precision_at_1": 0.0039, + "precision_at_3": 0.00863, + "precision_at_5": 0.01169, + "precision_at_10": 0.01149, + "precision_at_100": 0.00607, + "precision_at_1000": 0.00129 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL1.json b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL1.json new file mode 100644 index 000000000..5065d4052 --- /dev/null +++ b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL1.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01434, + "ndcg_at_1": 0.001, + "ndcg_at_3": 0.00527, + "ndcg_at_5": 0.00854, + "ndcg_at_10": 0.01434, + "ndcg_at_100": 0.05151, + "ndcg_at_1000": 0.11238, + "map_at_1": 0.001, + "map_at_3": 0.00417, + "map_at_5": 0.00597, + "map_at_10": 0.00835, + "map_at_100": 0.01438, + "map_at_1000": 0.01614, + "recall_at_1": 0.001, + "recall_at_3": 0.0085, + "recall_at_5": 0.0165, + "recall_at_10": 0.0345, + "recall_at_100": 0.22675, + "recall_at_1000": 0.737, + "precision_at_1": 0.001, + "precision_at_3": 0.00283, + "precision_at_5": 0.0033, + "precision_at_10": 0.00345, + "precision_at_100": 0.00227, + "precision_at_1000": 0.00074 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL2Fact.json b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL2Fact.json new file mode 100644 index 000000000..ef83d305a --- /dev/null +++ b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL2Fact.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.40461, + "ndcg_at_1": 0.18825, + "ndcg_at_3": 0.31894, + "ndcg_at_5": 0.36429, + "ndcg_at_10": 0.40461, + "ndcg_at_100": 0.45632, + "ndcg_at_1000": 0.46722, + "map_at_1": 0.18825, + "map_at_3": 0.28575, + "map_at_5": 0.31096, + "map_at_10": 0.32775, + "map_at_100": 0.33822, + "map_at_1000": 0.33861, + "recall_at_1": 0.18825, + "recall_at_3": 0.41542, + "recall_at_5": 0.52529, + "recall_at_10": 0.64925, + "recall_at_100": 0.8929, + "recall_at_1000": 0.97962, + "precision_at_1": 0.18825, + "precision_at_3": 0.13847, + "precision_at_5": 0.10506, + "precision_at_10": 0.06492, + "precision_at_100": 0.00893, + "precision_at_1000": 0.00098 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL2Pure.json b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL2Pure.json new file mode 100644 index 000000000..059fac57f --- /dev/null +++ b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL2Pure.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02387, + "ndcg_at_1": 0.00963, + "ndcg_at_3": 0.0166, + "ndcg_at_5": 0.02001, + "ndcg_at_10": 0.02387, + "ndcg_at_100": 0.04872, + "ndcg_at_1000": 0.09458, + "map_at_1": 0.00963, + "map_at_3": 0.01485, + "map_at_5": 0.01673, + "map_at_10": 0.01826, + "map_at_100": 0.02216, + "map_at_1000": 0.02345, + "recall_at_1": 0.00963, + "recall_at_3": 0.02168, + "recall_at_5": 0.03002, + "recall_at_10": 0.04225, + "recall_at_100": 0.17232, + "recall_at_1000": 0.55883, + "precision_at_1": 0.00963, + "precision_at_3": 0.00723, + "precision_at_5": 0.006, + "precision_at_10": 0.00422, + "precision_at_100": 0.00172, + "precision_at_1000": 0.00056 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL3Fact.json b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL3Fact.json new file mode 100644 index 000000000..d1c9a82e6 --- /dev/null +++ b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL3Fact.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.33868, + "ndcg_at_1": 0.12359, + "ndcg_at_3": 0.24437, + "ndcg_at_5": 0.29413, + "ndcg_at_10": 0.33868, + "ndcg_at_100": 0.39629, + "ndcg_at_1000": 0.4103, + "map_at_1": 0.12359, + "map_at_3": 0.21336, + "map_at_5": 0.24107, + "map_at_10": 0.25971, + "map_at_100": 0.27155, + "map_at_1000": 0.27208, + "recall_at_1": 0.12359, + "recall_at_3": 0.33461, + "recall_at_5": 0.45504, + "recall_at_10": 0.5915, + "recall_at_100": 0.86127, + "recall_at_1000": 0.97176, + "precision_at_1": 0.12359, + "precision_at_3": 0.11154, + "precision_at_5": 0.09101, + "precision_at_10": 0.05915, + "precision_at_100": 0.00861, + "precision_at_1000": 0.00097 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL3Pure.json b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL3Pure.json new file mode 100644 index 000000000..659f87b3c --- /dev/null +++ b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/TempReasonL3Pure.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07524, + "ndcg_at_1": 0.00587, + "ndcg_at_3": 0.03333, + "ndcg_at_5": 0.05433, + "ndcg_at_10": 0.07524, + "ndcg_at_100": 0.12654, + "ndcg_at_1000": 0.17137, + "map_at_1": 0.00587, + "map_at_3": 0.02576, + "map_at_5": 0.03739, + "map_at_10": 0.04599, + "map_at_100": 0.05492, + "map_at_1000": 0.05633, + "recall_at_1": 0.00587, + "recall_at_3": 0.05558, + "recall_at_5": 0.10664, + "recall_at_10": 0.17149, + "recall_at_100": 0.43064, + "recall_at_1000": 0.79959, + "precision_at_1": 0.00587, + "precision_at_3": 0.01853, + "precision_at_5": 0.02133, + "precision_at_10": 0.01715, + "precision_at_100": 0.00431, + "precision_at_1000": 0.0008 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0-instruct/no_revision_available/WinoGrande.json b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/WinoGrande.json new file mode 100644 index 000000000..3e437425a --- /dev/null +++ b/results/Cohere-embed-english-v3.0-instruct/no_revision_available/WinoGrande.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.65016, + "ndcg_at_1": 0.34096, + "ndcg_at_3": 0.57077, + "ndcg_at_5": 0.62108, + "ndcg_at_10": 0.65016, + "ndcg_at_100": 0.66367, + "ndcg_at_1000": 0.66409, + "map_at_1": 0.34096, + "map_at_3": 0.51579, + "map_at_5": 0.54384, + "map_at_10": 0.55613, + "map_at_100": 0.55943, + "map_at_1000": 0.55945, + "recall_at_1": 0.34096, + "recall_at_3": 0.72928, + "recall_at_5": 0.85083, + "recall_at_10": 0.93923, + "recall_at_100": 0.99684, + "recall_at_1000": 1.0, + "precision_at_1": 0.34096, + "precision_at_3": 0.24309, + "precision_at_5": 0.17017, + "precision_at_10": 0.09392, + "precision_at_100": 0.00997, + "precision_at_1000": 0.001 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0/no_revision_available/ARCChallenge.json b/results/Cohere-embed-english-v3.0/no_revision_available/ARCChallenge.json new file mode 100644 index 000000000..cf81c9db5 --- /dev/null +++ b/results/Cohere-embed-english-v3.0/no_revision_available/ARCChallenge.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.09891, + "ndcg_at_1": 0.03328, + "ndcg_at_3": 0.07004, + "ndcg_at_5": 0.08208, + "ndcg_at_10": 0.09891, + "ndcg_at_100": 0.15471, + "ndcg_at_1000": 0.19775, + "map_at_1": 0.03328, + "map_at_3": 0.06015, + "map_at_5": 0.06689, + "map_at_10": 0.07384, + "map_at_100": 0.08362, + "map_at_1000": 0.08502, + "recall_at_1": 0.03328, + "recall_at_3": 0.09898, + "recall_at_5": 0.12799, + "recall_at_10": 0.18003, + "recall_at_100": 0.45904, + "recall_at_1000": 0.81058, + "precision_at_1": 0.03328, + "precision_at_3": 0.03299, + "precision_at_5": 0.0256, + "precision_at_10": 0.018, + "precision_at_100": 0.00459, + "precision_at_1000": 0.00081 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0/no_revision_available/AlphaNLI.json b/results/Cohere-embed-english-v3.0/no_revision_available/AlphaNLI.json new file mode 100644 index 000000000..251c2e57e --- /dev/null +++ b/results/Cohere-embed-english-v3.0/no_revision_available/AlphaNLI.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.15098, + "ndcg_at_1": 0.09399, + "ndcg_at_3": 0.12206, + "ndcg_at_5": 0.13737, + "ndcg_at_10": 0.15098, + "ndcg_at_100": 0.18825, + "ndcg_at_1000": 0.21805, + "map_at_1": 0.09399, + "map_at_3": 0.11488, + "map_at_5": 0.12337, + "map_at_10": 0.12892, + "map_at_100": 0.13551, + "map_at_1000": 0.13645, + "recall_at_1": 0.09399, + "recall_at_3": 0.14295, + "recall_at_5": 0.18016, + "recall_at_10": 0.22258, + "recall_at_100": 0.40927, + "recall_at_1000": 0.65405, + "precision_at_1": 0.09399, + "precision_at_3": 0.04765, + "precision_at_5": 0.03603, + "precision_at_10": 0.02226, + "precision_at_100": 0.00409, + "precision_at_1000": 0.00065 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0/no_revision_available/HellaSwag.json b/results/Cohere-embed-english-v3.0/no_revision_available/HellaSwag.json new file mode 100644 index 000000000..69fa37223 --- /dev/null +++ b/results/Cohere-embed-english-v3.0/no_revision_available/HellaSwag.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.26349, + "ndcg_at_1": 0.1417, + "ndcg_at_3": 0.21575, + "ndcg_at_5": 0.24111, + "ndcg_at_10": 0.26349, + "ndcg_at_100": 0.31154, + "ndcg_at_1000": 0.33737, + "map_at_1": 0.1417, + "map_at_3": 0.19711, + "map_at_5": 0.21119, + "map_at_10": 0.2205, + "map_at_100": 0.2294, + "map_at_1000": 0.23027, + "recall_at_1": 0.1417, + "recall_at_3": 0.26987, + "recall_at_5": 0.33141, + "recall_at_10": 0.40022, + "recall_at_100": 0.63623, + "recall_at_1000": 0.84545, + "precision_at_1": 0.1417, + "precision_at_3": 0.08996, + "precision_at_5": 0.06628, + "precision_at_10": 0.04002, + "precision_at_100": 0.00636, + "precision_at_1000": 0.00085 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0/no_revision_available/PIQA.json b/results/Cohere-embed-english-v3.0/no_revision_available/PIQA.json new file mode 100644 index 000000000..1c7929e61 --- /dev/null +++ b/results/Cohere-embed-english-v3.0/no_revision_available/PIQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.2849, + "ndcg_at_1": 0.1518, + "ndcg_at_3": 0.24104, + "ndcg_at_5": 0.26337, + "ndcg_at_10": 0.2849, + "ndcg_at_100": 0.32832, + "ndcg_at_1000": 0.35172, + "map_at_1": 0.1518, + "map_at_3": 0.21971, + "map_at_5": 0.23206, + "map_at_10": 0.24098, + "map_at_100": 0.24933, + "map_at_1000": 0.25014, + "recall_at_1": 0.1518, + "recall_at_3": 0.3025, + "recall_at_5": 0.35691, + "recall_at_10": 0.42329, + "recall_at_100": 0.63275, + "recall_at_1000": 0.82209, + "precision_at_1": 0.1518, + "precision_at_3": 0.10083, + "precision_at_5": 0.07138, + "precision_at_10": 0.04233, + "precision_at_100": 0.00633, + "precision_at_1000": 0.00082 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0/no_revision_available/Quail.json b/results/Cohere-embed-english-v3.0/no_revision_available/Quail.json new file mode 100644 index 000000000..e54c6b683 --- /dev/null +++ b/results/Cohere-embed-english-v3.0/no_revision_available/Quail.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.04102, + "ndcg_at_1": 0.01176, + "ndcg_at_3": 0.02378, + "ndcg_at_5": 0.03115, + "ndcg_at_10": 0.04102, + "ndcg_at_100": 0.07407, + "ndcg_at_1000": 0.10933, + "map_at_1": 0.01176, + "map_at_3": 0.02071, + "map_at_5": 0.02477, + "map_at_10": 0.02877, + "map_at_100": 0.03441, + "map_at_1000": 0.0355, + "recall_at_1": 0.01176, + "recall_at_3": 0.03272, + "recall_at_5": 0.05074, + "recall_at_10": 0.08162, + "recall_at_100": 0.24963, + "recall_at_1000": 0.54228, + "precision_at_1": 0.01176, + "precision_at_3": 0.01091, + "precision_at_5": 0.01015, + "precision_at_10": 0.00816, + "precision_at_100": 0.0025, + "precision_at_1000": 0.00054 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0/no_revision_available/RARbCode.json b/results/Cohere-embed-english-v3.0/no_revision_available/RARbCode.json new file mode 100644 index 000000000..185eaf27d --- /dev/null +++ b/results/Cohere-embed-english-v3.0/no_revision_available/RARbCode.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.57195, + "ndcg_at_1": 0.41914, + "ndcg_at_3": 0.51141, + "ndcg_at_5": 0.54499, + "ndcg_at_10": 0.57195, + "ndcg_at_100": 0.61082, + "ndcg_at_1000": 0.61814, + "map_at_1": 0.41914, + "map_at_3": 0.48899, + "map_at_5": 0.50779, + "map_at_10": 0.51914, + "map_at_100": 0.52696, + "map_at_1000": 0.52724, + "recall_at_1": 0.41914, + "recall_at_3": 0.57615, + "recall_at_5": 0.65701, + "recall_at_10": 0.73922, + "recall_at_100": 0.92318, + "recall_at_1000": 0.98046, + "precision_at_1": 0.41914, + "precision_at_3": 0.19205, + "precision_at_5": 0.1314, + "precision_at_10": 0.07392, + "precision_at_100": 0.00923, + "precision_at_1000": 0.00098 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0/no_revision_available/RARbMath.json b/results/Cohere-embed-english-v3.0/no_revision_available/RARbMath.json new file mode 100644 index 000000000..29ca59867 --- /dev/null +++ b/results/Cohere-embed-english-v3.0/no_revision_available/RARbMath.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.72259, + "ndcg_at_1": 0.66071, + "ndcg_at_3": 0.69936, + "ndcg_at_5": 0.7105, + "ndcg_at_10": 0.72259, + "ndcg_at_100": 0.74748, + "ndcg_at_1000": 0.75587, + "map_at_1": 0.66071, + "map_at_3": 0.69014, + "map_at_5": 0.69633, + "map_at_10": 0.70135, + "map_at_100": 0.70603, + "map_at_1000": 0.70633, + "recall_at_1": 0.66071, + "recall_at_3": 0.72591, + "recall_at_5": 0.75297, + "recall_at_10": 0.79016, + "recall_at_100": 0.91154, + "recall_at_1000": 0.97832, + "precision_at_1": 0.66071, + "precision_at_3": 0.24197, + "precision_at_5": 0.15059, + "precision_at_10": 0.07902, + "precision_at_100": 0.00912, + "precision_at_1000": 0.00098 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0/no_revision_available/SIQA.json b/results/Cohere-embed-english-v3.0/no_revision_available/SIQA.json new file mode 100644 index 000000000..ce9fc3078 --- /dev/null +++ b/results/Cohere-embed-english-v3.0/no_revision_available/SIQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.04262, + "ndcg_at_1": 0.01945, + "ndcg_at_3": 0.02955, + "ndcg_at_5": 0.03605, + "ndcg_at_10": 0.04262, + "ndcg_at_100": 0.06994, + "ndcg_at_1000": 0.10996, + "map_at_1": 0.01945, + "map_at_3": 0.02704, + "map_at_5": 0.03062, + "map_at_10": 0.0333, + "map_at_100": 0.03739, + "map_at_1000": 0.0386, + "recall_at_1": 0.01945, + "recall_at_3": 0.03685, + "recall_at_5": 0.05271, + "recall_at_10": 0.07318, + "recall_at_100": 0.21853, + "recall_at_1000": 0.55067, + "precision_at_1": 0.01945, + "precision_at_3": 0.01228, + "precision_at_5": 0.01054, + "precision_at_10": 0.00732, + "precision_at_100": 0.00219, + "precision_at_1000": 0.00055 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0/no_revision_available/SpartQA.json b/results/Cohere-embed-english-v3.0/no_revision_available/SpartQA.json new file mode 100644 index 000000000..247c5f1ac --- /dev/null +++ b/results/Cohere-embed-english-v3.0/no_revision_available/SpartQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.03752, + "ndcg_at_1": 0.00473, + "ndcg_at_3": 0.01276, + "ndcg_at_5": 0.02226, + "ndcg_at_10": 0.03752, + "ndcg_at_100": 0.1067, + "ndcg_at_1000": 0.15676, + "map_at_1": 0.00213, + "map_at_3": 0.00864, + "map_at_5": 0.01355, + "map_at_10": 0.01965, + "map_at_100": 0.03094, + "map_at_1000": 0.0326, + "recall_at_1": 0.00213, + "recall_at_3": 0.01753, + "recall_at_5": 0.03803, + "recall_at_10": 0.08013, + "recall_at_100": 0.39102, + "recall_at_1000": 0.74578, + "precision_at_1": 0.00473, + "precision_at_3": 0.01141, + "precision_at_5": 0.0138, + "precision_at_10": 0.01375, + "precision_at_100": 0.00659, + "precision_at_1000": 0.00128 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL1.json b/results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL1.json new file mode 100644 index 000000000..c39b5617a --- /dev/null +++ b/results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL1.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.015, + "ndcg_at_1": 0.001, + "ndcg_at_3": 0.00506, + "ndcg_at_5": 0.00883, + "ndcg_at_10": 0.015, + "ndcg_at_100": 0.05369, + "ndcg_at_1000": 0.11572, + "map_at_1": 0.001, + "map_at_3": 0.00404, + "map_at_5": 0.00612, + "map_at_10": 0.00868, + "map_at_100": 0.01484, + "map_at_1000": 0.01665, + "recall_at_1": 0.001, + "recall_at_3": 0.008, + "recall_at_5": 0.01725, + "recall_at_10": 0.03625, + "recall_at_100": 0.238, + "recall_at_1000": 0.7565, + "precision_at_1": 0.001, + "precision_at_3": 0.00267, + "precision_at_5": 0.00345, + "precision_at_10": 0.00362, + "precision_at_100": 0.00238, + "precision_at_1000": 0.00076 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL2Fact.json b/results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL2Fact.json new file mode 100644 index 000000000..4386434f3 --- /dev/null +++ b/results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL2Fact.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.35911, + "ndcg_at_1": 0.15768, + "ndcg_at_3": 0.27502, + "ndcg_at_5": 0.31954, + "ndcg_at_10": 0.35911, + "ndcg_at_100": 0.41617, + "ndcg_at_1000": 0.42979, + "map_at_1": 0.15768, + "map_at_3": 0.24498, + "map_at_5": 0.26975, + "map_at_10": 0.28623, + "map_at_100": 0.29749, + "map_at_1000": 0.29798, + "recall_at_1": 0.15768, + "recall_at_3": 0.36242, + "recall_at_5": 0.47026, + "recall_at_10": 0.59181, + "recall_at_100": 0.86326, + "recall_at_1000": 0.97184, + "precision_at_1": 0.15768, + "precision_at_3": 0.12081, + "precision_at_5": 0.09405, + "precision_at_10": 0.05918, + "precision_at_100": 0.00863, + "precision_at_1000": 0.00097 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL2Pure.json b/results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL2Pure.json new file mode 100644 index 000000000..95e751461 --- /dev/null +++ b/results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL2Pure.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01886, + "ndcg_at_1": 0.00667, + "ndcg_at_3": 0.01143, + "ndcg_at_5": 0.01532, + "ndcg_at_10": 0.01886, + "ndcg_at_100": 0.04205, + "ndcg_at_1000": 0.0842, + "map_at_1": 0.00667, + "map_at_3": 0.01025, + "map_at_5": 0.01241, + "map_at_10": 0.01384, + "map_at_100": 0.01745, + "map_at_1000": 0.01863, + "recall_at_1": 0.00667, + "recall_at_3": 0.01482, + "recall_at_5": 0.02427, + "recall_at_10": 0.03539, + "recall_at_100": 0.15749, + "recall_at_1000": 0.51343, + "precision_at_1": 0.00667, + "precision_at_3": 0.00494, + "precision_at_5": 0.00485, + "precision_at_10": 0.00354, + "precision_at_100": 0.00157, + "precision_at_1000": 0.00051 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL3Fact.json b/results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL3Fact.json new file mode 100644 index 000000000..0accb1dc5 --- /dev/null +++ b/results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL3Fact.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.27514, + "ndcg_at_1": 0.0714, + "ndcg_at_3": 0.18146, + "ndcg_at_5": 0.23081, + "ndcg_at_10": 0.27514, + "ndcg_at_100": 0.33871, + "ndcg_at_1000": 0.35662, + "map_at_1": 0.0714, + "map_at_3": 0.15273, + "map_at_5": 0.18014, + "map_at_10": 0.19864, + "map_at_100": 0.21148, + "map_at_1000": 0.21213, + "recall_at_1": 0.0714, + "recall_at_3": 0.26525, + "recall_at_5": 0.385, + "recall_at_10": 0.52101, + "recall_at_100": 0.82083, + "recall_at_1000": 0.9634, + "precision_at_1": 0.0714, + "precision_at_3": 0.08842, + "precision_at_5": 0.077, + "precision_at_10": 0.0521, + "precision_at_100": 0.00821, + "precision_at_1000": 0.00096 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL3Pure.json b/results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL3Pure.json new file mode 100644 index 000000000..ad98f863d --- /dev/null +++ b/results/Cohere-embed-english-v3.0/no_revision_available/TempReasonL3Pure.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.08527, + "ndcg_at_1": 0.00339, + "ndcg_at_3": 0.04484, + "ndcg_at_5": 0.06348, + "ndcg_at_10": 0.08527, + "ndcg_at_100": 0.13206, + "ndcg_at_1000": 0.17685, + "map_at_1": 0.00339, + "map_at_3": 0.03389, + "map_at_5": 0.0442, + "map_at_10": 0.05329, + "map_at_100": 0.06145, + "map_at_1000": 0.06286, + "recall_at_1": 0.00339, + "recall_at_3": 0.07682, + "recall_at_5": 0.12223, + "recall_at_10": 0.18911, + "recall_at_100": 0.42544, + "recall_at_1000": 0.79327, + "precision_at_1": 0.00339, + "precision_at_3": 0.02561, + "precision_at_5": 0.02445, + "precision_at_10": 0.01891, + "precision_at_100": 0.00425, + "precision_at_1000": 0.00079 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/Cohere-embed-english-v3.0/no_revision_available/WinoGrande.json b/results/Cohere-embed-english-v3.0/no_revision_available/WinoGrande.json new file mode 100644 index 000000000..23970ec2c --- /dev/null +++ b/results/Cohere-embed-english-v3.0/no_revision_available/WinoGrande.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.58005, + "ndcg_at_1": 0.28808, + "ndcg_at_3": 0.48566, + "ndcg_at_5": 0.53549, + "ndcg_at_10": 0.58005, + "ndcg_at_100": 0.60469, + "ndcg_at_1000": 0.60565, + "map_at_1": 0.28808, + "map_at_3": 0.43646, + "map_at_5": 0.46417, + "map_at_10": 0.4828, + "map_at_100": 0.48859, + "map_at_1000": 0.48864, + "recall_at_1": 0.28808, + "recall_at_3": 0.62826, + "recall_at_5": 0.74901, + "recall_at_10": 0.88556, + "recall_at_100": 0.9929, + "recall_at_1000": 1.0, + "precision_at_1": 0.28808, + "precision_at_3": 0.20942, + "precision_at_5": 0.1498, + "precision_at_10": 0.08856, + "precision_at_100": 0.00993, + "precision_at_1000": 0.001 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/ARCChallenge.json b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/ARCChallenge.json new file mode 100644 index 000000000..6c88006a6 --- /dev/null +++ b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/ARCChallenge.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 78.18728423118591, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.16567, + "map_at_1": 0.08276, + "map_at_10": 0.1332, + "map_at_100": 0.14363, + "map_at_1000": 0.14482, + "map_at_20": 0.13866, + "map_at_3": 0.11277, + "map_at_5": 0.12433, + "mrr_at_1": 0.08276450511945392, + "mrr_at_10": 0.13319620510320165, + "mrr_at_100": 0.14362586972749813, + "mrr_at_1000": 0.1448178804221324, + "mrr_at_20": 0.1386578989402944, + "mrr_at_3": 0.11277019340159264, + "mrr_at_5": 0.12433162684869167, + "nauc_map_at_1000_diff1": 0.11606267607104377, + "nauc_map_at_1000_max": -0.10084652504177026, + "nauc_map_at_1000_std": -0.11828505538008827, + "nauc_map_at_100_diff1": 0.11617938969146996, + "nauc_map_at_100_max": -0.10103608095245299, + "nauc_map_at_100_std": -0.11836784322419454, + "nauc_map_at_10_diff1": 0.12171741485767183, + "nauc_map_at_10_max": -0.0951712196064573, + "nauc_map_at_10_std": -0.12040642685533308, + "nauc_map_at_1_diff1": 0.1637549340679917, + "nauc_map_at_1_max": -0.06866843294505832, + "nauc_map_at_1_std": -0.11623156565719857, + "nauc_map_at_20_diff1": 0.1189920257095774, + "nauc_map_at_20_max": -0.0991905913147805, + "nauc_map_at_20_std": -0.12012391309456927, + "nauc_map_at_3_diff1": 0.13195461509097473, + "nauc_map_at_3_max": -0.08656050010347069, + "nauc_map_at_3_std": -0.12814440057787524, + "nauc_map_at_5_diff1": 0.12381744141594893, + "nauc_map_at_5_max": -0.08188524850924572, + "nauc_map_at_5_std": -0.11540567655833621, + "nauc_mrr_at_1000_diff1": 0.11606267607104377, + "nauc_mrr_at_1000_max": -0.10084652504177026, + "nauc_mrr_at_1000_std": -0.11828505538008827, + "nauc_mrr_at_100_diff1": 0.11617938969146996, + "nauc_mrr_at_100_max": -0.10103608095245299, + "nauc_mrr_at_100_std": -0.11836784322419454, + "nauc_mrr_at_10_diff1": 0.12171741485767183, + "nauc_mrr_at_10_max": -0.0951712196064573, + "nauc_mrr_at_10_std": -0.12040642685533308, + "nauc_mrr_at_1_diff1": 0.1637549340679917, + "nauc_mrr_at_1_max": -0.06866843294505832, + "nauc_mrr_at_1_std": -0.11623156565719857, + "nauc_mrr_at_20_diff1": 0.1189920257095774, + "nauc_mrr_at_20_max": -0.0991905913147805, + "nauc_mrr_at_20_std": -0.12012391309456927, + "nauc_mrr_at_3_diff1": 0.13195461509097473, + "nauc_mrr_at_3_max": -0.08656050010347069, + "nauc_mrr_at_3_std": -0.12814440057787524, + "nauc_mrr_at_5_diff1": 0.12381744141594893, + "nauc_mrr_at_5_max": -0.08188524850924572, + "nauc_mrr_at_5_std": -0.11540567655833621, + "nauc_ndcg_at_1000_diff1": 0.07782564462113492, + "nauc_ndcg_at_1000_max": -0.1311850591294924, + "nauc_ndcg_at_1000_std": -0.1050073073458404, + "nauc_ndcg_at_100_diff1": 0.08039808605161892, + "nauc_ndcg_at_100_max": -0.130185279752856, + "nauc_ndcg_at_100_std": -0.10462409602995773, + "nauc_ndcg_at_10_diff1": 0.10518245547538639, + "nauc_ndcg_at_10_max": -0.11041301107009849, + "nauc_ndcg_at_10_std": -0.11849884556559163, + "nauc_ndcg_at_1_diff1": 0.1637549340679917, + "nauc_ndcg_at_1_max": -0.06866843294505832, + "nauc_ndcg_at_1_std": -0.11623156565719857, + "nauc_ndcg_at_20_diff1": 0.09856770854187791, + "nauc_ndcg_at_20_max": -0.12213906580274646, + "nauc_ndcg_at_20_std": -0.11819865442488073, + "nauc_ndcg_at_3_diff1": 0.12119705302223491, + "nauc_ndcg_at_3_max": -0.09227415998343752, + "nauc_ndcg_at_3_std": -0.12911306275481269, + "nauc_ndcg_at_5_diff1": 0.10981759290664823, + "nauc_ndcg_at_5_max": -0.08336011154639276, + "nauc_ndcg_at_5_std": -0.10750180809854237, + "nauc_precision_at_1000_diff1": -0.1695783827238421, + "nauc_precision_at_1000_max": -0.3245680277313244, + "nauc_precision_at_1000_std": -0.012669573395770703, + "nauc_precision_at_100_diff1": -0.013170183794179467, + "nauc_precision_at_100_max": -0.2004149608472424, + "nauc_precision_at_100_std": -0.05897637081303174, + "nauc_precision_at_10_diff1": 0.07275127233245807, + "nauc_precision_at_10_max": -0.14279613765432786, + "nauc_precision_at_10_std": -0.11534315061842612, + "nauc_precision_at_1_diff1": 0.1637549340679917, + "nauc_precision_at_1_max": -0.06866843294505832, + "nauc_precision_at_1_std": -0.11623156565719857, + "nauc_precision_at_20_diff1": 0.05928787026612005, + "nauc_precision_at_20_max": -0.17129862954688976, + "nauc_precision_at_20_std": -0.11542140579282543, + "nauc_precision_at_3_diff1": 0.09613544495372242, + "nauc_precision_at_3_max": -0.10552411799048211, + "nauc_precision_at_3_std": -0.13081876562122427, + "nauc_precision_at_5_diff1": 0.08113003762777546, + "nauc_precision_at_5_max": -0.08527591607021416, + "nauc_precision_at_5_std": -0.08915421346354885, + "nauc_recall_at_1000_diff1": -0.16957838272384387, + "nauc_recall_at_1000_max": -0.3245680277313267, + "nauc_recall_at_1000_std": -0.012669573395772498, + "nauc_recall_at_100_diff1": -0.013170183794179738, + "nauc_recall_at_100_max": -0.20041496084724292, + "nauc_recall_at_100_std": -0.05897637081303231, + "nauc_recall_at_10_diff1": 0.0727512723324577, + "nauc_recall_at_10_max": -0.1427961376543279, + "nauc_recall_at_10_std": -0.11534315061842598, + "nauc_recall_at_1_diff1": 0.1637549340679917, + "nauc_recall_at_1_max": -0.06866843294505832, + "nauc_recall_at_1_std": -0.11623156565719857, + "nauc_recall_at_20_diff1": 0.059287870266119605, + "nauc_recall_at_20_max": -0.17129862954689018, + "nauc_recall_at_20_std": -0.11542140579282577, + "nauc_recall_at_3_diff1": 0.09613544495372225, + "nauc_recall_at_3_max": -0.10552411799048216, + "nauc_recall_at_3_std": -0.13081876562122424, + "nauc_recall_at_5_diff1": 0.08113003762777533, + "nauc_recall_at_5_max": -0.08527591607021426, + "nauc_recall_at_5_std": -0.08915421346354895, + "ndcg_at_1": 0.08276, + "ndcg_at_10": 0.16567, + "ndcg_at_100": 0.2226, + "ndcg_at_1000": 0.25982, + "ndcg_at_20": 0.18539, + "ndcg_at_3": 0.1232, + "ndcg_at_5": 0.14417, + "precision_at_1": 0.08276, + "precision_at_10": 0.02713, + "precision_at_100": 0.00552, + "precision_at_1000": 0.00086, + "precision_at_20": 0.01745, + "precision_at_3": 0.05119, + "precision_at_5": 0.04096, + "recall_at_1": 0.08276, + "recall_at_10": 0.27133, + "recall_at_100": 0.55205, + "recall_at_1000": 0.85666, + "recall_at_20": 0.34898, + "recall_at_3": 0.15358, + "recall_at_5": 0.20478 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/AlphaNLI.json b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/AlphaNLI.json new file mode 100644 index 000000000..33cdfe731 --- /dev/null +++ b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/AlphaNLI.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 1270.652179479599, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.29556, + "map_at_1": 0.19582, + "map_at_10": 0.26009, + "map_at_100": 0.26884, + "map_at_1000": 0.26961, + "map_at_20": 0.26455, + "map_at_3": 0.24086, + "map_at_5": 0.25173, + "mrr_at_1": 0.195822454308094, + "mrr_at_10": 0.2600939222512328, + "mrr_at_100": 0.26883610136872893, + "mrr_at_1000": 0.26961346115632173, + "mrr_at_20": 0.2645490625655516, + "mrr_at_3": 0.24086161879895546, + "mrr_at_5": 0.2517297650130545, + "nauc_map_at_1000_diff1": 0.3581262993761119, + "nauc_map_at_1000_max": 0.18737882517084573, + "nauc_map_at_1000_std": -0.06452508289227181, + "nauc_map_at_100_diff1": 0.3580396187920006, + "nauc_map_at_100_max": 0.18715247309578215, + "nauc_map_at_100_std": -0.06467289761940416, + "nauc_map_at_10_diff1": 0.3602649101950382, + "nauc_map_at_10_max": 0.19084692411391246, + "nauc_map_at_10_std": -0.06424330205810602, + "nauc_map_at_1_diff1": 0.41684305133357324, + "nauc_map_at_1_max": 0.23999061803519373, + "nauc_map_at_1_std": -0.03497237739685838, + "nauc_map_at_20_diff1": 0.35923735124817535, + "nauc_map_at_20_max": 0.18692626854610142, + "nauc_map_at_20_std": -0.06671937446108235, + "nauc_map_at_3_diff1": 0.37685381270276136, + "nauc_map_at_3_max": 0.20715287494533172, + "nauc_map_at_3_std": -0.05590743263735323, + "nauc_map_at_5_diff1": 0.3654358413863913, + "nauc_map_at_5_max": 0.19607730137035934, + "nauc_map_at_5_std": -0.06337248072588127, + "nauc_mrr_at_1000_diff1": 0.3581262993761119, + "nauc_mrr_at_1000_max": 0.18737882517084573, + "nauc_mrr_at_1000_std": -0.06452508289227181, + "nauc_mrr_at_100_diff1": 0.3580396187920006, + "nauc_mrr_at_100_max": 0.18715247309578215, + "nauc_mrr_at_100_std": -0.06467289761940416, + "nauc_mrr_at_10_diff1": 0.3602649101950382, + "nauc_mrr_at_10_max": 0.19084692411391246, + "nauc_mrr_at_10_std": -0.06424330205810602, + "nauc_mrr_at_1_diff1": 0.41684305133357324, + "nauc_mrr_at_1_max": 0.23999061803519373, + "nauc_mrr_at_1_std": -0.03497237739685838, + "nauc_mrr_at_20_diff1": 0.35923735124817535, + "nauc_mrr_at_20_max": 0.18692626854610142, + "nauc_mrr_at_20_std": -0.06671937446108235, + "nauc_mrr_at_3_diff1": 0.37685381270276136, + "nauc_mrr_at_3_max": 0.20715287494533172, + "nauc_mrr_at_3_std": -0.05590743263735323, + "nauc_mrr_at_5_diff1": 0.3654358413863913, + "nauc_mrr_at_5_max": 0.19607730137035934, + "nauc_mrr_at_5_std": -0.06337248072588127, + "nauc_ndcg_at_1000_diff1": 0.3273834438022227, + "nauc_ndcg_at_1000_max": 0.1622409096338372, + "nauc_ndcg_at_1000_std": -0.0669388102417427, + "nauc_ndcg_at_100_diff1": 0.3223003368537524, + "nauc_ndcg_at_100_max": 0.1547146909189916, + "nauc_ndcg_at_100_std": -0.07012998864619853, + "nauc_ndcg_at_10_diff1": 0.33558897971035817, + "nauc_ndcg_at_10_max": 0.16674222031452857, + "nauc_ndcg_at_10_std": -0.07599286983639812, + "nauc_ndcg_at_1_diff1": 0.41684305133357324, + "nauc_ndcg_at_1_max": 0.23999061803519373, + "nauc_ndcg_at_1_std": -0.03497237739685838, + "nauc_ndcg_at_20_diff1": 0.3321776819933026, + "nauc_ndcg_at_20_max": 0.1526275128682169, + "nauc_ndcg_at_20_std": -0.08555865426380696, + "nauc_ndcg_at_3_diff1": 0.36622693404119916, + "nauc_ndcg_at_3_max": 0.1979519921767349, + "nauc_ndcg_at_3_std": -0.06086233490189131, + "nauc_ndcg_at_5_diff1": 0.346250107952567, + "nauc_ndcg_at_5_max": 0.17847240288665858, + "nauc_ndcg_at_5_std": -0.07384965773020805, + "nauc_precision_at_1000_diff1": 0.15722783022505635, + "nauc_precision_at_1000_max": 0.062389360128002475, + "nauc_precision_at_1000_std": -0.020194075968903987, + "nauc_precision_at_100_diff1": 0.17926769479182755, + "nauc_precision_at_100_max": 0.03764458108362797, + "nauc_precision_at_100_std": -0.06516684759990607, + "nauc_precision_at_10_diff1": 0.26861850851333074, + "nauc_precision_at_10_max": 0.09981912991436129, + "nauc_precision_at_10_std": -0.10775280987881723, + "nauc_precision_at_1_diff1": 0.41684305133357324, + "nauc_precision_at_1_max": 0.23999061803519373, + "nauc_precision_at_1_std": -0.03497237739685838, + "nauc_precision_at_20_diff1": 0.25543225738691927, + "nauc_precision_at_20_max": 0.04693182684250898, + "nauc_precision_at_20_std": -0.1445516047213592, + "nauc_precision_at_3_diff1": 0.33871394447027126, + "nauc_precision_at_3_max": 0.17398390212102777, + "nauc_precision_at_3_std": -0.07350206090918988, + "nauc_precision_at_5_diff1": 0.2946779502612536, + "nauc_precision_at_5_max": 0.1307848039211153, + "nauc_precision_at_5_std": -0.10206440369947867, + "nauc_recall_at_1000_diff1": 0.15722783022505793, + "nauc_recall_at_1000_max": 0.0623893601280026, + "nauc_recall_at_1000_std": -0.020194075968902568, + "nauc_recall_at_100_diff1": 0.17926769479182714, + "nauc_recall_at_100_max": 0.03764458108362699, + "nauc_recall_at_100_std": -0.06516684759990606, + "nauc_recall_at_10_diff1": 0.2686185085133306, + "nauc_recall_at_10_max": 0.09981912991436125, + "nauc_recall_at_10_std": -0.10775280987881715, + "nauc_recall_at_1_diff1": 0.41684305133357324, + "nauc_recall_at_1_max": 0.23999061803519373, + "nauc_recall_at_1_std": -0.03497237739685838, + "nauc_recall_at_20_diff1": 0.2554322573869195, + "nauc_recall_at_20_max": 0.046931826842508566, + "nauc_recall_at_20_std": -0.14455160472135906, + "nauc_recall_at_3_diff1": 0.3387139444702712, + "nauc_recall_at_3_max": 0.17398390212102802, + "nauc_recall_at_3_std": -0.07350206090918995, + "nauc_recall_at_5_diff1": 0.2946779502612537, + "nauc_recall_at_5_max": 0.13078480392111536, + "nauc_recall_at_5_std": -0.10206440369947854, + "ndcg_at_1": 0.19582, + "ndcg_at_10": 0.29556, + "ndcg_at_100": 0.34419, + "ndcg_at_1000": 0.36667, + "ndcg_at_20": 0.31208, + "ndcg_at_3": 0.25545, + "ndcg_at_5": 0.27506, + "precision_at_1": 0.19582, + "precision_at_10": 0.04093, + "precision_at_100": 0.00651, + "precision_at_1000": 0.00083, + "precision_at_20": 0.02376, + "precision_at_3": 0.09922, + "precision_at_5": 0.06906, + "recall_at_1": 0.19582, + "recall_at_10": 0.40927, + "recall_at_100": 0.65078, + "recall_at_1000": 0.83159, + "recall_at_20": 0.4752, + "recall_at_3": 0.29765, + "recall_at_5": 0.3453 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/HellaSwag.json b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/HellaSwag.json new file mode 100644 index 000000000..741cfb4e7 --- /dev/null +++ b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/HellaSwag.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 2612.5123026371, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.36029, + "map_at_1": 0.23023, + "map_at_10": 0.31586, + "map_at_100": 0.32458, + "map_at_1000": 0.32531, + "map_at_20": 0.32076, + "map_at_3": 0.29262, + "map_at_5": 0.30631, + "mrr_at_1": 0.23023302131049592, + "mrr_at_10": 0.3158607262197196, + "mrr_at_100": 0.3245830133120316, + "mrr_at_1000": 0.3253084468424516, + "mrr_at_20": 0.3207625876381118, + "mrr_at_3": 0.292620991834297, + "mrr_at_5": 0.30630850428201617, + "nauc_map_at_1000_diff1": 0.27580497960691985, + "nauc_map_at_1000_max": 0.18625701003944933, + "nauc_map_at_1000_std": -0.24676800806938665, + "nauc_map_at_100_diff1": 0.2755593604742009, + "nauc_map_at_100_max": 0.18614675032953235, + "nauc_map_at_100_std": -0.24705706981062175, + "nauc_map_at_10_diff1": 0.2772900372286112, + "nauc_map_at_10_max": 0.18698397312819579, + "nauc_map_at_10_std": -0.24741394766281596, + "nauc_map_at_1_diff1": 0.3354133561428343, + "nauc_map_at_1_max": 0.19004997541095103, + "nauc_map_at_1_std": -0.21676244650289994, + "nauc_map_at_20_diff1": 0.27590079352522445, + "nauc_map_at_20_max": 0.18609826043595196, + "nauc_map_at_20_std": -0.24807407855984331, + "nauc_map_at_3_diff1": 0.28684207804861767, + "nauc_map_at_3_max": 0.1916725368715439, + "nauc_map_at_3_std": -0.24010116933611186, + "nauc_map_at_5_diff1": 0.2808502148053725, + "nauc_map_at_5_max": 0.1887447468764204, + "nauc_map_at_5_std": -0.24560665609770493, + "nauc_mrr_at_1000_diff1": 0.27580497960691985, + "nauc_mrr_at_1000_max": 0.18625701003944933, + "nauc_mrr_at_1000_std": -0.24676800806938665, + "nauc_mrr_at_100_diff1": 0.2755593604742009, + "nauc_mrr_at_100_max": 0.18614675032953235, + "nauc_mrr_at_100_std": -0.24705706981062175, + "nauc_mrr_at_10_diff1": 0.2772900372286112, + "nauc_mrr_at_10_max": 0.18698397312819579, + "nauc_mrr_at_10_std": -0.24741394766281596, + "nauc_mrr_at_1_diff1": 0.3354133561428343, + "nauc_mrr_at_1_max": 0.19004997541095103, + "nauc_mrr_at_1_std": -0.21676244650289994, + "nauc_mrr_at_20_diff1": 0.27590079352522445, + "nauc_mrr_at_20_max": 0.18609826043595196, + "nauc_mrr_at_20_std": -0.24807407855984331, + "nauc_mrr_at_3_diff1": 0.28684207804861767, + "nauc_mrr_at_3_max": 0.1916725368715439, + "nauc_mrr_at_3_std": -0.24010116933611186, + "nauc_mrr_at_5_diff1": 0.2808502148053725, + "nauc_mrr_at_5_max": 0.1887447468764204, + "nauc_mrr_at_5_std": -0.24560665609770493, + "nauc_ndcg_at_1000_diff1": 0.25243320200096475, + "nauc_ndcg_at_1000_max": 0.18278833590706065, + "nauc_ndcg_at_1000_std": -0.25085567799807074, + "nauc_ndcg_at_100_diff1": 0.2462745372425762, + "nauc_ndcg_at_100_max": 0.1802754649358636, + "nauc_ndcg_at_100_std": -0.2569567715377601, + "nauc_ndcg_at_10_diff1": 0.2549947029512527, + "nauc_ndcg_at_10_max": 0.1831676353378172, + "nauc_ndcg_at_10_std": -0.26084960431261855, + "nauc_ndcg_at_1_diff1": 0.3354133561428343, + "nauc_ndcg_at_1_max": 0.19004997541095103, + "nauc_ndcg_at_1_std": -0.21676244650289994, + "nauc_ndcg_at_20_diff1": 0.2498596331994722, + "nauc_ndcg_at_20_max": 0.18025035049548516, + "nauc_ndcg_at_20_std": -0.2633000301036997, + "nauc_ndcg_at_3_diff1": 0.27362923857298443, + "nauc_ndcg_at_3_max": 0.19254376211859964, + "nauc_ndcg_at_3_std": -0.246890523333178, + "nauc_ndcg_at_5_diff1": 0.26323097577974414, + "nauc_ndcg_at_5_max": 0.18727285816506173, + "nauc_ndcg_at_5_std": -0.2568312670776633, + "nauc_precision_at_1000_diff1": 0.07984766195114014, + "nauc_precision_at_1000_max": 0.16664587696955235, + "nauc_precision_at_1000_std": -0.200734419156548, + "nauc_precision_at_100_diff1": 0.11145064013237672, + "nauc_precision_at_100_max": 0.15129111137097911, + "nauc_precision_at_100_std": -0.28673774423906656, + "nauc_precision_at_10_diff1": 0.19042543161442663, + "nauc_precision_at_10_max": 0.1706245111362394, + "nauc_precision_at_10_std": -0.3001404446220411, + "nauc_precision_at_1_diff1": 0.3354133561428343, + "nauc_precision_at_1_max": 0.19004997541095103, + "nauc_precision_at_1_std": -0.21676244650289994, + "nauc_precision_at_20_diff1": 0.16555645848774045, + "nauc_precision_at_20_max": 0.15875925121026774, + "nauc_precision_at_20_std": -0.312539321059759, + "nauc_precision_at_3_diff1": 0.23860538409899099, + "nauc_precision_at_3_max": 0.19498791917524325, + "nauc_precision_at_3_std": -0.2650254739772059, + "nauc_precision_at_5_diff1": 0.2152331332947587, + "nauc_precision_at_5_max": 0.18268922805189303, + "nauc_precision_at_5_std": -0.28824490384748436, + "nauc_recall_at_1000_diff1": 0.07984766195114047, + "nauc_recall_at_1000_max": 0.16664587696955238, + "nauc_recall_at_1000_std": -0.20073441915654822, + "nauc_recall_at_100_diff1": 0.11145064013237652, + "nauc_recall_at_100_max": 0.15129111137097934, + "nauc_recall_at_100_std": -0.28673774423906523, + "nauc_recall_at_10_diff1": 0.19042543161442685, + "nauc_recall_at_10_max": 0.1706245111362396, + "nauc_recall_at_10_std": -0.3001404446220414, + "nauc_recall_at_1_diff1": 0.3354133561428343, + "nauc_recall_at_1_max": 0.19004997541095103, + "nauc_recall_at_1_std": -0.21676244650289994, + "nauc_recall_at_20_diff1": 0.16555645848774078, + "nauc_recall_at_20_max": 0.1587592512102679, + "nauc_recall_at_20_std": -0.3125393210597586, + "nauc_recall_at_3_diff1": 0.2386053840989911, + "nauc_recall_at_3_max": 0.19498791917524314, + "nauc_recall_at_3_std": -0.2650254739772058, + "nauc_recall_at_5_diff1": 0.21523313329475943, + "nauc_recall_at_5_max": 0.18268922805189336, + "nauc_recall_at_5_std": -0.2882449038474837, + "ndcg_at_1": 0.23023, + "ndcg_at_10": 0.36029, + "ndcg_at_100": 0.40633, + "ndcg_at_1000": 0.42705, + "ndcg_at_20": 0.3781, + "ndcg_at_3": 0.31263, + "ndcg_at_5": 0.33729, + "precision_at_1": 0.23023, + "precision_at_10": 0.05011, + "precision_at_100": 0.00725, + "precision_at_1000": 0.00089, + "precision_at_20": 0.02857, + "precision_at_3": 0.12348, + "precision_at_5": 0.08606, + "recall_at_1": 0.23023, + "recall_at_10": 0.5011, + "recall_at_100": 0.72476, + "recall_at_1000": 0.89076, + "recall_at_20": 0.5714, + "recall_at_3": 0.37044, + "recall_at_5": 0.43029 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/PIQA.json b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/PIQA.json new file mode 100644 index 000000000..47e644e5c --- /dev/null +++ b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/PIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 370.6609456539154, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.358, + "map_at_1": 0.21164, + "map_at_10": 0.3093, + "map_at_100": 0.31932, + "map_at_1000": 0.31988, + "map_at_20": 0.31506, + "map_at_3": 0.28455, + "map_at_5": 0.29984, + "mrr_at_1": 0.2116430903155604, + "mrr_at_10": 0.3092966820387931, + "mrr_at_100": 0.3193174966612901, + "mrr_at_1000": 0.31988181188908005, + "mrr_at_20": 0.3150589657281461, + "mrr_at_3": 0.28454842219804094, + "mrr_at_5": 0.2998367791077254, + "nauc_map_at_1000_diff1": 0.08955126901295282, + "nauc_map_at_1000_max": 0.03113170913204904, + "nauc_map_at_1000_std": -0.10178046564662836, + "nauc_map_at_100_diff1": 0.08945518652902479, + "nauc_map_at_100_max": 0.03104237632387918, + "nauc_map_at_100_std": -0.10185036060075132, + "nauc_map_at_10_diff1": 0.09125960519353415, + "nauc_map_at_10_max": 0.03524443361897731, + "nauc_map_at_10_std": -0.10245943118807374, + "nauc_map_at_1_diff1": 0.13935922475361198, + "nauc_map_at_1_max": 0.03995020889299259, + "nauc_map_at_1_std": -0.1008863850181277, + "nauc_map_at_20_diff1": 0.0902103913712896, + "nauc_map_at_20_max": 0.03296897643021872, + "nauc_map_at_20_std": -0.10204645636138575, + "nauc_map_at_3_diff1": 0.09206701509648749, + "nauc_map_at_3_max": 0.043193181833316746, + "nauc_map_at_3_std": -0.10229669889681861, + "nauc_map_at_5_diff1": 0.09219470104320367, + "nauc_map_at_5_max": 0.04025434220729681, + "nauc_map_at_5_std": -0.10306388427111525, + "nauc_mrr_at_1000_diff1": 0.08955126901295282, + "nauc_mrr_at_1000_max": 0.03113170913204904, + "nauc_mrr_at_1000_std": -0.10178046564662836, + "nauc_mrr_at_100_diff1": 0.08945518652902479, + "nauc_mrr_at_100_max": 0.03104237632387918, + "nauc_mrr_at_100_std": -0.10185036060075132, + "nauc_mrr_at_10_diff1": 0.09125960519353415, + "nauc_mrr_at_10_max": 0.03524443361897731, + "nauc_mrr_at_10_std": -0.10245943118807374, + "nauc_mrr_at_1_diff1": 0.13935922475361198, + "nauc_mrr_at_1_max": 0.03995020889299259, + "nauc_mrr_at_1_std": -0.1008863850181277, + "nauc_mrr_at_20_diff1": 0.0902103913712896, + "nauc_mrr_at_20_max": 0.03296897643021872, + "nauc_mrr_at_20_std": -0.10204645636138575, + "nauc_mrr_at_3_diff1": 0.09206701509648749, + "nauc_mrr_at_3_max": 0.043193181833316746, + "nauc_mrr_at_3_std": -0.10229669889681861, + "nauc_mrr_at_5_diff1": 0.09219470104320367, + "nauc_mrr_at_5_max": 0.04025434220729681, + "nauc_mrr_at_5_std": -0.10306388427111525, + "nauc_ndcg_at_1000_diff1": 0.07117954262621701, + "nauc_ndcg_at_1000_max": 0.007937951286985344, + "nauc_ndcg_at_1000_std": -0.09766344420304353, + "nauc_ndcg_at_100_diff1": 0.06924384145815779, + "nauc_ndcg_at_100_max": 0.006082719582374023, + "nauc_ndcg_at_100_std": -0.09807583654970788, + "nauc_ndcg_at_10_diff1": 0.07818608684302861, + "nauc_ndcg_at_10_max": 0.027133720166217505, + "nauc_ndcg_at_10_std": -0.10187004634107966, + "nauc_ndcg_at_1_diff1": 0.13935922475361198, + "nauc_ndcg_at_1_max": 0.03995020889299259, + "nauc_ndcg_at_1_std": -0.1008863850181277, + "nauc_ndcg_at_20_diff1": 0.07378363956267808, + "nauc_ndcg_at_20_max": 0.019371503803079154, + "nauc_ndcg_at_20_std": -0.09956376401190237, + "nauc_ndcg_at_3_diff1": 0.07964885582097635, + "nauc_ndcg_at_3_max": 0.04365901517867718, + "nauc_ndcg_at_3_std": -0.1016025363173534, + "nauc_ndcg_at_5_diff1": 0.08005248636871233, + "nauc_ndcg_at_5_max": 0.03877936801579521, + "nauc_ndcg_at_5_std": -0.10294001233544803, + "nauc_precision_at_1000_diff1": -0.09535054122452125, + "nauc_precision_at_1000_max": -0.27129672743481686, + "nauc_precision_at_1000_std": -0.04761543163524454, + "nauc_precision_at_100_diff1": -0.03046694256478702, + "nauc_precision_at_100_max": -0.148647119753794, + "nauc_precision_at_100_std": -0.0728353868619562, + "nauc_precision_at_10_diff1": 0.04298950380943594, + "nauc_precision_at_10_max": 0.0003041395359705056, + "nauc_precision_at_10_std": -0.1001075771396714, + "nauc_precision_at_1_diff1": 0.13935922475361198, + "nauc_precision_at_1_max": 0.03995020889299259, + "nauc_precision_at_1_std": -0.1008863850181277, + "nauc_precision_at_20_diff1": 0.021384743083329435, + "nauc_precision_at_20_max": -0.03192096292812002, + "nauc_precision_at_20_std": -0.08881477114323473, + "nauc_precision_at_3_diff1": 0.04733911750123274, + "nauc_precision_at_3_max": 0.04475026179138858, + "nauc_precision_at_3_std": -0.0994631726192624, + "nauc_precision_at_5_diff1": 0.04857897502836194, + "nauc_precision_at_5_max": 0.03430013525716812, + "nauc_precision_at_5_std": -0.10246855194424888, + "nauc_recall_at_1000_diff1": -0.09535054122451886, + "nauc_recall_at_1000_max": -0.2712967274348162, + "nauc_recall_at_1000_std": -0.047615431635242414, + "nauc_recall_at_100_diff1": -0.030466942564788258, + "nauc_recall_at_100_max": -0.14864711975379435, + "nauc_recall_at_100_std": -0.0728353868619568, + "nauc_recall_at_10_diff1": 0.04298950380943654, + "nauc_recall_at_10_max": 0.0003041395359707412, + "nauc_recall_at_10_std": -0.10010757713967074, + "nauc_recall_at_1_diff1": 0.13935922475361198, + "nauc_recall_at_1_max": 0.03995020889299259, + "nauc_recall_at_1_std": -0.1008863850181277, + "nauc_recall_at_20_diff1": 0.021384743083329785, + "nauc_recall_at_20_max": -0.03192096292811959, + "nauc_recall_at_20_std": -0.08881477114323459, + "nauc_recall_at_3_diff1": 0.04733911750123271, + "nauc_recall_at_3_max": 0.04475026179138868, + "nauc_recall_at_3_std": -0.09946317261926252, + "nauc_recall_at_5_diff1": 0.04857897502836221, + "nauc_recall_at_5_max": 0.034300135257168025, + "nauc_recall_at_5_std": -0.1024685519442486, + "ndcg_at_1": 0.21164, + "ndcg_at_10": 0.358, + "ndcg_at_100": 0.40931, + "ndcg_at_1000": 0.42629, + "ndcg_at_20": 0.37886, + "ndcg_at_3": 0.30779, + "ndcg_at_5": 0.33511, + "precision_at_1": 0.21164, + "precision_at_10": 0.05114, + "precision_at_100": 0.00757, + "precision_at_1000": 0.00089, + "precision_at_20": 0.02968, + "precision_at_3": 0.12495, + "precision_at_5": 0.08814, + "recall_at_1": 0.21164, + "recall_at_10": 0.51143, + "recall_at_100": 0.7568, + "recall_at_1000": 0.89445, + "recall_at_20": 0.59358, + "recall_at_3": 0.37486, + "recall_at_5": 0.4407 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/Quail.json b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/Quail.json new file mode 100644 index 000000000..848bc4917 --- /dev/null +++ b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/Quail.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 464.26184916496277, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.08684, + "map_at_1": 0.03235, + "map_at_10": 0.0648, + "map_at_100": 0.07253, + "map_at_1000": 0.07352, + "map_at_20": 0.06855, + "map_at_3": 0.05092, + "map_at_5": 0.05811, + "mrr_at_1": 0.03235294117647059, + "mrr_at_10": 0.06479545985060688, + "mrr_at_100": 0.07253376394789232, + "mrr_at_1000": 0.07351736690148866, + "mrr_at_20": 0.06855391573314937, + "mrr_at_3": 0.050919117647058795, + "mrr_at_5": 0.058106617647058816, + "nauc_map_at_1000_diff1": 0.10348807579538172, + "nauc_map_at_1000_max": 0.03247965066937991, + "nauc_map_at_1000_std": 0.0005910049024441574, + "nauc_map_at_100_diff1": 0.10389146797942307, + "nauc_map_at_100_max": 0.033016985981717616, + "nauc_map_at_100_std": 0.0010952283866273952, + "nauc_map_at_10_diff1": 0.11284257818896776, + "nauc_map_at_10_max": 0.03207045707675135, + "nauc_map_at_10_std": -0.001499481003068081, + "nauc_map_at_1_diff1": 0.18097360782496275, + "nauc_map_at_1_max": 0.05140315145010598, + "nauc_map_at_1_std": 0.01944654486913667, + "nauc_map_at_20_diff1": 0.10707726763794996, + "nauc_map_at_20_max": 0.034591286677849, + "nauc_map_at_20_std": 0.0019400674934596316, + "nauc_map_at_3_diff1": 0.1411067705432469, + "nauc_map_at_3_max": 0.022071997460880764, + "nauc_map_at_3_std": -0.014333560317157391, + "nauc_map_at_5_diff1": 0.12295474079850716, + "nauc_map_at_5_max": 0.022493939985965435, + "nauc_map_at_5_std": -0.012514194373251712, + "nauc_mrr_at_1000_diff1": 0.10348808816528508, + "nauc_mrr_at_1000_max": 0.03247964706442863, + "nauc_mrr_at_1000_std": 0.0005909991383809265, + "nauc_mrr_at_100_diff1": 0.10389146797942307, + "nauc_mrr_at_100_max": 0.033016985981717616, + "nauc_mrr_at_100_std": 0.0010952283866273952, + "nauc_mrr_at_10_diff1": 0.11284257818896776, + "nauc_mrr_at_10_max": 0.03207045707675135, + "nauc_mrr_at_10_std": -0.001499481003068081, + "nauc_mrr_at_1_diff1": 0.18097360782496275, + "nauc_mrr_at_1_max": 0.05140315145010598, + "nauc_mrr_at_1_std": 0.01944654486913667, + "nauc_mrr_at_20_diff1": 0.10707726763794996, + "nauc_mrr_at_20_max": 0.034591286677849, + "nauc_mrr_at_20_std": 0.0019400674934596316, + "nauc_mrr_at_3_diff1": 0.1411067705432469, + "nauc_mrr_at_3_max": 0.022071997460880764, + "nauc_mrr_at_3_std": -0.014333560317157391, + "nauc_mrr_at_5_diff1": 0.12295474079850716, + "nauc_mrr_at_5_max": 0.022493939985965435, + "nauc_mrr_at_5_std": -0.012514194373251712, + "nauc_ndcg_at_1000_diff1": 0.05662596594310036, + "nauc_ndcg_at_1000_max": 0.018423340563016068, + "nauc_ndcg_at_1000_std": -0.005887484788003341, + "nauc_ndcg_at_100_diff1": 0.06308531940345355, + "nauc_ndcg_at_100_max": 0.030986722640925366, + "nauc_ndcg_at_100_std": 0.007294398294922403, + "nauc_ndcg_at_10_diff1": 0.09176858000444509, + "nauc_ndcg_at_10_max": 0.038370317936614384, + "nauc_ndcg_at_10_std": 0.00509453093410027, + "nauc_ndcg_at_1_diff1": 0.18097360782496275, + "nauc_ndcg_at_1_max": 0.05140315145010598, + "nauc_ndcg_at_1_std": 0.01944654486913667, + "nauc_ndcg_at_20_diff1": 0.07713120880270144, + "nauc_ndcg_at_20_max": 0.04475156318961829, + "nauc_ndcg_at_20_std": 0.014191932887554454, + "nauc_ndcg_at_3_diff1": 0.13306109555314485, + "nauc_ndcg_at_3_max": 0.018076376608458154, + "nauc_ndcg_at_3_std": -0.02015270320874548, + "nauc_ndcg_at_5_diff1": 0.10738024405785034, + "nauc_ndcg_at_5_max": 0.019732064157017976, + "nauc_ndcg_at_5_std": -0.01614708209041563, + "nauc_precision_at_1000_diff1": -0.03139604105101451, + "nauc_precision_at_1000_max": -0.03985743601077482, + "nauc_precision_at_1000_std": -0.0476973860100029, + "nauc_precision_at_100_diff1": 0.007053360768110458, + "nauc_precision_at_100_max": 0.019828772994095002, + "nauc_precision_at_100_std": 0.012551458113179733, + "nauc_precision_at_10_diff1": 0.06091651540720295, + "nauc_precision_at_10_max": 0.050488648984252454, + "nauc_precision_at_10_std": 0.017968986435198002, + "nauc_precision_at_1_diff1": 0.18097360782496275, + "nauc_precision_at_1_max": 0.05140315145010598, + "nauc_precision_at_1_std": 0.01944654486913667, + "nauc_precision_at_20_diff1": 0.03546800807422405, + "nauc_precision_at_20_max": 0.06150323728505408, + "nauc_precision_at_20_std": 0.03471306353272621, + "nauc_precision_at_3_diff1": 0.11740727745557365, + "nauc_precision_at_3_max": 0.010704113434191139, + "nauc_precision_at_3_std": -0.03126612453819339, + "nauc_precision_at_5_diff1": 0.0808269149030581, + "nauc_precision_at_5_max": 0.015891862099889457, + "nauc_precision_at_5_std": -0.02137348958649579, + "nauc_recall_at_1000_diff1": -0.03139604105101441, + "nauc_recall_at_1000_max": -0.03985743601077491, + "nauc_recall_at_1000_std": -0.047697386010002576, + "nauc_recall_at_100_diff1": 0.007053360768110136, + "nauc_recall_at_100_max": 0.01982877299409465, + "nauc_recall_at_100_std": 0.012551458113179346, + "nauc_recall_at_10_diff1": 0.0609165154072027, + "nauc_recall_at_10_max": 0.05048864898425212, + "nauc_recall_at_10_std": 0.017968986435197648, + "nauc_recall_at_1_diff1": 0.18097360782496275, + "nauc_recall_at_1_max": 0.05140315145010598, + "nauc_recall_at_1_std": 0.01944654486913667, + "nauc_recall_at_20_diff1": 0.035468008074223824, + "nauc_recall_at_20_max": 0.06150323728505366, + "nauc_recall_at_20_std": 0.03471306353272607, + "nauc_recall_at_3_diff1": 0.11740727745557361, + "nauc_recall_at_3_max": 0.010704113434191257, + "nauc_recall_at_3_std": -0.03126612453819329, + "nauc_recall_at_5_diff1": 0.08082691490305796, + "nauc_recall_at_5_max": 0.0158918620998893, + "nauc_recall_at_5_std": -0.021373489586495768, + "ndcg_at_1": 0.03235, + "ndcg_at_10": 0.08684, + "ndcg_at_100": 0.13111, + "ndcg_at_1000": 0.1631, + "ndcg_at_20": 0.101, + "ndcg_at_3": 0.05744, + "ndcg_at_5": 0.07051, + "precision_at_1": 0.03235, + "precision_at_10": 0.01592, + "precision_at_100": 0.00381, + "precision_at_1000": 0.00065, + "precision_at_20": 0.01081, + "precision_at_3": 0.02549, + "precision_at_5": 0.02169, + "recall_at_1": 0.03235, + "recall_at_10": 0.15919, + "recall_at_100": 0.38125, + "recall_at_1000": 0.64632, + "recall_at_20": 0.21618, + "recall_at_3": 0.07647, + "recall_at_5": 0.10846 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/RARbCode.json b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/RARbCode.json new file mode 100644 index 000000000..49c18e17e --- /dev/null +++ b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/RARbCode.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 17227.087099075317, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.83141, + "map_at_1": 0.69946, + "map_at_10": 0.79187, + "map_at_100": 0.79398, + "map_at_1000": 0.79402, + "map_at_20": 0.79349, + "map_at_3": 0.77392, + "map_at_5": 0.78767, + "mrr_at_1": 0.6994609164420486, + "mrr_at_10": 0.7918690904034572, + "mrr_at_100": 0.7939781446015942, + "mrr_at_1000": 0.7940182050270139, + "mrr_at_20": 0.7934905053124786, + "mrr_at_3": 0.7739218328840973, + "mrr_at_5": 0.7876684636118605, + "nauc_map_at_1000_diff1": 0.6789058857010448, + "nauc_map_at_1000_max": 0.5355674968103764, + "nauc_map_at_1000_std": 0.047243043284209724, + "nauc_map_at_100_diff1": 0.6789219213923385, + "nauc_map_at_100_max": 0.5356575782751319, + "nauc_map_at_100_std": 0.047368134226580275, + "nauc_map_at_10_diff1": 0.6777457584547923, + "nauc_map_at_10_max": 0.5376459856615491, + "nauc_map_at_10_std": 0.04770595957313594, + "nauc_map_at_1_diff1": 0.7089314763071972, + "nauc_map_at_1_max": 0.5161732522783807, + "nauc_map_at_1_std": 0.02960649292391975, + "nauc_map_at_20_diff1": 0.6784427061154192, + "nauc_map_at_20_max": 0.5361368347899133, + "nauc_map_at_20_std": 0.04782603167458187, + "nauc_map_at_3_diff1": 0.6760707718504894, + "nauc_map_at_3_max": 0.5323224568324469, + "nauc_map_at_3_std": 0.0381282309137976, + "nauc_map_at_5_diff1": 0.6741095292506497, + "nauc_map_at_5_max": 0.5330390002563199, + "nauc_map_at_5_std": 0.045540734181559364, + "nauc_mrr_at_1000_diff1": 0.6789058857010448, + "nauc_mrr_at_1000_max": 0.5355674968103764, + "nauc_mrr_at_1000_std": 0.047243043284209724, + "nauc_mrr_at_100_diff1": 0.6789219213923385, + "nauc_mrr_at_100_max": 0.5356575782751319, + "nauc_mrr_at_100_std": 0.047368134226580275, + "nauc_mrr_at_10_diff1": 0.6777457584547923, + "nauc_mrr_at_10_max": 0.5376459856615491, + "nauc_mrr_at_10_std": 0.04770595957313594, + "nauc_mrr_at_1_diff1": 0.7089314763071972, + "nauc_mrr_at_1_max": 0.5161732522783807, + "nauc_mrr_at_1_std": 0.02960649292391975, + "nauc_mrr_at_20_diff1": 0.6784427061154192, + "nauc_mrr_at_20_max": 0.5361368347899133, + "nauc_mrr_at_20_std": 0.04782603167458187, + "nauc_mrr_at_3_diff1": 0.6760707718504894, + "nauc_mrr_at_3_max": 0.5323224568324469, + "nauc_mrr_at_3_std": 0.0381282309137976, + "nauc_mrr_at_5_diff1": 0.6741095292506497, + "nauc_mrr_at_5_max": 0.5330390002563199, + "nauc_mrr_at_5_std": 0.045540734181559364, + "nauc_ndcg_at_1000_diff1": 0.675193686297541, + "nauc_ndcg_at_1000_max": 0.5419075174496323, + "nauc_ndcg_at_1000_std": 0.05435992834391301, + "nauc_ndcg_at_100_diff1": 0.6755085747076196, + "nauc_ndcg_at_100_max": 0.5447387158430983, + "nauc_ndcg_at_100_std": 0.058219327887824524, + "nauc_ndcg_at_10_diff1": 0.6690173693124819, + "nauc_ndcg_at_10_max": 0.5553508048813397, + "nauc_ndcg_at_10_std": 0.0626198464020488, + "nauc_ndcg_at_1_diff1": 0.7089314763071972, + "nauc_ndcg_at_1_max": 0.5161732522783807, + "nauc_ndcg_at_1_std": 0.02960649292391975, + "nauc_ndcg_at_20_diff1": 0.6715564863950002, + "nauc_ndcg_at_20_max": 0.5494984541349002, + "nauc_ndcg_at_20_std": 0.06298162326905958, + "nauc_ndcg_at_3_diff1": 0.6647803609648824, + "nauc_ndcg_at_3_max": 0.5389209644004442, + "nauc_ndcg_at_3_std": 0.03968068793635892, + "nauc_ndcg_at_5_diff1": 0.6597650514381863, + "nauc_ndcg_at_5_max": 0.5425930370769675, + "nauc_ndcg_at_5_std": 0.056153223300391415, + "nauc_precision_at_1000_diff1": 0.554201706236117, + "nauc_precision_at_1000_max": 1.0, + "nauc_precision_at_1000_std": 1.0, + "nauc_precision_at_100_diff1": 0.6990660747825256, + "nauc_precision_at_100_max": 0.9355509427480959, + "nauc_precision_at_100_std": 0.6103318252784358, + "nauc_precision_at_10_diff1": 0.5854718618421733, + "nauc_precision_at_10_max": 0.7705763290511993, + "nauc_precision_at_10_std": 0.24423257774528845, + "nauc_precision_at_1_diff1": 0.7089314763071972, + "nauc_precision_at_1_max": 0.5161732522783807, + "nauc_precision_at_1_std": 0.02960649292391975, + "nauc_precision_at_20_diff1": 0.5694965043050201, + "nauc_precision_at_20_max": 0.8227526594648089, + "nauc_precision_at_20_std": 0.39289880914651, + "nauc_precision_at_3_diff1": 0.6161565522633383, + "nauc_precision_at_3_max": 0.5679394413617624, + "nauc_precision_at_3_std": 0.04557915168724148, + "nauc_precision_at_5_diff1": 0.5595307580270019, + "nauc_precision_at_5_max": 0.6132103362490371, + "nauc_precision_at_5_std": 0.13649553802217762, + "nauc_recall_at_1000_diff1": 0.5542017062361725, + "nauc_recall_at_1000_max": 1.0, + "nauc_recall_at_1000_std": 1.0, + "nauc_recall_at_100_diff1": 0.699066074782512, + "nauc_recall_at_100_max": 0.9355509427481052, + "nauc_recall_at_100_std": 0.6103318252784216, + "nauc_recall_at_10_diff1": 0.585471861842174, + "nauc_recall_at_10_max": 0.7705763290512004, + "nauc_recall_at_10_std": 0.24423257774529342, + "nauc_recall_at_1_diff1": 0.7089314763071972, + "nauc_recall_at_1_max": 0.5161732522783807, + "nauc_recall_at_1_std": 0.02960649292391975, + "nauc_recall_at_20_diff1": 0.5694965043050141, + "nauc_recall_at_20_max": 0.8227526594648025, + "nauc_recall_at_20_std": 0.39289880914650005, + "nauc_recall_at_3_diff1": 0.6161565522633389, + "nauc_recall_at_3_max": 0.56793944136176, + "nauc_recall_at_3_std": 0.0455791516872424, + "nauc_recall_at_5_diff1": 0.5595307580270028, + "nauc_recall_at_5_max": 0.6132103362490359, + "nauc_recall_at_5_std": 0.1364955380221769, + "ndcg_at_1": 0.69946, + "ndcg_at_10": 0.83141, + "ndcg_at_100": 0.84035, + "ndcg_at_1000": 0.84138, + "ndcg_at_20": 0.83702, + "ndcg_at_3": 0.79711, + "ndcg_at_5": 0.8217, + "precision_at_1": 0.69946, + "precision_at_10": 0.09522, + "precision_at_100": 0.00991, + "precision_at_1000": 0.001, + "precision_at_20": 0.04869, + "precision_at_3": 0.28796, + "precision_at_5": 0.18464, + "recall_at_1": 0.69946, + "recall_at_10": 0.95216, + "recall_at_100": 0.99124, + "recall_at_1000": 0.99933, + "recall_at_20": 0.97372, + "recall_at_3": 0.86388, + "recall_at_5": 0.92318 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/RARbMath.json b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/RARbMath.json new file mode 100644 index 000000000..bbf3774ad --- /dev/null +++ b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/RARbMath.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 24633.75252223015, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.83007, + "map_at_1": 0.77639, + "map_at_10": 0.81186, + "map_at_100": 0.81532, + "map_at_1000": 0.81544, + "map_at_20": 0.81384, + "map_at_3": 0.80308, + "map_at_5": 0.80743, + "mrr_at_1": 0.7763886690932109, + "mrr_at_10": 0.8118631891222496, + "mrr_at_100": 0.8153151693693366, + "mrr_at_1000": 0.815443393552917, + "mrr_at_20": 0.8138388529799246, + "mrr_at_3": 0.8030806562219768, + "mrr_at_5": 0.8074326106451445, + "nauc_map_at_1000_diff1": 0.904643121690942, + "nauc_map_at_1000_max": 0.5102325809317898, + "nauc_map_at_1000_std": -0.32751126741873926, + "nauc_map_at_100_diff1": 0.9046060334475071, + "nauc_map_at_100_max": 0.5102733800874338, + "nauc_map_at_100_std": -0.3274944377816662, + "nauc_map_at_10_diff1": 0.9043750582066331, + "nauc_map_at_10_max": 0.509568831778044, + "nauc_map_at_10_std": -0.330093842670501, + "nauc_map_at_1_diff1": 0.9147341168158755, + "nauc_map_at_1_max": 0.5163131958441465, + "nauc_map_at_1_std": -0.3093363438609314, + "nauc_map_at_20_diff1": 0.9043863642994707, + "nauc_map_at_20_max": 0.5101071582019623, + "nauc_map_at_20_std": -0.32882719778698916, + "nauc_map_at_3_diff1": 0.9057820950868172, + "nauc_map_at_3_max": 0.5075592924064316, + "nauc_map_at_3_std": -0.3280597012970142, + "nauc_map_at_5_diff1": 0.9049783701788269, + "nauc_map_at_5_max": 0.5069436834560236, + "nauc_map_at_5_std": -0.33068571488369386, + "nauc_mrr_at_1000_diff1": 0.904643121690942, + "nauc_mrr_at_1000_max": 0.5102325809317898, + "nauc_mrr_at_1000_std": -0.32751126741873926, + "nauc_mrr_at_100_diff1": 0.9046060334475071, + "nauc_mrr_at_100_max": 0.5102733800874338, + "nauc_mrr_at_100_std": -0.3274944377816662, + "nauc_mrr_at_10_diff1": 0.9043750582066331, + "nauc_mrr_at_10_max": 0.509568831778044, + "nauc_mrr_at_10_std": -0.330093842670501, + "nauc_mrr_at_1_diff1": 0.9147341168158755, + "nauc_mrr_at_1_max": 0.5163131958441465, + "nauc_mrr_at_1_std": -0.3093363438609314, + "nauc_mrr_at_20_diff1": 0.9043863642994707, + "nauc_mrr_at_20_max": 0.5101071582019623, + "nauc_mrr_at_20_std": -0.32882719778698916, + "nauc_mrr_at_3_diff1": 0.9057820950868172, + "nauc_mrr_at_3_max": 0.5075592924064316, + "nauc_mrr_at_3_std": -0.3280597012970142, + "nauc_mrr_at_5_diff1": 0.9049783701788269, + "nauc_mrr_at_5_max": 0.5069436834560236, + "nauc_mrr_at_5_std": -0.33068571488369386, + "nauc_ndcg_at_1000_diff1": 0.9019422906149392, + "nauc_ndcg_at_1000_max": 0.5116386748040189, + "nauc_ndcg_at_1000_std": -0.3258761578408881, + "nauc_ndcg_at_100_diff1": 0.9007897585718183, + "nauc_ndcg_at_100_max": 0.5131222838710497, + "nauc_ndcg_at_100_std": -0.32431524556635766, + "nauc_ndcg_at_10_diff1": 0.8994052408457824, + "nauc_ndcg_at_10_max": 0.5090373067991469, + "nauc_ndcg_at_10_std": -0.3392396130180596, + "nauc_ndcg_at_1_diff1": 0.9147341168158755, + "nauc_ndcg_at_1_max": 0.5163131958441465, + "nauc_ndcg_at_1_std": -0.3093363438609314, + "nauc_ndcg_at_20_diff1": 0.8994269348930599, + "nauc_ndcg_at_20_max": 0.5114629526730767, + "nauc_ndcg_at_20_std": -0.33476106823119767, + "nauc_ndcg_at_3_diff1": 0.9029803804373436, + "nauc_ndcg_at_3_max": 0.5038209042987358, + "nauc_ndcg_at_3_std": -0.3352867449055076, + "nauc_ndcg_at_5_diff1": 0.9012885247550737, + "nauc_ndcg_at_5_max": 0.5024272825594533, + "nauc_ndcg_at_5_std": -0.3405222120618805, + "nauc_precision_at_1000_diff1": 0.8119246766606026, + "nauc_precision_at_1000_max": 0.7516231939294363, + "nauc_precision_at_1000_std": 0.4211764018328688, + "nauc_precision_at_100_diff1": 0.8430669901649576, + "nauc_precision_at_100_max": 0.6065339042022491, + "nauc_precision_at_100_std": -0.1436360495602589, + "nauc_precision_at_10_diff1": 0.8752318037915061, + "nauc_precision_at_10_max": 0.5098653218714272, + "nauc_precision_at_10_std": -0.3811788893098281, + "nauc_precision_at_1_diff1": 0.9147341168158755, + "nauc_precision_at_1_max": 0.5163131958441465, + "nauc_precision_at_1_std": -0.3093363438609314, + "nauc_precision_at_20_diff1": 0.8684902391562105, + "nauc_precision_at_20_max": 0.5285227034601157, + "nauc_precision_at_20_std": -0.3631968746773363, + "nauc_precision_at_3_diff1": 0.8937225878421171, + "nauc_precision_at_3_max": 0.491053553450138, + "nauc_precision_at_3_std": -0.3597347121906108, + "nauc_precision_at_5_diff1": 0.88752535673639, + "nauc_precision_at_5_max": 0.48525083632299715, + "nauc_precision_at_5_std": -0.377837938530851, + "nauc_recall_at_1000_diff1": 0.8119246766606091, + "nauc_recall_at_1000_max": 0.7516231939294187, + "nauc_recall_at_1000_std": 0.42117640183295163, + "nauc_recall_at_100_diff1": 0.8430669901649563, + "nauc_recall_at_100_max": 0.6065339042022442, + "nauc_recall_at_100_std": -0.14363604956025697, + "nauc_recall_at_10_diff1": 0.8752318037915056, + "nauc_recall_at_10_max": 0.5098653218714282, + "nauc_recall_at_10_std": -0.3811788893098262, + "nauc_recall_at_1_diff1": 0.9147341168158755, + "nauc_recall_at_1_max": 0.5163131958441465, + "nauc_recall_at_1_std": -0.3093363438609314, + "nauc_recall_at_20_diff1": 0.8684902391562105, + "nauc_recall_at_20_max": 0.5285227034601169, + "nauc_recall_at_20_std": -0.3631968746773327, + "nauc_recall_at_3_diff1": 0.8937225878421174, + "nauc_recall_at_3_max": 0.49105355345013824, + "nauc_recall_at_3_std": -0.3597347121906103, + "nauc_recall_at_5_diff1": 0.8875253567363908, + "nauc_recall_at_5_max": 0.4852508363229974, + "nauc_recall_at_5_std": -0.37783793853084763, + "ndcg_at_1": 0.77639, + "ndcg_at_10": 0.83007, + "ndcg_at_100": 0.8476, + "ndcg_at_1000": 0.85075, + "ndcg_at_20": 0.83719, + "ndcg_at_3": 0.81134, + "ndcg_at_5": 0.8192, + "precision_at_1": 0.77639, + "precision_at_10": 0.08881, + "precision_at_100": 0.00972, + "precision_at_1000": 0.001, + "precision_at_20": 0.04581, + "precision_at_3": 0.27837, + "precision_at_5": 0.17085, + "recall_at_1": 0.77639, + "recall_at_10": 0.88812, + "recall_at_100": 0.97167, + "recall_at_1000": 0.99589, + "recall_at_20": 0.91613, + "recall_at_3": 0.8351, + "recall_at_5": 0.85425 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/SIQA.json b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/SIQA.json new file mode 100644 index 000000000..e12729885 --- /dev/null +++ b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/SIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 292.49882316589355, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.05734, + "map_at_1": 0.03019, + "map_at_10": 0.04707, + "map_at_100": 0.05135, + "map_at_1000": 0.05239, + "map_at_20": 0.04914, + "map_at_3": 0.0406, + "map_at_5": 0.04426, + "mrr_at_1": 0.030194472876151485, + "mrr_at_10": 0.047071331091290164, + "mrr_at_100": 0.051346198411670915, + "mrr_at_1000": 0.05239237634579249, + "mrr_at_20": 0.04913744179561145, + "mrr_at_3": 0.04060047765267828, + "mrr_at_5": 0.044259638348686466, + "nauc_map_at_1000_diff1": 0.2333386045702445, + "nauc_map_at_1000_max": -0.011994326331843585, + "nauc_map_at_1000_std": -0.13111886243532936, + "nauc_map_at_100_diff1": 0.23430562976590083, + "nauc_map_at_100_max": -0.012500379195010607, + "nauc_map_at_100_std": -0.1323684624271175, + "nauc_map_at_10_diff1": 0.24950158794155106, + "nauc_map_at_10_max": -0.006508651598278288, + "nauc_map_at_10_std": -0.13907436608458792, + "nauc_map_at_1_diff1": 0.3626663876284205, + "nauc_map_at_1_max": -0.029829308178159528, + "nauc_map_at_1_std": -0.17830856814913684, + "nauc_map_at_20_diff1": 0.24105173489823353, + "nauc_map_at_20_max": -0.010270625758449484, + "nauc_map_at_20_std": -0.13526865946273767, + "nauc_map_at_3_diff1": 0.28126253892141323, + "nauc_map_at_3_max": -0.021645195296666992, + "nauc_map_at_3_std": -0.158266727302491, + "nauc_map_at_5_diff1": 0.2657064325580696, + "nauc_map_at_5_max": -0.016199163759814263, + "nauc_map_at_5_std": -0.1570351101875909, + "nauc_mrr_at_1000_diff1": 0.2333386045702445, + "nauc_mrr_at_1000_max": -0.011994326331843585, + "nauc_mrr_at_1000_std": -0.13111886243532936, + "nauc_mrr_at_100_diff1": 0.23430562976590083, + "nauc_mrr_at_100_max": -0.012500379195010607, + "nauc_mrr_at_100_std": -0.1323684624271175, + "nauc_mrr_at_10_diff1": 0.24950158794155106, + "nauc_mrr_at_10_max": -0.006508651598278288, + "nauc_mrr_at_10_std": -0.13907436608458792, + "nauc_mrr_at_1_diff1": 0.3626663876284205, + "nauc_mrr_at_1_max": -0.029829308178159528, + "nauc_mrr_at_1_std": -0.17830856814913684, + "nauc_mrr_at_20_diff1": 0.24105173489823353, + "nauc_mrr_at_20_max": -0.010270625758449484, + "nauc_mrr_at_20_std": -0.13526865946273767, + "nauc_mrr_at_3_diff1": 0.28126253892141323, + "nauc_mrr_at_3_max": -0.021645195296666992, + "nauc_mrr_at_3_std": -0.158266727302491, + "nauc_mrr_at_5_diff1": 0.2657064325580696, + "nauc_mrr_at_5_max": -0.016199163759814263, + "nauc_mrr_at_5_std": -0.1570351101875909, + "nauc_ndcg_at_1000_diff1": 0.135983361709533, + "nauc_ndcg_at_1000_max": -0.007874991412648908, + "nauc_ndcg_at_1000_std": -0.07111080026121672, + "nauc_ndcg_at_100_diff1": 0.15761389150961444, + "nauc_ndcg_at_100_max": -0.014261577357317628, + "nauc_ndcg_at_100_std": -0.09644486335521416, + "nauc_ndcg_at_10_diff1": 0.21073427960910485, + "nauc_ndcg_at_10_max": 0.007452710685603831, + "nauc_ndcg_at_10_std": -0.11809567304173556, + "nauc_ndcg_at_1_diff1": 0.3626663876284205, + "nauc_ndcg_at_1_max": -0.029829308178159528, + "nauc_ndcg_at_1_std": -0.17830856814913684, + "nauc_ndcg_at_20_diff1": 0.18912293863818974, + "nauc_ndcg_at_20_max": -0.005152002524504787, + "nauc_ndcg_at_20_std": -0.10894611894713616, + "nauc_ndcg_at_3_diff1": 0.26229327866786883, + "nauc_ndcg_at_3_max": -0.01881326444249619, + "nauc_ndcg_at_3_std": -0.15352241440612174, + "nauc_ndcg_at_5_diff1": 0.24002096898844613, + "nauc_ndcg_at_5_max": -0.009874268450781664, + "nauc_ndcg_at_5_std": -0.15199670587938025, + "nauc_precision_at_1000_diff1": -0.0032246308029948234, + "nauc_precision_at_1000_max": -0.004034382579987737, + "nauc_precision_at_1000_std": 0.026170568801908985, + "nauc_precision_at_100_diff1": 0.059433947672312464, + "nauc_precision_at_100_max": -0.02073211423345185, + "nauc_precision_at_100_std": -0.050488038809699765, + "nauc_precision_at_10_diff1": 0.14448576786956746, + "nauc_precision_at_10_max": 0.03227529971820231, + "nauc_precision_at_10_std": -0.08006144766225269, + "nauc_precision_at_1_diff1": 0.3626663876284205, + "nauc_precision_at_1_max": -0.029829308178159528, + "nauc_precision_at_1_std": -0.17830856814913684, + "nauc_precision_at_20_diff1": 0.10816446154844202, + "nauc_precision_at_20_max": -0.001297126482058222, + "nauc_precision_at_20_std": -0.0668333267286286, + "nauc_precision_at_3_diff1": 0.22063125375258028, + "nauc_precision_at_3_max": -0.012371405006896657, + "nauc_precision_at_3_std": -0.14308474017470527, + "nauc_precision_at_5_diff1": 0.19053443842992812, + "nauc_precision_at_5_max": 0.003110395924499442, + "nauc_precision_at_5_std": -0.1424386428199352, + "nauc_recall_at_1000_diff1": -0.0032246308029942983, + "nauc_recall_at_1000_max": -0.004034382579986916, + "nauc_recall_at_1000_std": 0.02617056880190989, + "nauc_recall_at_100_diff1": 0.05943394767231228, + "nauc_recall_at_100_max": -0.020732114233451965, + "nauc_recall_at_100_std": -0.05048803880969979, + "nauc_recall_at_10_diff1": 0.14448576786956724, + "nauc_recall_at_10_max": 0.032275299718202255, + "nauc_recall_at_10_std": -0.08006144766225286, + "nauc_recall_at_1_diff1": 0.3626663876284205, + "nauc_recall_at_1_max": -0.029829308178159528, + "nauc_recall_at_1_std": -0.17830856814913684, + "nauc_recall_at_20_diff1": 0.10816446154844193, + "nauc_recall_at_20_max": -0.0012971264820582841, + "nauc_recall_at_20_std": -0.0668333267286286, + "nauc_recall_at_3_diff1": 0.2206312537525804, + "nauc_recall_at_3_max": -0.012371405006896615, + "nauc_recall_at_3_std": -0.14308474017470513, + "nauc_recall_at_5_diff1": 0.19053443842992812, + "nauc_recall_at_5_max": 0.003110395924499358, + "nauc_recall_at_5_std": -0.14243864281993524, + "ndcg_at_1": 0.03019, + "ndcg_at_10": 0.05734, + "ndcg_at_100": 0.08291, + "ndcg_at_1000": 0.11872, + "ndcg_at_20": 0.06476, + "ndcg_at_3": 0.04398, + "ndcg_at_5": 0.05054, + "precision_at_1": 0.03019, + "precision_at_10": 0.00906, + "precision_at_100": 0.00222, + "precision_at_1000": 0.00052, + "precision_at_20": 0.00599, + "precision_at_3": 0.01791, + "precision_at_5": 0.01392, + "recall_at_1": 0.03019, + "recall_at_10": 0.09058, + "recall_at_100": 0.22211, + "recall_at_1000": 0.52149, + "recall_at_20": 0.11975, + "recall_at_3": 0.05374, + "recall_at_5": 0.0696 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/SpartQA.json b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/SpartQA.json new file mode 100644 index 000000000..1119602c9 --- /dev/null +++ b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/SpartQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 201.9166955947876, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.0156, + "map_at_1": 0.00232, + "map_at_10": 0.00852, + "map_at_100": 0.01471, + "map_at_1000": 0.01623, + "map_at_20": 0.01028, + "map_at_3": 0.00532, + "map_at_5": 0.00656, + "mrr_at_1": 0.004173622704507512, + "mrr_at_10": 0.015281531829945875, + "mrr_at_100": 0.023826751152137417, + "mrr_at_1000": 0.025389361100729792, + "mrr_at_20": 0.0183342927648776, + "mrr_at_3": 0.00936746429233908, + "mrr_at_5": 0.011857725839361902, + "nauc_map_at_1000_diff1": -0.04129208517136304, + "nauc_map_at_1000_max": 0.24429510802397328, + "nauc_map_at_1000_std": 0.3708435706695593, + "nauc_map_at_100_diff1": -0.04307952431865895, + "nauc_map_at_100_max": 0.23790310667189693, + "nauc_map_at_100_std": 0.3593511305480817, + "nauc_map_at_10_diff1": -0.06502254024290464, + "nauc_map_at_10_max": 0.25751813512120303, + "nauc_map_at_10_std": 0.33769971431293583, + "nauc_map_at_1_diff1": -0.11491950575124972, + "nauc_map_at_1_max": 0.3613800919258028, + "nauc_map_at_1_std": 0.348285572105651, + "nauc_map_at_20_diff1": -0.06571738124657214, + "nauc_map_at_20_max": 0.2510572744778845, + "nauc_map_at_20_std": 0.335590550208877, + "nauc_map_at_3_diff1": -0.049925071747528936, + "nauc_map_at_3_max": 0.24767429726304427, + "nauc_map_at_3_std": 0.31142033388211504, + "nauc_map_at_5_diff1": -0.044395974906536725, + "nauc_map_at_5_max": 0.25968493571139434, + "nauc_map_at_5_std": 0.3212632207808508, + "nauc_mrr_at_1000_diff1": -0.034449776505730195, + "nauc_mrr_at_1000_max": 0.2167742965434266, + "nauc_mrr_at_1000_std": 0.3411069534033563, + "nauc_mrr_at_100_diff1": -0.03575903266703338, + "nauc_mrr_at_100_max": 0.2135607085774618, + "nauc_mrr_at_100_std": 0.3366212018492373, + "nauc_mrr_at_10_diff1": -0.050183630266621954, + "nauc_mrr_at_10_max": 0.2131288702703527, + "nauc_mrr_at_10_std": 0.3181217086150279, + "nauc_mrr_at_1_diff1": -0.14063437186686895, + "nauc_mrr_at_1_max": 0.2617234178690383, + "nauc_mrr_at_1_std": 0.26698754271430214, + "nauc_mrr_at_20_diff1": -0.04580602575804512, + "nauc_mrr_at_20_max": 0.21556849132160755, + "nauc_mrr_at_20_std": 0.31593697904060164, + "nauc_mrr_at_3_diff1": -0.050970682366141794, + "nauc_mrr_at_3_max": 0.18709408405146047, + "nauc_mrr_at_3_std": 0.30079469947965853, + "nauc_mrr_at_5_diff1": -0.03901274900713443, + "nauc_mrr_at_5_max": 0.2073307304530377, + "nauc_mrr_at_5_std": 0.3035310649289242, + "nauc_ndcg_at_1000_diff1": -0.001959753651394292, + "nauc_ndcg_at_1000_max": 0.27669880634157895, + "nauc_ndcg_at_1000_std": 0.4802283619860673, + "nauc_ndcg_at_100_diff1": -0.011026586020262963, + "nauc_ndcg_at_100_max": 0.21678915229477305, + "nauc_ndcg_at_100_std": 0.3880394963487701, + "nauc_ndcg_at_10_diff1": -0.06345163039885018, + "nauc_ndcg_at_10_max": 0.2430892874222927, + "nauc_ndcg_at_10_std": 0.3438566387966649, + "nauc_ndcg_at_1_diff1": -0.14063437186686895, + "nauc_ndcg_at_1_max": 0.2617234178690383, + "nauc_ndcg_at_1_std": 0.26698754271430214, + "nauc_ndcg_at_20_diff1": -0.05927260848217137, + "nauc_ndcg_at_20_max": 0.23626224228151887, + "nauc_ndcg_at_20_std": 0.3381966301818091, + "nauc_ndcg_at_3_diff1": -0.047949102781489006, + "nauc_ndcg_at_3_max": 0.2137194994539658, + "nauc_ndcg_at_3_std": 0.30795093055996947, + "nauc_ndcg_at_5_diff1": -0.03829838701534693, + "nauc_ndcg_at_5_max": 0.2372567052769276, + "nauc_ndcg_at_5_std": 0.3194122148164323, + "nauc_precision_at_1000_diff1": 0.034294600814221095, + "nauc_precision_at_1000_max": 0.22252579427404953, + "nauc_precision_at_1000_std": 0.37361868248929314, + "nauc_precision_at_100_diff1": -0.009302489088048635, + "nauc_precision_at_100_max": 0.20440647254264743, + "nauc_precision_at_100_std": 0.41428598169593556, + "nauc_precision_at_10_diff1": -0.05013082613319985, + "nauc_precision_at_10_max": 0.2195164794382872, + "nauc_precision_at_10_std": 0.34623124819155926, + "nauc_precision_at_1_diff1": -0.14063437186686895, + "nauc_precision_at_1_max": 0.2617234178690383, + "nauc_precision_at_1_std": 0.26698754271430214, + "nauc_precision_at_20_diff1": -0.038352684213515405, + "nauc_precision_at_20_max": 0.21667517255320032, + "nauc_precision_at_20_std": 0.3314648487099529, + "nauc_precision_at_3_diff1": -0.04127252066582855, + "nauc_precision_at_3_max": 0.1573526503349079, + "nauc_precision_at_3_std": 0.3168889960877855, + "nauc_precision_at_5_diff1": -0.022972482748758436, + "nauc_precision_at_5_max": 0.20773725311408273, + "nauc_precision_at_5_std": 0.3172416708687197, + "nauc_recall_at_1000_diff1": 0.012067758736875038, + "nauc_recall_at_1000_max": 0.23127185039324394, + "nauc_recall_at_1000_std": 0.41744480140906864, + "nauc_recall_at_100_diff1": 0.012233500849735957, + "nauc_recall_at_100_max": 0.18856092918908285, + "nauc_recall_at_100_std": 0.3554380422652705, + "nauc_recall_at_10_diff1": -0.07511712873219044, + "nauc_recall_at_10_max": 0.25665499759585997, + "nauc_recall_at_10_std": 0.3633123335874682, + "nauc_recall_at_1_diff1": -0.11491950575124972, + "nauc_recall_at_1_max": 0.3613800919258028, + "nauc_recall_at_1_std": 0.348285572105651, + "nauc_recall_at_20_diff1": -0.06756181993124624, + "nauc_recall_at_20_max": 0.24218240440550656, + "nauc_recall_at_20_std": 0.3513732830890718, + "nauc_recall_at_3_diff1": -0.0473974638829585, + "nauc_recall_at_3_max": 0.20212365910029248, + "nauc_recall_at_3_std": 0.3040176106592407, + "nauc_recall_at_5_diff1": -0.037834323604581284, + "nauc_recall_at_5_max": 0.24171534734075198, + "nauc_recall_at_5_std": 0.3293309398773487, + "ndcg_at_1": 0.00417, + "ndcg_at_10": 0.0156, + "ndcg_at_100": 0.06035, + "ndcg_at_1000": 0.11354, + "ndcg_at_20": 0.02315, + "ndcg_at_3": 0.00734, + "ndcg_at_5": 0.01006, + "precision_at_1": 0.00417, + "precision_at_10": 0.00543, + "precision_at_100": 0.00389, + "precision_at_1000": 0.00108, + "precision_at_20": 0.00501, + "precision_at_3": 0.00547, + "precision_at_5": 0.00551, + "recall_at_1": 0.00232, + "recall_at_10": 0.02977, + "recall_at_100": 0.24402, + "recall_at_1000": 0.633, + "recall_at_20": 0.05602, + "recall_at_3": 0.00937, + "recall_at_5": 0.01493 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL1.json b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL1.json new file mode 100644 index 000000000..eae065039 --- /dev/null +++ b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL1.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 76.46292352676392, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02565, + "map_at_1": 0.00375, + "map_at_10": 0.01596, + "map_at_100": 0.02191, + "map_at_1000": 0.02395, + "map_at_20": 0.0181, + "map_at_3": 0.00971, + "map_at_5": 0.01233, + "mrr_at_1": 0.00375, + "mrr_at_10": 0.01595942460317464, + "mrr_at_100": 0.021906446847129883, + "mrr_at_1000": 0.023946770088631116, + "mrr_at_20": 0.018103135112007056, + "mrr_at_3": 0.009708333333333336, + "mrr_at_5": 0.01233333333333334, + "nauc_map_at_1000_diff1": 0.11459106749524707, + "nauc_map_at_1000_max": 0.39597161980769324, + "nauc_map_at_1000_std": 0.3285747483427571, + "nauc_map_at_100_diff1": 0.11489842107639558, + "nauc_map_at_100_max": 0.396974619441942, + "nauc_map_at_100_std": 0.3242119702248437, + "nauc_map_at_10_diff1": 0.12782258877671232, + "nauc_map_at_10_max": 0.42023857391551495, + "nauc_map_at_10_std": 0.3511222030710249, + "nauc_map_at_1_diff1": -0.009856005723996135, + "nauc_map_at_1_max": 0.28473302924604244, + "nauc_map_at_1_std": 0.4949110097486809, + "nauc_map_at_20_diff1": 0.12613276490555048, + "nauc_map_at_20_max": 0.41337770265530943, + "nauc_map_at_20_std": 0.33614168361579944, + "nauc_map_at_3_diff1": 0.17022055732958993, + "nauc_map_at_3_max": 0.43519681802321775, + "nauc_map_at_3_std": 0.4040219210010237, + "nauc_map_at_5_diff1": 0.11816465311568629, + "nauc_map_at_5_max": 0.433817685407436, + "nauc_map_at_5_std": 0.3705523607857927, + "nauc_mrr_at_1000_diff1": 0.11459104807745335, + "nauc_mrr_at_1000_max": 0.3959716065608215, + "nauc_mrr_at_1000_std": 0.32857462654843944, + "nauc_mrr_at_100_diff1": 0.11489842107639558, + "nauc_mrr_at_100_max": 0.396974619441942, + "nauc_mrr_at_100_std": 0.3242119702248437, + "nauc_mrr_at_10_diff1": 0.12782258877671232, + "nauc_mrr_at_10_max": 0.42023857391551495, + "nauc_mrr_at_10_std": 0.3511222030710249, + "nauc_mrr_at_1_diff1": -0.009856005723996135, + "nauc_mrr_at_1_max": 0.28473302924604244, + "nauc_mrr_at_1_std": 0.4949110097486809, + "nauc_mrr_at_20_diff1": 0.12613276490555048, + "nauc_mrr_at_20_max": 0.41337770265530943, + "nauc_mrr_at_20_std": 0.33614168361579944, + "nauc_mrr_at_3_diff1": 0.17022055732958993, + "nauc_mrr_at_3_max": 0.43519681802321775, + "nauc_mrr_at_3_std": 0.4040219210010237, + "nauc_mrr_at_5_diff1": 0.11816465311568629, + "nauc_mrr_at_5_max": 0.433817685407436, + "nauc_mrr_at_5_std": 0.3705523607857927, + "nauc_ndcg_at_1000_diff1": 0.09403556210196658, + "nauc_ndcg_at_1000_max": 0.3706008409856427, + "nauc_ndcg_at_1000_std": 0.3350279481541897, + "nauc_ndcg_at_100_diff1": 0.09909572132716206, + "nauc_ndcg_at_100_max": 0.34945440229840863, + "nauc_ndcg_at_100_std": 0.2756963308155084, + "nauc_ndcg_at_10_diff1": 0.13241738889799878, + "nauc_ndcg_at_10_max": 0.4174460967555005, + "nauc_ndcg_at_10_std": 0.3248845141513829, + "nauc_ndcg_at_1_diff1": -0.009856005723996135, + "nauc_ndcg_at_1_max": 0.28473302924604244, + "nauc_ndcg_at_1_std": 0.4949110097486809, + "nauc_ndcg_at_20_diff1": 0.1275982971990755, + "nauc_ndcg_at_20_max": 0.40187549124043614, + "nauc_ndcg_at_20_std": 0.3013702953060811, + "nauc_ndcg_at_3_diff1": 0.18797349313074962, + "nauc_ndcg_at_3_max": 0.4438933906883564, + "nauc_ndcg_at_3_std": 0.38525994296144445, + "nauc_ndcg_at_5_diff1": 0.11389580923755961, + "nauc_ndcg_at_5_max": 0.4395894480363315, + "nauc_ndcg_at_5_std": 0.345900625919815, + "nauc_precision_at_1000_diff1": 0.056639460386804494, + "nauc_precision_at_1000_max": 0.3879473396594881, + "nauc_precision_at_1000_std": 0.43248095780169604, + "nauc_precision_at_100_diff1": 0.08797229607236777, + "nauc_precision_at_100_max": 0.3132540893466628, + "nauc_precision_at_100_std": 0.24866918337037622, + "nauc_precision_at_10_diff1": 0.13699474084830446, + "nauc_precision_at_10_max": 0.41269197861332063, + "nauc_precision_at_10_std": 0.3003324539291633, + "nauc_precision_at_1_diff1": -0.009856005723996135, + "nauc_precision_at_1_max": 0.28473302924604244, + "nauc_precision_at_1_std": 0.4949110097486809, + "nauc_precision_at_20_diff1": 0.12798646513430514, + "nauc_precision_at_20_max": 0.3893055182899561, + "nauc_precision_at_20_std": 0.2740333303520854, + "nauc_precision_at_3_diff1": 0.21545478937483226, + "nauc_precision_at_3_max": 0.4560638583310974, + "nauc_precision_at_3_std": 0.3541536237068836, + "nauc_precision_at_5_diff1": 0.10499128548655842, + "nauc_precision_at_5_max": 0.4454457930207233, + "nauc_precision_at_5_std": 0.3131881139898943, + "nauc_recall_at_1000_diff1": 0.05663946038680669, + "nauc_recall_at_1000_max": 0.3879473396594892, + "nauc_recall_at_1000_std": 0.4324809578016973, + "nauc_recall_at_100_diff1": 0.08797229607236756, + "nauc_recall_at_100_max": 0.3132540893466629, + "nauc_recall_at_100_std": 0.24866918337037613, + "nauc_recall_at_10_diff1": 0.13699474084830449, + "nauc_recall_at_10_max": 0.4126919786133204, + "nauc_recall_at_10_std": 0.30033245392916336, + "nauc_recall_at_1_diff1": -0.009856005723996135, + "nauc_recall_at_1_max": 0.28473302924604244, + "nauc_recall_at_1_std": 0.4949110097486809, + "nauc_recall_at_20_diff1": 0.12798646513430514, + "nauc_recall_at_20_max": 0.3893055182899562, + "nauc_recall_at_20_std": 0.2740333303520853, + "nauc_recall_at_3_diff1": 0.21545478937483245, + "nauc_recall_at_3_max": 0.45606385833109747, + "nauc_recall_at_3_std": 0.35415362370688386, + "nauc_recall_at_5_diff1": 0.10499128548655848, + "nauc_recall_at_5_max": 0.44544579302072324, + "nauc_recall_at_5_std": 0.31318811398989427, + "ndcg_at_1": 0.00375, + "ndcg_at_10": 0.02565, + "ndcg_at_100": 0.06512, + "ndcg_at_1000": 0.13303, + "ndcg_at_20": 0.03361, + "ndcg_at_3": 0.01182, + "ndcg_at_5": 0.01661, + "precision_at_1": 0.00375, + "precision_at_10": 0.00583, + "precision_at_100": 0.00268, + "precision_at_1000": 0.00083, + "precision_at_20": 0.0045, + "precision_at_3": 0.006, + "precision_at_5": 0.00595, + "recall_at_1": 0.00375, + "recall_at_10": 0.05825, + "recall_at_100": 0.26825, + "recall_at_1000": 0.83175, + "recall_at_20": 0.09, + "recall_at_3": 0.018, + "recall_at_5": 0.02975 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL2Fact.json b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL2Fact.json new file mode 100644 index 000000000..2a00e52e7 --- /dev/null +++ b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL2Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 676.9670875072479, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.48248, + "map_at_1": 0.24569, + "map_at_10": 0.40162, + "map_at_100": 0.41099, + "map_at_1000": 0.41121, + "map_at_20": 0.40791, + "map_at_3": 0.3606, + "map_at_5": 0.38535, + "mrr_at_1": 0.24569205113952194, + "mrr_at_10": 0.4016195064277317, + "mrr_at_100": 0.4109883690888079, + "mrr_at_1000": 0.4112090634212447, + "mrr_at_20": 0.40790944790541417, + "mrr_at_3": 0.36060156877277216, + "mrr_at_5": 0.38534679760360585, + "nauc_map_at_1000_diff1": 0.14280539427472336, + "nauc_map_at_1000_max": 0.05943649344213885, + "nauc_map_at_1000_std": -0.1497006806704932, + "nauc_map_at_100_diff1": 0.14269535590684762, + "nauc_map_at_100_max": 0.05955791630308128, + "nauc_map_at_100_std": -0.14940111519291072, + "nauc_map_at_10_diff1": 0.14304519699373347, + "nauc_map_at_10_max": 0.061299507868574306, + "nauc_map_at_10_std": -0.15449188767848673, + "nauc_map_at_1_diff1": 0.1769532326495871, + "nauc_map_at_1_max": 0.03874006739507716, + "nauc_map_at_1_std": -0.13131553097620585, + "nauc_map_at_20_diff1": 0.14217933478368233, + "nauc_map_at_20_max": 0.06112015047173461, + "nauc_map_at_20_std": -0.14996758119028614, + "nauc_map_at_3_diff1": 0.14530305887422637, + "nauc_map_at_3_max": 0.05363488541802073, + "nauc_map_at_3_std": -0.16101565701587667, + "nauc_map_at_5_diff1": 0.14411778925430968, + "nauc_map_at_5_max": 0.05974922860828305, + "nauc_map_at_5_std": -0.16030093306951568, + "nauc_mrr_at_1000_diff1": 0.14280539427472336, + "nauc_mrr_at_1000_max": 0.05943649344213885, + "nauc_mrr_at_1000_std": -0.1497006806704932, + "nauc_mrr_at_100_diff1": 0.14269535590684762, + "nauc_mrr_at_100_max": 0.05955791630308128, + "nauc_mrr_at_100_std": -0.14940111519291072, + "nauc_mrr_at_10_diff1": 0.14304519699373347, + "nauc_mrr_at_10_max": 0.061299507868574306, + "nauc_mrr_at_10_std": -0.15449188767848673, + "nauc_mrr_at_1_diff1": 0.1769532326495871, + "nauc_mrr_at_1_max": 0.03874006739507716, + "nauc_mrr_at_1_std": -0.13131553097620585, + "nauc_mrr_at_20_diff1": 0.14217933478368233, + "nauc_mrr_at_20_max": 0.06112015047173461, + "nauc_mrr_at_20_std": -0.14996758119028614, + "nauc_mrr_at_3_diff1": 0.14530305887422637, + "nauc_mrr_at_3_max": 0.05363488541802073, + "nauc_mrr_at_3_std": -0.16101565701587667, + "nauc_mrr_at_5_diff1": 0.14411778925430968, + "nauc_mrr_at_5_max": 0.05974922860828305, + "nauc_mrr_at_5_std": -0.16030093306951568, + "nauc_ndcg_at_1000_diff1": 0.13294785596297173, + "nauc_ndcg_at_1000_max": 0.0643350647152204, + "nauc_ndcg_at_1000_std": -0.13986445426549535, + "nauc_ndcg_at_100_diff1": 0.12865423420404729, + "nauc_ndcg_at_100_max": 0.06645869555790038, + "nauc_ndcg_at_100_std": -0.1299263934427331, + "nauc_ndcg_at_10_diff1": 0.13007522906433192, + "nauc_ndcg_at_10_max": 0.07685109904910538, + "nauc_ndcg_at_10_std": -0.15404141047773923, + "nauc_ndcg_at_1_diff1": 0.1769532326495871, + "nauc_ndcg_at_1_max": 0.03874006739507716, + "nauc_ndcg_at_1_std": -0.13131553097620585, + "nauc_ndcg_at_20_diff1": 0.12583319468227044, + "nauc_ndcg_at_20_max": 0.07739705968119948, + "nauc_ndcg_at_20_std": -0.13555637014483346, + "nauc_ndcg_at_3_diff1": 0.13607542127007816, + "nauc_ndcg_at_3_max": 0.0599188010441661, + "nauc_ndcg_at_3_std": -0.17012963946381118, + "nauc_ndcg_at_5_diff1": 0.1328561720149451, + "nauc_ndcg_at_5_max": 0.07120832274259502, + "nauc_ndcg_at_5_std": -0.16885745318443307, + "nauc_precision_at_1000_diff1": -0.15717956706949288, + "nauc_precision_at_1000_max": -0.03187722781632141, + "nauc_precision_at_1000_std": 0.4739348766711164, + "nauc_precision_at_100_diff1": -0.08478241526664337, + "nauc_precision_at_100_max": 0.10652305701322723, + "nauc_precision_at_100_std": 0.34193612165365694, + "nauc_precision_at_10_diff1": 0.07773517898835125, + "nauc_precision_at_10_max": 0.1448021880697199, + "nauc_precision_at_10_std": -0.14276168827995714, + "nauc_precision_at_1_diff1": 0.1769532326495871, + "nauc_precision_at_1_max": 0.03874006739507716, + "nauc_precision_at_1_std": -0.13131553097620585, + "nauc_precision_at_20_diff1": 0.027666308728523433, + "nauc_precision_at_20_max": 0.17780912822161407, + "nauc_precision_at_20_std": -0.012912687932824676, + "nauc_precision_at_3_diff1": 0.11053523054410946, + "nauc_precision_at_3_max": 0.07791285259404024, + "nauc_precision_at_3_std": -0.1954961916063043, + "nauc_precision_at_5_diff1": 0.09740019556941973, + "nauc_precision_at_5_max": 0.10870820455801775, + "nauc_precision_at_5_std": -0.19470180097156053, + "nauc_recall_at_1000_diff1": -0.15717956706949518, + "nauc_recall_at_1000_max": -0.031877227816318444, + "nauc_recall_at_1000_std": 0.4739348766711087, + "nauc_recall_at_100_diff1": -0.08478241526664343, + "nauc_recall_at_100_max": 0.10652305701322887, + "nauc_recall_at_100_std": 0.3419361216536553, + "nauc_recall_at_10_diff1": 0.07773517898834996, + "nauc_recall_at_10_max": 0.14480218806971928, + "nauc_recall_at_10_std": -0.14276168827995725, + "nauc_recall_at_1_diff1": 0.1769532326495871, + "nauc_recall_at_1_max": 0.03874006739507716, + "nauc_recall_at_1_std": -0.13131553097620585, + "nauc_recall_at_20_diff1": 0.027666308728522635, + "nauc_recall_at_20_max": 0.17780912822161268, + "nauc_recall_at_20_std": -0.012912687932825873, + "nauc_recall_at_3_diff1": 0.11053523054410952, + "nauc_recall_at_3_max": 0.07791285259404046, + "nauc_recall_at_3_std": -0.1954961916063045, + "nauc_recall_at_5_diff1": 0.0974001955694198, + "nauc_recall_at_5_max": 0.1087082045580175, + "nauc_recall_at_5_std": -0.1947018009715605, + "ndcg_at_1": 0.24569, + "ndcg_at_10": 0.48248, + "ndcg_at_100": 0.5267, + "ndcg_at_1000": 0.53258, + "ndcg_at_20": 0.50508, + "ndcg_at_3": 0.39862, + "ndcg_at_5": 0.44344, + "precision_at_1": 0.24569, + "precision_at_10": 0.0738, + "precision_at_100": 0.00942, + "precision_at_1000": 0.00099, + "precision_at_20": 0.04134, + "precision_at_3": 0.1696, + "precision_at_5": 0.12362, + "recall_at_1": 0.24569, + "recall_at_10": 0.738, + "recall_at_100": 0.942, + "recall_at_1000": 0.98814, + "recall_at_20": 0.82676, + "recall_at_3": 0.5088, + "recall_at_5": 0.61812 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL2Pure.json b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL2Pure.json new file mode 100644 index 000000000..f3ef2dc6a --- /dev/null +++ b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL2Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 118.30626153945923, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.08977, + "map_at_1": 0.03706, + "map_at_10": 0.06879, + "map_at_100": 0.07704, + "map_at_1000": 0.07839, + "map_at_20": 0.0728, + "map_at_3": 0.05623, + "map_at_5": 0.06209, + "mrr_at_1": 0.03705762460626274, + "mrr_at_10": 0.06878975974306706, + "mrr_at_100": 0.07704379597406215, + "mrr_at_1000": 0.07838508222360366, + "mrr_at_20": 0.07279869090625218, + "mrr_at_3": 0.05623494534000375, + "mrr_at_5": 0.062090050027793116, + "nauc_map_at_1000_diff1": 0.08764519611936816, + "nauc_map_at_1000_max": 0.1819897957146159, + "nauc_map_at_1000_std": 0.158186552036145, + "nauc_map_at_100_diff1": 0.08820384796480596, + "nauc_map_at_100_max": 0.1827816224159456, + "nauc_map_at_100_std": 0.15745697015912244, + "nauc_map_at_10_diff1": 0.09283436127846716, + "nauc_map_at_10_max": 0.1835318242405548, + "nauc_map_at_10_std": 0.14699572830443924, + "nauc_map_at_1_diff1": 0.11518395989252284, + "nauc_map_at_1_max": 0.11475095968780469, + "nauc_map_at_1_std": 0.09696688179560894, + "nauc_map_at_20_diff1": 0.09100599640996025, + "nauc_map_at_20_max": 0.18373254708605688, + "nauc_map_at_20_std": 0.15172213795179443, + "nauc_map_at_3_diff1": 0.09272102899514818, + "nauc_map_at_3_max": 0.1716805694393427, + "nauc_map_at_3_std": 0.13077338289993778, + "nauc_map_at_5_diff1": 0.08878200439498352, + "nauc_map_at_5_max": 0.17305686669735038, + "nauc_map_at_5_std": 0.1343432219396893, + "nauc_mrr_at_1000_diff1": 0.08764519611936816, + "nauc_mrr_at_1000_max": 0.1819897957146159, + "nauc_mrr_at_1000_std": 0.158186552036145, + "nauc_mrr_at_100_diff1": 0.08820384796480596, + "nauc_mrr_at_100_max": 0.1827816224159456, + "nauc_mrr_at_100_std": 0.15745697015912244, + "nauc_mrr_at_10_diff1": 0.09283436127846716, + "nauc_mrr_at_10_max": 0.1835318242405548, + "nauc_mrr_at_10_std": 0.14699572830443924, + "nauc_mrr_at_1_diff1": 0.11518395989252284, + "nauc_mrr_at_1_max": 0.11475095968780469, + "nauc_mrr_at_1_std": 0.09696688179560894, + "nauc_mrr_at_20_diff1": 0.09100599640996025, + "nauc_mrr_at_20_max": 0.18373254708605688, + "nauc_mrr_at_20_std": 0.15172213795179443, + "nauc_mrr_at_3_diff1": 0.09272102899514818, + "nauc_mrr_at_3_max": 0.1716805694393427, + "nauc_mrr_at_3_std": 0.13077338289993778, + "nauc_mrr_at_5_diff1": 0.08878200439498352, + "nauc_mrr_at_5_max": 0.17305686669735038, + "nauc_mrr_at_5_std": 0.1343432219396893, + "nauc_ndcg_at_1000_diff1": 0.053209962712327696, + "nauc_ndcg_at_1000_max": 0.17103430078262585, + "nauc_ndcg_at_1000_std": 0.21403985900407468, + "nauc_ndcg_at_100_diff1": 0.07158618622060337, + "nauc_ndcg_at_100_max": 0.19558351814171415, + "nauc_ndcg_at_100_std": 0.2063058896729725, + "nauc_ndcg_at_10_diff1": 0.09071639951860924, + "nauc_ndcg_at_10_max": 0.2011029072026743, + "nauc_ndcg_at_10_std": 0.1642927290331739, + "nauc_ndcg_at_1_diff1": 0.11518395989252284, + "nauc_ndcg_at_1_max": 0.11475095968780469, + "nauc_ndcg_at_1_std": 0.09696688179560894, + "nauc_ndcg_at_20_diff1": 0.0849620189916179, + "nauc_ndcg_at_20_max": 0.1995220360431707, + "nauc_ndcg_at_20_std": 0.17558023278941579, + "nauc_ndcg_at_3_diff1": 0.08790483243308926, + "nauc_ndcg_at_3_max": 0.18075680007425277, + "nauc_ndcg_at_3_std": 0.1355431906202884, + "nauc_ndcg_at_5_diff1": 0.08198127323143117, + "nauc_ndcg_at_5_max": 0.18172699261688469, + "nauc_ndcg_at_5_std": 0.14034550610619775, + "nauc_precision_at_1000_diff1": -0.07560396655550146, + "nauc_precision_at_1000_max": 0.0727193169710863, + "nauc_precision_at_1000_std": 0.356603568946037, + "nauc_precision_at_100_diff1": 0.04424209689911112, + "nauc_precision_at_100_max": 0.20819791954532998, + "nauc_precision_at_100_std": 0.28672707813092435, + "nauc_precision_at_10_diff1": 0.08892212986311311, + "nauc_precision_at_10_max": 0.22907026846332526, + "nauc_precision_at_10_std": 0.19301857174913317, + "nauc_precision_at_1_diff1": 0.11518395989252284, + "nauc_precision_at_1_max": 0.11475095968780469, + "nauc_precision_at_1_std": 0.09696688179560894, + "nauc_precision_at_20_diff1": 0.07611652554818145, + "nauc_precision_at_20_max": 0.21990649325431696, + "nauc_precision_at_20_std": 0.21137999007802113, + "nauc_precision_at_3_diff1": 0.07824680445465058, + "nauc_precision_at_3_max": 0.19830116193139774, + "nauc_precision_at_3_std": 0.14458838374476304, + "nauc_precision_at_5_diff1": 0.0696556128666733, + "nauc_precision_at_5_max": 0.19614806734300164, + "nauc_precision_at_5_std": 0.15055479478275335, + "nauc_recall_at_1000_diff1": -0.07560396655550208, + "nauc_recall_at_1000_max": 0.07271931697108622, + "nauc_recall_at_1000_std": 0.35660356894603634, + "nauc_recall_at_100_diff1": 0.04424209689911097, + "nauc_recall_at_100_max": 0.20819791954532949, + "nauc_recall_at_100_std": 0.286727078130924, + "nauc_recall_at_10_diff1": 0.088922129863113, + "nauc_recall_at_10_max": 0.22907026846332496, + "nauc_recall_at_10_std": 0.19301857174913292, + "nauc_recall_at_1_diff1": 0.11518395989252284, + "nauc_recall_at_1_max": 0.11475095968780469, + "nauc_recall_at_1_std": 0.09696688179560894, + "nauc_recall_at_20_diff1": 0.07611652554818121, + "nauc_recall_at_20_max": 0.2199064932543166, + "nauc_recall_at_20_std": 0.21137999007802086, + "nauc_recall_at_3_diff1": 0.07824680445465067, + "nauc_recall_at_3_max": 0.1983011619313978, + "nauc_recall_at_3_std": 0.14458838374476318, + "nauc_recall_at_5_diff1": 0.0696556128666732, + "nauc_recall_at_5_max": 0.1961480673430015, + "nauc_recall_at_5_std": 0.15055479478275308, + "ndcg_at_1": 0.03706, + "ndcg_at_10": 0.08977, + "ndcg_at_100": 0.13733, + "ndcg_at_1000": 0.17857, + "ndcg_at_20": 0.10457, + "ndcg_at_3": 0.06285, + "ndcg_at_5": 0.07346, + "precision_at_1": 0.03706, + "precision_at_10": 0.01586, + "precision_at_100": 0.00398, + "precision_at_1000": 0.00073, + "precision_at_20": 0.01088, + "precision_at_3": 0.02736, + "precision_at_5": 0.0216, + "recall_at_1": 0.03706, + "recall_at_10": 0.15861, + "recall_at_100": 0.39818, + "recall_at_1000": 0.73467, + "recall_at_20": 0.21753, + "recall_at_3": 0.08208, + "recall_at_5": 0.10802 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL3Fact.json b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL3Fact.json new file mode 100644 index 000000000..816d81844 --- /dev/null +++ b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL3Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 598.7155323028564, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.34114, + "map_at_1": 0.08789, + "map_at_10": 0.25009, + "map_at_100": 0.2627, + "map_at_1000": 0.26306, + "map_at_20": 0.2586, + "map_at_3": 0.19999, + "map_at_5": 0.23038, + "mrr_at_1": 0.08788974243108902, + "mrr_at_10": 0.2500875956648672, + "mrr_at_100": 0.26269721668209245, + "mrr_at_1000": 0.2630552172914749, + "mrr_at_20": 0.2586020229064641, + "mrr_at_3": 0.19999246874529428, + "mrr_at_5": 0.2303810814881787, + "nauc_map_at_1000_diff1": -0.013045862332082334, + "nauc_map_at_1000_max": 0.1060872418579747, + "nauc_map_at_1000_std": -0.04204423348446712, + "nauc_map_at_100_diff1": -0.013170667699437111, + "nauc_map_at_100_max": 0.10653853661495472, + "nauc_map_at_100_std": -0.04148902792495059, + "nauc_map_at_10_diff1": -0.010120045006086605, + "nauc_map_at_10_max": 0.10793192226818751, + "nauc_map_at_10_std": -0.047162500659814505, + "nauc_map_at_1_diff1": -0.05880155621681682, + "nauc_map_at_1_max": -0.022358518862777718, + "nauc_map_at_1_std": -0.08595079899494859, + "nauc_map_at_20_diff1": -0.013610816650932509, + "nauc_map_at_20_max": 0.10829601223502593, + "nauc_map_at_20_std": -0.04173738172250666, + "nauc_map_at_3_diff1": -0.0036038367925979166, + "nauc_map_at_3_max": 0.08365351825629389, + "nauc_map_at_3_std": -0.06838210622630338, + "nauc_map_at_5_diff1": -0.00532623254181204, + "nauc_map_at_5_max": 0.10086230471327005, + "nauc_map_at_5_std": -0.05967423275597344, + "nauc_mrr_at_1000_diff1": -0.013044805263433988, + "nauc_mrr_at_1000_max": 0.1060880514514507, + "nauc_mrr_at_1000_std": -0.04204463910539669, + "nauc_mrr_at_100_diff1": -0.013169612016985013, + "nauc_mrr_at_100_max": 0.10653934401249451, + "nauc_mrr_at_100_std": -0.04148943406617103, + "nauc_mrr_at_10_diff1": -0.010120045006086605, + "nauc_mrr_at_10_max": 0.10793192226818751, + "nauc_mrr_at_10_std": -0.047162500659814505, + "nauc_mrr_at_1_diff1": -0.05880155621681682, + "nauc_mrr_at_1_max": -0.022358518862777718, + "nauc_mrr_at_1_std": -0.08595079899494859, + "nauc_mrr_at_20_diff1": -0.013609774910637893, + "nauc_mrr_at_20_max": 0.10829680468719788, + "nauc_mrr_at_20_std": -0.04173778164578054, + "nauc_mrr_at_3_diff1": -0.0036038367925979166, + "nauc_mrr_at_3_max": 0.08365351825629389, + "nauc_mrr_at_3_std": -0.06838210622630338, + "nauc_mrr_at_5_diff1": -0.00532623254181204, + "nauc_mrr_at_5_max": 0.10086230471327005, + "nauc_mrr_at_5_std": -0.05967423275597344, + "nauc_ndcg_at_1000_diff1": -0.015546793373840198, + "nauc_ndcg_at_1000_max": 0.13219378254162753, + "nauc_ndcg_at_1000_std": -0.015161476064705293, + "nauc_ndcg_at_100_diff1": -0.018586799709314185, + "nauc_ndcg_at_100_max": 0.1442485406811629, + "nauc_ndcg_at_100_std": 0.002700682655679079, + "nauc_ndcg_at_10_diff1": -0.010565665904735226, + "nauc_ndcg_at_10_max": 0.15084457545734758, + "nauc_ndcg_at_10_std": -0.021153412817599013, + "nauc_ndcg_at_1_diff1": -0.05880155621681682, + "nauc_ndcg_at_1_max": -0.022358518862777718, + "nauc_ndcg_at_1_std": -0.08595079899494859, + "nauc_ndcg_at_20_diff1": -0.02199915432527928, + "nauc_ndcg_at_20_max": 0.15488155509440626, + "nauc_ndcg_at_20_std": -0.000641321059041629, + "nauc_ndcg_at_3_diff1": 0.003129087916292734, + "nauc_ndcg_at_3_max": 0.10527054921900733, + "nauc_ndcg_at_3_std": -0.06583380907505629, + "nauc_ndcg_at_5_diff1": -0.0001324312603617485, + "nauc_ndcg_at_5_max": 0.1329583358879005, + "nauc_ndcg_at_5_std": -0.05119945925804275, + "nauc_precision_at_1000_diff1": -0.06517221330244888, + "nauc_precision_at_1000_max": 0.4159220997408501, + "nauc_precision_at_1000_std": 0.5795174216097888, + "nauc_precision_at_100_diff1": -0.07619368136707795, + "nauc_precision_at_100_max": 0.39275530324138647, + "nauc_precision_at_100_std": 0.4119591372632846, + "nauc_precision_at_10_diff1": -0.016987624791222098, + "nauc_precision_at_10_max": 0.26115783745107896, + "nauc_precision_at_10_std": 0.05338183265793142, + "nauc_precision_at_1_diff1": -0.05880155621681682, + "nauc_precision_at_1_max": -0.022358518862777718, + "nauc_precision_at_1_std": -0.08595079899494859, + "nauc_precision_at_20_diff1": -0.0648473320922017, + "nauc_precision_at_20_max": 0.3136985706529079, + "nauc_precision_at_20_std": 0.16249376321837739, + "nauc_precision_at_3_diff1": 0.015872008012516363, + "nauc_precision_at_3_max": 0.14924281465381814, + "nauc_precision_at_3_std": -0.060868080110355494, + "nauc_precision_at_5_diff1": 0.008950115293041211, + "nauc_precision_at_5_max": 0.2012630167746775, + "nauc_precision_at_5_std": -0.03234194092243625, + "nauc_recall_at_1000_diff1": -0.06517221330245196, + "nauc_recall_at_1000_max": 0.41592209974084066, + "nauc_recall_at_1000_std": 0.5795174216097915, + "nauc_recall_at_100_diff1": -0.0761936813670747, + "nauc_recall_at_100_max": 0.3927553032413881, + "nauc_recall_at_100_std": 0.4119591372632837, + "nauc_recall_at_10_diff1": -0.016987624791221765, + "nauc_recall_at_10_max": 0.26115783745107846, + "nauc_recall_at_10_std": 0.053381832657931255, + "nauc_recall_at_1_diff1": -0.05880155621681682, + "nauc_recall_at_1_max": -0.022358518862777718, + "nauc_recall_at_1_std": -0.08595079899494859, + "nauc_recall_at_20_diff1": -0.06484733209220239, + "nauc_recall_at_20_max": 0.31369857065290724, + "nauc_recall_at_20_std": 0.16249376321837736, + "nauc_recall_at_3_diff1": 0.015872008012516415, + "nauc_recall_at_3_max": 0.14924281465381806, + "nauc_recall_at_3_std": -0.06086808011035551, + "nauc_recall_at_5_diff1": 0.008950115293040933, + "nauc_recall_at_5_max": 0.20126301677467742, + "nauc_recall_at_5_std": -0.032341940922436814, + "ndcg_at_1": 0.08789, + "ndcg_at_10": 0.34114, + "ndcg_at_100": 0.40066, + "ndcg_at_1000": 0.4106, + "ndcg_at_20": 0.37159, + "ndcg_at_3": 0.23885, + "ndcg_at_5": 0.29345, + "precision_at_1": 0.08789, + "precision_at_10": 0.06315, + "precision_at_100": 0.00906, + "precision_at_1000": 0.00099, + "precision_at_20": 0.03754, + "precision_at_3": 0.11734, + "precision_at_5": 0.09684, + "recall_at_1": 0.08789, + "recall_at_10": 0.6315, + "recall_at_100": 0.90624, + "recall_at_1000": 0.98531, + "recall_at_20": 0.75079, + "recall_at_3": 0.35201, + "recall_at_5": 0.48418 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL3Pure.json b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL3Pure.json new file mode 100644 index 000000000..719124ad1 --- /dev/null +++ b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/TempReasonL3Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 112.51635193824768, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.12441, + "map_at_1": 0.00587, + "map_at_10": 0.07851, + "map_at_100": 0.091, + "map_at_1000": 0.09211, + "map_at_20": 0.08569, + "map_at_3": 0.05148, + "map_at_5": 0.06513, + "mrr_at_1": 0.00587437867148667, + "mrr_at_10": 0.07851261305847823, + "mrr_at_100": 0.0910008844954526, + "mrr_at_1000": 0.09211248026812748, + "mrr_at_20": 0.08569356491660488, + "mrr_at_3": 0.05147612592257884, + "mrr_at_5": 0.06513405633378509, + "nauc_map_at_1000_diff1": -0.054833590577448944, + "nauc_map_at_1000_max": 0.2272920520105501, + "nauc_map_at_1000_std": 0.3257727369668284, + "nauc_map_at_100_diff1": -0.0543852007992989, + "nauc_map_at_100_max": 0.22770340571885603, + "nauc_map_at_100_std": 0.3258023778548565, + "nauc_map_at_10_diff1": -0.05486247274026119, + "nauc_map_at_10_max": 0.2207900478792447, + "nauc_map_at_10_std": 0.3085630170066589, + "nauc_map_at_1_diff1": -0.4323283036647323, + "nauc_map_at_1_max": -0.1967364973937561, + "nauc_map_at_1_std": 0.08412439280034595, + "nauc_map_at_20_diff1": -0.055383945408374644, + "nauc_map_at_20_max": 0.22613541511990462, + "nauc_map_at_20_std": 0.3234213045212249, + "nauc_map_at_3_diff1": -0.033984185522761834, + "nauc_map_at_3_max": 0.2086270477621345, + "nauc_map_at_3_std": 0.227091581373624, + "nauc_map_at_5_diff1": -0.048870879412160784, + "nauc_map_at_5_max": 0.20983627262762497, + "nauc_map_at_5_std": 0.2697118222108104, + "nauc_mrr_at_1000_diff1": -0.05483457687832298, + "nauc_mrr_at_1000_max": 0.22728996202757756, + "nauc_mrr_at_1000_std": 0.3257723624813744, + "nauc_mrr_at_100_diff1": -0.05438618135053252, + "nauc_mrr_at_100_max": 0.22770132803594983, + "nauc_mrr_at_100_std": 0.32580200558287103, + "nauc_mrr_at_10_diff1": -0.05486247274026119, + "nauc_mrr_at_10_max": 0.2207900478792447, + "nauc_mrr_at_10_std": 0.3085630170066589, + "nauc_mrr_at_1_diff1": -0.4323283036647323, + "nauc_mrr_at_1_max": -0.1967364973937561, + "nauc_mrr_at_1_std": 0.08412439280034595, + "nauc_mrr_at_20_diff1": -0.055383945408374644, + "nauc_mrr_at_20_max": 0.22613541511990462, + "nauc_mrr_at_20_std": 0.3234213045212249, + "nauc_mrr_at_3_diff1": -0.033984185522761834, + "nauc_mrr_at_3_max": 0.2086270477621345, + "nauc_mrr_at_3_std": 0.227091581373624, + "nauc_mrr_at_5_diff1": -0.048870879412160784, + "nauc_mrr_at_5_max": 0.20983627262762497, + "nauc_mrr_at_5_std": 0.2697118222108104, + "nauc_ndcg_at_1000_diff1": -0.05796967362086573, + "nauc_ndcg_at_1000_max": 0.2470290944635618, + "nauc_ndcg_at_1000_std": 0.3938360458134586, + "nauc_ndcg_at_100_diff1": -0.051249155199604664, + "nauc_ndcg_at_100_max": 0.2559124649313534, + "nauc_ndcg_at_100_std": 0.39450330768406067, + "nauc_ndcg_at_10_diff1": -0.05668484482915861, + "nauc_ndcg_at_10_max": 0.23973062989291566, + "nauc_ndcg_at_10_std": 0.35039565314944143, + "nauc_ndcg_at_1_diff1": -0.4323283036647323, + "nauc_ndcg_at_1_max": -0.1967364973937561, + "nauc_ndcg_at_1_std": 0.08412439280034595, + "nauc_ndcg_at_20_diff1": -0.05777258668383804, + "nauc_ndcg_at_20_max": 0.2516595882693558, + "nauc_ndcg_at_20_std": 0.38413478329959644, + "nauc_ndcg_at_3_diff1": -0.02524548800334743, + "nauc_ndcg_at_3_max": 0.22289926554420783, + "nauc_ndcg_at_3_std": 0.23301338641125705, + "nauc_ndcg_at_5_diff1": -0.04675597928070696, + "nauc_ndcg_at_5_max": 0.22216521101479603, + "nauc_ndcg_at_5_std": 0.28851537106223674, + "nauc_precision_at_1000_diff1": -0.08500720588508376, + "nauc_precision_at_1000_max": 0.26473800835280537, + "nauc_precision_at_1000_std": 0.6121566835833671, + "nauc_precision_at_100_diff1": -0.043391612493346055, + "nauc_precision_at_100_max": 0.29505956804528566, + "nauc_precision_at_100_std": 0.5008700265161659, + "nauc_precision_at_10_diff1": -0.06131917247002842, + "nauc_precision_at_10_max": 0.26215939869387517, + "nauc_precision_at_10_std": 0.404678838120454, + "nauc_precision_at_1_diff1": -0.4323283036647323, + "nauc_precision_at_1_max": -0.1967364973937561, + "nauc_precision_at_1_std": 0.08412439280034595, + "nauc_precision_at_20_diff1": -0.06293095135165078, + "nauc_precision_at_20_max": 0.28289131851267985, + "nauc_precision_at_20_std": 0.46424522356121856, + "nauc_precision_at_3_diff1": -0.014139401578006016, + "nauc_precision_at_3_max": 0.24236070376117805, + "nauc_precision_at_3_std": 0.24122436467828337, + "nauc_precision_at_5_diff1": -0.046124810870943764, + "nauc_precision_at_5_max": 0.23678406587565728, + "nauc_precision_at_5_std": 0.3139930924142894, + "nauc_recall_at_1000_diff1": -0.08500720588508441, + "nauc_recall_at_1000_max": 0.2647380083528051, + "nauc_recall_at_1000_std": 0.612156683583366, + "nauc_recall_at_100_diff1": -0.04339161249334581, + "nauc_recall_at_100_max": 0.295059568045286, + "nauc_recall_at_100_std": 0.5008700265161655, + "nauc_recall_at_10_diff1": -0.061319172470028584, + "nauc_recall_at_10_max": 0.26215939869387495, + "nauc_recall_at_10_std": 0.40467883812045374, + "nauc_recall_at_1_diff1": -0.4323283036647323, + "nauc_recall_at_1_max": -0.1967364973937561, + "nauc_recall_at_1_std": 0.08412439280034595, + "nauc_recall_at_20_diff1": -0.06293095135165101, + "nauc_recall_at_20_max": 0.28289131851267985, + "nauc_recall_at_20_std": 0.46424522356121856, + "nauc_recall_at_3_diff1": -0.014139401578006187, + "nauc_recall_at_3_max": 0.2423607037611781, + "nauc_recall_at_3_std": 0.24122436467828334, + "nauc_recall_at_5_diff1": -0.046124810870944076, + "nauc_recall_at_5_max": 0.23678406587565723, + "nauc_recall_at_5_std": 0.31399309241428913, + "ndcg_at_1": 0.00587, + "ndcg_at_10": 0.12441, + "ndcg_at_100": 0.19025, + "ndcg_at_1000": 0.2227, + "ndcg_at_20": 0.15061, + "ndcg_at_3": 0.06715, + "ndcg_at_5": 0.09202, + "precision_at_1": 0.00587, + "precision_at_10": 0.02738, + "precision_at_100": 0.00594, + "precision_at_1000": 0.00086, + "precision_at_20": 0.01888, + "precision_at_3": 0.03758, + "precision_at_5": 0.03475, + "recall_at_1": 0.00587, + "recall_at_10": 0.27384, + "recall_at_100": 0.59376, + "recall_at_1000": 0.85563, + "recall_at_20": 0.37754, + "recall_at_3": 0.11274, + "recall_at_5": 0.17375 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/WinoGrande.json b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/WinoGrande.json new file mode 100644 index 000000000..587f6ac3c --- /dev/null +++ b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/WinoGrande.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 29.388219356536865, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.52117, + "map_at_1": 0.23678, + "map_at_10": 0.41794, + "map_at_100": 0.42622, + "map_at_1000": 0.42625, + "map_at_20": 0.42468, + "map_at_3": 0.35872, + "map_at_5": 0.39262, + "mrr_at_1": 0.23677979479084452, + "mrr_at_10": 0.41794483907743524, + "mrr_at_100": 0.42622065271130893, + "mrr_at_1000": 0.42624843530589474, + "mrr_at_20": 0.4246764396983329, + "mrr_at_3": 0.3587213891081286, + "mrr_at_5": 0.3926203630623506, + "nauc_map_at_1000_diff1": 0.06431101788891462, + "nauc_map_at_1000_max": 0.0888876176432186, + "nauc_map_at_1000_std": -0.04190015211770828, + "nauc_map_at_100_diff1": 0.06429899623115802, + "nauc_map_at_100_max": 0.08879515104864939, + "nauc_map_at_100_std": -0.04190764994769363, + "nauc_map_at_10_diff1": 0.06509489447615927, + "nauc_map_at_10_max": 0.08622548090010017, + "nauc_map_at_10_std": -0.04947681701581228, + "nauc_map_at_1_diff1": 0.07643680298648814, + "nauc_map_at_1_max": 0.12076916609716395, + "nauc_map_at_1_std": 0.01991646836115088, + "nauc_map_at_20_diff1": 0.06480028712511615, + "nauc_map_at_20_max": 0.08839943389588291, + "nauc_map_at_20_std": -0.044104129943796866, + "nauc_map_at_3_diff1": 0.05078014653998991, + "nauc_map_at_3_max": 0.09039179707701028, + "nauc_map_at_3_std": -0.027992291087513832, + "nauc_map_at_5_diff1": 0.062078252375075985, + "nauc_map_at_5_max": 0.09105301137016235, + "nauc_map_at_5_std": -0.042662349121587985, + "nauc_mrr_at_1000_diff1": 0.06431101788891462, + "nauc_mrr_at_1000_max": 0.0888876176432186, + "nauc_mrr_at_1000_std": -0.04190015211770828, + "nauc_mrr_at_100_diff1": 0.06429899623115802, + "nauc_mrr_at_100_max": 0.08879515104864939, + "nauc_mrr_at_100_std": -0.04190764994769363, + "nauc_mrr_at_10_diff1": 0.06509489447615927, + "nauc_mrr_at_10_max": 0.08622548090010017, + "nauc_mrr_at_10_std": -0.04947681701581228, + "nauc_mrr_at_1_diff1": 0.07643680298648814, + "nauc_mrr_at_1_max": 0.12076916609716395, + "nauc_mrr_at_1_std": 0.01991646836115088, + "nauc_mrr_at_20_diff1": 0.06480028712511615, + "nauc_mrr_at_20_max": 0.08839943389588291, + "nauc_mrr_at_20_std": -0.044104129943796866, + "nauc_mrr_at_3_diff1": 0.05078014653998991, + "nauc_mrr_at_3_max": 0.09039179707701028, + "nauc_mrr_at_3_std": -0.027992291087513832, + "nauc_mrr_at_5_diff1": 0.062078252375075985, + "nauc_mrr_at_5_max": 0.09105301137016235, + "nauc_mrr_at_5_std": -0.042662349121587985, + "nauc_ndcg_at_1000_diff1": 0.06446087816357458, + "nauc_ndcg_at_1000_max": 0.08333226125265099, + "nauc_ndcg_at_1000_std": -0.053677361094945183, + "nauc_ndcg_at_100_diff1": 0.0643415702452091, + "nauc_ndcg_at_100_max": 0.08074358699460724, + "nauc_ndcg_at_100_std": -0.05391870021656425, + "nauc_ndcg_at_10_diff1": 0.06879511037693656, + "nauc_ndcg_at_10_max": 0.06960931495746725, + "nauc_ndcg_at_10_std": -0.09131347069670813, + "nauc_ndcg_at_1_diff1": 0.07643680298648814, + "nauc_ndcg_at_1_max": 0.12076916609716395, + "nauc_ndcg_at_1_std": 0.01991646836115088, + "nauc_ndcg_at_20_diff1": 0.06717121441513381, + "nauc_ndcg_at_20_max": 0.07838269009989404, + "nauc_ndcg_at_20_std": -0.07009677838430893, + "nauc_ndcg_at_3_diff1": 0.04229685384473465, + "nauc_ndcg_at_3_max": 0.08215016848950492, + "nauc_ndcg_at_3_std": -0.04218966944313996, + "nauc_ndcg_at_5_diff1": 0.061551676022965865, + "nauc_ndcg_at_5_max": 0.08264661760902879, + "nauc_ndcg_at_5_std": -0.07083424524879844, + "nauc_precision_at_1000_diff1": 1.0, + "nauc_precision_at_1000_max": 1.0, + "nauc_precision_at_1000_std": 1.0, + "nauc_precision_at_100_diff1": 0.047003724774739984, + "nauc_precision_at_100_max": -0.8723695919177473, + "nauc_precision_at_100_std": -0.1495673731940228, + "nauc_precision_at_10_diff1": 0.10073896750505361, + "nauc_precision_at_10_max": -0.03856041836642931, + "nauc_precision_at_10_std": -0.36698000962972355, + "nauc_precision_at_1_diff1": 0.07643680298648814, + "nauc_precision_at_1_max": 0.12076916609716395, + "nauc_precision_at_1_std": 0.01991646836115088, + "nauc_precision_at_20_diff1": 0.11814499901982936, + "nauc_precision_at_20_max": -0.0548795664523561, + "nauc_precision_at_20_std": -0.4318355323308492, + "nauc_precision_at_3_diff1": 0.018504444079987498, + "nauc_precision_at_3_max": 0.05952512731612694, + "nauc_precision_at_3_std": -0.08156152358623447, + "nauc_precision_at_5_diff1": 0.06213568878925811, + "nauc_precision_at_5_max": 0.05546648365170001, + "nauc_precision_at_5_std": -0.16831223452845268, + "nauc_recall_at_1000_diff1": NaN, + "nauc_recall_at_1000_max": NaN, + "nauc_recall_at_1000_std": NaN, + "nauc_recall_at_100_diff1": 0.04700372477469328, + "nauc_recall_at_100_max": -0.8723695919178236, + "nauc_recall_at_100_std": -0.1495673731940447, + "nauc_recall_at_10_diff1": 0.10073896750505343, + "nauc_recall_at_10_max": -0.03856041836642979, + "nauc_recall_at_10_std": -0.3669800096297244, + "nauc_recall_at_1_diff1": 0.07643680298648814, + "nauc_recall_at_1_max": 0.12076916609716395, + "nauc_recall_at_1_std": 0.01991646836115088, + "nauc_recall_at_20_diff1": 0.11814499901982303, + "nauc_recall_at_20_max": -0.054879566452358704, + "nauc_recall_at_20_std": -0.4318355323308548, + "nauc_recall_at_3_diff1": 0.018504444079987775, + "nauc_recall_at_3_max": 0.059525127316127496, + "nauc_recall_at_3_std": -0.08156152358623436, + "nauc_recall_at_5_diff1": 0.06213568878925756, + "nauc_recall_at_5_max": 0.055466483651699504, + "nauc_recall_at_5_std": -0.16831223452845304, + "ndcg_at_1": 0.23678, + "ndcg_at_10": 0.52117, + "ndcg_at_100": 0.55494, + "ndcg_at_1000": 0.55557, + "ndcg_at_20": 0.54531, + "ndcg_at_3": 0.39967, + "ndcg_at_5": 0.46061, + "precision_at_1": 0.23678, + "precision_at_10": 0.08516, + "precision_at_100": 0.00995, + "precision_at_1000": 0.001, + "precision_at_20": 0.04732, + "precision_at_3": 0.17285, + "precision_at_5": 0.13323, + "recall_at_1": 0.23678, + "recall_at_10": 0.85162, + "recall_at_100": 0.99526, + "recall_at_1000": 1.0, + "recall_at_20": 0.94633, + "recall_at_3": 0.51855, + "recall_at_5": 0.66614 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/model_meta.json b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/model_meta.json new file mode 100644 index 000000000..01167804b --- /dev/null +++ b/results/GritLM-7B-noinstruct/13f00a0e36500c80ce12870ea513846a066004af-temp/model_meta.json @@ -0,0 +1 @@ +{"name": "GritLM/GritLM-7B", "revision": "13f00a0e36500c80ce12870ea513846a066004af", "release_date": "2024-02-15", "languages": ["eng_Latn", "fra_Latn", "deu_Latn", "ita_Latn", "spa_Latn"], "n_parameters": null, "memory_usage": null, "max_tokens": null, "embed_dim": null, "license": null, "open_source": true, "similarity_fn_name": null, "framework": [], "loader": "gritlm_loader"} \ No newline at end of file diff --git a/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/ARCChallenge.json b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/ARCChallenge.json new file mode 100644 index 000000000..564eca66f --- /dev/null +++ b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/ARCChallenge.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 2.2498011589050293, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.09396, + "map_at_1": 0.03498, + "map_at_10": 0.07266, + "map_at_100": 0.08038, + "map_at_1000": 0.08172, + "map_at_20": 0.0763, + "map_at_3": 0.06015, + "map_at_5": 0.06796, + "mrr_at_1": 0.03498293515358362, + "mrr_at_10": 0.07265764667641803, + "mrr_at_100": 0.08038082746884427, + "mrr_at_1000": 0.08171570916576305, + "mrr_at_20": 0.07630273138114121, + "mrr_at_3": 0.06015358361774747, + "mrr_at_5": 0.06796075085324237, + "nauc_map_at_1000_diff1": 0.02003795179695383, + "nauc_map_at_1000_max": 0.10499547200118084, + "nauc_map_at_1000_std": -0.07888364584760689, + "nauc_map_at_100_diff1": 0.020657269719434893, + "nauc_map_at_100_max": 0.10572648561122054, + "nauc_map_at_100_std": -0.07996679218879599, + "nauc_map_at_10_diff1": 0.024010720099468703, + "nauc_map_at_10_max": 0.1094030555412913, + "nauc_map_at_10_std": -0.08748581308233769, + "nauc_map_at_1_diff1": 0.004287334329413217, + "nauc_map_at_1_max": 0.1095714828587646, + "nauc_map_at_1_std": -0.11028794542148944, + "nauc_map_at_20_diff1": 0.0231357319916855, + "nauc_map_at_20_max": 0.11120402157507069, + "nauc_map_at_20_std": -0.08357361939954745, + "nauc_map_at_3_diff1": 0.02237150034539165, + "nauc_map_at_3_max": 0.12051311579400607, + "nauc_map_at_3_std": -0.08963045635972826, + "nauc_map_at_5_diff1": 0.02694569233771514, + "nauc_map_at_5_max": 0.11526540060248501, + "nauc_map_at_5_std": -0.09121603126605453, + "nauc_mrr_at_1000_diff1": 0.020038348366691053, + "nauc_mrr_at_1000_max": 0.10499595697916683, + "nauc_mrr_at_1000_std": -0.07888388110213453, + "nauc_mrr_at_100_diff1": 0.020657269719434893, + "nauc_mrr_at_100_max": 0.10572648561122054, + "nauc_mrr_at_100_std": -0.07996679218879599, + "nauc_mrr_at_10_diff1": 0.024010720099468703, + "nauc_mrr_at_10_max": 0.1094030555412913, + "nauc_mrr_at_10_std": -0.08748581308233769, + "nauc_mrr_at_1_diff1": 0.004287334329413217, + "nauc_mrr_at_1_max": 0.1095714828587646, + "nauc_mrr_at_1_std": -0.11028794542148944, + "nauc_mrr_at_20_diff1": 0.0231357319916855, + "nauc_mrr_at_20_max": 0.11120402157507069, + "nauc_mrr_at_20_std": -0.08357361939954745, + "nauc_mrr_at_3_diff1": 0.02237150034539165, + "nauc_mrr_at_3_max": 0.12051311579400607, + "nauc_mrr_at_3_std": -0.08963045635972826, + "nauc_mrr_at_5_diff1": 0.02694569233771514, + "nauc_mrr_at_5_max": 0.11526540060248501, + "nauc_mrr_at_5_std": -0.09121603126605453, + "nauc_ndcg_at_1000_diff1": -0.007737559822868548, + "nauc_ndcg_at_1000_max": 0.06889869073589162, + "nauc_ndcg_at_1000_std": -0.03061311310180431, + "nauc_ndcg_at_100_diff1": 0.008926736104468135, + "nauc_ndcg_at_100_max": 0.08073245136202091, + "nauc_ndcg_at_100_std": -0.055067563535606226, + "nauc_ndcg_at_10_diff1": 0.028356870101955256, + "nauc_ndcg_at_10_max": 0.10046031355791889, + "nauc_ndcg_at_10_std": -0.08415225809236483, + "nauc_ndcg_at_1_diff1": 0.004287334329413217, + "nauc_ndcg_at_1_max": 0.1095714828587646, + "nauc_ndcg_at_1_std": -0.11028794542148944, + "nauc_ndcg_at_20_diff1": 0.024413947517824025, + "nauc_ndcg_at_20_max": 0.10352798098944349, + "nauc_ndcg_at_20_std": -0.07518694309152728, + "nauc_ndcg_at_3_diff1": 0.026685234703466086, + "nauc_ndcg_at_3_max": 0.11936374143810945, + "nauc_ndcg_at_3_std": -0.0880654347593911, + "nauc_ndcg_at_5_diff1": 0.03274648471257263, + "nauc_ndcg_at_5_max": 0.1110358680794169, + "nauc_ndcg_at_5_std": -0.09051902507019055, + "nauc_precision_at_1000_diff1": -0.12745552053757023, + "nauc_precision_at_1000_max": -0.04025029811753049, + "nauc_precision_at_1000_std": 0.1460476986370867, + "nauc_precision_at_100_diff1": -0.01897742963012519, + "nauc_precision_at_100_max": 0.03892581325041562, + "nauc_precision_at_100_std": -0.008890121970997061, + "nauc_precision_at_10_diff1": 0.03522100874120472, + "nauc_precision_at_10_max": 0.08459123832992446, + "nauc_precision_at_10_std": -0.07900445340612357, + "nauc_precision_at_1_diff1": 0.004287334329413217, + "nauc_precision_at_1_max": 0.1095714828587646, + "nauc_precision_at_1_std": -0.11028794542148944, + "nauc_precision_at_20_diff1": 0.024176802913794454, + "nauc_precision_at_20_max": 0.09100858721850948, + "nauc_precision_at_20_std": -0.062249723502337234, + "nauc_precision_at_3_diff1": 0.035050017134445305, + "nauc_precision_at_3_max": 0.11654453985390345, + "nauc_precision_at_3_std": -0.08555881557494263, + "nauc_precision_at_5_diff1": 0.042777763904717166, + "nauc_precision_at_5_max": 0.10268449489568562, + "nauc_precision_at_5_std": -0.08985636074660593, + "nauc_recall_at_1000_diff1": -0.127455520537571, + "nauc_recall_at_1000_max": -0.040250298117531495, + "nauc_recall_at_1000_std": 0.14604769863708694, + "nauc_recall_at_100_diff1": -0.01897742963012525, + "nauc_recall_at_100_max": 0.03892581325041559, + "nauc_recall_at_100_std": -0.008890121970997068, + "nauc_recall_at_10_diff1": 0.03522100874120455, + "nauc_recall_at_10_max": 0.08459123832992421, + "nauc_recall_at_10_std": -0.07900445340612372, + "nauc_recall_at_1_diff1": 0.004287334329413217, + "nauc_recall_at_1_max": 0.1095714828587646, + "nauc_recall_at_1_std": -0.11028794542148944, + "nauc_recall_at_20_diff1": 0.024176802913794652, + "nauc_recall_at_20_max": 0.09100858721850949, + "nauc_recall_at_20_std": -0.062249723502337186, + "nauc_recall_at_3_diff1": 0.03505001713444514, + "nauc_recall_at_3_max": 0.11654453985390324, + "nauc_recall_at_3_std": -0.08555881557494292, + "nauc_recall_at_5_diff1": 0.04277776390471683, + "nauc_recall_at_5_max": 0.10268449489568557, + "nauc_recall_at_5_std": -0.0898563607466061, + "ndcg_at_1": 0.03498, + "ndcg_at_10": 0.09396, + "ndcg_at_100": 0.13842, + "ndcg_at_1000": 0.17996, + "ndcg_at_20": 0.10745, + "ndcg_at_3": 0.06857, + "ndcg_at_5": 0.08246, + "precision_at_1": 0.03498, + "precision_at_10": 0.01621, + "precision_at_100": 0.00386, + "precision_at_1000": 0.00073, + "precision_at_20": 0.01079, + "precision_at_3": 0.031, + "precision_at_5": 0.02526, + "recall_at_1": 0.03498, + "recall_at_10": 0.16212, + "recall_at_100": 0.38567, + "recall_at_1000": 0.72611, + "recall_at_20": 0.21587, + "recall_at_3": 0.093, + "recall_at_5": 0.12628 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/AlphaNLI.json b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/AlphaNLI.json new file mode 100644 index 000000000..cfd7d32a1 --- /dev/null +++ b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/AlphaNLI.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 16.837814569473267, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.15085, + "map_at_1": 0.08877, + "map_at_10": 0.12704, + "map_at_100": 0.134, + "map_at_1000": 0.13483, + "map_at_20": 0.13085, + "map_at_3": 0.11282, + "map_at_5": 0.11996, + "mrr_at_1": 0.08877284595300261, + "mrr_at_10": 0.12703929918355503, + "mrr_at_100": 0.13399741798078485, + "mrr_at_1000": 0.13483034200425298, + "mrr_at_20": 0.1308528210768297, + "mrr_at_3": 0.11281549173194086, + "mrr_at_5": 0.11996301131418627, + "nauc_map_at_1000_diff1": 0.29938001107172874, + "nauc_map_at_1000_max": 0.3001639175819397, + "nauc_map_at_1000_std": 0.028478308210333387, + "nauc_map_at_100_diff1": 0.2994699840681743, + "nauc_map_at_100_max": 0.3000115657808576, + "nauc_map_at_100_std": 0.028139547147370974, + "nauc_map_at_10_diff1": 0.3038431108043259, + "nauc_map_at_10_max": 0.3019701784406907, + "nauc_map_at_10_std": 0.025436213052624623, + "nauc_map_at_1_diff1": 0.3565211716758729, + "nauc_map_at_1_max": 0.32988302922627205, + "nauc_map_at_1_std": 0.007810169638648712, + "nauc_map_at_20_diff1": 0.30206550940343896, + "nauc_map_at_20_max": 0.301025232572548, + "nauc_map_at_20_std": 0.026934302437428503, + "nauc_map_at_3_diff1": 0.3270771819416992, + "nauc_map_at_3_max": 0.31605059536845276, + "nauc_map_at_3_std": 0.018550532715995403, + "nauc_map_at_5_diff1": 0.30837682953878215, + "nauc_map_at_5_max": 0.3084231618031781, + "nauc_map_at_5_std": 0.02024854445744312, + "nauc_mrr_at_1000_diff1": 0.29938001107172874, + "nauc_mrr_at_1000_max": 0.3001639175819397, + "nauc_mrr_at_1000_std": 0.028478308210333387, + "nauc_mrr_at_100_diff1": 0.2994699840681743, + "nauc_mrr_at_100_max": 0.3000115657808576, + "nauc_mrr_at_100_std": 0.028139547147370974, + "nauc_mrr_at_10_diff1": 0.3038431108043259, + "nauc_mrr_at_10_max": 0.3019701784406907, + "nauc_mrr_at_10_std": 0.025436213052624623, + "nauc_mrr_at_1_diff1": 0.3565211716758729, + "nauc_mrr_at_1_max": 0.32988302922627205, + "nauc_mrr_at_1_std": 0.007810169638648712, + "nauc_mrr_at_20_diff1": 0.30206550940343896, + "nauc_mrr_at_20_max": 0.301025232572548, + "nauc_mrr_at_20_std": 0.026934302437428503, + "nauc_mrr_at_3_diff1": 0.3270771819416992, + "nauc_mrr_at_3_max": 0.31605059536845276, + "nauc_mrr_at_3_std": 0.018550532715995403, + "nauc_mrr_at_5_diff1": 0.30837682953878215, + "nauc_mrr_at_5_max": 0.3084231618031781, + "nauc_mrr_at_5_std": 0.02024854445744312, + "nauc_ndcg_at_1000_diff1": 0.2543307157790473, + "nauc_ndcg_at_1000_max": 0.27668597983044385, + "nauc_ndcg_at_1000_std": 0.05184464089123761, + "nauc_ndcg_at_100_diff1": 0.25694825369318874, + "nauc_ndcg_at_100_max": 0.2763567815409105, + "nauc_ndcg_at_100_std": 0.045455309806606656, + "nauc_ndcg_at_10_diff1": 0.2786797681477087, + "nauc_ndcg_at_10_max": 0.2852421654213901, + "nauc_ndcg_at_10_std": 0.03468441030301039, + "nauc_ndcg_at_1_diff1": 0.3565211716758729, + "nauc_ndcg_at_1_max": 0.32988302922627205, + "nauc_ndcg_at_1_std": 0.007810169638648712, + "nauc_ndcg_at_20_diff1": 0.273055396904665, + "nauc_ndcg_at_20_max": 0.28254166170714956, + "nauc_ndcg_at_20_std": 0.03854036023068576, + "nauc_ndcg_at_3_diff1": 0.31656155987325263, + "nauc_ndcg_at_3_max": 0.3099396497178243, + "nauc_ndcg_at_3_std": 0.021000746491754704, + "nauc_ndcg_at_5_diff1": 0.28655339755557635, + "nauc_ndcg_at_5_max": 0.2979695219528929, + "nauc_ndcg_at_5_std": 0.023774430056645205, + "nauc_precision_at_1000_diff1": 0.12777899392560604, + "nauc_precision_at_1000_max": 0.21191488923992802, + "nauc_precision_at_1000_std": 0.12709088466999746, + "nauc_precision_at_100_diff1": 0.1603623487047558, + "nauc_precision_at_100_max": 0.22413322245208456, + "nauc_precision_at_100_std": 0.0849962055027627, + "nauc_precision_at_10_diff1": 0.22595857528838365, + "nauc_precision_at_10_max": 0.24894691822233633, + "nauc_precision_at_10_std": 0.05528043800931334, + "nauc_precision_at_1_diff1": 0.3565211716758729, + "nauc_precision_at_1_max": 0.32988302922627205, + "nauc_precision_at_1_std": 0.007810169638648712, + "nauc_precision_at_20_diff1": 0.21414011275236292, + "nauc_precision_at_20_max": 0.24440927895609488, + "nauc_precision_at_20_std": 0.06313069489430052, + "nauc_precision_at_3_diff1": 0.2906074632037461, + "nauc_precision_at_3_max": 0.29463190197795003, + "nauc_precision_at_3_std": 0.026781916425931602, + "nauc_precision_at_5_diff1": 0.23589217090451578, + "nauc_precision_at_5_max": 0.2737598416627718, + "nauc_precision_at_5_std": 0.03165806558384649, + "nauc_recall_at_1000_diff1": 0.12777899392560668, + "nauc_recall_at_1000_max": 0.2119148892399281, + "nauc_recall_at_1000_std": 0.12709088466999743, + "nauc_recall_at_100_diff1": 0.16036234870475558, + "nauc_recall_at_100_max": 0.22413322245208425, + "nauc_recall_at_100_std": 0.08499620550276213, + "nauc_recall_at_10_diff1": 0.22595857528838376, + "nauc_recall_at_10_max": 0.2489469182223361, + "nauc_recall_at_10_std": 0.055280438009313246, + "nauc_recall_at_1_diff1": 0.3565211716758729, + "nauc_recall_at_1_max": 0.32988302922627205, + "nauc_recall_at_1_std": 0.007810169638648712, + "nauc_recall_at_20_diff1": 0.21414011275236286, + "nauc_recall_at_20_max": 0.24440927895609488, + "nauc_recall_at_20_std": 0.06313069489430041, + "nauc_recall_at_3_diff1": 0.2906074632037461, + "nauc_recall_at_3_max": 0.29463190197795025, + "nauc_recall_at_3_std": 0.026781916425931786, + "nauc_recall_at_5_diff1": 0.23589217090451586, + "nauc_recall_at_5_max": 0.2737598416627719, + "nauc_recall_at_5_std": 0.03165806558384641, + "ndcg_at_1": 0.08877, + "ndcg_at_10": 0.15085, + "ndcg_at_100": 0.18794, + "ndcg_at_1000": 0.21334, + "ndcg_at_20": 0.16473, + "ndcg_at_3": 0.12072, + "ndcg_at_5": 0.13361, + "precision_at_1": 0.08877, + "precision_at_10": 0.02285, + "precision_at_100": 0.00409, + "precision_at_1000": 0.00062, + "precision_at_20": 0.01416, + "precision_at_3": 0.04787, + "precision_at_5": 0.03499, + "recall_at_1": 0.08877, + "recall_at_10": 0.22846, + "recall_at_100": 0.40927, + "recall_at_1000": 0.61619, + "recall_at_20": 0.28329, + "recall_at_3": 0.1436, + "recall_at_5": 0.17493 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/HellaSwag.json b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/HellaSwag.json new file mode 100644 index 000000000..eb1f0395c --- /dev/null +++ b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/HellaSwag.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 55.767213582992554, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.20509, + "map_at_1": 0.10526, + "map_at_10": 0.16902, + "map_at_100": 0.17658, + "map_at_1000": 0.17747, + "map_at_20": 0.17309, + "map_at_3": 0.14917, + "map_at_5": 0.16073, + "mrr_at_1": 0.10525791674965146, + "mrr_at_10": 0.16902252602561263, + "mrr_at_100": 0.17658112568157064, + "mrr_at_1000": 0.1774703440924315, + "mrr_at_20": 0.1730889261548795, + "mrr_at_3": 0.14917347142003543, + "mrr_at_5": 0.1607349133638716, + "nauc_map_at_1000_diff1": 0.2554303228748277, + "nauc_map_at_1000_max": 0.19694524519794382, + "nauc_map_at_1000_std": 0.09996688300375778, + "nauc_map_at_100_diff1": 0.25555093266001816, + "nauc_map_at_100_max": 0.19684720401389802, + "nauc_map_at_100_std": 0.09976635488679904, + "nauc_map_at_10_diff1": 0.2555781170961617, + "nauc_map_at_10_max": 0.19492756523108676, + "nauc_map_at_10_std": 0.09345623639870085, + "nauc_map_at_1_diff1": 0.2848683967457831, + "nauc_map_at_1_max": 0.1830195596824384, + "nauc_map_at_1_std": 0.07549803331789048, + "nauc_map_at_20_diff1": 0.2563069637891677, + "nauc_map_at_20_max": 0.19606651845976975, + "nauc_map_at_20_std": 0.09674388949169618, + "nauc_map_at_3_diff1": 0.2585477342231996, + "nauc_map_at_3_max": 0.1912753471137965, + "nauc_map_at_3_std": 0.08053735917881188, + "nauc_map_at_5_diff1": 0.25700358762170694, + "nauc_map_at_5_max": 0.19434259852483204, + "nauc_map_at_5_std": 0.08786770986492323, + "nauc_mrr_at_1000_diff1": 0.2554302201977657, + "nauc_mrr_at_1000_max": 0.196945236894258, + "nauc_mrr_at_1000_std": 0.09996687428256544, + "nauc_mrr_at_100_diff1": 0.2555508312435078, + "nauc_mrr_at_100_max": 0.19684719417586272, + "nauc_mrr_at_100_std": 0.09976634385959421, + "nauc_mrr_at_10_diff1": 0.2555781170961617, + "nauc_mrr_at_10_max": 0.19492756523108676, + "nauc_mrr_at_10_std": 0.09345623639870085, + "nauc_mrr_at_1_diff1": 0.2848683967457831, + "nauc_mrr_at_1_max": 0.1830195596824384, + "nauc_mrr_at_1_std": 0.07549803331789048, + "nauc_mrr_at_20_diff1": 0.2563069637891677, + "nauc_mrr_at_20_max": 0.19606651845976975, + "nauc_mrr_at_20_std": 0.09674388949169618, + "nauc_mrr_at_3_diff1": 0.2585477342231996, + "nauc_mrr_at_3_max": 0.1912753471137965, + "nauc_mrr_at_3_std": 0.08053735917881188, + "nauc_mrr_at_5_diff1": 0.25700358762170694, + "nauc_mrr_at_5_max": 0.19434259852483204, + "nauc_mrr_at_5_std": 0.08786770986492323, + "nauc_ndcg_at_1000_diff1": 0.24184119552815495, + "nauc_ndcg_at_1000_max": 0.21354780608563487, + "nauc_ndcg_at_1000_std": 0.14305674051908118, + "nauc_ndcg_at_100_diff1": 0.24421269326316716, + "nauc_ndcg_at_100_max": 0.21043467237538288, + "nauc_ndcg_at_100_std": 0.1388934993549178, + "nauc_ndcg_at_10_diff1": 0.2463649756724755, + "nauc_ndcg_at_10_max": 0.20042142395462284, + "nauc_ndcg_at_10_std": 0.10624825268544366, + "nauc_ndcg_at_1_diff1": 0.2848683967457831, + "nauc_ndcg_at_1_max": 0.1830195596824384, + "nauc_ndcg_at_1_std": 0.07549803331789048, + "nauc_ndcg_at_20_diff1": 0.2487107186269684, + "nauc_ndcg_at_20_max": 0.20365903205672417, + "nauc_ndcg_at_20_std": 0.11642308796600508, + "nauc_ndcg_at_3_diff1": 0.251457194280321, + "nauc_ndcg_at_3_max": 0.19423146533482583, + "nauc_ndcg_at_3_std": 0.08227578532712543, + "nauc_ndcg_at_5_diff1": 0.2492574773137313, + "nauc_ndcg_at_5_max": 0.19890414363555564, + "nauc_ndcg_at_5_std": 0.09408857892653899, + "nauc_precision_at_1000_diff1": 0.18183067153859603, + "nauc_precision_at_1000_max": 0.30236337970384225, + "nauc_precision_at_1000_std": 0.3611693942676633, + "nauc_precision_at_100_diff1": 0.21526778505439934, + "nauc_precision_at_100_max": 0.25329159656656847, + "nauc_precision_at_100_std": 0.2660871201793366, + "nauc_precision_at_10_diff1": 0.22683720088084672, + "nauc_precision_at_10_max": 0.21259359820665966, + "nauc_precision_at_10_std": 0.13644549436238546, + "nauc_precision_at_1_diff1": 0.2848683967457831, + "nauc_precision_at_1_max": 0.1830195596824384, + "nauc_precision_at_1_std": 0.07549803331789048, + "nauc_precision_at_20_diff1": 0.23417000614610253, + "nauc_precision_at_20_max": 0.22118613386704095, + "nauc_precision_at_20_std": 0.1651117205647171, + "nauc_precision_at_3_diff1": 0.2352261255947383, + "nauc_precision_at_3_max": 0.20116450535402647, + "nauc_precision_at_3_std": 0.08634168257919944, + "nauc_precision_at_5_diff1": 0.23244230154551532, + "nauc_precision_at_5_max": 0.20915248223704294, + "nauc_precision_at_5_std": 0.10853485283972363, + "nauc_recall_at_1000_diff1": 0.1818306715385971, + "nauc_recall_at_1000_max": 0.3023633797038426, + "nauc_recall_at_1000_std": 0.3611693942676637, + "nauc_recall_at_100_diff1": 0.21526778505439942, + "nauc_recall_at_100_max": 0.2532915965665688, + "nauc_recall_at_100_std": 0.2660871201793368, + "nauc_recall_at_10_diff1": 0.22683720088084675, + "nauc_recall_at_10_max": 0.21259359820665977, + "nauc_recall_at_10_std": 0.1364454943623858, + "nauc_recall_at_1_diff1": 0.2848683967457831, + "nauc_recall_at_1_max": 0.1830195596824384, + "nauc_recall_at_1_std": 0.07549803331789048, + "nauc_recall_at_20_diff1": 0.23417000614610275, + "nauc_recall_at_20_max": 0.22118613386704117, + "nauc_recall_at_20_std": 0.1651117205647171, + "nauc_recall_at_3_diff1": 0.2352261255947385, + "nauc_recall_at_3_max": 0.20116450535402647, + "nauc_recall_at_3_std": 0.08634168257919939, + "nauc_recall_at_5_diff1": 0.23244230154551535, + "nauc_recall_at_5_max": 0.20915248223704297, + "nauc_recall_at_5_std": 0.1085348528397236, + "ndcg_at_1": 0.10526, + "ndcg_at_10": 0.20509, + "ndcg_at_100": 0.24655, + "ndcg_at_1000": 0.27372, + "ndcg_at_20": 0.21991, + "ndcg_at_3": 0.16409, + "ndcg_at_5": 0.18494, + "precision_at_1": 0.10526, + "precision_at_10": 0.03206, + "precision_at_100": 0.00526, + "precision_at_1000": 0.00075, + "precision_at_20": 0.01896, + "precision_at_3": 0.06914, + "precision_at_5": 0.05162, + "recall_at_1": 0.10526, + "recall_at_10": 0.32055, + "recall_at_100": 0.52559, + "recall_at_1000": 0.74716, + "recall_at_20": 0.37921, + "recall_at_3": 0.20743, + "recall_at_5": 0.25812 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/PIQA.json b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/PIQA.json new file mode 100644 index 000000000..1179594bb --- /dev/null +++ b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/PIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 5.4732277393341064, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.24684, + "map_at_1": 0.12133, + "map_at_10": 0.20396, + "map_at_100": 0.21168, + "map_at_1000": 0.21236, + "map_at_20": 0.20821, + "map_at_3": 0.18226, + "map_at_5": 0.19404, + "mrr_at_1": 0.12132752992383025, + "mrr_at_10": 0.20396264055132368, + "mrr_at_100": 0.21167903861920834, + "mrr_at_1000": 0.21235846363973274, + "mrr_at_20": 0.20820739946137432, + "mrr_at_3": 0.18226332970620224, + "mrr_at_5": 0.19404243743199096, + "nauc_map_at_1000_diff1": 0.014283787455313552, + "nauc_map_at_1000_max": 0.31844530205741406, + "nauc_map_at_1000_std": 0.05133162553927162, + "nauc_map_at_100_diff1": 0.014213515515727453, + "nauc_map_at_100_max": 0.31835813590034084, + "nauc_map_at_100_std": 0.05115417008456484, + "nauc_map_at_10_diff1": 0.01606684289542216, + "nauc_map_at_10_max": 0.32022144877720526, + "nauc_map_at_10_std": 0.047263849406718954, + "nauc_map_at_1_diff1": 0.0989433022331635, + "nauc_map_at_1_max": 0.26260599255581774, + "nauc_map_at_1_std": 0.025574571410438972, + "nauc_map_at_20_diff1": 0.016189897239432278, + "nauc_map_at_20_max": 0.31824650990083025, + "nauc_map_at_20_std": 0.048856989562354514, + "nauc_map_at_3_diff1": 0.02858146837618823, + "nauc_map_at_3_max": 0.31475205528190925, + "nauc_map_at_3_std": 0.034144914135810896, + "nauc_map_at_5_diff1": 0.022034205104986854, + "nauc_map_at_5_max": 0.3177130179634545, + "nauc_map_at_5_std": 0.038123362285869315, + "nauc_mrr_at_1000_diff1": 0.014283728101272113, + "nauc_mrr_at_1000_max": 0.3184454446622737, + "nauc_mrr_at_1000_std": 0.05133191806543639, + "nauc_mrr_at_100_diff1": 0.014213460396215814, + "nauc_mrr_at_100_max": 0.3183582695222141, + "nauc_mrr_at_100_std": 0.05115444264879206, + "nauc_mrr_at_10_diff1": 0.01606684289542216, + "nauc_mrr_at_10_max": 0.32022144877720526, + "nauc_mrr_at_10_std": 0.047263849406718954, + "nauc_mrr_at_1_diff1": 0.0989433022331635, + "nauc_mrr_at_1_max": 0.26260599255581774, + "nauc_mrr_at_1_std": 0.025574571410438972, + "nauc_mrr_at_20_diff1": 0.016189897239432278, + "nauc_mrr_at_20_max": 0.31824650990083025, + "nauc_mrr_at_20_std": 0.048856989562354514, + "nauc_mrr_at_3_diff1": 0.02858146837618823, + "nauc_mrr_at_3_max": 0.31475205528190925, + "nauc_mrr_at_3_std": 0.034144914135810896, + "nauc_mrr_at_5_diff1": 0.022034205104986854, + "nauc_mrr_at_5_max": 0.3177130179634545, + "nauc_mrr_at_5_std": 0.038123362285869315, + "nauc_ndcg_at_1000_diff1": -0.017634117570182073, + "nauc_ndcg_at_1000_max": 0.3329963262856198, + "nauc_ndcg_at_1000_std": 0.08862442657381038, + "nauc_ndcg_at_100_diff1": -0.020496520977799706, + "nauc_ndcg_at_100_max": 0.33157551633385796, + "nauc_ndcg_at_100_std": 0.08476283024240498, + "nauc_ndcg_at_10_diff1": -0.009319958187418141, + "nauc_ndcg_at_10_max": 0.3349570779885499, + "nauc_ndcg_at_10_std": 0.06431722966455784, + "nauc_ndcg_at_1_diff1": 0.0989433022331635, + "nauc_ndcg_at_1_max": 0.26260599255581774, + "nauc_ndcg_at_1_std": 0.025574571410438972, + "nauc_ndcg_at_20_diff1": -0.008945614015062046, + "nauc_ndcg_at_20_max": 0.32893352001477283, + "nauc_ndcg_at_20_std": 0.06929256575023786, + "nauc_ndcg_at_3_diff1": 0.013950998395833381, + "nauc_ndcg_at_3_max": 0.32614220841062375, + "nauc_ndcg_at_3_std": 0.03720125081224806, + "nauc_ndcg_at_5_diff1": 0.003325921595544366, + "nauc_ndcg_at_5_max": 0.33099357461017603, + "nauc_ndcg_at_5_std": 0.04433986873667119, + "nauc_precision_at_1000_diff1": -0.13746449314724507, + "nauc_precision_at_1000_max": 0.3928415535702204, + "nauc_precision_at_1000_std": 0.28578719416831844, + "nauc_precision_at_100_diff1": -0.12293618603226258, + "nauc_precision_at_100_max": 0.36603374568798913, + "nauc_precision_at_100_std": 0.2003460177429074, + "nauc_precision_at_10_diff1": -0.06759744831240334, + "nauc_precision_at_10_max": 0.36678503459417955, + "nauc_precision_at_10_std": 0.10777719690769895, + "nauc_precision_at_1_diff1": 0.0989433022331635, + "nauc_precision_at_1_max": 0.26260599255581774, + "nauc_precision_at_1_std": 0.025574571410438972, + "nauc_precision_at_20_diff1": -0.06686902201112956, + "nauc_precision_at_20_max": 0.3487818210274398, + "nauc_precision_at_20_std": 0.12328157085785484, + "nauc_precision_at_3_diff1": -0.019222001518247763, + "nauc_precision_at_3_max": 0.35212984177064616, + "nauc_precision_at_3_std": 0.044507634254238614, + "nauc_precision_at_5_diff1": -0.03839073496623614, + "nauc_precision_at_5_max": 0.3605113445817558, + "nauc_precision_at_5_std": 0.059317602926378554, + "nauc_recall_at_1000_diff1": -0.1374644931472446, + "nauc_recall_at_1000_max": 0.39284155357022144, + "nauc_recall_at_1000_std": 0.2857871941683188, + "nauc_recall_at_100_diff1": -0.12293618603226336, + "nauc_recall_at_100_max": 0.36603374568798847, + "nauc_recall_at_100_std": 0.20034601774290753, + "nauc_recall_at_10_diff1": -0.06759744831240319, + "nauc_recall_at_10_max": 0.3667850345941801, + "nauc_recall_at_10_std": 0.10777719690769921, + "nauc_recall_at_1_diff1": 0.0989433022331635, + "nauc_recall_at_1_max": 0.26260599255581774, + "nauc_recall_at_1_std": 0.025574571410438972, + "nauc_recall_at_20_diff1": -0.06686902201112983, + "nauc_recall_at_20_max": 0.3487818210274396, + "nauc_recall_at_20_std": 0.12328157085785496, + "nauc_recall_at_3_diff1": -0.01922200151824761, + "nauc_recall_at_3_max": 0.3521298417706464, + "nauc_recall_at_3_std": 0.044507634254238815, + "nauc_recall_at_5_diff1": -0.038390734966236184, + "nauc_recall_at_5_max": 0.3605113445817557, + "nauc_recall_at_5_std": 0.05931760292637841, + "ndcg_at_1": 0.12133, + "ndcg_at_10": 0.24684, + "ndcg_at_100": 0.28742, + "ndcg_at_1000": 0.30874, + "ndcg_at_20": 0.26227, + "ndcg_at_3": 0.20172, + "ndcg_at_5": 0.22298, + "precision_at_1": 0.12133, + "precision_at_10": 0.0383, + "precision_at_100": 0.00579, + "precision_at_1000": 0.00075, + "precision_at_20": 0.0222, + "precision_at_3": 0.08596, + "precision_at_5": 0.06192, + "recall_at_1": 0.12133, + "recall_at_10": 0.38303, + "recall_at_100": 0.57943, + "recall_at_1000": 0.75462, + "recall_at_20": 0.44396, + "recall_at_3": 0.25789, + "recall_at_5": 0.30958 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/Quail.json b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/Quail.json new file mode 100644 index 000000000..d1e86da2c --- /dev/null +++ b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/Quail.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 6.339292764663696, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.03465, + "map_at_1": 0.01213, + "map_at_10": 0.02524, + "map_at_100": 0.03011, + "map_at_1000": 0.03078, + "map_at_20": 0.02806, + "map_at_3": 0.01942, + "map_at_5": 0.02229, + "mrr_at_1": 0.01213235294117647, + "mrr_at_10": 0.02523721988795521, + "mrr_at_100": 0.030109889563385644, + "mrr_at_1000": 0.030784487723827504, + "mrr_at_20": 0.028079289859973624, + "mrr_at_3": 0.019424019607843145, + "mrr_at_5": 0.02229166666666668, + "nauc_map_at_1000_diff1": 0.1309881121544304, + "nauc_map_at_1000_max": 0.1780007689102083, + "nauc_map_at_1000_std": 0.17474860831975436, + "nauc_map_at_100_diff1": 0.13182701033276012, + "nauc_map_at_100_max": 0.17730928599059306, + "nauc_map_at_100_std": 0.17399075448453596, + "nauc_map_at_10_diff1": 0.14932824467780173, + "nauc_map_at_10_max": 0.18335969412724853, + "nauc_map_at_10_std": 0.17891600968336563, + "nauc_map_at_1_diff1": 0.18126529583465453, + "nauc_map_at_1_max": 0.24489596799765834, + "nauc_map_at_1_std": 0.23132586937255567, + "nauc_map_at_20_diff1": 0.13903686123633283, + "nauc_map_at_20_max": 0.18021001775282852, + "nauc_map_at_20_std": 0.17270031152827128, + "nauc_map_at_3_diff1": 0.16782300528414446, + "nauc_map_at_3_max": 0.18507709535413425, + "nauc_map_at_3_std": 0.17754572947516603, + "nauc_map_at_5_diff1": 0.15798956340320325, + "nauc_map_at_5_max": 0.18813974012204301, + "nauc_map_at_5_std": 0.18050058316258363, + "nauc_mrr_at_1000_diff1": 0.13097251440016436, + "nauc_mrr_at_1000_max": 0.177987194406999, + "nauc_mrr_at_1000_std": 0.17474800092900789, + "nauc_mrr_at_100_diff1": 0.1318114685991495, + "nauc_mrr_at_100_max": 0.17729556316368306, + "nauc_mrr_at_100_std": 0.17398968329466988, + "nauc_mrr_at_10_diff1": 0.14932824467780173, + "nauc_mrr_at_10_max": 0.18335969412724853, + "nauc_mrr_at_10_std": 0.17891600968336563, + "nauc_mrr_at_1_diff1": 0.18126529583465453, + "nauc_mrr_at_1_max": 0.24489596799765834, + "nauc_mrr_at_1_std": 0.23132586937255567, + "nauc_mrr_at_20_diff1": 0.1387034432248586, + "nauc_mrr_at_20_max": 0.17992218897125187, + "nauc_mrr_at_20_std": 0.17268989414790667, + "nauc_mrr_at_3_diff1": 0.16782300528414446, + "nauc_mrr_at_3_max": 0.18507709535413425, + "nauc_mrr_at_3_std": 0.17754572947516603, + "nauc_mrr_at_5_diff1": 0.15798956340320325, + "nauc_mrr_at_5_max": 0.18813974012204301, + "nauc_mrr_at_5_std": 0.18050058316258363, + "nauc_ndcg_at_1000_diff1": 0.07496661989114274, + "nauc_ndcg_at_1000_max": 0.16521225937855222, + "nauc_ndcg_at_1000_std": 0.17484697219868534, + "nauc_ndcg_at_100_diff1": 0.08954932948950015, + "nauc_ndcg_at_100_max": 0.15324542229819574, + "nauc_ndcg_at_100_std": 0.16281862912642314, + "nauc_ndcg_at_10_diff1": 0.13497894618768552, + "nauc_ndcg_at_10_max": 0.1716594091881175, + "nauc_ndcg_at_10_std": 0.16926018043987048, + "nauc_ndcg_at_1_diff1": 0.18126529583465453, + "nauc_ndcg_at_1_max": 0.24489596799765834, + "nauc_ndcg_at_1_std": 0.23132586937255567, + "nauc_ndcg_at_20_diff1": 0.11349020039808734, + "nauc_ndcg_at_20_max": 0.16826666761338677, + "nauc_ndcg_at_20_std": 0.15993297333664974, + "nauc_ndcg_at_3_diff1": 0.1615068165068899, + "nauc_ndcg_at_3_max": 0.17031574137750816, + "nauc_ndcg_at_3_std": 0.16406831444511902, + "nauc_ndcg_at_5_diff1": 0.14772882065141713, + "nauc_ndcg_at_5_max": 0.1775267476717012, + "nauc_ndcg_at_5_std": 0.1704097513221365, + "nauc_precision_at_1000_diff1": 0.02117749042561679, + "nauc_precision_at_1000_max": 0.16291511867079903, + "nauc_precision_at_1000_std": 0.1846458540283057, + "nauc_precision_at_100_diff1": 0.051299246311514654, + "nauc_precision_at_100_max": 0.13003144262858218, + "nauc_precision_at_100_std": 0.15473766555020374, + "nauc_precision_at_10_diff1": 0.11613276513079113, + "nauc_precision_at_10_max": 0.1578845597504547, + "nauc_precision_at_10_std": 0.15787106918710384, + "nauc_precision_at_1_diff1": 0.18126529583465453, + "nauc_precision_at_1_max": 0.24489596799765834, + "nauc_precision_at_1_std": 0.23132586937255567, + "nauc_precision_at_20_diff1": 0.08594906204224374, + "nauc_precision_at_20_max": 0.158261116098852, + "nauc_precision_at_20_std": 0.14867173841137868, + "nauc_precision_at_3_diff1": 0.1488740699051744, + "nauc_precision_at_3_max": 0.14193067071534685, + "nauc_precision_at_3_std": 0.13811867257390043, + "nauc_precision_at_5_diff1": 0.13040903749895907, + "nauc_precision_at_5_max": 0.1613320318644005, + "nauc_precision_at_5_std": 0.15476531924539466, + "nauc_recall_at_1000_diff1": 0.021177490425616775, + "nauc_recall_at_1000_max": 0.16291511867079939, + "nauc_recall_at_1000_std": 0.18464585402830574, + "nauc_recall_at_100_diff1": 0.05129924631151453, + "nauc_recall_at_100_max": 0.1300314426285819, + "nauc_recall_at_100_std": 0.15473766555020343, + "nauc_recall_at_10_diff1": 0.11613276513079103, + "nauc_recall_at_10_max": 0.1578845597504546, + "nauc_recall_at_10_std": 0.15787106918710364, + "nauc_recall_at_1_diff1": 0.18126529583465453, + "nauc_recall_at_1_max": 0.24489596799765834, + "nauc_recall_at_1_std": 0.23132586937255567, + "nauc_recall_at_20_diff1": 0.08594906204224356, + "nauc_recall_at_20_max": 0.15826111609885188, + "nauc_recall_at_20_std": 0.14867173841137843, + "nauc_recall_at_3_diff1": 0.1488740699051745, + "nauc_recall_at_3_max": 0.1419306707153468, + "nauc_recall_at_3_std": 0.13811867257390043, + "nauc_recall_at_5_diff1": 0.13040903749895913, + "nauc_recall_at_5_max": 0.16133203186440054, + "nauc_recall_at_5_std": 0.15476531924539488, + "ndcg_at_1": 0.01213, + "ndcg_at_10": 0.03465, + "ndcg_at_100": 0.06082, + "ndcg_at_1000": 0.08334, + "ndcg_at_20": 0.04496, + "ndcg_at_3": 0.02215, + "ndcg_at_5": 0.02731, + "precision_at_1": 0.01213, + "precision_at_10": 0.00658, + "precision_at_100": 0.00194, + "precision_at_1000": 0.00038, + "precision_at_20": 0.00533, + "precision_at_3": 0.01005, + "precision_at_5": 0.00853, + "recall_at_1": 0.01213, + "recall_at_10": 0.06581, + "recall_at_100": 0.19449, + "recall_at_1000": 0.38199, + "recall_at_20": 0.10662, + "recall_at_3": 0.03015, + "recall_at_5": 0.04265 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/RARbCode.json b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/RARbCode.json new file mode 100644 index 000000000..5e9df557c --- /dev/null +++ b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/RARbCode.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 134.80099868774414, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.4247, + "map_at_1": 0.28235, + "map_at_10": 0.37632, + "map_at_100": 0.3863, + "map_at_1000": 0.38693, + "map_at_20": 0.38232, + "map_at_3": 0.35153, + "map_at_5": 0.36612, + "mrr_at_1": 0.28234501347708896, + "mrr_at_10": 0.3763321995464853, + "mrr_at_100": 0.38631682552100366, + "mrr_at_1000": 0.3869456373885609, + "mrr_at_20": 0.3823350484491405, + "mrr_at_3": 0.3515274034141957, + "mrr_at_5": 0.3661163522012576, + "nauc_map_at_1000_diff1": 0.42588293443878106, + "nauc_map_at_1000_max": 0.2975583646086392, + "nauc_map_at_1000_std": 0.07883009185437109, + "nauc_map_at_100_diff1": 0.4256628809436213, + "nauc_map_at_100_max": 0.297326202227266, + "nauc_map_at_100_std": 0.07883391906687844, + "nauc_map_at_10_diff1": 0.42448221336685654, + "nauc_map_at_10_max": 0.2986338396648249, + "nauc_map_at_10_std": 0.07596662453193963, + "nauc_map_at_1_diff1": 0.5082883630668867, + "nauc_map_at_1_max": 0.2769025813951085, + "nauc_map_at_1_std": 0.04539535812221134, + "nauc_map_at_20_diff1": 0.424014833678709, + "nauc_map_at_20_max": 0.29731576190108605, + "nauc_map_at_20_std": 0.07802956814456148, + "nauc_map_at_3_diff1": 0.431990936059351, + "nauc_map_at_3_max": 0.29537448829505947, + "nauc_map_at_3_std": 0.06616037736815998, + "nauc_map_at_5_diff1": 0.4254599604822691, + "nauc_map_at_5_max": 0.2971605068982014, + "nauc_map_at_5_std": 0.07459448201051809, + "nauc_mrr_at_1000_diff1": 0.4258808146336753, + "nauc_mrr_at_1000_max": 0.2969436981503061, + "nauc_mrr_at_1000_std": 0.07709838172866071, + "nauc_mrr_at_100_diff1": 0.4256607604510835, + "nauc_mrr_at_100_max": 0.29671248158784813, + "nauc_mrr_at_100_std": 0.07710500919422546, + "nauc_mrr_at_10_diff1": 0.42447252930564766, + "nauc_mrr_at_10_max": 0.2980227972793701, + "nauc_mrr_at_10_std": 0.07426779165960372, + "nauc_mrr_at_1_diff1": 0.5082883630668867, + "nauc_mrr_at_1_max": 0.2757181787225371, + "nauc_mrr_at_1_std": 0.04197051076648685, + "nauc_mrr_at_20_diff1": 0.42401312846620187, + "nauc_mrr_at_20_max": 0.2967070490333568, + "nauc_mrr_at_20_std": 0.07631303190147899, + "nauc_mrr_at_3_diff1": 0.431990936059351, + "nauc_mrr_at_3_max": 0.2948017179688943, + "nauc_mrr_at_3_std": 0.06450414086816512, + "nauc_mrr_at_5_diff1": 0.4254599604822691, + "nauc_mrr_at_5_max": 0.29658455350949714, + "nauc_mrr_at_5_std": 0.07292904129005628, + "nauc_ndcg_at_1000_diff1": 0.4062876975398227, + "nauc_ndcg_at_1000_max": 0.3042438921520285, + "nauc_ndcg_at_1000_std": 0.10006840897141236, + "nauc_ndcg_at_100_diff1": 0.398951832327945, + "nauc_ndcg_at_100_max": 0.29769412069681617, + "nauc_ndcg_at_100_std": 0.10243740153134236, + "nauc_ndcg_at_10_diff1": 0.3935420712152924, + "nauc_ndcg_at_10_max": 0.30415162970517706, + "nauc_ndcg_at_10_std": 0.08797668046034772, + "nauc_ndcg_at_1_diff1": 0.5082883630668867, + "nauc_ndcg_at_1_max": 0.2769025813951085, + "nauc_ndcg_at_1_std": 0.04539535812221134, + "nauc_ndcg_at_20_diff1": 0.39013529370100275, + "nauc_ndcg_at_20_max": 0.298975628034813, + "nauc_ndcg_at_20_std": 0.095930350844033, + "nauc_ndcg_at_3_diff1": 0.40799951496514775, + "nauc_ndcg_at_3_max": 0.2975352461979362, + "nauc_ndcg_at_3_std": 0.06988680172173267, + "nauc_ndcg_at_5_diff1": 0.39614471912130506, + "nauc_ndcg_at_5_max": 0.3010824298639677, + "nauc_ndcg_at_5_std": 0.08473848177177792, + "nauc_precision_at_1000_diff1": 0.2932713004112303, + "nauc_precision_at_1000_max": 0.5377252487720711, + "nauc_precision_at_1000_std": 0.5365963753019272, + "nauc_precision_at_100_diff1": 0.2658690877500581, + "nauc_precision_at_100_max": 0.2822465735871644, + "nauc_precision_at_100_std": 0.27072716102188454, + "nauc_precision_at_10_diff1": 0.2965662236458188, + "nauc_precision_at_10_max": 0.32122896997656586, + "nauc_precision_at_10_std": 0.1267502829989326, + "nauc_precision_at_1_diff1": 0.5082883630668867, + "nauc_precision_at_1_max": 0.2769025813951085, + "nauc_precision_at_1_std": 0.04539535812221134, + "nauc_precision_at_20_diff1": 0.2643759708987758, + "nauc_precision_at_20_max": 0.2989893858663729, + "nauc_precision_at_20_std": 0.168861533330369, + "nauc_precision_at_3_diff1": 0.3406143764239548, + "nauc_precision_at_3_max": 0.3025204402105395, + "nauc_precision_at_3_std": 0.07952045469216078, + "nauc_precision_at_5_diff1": 0.3107287140000561, + "nauc_precision_at_5_max": 0.3119032280392485, + "nauc_precision_at_5_std": 0.11474644390505934, + "nauc_recall_at_1000_diff1": 0.29327130041123484, + "nauc_recall_at_1000_max": 0.5377252487720771, + "nauc_recall_at_1000_std": 0.5365963753019315, + "nauc_recall_at_100_diff1": 0.2658690877500584, + "nauc_recall_at_100_max": 0.2822465735871649, + "nauc_recall_at_100_std": 0.27072716102188493, + "nauc_recall_at_10_diff1": 0.2965662236458186, + "nauc_recall_at_10_max": 0.3212289699765658, + "nauc_recall_at_10_std": 0.1267502829989323, + "nauc_recall_at_1_diff1": 0.5082883630668867, + "nauc_recall_at_1_max": 0.2769025813951085, + "nauc_recall_at_1_std": 0.04539535812221134, + "nauc_recall_at_20_diff1": 0.26437597089877646, + "nauc_recall_at_20_max": 0.29898938586637297, + "nauc_recall_at_20_std": 0.16886153333036963, + "nauc_recall_at_3_diff1": 0.34061437642395465, + "nauc_recall_at_3_max": 0.3025204402105394, + "nauc_recall_at_3_std": 0.07952045469216078, + "nauc_recall_at_5_diff1": 0.3107287140000558, + "nauc_recall_at_5_max": 0.31190322803924847, + "nauc_recall_at_5_std": 0.11474644390505906, + "ndcg_at_1": 0.28235, + "ndcg_at_10": 0.4247, + "ndcg_at_100": 0.47459, + "ndcg_at_1000": 0.49172, + "ndcg_at_20": 0.44641, + "ndcg_at_3": 0.37424, + "ndcg_at_5": 0.40029, + "precision_at_1": 0.28235, + "precision_at_10": 0.05775, + "precision_at_100": 0.00813, + "precision_at_1000": 0.00095, + "precision_at_20": 0.03315, + "precision_at_3": 0.14668, + "precision_at_5": 0.10054, + "recall_at_1": 0.28235, + "recall_at_10": 0.57749, + "recall_at_100": 0.81334, + "recall_at_1000": 0.94946, + "recall_at_20": 0.66307, + "recall_at_3": 0.44003, + "recall_at_5": 0.5027 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/RARbMath.json b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/RARbMath.json new file mode 100644 index 000000000..8f9057c7d --- /dev/null +++ b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/RARbMath.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 247.88923478126526, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.62387, + "map_at_1": 0.5542, + "map_at_10": 0.5999, + "map_at_100": 0.60609, + "map_at_1000": 0.60655, + "map_at_20": 0.60323, + "map_at_3": 0.58765, + "map_at_5": 0.59406, + "mrr_at_1": 0.5540433612913436, + "mrr_at_10": 0.5998210863181593, + "mrr_at_100": 0.6060101054146299, + "mrr_at_1000": 0.606471319875597, + "mrr_at_20": 0.603149457489372, + "mrr_at_3": 0.5875665980904161, + "mrr_at_5": 0.5939837527034869, + "nauc_map_at_1000_diff1": 0.8107930908687988, + "nauc_map_at_1000_max": 0.4260774276612989, + "nauc_map_at_1000_std": -0.28798595479570666, + "nauc_map_at_100_diff1": 0.8106273454734498, + "nauc_map_at_100_max": 0.4260224179443739, + "nauc_map_at_100_std": -0.28811088897870346, + "nauc_map_at_10_diff1": 0.8115702593397276, + "nauc_map_at_10_max": 0.4241728942057318, + "nauc_map_at_10_std": -0.2886578699801378, + "nauc_map_at_1_diff1": 0.8458567763721575, + "nauc_map_at_1_max": 0.44451207797844194, + "nauc_map_at_1_std": -0.2858767598219191, + "nauc_map_at_20_diff1": 0.8107240613827668, + "nauc_map_at_20_max": 0.42505603949530035, + "nauc_map_at_20_std": -0.2885790342841267, + "nauc_map_at_3_diff1": 0.8182603436892528, + "nauc_map_at_3_max": 0.4261297918963336, + "nauc_map_at_3_std": -0.28886807612882454, + "nauc_map_at_5_diff1": 0.8150492493653809, + "nauc_map_at_5_max": 0.4268770429460275, + "nauc_map_at_5_std": -0.2890504610730171, + "nauc_mrr_at_1000_diff1": 0.8109771320580916, + "nauc_mrr_at_1000_max": 0.4262251499083839, + "nauc_mrr_at_1000_std": -0.2877719308135018, + "nauc_mrr_at_100_diff1": 0.8108111483947898, + "nauc_mrr_at_100_max": 0.42616994450043544, + "nauc_mrr_at_100_std": -0.28789714935985505, + "nauc_mrr_at_10_diff1": 0.8117512383628663, + "nauc_mrr_at_10_max": 0.42431839225905055, + "nauc_mrr_at_10_std": -0.2884472640890499, + "nauc_mrr_at_1_diff1": 0.8461900443587859, + "nauc_mrr_at_1_max": 0.444781245399084, + "nauc_mrr_at_1_std": -0.2854825817391683, + "nauc_mrr_at_20_diff1": 0.8109065318217072, + "nauc_mrr_at_20_max": 0.4252025926562565, + "nauc_mrr_at_20_std": -0.28836679072854904, + "nauc_mrr_at_3_diff1": 0.8184368444664766, + "nauc_mrr_at_3_max": 0.42627199548231626, + "nauc_mrr_at_3_std": -0.2886619669618197, + "nauc_mrr_at_5_diff1": 0.8152280429834865, + "nauc_mrr_at_5_max": 0.42702079243042573, + "nauc_mrr_at_5_std": -0.2888419969012934, + "nauc_ndcg_at_1000_diff1": 0.7959071274575394, + "nauc_ndcg_at_1000_max": 0.42523116652289483, + "nauc_ndcg_at_1000_std": -0.2825706201147159, + "nauc_ndcg_at_100_diff1": 0.790289295738062, + "nauc_ndcg_at_100_max": 0.42408904496287125, + "nauc_ndcg_at_100_std": -0.2844696921835686, + "nauc_ndcg_at_10_diff1": 0.7942193909873827, + "nauc_ndcg_at_10_max": 0.4140520313121641, + "nauc_ndcg_at_10_std": -0.289686591562302, + "nauc_ndcg_at_1_diff1": 0.8458567763721575, + "nauc_ndcg_at_1_max": 0.44451207797844194, + "nauc_ndcg_at_1_std": -0.2858767598219191, + "nauc_ndcg_at_20_diff1": 0.7903455811294623, + "nauc_ndcg_at_20_max": 0.4166567176636, + "nauc_ndcg_at_20_std": -0.2895563746056667, + "nauc_ndcg_at_3_diff1": 0.8095143949396701, + "nauc_ndcg_at_3_max": 0.4196769182838012, + "nauc_ndcg_at_3_std": -0.29024022525125814, + "nauc_ndcg_at_5_diff1": 0.8033660846973552, + "nauc_ndcg_at_5_max": 0.4210802080914773, + "nauc_ndcg_at_5_std": -0.2905241226222715, + "nauc_precision_at_1000_diff1": 0.6094153604188238, + "nauc_precision_at_1000_max": 0.5313757351321383, + "nauc_precision_at_1000_std": -0.0563297757561895, + "nauc_precision_at_100_diff1": 0.6444839574833875, + "nauc_precision_at_100_max": 0.4407013044305379, + "nauc_precision_at_100_std": -0.23504969487792698, + "nauc_precision_at_10_diff1": 0.7289605085737365, + "nauc_precision_at_10_max": 0.3759476757824112, + "nauc_precision_at_10_std": -0.29309547570488, + "nauc_precision_at_1_diff1": 0.8458567763721575, + "nauc_precision_at_1_max": 0.44451207797844194, + "nauc_precision_at_1_std": -0.2858767598219191, + "nauc_precision_at_20_diff1": 0.6989575988168195, + "nauc_precision_at_20_max": 0.3820647726994443, + "nauc_precision_at_20_std": -0.29327712037054043, + "nauc_precision_at_3_diff1": 0.7829161026277973, + "nauc_precision_at_3_max": 0.3998339996858003, + "nauc_precision_at_3_std": -0.29456090508476257, + "nauc_precision_at_5_diff1": 0.765235248382252, + "nauc_precision_at_5_max": 0.402814635003933, + "nauc_precision_at_5_std": -0.2953409965412914, + "nauc_recall_at_1000_diff1": 0.6094153604188263, + "nauc_recall_at_1000_max": 0.5313757351321442, + "nauc_recall_at_1000_std": -0.0563297757561907, + "nauc_recall_at_100_diff1": 0.644483957483384, + "nauc_recall_at_100_max": 0.4407013044305365, + "nauc_recall_at_100_std": -0.2350496948779282, + "nauc_recall_at_10_diff1": 0.7289605085737356, + "nauc_recall_at_10_max": 0.37594767578241156, + "nauc_recall_at_10_std": -0.2930954757048794, + "nauc_recall_at_1_diff1": 0.8458567763721575, + "nauc_recall_at_1_max": 0.44451207797844194, + "nauc_recall_at_1_std": -0.2858767598219191, + "nauc_recall_at_20_diff1": 0.6989575988168193, + "nauc_recall_at_20_max": 0.3820647726994452, + "nauc_recall_at_20_std": -0.2932771203705389, + "nauc_recall_at_3_diff1": 0.7829161026277975, + "nauc_recall_at_3_max": 0.39983399968580013, + "nauc_recall_at_3_std": -0.29456090508476285, + "nauc_recall_at_5_diff1": 0.7652352483822521, + "nauc_recall_at_5_max": 0.40281463500393383, + "nauc_recall_at_5_std": -0.2953409965412905, + "ndcg_at_1": 0.5542, + "ndcg_at_10": 0.62387, + "ndcg_at_100": 0.65689, + "ndcg_at_1000": 0.66938, + "ndcg_at_20": 0.636, + "ndcg_at_3": 0.59819, + "ndcg_at_5": 0.60977, + "precision_at_1": 0.5542, + "precision_at_10": 0.07003, + "precision_at_100": 0.00861, + "precision_at_1000": 0.00096, + "precision_at_20": 0.03741, + "precision_at_3": 0.20953, + "precision_at_5": 0.13135, + "recall_at_1": 0.5542, + "recall_at_10": 0.70027, + "recall_at_100": 0.86121, + "recall_at_1000": 0.9598, + "recall_at_20": 0.74822, + "recall_at_3": 0.62858, + "recall_at_5": 0.65675 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/SIQA.json b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/SIQA.json new file mode 100644 index 000000000..1df0eb320 --- /dev/null +++ b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/SIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 6.434633731842041, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01533, + "map_at_1": 0.00512, + "map_at_10": 0.01112, + "map_at_100": 0.013, + "map_at_1000": 0.01356, + "map_at_20": 0.01187, + "map_at_3": 0.00861, + "map_at_5": 0.00956, + "mrr_at_1": 0.00511770726714432, + "mrr_at_10": 0.011122483793926986, + "mrr_at_100": 0.013000221798508104, + "mrr_at_1000": 0.013557541679848718, + "mrr_at_20": 0.011874232508218204, + "mrr_at_3": 0.008614807233026272, + "mrr_at_5": 0.009561583077447972, + "nauc_map_at_1000_diff1": -0.006237535066193638, + "nauc_map_at_1000_max": -0.11284096994943947, + "nauc_map_at_1000_std": -0.10130692148017159, + "nauc_map_at_100_diff1": -0.004691802345870597, + "nauc_map_at_100_max": -0.11421872643743347, + "nauc_map_at_100_std": -0.10258803129841808, + "nauc_map_at_10_diff1": 0.0015748548794679406, + "nauc_map_at_10_max": -0.12570891391914518, + "nauc_map_at_10_std": -0.10685964328110285, + "nauc_map_at_1_diff1": -0.06685979428531999, + "nauc_map_at_1_max": -0.20498688450826993, + "nauc_map_at_1_std": -0.14661899996513097, + "nauc_map_at_20_diff1": 0.00021576795234552022, + "nauc_map_at_20_max": -0.12126852350982109, + "nauc_map_at_20_std": -0.10854809666880216, + "nauc_map_at_3_diff1": 0.007454165854714832, + "nauc_map_at_3_max": -0.086057667558602, + "nauc_map_at_3_std": -0.056718893741975786, + "nauc_map_at_5_diff1": 0.02255517407900852, + "nauc_map_at_5_max": -0.10532675259936228, + "nauc_map_at_5_std": -0.06786240563119256, + "nauc_mrr_at_1000_diff1": -0.006243319126322935, + "nauc_mrr_at_1000_max": -0.11284623574534185, + "nauc_mrr_at_1000_std": -0.10131159090275137, + "nauc_mrr_at_100_diff1": -0.004695670491054352, + "nauc_mrr_at_100_max": -0.11422347619071793, + "nauc_mrr_at_100_std": -0.10259188256014005, + "nauc_mrr_at_10_diff1": 0.0015748548794679406, + "nauc_mrr_at_10_max": -0.12570891391914518, + "nauc_mrr_at_10_std": -0.10685964328110285, + "nauc_mrr_at_1_diff1": -0.06685979428531999, + "nauc_mrr_at_1_max": -0.20498688450826993, + "nauc_mrr_at_1_std": -0.14661899996513097, + "nauc_mrr_at_20_diff1": 0.00021576795234552022, + "nauc_mrr_at_20_max": -0.12126852350982109, + "nauc_mrr_at_20_std": -0.10854809666880216, + "nauc_mrr_at_3_diff1": 0.007454165854714832, + "nauc_mrr_at_3_max": -0.086057667558602, + "nauc_mrr_at_3_std": -0.056718893741975786, + "nauc_mrr_at_5_diff1": 0.02255517407900852, + "nauc_mrr_at_5_max": -0.10532675259936228, + "nauc_mrr_at_5_std": -0.06786240563119256, + "nauc_ndcg_at_1000_diff1": -0.03218756175328398, + "nauc_ndcg_at_1000_max": -0.07577968800323445, + "nauc_ndcg_at_1000_std": -0.08005757853730892, + "nauc_ndcg_at_100_diff1": -0.021179347181306526, + "nauc_ndcg_at_100_max": -0.09618915360171995, + "nauc_ndcg_at_100_std": -0.10542432453106945, + "nauc_ndcg_at_10_diff1": -0.003941664451990678, + "nauc_ndcg_at_10_max": -0.13957407599113142, + "nauc_ndcg_at_10_std": -0.13178929222011057, + "nauc_ndcg_at_1_diff1": -0.06685979428531999, + "nauc_ndcg_at_1_max": -0.20498688450826993, + "nauc_ndcg_at_1_std": -0.14661899996513097, + "nauc_ndcg_at_20_diff1": -0.006183031102574828, + "nauc_ndcg_at_20_max": -0.1272368391755442, + "nauc_ndcg_at_20_std": -0.13299556059244874, + "nauc_ndcg_at_3_diff1": 0.01307971966682068, + "nauc_ndcg_at_3_max": -0.06904500637077705, + "nauc_ndcg_at_3_std": -0.04395366055458928, + "nauc_ndcg_at_5_diff1": 0.03424268085325115, + "nauc_ndcg_at_5_max": -0.10139745057283066, + "nauc_ndcg_at_5_std": -0.061874985514917526, + "nauc_precision_at_1000_diff1": -0.046148973617548564, + "nauc_precision_at_1000_max": -0.04843518432801955, + "nauc_precision_at_1000_std": -0.05619877495085748, + "nauc_precision_at_100_diff1": -0.03505137222397459, + "nauc_precision_at_100_max": -0.07795908006335965, + "nauc_precision_at_100_std": -0.10214882908578948, + "nauc_precision_at_10_diff1": -0.014732862011041688, + "nauc_precision_at_10_max": -0.16342935055320687, + "nauc_precision_at_10_std": -0.17067388927698598, + "nauc_precision_at_1_diff1": -0.06685979428531999, + "nauc_precision_at_1_max": -0.20498688450826993, + "nauc_precision_at_1_std": -0.14661899996513097, + "nauc_precision_at_20_diff1": -0.015631461976507333, + "nauc_precision_at_20_max": -0.13536998338467376, + "nauc_precision_at_20_std": -0.16294773967485382, + "nauc_precision_at_3_diff1": 0.02170066942746417, + "nauc_precision_at_3_max": -0.03907052126273127, + "nauc_precision_at_3_std": -0.021487148963251945, + "nauc_precision_at_5_diff1": 0.052531624711719474, + "nauc_precision_at_5_max": -0.09889749364654028, + "nauc_precision_at_5_std": -0.05419751264009104, + "nauc_recall_at_1000_diff1": -0.04614897361754837, + "nauc_recall_at_1000_max": -0.04843518432801933, + "nauc_recall_at_1000_std": -0.056198774950857476, + "nauc_recall_at_100_diff1": -0.03505137222397454, + "nauc_recall_at_100_max": -0.07795908006335968, + "nauc_recall_at_100_std": -0.10214882908578943, + "nauc_recall_at_10_diff1": -0.014732862011041722, + "nauc_recall_at_10_max": -0.16342935055320687, + "nauc_recall_at_10_std": -0.17067388927698596, + "nauc_recall_at_1_diff1": -0.06685979428531999, + "nauc_recall_at_1_max": -0.20498688450826993, + "nauc_recall_at_1_std": -0.14661899996513097, + "nauc_recall_at_20_diff1": -0.015631461976507575, + "nauc_recall_at_20_max": -0.13536998338467393, + "nauc_recall_at_20_std": -0.1629477396748541, + "nauc_recall_at_3_diff1": 0.02170066942746417, + "nauc_recall_at_3_max": -0.03907052126273122, + "nauc_recall_at_3_std": -0.0214871489632519, + "nauc_recall_at_5_diff1": 0.052531624711719425, + "nauc_recall_at_5_max": -0.09889749364654027, + "nauc_recall_at_5_std": -0.05419751264009109, + "ndcg_at_1": 0.00512, + "ndcg_at_10": 0.01533, + "ndcg_at_100": 0.02708, + "ndcg_at_1000": 0.04853, + "ndcg_at_20": 0.01814, + "ndcg_at_3": 0.00994, + "ndcg_at_5": 0.01163, + "precision_at_1": 0.00512, + "precision_at_10": 0.00292, + "precision_at_100": 0.0009, + "precision_at_1000": 0.00027, + "precision_at_20": 0.00202, + "precision_at_3": 0.00461, + "precision_at_5": 0.00358, + "recall_at_1": 0.00512, + "recall_at_10": 0.02917, + "recall_at_100": 0.09007, + "recall_at_1000": 0.2738, + "recall_at_20": 0.04043, + "recall_at_3": 0.01382, + "recall_at_5": 0.01791 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/SpartQA.json b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/SpartQA.json new file mode 100644 index 000000000..c055d9acc --- /dev/null +++ b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/SpartQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 5.84786581993103, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.00575, + "map_at_1": 0.00019, + "map_at_10": 0.00257, + "map_at_100": 0.00756, + "map_at_1000": 0.00894, + "map_at_20": 0.00442, + "map_at_3": 0.00077, + "map_at_5": 0.00139, + "mrr_at_1": 0.0005564830272676684, + "mrr_at_10": 0.004161035588414549, + "mrr_at_100": 0.011800817308986194, + "mrr_at_1000": 0.013445759468269517, + "mrr_at_20": 0.006983182219773654, + "mrr_at_3": 0.0014839547393804488, + "mrr_at_5": 0.0023882396586904094, + "nauc_map_at_1000_diff1": 0.15481222668789493, + "nauc_map_at_1000_max": -0.09996918204118979, + "nauc_map_at_1000_std": 0.16763154815462764, + "nauc_map_at_100_diff1": 0.1505015744999824, + "nauc_map_at_100_max": -0.08835539080141583, + "nauc_map_at_100_std": 0.166518969970269, + "nauc_map_at_10_diff1": 0.095431690723471, + "nauc_map_at_10_max": -0.16561073446574168, + "nauc_map_at_10_std": 0.15140183969456567, + "nauc_map_at_1_diff1": -0.4994633460044067, + "nauc_map_at_1_max": 0.8308234967274296, + "nauc_map_at_1_std": 0.17162032582300227, + "nauc_map_at_20_diff1": 0.14495589341593262, + "nauc_map_at_20_max": -0.12794989261743403, + "nauc_map_at_20_std": 0.17241569447456015, + "nauc_map_at_3_diff1": -0.014095816679999994, + "nauc_map_at_3_max": 0.07331126780660335, + "nauc_map_at_3_std": 0.12928422216509486, + "nauc_map_at_5_diff1": 0.04358391158405404, + "nauc_map_at_5_max": -0.11701793060012775, + "nauc_map_at_5_std": 0.13134997691765668, + "nauc_mrr_at_1000_diff1": 0.17813884934650573, + "nauc_mrr_at_1000_max": -0.018544041048224234, + "nauc_mrr_at_1000_std": 0.20221089478745832, + "nauc_mrr_at_100_diff1": 0.17947615612381657, + "nauc_mrr_at_100_max": -0.01463223079410617, + "nauc_mrr_at_100_std": 0.1999462829999631, + "nauc_mrr_at_10_diff1": 0.12350936335277739, + "nauc_mrr_at_10_max": -0.06967352608609546, + "nauc_mrr_at_10_std": 0.1738451277716448, + "nauc_mrr_at_1_diff1": -0.49946334600440684, + "nauc_mrr_at_1_max": 0.8308234967274296, + "nauc_mrr_at_1_std": 0.17162032582300216, + "nauc_mrr_at_20_diff1": 0.1619626282722759, + "nauc_mrr_at_20_max": -0.060215110836746896, + "nauc_mrr_at_20_std": 0.19136722144187412, + "nauc_mrr_at_3_diff1": 0.016399348752052508, + "nauc_mrr_at_3_max": 0.12373468406498075, + "nauc_mrr_at_3_std": 0.10017997785117709, + "nauc_mrr_at_5_diff1": 0.06392294466921193, + "nauc_mrr_at_5_max": -0.022515827988556808, + "nauc_mrr_at_5_std": 0.15747860802450747, + "nauc_ndcg_at_1000_diff1": 0.20582703352335005, + "nauc_ndcg_at_1000_max": -0.15119000914351483, + "nauc_ndcg_at_1000_std": 0.18577565183031355, + "nauc_ndcg_at_100_diff1": 0.17687599653462305, + "nauc_ndcg_at_100_max": -0.041224847277576505, + "nauc_ndcg_at_100_std": 0.17224061807994878, + "nauc_ndcg_at_10_diff1": 0.1315052355183127, + "nauc_ndcg_at_10_max": -0.17880973093875482, + "nauc_ndcg_at_10_std": 0.1558305590462158, + "nauc_ndcg_at_1_diff1": -0.49946334600440684, + "nauc_ndcg_at_1_max": 0.8308234967274296, + "nauc_ndcg_at_1_std": 0.17162032582300216, + "nauc_ndcg_at_20_diff1": 0.18024536697220553, + "nauc_ndcg_at_20_max": -0.11521561705945627, + "nauc_ndcg_at_20_std": 0.18675165471324215, + "nauc_ndcg_at_3_diff1": 0.044859328265402065, + "nauc_ndcg_at_3_max": 0.0010026557112000959, + "nauc_ndcg_at_3_std": 0.10261045280050307, + "nauc_ndcg_at_5_diff1": 0.08543879453453818, + "nauc_ndcg_at_5_max": -0.16987828872635405, + "nauc_ndcg_at_5_std": 0.13304572673858328, + "nauc_precision_at_1000_diff1": 0.19442223422163313, + "nauc_precision_at_1000_max": -0.14836853384309506, + "nauc_precision_at_1000_std": 0.17404034563758122, + "nauc_precision_at_100_diff1": 0.2105176455589063, + "nauc_precision_at_100_max": 0.02296678028950601, + "nauc_precision_at_100_std": 0.20517620949851326, + "nauc_precision_at_10_diff1": 0.16406818594000608, + "nauc_precision_at_10_max": -0.12484566250309641, + "nauc_precision_at_10_std": 0.1966278002149427, + "nauc_precision_at_1_diff1": -0.49946334600440684, + "nauc_precision_at_1_max": 0.8308234967274296, + "nauc_precision_at_1_std": 0.17162032582300216, + "nauc_precision_at_20_diff1": 0.19981217564968556, + "nauc_precision_at_20_max": -0.0647076694247742, + "nauc_precision_at_20_std": 0.2166914208609477, + "nauc_precision_at_3_diff1": 0.0915747775356748, + "nauc_precision_at_3_max": 0.00947285927642434, + "nauc_precision_at_3_std": 0.12658553026287941, + "nauc_precision_at_5_diff1": 0.11587178492295268, + "nauc_precision_at_5_max": -0.1439383298222283, + "nauc_precision_at_5_std": 0.1940999098376494, + "nauc_recall_at_1000_diff1": 0.16858499096631976, + "nauc_recall_at_1000_max": -0.19645025145919365, + "nauc_recall_at_1000_std": 0.12878499918104738, + "nauc_recall_at_100_diff1": 0.1637194070131288, + "nauc_recall_at_100_max": -0.045332824971529254, + "nauc_recall_at_100_std": 0.15016070424248484, + "nauc_recall_at_10_diff1": 0.14028487966419675, + "nauc_recall_at_10_max": -0.23043645726559148, + "nauc_recall_at_10_std": 0.13803529149848617, + "nauc_recall_at_1_diff1": -0.4994633460044067, + "nauc_recall_at_1_max": 0.8308234967274296, + "nauc_recall_at_1_std": 0.17162032582300227, + "nauc_recall_at_20_diff1": 0.19095185976920045, + "nauc_recall_at_20_max": -0.13158955627642593, + "nauc_recall_at_20_std": 0.1830857811977923, + "nauc_recall_at_3_diff1": 0.11013902063380412, + "nauc_recall_at_3_max": -0.16851660769763976, + "nauc_recall_at_3_std": 0.06462840507213995, + "nauc_recall_at_5_diff1": 0.11667072790749718, + "nauc_recall_at_5_max": -0.28763020629085584, + "nauc_recall_at_5_std": 0.10252023076610271, + "ndcg_at_1": 0.00056, + "ndcg_at_10": 0.00575, + "ndcg_at_100": 0.04026, + "ndcg_at_1000": 0.09303, + "ndcg_at_20": 0.01342, + "ndcg_at_3": 0.00119, + "ndcg_at_5": 0.00244, + "precision_at_1": 0.00056, + "precision_at_10": 0.00225, + "precision_at_100": 0.0028, + "precision_at_1000": 0.00095, + "precision_at_20": 0.00327, + "precision_at_3": 0.00111, + "precision_at_5": 0.0015, + "recall_at_1": 0.00019, + "recall_at_10": 0.014, + "recall_at_100": 0.17279, + "recall_at_1000": 0.56789, + "recall_at_20": 0.04164, + "recall_at_3": 0.00167, + "recall_at_5": 0.00454 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL1.json b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL1.json new file mode 100644 index 000000000..e40ebebff --- /dev/null +++ b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL1.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 5.831682920455933, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01049, + "map_at_1": 0.0025, + "map_at_10": 0.00708, + "map_at_100": 0.01003, + "map_at_1000": 0.0109, + "map_at_20": 0.00815, + "map_at_3": 0.00475, + "map_at_5": 0.006, + "mrr_at_1": 0.0025, + "mrr_at_10": 0.0070841269841269835, + "mrr_at_100": 0.010028197920111054, + "mrr_at_1000": 0.010897082496764238, + "mrr_at_20": 0.00814724872543178, + "mrr_at_3": 0.00475, + "mrr_at_5": 0.006, + "nauc_map_at_1000_diff1": 0.057726205322592546, + "nauc_map_at_1000_max": 0.22990440946996643, + "nauc_map_at_1000_std": 0.10747345060739334, + "nauc_map_at_100_diff1": 0.059830077992269325, + "nauc_map_at_100_max": 0.23436820291254493, + "nauc_map_at_100_std": 0.10897473475856924, + "nauc_map_at_10_diff1": 0.07405873433539734, + "nauc_map_at_10_max": 0.23262097981669755, + "nauc_map_at_10_std": 0.07941790911661287, + "nauc_map_at_1_diff1": 0.01435470888113765, + "nauc_map_at_1_max": -0.015052320901529397, + "nauc_map_at_1_std": -0.11183257311510604, + "nauc_map_at_20_diff1": 0.06601571436191431, + "nauc_map_at_20_max": 0.24291002853052976, + "nauc_map_at_20_std": 0.10478522789965232, + "nauc_map_at_3_diff1": 0.019709187107828523, + "nauc_map_at_3_max": 0.09883072317229881, + "nauc_map_at_3_std": -0.04395144017812179, + "nauc_map_at_5_diff1": 0.033996474674298525, + "nauc_map_at_5_max": 0.16660629639567118, + "nauc_map_at_5_std": 0.015184986435321788, + "nauc_mrr_at_1000_diff1": 0.057726205322592546, + "nauc_mrr_at_1000_max": 0.22990440946996643, + "nauc_mrr_at_1000_std": 0.10747345060739334, + "nauc_mrr_at_100_diff1": 0.059830077992269325, + "nauc_mrr_at_100_max": 0.23436820291254493, + "nauc_mrr_at_100_std": 0.10897473475856924, + "nauc_mrr_at_10_diff1": 0.07405873433539734, + "nauc_mrr_at_10_max": 0.23262097981669755, + "nauc_mrr_at_10_std": 0.07941790911661287, + "nauc_mrr_at_1_diff1": 0.01435470888113765, + "nauc_mrr_at_1_max": -0.015052320901529397, + "nauc_mrr_at_1_std": -0.11183257311510604, + "nauc_mrr_at_20_diff1": 0.06601571436191431, + "nauc_mrr_at_20_max": 0.24291002853052976, + "nauc_mrr_at_20_std": 0.10478522789965232, + "nauc_mrr_at_3_diff1": 0.019709187107828523, + "nauc_mrr_at_3_max": 0.09883072317229881, + "nauc_mrr_at_3_std": -0.04395144017812179, + "nauc_mrr_at_5_diff1": 0.033996474674298525, + "nauc_mrr_at_5_max": 0.16660629639567118, + "nauc_mrr_at_5_std": 0.015184986435321788, + "nauc_ndcg_at_1000_diff1": 0.04924607813605249, + "nauc_ndcg_at_1000_max": 0.21285791000177764, + "nauc_ndcg_at_1000_std": 0.12729157235756844, + "nauc_ndcg_at_100_diff1": 0.047070171023755276, + "nauc_ndcg_at_100_max": 0.24626845463626354, + "nauc_ndcg_at_100_std": 0.14787553729025935, + "nauc_ndcg_at_10_diff1": 0.09890798331759747, + "nauc_ndcg_at_10_max": 0.3048939671770459, + "nauc_ndcg_at_10_std": 0.14201465301260674, + "nauc_ndcg_at_1_diff1": 0.01435470888113765, + "nauc_ndcg_at_1_max": -0.015052320901529397, + "nauc_ndcg_at_1_std": -0.11183257311510604, + "nauc_ndcg_at_20_diff1": 0.07577597798407242, + "nauc_ndcg_at_20_max": 0.3043827422883419, + "nauc_ndcg_at_20_std": 0.1746623615246337, + "nauc_ndcg_at_3_diff1": 0.0182979884912401, + "nauc_ndcg_at_3_max": 0.12433208658533562, + "nauc_ndcg_at_3_std": -0.03127835415812653, + "nauc_ndcg_at_5_diff1": 0.038672492774403655, + "nauc_ndcg_at_5_max": 0.20775893765045217, + "nauc_ndcg_at_5_std": 0.048508690907374065, + "nauc_precision_at_1000_diff1": 0.05050049128373729, + "nauc_precision_at_1000_max": 0.1921556860780613, + "nauc_precision_at_1000_std": 0.12160141757572332, + "nauc_precision_at_100_diff1": 0.03532794862672353, + "nauc_precision_at_100_max": 0.2378001699505145, + "nauc_precision_at_100_std": 0.15493723886280206, + "nauc_precision_at_10_diff1": 0.12852468319100444, + "nauc_precision_at_10_max": 0.38770204379967255, + "nauc_precision_at_10_std": 0.2146591045770382, + "nauc_precision_at_1_diff1": 0.01435470888113765, + "nauc_precision_at_1_max": -0.015052320901529397, + "nauc_precision_at_1_std": -0.11183257311510604, + "nauc_precision_at_20_diff1": 0.0808782756461854, + "nauc_precision_at_20_max": 0.35030855916286563, + "nauc_precision_at_20_std": 0.23149986584384222, + "nauc_precision_at_3_diff1": 0.015411188623557903, + "nauc_precision_at_3_max": 0.16994231285215994, + "nauc_precision_at_3_std": -0.00896330829085052, + "nauc_precision_at_5_diff1": 0.045642906120502154, + "nauc_precision_at_5_max": 0.2652565363861315, + "nauc_precision_at_5_std": 0.0968408709219013, + "nauc_recall_at_1000_diff1": 0.05050049128373791, + "nauc_recall_at_1000_max": 0.1921556860780619, + "nauc_recall_at_1000_std": 0.12160141757572396, + "nauc_recall_at_100_diff1": 0.035327948626723345, + "nauc_recall_at_100_max": 0.23780016995051442, + "nauc_recall_at_100_std": 0.15493723886280178, + "nauc_recall_at_10_diff1": 0.12852468319100455, + "nauc_recall_at_10_max": 0.3877020437996726, + "nauc_recall_at_10_std": 0.21465910457703807, + "nauc_recall_at_1_diff1": 0.01435470888113765, + "nauc_recall_at_1_max": -0.015052320901529397, + "nauc_recall_at_1_std": -0.11183257311510604, + "nauc_recall_at_20_diff1": 0.08087827564618542, + "nauc_recall_at_20_max": 0.3503085591628654, + "nauc_recall_at_20_std": 0.23149986584384222, + "nauc_recall_at_3_diff1": 0.015411188623557757, + "nauc_recall_at_3_max": 0.16994231285216002, + "nauc_recall_at_3_std": -0.00896330829085052, + "nauc_recall_at_5_diff1": 0.045642906120501994, + "nauc_recall_at_5_max": 0.26525653638613134, + "nauc_recall_at_5_std": 0.09684087092190133, + "ndcg_at_1": 0.0025, + "ndcg_at_10": 0.01049, + "ndcg_at_100": 0.02943, + "ndcg_at_1000": 0.06218, + "ndcg_at_20": 0.01443, + "ndcg_at_3": 0.00558, + "ndcg_at_5": 0.00784, + "precision_at_1": 0.0025, + "precision_at_10": 0.00217, + "precision_at_100": 0.00121, + "precision_at_1000": 0.0004, + "precision_at_20": 0.00187, + "precision_at_3": 0.00267, + "precision_at_5": 0.0027, + "recall_at_1": 0.0025, + "recall_at_10": 0.02175, + "recall_at_100": 0.12125, + "recall_at_1000": 0.401, + "recall_at_20": 0.0375, + "recall_at_3": 0.008, + "recall_at_5": 0.0135 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL2Fact.json b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL2Fact.json new file mode 100644 index 000000000..7b8e89ad3 --- /dev/null +++ b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL2Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 10.000613689422607, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.16572, + "map_at_1": 0.06541, + "map_at_10": 0.12743, + "map_at_100": 0.1374, + "map_at_1000": 0.13846, + "map_at_20": 0.13291, + "map_at_3": 0.10364, + "map_at_5": 0.11739, + "mrr_at_1": 0.06540670743005374, + "mrr_at_10": 0.12742837731720444, + "mrr_at_100": 0.13740024911852838, + "mrr_at_1000": 0.1384633426836851, + "mrr_at_20": 0.1329107695287222, + "mrr_at_3": 0.10363782348218126, + "mrr_at_5": 0.11738620221110503, + "nauc_map_at_1000_diff1": -0.04413001123759533, + "nauc_map_at_1000_max": 0.1360414756207788, + "nauc_map_at_1000_std": 0.1992182983826255, + "nauc_map_at_100_diff1": -0.0443227872837382, + "nauc_map_at_100_max": 0.1362765098396324, + "nauc_map_at_100_std": 0.19966886302650813, + "nauc_map_at_10_diff1": -0.03986802350783358, + "nauc_map_at_10_max": 0.13610090592266494, + "nauc_map_at_10_std": 0.19109370936061312, + "nauc_map_at_1_diff1": 0.033451327211939774, + "nauc_map_at_1_max": 0.1148659518553407, + "nauc_map_at_1_std": 0.14118190296331876, + "nauc_map_at_20_diff1": -0.04393611448766317, + "nauc_map_at_20_max": 0.13888241289590814, + "nauc_map_at_20_std": 0.19901191927891493, + "nauc_map_at_3_diff1": -0.015294696473105301, + "nauc_map_at_3_max": 0.12480323654626857, + "nauc_map_at_3_std": 0.15947559758952484, + "nauc_map_at_5_diff1": -0.030552560115611038, + "nauc_map_at_5_max": 0.13117176560609906, + "nauc_map_at_5_std": 0.1768822439626139, + "nauc_mrr_at_1000_diff1": -0.04413001123759533, + "nauc_mrr_at_1000_max": 0.1360414756207788, + "nauc_mrr_at_1000_std": 0.1992182983826255, + "nauc_mrr_at_100_diff1": -0.0443227872837382, + "nauc_mrr_at_100_max": 0.1362765098396324, + "nauc_mrr_at_100_std": 0.19966886302650813, + "nauc_mrr_at_10_diff1": -0.03986802350783358, + "nauc_mrr_at_10_max": 0.13610090592266494, + "nauc_mrr_at_10_std": 0.19109370936061312, + "nauc_mrr_at_1_diff1": 0.033451327211939774, + "nauc_mrr_at_1_max": 0.1148659518553407, + "nauc_mrr_at_1_std": 0.14118190296331876, + "nauc_mrr_at_20_diff1": -0.04393611448766317, + "nauc_mrr_at_20_max": 0.13888241289590814, + "nauc_mrr_at_20_std": 0.19901191927891493, + "nauc_mrr_at_3_diff1": -0.015294696473105301, + "nauc_mrr_at_3_max": 0.12480323654626857, + "nauc_mrr_at_3_std": 0.15947559758952484, + "nauc_mrr_at_5_diff1": -0.030552560115611038, + "nauc_mrr_at_5_max": 0.13117176560609906, + "nauc_mrr_at_5_std": 0.1768822439626139, + "nauc_ndcg_at_1000_diff1": -0.07580021772077278, + "nauc_ndcg_at_1000_max": 0.13685054976469574, + "nauc_ndcg_at_1000_std": 0.23756655883409158, + "nauc_ndcg_at_100_diff1": -0.07868171923604991, + "nauc_ndcg_at_100_max": 0.1422164079950682, + "nauc_ndcg_at_100_std": 0.24834014292732715, + "nauc_ndcg_at_10_diff1": -0.06497588212643815, + "nauc_ndcg_at_10_max": 0.14757255067722838, + "nauc_ndcg_at_10_std": 0.2199373918009126, + "nauc_ndcg_at_1_diff1": 0.033451327211939774, + "nauc_ndcg_at_1_max": 0.1148659518553407, + "nauc_ndcg_at_1_std": 0.14118190296331876, + "nauc_ndcg_at_20_diff1": -0.07653840992649794, + "nauc_ndcg_at_20_max": 0.15514119776719762, + "nauc_ndcg_at_20_std": 0.242775050567943, + "nauc_ndcg_at_3_diff1": -0.024275821668742932, + "nauc_ndcg_at_3_max": 0.12931322425066089, + "nauc_ndcg_at_3_std": 0.1660446231228705, + "nauc_ndcg_at_5_diff1": -0.047134769146135104, + "nauc_ndcg_at_5_max": 0.13865651348647232, + "nauc_ndcg_at_5_std": 0.19258783319085773, + "nauc_precision_at_1000_diff1": -0.18786766045236797, + "nauc_precision_at_1000_max": 0.09743067246450954, + "nauc_precision_at_1000_std": 0.35144015331641704, + "nauc_precision_at_100_diff1": -0.14991711945824066, + "nauc_precision_at_100_max": 0.1449638829943923, + "nauc_precision_at_100_std": 0.3583890157434987, + "nauc_precision_at_10_diff1": -0.11106412430168315, + "nauc_precision_at_10_max": 0.168753246189683, + "nauc_precision_at_10_std": 0.2748624997504992, + "nauc_precision_at_1_diff1": 0.033451327211939774, + "nauc_precision_at_1_max": 0.1148659518553407, + "nauc_precision_at_1_std": 0.14118190296331876, + "nauc_precision_at_20_diff1": -0.1379507775527006, + "nauc_precision_at_20_max": 0.18618771064937864, + "nauc_precision_at_20_std": 0.3295675597307863, + "nauc_precision_at_3_diff1": -0.04251574754856308, + "nauc_precision_at_3_max": 0.13916792437141626, + "nauc_precision_at_3_std": 0.1802158616648351, + "nauc_precision_at_5_diff1": -0.07845573845328058, + "nauc_precision_at_5_max": 0.15319934967008209, + "nauc_precision_at_5_std": 0.22340492338559195, + "nauc_recall_at_1000_diff1": -0.18786766045236836, + "nauc_recall_at_1000_max": 0.09743067246451033, + "nauc_recall_at_1000_std": 0.3514401533164168, + "nauc_recall_at_100_diff1": -0.14991711945824077, + "nauc_recall_at_100_max": 0.14496388299439214, + "nauc_recall_at_100_std": 0.35838901574349874, + "nauc_recall_at_10_diff1": -0.1110641243016834, + "nauc_recall_at_10_max": 0.16875324618968263, + "nauc_recall_at_10_std": 0.27486249975049887, + "nauc_recall_at_1_diff1": 0.033451327211939774, + "nauc_recall_at_1_max": 0.1148659518553407, + "nauc_recall_at_1_std": 0.14118190296331876, + "nauc_recall_at_20_diff1": -0.13795077755270085, + "nauc_recall_at_20_max": 0.1861877106493784, + "nauc_recall_at_20_std": 0.3295675597307859, + "nauc_recall_at_3_diff1": -0.04251574754856302, + "nauc_recall_at_3_max": 0.1391679243714166, + "nauc_recall_at_3_std": 0.18021586166483536, + "nauc_recall_at_5_diff1": -0.07845573845328081, + "nauc_recall_at_5_max": 0.15319934967008203, + "nauc_recall_at_5_std": 0.22340492338559165, + "ndcg_at_1": 0.06541, + "ndcg_at_10": 0.16572, + "ndcg_at_100": 0.21988, + "ndcg_at_1000": 0.25213, + "ndcg_at_20": 0.18571, + "ndcg_at_3": 0.11671, + "ndcg_at_5": 0.1415, + "precision_at_1": 0.06541, + "precision_at_10": 0.02896, + "precision_at_100": 0.00556, + "precision_at_1000": 0.00082, + "precision_at_20": 0.01844, + "precision_at_3": 0.05157, + "precision_at_5": 0.04299, + "recall_at_1": 0.06541, + "recall_at_10": 0.28961, + "recall_at_100": 0.55642, + "recall_at_1000": 0.81879, + "recall_at_20": 0.36872, + "recall_at_3": 0.15472, + "recall_at_5": 0.21493 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL2Pure.json b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL2Pure.json new file mode 100644 index 000000000..99baa4c19 --- /dev/null +++ b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL2Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 7.889456033706665, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.00493, + "map_at_1": 0.00167, + "map_at_10": 0.00357, + "map_at_100": 0.0047, + "map_at_1000": 0.00527, + "map_at_20": 0.00394, + "map_at_3": 0.00266, + "map_at_5": 0.00303, + "mrr_at_1": 0.0016675931072818232, + "mrr_at_10": 0.003569149233407153, + "mrr_at_100": 0.004696102628163091, + "mrr_at_1000": 0.005265933998487099, + "mrr_at_20": 0.003940193340565407, + "mrr_at_3": 0.0026557964301154964, + "mrr_at_5": 0.0030263726761781233, + "nauc_map_at_1000_diff1": 0.018694097329180204, + "nauc_map_at_1000_max": 0.1521576856220309, + "nauc_map_at_1000_std": 0.4141377254291378, + "nauc_map_at_100_diff1": 0.016812986226978303, + "nauc_map_at_100_max": 0.14781562333699086, + "nauc_map_at_100_std": 0.4253657691372399, + "nauc_map_at_10_diff1": 0.0037452241571351227, + "nauc_map_at_10_max": 0.12065261604214009, + "nauc_map_at_10_std": 0.4312150292144299, + "nauc_map_at_1_diff1": 0.09587087405674845, + "nauc_map_at_1_max": 0.13136172519993175, + "nauc_map_at_1_std": 0.47579153289680254, + "nauc_map_at_20_diff1": 0.0045115296622111134, + "nauc_map_at_20_max": 0.1323758915681817, + "nauc_map_at_20_std": 0.43613707748180824, + "nauc_map_at_3_diff1": 0.02938156606376514, + "nauc_map_at_3_max": 0.07687553864488243, + "nauc_map_at_3_std": 0.4300849312281301, + "nauc_map_at_5_diff1": -0.010010033228240029, + "nauc_map_at_5_max": 0.09733740807009283, + "nauc_map_at_5_std": 0.43338690676026, + "nauc_mrr_at_1000_diff1": 0.018694097329180204, + "nauc_mrr_at_1000_max": 0.1521576856220309, + "nauc_mrr_at_1000_std": 0.4141377254291378, + "nauc_mrr_at_100_diff1": 0.016812986226978303, + "nauc_mrr_at_100_max": 0.14781562333699086, + "nauc_mrr_at_100_std": 0.4253657691372399, + "nauc_mrr_at_10_diff1": 0.0037452241571351227, + "nauc_mrr_at_10_max": 0.12065261604214009, + "nauc_mrr_at_10_std": 0.4312150292144299, + "nauc_mrr_at_1_diff1": 0.09587087405674845, + "nauc_mrr_at_1_max": 0.13136172519993175, + "nauc_mrr_at_1_std": 0.47579153289680254, + "nauc_mrr_at_20_diff1": 0.0045115296622111134, + "nauc_mrr_at_20_max": 0.1323758915681817, + "nauc_mrr_at_20_std": 0.43613707748180824, + "nauc_mrr_at_3_diff1": 0.02938156606376514, + "nauc_mrr_at_3_max": 0.07687553864488243, + "nauc_mrr_at_3_std": 0.4300849312281301, + "nauc_mrr_at_5_diff1": -0.010010033228240029, + "nauc_mrr_at_5_max": 0.09733740807009283, + "nauc_mrr_at_5_std": 0.43338690676026, + "nauc_ndcg_at_1000_diff1": 0.026749639712771472, + "nauc_ndcg_at_1000_max": 0.183504742219579, + "nauc_ndcg_at_1000_std": 0.32910869665685655, + "nauc_ndcg_at_100_diff1": 0.03991147381513316, + "nauc_ndcg_at_100_max": 0.20184512180580944, + "nauc_ndcg_at_100_std": 0.3977261192130825, + "nauc_ndcg_at_10_diff1": -0.006000369678695232, + "nauc_ndcg_at_10_max": 0.13991522002004067, + "nauc_ndcg_at_10_std": 0.41820273092852667, + "nauc_ndcg_at_1_diff1": 0.09587087405674845, + "nauc_ndcg_at_1_max": 0.13136172519993175, + "nauc_ndcg_at_1_std": 0.47579153289680254, + "nauc_ndcg_at_20_diff1": -0.0030753980504707444, + "nauc_ndcg_at_20_max": 0.1611063441944696, + "nauc_ndcg_at_20_std": 0.43226938216701905, + "nauc_ndcg_at_3_diff1": 0.02209456135954505, + "nauc_ndcg_at_3_max": 0.06667648875880645, + "nauc_ndcg_at_3_std": 0.41663928387113064, + "nauc_ndcg_at_5_diff1": -0.03411431717823831, + "nauc_ndcg_at_5_max": 0.10128804160429342, + "nauc_ndcg_at_5_std": 0.4229984563676023, + "nauc_precision_at_1000_diff1": 0.02474332061352617, + "nauc_precision_at_1000_max": 0.18235957099607772, + "nauc_precision_at_1000_std": 0.3003154018722924, + "nauc_precision_at_100_diff1": 0.05628559897874885, + "nauc_precision_at_100_max": 0.23068813715238876, + "nauc_precision_at_100_std": 0.3817750152512344, + "nauc_precision_at_10_diff1": -0.015311580311257053, + "nauc_precision_at_10_max": 0.16791083123559883, + "nauc_precision_at_10_std": 0.40074543750124536, + "nauc_precision_at_1_diff1": 0.09587087405674845, + "nauc_precision_at_1_max": 0.13136172519993175, + "nauc_precision_at_1_std": 0.47579153289680254, + "nauc_precision_at_20_diff1": -0.007912191356581371, + "nauc_precision_at_20_max": 0.19200218802568866, + "nauc_precision_at_20_std": 0.43068068836311907, + "nauc_precision_at_3_diff1": 0.008836629281971242, + "nauc_precision_at_3_max": 0.04647383844371308, + "nauc_precision_at_3_std": 0.3888905304730611, + "nauc_precision_at_5_diff1": -0.0748556194332489, + "nauc_precision_at_5_max": 0.11102054992753993, + "nauc_precision_at_5_std": 0.4057965619322147, + "nauc_recall_at_1000_diff1": 0.024743320613526232, + "nauc_recall_at_1000_max": 0.18235957099607789, + "nauc_recall_at_1000_std": 0.3003154018722924, + "nauc_recall_at_100_diff1": 0.056285598978748776, + "nauc_recall_at_100_max": 0.23068813715238873, + "nauc_recall_at_100_std": 0.3817750152512344, + "nauc_recall_at_10_diff1": -0.015311580311257459, + "nauc_recall_at_10_max": 0.16791083123559858, + "nauc_recall_at_10_std": 0.4007454375012453, + "nauc_recall_at_1_diff1": 0.09587087405674845, + "nauc_recall_at_1_max": 0.13136172519993175, + "nauc_recall_at_1_std": 0.47579153289680254, + "nauc_recall_at_20_diff1": -0.007912191356581468, + "nauc_recall_at_20_max": 0.19200218802568833, + "nauc_recall_at_20_std": 0.43068068836311896, + "nauc_recall_at_3_diff1": 0.008836629281971202, + "nauc_recall_at_3_max": 0.04647383844371295, + "nauc_recall_at_3_std": 0.3888905304730609, + "nauc_recall_at_5_diff1": -0.0748556194332486, + "nauc_recall_at_5_max": 0.1110205499275401, + "nauc_recall_at_5_std": 0.4057965619322148, + "ndcg_at_1": 0.00167, + "ndcg_at_10": 0.00493, + "ndcg_at_100": 0.01263, + "ndcg_at_1000": 0.0347, + "ndcg_at_20": 0.00629, + "ndcg_at_3": 0.00297, + "ndcg_at_5": 0.00365, + "precision_at_1": 0.00167, + "precision_at_10": 0.00094, + "precision_at_100": 0.00051, + "precision_at_1000": 0.00024, + "precision_at_20": 0.00074, + "precision_at_3": 0.0013, + "precision_at_5": 0.00111, + "recall_at_1": 0.00167, + "recall_at_10": 0.00945, + "recall_at_100": 0.05077, + "recall_at_1000": 0.24032, + "recall_at_20": 0.01482, + "recall_at_3": 0.00389, + "recall_at_5": 0.00556 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL3Fact.json b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL3Fact.json new file mode 100644 index 000000000..bf35fcd53 --- /dev/null +++ b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL3Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 8.497321128845215, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.14011, + "map_at_1": 0.03705, + "map_at_10": 0.10174, + "map_at_100": 0.11128, + "map_at_1000": 0.11235, + "map_at_20": 0.10681, + "map_at_3": 0.07961, + "map_at_5": 0.09178, + "mrr_at_1": 0.03705377315860822, + "mrr_at_10": 0.10174384409585482, + "mrr_at_100": 0.1112753619125977, + "mrr_at_1000": 0.1123549581128959, + "mrr_at_20": 0.10681349281396256, + "mrr_at_3": 0.07960536225335135, + "mrr_at_5": 0.09178340111462537, + "nauc_map_at_1000_diff1": -0.1591917833236728, + "nauc_map_at_1000_max": 0.2898236008788807, + "nauc_map_at_1000_std": 0.3897852814461068, + "nauc_map_at_100_diff1": -0.15909390967353476, + "nauc_map_at_100_max": 0.28999824794405005, + "nauc_map_at_100_std": 0.38994938573287835, + "nauc_map_at_10_diff1": -0.16202226377892662, + "nauc_map_at_10_max": 0.2946572207048373, + "nauc_map_at_10_std": 0.3887057719563069, + "nauc_map_at_1_diff1": -0.2721474343964684, + "nauc_map_at_1_max": 0.17545290342074538, + "nauc_map_at_1_std": 0.32348606711805594, + "nauc_map_at_20_diff1": -0.16068528058754283, + "nauc_map_at_20_max": 0.2940105166052597, + "nauc_map_at_20_std": 0.3904288786045742, + "nauc_map_at_3_diff1": -0.16382461154325098, + "nauc_map_at_3_max": 0.279109672211248, + "nauc_map_at_3_std": 0.35791227739427955, + "nauc_map_at_5_diff1": -0.16050162186805872, + "nauc_map_at_5_max": 0.2950640323015788, + "nauc_map_at_5_std": 0.3791398178953717, + "nauc_mrr_at_1000_diff1": -0.1591917833236728, + "nauc_mrr_at_1000_max": 0.2898236008788807, + "nauc_mrr_at_1000_std": 0.3897852814461068, + "nauc_mrr_at_100_diff1": -0.15909390967353476, + "nauc_mrr_at_100_max": 0.28999824794405005, + "nauc_mrr_at_100_std": 0.38994938573287835, + "nauc_mrr_at_10_diff1": -0.16202226377892662, + "nauc_mrr_at_10_max": 0.2946572207048373, + "nauc_mrr_at_10_std": 0.3887057719563069, + "nauc_mrr_at_1_diff1": -0.2721474343964684, + "nauc_mrr_at_1_max": 0.17545290342074538, + "nauc_mrr_at_1_std": 0.32348606711805594, + "nauc_mrr_at_20_diff1": -0.16068528058754283, + "nauc_mrr_at_20_max": 0.2940105166052597, + "nauc_mrr_at_20_std": 0.3904288786045742, + "nauc_mrr_at_3_diff1": -0.16382461154325098, + "nauc_mrr_at_3_max": 0.279109672211248, + "nauc_mrr_at_3_std": 0.35791227739427955, + "nauc_mrr_at_5_diff1": -0.16050162186805872, + "nauc_mrr_at_5_max": 0.2950640323015788, + "nauc_mrr_at_5_std": 0.3791398178953717, + "nauc_ndcg_at_1000_diff1": -0.14520614711044189, + "nauc_ndcg_at_1000_max": 0.2889210148961516, + "nauc_ndcg_at_1000_std": 0.4142500038559362, + "nauc_ndcg_at_100_diff1": -0.14147089512600322, + "nauc_ndcg_at_100_max": 0.2915781628863857, + "nauc_ndcg_at_100_std": 0.41692415006569866, + "nauc_ndcg_at_10_diff1": -0.15130707846599592, + "nauc_ndcg_at_10_max": 0.31651623547676394, + "nauc_ndcg_at_10_std": 0.41513054904923147, + "nauc_ndcg_at_1_diff1": -0.2721474343964684, + "nauc_ndcg_at_1_max": 0.17545290342074538, + "nauc_ndcg_at_1_std": 0.32348606711805594, + "nauc_ndcg_at_20_diff1": -0.14792587238444765, + "nauc_ndcg_at_20_max": 0.3137012868078804, + "nauc_ndcg_at_20_std": 0.4186586931872674, + "nauc_ndcg_at_3_diff1": -0.15158158654889803, + "nauc_ndcg_at_3_max": 0.2974951703182259, + "nauc_ndcg_at_3_std": 0.3683121475284505, + "nauc_ndcg_at_5_diff1": -0.147848002546262, + "nauc_ndcg_at_5_max": 0.31854131571264566, + "nauc_ndcg_at_5_std": 0.3979106802545553, + "nauc_precision_at_1000_diff1": -0.12444742852531249, + "nauc_precision_at_1000_max": 0.23465874896306982, + "nauc_precision_at_1000_std": 0.46851580200172327, + "nauc_precision_at_100_diff1": -0.11214173309494795, + "nauc_precision_at_100_max": 0.27077788742551884, + "nauc_precision_at_100_std": 0.4588128627520911, + "nauc_precision_at_10_diff1": -0.1371105994243231, + "nauc_precision_at_10_max": 0.34814876541552797, + "nauc_precision_at_10_std": 0.4574831503993074, + "nauc_precision_at_1_diff1": -0.2721474343964684, + "nauc_precision_at_1_max": 0.17545290342074538, + "nauc_precision_at_1_std": 0.32348606711805594, + "nauc_precision_at_20_diff1": -0.13045111970941758, + "nauc_precision_at_20_max": 0.33910886210568114, + "nauc_precision_at_20_std": 0.46181489599061154, + "nauc_precision_at_3_diff1": -0.13050532013261398, + "nauc_precision_at_3_max": 0.3309059055812422, + "nauc_precision_at_3_std": 0.3879332141781356, + "nauc_precision_at_5_diff1": -0.12847921032909307, + "nauc_precision_at_5_max": 0.356702266789038, + "nauc_precision_at_5_std": 0.42967782588681125, + "nauc_recall_at_1000_diff1": -0.12444742852531324, + "nauc_recall_at_1000_max": 0.23465874896306893, + "nauc_recall_at_1000_std": 0.46851580200172294, + "nauc_recall_at_100_diff1": -0.11214173309494793, + "nauc_recall_at_100_max": 0.27077788742551817, + "nauc_recall_at_100_std": 0.4588128627520907, + "nauc_recall_at_10_diff1": -0.13711059942432322, + "nauc_recall_at_10_max": 0.3481487654155282, + "nauc_recall_at_10_std": 0.45748315039930737, + "nauc_recall_at_1_diff1": -0.2721474343964684, + "nauc_recall_at_1_max": 0.17545290342074538, + "nauc_recall_at_1_std": 0.32348606711805594, + "nauc_recall_at_20_diff1": -0.1304511197094179, + "nauc_recall_at_20_max": 0.3391088621056807, + "nauc_recall_at_20_std": 0.4618148959906115, + "nauc_recall_at_3_diff1": -0.13050532013261387, + "nauc_recall_at_3_max": 0.33090590558124205, + "nauc_recall_at_3_std": 0.3879332141781357, + "nauc_recall_at_5_diff1": -0.12847921032909335, + "nauc_recall_at_5_max": 0.3567022667890381, + "nauc_recall_at_5_std": 0.42967782588681164, + "ndcg_at_1": 0.03705, + "ndcg_at_10": 0.14011, + "ndcg_at_100": 0.19263, + "ndcg_at_1000": 0.22577, + "ndcg_at_20": 0.15846, + "ndcg_at_3": 0.09399, + "ndcg_at_5": 0.11595, + "precision_at_1": 0.03705, + "precision_at_10": 0.02639, + "precision_at_100": 0.00524, + "precision_at_1000": 0.00079, + "precision_at_20": 0.01681, + "precision_at_3": 0.04526, + "precision_at_5": 0.03782, + "recall_at_1": 0.03705, + "recall_at_10": 0.2639, + "recall_at_100": 0.5244, + "recall_at_1000": 0.79485, + "recall_at_20": 0.3362, + "recall_at_3": 0.13579, + "recall_at_5": 0.18911 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL3Pure.json b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL3Pure.json new file mode 100644 index 000000000..412765f6a --- /dev/null +++ b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/TempReasonL3Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 6.630683660507202, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.06268, + "map_at_1": 0.00407, + "map_at_10": 0.03984, + "map_at_100": 0.04541, + "map_at_1000": 0.04631, + "map_at_20": 0.04286, + "map_at_3": 0.02579, + "map_at_5": 0.0336, + "mrr_at_1": 0.004066877541798464, + "mrr_at_10": 0.0398402477424167, + "mrr_at_100": 0.04540972791037541, + "mrr_at_1000": 0.04631381825784851, + "mrr_at_20": 0.04286186644703689, + "mrr_at_3": 0.025794547371592064, + "mrr_at_5": 0.03360069287543307, + "nauc_map_at_1000_diff1": -0.17108122502323295, + "nauc_map_at_1000_max": 0.10950273114329669, + "nauc_map_at_1000_std": 0.5530766648510845, + "nauc_map_at_100_diff1": -0.17153838029919186, + "nauc_map_at_100_max": 0.10920141289914091, + "nauc_map_at_100_std": 0.5546815822159179, + "nauc_map_at_10_diff1": -0.16928165192675396, + "nauc_map_at_10_max": 0.12185749582173891, + "nauc_map_at_10_std": 0.5463462132184314, + "nauc_map_at_1_diff1": -0.30795410602427153, + "nauc_map_at_1_max": 0.12969569430538688, + "nauc_map_at_1_std": 0.5551912196186651, + "nauc_map_at_20_diff1": -0.17486381886854294, + "nauc_map_at_20_max": 0.11198753265144257, + "nauc_map_at_20_std": 0.5564888405861973, + "nauc_map_at_3_diff1": -0.13913819884856862, + "nauc_map_at_3_max": 0.17681288568682027, + "nauc_map_at_3_std": 0.48676348887150367, + "nauc_map_at_5_diff1": -0.1498488399288405, + "nauc_map_at_5_max": 0.15281799219967723, + "nauc_map_at_5_std": 0.5227694957950663, + "nauc_mrr_at_1000_diff1": -0.17108122434740658, + "nauc_mrr_at_1000_max": 0.1095027252470485, + "nauc_mrr_at_1000_std": 0.5530766638689437, + "nauc_mrr_at_100_diff1": -0.17153838029919186, + "nauc_mrr_at_100_max": 0.10920141289914091, + "nauc_mrr_at_100_std": 0.5546815822159179, + "nauc_mrr_at_10_diff1": -0.16928165192675396, + "nauc_mrr_at_10_max": 0.12185749582173891, + "nauc_mrr_at_10_std": 0.5463462132184314, + "nauc_mrr_at_1_diff1": -0.30795410602427153, + "nauc_mrr_at_1_max": 0.12969569430538688, + "nauc_mrr_at_1_std": 0.5551912196186651, + "nauc_mrr_at_20_diff1": -0.17486381886854294, + "nauc_mrr_at_20_max": 0.11198753265144257, + "nauc_mrr_at_20_std": 0.5564888405861973, + "nauc_mrr_at_3_diff1": -0.13913819884856862, + "nauc_mrr_at_3_max": 0.17681288568682027, + "nauc_mrr_at_3_std": 0.48676348887150367, + "nauc_mrr_at_5_diff1": -0.1498488399288405, + "nauc_mrr_at_5_max": 0.15281799219967723, + "nauc_mrr_at_5_std": 0.5227694957950663, + "nauc_ndcg_at_1000_diff1": -0.16628140081074805, + "nauc_ndcg_at_1000_max": 0.07629419062551314, + "nauc_ndcg_at_1000_std": 0.5476797073729883, + "nauc_ndcg_at_100_diff1": -0.17466976117641142, + "nauc_ndcg_at_100_max": 0.07111947595083788, + "nauc_ndcg_at_100_std": 0.5738655046206431, + "nauc_ndcg_at_10_diff1": -0.17911506710040634, + "nauc_ndcg_at_10_max": 0.09725914353782855, + "nauc_ndcg_at_10_std": 0.5688464331203713, + "nauc_ndcg_at_1_diff1": -0.30795410602427153, + "nauc_ndcg_at_1_max": 0.12969569430538688, + "nauc_ndcg_at_1_std": 0.5551912196186651, + "nauc_ndcg_at_20_diff1": -0.19097131548010748, + "nauc_ndcg_at_20_max": 0.07697863928829717, + "nauc_ndcg_at_20_std": 0.5883302519236171, + "nauc_ndcg_at_3_diff1": -0.13143791765900034, + "nauc_ndcg_at_3_max": 0.17759302176454306, + "nauc_ndcg_at_3_std": 0.4882892298372537, + "nauc_ndcg_at_5_diff1": -0.1478407297539624, + "nauc_ndcg_at_5_max": 0.14521563273071728, + "nauc_ndcg_at_5_std": 0.5341268290418582, + "nauc_precision_at_1000_diff1": -0.14538660676500065, + "nauc_precision_at_1000_max": 0.04959369405497503, + "nauc_precision_at_1000_std": 0.5010066594152331, + "nauc_precision_at_100_diff1": -0.17260009807396673, + "nauc_precision_at_100_max": 0.03477573989197899, + "nauc_precision_at_100_std": 0.5826811624681153, + "nauc_precision_at_10_diff1": -0.19280366951232542, + "nauc_precision_at_10_max": 0.06700889963005957, + "nauc_precision_at_10_std": 0.5954418566998717, + "nauc_precision_at_1_diff1": -0.30795410602427153, + "nauc_precision_at_1_max": 0.12969569430538688, + "nauc_precision_at_1_std": 0.5551912196186651, + "nauc_precision_at_20_diff1": -0.2109473205173619, + "nauc_precision_at_20_max": 0.03721658793444241, + "nauc_precision_at_20_std": 0.6231048520015809, + "nauc_precision_at_3_diff1": -0.1209356116605589, + "nauc_precision_at_3_max": 0.17843830024968646, + "nauc_precision_at_3_std": 0.4911126337948056, + "nauc_precision_at_5_diff1": -0.14656093999753117, + "nauc_precision_at_5_max": 0.13468207942708973, + "nauc_precision_at_5_std": 0.5493187499055098, + "nauc_recall_at_1000_diff1": -0.14538660676500062, + "nauc_recall_at_1000_max": 0.04959369405497516, + "nauc_recall_at_1000_std": 0.5010066594152328, + "nauc_recall_at_100_diff1": -0.17260009807396667, + "nauc_recall_at_100_max": 0.03477573989197892, + "nauc_recall_at_100_std": 0.5826811624681155, + "nauc_recall_at_10_diff1": -0.19280366951232558, + "nauc_recall_at_10_max": 0.06700889963005946, + "nauc_recall_at_10_std": 0.5954418566998717, + "nauc_recall_at_1_diff1": -0.30795410602427153, + "nauc_recall_at_1_max": 0.12969569430538688, + "nauc_recall_at_1_std": 0.5551912196186651, + "nauc_recall_at_20_diff1": -0.2109473205173621, + "nauc_recall_at_20_max": 0.03721658793444236, + "nauc_recall_at_20_std": 0.6231048520015812, + "nauc_recall_at_3_diff1": -0.12093561166055886, + "nauc_recall_at_3_max": 0.17843830024968646, + "nauc_recall_at_3_std": 0.4911126337948055, + "nauc_recall_at_5_diff1": -0.14656093999753136, + "nauc_recall_at_5_max": 0.13468207942708968, + "nauc_recall_at_5_std": 0.5493187499055096, + "ndcg_at_1": 0.00407, + "ndcg_at_10": 0.06268, + "ndcg_at_100": 0.09338, + "ndcg_at_1000": 0.12458, + "ndcg_at_20": 0.07373, + "ndcg_at_3": 0.0334, + "ndcg_at_5": 0.04751, + "precision_at_1": 0.00407, + "precision_at_10": 0.01369, + "precision_at_100": 0.00289, + "precision_at_1000": 0.00055, + "precision_at_20": 0.00904, + "precision_at_3": 0.01853, + "precision_at_5": 0.01798, + "recall_at_1": 0.00407, + "recall_at_10": 0.13692, + "recall_at_100": 0.2892, + "recall_at_1000": 0.55084, + "recall_at_20": 0.18075, + "recall_at_3": 0.05558, + "recall_at_5": 0.08992 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/WinoGrande.json b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/WinoGrande.json new file mode 100644 index 000000000..9545add01 --- /dev/null +++ b/results/all-MiniLM-L6-v2-instruct/8b3219a92973c328a8e22fadcfa821b5dc75636a/WinoGrande.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 1.9192421436309814, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.20733, + "map_at_1": 0.06314, + "map_at_10": 0.1485, + "map_at_100": 0.16623, + "map_at_1000": 0.16713, + "map_at_20": 0.15934, + "map_at_3": 0.1105, + "map_at_5": 0.13047, + "mrr_at_1": 0.06314127861089187, + "mrr_at_10": 0.1488793675849711, + "mrr_at_100": 0.16662867863866326, + "mrr_at_1000": 0.16752332228937242, + "mrr_at_20": 0.1597328480991773, + "mrr_at_3": 0.11128650355169684, + "mrr_at_5": 0.1308208366219416, + "nauc_map_at_1000_diff1": -0.08865640256720551, + "nauc_map_at_1000_max": 0.07439837230435095, + "nauc_map_at_1000_std": 0.1585640634613348, + "nauc_map_at_100_diff1": -0.08867347919406365, + "nauc_map_at_100_max": 0.07460138160527711, + "nauc_map_at_100_std": 0.1584171792667555, + "nauc_map_at_10_diff1": -0.09005378065624003, + "nauc_map_at_10_max": 0.0742784229499677, + "nauc_map_at_10_std": 0.15464962115782332, + "nauc_map_at_1_diff1": -0.1359857475328102, + "nauc_map_at_1_max": 0.08319706188460263, + "nauc_map_at_1_std": 0.22130937149582905, + "nauc_map_at_20_diff1": -0.08878292195184075, + "nauc_map_at_20_max": 0.07283101222033088, + "nauc_map_at_20_std": 0.15704896486186629, + "nauc_map_at_3_diff1": -0.10300130975644398, + "nauc_map_at_3_max": 0.0702799849550662, + "nauc_map_at_3_std": 0.18155782442279217, + "nauc_map_at_5_diff1": -0.09656719357774098, + "nauc_map_at_5_max": 0.07380984448653675, + "nauc_map_at_5_std": 0.16648402032508666, + "nauc_mrr_at_1000_diff1": -0.08916897951453352, + "nauc_mrr_at_1000_max": 0.06892025204451308, + "nauc_mrr_at_1000_std": 0.15599302704327045, + "nauc_mrr_at_100_diff1": -0.08918339512398007, + "nauc_mrr_at_100_max": 0.06914652416346663, + "nauc_mrr_at_100_std": 0.15585732052760765, + "nauc_mrr_at_10_diff1": -0.09051965872856813, + "nauc_mrr_at_10_max": 0.06905962115213012, + "nauc_mrr_at_10_std": 0.15214027677502667, + "nauc_mrr_at_1_diff1": -0.1359857475328102, + "nauc_mrr_at_1_max": 0.06445134396906334, + "nauc_mrr_at_1_std": 0.2128594873843023, + "nauc_mrr_at_20_diff1": -0.08928693985243234, + "nauc_mrr_at_20_max": 0.06749301091626494, + "nauc_mrr_at_20_std": 0.15455106520435277, + "nauc_mrr_at_3_diff1": -0.10337875533517306, + "nauc_mrr_at_3_max": 0.06630955905056828, + "nauc_mrr_at_3_std": 0.17840177810553598, + "nauc_mrr_at_5_diff1": -0.09697002787327996, + "nauc_mrr_at_5_max": 0.06847817541404354, + "nauc_mrr_at_5_std": 0.16378906675663515, + "nauc_ndcg_at_1000_diff1": -0.07191419279111765, + "nauc_ndcg_at_1000_max": 0.07586257315208851, + "nauc_ndcg_at_1000_std": 0.1459287182048727, + "nauc_ndcg_at_100_diff1": -0.06919687821051457, + "nauc_ndcg_at_100_max": 0.07948189552414321, + "nauc_ndcg_at_100_std": 0.14230618835366854, + "nauc_ndcg_at_10_diff1": -0.07030872221316829, + "nauc_ndcg_at_10_max": 0.07569918534726441, + "nauc_ndcg_at_10_std": 0.12699309383704493, + "nauc_ndcg_at_1_diff1": -0.1359857475328102, + "nauc_ndcg_at_1_max": 0.08319706188460263, + "nauc_ndcg_at_1_std": 0.22130937149582905, + "nauc_ndcg_at_20_diff1": -0.0657613022366222, + "nauc_ndcg_at_20_max": 0.07209615340316132, + "nauc_ndcg_at_20_std": 0.13427439608808434, + "nauc_ndcg_at_3_diff1": -0.09481635322051557, + "nauc_ndcg_at_3_max": 0.06718911178663174, + "nauc_ndcg_at_3_std": 0.17267299574204034, + "nauc_ndcg_at_5_diff1": -0.08527313094480742, + "nauc_ndcg_at_5_max": 0.07353370196923376, + "nauc_ndcg_at_5_std": 0.1504590335514491, + "nauc_precision_at_1000_diff1": 0.37821454962868784, + "nauc_precision_at_1000_max": 0.11984603687778575, + "nauc_precision_at_1000_std": 0.0708128442284462, + "nauc_precision_at_100_diff1": -0.006118517598168688, + "nauc_precision_at_100_max": 0.10967617811014121, + "nauc_precision_at_100_std": 0.10628472183993351, + "nauc_precision_at_10_diff1": -0.03299367546078431, + "nauc_precision_at_10_max": 0.07979425504256805, + "nauc_precision_at_10_std": 0.07598466349948998, + "nauc_precision_at_1_diff1": -0.1359857475328102, + "nauc_precision_at_1_max": 0.08319706188460263, + "nauc_precision_at_1_std": 0.22130937149582905, + "nauc_precision_at_20_diff1": -0.0170811786357001, + "nauc_precision_at_20_max": 0.0714554229299452, + "nauc_precision_at_20_std": 0.09201380795359371, + "nauc_precision_at_3_diff1": -0.07839344728811526, + "nauc_precision_at_3_max": 0.06100670049233631, + "nauc_precision_at_3_std": 0.1550113684065098, + "nauc_precision_at_5_diff1": -0.0645922259112416, + "nauc_precision_at_5_max": 0.07373971197565173, + "nauc_precision_at_5_std": 0.12100762109611164, + "nauc_recall_at_1000_diff1": 0.3782145496286795, + "nauc_recall_at_1000_max": 0.11984603687777724, + "nauc_recall_at_1000_std": 0.07081284422843599, + "nauc_recall_at_100_diff1": -0.006118517598168267, + "nauc_recall_at_100_max": 0.10967617811014219, + "nauc_recall_at_100_std": 0.10628472183993315, + "nauc_recall_at_10_diff1": -0.032993675460784216, + "nauc_recall_at_10_max": 0.07979425504256807, + "nauc_recall_at_10_std": 0.07598466349949008, + "nauc_recall_at_1_diff1": -0.1359857475328102, + "nauc_recall_at_1_max": 0.08319706188460263, + "nauc_recall_at_1_std": 0.22130937149582905, + "nauc_recall_at_20_diff1": -0.017081178635699898, + "nauc_recall_at_20_max": 0.07145542292994553, + "nauc_recall_at_20_std": 0.09201380795359373, + "nauc_recall_at_3_diff1": -0.07839344728811512, + "nauc_recall_at_3_max": 0.06100670049233629, + "nauc_recall_at_3_std": 0.15501136840650975, + "nauc_recall_at_5_diff1": -0.06459222591124175, + "nauc_recall_at_5_max": 0.07373971197565177, + "nauc_recall_at_5_std": 0.12100762109611164, + "ndcg_at_1": 0.06314, + "ndcg_at_10": 0.20733, + "ndcg_at_100": 0.29622, + "ndcg_at_1000": 0.31785, + "ndcg_at_20": 0.24644, + "ndcg_at_3": 0.12703, + "ndcg_at_5": 0.16307, + "precision_at_1": 0.06314, + "precision_at_10": 0.04009, + "precision_at_100": 0.00823, + "precision_at_1000": 0.00099, + "precision_at_20": 0.02774, + "precision_at_3": 0.05841, + "precision_at_5": 0.05257, + "recall_at_1": 0.06314, + "recall_at_10": 0.40095, + "recall_at_100": 0.8232, + "recall_at_1000": 0.98895, + "recall_at_20": 0.55485, + "recall_at_3": 0.17522, + "recall_at_5": 0.26283 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/ARCChallenge.json b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/ARCChallenge.json new file mode 100644 index 000000000..ac78ef54e --- /dev/null +++ b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/ARCChallenge.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 4.764032363891602, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.10354, + "map_at_1": 0.04352, + "map_at_10": 0.08025, + "map_at_100": 0.08931, + "map_at_1000": 0.09062, + "map_at_20": 0.08414, + "map_at_3": 0.06485, + "map_at_5": 0.07415, + "mrr_at_1": 0.043515358361774746, + "mrr_at_10": 0.08024676309659247, + "mrr_at_100": 0.08930815460959744, + "mrr_at_1000": 0.09062072608076885, + "mrr_at_20": 0.08414214039772086, + "mrr_at_3": 0.06484641638225255, + "mrr_at_5": 0.07414675767918089, + "nauc_map_at_1000_diff1": 0.00022906395589158791, + "nauc_map_at_1000_max": 0.07113802111311898, + "nauc_map_at_1000_std": -0.1273107215837024, + "nauc_map_at_100_diff1": 0.0006003453372509409, + "nauc_map_at_100_max": 0.0714085622761985, + "nauc_map_at_100_std": -0.1274976401377723, + "nauc_map_at_10_diff1": 0.0007334410419890939, + "nauc_map_at_10_max": 0.07519690739250692, + "nauc_map_at_10_std": -0.13884961356357284, + "nauc_map_at_1_diff1": 0.028969211205600105, + "nauc_map_at_1_max": 0.026289902258216806, + "nauc_map_at_1_std": -0.22444055091687534, + "nauc_map_at_20_diff1": 0.00013369719730477883, + "nauc_map_at_20_max": 0.07677090634086754, + "nauc_map_at_20_std": -0.1323601043003802, + "nauc_map_at_3_diff1": 0.008731401618527555, + "nauc_map_at_3_max": 0.08497524095122805, + "nauc_map_at_3_std": -0.14065365720522416, + "nauc_map_at_5_diff1": 0.002103587488018814, + "nauc_map_at_5_max": 0.08880776215118255, + "nauc_map_at_5_std": -0.13659459873283608, + "nauc_mrr_at_1000_diff1": 0.00022907594721551013, + "nauc_mrr_at_1000_max": 0.07113830591958238, + "nauc_mrr_at_1000_std": -0.12731110776561635, + "nauc_mrr_at_100_diff1": 0.0006003453372509409, + "nauc_mrr_at_100_max": 0.0714085622761985, + "nauc_mrr_at_100_std": -0.1274976401377723, + "nauc_mrr_at_10_diff1": 0.0007334410419890939, + "nauc_mrr_at_10_max": 0.07519690739250692, + "nauc_mrr_at_10_std": -0.13884961356357284, + "nauc_mrr_at_1_diff1": 0.028969211205600105, + "nauc_mrr_at_1_max": 0.026289902258216806, + "nauc_mrr_at_1_std": -0.22444055091687534, + "nauc_mrr_at_20_diff1": 0.00013369719730477883, + "nauc_mrr_at_20_max": 0.07677090634086754, + "nauc_mrr_at_20_std": -0.1323601043003802, + "nauc_mrr_at_3_diff1": 0.008731401618527555, + "nauc_mrr_at_3_max": 0.08497524095122805, + "nauc_mrr_at_3_std": -0.14065365720522416, + "nauc_mrr_at_5_diff1": 0.002103587488018814, + "nauc_mrr_at_5_max": 0.08880776215118255, + "nauc_mrr_at_5_std": -0.13659459873283608, + "nauc_ndcg_at_1000_diff1": -0.01965592906027164, + "nauc_ndcg_at_1000_max": 0.040744926538872614, + "nauc_ndcg_at_1000_std": -0.08223668832434186, + "nauc_ndcg_at_100_diff1": -0.013418244266380734, + "nauc_ndcg_at_100_max": 0.04703949325137173, + "nauc_ndcg_at_100_std": -0.08486278321471902, + "nauc_ndcg_at_10_diff1": -0.010985975125923437, + "nauc_ndcg_at_10_max": 0.07255962970259633, + "nauc_ndcg_at_10_std": -0.12361504471394393, + "nauc_ndcg_at_1_diff1": 0.028969211205600105, + "nauc_ndcg_at_1_max": 0.026289902258216806, + "nauc_ndcg_at_1_std": -0.22444055091687534, + "nauc_ndcg_at_20_diff1": -0.013073644236692985, + "nauc_ndcg_at_20_max": 0.07866157800729734, + "nauc_ndcg_at_20_std": -0.10496554786611331, + "nauc_ndcg_at_3_diff1": 0.00245187605451391, + "nauc_ndcg_at_3_max": 0.09621489402692206, + "nauc_ndcg_at_3_std": -0.12143475203487009, + "nauc_ndcg_at_5_diff1": -0.0073671323003886265, + "nauc_ndcg_at_5_max": 0.10014767473680308, + "nauc_ndcg_at_5_std": -0.11822737654976045, + "nauc_precision_at_1000_diff1": -0.09240399271907114, + "nauc_precision_at_1000_max": -0.0980148955423782, + "nauc_precision_at_1000_std": 0.05262907483674767, + "nauc_precision_at_100_diff1": -0.03616053689094682, + "nauc_precision_at_100_max": -0.010951103427806681, + "nauc_precision_at_100_std": -0.014972007905888674, + "nauc_precision_at_10_diff1": -0.03100015402025059, + "nauc_precision_at_10_max": 0.06323436620872507, + "nauc_precision_at_10_std": -0.10178195264382782, + "nauc_precision_at_1_diff1": 0.028969211205600105, + "nauc_precision_at_1_max": 0.026289902258216806, + "nauc_precision_at_1_std": -0.22444055091687534, + "nauc_precision_at_20_diff1": -0.034065961256167496, + "nauc_precision_at_20_max": 0.07998437238990314, + "nauc_precision_at_20_std": -0.06186581220102375, + "nauc_precision_at_3_diff1": -0.010755783916055356, + "nauc_precision_at_3_max": 0.11880836205170214, + "nauc_precision_at_3_std": -0.08202998517996882, + "nauc_precision_at_5_diff1": -0.024955332209994584, + "nauc_precision_at_5_max": 0.11952967135748674, + "nauc_precision_at_5_std": -0.08637887784822898, + "nauc_recall_at_1000_diff1": -0.09240399271907022, + "nauc_recall_at_1000_max": -0.09801489554237806, + "nauc_recall_at_1000_std": 0.052629074836748266, + "nauc_recall_at_100_diff1": -0.036160536890946865, + "nauc_recall_at_100_max": -0.010951103427806794, + "nauc_recall_at_100_std": -0.014972007905888854, + "nauc_recall_at_10_diff1": -0.031000154020250848, + "nauc_recall_at_10_max": 0.06323436620872475, + "nauc_recall_at_10_std": -0.10178195264382817, + "nauc_recall_at_1_diff1": 0.028969211205600105, + "nauc_recall_at_1_max": 0.026289902258216806, + "nauc_recall_at_1_std": -0.22444055091687534, + "nauc_recall_at_20_diff1": -0.03406596125616754, + "nauc_recall_at_20_max": 0.07998437238990307, + "nauc_recall_at_20_std": -0.06186581220102376, + "nauc_recall_at_3_diff1": -0.010755783916055384, + "nauc_recall_at_3_max": 0.11880836205170203, + "nauc_recall_at_3_std": -0.08202998517996887, + "nauc_recall_at_5_diff1": -0.024955332209994782, + "nauc_recall_at_5_max": 0.11952967135748639, + "nauc_recall_at_5_std": -0.08637887784822923, + "ndcg_at_1": 0.04352, + "ndcg_at_10": 0.10354, + "ndcg_at_100": 0.15705, + "ndcg_at_1000": 0.19814, + "ndcg_at_20": 0.11834, + "ndcg_at_3": 0.07206, + "ndcg_at_5": 0.08869, + "precision_at_1": 0.04352, + "precision_at_10": 0.01792, + "precision_at_100": 0.00451, + "precision_at_1000": 0.00079, + "precision_at_20": 0.01195, + "precision_at_3": 0.031, + "precision_at_5": 0.02662, + "recall_at_1": 0.04352, + "recall_at_10": 0.17918, + "recall_at_100": 0.45051, + "recall_at_1000": 0.78754, + "recall_at_20": 0.23891, + "recall_at_3": 0.093, + "recall_at_5": 0.13311 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/AlphaNLI.json b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/AlphaNLI.json new file mode 100644 index 000000000..6be21f6ba --- /dev/null +++ b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/AlphaNLI.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 54.794071674346924, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01963, + "map_at_1": 0.00392, + "map_at_10": 0.01378, + "map_at_100": 0.01682, + "map_at_1000": 0.01748, + "map_at_20": 0.01528, + "map_at_3": 0.01055, + "map_at_5": 0.01218, + "mrr_at_1": 0.0039164490861618795, + "mrr_at_10": 0.01377621327033859, + "mrr_at_100": 0.016817012372004125, + "mrr_at_1000": 0.017484676784929216, + "mrr_at_20": 0.015281872658786421, + "mrr_at_3": 0.010552654482158402, + "mrr_at_5": 0.012184508268059177, + "nauc_map_at_1000_diff1": -0.11001010691911578, + "nauc_map_at_1000_max": 0.10165904794107772, + "nauc_map_at_1000_std": -0.02438064823724892, + "nauc_map_at_100_diff1": -0.11111160483207642, + "nauc_map_at_100_max": 0.1070316063283239, + "nauc_map_at_100_std": -0.025730285544372702, + "nauc_map_at_10_diff1": -0.16046640689210878, + "nauc_map_at_10_max": 0.12322707811759022, + "nauc_map_at_10_std": -0.029802533563052368, + "nauc_map_at_1_diff1": -0.47786248810736676, + "nauc_map_at_1_max": -0.0001924947503709687, + "nauc_map_at_1_std": -0.1321365762564981, + "nauc_map_at_20_diff1": -0.12950733771854092, + "nauc_map_at_20_max": 0.10849292146919343, + "nauc_map_at_20_std": -0.03645006090540583, + "nauc_map_at_3_diff1": -0.1747502346681631, + "nauc_map_at_3_max": 0.1487860240027769, + "nauc_map_at_3_std": -0.03335676587437545, + "nauc_map_at_5_diff1": -0.173829193193814, + "nauc_map_at_5_max": 0.14322894882737291, + "nauc_map_at_5_std": -0.04163003416290659, + "nauc_mrr_at_1000_diff1": -0.11001010691911578, + "nauc_mrr_at_1000_max": 0.10165904794107772, + "nauc_mrr_at_1000_std": -0.02438064823724892, + "nauc_mrr_at_100_diff1": -0.11111160483207642, + "nauc_mrr_at_100_max": 0.1070316063283239, + "nauc_mrr_at_100_std": -0.025730285544372702, + "nauc_mrr_at_10_diff1": -0.16046640689210878, + "nauc_mrr_at_10_max": 0.12322707811759022, + "nauc_mrr_at_10_std": -0.029802533563052368, + "nauc_mrr_at_1_diff1": -0.47786248810736676, + "nauc_mrr_at_1_max": -0.0001924947503709687, + "nauc_mrr_at_1_std": -0.1321365762564981, + "nauc_mrr_at_20_diff1": -0.12950733771854092, + "nauc_mrr_at_20_max": 0.10849292146919343, + "nauc_mrr_at_20_std": -0.03645006090540583, + "nauc_mrr_at_3_diff1": -0.1747502346681631, + "nauc_mrr_at_3_max": 0.1487860240027769, + "nauc_mrr_at_3_std": -0.03335676587437545, + "nauc_mrr_at_5_diff1": -0.173829193193814, + "nauc_mrr_at_5_max": 0.14322894882737291, + "nauc_mrr_at_5_std": -0.04163003416290659, + "nauc_ndcg_at_1000_diff1": -0.019978268995831393, + "nauc_ndcg_at_1000_max": 0.04749624530471443, + "nauc_ndcg_at_1000_std": 0.017754436664280934, + "nauc_ndcg_at_100_diff1": -0.025636031053687305, + "nauc_ndcg_at_100_max": 0.08488966405617387, + "nauc_ndcg_at_100_std": 0.002464558788771415, + "nauc_ndcg_at_10_diff1": -0.13422758536074703, + "nauc_ndcg_at_10_max": 0.1205870000861631, + "nauc_ndcg_at_10_std": -0.019079161178150394, + "nauc_ndcg_at_1_diff1": -0.47786248810736676, + "nauc_ndcg_at_1_max": -0.0001924947503709687, + "nauc_ndcg_at_1_std": -0.1321365762564981, + "nauc_ndcg_at_20_diff1": -0.07016174240253326, + "nauc_ndcg_at_20_max": 0.08604196074122777, + "nauc_ndcg_at_20_std": -0.03795567747048593, + "nauc_ndcg_at_3_diff1": -0.1476308642276088, + "nauc_ndcg_at_3_max": 0.16266776953460108, + "nauc_ndcg_at_3_std": -0.02455019845498114, + "nauc_ndcg_at_5_diff1": -0.1524827800896692, + "nauc_ndcg_at_5_max": 0.15363688323663227, + "nauc_ndcg_at_5_std": -0.03739603894570525, + "nauc_precision_at_1000_diff1": 0.025529434884571763, + "nauc_precision_at_1000_max": 0.013104901475797957, + "nauc_precision_at_1000_std": 0.04905762572047469, + "nauc_precision_at_100_diff1": 0.03395827436953835, + "nauc_precision_at_100_max": 0.06812544836866698, + "nauc_precision_at_100_std": 0.027222478139445394, + "nauc_precision_at_10_diff1": -0.10553156041626716, + "nauc_precision_at_10_max": 0.11396941741871876, + "nauc_precision_at_10_std": -0.006355046924782172, + "nauc_precision_at_1_diff1": -0.47786248810736676, + "nauc_precision_at_1_max": -0.0001924947503709687, + "nauc_precision_at_1_std": -0.1321365762564981, + "nauc_precision_at_20_diff1": -0.009577436170286792, + "nauc_precision_at_20_max": 0.057481546631185834, + "nauc_precision_at_20_std": -0.04357332477072585, + "nauc_precision_at_3_diff1": -0.10599935555834372, + "nauc_precision_at_3_max": 0.18410097760285252, + "nauc_precision_at_3_std": -0.011038008382263556, + "nauc_precision_at_5_diff1": -0.12560340537055797, + "nauc_precision_at_5_max": 0.16712197258685785, + "nauc_precision_at_5_std": -0.03270325650683315, + "nauc_recall_at_1000_diff1": 0.025529434884571933, + "nauc_recall_at_1000_max": 0.013104901475798488, + "nauc_recall_at_1000_std": 0.04905762572047504, + "nauc_recall_at_100_diff1": 0.03395827436953829, + "nauc_recall_at_100_max": 0.06812544836866695, + "nauc_recall_at_100_std": 0.02722247813944536, + "nauc_recall_at_10_diff1": -0.1055315604162673, + "nauc_recall_at_10_max": 0.11396941741871848, + "nauc_recall_at_10_std": -0.006355046924782443, + "nauc_recall_at_1_diff1": -0.47786248810736676, + "nauc_recall_at_1_max": -0.0001924947503709687, + "nauc_recall_at_1_std": -0.1321365762564981, + "nauc_recall_at_20_diff1": -0.009577436170287081, + "nauc_recall_at_20_max": 0.057481546631185584, + "nauc_recall_at_20_std": -0.04357332477072613, + "nauc_recall_at_3_diff1": -0.10599935555834356, + "nauc_recall_at_3_max": 0.18410097760285268, + "nauc_recall_at_3_std": -0.011038008382263495, + "nauc_recall_at_5_diff1": -0.125603405370558, + "nauc_recall_at_5_max": 0.16712197258685768, + "nauc_recall_at_5_std": -0.03270325650683328, + "ndcg_at_1": 0.00392, + "ndcg_at_10": 0.01963, + "ndcg_at_100": 0.03703, + "ndcg_at_1000": 0.05852, + "ndcg_at_20": 0.0252, + "ndcg_at_3": 0.01286, + "ndcg_at_5": 0.01581, + "precision_at_1": 0.00392, + "precision_at_10": 0.00385, + "precision_at_100": 0.00126, + "precision_at_1000": 0.0003, + "precision_at_20": 0.00304, + "precision_at_3": 0.00653, + "precision_at_5": 0.00535, + "recall_at_1": 0.00392, + "recall_at_10": 0.03851, + "recall_at_100": 0.12598, + "recall_at_1000": 0.30352, + "recall_at_20": 0.0607, + "recall_at_3": 0.01958, + "recall_at_5": 0.02676 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/HellaSwag.json b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/HellaSwag.json new file mode 100644 index 000000000..8f90062c3 --- /dev/null +++ b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/HellaSwag.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 146.68395352363586, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.13009, + "map_at_1": 0.06443, + "map_at_10": 0.10606, + "map_at_100": 0.11265, + "map_at_1000": 0.11363, + "map_at_20": 0.1093, + "map_at_3": 0.09254, + "map_at_5": 0.1, + "mrr_at_1": 0.06442939653455487, + "mrr_at_10": 0.10605864100934825, + "mrr_at_100": 0.11265070938946893, + "mrr_at_1000": 0.11363324246825376, + "mrr_at_20": 0.10930321468442557, + "mrr_at_3": 0.09254464582088595, + "mrr_at_5": 0.10000331939188803, + "nauc_map_at_1000_diff1": 0.28739513310190806, + "nauc_map_at_1000_max": 0.39258359833832834, + "nauc_map_at_1000_std": 0.24097493849848112, + "nauc_map_at_100_diff1": 0.287356537668248, + "nauc_map_at_100_max": 0.392497440409265, + "nauc_map_at_100_std": 0.24087005349281515, + "nauc_map_at_10_diff1": 0.2923520462075453, + "nauc_map_at_10_max": 0.3944222119985664, + "nauc_map_at_10_std": 0.2395404416296316, + "nauc_map_at_1_diff1": 0.37082403678939196, + "nauc_map_at_1_max": 0.3987685837332685, + "nauc_map_at_1_std": 0.22465961380130345, + "nauc_map_at_20_diff1": 0.28951056429978245, + "nauc_map_at_20_max": 0.39411357915625955, + "nauc_map_at_20_std": 0.24071535338810854, + "nauc_map_at_3_diff1": 0.3082346247124955, + "nauc_map_at_3_max": 0.3974706737079193, + "nauc_map_at_3_std": 0.231907036608837, + "nauc_map_at_5_diff1": 0.29872935652803945, + "nauc_map_at_5_max": 0.39871604171789155, + "nauc_map_at_5_std": 0.23820177542218043, + "nauc_mrr_at_1000_diff1": 0.2873951230296606, + "nauc_mrr_at_1000_max": 0.3925835931486544, + "nauc_mrr_at_1000_std": 0.24097493346674634, + "nauc_mrr_at_100_diff1": 0.287356537668248, + "nauc_mrr_at_100_max": 0.392497440409265, + "nauc_mrr_at_100_std": 0.24087005349281515, + "nauc_mrr_at_10_diff1": 0.2923520462075453, + "nauc_mrr_at_10_max": 0.3944222119985664, + "nauc_mrr_at_10_std": 0.2395404416296316, + "nauc_mrr_at_1_diff1": 0.37082403678939196, + "nauc_mrr_at_1_max": 0.3987685837332685, + "nauc_mrr_at_1_std": 0.22465961380130345, + "nauc_mrr_at_20_diff1": 0.28951056429978245, + "nauc_mrr_at_20_max": 0.39411357915625955, + "nauc_mrr_at_20_std": 0.24071535338810854, + "nauc_mrr_at_3_diff1": 0.3082346247124955, + "nauc_mrr_at_3_max": 0.3974706737079193, + "nauc_mrr_at_3_std": 0.231907036608837, + "nauc_mrr_at_5_diff1": 0.29872935652803945, + "nauc_mrr_at_5_max": 0.39871604171789155, + "nauc_mrr_at_5_std": 0.23820177542218043, + "nauc_ndcg_at_1000_diff1": 0.2530695184703152, + "nauc_ndcg_at_1000_max": 0.3838833532166506, + "nauc_ndcg_at_1000_std": 0.2531734724747529, + "nauc_ndcg_at_100_diff1": 0.25180052909038253, + "nauc_ndcg_at_100_max": 0.3825438592961286, + "nauc_ndcg_at_100_std": 0.25318012594720907, + "nauc_ndcg_at_10_diff1": 0.2710154670489083, + "nauc_ndcg_at_10_max": 0.3920632317289448, + "nauc_ndcg_at_10_std": 0.24731708265360586, + "nauc_ndcg_at_1_diff1": 0.37082403678939196, + "nauc_ndcg_at_1_max": 0.3987685837332685, + "nauc_ndcg_at_1_std": 0.22465961380130345, + "nauc_ndcg_at_20_diff1": 0.26269738822648175, + "nauc_ndcg_at_20_max": 0.39114834414483646, + "nauc_ndcg_at_20_std": 0.2506830787106939, + "nauc_ndcg_at_3_diff1": 0.29659710040501497, + "nauc_ndcg_at_3_max": 0.3989556004065897, + "nauc_ndcg_at_3_std": 0.23482507285442938, + "nauc_ndcg_at_5_diff1": 0.28239413894802257, + "nauc_ndcg_at_5_max": 0.40089355688892553, + "nauc_ndcg_at_5_std": 0.24470204531189782, + "nauc_precision_at_1000_diff1": 0.1759254469697388, + "nauc_precision_at_1000_max": 0.3590567728468226, + "nauc_precision_at_1000_std": 0.2805806048777303, + "nauc_precision_at_100_diff1": 0.1852020820094084, + "nauc_precision_at_100_max": 0.35853716269587976, + "nauc_precision_at_100_std": 0.2777098123621585, + "nauc_precision_at_10_diff1": 0.2320351489410562, + "nauc_precision_at_10_max": 0.3866206414876001, + "nauc_precision_at_10_std": 0.26227215653072583, + "nauc_precision_at_1_diff1": 0.37082403678939196, + "nauc_precision_at_1_max": 0.3987685837332685, + "nauc_precision_at_1_std": 0.22465961380130345, + "nauc_precision_at_20_diff1": 0.21350333963069976, + "nauc_precision_at_20_max": 0.3846531941903261, + "nauc_precision_at_20_std": 0.26970306930466204, + "nauc_precision_at_3_diff1": 0.2719602514104511, + "nauc_precision_at_3_max": 0.40259810102459836, + "nauc_precision_at_3_std": 0.24145647738731219, + "nauc_precision_at_5_diff1": 0.2499310758589695, + "nauc_precision_at_5_max": 0.4056885626041614, + "nauc_precision_at_5_std": 0.25850174429498834, + "nauc_recall_at_1000_diff1": 0.17592544696973894, + "nauc_recall_at_1000_max": 0.3590567728468226, + "nauc_recall_at_1000_std": 0.2805806048777303, + "nauc_recall_at_100_diff1": 0.18520208200940821, + "nauc_recall_at_100_max": 0.35853716269587976, + "nauc_recall_at_100_std": 0.27770981236215886, + "nauc_recall_at_10_diff1": 0.23203514894105653, + "nauc_recall_at_10_max": 0.38662064148760034, + "nauc_recall_at_10_std": 0.26227215653072605, + "nauc_recall_at_1_diff1": 0.37082403678939196, + "nauc_recall_at_1_max": 0.3987685837332685, + "nauc_recall_at_1_std": 0.22465961380130345, + "nauc_recall_at_20_diff1": 0.2135033396306999, + "nauc_recall_at_20_max": 0.3846531941903259, + "nauc_recall_at_20_std": 0.2697030693046619, + "nauc_recall_at_3_diff1": 0.27196025141045105, + "nauc_recall_at_3_max": 0.40259810102459836, + "nauc_recall_at_3_std": 0.2414564773873121, + "nauc_recall_at_5_diff1": 0.24993107585896962, + "nauc_recall_at_5_max": 0.4056885626041614, + "nauc_recall_at_5_std": 0.25850174429498834, + "ndcg_at_1": 0.06443, + "ndcg_at_10": 0.13009, + "ndcg_at_100": 0.16769, + "ndcg_at_1000": 0.19946, + "ndcg_at_20": 0.14193, + "ndcg_at_3": 0.10198, + "ndcg_at_5": 0.1154, + "precision_at_1": 0.06443, + "precision_at_10": 0.02073, + "precision_at_100": 0.00396, + "precision_at_1000": 0.00066, + "precision_at_20": 0.01271, + "precision_at_3": 0.04312, + "precision_at_5": 0.03238, + "recall_at_1": 0.06443, + "recall_at_10": 0.20733, + "recall_at_100": 0.39634, + "recall_at_1000": 0.65883, + "recall_at_20": 0.25423, + "recall_at_3": 0.12936, + "recall_at_5": 0.16192 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/PIQA.json b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/PIQA.json new file mode 100644 index 000000000..7e3c357ea --- /dev/null +++ b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/PIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 17.42623805999756, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.27184, + "map_at_1": 0.12568, + "map_at_10": 0.22311, + "map_at_100": 0.23193, + "map_at_1000": 0.23256, + "map_at_20": 0.22798, + "map_at_3": 0.19904, + "map_at_5": 0.2125, + "mrr_at_1": 0.12568008705114256, + "mrr_at_10": 0.22310978979912593, + "mrr_at_100": 0.23192751911143225, + "mrr_at_1000": 0.23255831001643174, + "mrr_at_20": 0.22798211856847117, + "mrr_at_3": 0.19903881030105178, + "mrr_at_5": 0.21250453391367388, + "nauc_map_at_1000_diff1": -0.07598973921725949, + "nauc_map_at_1000_max": 0.2773339245643944, + "nauc_map_at_1000_std": 0.09279463938738114, + "nauc_map_at_100_diff1": -0.07593286712519093, + "nauc_map_at_100_max": 0.277196462908403, + "nauc_map_at_100_std": 0.092738137292116, + "nauc_map_at_10_diff1": -0.07305787743725962, + "nauc_map_at_10_max": 0.27976526647309996, + "nauc_map_at_10_std": 0.08620321300627413, + "nauc_map_at_1_diff1": 0.00347604314253036, + "nauc_map_at_1_max": 0.2391858121167478, + "nauc_map_at_1_std": 0.08368157531810454, + "nauc_map_at_20_diff1": -0.07451316640124761, + "nauc_map_at_20_max": 0.2777709988089505, + "nauc_map_at_20_std": 0.08889513552220069, + "nauc_map_at_3_diff1": -0.06589736769409717, + "nauc_map_at_3_max": 0.28462928123492626, + "nauc_map_at_3_std": 0.08190094100565835, + "nauc_map_at_5_diff1": -0.07035294000816472, + "nauc_map_at_5_max": 0.28133500091535146, + "nauc_map_at_5_std": 0.081836976712817, + "nauc_mrr_at_1000_diff1": -0.07598973921725949, + "nauc_mrr_at_1000_max": 0.2773339245643944, + "nauc_mrr_at_1000_std": 0.09279463938738114, + "nauc_mrr_at_100_diff1": -0.07593286712519093, + "nauc_mrr_at_100_max": 0.277196462908403, + "nauc_mrr_at_100_std": 0.092738137292116, + "nauc_mrr_at_10_diff1": -0.07305787743725962, + "nauc_mrr_at_10_max": 0.27976526647309996, + "nauc_mrr_at_10_std": 0.08620321300627413, + "nauc_mrr_at_1_diff1": 0.00347604314253036, + "nauc_mrr_at_1_max": 0.2391858121167478, + "nauc_mrr_at_1_std": 0.08368157531810454, + "nauc_mrr_at_20_diff1": -0.07451316640124761, + "nauc_mrr_at_20_max": 0.2777709988089505, + "nauc_mrr_at_20_std": 0.08889513552220069, + "nauc_mrr_at_3_diff1": -0.06589736769409717, + "nauc_mrr_at_3_max": 0.28462928123492626, + "nauc_mrr_at_3_std": 0.08190094100565835, + "nauc_mrr_at_5_diff1": -0.07035294000816472, + "nauc_mrr_at_5_max": 0.28133500091535146, + "nauc_mrr_at_5_std": 0.081836976712817, + "nauc_ndcg_at_1000_diff1": -0.11370324241005937, + "nauc_ndcg_at_1000_max": 0.2750857023761677, + "nauc_ndcg_at_1000_std": 0.1290781552414173, + "nauc_ndcg_at_100_diff1": -0.10976806592676958, + "nauc_ndcg_at_100_max": 0.2732546648888091, + "nauc_ndcg_at_100_std": 0.12841357426144676, + "nauc_ndcg_at_10_diff1": -0.09285194751418462, + "nauc_ndcg_at_10_max": 0.2822667951418532, + "nauc_ndcg_at_10_std": 0.09243845701095205, + "nauc_ndcg_at_1_diff1": 0.00347604314253036, + "nauc_ndcg_at_1_max": 0.2391858121167478, + "nauc_ndcg_at_1_std": 0.08368157531810454, + "nauc_ndcg_at_20_diff1": -0.09772366801519432, + "nauc_ndcg_at_20_max": 0.27628275318735374, + "nauc_ndcg_at_20_std": 0.10229948339413633, + "nauc_ndcg_at_3_diff1": -0.07955879562453055, + "nauc_ndcg_at_3_max": 0.2906292641441194, + "nauc_ndcg_at_3_std": 0.08160482349950966, + "nauc_ndcg_at_5_diff1": -0.0861700468101539, + "nauc_ndcg_at_5_max": 0.28501683153759844, + "nauc_ndcg_at_5_std": 0.08144754670187174, + "nauc_precision_at_1000_diff1": -0.36707870091885497, + "nauc_precision_at_1000_max": 0.2517518686479323, + "nauc_precision_at_1000_std": 0.3922403160361039, + "nauc_precision_at_100_diff1": -0.23436427117319394, + "nauc_precision_at_100_max": 0.25086049353265694, + "nauc_precision_at_100_std": 0.2882474770496079, + "nauc_precision_at_10_diff1": -0.13863544912116096, + "nauc_precision_at_10_max": 0.2858144315700379, + "nauc_precision_at_10_std": 0.11048528808131666, + "nauc_precision_at_1_diff1": 0.00347604314253036, + "nauc_precision_at_1_max": 0.2391858121167478, + "nauc_precision_at_1_std": 0.08368157531810454, + "nauc_precision_at_20_diff1": -0.15539534691742118, + "nauc_precision_at_20_max": 0.2675035682933887, + "nauc_precision_at_20_std": 0.14454452690468542, + "nauc_precision_at_3_diff1": -0.11008356941612478, + "nauc_precision_at_3_max": 0.30313929508088855, + "nauc_precision_at_3_std": 0.08095975858550818, + "nauc_precision_at_5_diff1": -0.12103073798135426, + "nauc_precision_at_5_max": 0.29141283970923487, + "nauc_precision_at_5_std": 0.08056399399532468, + "nauc_recall_at_1000_diff1": -0.367078700918854, + "nauc_recall_at_1000_max": 0.25175186864793236, + "nauc_recall_at_1000_std": 0.39224031603610393, + "nauc_recall_at_100_diff1": -0.23436427117319486, + "nauc_recall_at_100_max": 0.25086049353265605, + "nauc_recall_at_100_std": 0.28824747704960674, + "nauc_recall_at_10_diff1": -0.13863544912116083, + "nauc_recall_at_10_max": 0.28581443157003833, + "nauc_recall_at_10_std": 0.11048528808131663, + "nauc_recall_at_1_diff1": 0.00347604314253036, + "nauc_recall_at_1_max": 0.2391858121167478, + "nauc_recall_at_1_std": 0.08368157531810454, + "nauc_recall_at_20_diff1": -0.15539534691742135, + "nauc_recall_at_20_max": 0.26750356829338834, + "nauc_recall_at_20_std": 0.1445445269046852, + "nauc_recall_at_3_diff1": -0.1100835694161248, + "nauc_recall_at_3_max": 0.30313929508088844, + "nauc_recall_at_3_std": 0.08095975858550804, + "nauc_recall_at_5_diff1": -0.12103073798135447, + "nauc_recall_at_5_max": 0.2914128397092351, + "nauc_recall_at_5_std": 0.08056399399532463, + "ndcg_at_1": 0.12568, + "ndcg_at_10": 0.27184, + "ndcg_at_100": 0.31811, + "ndcg_at_1000": 0.33833, + "ndcg_at_20": 0.2895, + "ndcg_at_3": 0.22192, + "ndcg_at_5": 0.24615, + "precision_at_1": 0.12568, + "precision_at_10": 0.0426, + "precision_at_100": 0.0065, + "precision_at_1000": 0.00082, + "precision_at_20": 0.02478, + "precision_at_3": 0.09594, + "precision_at_5": 0.06931, + "recall_at_1": 0.12568, + "recall_at_10": 0.42601, + "recall_at_100": 0.65016, + "recall_at_1000": 0.81719, + "recall_at_20": 0.49565, + "recall_at_3": 0.28781, + "recall_at_5": 0.34657 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/Quail.json b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/Quail.json new file mode 100644 index 000000000..48fac6aa9 --- /dev/null +++ b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/Quail.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 22.84514021873474, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.03015, + "map_at_1": 0.0125, + "map_at_10": 0.02286, + "map_at_100": 0.02701, + "map_at_1000": 0.02767, + "map_at_20": 0.02513, + "map_at_3": 0.01777, + "map_at_5": 0.0206, + "mrr_at_1": 0.0125, + "mrr_at_10": 0.022859768907563045, + "mrr_at_100": 0.027007550257001505, + "mrr_at_1000": 0.027666479570910046, + "mrr_at_20": 0.025129644823561618, + "mrr_at_3": 0.017769607843137258, + "mrr_at_5": 0.020600490196078444, + "nauc_map_at_1000_diff1": 0.16668837468630857, + "nauc_map_at_1000_max": 0.22447333721825052, + "nauc_map_at_1000_std": 0.21729568272153357, + "nauc_map_at_100_diff1": 0.16818451856544728, + "nauc_map_at_100_max": 0.22737665077622796, + "nauc_map_at_100_std": 0.21948246444425792, + "nauc_map_at_10_diff1": 0.17165415163125455, + "nauc_map_at_10_max": 0.22592236627751192, + "nauc_map_at_10_std": 0.2203033183201416, + "nauc_map_at_1_diff1": 0.2049038021433419, + "nauc_map_at_1_max": 0.2687936993955081, + "nauc_map_at_1_std": 0.2405340993386891, + "nauc_map_at_20_diff1": 0.17550102633857137, + "nauc_map_at_20_max": 0.2313410411678815, + "nauc_map_at_20_std": 0.22067406480503174, + "nauc_map_at_3_diff1": 0.1783814290869056, + "nauc_map_at_3_max": 0.22936539511301504, + "nauc_map_at_3_std": 0.21976351507637645, + "nauc_map_at_5_diff1": 0.18076452888842579, + "nauc_map_at_5_max": 0.22891310208461604, + "nauc_map_at_5_std": 0.21199115032241386, + "nauc_mrr_at_1000_diff1": 0.16675607778786677, + "nauc_mrr_at_1000_max": 0.22457018465335563, + "nauc_mrr_at_1000_std": 0.21739706927337635, + "nauc_mrr_at_100_diff1": 0.16825309545113842, + "nauc_mrr_at_100_max": 0.22747520941989866, + "nauc_mrr_at_100_std": 0.21958544137152247, + "nauc_mrr_at_10_diff1": 0.171738462942874, + "nauc_mrr_at_10_max": 0.2260439714722827, + "nauc_mrr_at_10_std": 0.22042366838262237, + "nauc_mrr_at_1_diff1": 0.2049038021433419, + "nauc_mrr_at_1_max": 0.2687936993955081, + "nauc_mrr_at_1_std": 0.2405340993386891, + "nauc_mrr_at_20_diff1": 0.17557850375858336, + "nauc_mrr_at_20_max": 0.23145276322195127, + "nauc_mrr_at_20_std": 0.2207836193866722, + "nauc_mrr_at_3_diff1": 0.1783814290869056, + "nauc_mrr_at_3_max": 0.22936539511301504, + "nauc_mrr_at_3_std": 0.21976351507637645, + "nauc_mrr_at_5_diff1": 0.18076452888842579, + "nauc_mrr_at_5_max": 0.22891310208461604, + "nauc_mrr_at_5_std": 0.21199115032241386, + "nauc_ndcg_at_1000_diff1": 0.13159903248413568, + "nauc_ndcg_at_1000_max": 0.18751162671556584, + "nauc_ndcg_at_1000_std": 0.19426726185853632, + "nauc_ndcg_at_100_diff1": 0.15066077180271453, + "nauc_ndcg_at_100_max": 0.2241230169023215, + "nauc_ndcg_at_100_std": 0.22672137911272655, + "nauc_ndcg_at_10_diff1": 0.16520418624077224, + "nauc_ndcg_at_10_max": 0.2194111332507347, + "nauc_ndcg_at_10_std": 0.22252027615830575, + "nauc_ndcg_at_1_diff1": 0.2049038021433419, + "nauc_ndcg_at_1_max": 0.2687936993955081, + "nauc_ndcg_at_1_std": 0.2405340993386891, + "nauc_ndcg_at_20_diff1": 0.17363165771550362, + "nauc_ndcg_at_20_max": 0.2319854827801054, + "nauc_ndcg_at_20_std": 0.22256132658909306, + "nauc_ndcg_at_3_diff1": 0.17410384466915924, + "nauc_ndcg_at_3_max": 0.2229609329939231, + "nauc_ndcg_at_3_std": 0.21685456323814484, + "nauc_ndcg_at_5_diff1": 0.1781594866756607, + "nauc_ndcg_at_5_max": 0.22229541529971708, + "nauc_ndcg_at_5_std": 0.20527035909066565, + "nauc_precision_at_1000_diff1": 0.09711944358762203, + "nauc_precision_at_1000_max": 0.1455273396773415, + "nauc_precision_at_1000_std": 0.1624813701212779, + "nauc_precision_at_100_diff1": 0.13491017272215622, + "nauc_precision_at_100_max": 0.2252739345151747, + "nauc_precision_at_100_std": 0.23883062715243927, + "nauc_precision_at_10_diff1": 0.15711967641899796, + "nauc_precision_at_10_max": 0.211592552234202, + "nauc_precision_at_10_std": 0.228038089397283, + "nauc_precision_at_1_diff1": 0.2049038021433419, + "nauc_precision_at_1_max": 0.2687936993955081, + "nauc_precision_at_1_std": 0.2405340993386891, + "nauc_precision_at_20_diff1": 0.17294823157277447, + "nauc_precision_at_20_max": 0.23498951091306589, + "nauc_precision_at_20_std": 0.22566763915729562, + "nauc_precision_at_3_diff1": 0.1656078852254613, + "nauc_precision_at_3_max": 0.21022664499124052, + "nauc_precision_at_3_std": 0.2112130873277672, + "nauc_precision_at_5_diff1": 0.17432672022390938, + "nauc_precision_at_5_max": 0.21142221310311082, + "nauc_precision_at_5_std": 0.19374516643255113, + "nauc_recall_at_1000_diff1": 0.09711944358762223, + "nauc_recall_at_1000_max": 0.14552733967734152, + "nauc_recall_at_1000_std": 0.162481370121278, + "nauc_recall_at_100_diff1": 0.134910172722156, + "nauc_recall_at_100_max": 0.22527393451517452, + "nauc_recall_at_100_std": 0.2388306271524391, + "nauc_recall_at_10_diff1": 0.1571196764189979, + "nauc_recall_at_10_max": 0.21159255223420192, + "nauc_recall_at_10_std": 0.22803808939728282, + "nauc_recall_at_1_diff1": 0.2049038021433419, + "nauc_recall_at_1_max": 0.2687936993955081, + "nauc_recall_at_1_std": 0.2405340993386891, + "nauc_recall_at_20_diff1": 0.1729482315727744, + "nauc_recall_at_20_max": 0.2349895109130658, + "nauc_recall_at_20_std": 0.2256676391572956, + "nauc_recall_at_3_diff1": 0.1656078852254613, + "nauc_recall_at_3_max": 0.21022664499124033, + "nauc_recall_at_3_std": 0.2112130873277673, + "nauc_recall_at_5_diff1": 0.17432672022390908, + "nauc_recall_at_5_max": 0.21142221310311082, + "nauc_recall_at_5_std": 0.19374516643255094, + "ndcg_at_1": 0.0125, + "ndcg_at_10": 0.03015, + "ndcg_at_100": 0.05331, + "ndcg_at_1000": 0.07684, + "ndcg_at_20": 0.03848, + "ndcg_at_3": 0.01962, + "ndcg_at_5": 0.02474, + "precision_at_1": 0.0125, + "precision_at_10": 0.0054, + "precision_at_100": 0.00169, + "precision_at_1000": 0.00037, + "precision_at_20": 0.00436, + "precision_at_3": 0.00833, + "precision_at_5": 0.0075, + "recall_at_1": 0.0125, + "recall_at_10": 0.05404, + "recall_at_100": 0.16949, + "recall_at_1000": 0.36838, + "recall_at_20": 0.08713, + "recall_at_3": 0.025, + "recall_at_5": 0.0375 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/RARbCode.json b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/RARbCode.json new file mode 100644 index 000000000..59cb5bf2d --- /dev/null +++ b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/RARbCode.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 844.7904727458954, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.48949, + "map_at_1": 0.34434, + "map_at_10": 0.43737, + "map_at_100": 0.44655, + "map_at_1000": 0.44692, + "map_at_20": 0.4429, + "map_at_3": 0.40858, + "map_at_5": 0.42509, + "mrr_at_1": 0.3443396226415094, + "mrr_at_10": 0.43731843366277345, + "mrr_at_100": 0.44650164435151096, + "mrr_at_1000": 0.4468715255477031, + "mrr_at_20": 0.4428207941544731, + "mrr_at_3": 0.40869272237196763, + "mrr_at_5": 0.42503369272237207, + "nauc_map_at_1000_diff1": 0.43346654509227633, + "nauc_map_at_1000_max": 0.3194681343415463, + "nauc_map_at_1000_std": 0.05460969123062559, + "nauc_map_at_100_diff1": 0.4333117718849449, + "nauc_map_at_100_max": 0.31951877078314866, + "nauc_map_at_100_std": 0.054810268157213585, + "nauc_map_at_10_diff1": 0.4330059699851232, + "nauc_map_at_10_max": 0.31833269584201246, + "nauc_map_at_10_std": 0.05083273555115851, + "nauc_map_at_1_diff1": 0.5050650421547491, + "nauc_map_at_1_max": 0.31186618232809826, + "nauc_map_at_1_std": 0.02110953523457541, + "nauc_map_at_20_diff1": 0.43137574615022695, + "nauc_map_at_20_max": 0.31848662849903614, + "nauc_map_at_20_std": 0.05437748375682724, + "nauc_map_at_3_diff1": 0.4446838642333784, + "nauc_map_at_3_max": 0.3256051161747966, + "nauc_map_at_3_std": 0.0452599163905698, + "nauc_map_at_5_diff1": 0.4341113358745593, + "nauc_map_at_5_max": 0.31928852907950844, + "nauc_map_at_5_std": 0.0494159029106997, + "nauc_mrr_at_1000_diff1": 0.4336226594163164, + "nauc_mrr_at_1000_max": 0.31959078572739225, + "nauc_mrr_at_1000_std": 0.054733787941178266, + "nauc_mrr_at_100_diff1": 0.433467737121073, + "nauc_mrr_at_100_max": 0.3196413602223591, + "nauc_mrr_at_100_std": 0.054934312869757605, + "nauc_mrr_at_10_diff1": 0.4331587354797192, + "nauc_mrr_at_10_max": 0.3184523852086916, + "nauc_mrr_at_10_std": 0.050954568744882134, + "nauc_mrr_at_1_diff1": 0.5050650421547491, + "nauc_mrr_at_1_max": 0.31186618232809826, + "nauc_mrr_at_1_std": 0.02110953523457541, + "nauc_mrr_at_20_diff1": 0.4315541788194055, + "nauc_mrr_at_20_max": 0.31863974607498363, + "nauc_mrr_at_20_std": 0.05450880622731283, + "nauc_mrr_at_3_diff1": 0.4443833985307253, + "nauc_mrr_at_3_max": 0.32538828197936825, + "nauc_mrr_at_3_std": 0.04503214632222736, + "nauc_mrr_at_5_diff1": 0.434264115874452, + "nauc_mrr_at_5_max": 0.3193987583420833, + "nauc_mrr_at_5_std": 0.04953147775607696, + "nauc_ndcg_at_1000_diff1": 0.41531344298502065, + "nauc_ndcg_at_1000_max": 0.3243640711496104, + "nauc_ndcg_at_1000_std": 0.07786912038076035, + "nauc_ndcg_at_100_diff1": 0.4089507011278398, + "nauc_ndcg_at_100_max": 0.3250572897713092, + "nauc_ndcg_at_100_std": 0.08522484409825837, + "nauc_ndcg_at_10_diff1": 0.40478780077681076, + "nauc_ndcg_at_10_max": 0.31818581248317324, + "nauc_ndcg_at_10_std": 0.06647319662726107, + "nauc_ndcg_at_1_diff1": 0.5050650421547491, + "nauc_ndcg_at_1_max": 0.31186618232809826, + "nauc_ndcg_at_1_std": 0.02110953523457541, + "nauc_ndcg_at_20_diff1": 0.3975485387485904, + "nauc_ndcg_at_20_max": 0.3179557400896223, + "nauc_ndcg_at_20_std": 0.08072817710587374, + "nauc_ndcg_at_3_diff1": 0.426277138767668, + "nauc_ndcg_at_3_max": 0.33069822634709667, + "nauc_ndcg_at_3_std": 0.05380514816821169, + "nauc_ndcg_at_5_diff1": 0.406678211342978, + "nauc_ndcg_at_5_max": 0.31847389247855545, + "nauc_ndcg_at_5_std": 0.06173426690373925, + "nauc_precision_at_1000_diff1": 0.2987809438222364, + "nauc_precision_at_1000_max": 0.5363638390570233, + "nauc_precision_at_1000_std": 0.6138939587515095, + "nauc_precision_at_100_diff1": 0.2370129122134739, + "nauc_precision_at_100_max": 0.399868922019917, + "nauc_precision_at_100_std": 0.4069385506527337, + "nauc_precision_at_10_diff1": 0.3047747904166068, + "nauc_precision_at_10_max": 0.31738462681470614, + "nauc_precision_at_10_std": 0.12594359957254508, + "nauc_precision_at_1_diff1": 0.5050650421547491, + "nauc_precision_at_1_max": 0.31186618232809826, + "nauc_precision_at_1_std": 0.02110953523457541, + "nauc_precision_at_20_diff1": 0.24471210631748805, + "nauc_precision_at_20_max": 0.313708459861798, + "nauc_precision_at_20_std": 0.21495994967260743, + "nauc_precision_at_3_diff1": 0.3730945726340028, + "nauc_precision_at_3_max": 0.34571082154527627, + "nauc_precision_at_3_std": 0.07888331463324652, + "nauc_precision_at_5_diff1": 0.3199563433699587, + "nauc_precision_at_5_max": 0.313723237610018, + "nauc_precision_at_5_std": 0.1011000902028627, + "nauc_recall_at_1000_diff1": 0.29878094382223536, + "nauc_recall_at_1000_max": 0.5363638390570243, + "nauc_recall_at_1000_std": 0.613893958751512, + "nauc_recall_at_100_diff1": 0.2370129122134724, + "nauc_recall_at_100_max": 0.399868922019916, + "nauc_recall_at_100_std": 0.40693855065273343, + "nauc_recall_at_10_diff1": 0.3047747904166069, + "nauc_recall_at_10_max": 0.31738462681470603, + "nauc_recall_at_10_std": 0.1259435995725445, + "nauc_recall_at_1_diff1": 0.5050650421547491, + "nauc_recall_at_1_max": 0.31186618232809826, + "nauc_recall_at_1_std": 0.02110953523457541, + "nauc_recall_at_20_diff1": 0.24471210631748813, + "nauc_recall_at_20_max": 0.31370845986179846, + "nauc_recall_at_20_std": 0.21495994967260795, + "nauc_recall_at_3_diff1": 0.37309457263400303, + "nauc_recall_at_3_max": 0.3457108215452765, + "nauc_recall_at_3_std": 0.07888331463324637, + "nauc_recall_at_5_diff1": 0.31995634336995826, + "nauc_recall_at_5_max": 0.31372323761001775, + "nauc_recall_at_5_std": 0.10110009020286287, + "ndcg_at_1": 0.34434, + "ndcg_at_10": 0.48949, + "ndcg_at_100": 0.53648, + "ndcg_at_1000": 0.54672, + "ndcg_at_20": 0.50972, + "ndcg_at_3": 0.42995, + "ndcg_at_5": 0.45967, + "precision_at_1": 0.34434, + "precision_at_10": 0.06563, + "precision_at_100": 0.00881, + "precision_at_1000": 0.00096, + "precision_at_20": 0.03683, + "precision_at_3": 0.16397, + "precision_at_5": 0.1128, + "recall_at_1": 0.34434, + "recall_at_10": 0.65633, + "recall_at_100": 0.8814, + "recall_at_1000": 0.96294, + "recall_at_20": 0.73652, + "recall_at_3": 0.49191, + "recall_at_5": 0.56402 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/RARbMath.json b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/RARbMath.json new file mode 100644 index 000000000..cb8450783 --- /dev/null +++ b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/RARbMath.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 1402.2526426315308, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.69212, + "map_at_1": 0.6289, + "map_at_10": 0.66958, + "map_at_100": 0.67514, + "map_at_1000": 0.6755, + "map_at_20": 0.67275, + "map_at_3": 0.65823, + "map_at_5": 0.66369, + "mrr_at_1": 0.628896977369837, + "mrr_at_10": 0.6695785826067521, + "mrr_at_100": 0.6751398595378444, + "mrr_at_1000": 0.6755047750768913, + "mrr_at_20": 0.6727528941706958, + "mrr_at_3": 0.6582265126338563, + "mrr_at_5": 0.6636941499182364, + "nauc_map_at_1000_diff1": 0.8477937858915214, + "nauc_map_at_1000_max": 0.44882332231274, + "nauc_map_at_1000_std": -0.3639417349647764, + "nauc_map_at_100_diff1": 0.8476402346250004, + "nauc_map_at_100_max": 0.4487863387135156, + "nauc_map_at_100_std": -0.3639465148491382, + "nauc_map_at_10_diff1": 0.8481956959152165, + "nauc_map_at_10_max": 0.4478600732216293, + "nauc_map_at_10_std": -0.36590786936209513, + "nauc_map_at_1_diff1": 0.8738361850634895, + "nauc_map_at_1_max": 0.46633254613721703, + "nauc_map_at_1_std": -0.3539068657345511, + "nauc_map_at_20_diff1": 0.847330773162004, + "nauc_map_at_20_max": 0.4478342190765943, + "nauc_map_at_20_std": -0.36554409424918605, + "nauc_map_at_3_diff1": 0.8514620774155884, + "nauc_map_at_3_max": 0.4497759322591215, + "nauc_map_at_3_std": -0.36285708713827275, + "nauc_map_at_5_diff1": 0.8496576316667231, + "nauc_map_at_5_max": 0.4482375999764796, + "nauc_map_at_5_std": -0.3635884479993735, + "nauc_mrr_at_1000_diff1": 0.8477937781816416, + "nauc_mrr_at_1000_max": 0.448823338551331, + "nauc_mrr_at_1000_std": -0.3639416669518125, + "nauc_mrr_at_100_diff1": 0.8476402346250004, + "nauc_mrr_at_100_max": 0.4487863387135156, + "nauc_mrr_at_100_std": -0.3639465148491382, + "nauc_mrr_at_10_diff1": 0.8481956959152165, + "nauc_mrr_at_10_max": 0.4478600732216293, + "nauc_mrr_at_10_std": -0.36590786936209513, + "nauc_mrr_at_1_diff1": 0.8738361850634895, + "nauc_mrr_at_1_max": 0.46633254613721703, + "nauc_mrr_at_1_std": -0.3539068657345511, + "nauc_mrr_at_20_diff1": 0.847330773162004, + "nauc_mrr_at_20_max": 0.4478342190765943, + "nauc_mrr_at_20_std": -0.36554409424918605, + "nauc_mrr_at_3_diff1": 0.8514620774155884, + "nauc_mrr_at_3_max": 0.4497759322591215, + "nauc_mrr_at_3_std": -0.36285708713827275, + "nauc_mrr_at_5_diff1": 0.8496576316667231, + "nauc_mrr_at_5_max": 0.4482375999764796, + "nauc_mrr_at_5_std": -0.3635884479993735, + "nauc_ndcg_at_1000_diff1": 0.8387884859715838, + "nauc_ndcg_at_1000_max": 0.4470613352467656, + "nauc_ndcg_at_1000_std": -0.3611274375555337, + "nauc_ndcg_at_100_diff1": 0.8340742567412722, + "nauc_ndcg_at_100_max": 0.4468319444571547, + "nauc_ndcg_at_100_std": -0.3597818510428009, + "nauc_ndcg_at_10_diff1": 0.8357571321213887, + "nauc_ndcg_at_10_max": 0.43969114133168374, + "nauc_ndcg_at_10_std": -0.3735309590085301, + "nauc_ndcg_at_1_diff1": 0.8738361850634895, + "nauc_ndcg_at_1_max": 0.46633254613721703, + "nauc_ndcg_at_1_std": -0.3539068657345511, + "nauc_ndcg_at_20_diff1": 0.8320993266995964, + "nauc_ndcg_at_20_max": 0.4397723921048444, + "nauc_ndcg_at_20_std": -0.37225407580692316, + "nauc_ndcg_at_3_diff1": 0.843567429947465, + "nauc_ndcg_at_3_max": 0.44407975582238357, + "nauc_ndcg_at_3_std": -0.3655444968523263, + "nauc_ndcg_at_5_diff1": 0.840044450281338, + "nauc_ndcg_at_5_max": 0.44102715095397105, + "nauc_ndcg_at_5_std": -0.3671137990052701, + "nauc_precision_at_1000_diff1": 0.6959891509817718, + "nauc_precision_at_1000_max": 0.553366745894171, + "nauc_precision_at_1000_std": -0.02980839420937162, + "nauc_precision_at_100_diff1": 0.7163462310373779, + "nauc_precision_at_100_max": 0.4654405482109822, + "nauc_precision_at_100_std": -0.2650073308368285, + "nauc_precision_at_10_diff1": 0.786291035346212, + "nauc_precision_at_10_max": 0.40789456919470307, + "nauc_precision_at_10_std": -0.40587515976674376, + "nauc_precision_at_1_diff1": 0.8738361850634895, + "nauc_precision_at_1_max": 0.46633254613721703, + "nauc_precision_at_1_std": -0.3539068657345511, + "nauc_precision_at_20_diff1": 0.7568507348115606, + "nauc_precision_at_20_max": 0.4035697260261748, + "nauc_precision_at_20_std": -0.40473893129724936, + "nauc_precision_at_3_diff1": 0.8189159669762223, + "nauc_precision_at_3_max": 0.42634007945840474, + "nauc_precision_at_3_std": -0.3737845284823256, + "nauc_precision_at_5_diff1": 0.8079007171928745, + "nauc_precision_at_5_max": 0.416847776404632, + "nauc_precision_at_5_std": -0.3789004063326995, + "nauc_recall_at_1000_diff1": 0.6959891509817714, + "nauc_recall_at_1000_max": 0.5533667458941806, + "nauc_recall_at_1000_std": -0.029808394209363247, + "nauc_recall_at_100_diff1": 0.7163462310373762, + "nauc_recall_at_100_max": 0.46544054821098185, + "nauc_recall_at_100_std": -0.26500733083682687, + "nauc_recall_at_10_diff1": 0.7862910353462128, + "nauc_recall_at_10_max": 0.40789456919470407, + "nauc_recall_at_10_std": -0.40587515976674254, + "nauc_recall_at_1_diff1": 0.8738361850634895, + "nauc_recall_at_1_max": 0.46633254613721703, + "nauc_recall_at_1_std": -0.3539068657345511, + "nauc_recall_at_20_diff1": 0.7568507348115603, + "nauc_recall_at_20_max": 0.40356972602617586, + "nauc_recall_at_20_std": -0.4047389312972481, + "nauc_recall_at_3_diff1": 0.8189159669762232, + "nauc_recall_at_3_max": 0.4263400794584054, + "nauc_recall_at_3_std": -0.37378452848232546, + "nauc_recall_at_5_diff1": 0.8079007171928757, + "nauc_recall_at_5_max": 0.416847776404632, + "nauc_recall_at_5_std": -0.3789004063326982, + "ndcg_at_1": 0.6289, + "ndcg_at_10": 0.69212, + "ndcg_at_100": 0.72154, + "ndcg_at_1000": 0.73115, + "ndcg_at_20": 0.70366, + "ndcg_at_3": 0.66777, + "ndcg_at_5": 0.67761, + "precision_at_1": 0.6289, + "precision_at_10": 0.07647, + "precision_at_100": 0.00908, + "precision_at_1000": 0.00098, + "precision_at_20": 0.04051, + "precision_at_3": 0.23179, + "precision_at_5": 0.14385, + "recall_at_1": 0.6289, + "recall_at_10": 0.76468, + "recall_at_100": 0.9079, + "recall_at_1000": 0.98354, + "recall_at_20": 0.81025, + "recall_at_3": 0.69536, + "recall_at_5": 0.71926 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/SIQA.json b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/SIQA.json new file mode 100644 index 000000000..134048257 --- /dev/null +++ b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/SIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 13.2346932888031, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01288, + "map_at_1": 0.00665, + "map_at_10": 0.0103, + "map_at_100": 0.01221, + "map_at_1000": 0.01276, + "map_at_20": 0.01128, + "map_at_3": 0.00861, + "map_at_5": 0.00941, + "mrr_at_1": 0.006653019447287615, + "mrr_at_10": 0.010301213627723347, + "mrr_at_100": 0.012209486447356279, + "mrr_at_1000": 0.01275980075329914, + "mrr_at_20": 0.011282719901976738, + "mrr_at_3": 0.008614807233026272, + "mrr_at_5": 0.00940805185943364, + "nauc_map_at_1000_diff1": 0.18167809329288048, + "nauc_map_at_1000_max": 0.21376350153600773, + "nauc_map_at_1000_std": 0.04377933538302092, + "nauc_map_at_100_diff1": 0.18736298356581144, + "nauc_map_at_100_max": 0.22161687870244787, + "nauc_map_at_100_std": 0.044297809734502314, + "nauc_map_at_10_diff1": 0.22239866644728482, + "nauc_map_at_10_max": 0.27132876692860497, + "nauc_map_at_10_std": 0.0481530138471589, + "nauc_map_at_1_diff1": 0.3741011427696522, + "nauc_map_at_1_max": 0.35877722793904143, + "nauc_map_at_1_std": 0.05808336625405927, + "nauc_map_at_20_diff1": 0.20182061855963684, + "nauc_map_at_20_max": 0.23332529666876736, + "nauc_map_at_20_std": 0.038212248375279374, + "nauc_map_at_3_diff1": 0.26632486370811187, + "nauc_map_at_3_max": 0.30426049176462705, + "nauc_map_at_3_std": 0.03948151646504653, + "nauc_map_at_5_diff1": 0.2320854012156101, + "nauc_map_at_5_max": 0.27770003392284476, + "nauc_map_at_5_std": 0.029476973353548395, + "nauc_mrr_at_1000_diff1": 0.18167525810576446, + "nauc_mrr_at_1000_max": 0.21375825302188775, + "nauc_mrr_at_1000_std": 0.043772268803642975, + "nauc_mrr_at_100_diff1": 0.1873583091524695, + "nauc_mrr_at_100_max": 0.22161469931596667, + "nauc_mrr_at_100_std": 0.04429145561406321, + "nauc_mrr_at_10_diff1": 0.22239866644728482, + "nauc_mrr_at_10_max": 0.27132876692860497, + "nauc_mrr_at_10_std": 0.0481530138471589, + "nauc_mrr_at_1_diff1": 0.3741011427696522, + "nauc_mrr_at_1_max": 0.35877722793904143, + "nauc_mrr_at_1_std": 0.05808336625405927, + "nauc_mrr_at_20_diff1": 0.20182061855963684, + "nauc_mrr_at_20_max": 0.23332529666876736, + "nauc_mrr_at_20_std": 0.038212248375279374, + "nauc_mrr_at_3_diff1": 0.26632486370811187, + "nauc_mrr_at_3_max": 0.30426049176462705, + "nauc_mrr_at_3_std": 0.03948151646504653, + "nauc_mrr_at_5_diff1": 0.2320854012156101, + "nauc_mrr_at_5_max": 0.27770003392284476, + "nauc_mrr_at_5_std": 0.029476973353548395, + "nauc_ndcg_at_1000_diff1": 0.06273303955736272, + "nauc_ndcg_at_1000_max": 0.07027749752977303, + "nauc_ndcg_at_1000_std": 0.04165852548633053, + "nauc_ndcg_at_100_diff1": 0.09824552581068885, + "nauc_ndcg_at_100_max": 0.12413657297596692, + "nauc_ndcg_at_100_std": 0.05386372176409057, + "nauc_ndcg_at_10_diff1": 0.18246585109618627, + "nauc_ndcg_at_10_max": 0.24230689106536474, + "nauc_ndcg_at_10_std": 0.0581544447776417, + "nauc_ndcg_at_1_diff1": 0.3741011427696522, + "nauc_ndcg_at_1_max": 0.35877722793904143, + "nauc_ndcg_at_1_std": 0.05808336625405927, + "nauc_ndcg_at_20_diff1": 0.1408921073145395, + "nauc_ndcg_at_20_max": 0.15256299473921303, + "nauc_ndcg_at_20_std": 0.03171184164123388, + "nauc_ndcg_at_3_diff1": 0.24510292612790496, + "nauc_ndcg_at_3_max": 0.29034175292531483, + "nauc_ndcg_at_3_std": 0.03393411299734582, + "nauc_ndcg_at_5_diff1": 0.19314531267353263, + "nauc_ndcg_at_5_max": 0.25004119188621127, + "nauc_ndcg_at_5_std": 0.020310023433699014, + "nauc_precision_at_1000_diff1": 0.00990532545213754, + "nauc_precision_at_1000_max": 0.0038201560639352736, + "nauc_precision_at_1000_std": 0.03690154649908511, + "nauc_precision_at_100_diff1": 0.03461383786495039, + "nauc_precision_at_100_max": 0.05369284162545975, + "nauc_precision_at_100_std": 0.0627946050418847, + "nauc_precision_at_10_diff1": 0.12336055945967865, + "nauc_precision_at_10_max": 0.19790295378448072, + "nauc_precision_at_10_std": 0.07839177281002842, + "nauc_precision_at_1_diff1": 0.3741011427696522, + "nauc_precision_at_1_max": 0.35877722793904143, + "nauc_precision_at_1_std": 0.05808336625405927, + "nauc_precision_at_20_diff1": 0.07340456818900806, + "nauc_precision_at_20_max": 0.052689762197685654, + "nauc_precision_at_20_std": 0.022691386636857287, + "nauc_precision_at_3_diff1": 0.19693995011226828, + "nauc_precision_at_3_max": 0.25775630733128807, + "nauc_precision_at_3_std": 0.020754221541532943, + "nauc_precision_at_5_diff1": 0.11519074004798166, + "nauc_precision_at_5_max": 0.19374588306387083, + "nauc_precision_at_5_std": 0.0022519206118160866, + "nauc_recall_at_1000_diff1": 0.009905325452137773, + "nauc_recall_at_1000_max": 0.0038201560639355104, + "nauc_recall_at_1000_std": 0.03690154649908534, + "nauc_recall_at_100_diff1": 0.0346138378649503, + "nauc_recall_at_100_max": 0.05369284162545978, + "nauc_recall_at_100_std": 0.06279460504188462, + "nauc_recall_at_10_diff1": 0.12336055945967844, + "nauc_recall_at_10_max": 0.19790295378448064, + "nauc_recall_at_10_std": 0.07839177281002814, + "nauc_recall_at_1_diff1": 0.3741011427696522, + "nauc_recall_at_1_max": 0.35877722793904143, + "nauc_recall_at_1_std": 0.05808336625405927, + "nauc_recall_at_20_diff1": 0.07340456818900795, + "nauc_recall_at_20_max": 0.05268976219768538, + "nauc_recall_at_20_std": 0.02269138663685718, + "nauc_recall_at_3_diff1": 0.19693995011226814, + "nauc_recall_at_3_max": 0.2577563073312882, + "nauc_recall_at_3_std": 0.02075422154153281, + "nauc_recall_at_5_diff1": 0.1151907400479817, + "nauc_recall_at_5_max": 0.19374588306387097, + "nauc_recall_at_5_std": 0.0022519206118161686, + "ndcg_at_1": 0.00665, + "ndcg_at_10": 0.01288, + "ndcg_at_100": 0.02405, + "ndcg_at_1000": 0.04374, + "ndcg_at_20": 0.01657, + "ndcg_at_3": 0.00917, + "ndcg_at_5": 0.01062, + "precision_at_1": 0.00665, + "precision_at_10": 0.00215, + "precision_at_100": 0.00078, + "precision_at_1000": 0.00024, + "precision_at_20": 0.00182, + "precision_at_3": 0.00358, + "precision_at_5": 0.00287, + "recall_at_1": 0.00665, + "recall_at_10": 0.02149, + "recall_at_100": 0.0783, + "recall_at_1000": 0.24463, + "recall_at_20": 0.03634, + "recall_at_3": 0.01075, + "recall_at_5": 0.01433 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/SpartQA.json b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/SpartQA.json new file mode 100644 index 000000000..4f4246787 --- /dev/null +++ b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/SpartQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 12.25845217704773, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01007, + "map_at_1": 0.0, + "map_at_10": 0.00429, + "map_at_100": 0.00941, + "map_at_1000": 0.01034, + "map_at_20": 0.00669, + "map_at_3": 0.00053, + "map_at_5": 0.00192, + "mrr_at_1": 0.0, + "mrr_at_10": 0.0066461077103815, + "mrr_at_100": 0.013656852786860293, + "mrr_at_1000": 0.014821171259376998, + "mrr_at_20": 0.010168739369432495, + "mrr_at_3": 0.0011129660545353367, + "mrr_at_5": 0.0031719532554257087, + "nauc_map_at_1000_diff1": 0.03488828701982942, + "nauc_map_at_1000_max": -0.09445908121220409, + "nauc_map_at_1000_std": 0.22210877153395667, + "nauc_map_at_100_diff1": 0.0222039118267392, + "nauc_map_at_100_max": -0.11124743893466173, + "nauc_map_at_100_std": 0.2345852911320408, + "nauc_map_at_10_diff1": -0.04234089912711916, + "nauc_map_at_10_max": -0.1644317862524124, + "nauc_map_at_10_std": 0.2732521585187162, + "nauc_map_at_1_diff1": NaN, + "nauc_map_at_1_max": NaN, + "nauc_map_at_1_std": NaN, + "nauc_map_at_20_diff1": 0.00011045862863202182, + "nauc_map_at_20_max": -0.14402742099537116, + "nauc_map_at_20_std": 0.22245163167722296, + "nauc_map_at_3_diff1": -0.14640564981097948, + "nauc_map_at_3_max": -0.30359003695820347, + "nauc_map_at_3_std": 0.530806542166945, + "nauc_map_at_5_diff1": -0.15856799902703494, + "nauc_map_at_5_max": -0.2906708516496287, + "nauc_map_at_5_std": 0.3901723125053123, + "nauc_mrr_at_1000_diff1": 0.04154607879007832, + "nauc_mrr_at_1000_max": -0.07683644475023116, + "nauc_mrr_at_1000_std": 0.2237326055091275, + "nauc_mrr_at_100_diff1": 0.028627876536870493, + "nauc_mrr_at_100_max": -0.09844658677152231, + "nauc_mrr_at_100_std": 0.23524668336140397, + "nauc_mrr_at_10_diff1": -0.03496251589669911, + "nauc_mrr_at_10_max": -0.1569078515732262, + "nauc_mrr_at_10_std": 0.27682586471371295, + "nauc_mrr_at_1_diff1": NaN, + "nauc_mrr_at_1_max": NaN, + "nauc_mrr_at_1_std": NaN, + "nauc_mrr_at_20_diff1": 0.008399697421031001, + "nauc_mrr_at_20_max": -0.12104327086489731, + "nauc_mrr_at_20_std": 0.22962197631802309, + "nauc_mrr_at_3_diff1": -0.2202532822062927, + "nauc_mrr_at_3_max": -0.2974165766037654, + "nauc_mrr_at_3_std": 0.47628968746364747, + "nauc_mrr_at_5_diff1": -0.12698724877879033, + "nauc_mrr_at_5_max": -0.25012803072607726, + "nauc_mrr_at_5_std": 0.39141032935430176, + "nauc_ndcg_at_1000_diff1": 0.1354807653124511, + "nauc_ndcg_at_1000_max": 0.07702583641887521, + "nauc_ndcg_at_1000_std": 0.10976993922338783, + "nauc_ndcg_at_100_diff1": 0.0734925573433169, + "nauc_ndcg_at_100_max": -0.05368558939430174, + "nauc_ndcg_at_100_std": 0.2173062879674433, + "nauc_ndcg_at_10_diff1": -0.01836226793924039, + "nauc_ndcg_at_10_max": -0.13798633684732364, + "nauc_ndcg_at_10_std": 0.25158967719087977, + "nauc_ndcg_at_1_diff1": NaN, + "nauc_ndcg_at_1_max": NaN, + "nauc_ndcg_at_1_std": NaN, + "nauc_ndcg_at_20_diff1": 0.031215858389425418, + "nauc_ndcg_at_20_max": -0.11295103222233413, + "nauc_ndcg_at_20_std": 0.19267613787560672, + "nauc_ndcg_at_3_diff1": -0.1658407003947692, + "nauc_ndcg_at_3_max": -0.29989336898876184, + "nauc_ndcg_at_3_std": 0.5109774891073264, + "nauc_ndcg_at_5_diff1": -0.14464552112112758, + "nauc_ndcg_at_5_max": -0.2748575744449766, + "nauc_ndcg_at_5_std": 0.38173251224286747, + "nauc_precision_at_1000_diff1": 0.1963345138791826, + "nauc_precision_at_1000_max": 0.21480893826266487, + "nauc_precision_at_1000_std": -0.008890546993273653, + "nauc_precision_at_100_diff1": 0.10415027810417984, + "nauc_precision_at_100_max": -0.027733074741492548, + "nauc_precision_at_100_std": 0.20397824555324695, + "nauc_precision_at_10_diff1": 0.004605236867886382, + "nauc_precision_at_10_max": -0.12128574198551353, + "nauc_precision_at_10_std": 0.23801387317295314, + "nauc_precision_at_1_diff1": NaN, + "nauc_precision_at_1_max": NaN, + "nauc_precision_at_1_std": NaN, + "nauc_precision_at_20_diff1": 0.0533284611558673, + "nauc_precision_at_20_max": -0.08129619812970759, + "nauc_precision_at_20_std": 0.17686997428790674, + "nauc_precision_at_3_diff1": -0.19584788584333718, + "nauc_precision_at_3_max": -0.29321862356274747, + "nauc_precision_at_3_std": 0.47582737881454334, + "nauc_precision_at_5_diff1": -0.10149182877200534, + "nauc_precision_at_5_max": -0.23582056006927424, + "nauc_precision_at_5_std": 0.3758897983643905, + "nauc_recall_at_1000_diff1": 0.15937396217662173, + "nauc_recall_at_1000_max": 0.1588708038669617, + "nauc_recall_at_1000_std": 0.025869794845388424, + "nauc_recall_at_100_diff1": 0.09167963067116922, + "nauc_recall_at_100_max": -0.025839842840579136, + "nauc_recall_at_100_std": 0.20604810594754386, + "nauc_recall_at_10_diff1": -0.0045010282006400955, + "nauc_recall_at_10_max": -0.11861713677660658, + "nauc_recall_at_10_std": 0.23394082766893093, + "nauc_recall_at_1_diff1": NaN, + "nauc_recall_at_1_max": NaN, + "nauc_recall_at_1_std": NaN, + "nauc_recall_at_20_diff1": 0.0453525112978992, + "nauc_recall_at_20_max": -0.10566289013672057, + "nauc_recall_at_20_std": 0.1735844295427164, + "nauc_recall_at_3_diff1": -0.1359100478804335, + "nauc_recall_at_3_max": -0.30041511449020647, + "nauc_recall_at_3_std": 0.5289186972832053, + "nauc_recall_at_5_diff1": -0.15631034841510036, + "nauc_recall_at_5_max": -0.28560532224296786, + "nauc_recall_at_5_std": 0.3725627263680634, + "ndcg_at_1": 0.0, + "ndcg_at_10": 0.01007, + "ndcg_at_100": 0.04219, + "ndcg_at_1000": 0.07116, + "ndcg_at_20": 0.01971, + "ndcg_at_3": 0.00089, + "ndcg_at_5": 0.00367, + "precision_at_1": 0.0, + "precision_at_10": 0.00387, + "precision_at_100": 0.00263, + "precision_at_1000": 0.00061, + "precision_at_20": 0.00452, + "precision_at_3": 0.00093, + "precision_at_5": 0.00239, + "recall_at_1": 0.0, + "recall_at_10": 0.02588, + "recall_at_100": 0.17353, + "recall_at_1000": 0.37943, + "recall_at_20": 0.06056, + "recall_at_3": 0.0013, + "recall_at_5": 0.00751 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL1.json b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL1.json new file mode 100644 index 000000000..9f06c33cc --- /dev/null +++ b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL1.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 7.309831142425537, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01524, + "map_at_1": 0.0035, + "map_at_10": 0.00994, + "map_at_100": 0.01432, + "map_at_1000": 0.01588, + "map_at_20": 0.01137, + "map_at_3": 0.00629, + "map_at_5": 0.00797, + "mrr_at_1": 0.0035, + "mrr_at_10": 0.009936210317460316, + "mrr_at_100": 0.014318786350940998, + "mrr_at_1000": 0.015878826170723583, + "mrr_at_20": 0.011365202712019682, + "mrr_at_3": 0.006291666666666666, + "mrr_at_5": 0.007966666666666664, + "nauc_map_at_1000_diff1": 0.04726934110372493, + "nauc_map_at_1000_max": 0.16241689074733923, + "nauc_map_at_1000_std": 0.04395680929058939, + "nauc_map_at_100_diff1": 0.049694900493367944, + "nauc_map_at_100_max": 0.16153768671126487, + "nauc_map_at_100_std": 0.04109093876924155, + "nauc_map_at_10_diff1": 0.04913046109772944, + "nauc_map_at_10_max": 0.17487402572434052, + "nauc_map_at_10_std": 0.043345858994938466, + "nauc_map_at_1_diff1": -0.09130284794357774, + "nauc_map_at_1_max": 0.03028096132469622, + "nauc_map_at_1_std": -0.07298094982559696, + "nauc_map_at_20_diff1": 0.050657918828139754, + "nauc_map_at_20_max": 0.174564413821416, + "nauc_map_at_20_std": 0.046225333976614005, + "nauc_map_at_3_diff1": -0.014650563189327254, + "nauc_map_at_3_max": 0.17925217270784002, + "nauc_map_at_3_std": 0.02448038921277877, + "nauc_map_at_5_diff1": 0.03359797833967438, + "nauc_map_at_5_max": 0.1928427409169544, + "nauc_map_at_5_std": 0.0359591828486684, + "nauc_mrr_at_1000_diff1": 0.04726934110372493, + "nauc_mrr_at_1000_max": 0.16241689074733923, + "nauc_mrr_at_1000_std": 0.04395680929058939, + "nauc_mrr_at_100_diff1": 0.049694900493367944, + "nauc_mrr_at_100_max": 0.16153768671126487, + "nauc_mrr_at_100_std": 0.04109093876924155, + "nauc_mrr_at_10_diff1": 0.04913046109772944, + "nauc_mrr_at_10_max": 0.17487402572434052, + "nauc_mrr_at_10_std": 0.043345858994938466, + "nauc_mrr_at_1_diff1": -0.09130284794357774, + "nauc_mrr_at_1_max": 0.03028096132469622, + "nauc_mrr_at_1_std": -0.07298094982559696, + "nauc_mrr_at_20_diff1": 0.050657918828139754, + "nauc_mrr_at_20_max": 0.174564413821416, + "nauc_mrr_at_20_std": 0.046225333976614005, + "nauc_mrr_at_3_diff1": -0.014650563189327254, + "nauc_mrr_at_3_max": 0.17925217270784002, + "nauc_mrr_at_3_std": 0.02448038921277877, + "nauc_mrr_at_5_diff1": 0.03359797833967438, + "nauc_mrr_at_5_max": 0.1928427409169544, + "nauc_mrr_at_5_std": 0.0359591828486684, + "nauc_ndcg_at_1000_diff1": 0.04967463394140719, + "nauc_ndcg_at_1000_max": 0.1624646591905641, + "nauc_ndcg_at_1000_std": 0.06303347460789771, + "nauc_ndcg_at_100_diff1": 0.05579549601375812, + "nauc_ndcg_at_100_max": 0.1388064667425856, + "nauc_ndcg_at_100_std": 0.04041375382757585, + "nauc_ndcg_at_10_diff1": 0.07786748877247719, + "nauc_ndcg_at_10_max": 0.18062008481359584, + "nauc_ndcg_at_10_std": 0.05831533822038436, + "nauc_ndcg_at_1_diff1": -0.09130284794357774, + "nauc_ndcg_at_1_max": 0.03028096132469622, + "nauc_ndcg_at_1_std": -0.07298094982559696, + "nauc_ndcg_at_20_diff1": 0.07416691765197977, + "nauc_ndcg_at_20_max": 0.17665986478074713, + "nauc_ndcg_at_20_std": 0.057649561984485696, + "nauc_ndcg_at_3_diff1": 0.005578692131126525, + "nauc_ndcg_at_3_max": 0.20395556727133993, + "nauc_ndcg_at_3_std": 0.043248597795966015, + "nauc_ndcg_at_5_diff1": 0.06740614923630275, + "nauc_ndcg_at_5_max": 0.21548716604700188, + "nauc_ndcg_at_5_std": 0.05383328629661877, + "nauc_precision_at_1000_diff1": 0.05067525277670407, + "nauc_precision_at_1000_max": 0.17677172579272274, + "nauc_precision_at_1000_std": 0.08085492182850659, + "nauc_precision_at_100_diff1": 0.05210865109102013, + "nauc_precision_at_100_max": 0.12329968301074656, + "nauc_precision_at_100_std": 0.037246448781321516, + "nauc_precision_at_10_diff1": 0.10496703010789399, + "nauc_precision_at_10_max": 0.18252148531193318, + "nauc_precision_at_10_std": 0.07163938824792046, + "nauc_precision_at_1_diff1": -0.09130284794357774, + "nauc_precision_at_1_max": 0.03028096132469622, + "nauc_precision_at_1_std": -0.07298094982559696, + "nauc_precision_at_20_diff1": 0.08930681825272532, + "nauc_precision_at_20_max": 0.17444543588271638, + "nauc_precision_at_20_std": 0.06350640517655584, + "nauc_precision_at_3_diff1": 0.0423486271353189, + "nauc_precision_at_3_max": 0.2470198167810189, + "nauc_precision_at_3_std": 0.07648817509295112, + "nauc_precision_at_5_diff1": 0.11479356491504072, + "nauc_precision_at_5_max": 0.24481109710332988, + "nauc_precision_at_5_std": 0.07744669589923237, + "nauc_recall_at_1000_diff1": 0.05067525277670567, + "nauc_recall_at_1000_max": 0.17677172579272354, + "nauc_recall_at_1000_std": 0.08085492182850773, + "nauc_recall_at_100_diff1": 0.052108651091019975, + "nauc_recall_at_100_max": 0.12329968301074665, + "nauc_recall_at_100_std": 0.037246448781321384, + "nauc_recall_at_10_diff1": 0.1049670301078941, + "nauc_recall_at_10_max": 0.18252148531193352, + "nauc_recall_at_10_std": 0.07163938824792059, + "nauc_recall_at_1_diff1": -0.09130284794357774, + "nauc_recall_at_1_max": 0.03028096132469622, + "nauc_recall_at_1_std": -0.07298094982559696, + "nauc_recall_at_20_diff1": 0.08930681825272532, + "nauc_recall_at_20_max": 0.17444543588271644, + "nauc_recall_at_20_std": 0.06350640517655577, + "nauc_recall_at_3_diff1": 0.042348627135318916, + "nauc_recall_at_3_max": 0.24701981678101886, + "nauc_recall_at_3_std": 0.0764881750929511, + "nauc_recall_at_5_diff1": 0.11479356491504066, + "nauc_recall_at_5_max": 0.2448110971033297, + "nauc_recall_at_5_std": 0.07744669589923227, + "ndcg_at_1": 0.0035, + "ndcg_at_10": 0.01524, + "ndcg_at_100": 0.04445, + "ndcg_at_1000": 0.09913, + "ndcg_at_20": 0.02047, + "ndcg_at_3": 0.00736, + "ndcg_at_5": 0.01047, + "precision_at_1": 0.0035, + "precision_at_10": 0.0033, + "precision_at_100": 0.00188, + "precision_at_1000": 0.00065, + "precision_at_20": 0.00269, + "precision_at_3": 0.0035, + "precision_at_5": 0.00365, + "recall_at_1": 0.0035, + "recall_at_10": 0.033, + "recall_at_100": 0.1885, + "recall_at_1000": 0.64775, + "recall_at_20": 0.05375, + "recall_at_3": 0.0105, + "recall_at_5": 0.01825 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL2Fact.json b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL2Fact.json new file mode 100644 index 000000000..a528c17a1 --- /dev/null +++ b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL2Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 24.66033697128296, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07284, + "map_at_1": 0.0265, + "map_at_10": 0.05417, + "map_at_100": 0.06168, + "map_at_1000": 0.06297, + "map_at_20": 0.05771, + "map_at_3": 0.04252, + "map_at_5": 0.0484, + "mrr_at_1": 0.026496201593477858, + "mrr_at_10": 0.05417405613347802, + "mrr_at_100": 0.061681077991378785, + "mrr_at_1000": 0.06297078709232626, + "mrr_at_20": 0.0577123735505498, + "mrr_at_3": 0.04252362423568653, + "mrr_at_5": 0.04839725773577916, + "nauc_map_at_1000_diff1": -0.08847763468767939, + "nauc_map_at_1000_max": 0.20436222283876665, + "nauc_map_at_1000_std": 0.2397735987743752, + "nauc_map_at_100_diff1": -0.08898283671972469, + "nauc_map_at_100_max": 0.20512941914006855, + "nauc_map_at_100_std": 0.23948374115812002, + "nauc_map_at_10_diff1": -0.08602900918478812, + "nauc_map_at_10_max": 0.2221180611509691, + "nauc_map_at_10_std": 0.223439607814511, + "nauc_map_at_1_diff1": -0.01576142861272267, + "nauc_map_at_1_max": 0.27346138963539907, + "nauc_map_at_1_std": 0.20167829588293482, + "nauc_map_at_20_diff1": -0.08855333400010122, + "nauc_map_at_20_max": 0.2158945441892563, + "nauc_map_at_20_std": 0.23051605696431007, + "nauc_map_at_3_diff1": -0.0577188441707291, + "nauc_map_at_3_max": 0.26263390164280626, + "nauc_map_at_3_std": 0.22506018371730946, + "nauc_map_at_5_diff1": -0.07753252915093084, + "nauc_map_at_5_max": 0.24261193725431768, + "nauc_map_at_5_std": 0.2171656067429338, + "nauc_mrr_at_1000_diff1": -0.08847763468767939, + "nauc_mrr_at_1000_max": 0.20436222283876665, + "nauc_mrr_at_1000_std": 0.2397735987743752, + "nauc_mrr_at_100_diff1": -0.08898283671972469, + "nauc_mrr_at_100_max": 0.20512941914006855, + "nauc_mrr_at_100_std": 0.23948374115812002, + "nauc_mrr_at_10_diff1": -0.08602900918478812, + "nauc_mrr_at_10_max": 0.2221180611509691, + "nauc_mrr_at_10_std": 0.223439607814511, + "nauc_mrr_at_1_diff1": -0.01576142861272267, + "nauc_mrr_at_1_max": 0.27346138963539907, + "nauc_mrr_at_1_std": 0.20167829588293482, + "nauc_mrr_at_20_diff1": -0.08855333400010122, + "nauc_mrr_at_20_max": 0.2158945441892563, + "nauc_mrr_at_20_std": 0.23051605696431007, + "nauc_mrr_at_3_diff1": -0.0577188441707291, + "nauc_mrr_at_3_max": 0.26263390164280626, + "nauc_mrr_at_3_std": 0.22506018371730946, + "nauc_mrr_at_5_diff1": -0.07753252915093084, + "nauc_mrr_at_5_max": 0.24261193725431768, + "nauc_mrr_at_5_std": 0.2171656067429338, + "nauc_ndcg_at_1000_diff1": -0.10175726687818308, + "nauc_ndcg_at_1000_max": 0.12731576922366786, + "nauc_ndcg_at_1000_std": 0.29104526176634327, + "nauc_ndcg_at_100_diff1": -0.10507596252932322, + "nauc_ndcg_at_100_max": 0.13697558514707112, + "nauc_ndcg_at_100_std": 0.2955328189792036, + "nauc_ndcg_at_10_diff1": -0.10714650236897494, + "nauc_ndcg_at_10_max": 0.19507335327055483, + "nauc_ndcg_at_10_std": 0.22961108810725464, + "nauc_ndcg_at_1_diff1": -0.01576142861272267, + "nauc_ndcg_at_1_max": 0.27346138963539907, + "nauc_ndcg_at_1_std": 0.20167829588293482, + "nauc_ndcg_at_20_diff1": -0.11096708309394786, + "nauc_ndcg_at_20_max": 0.18130283420280716, + "nauc_ndcg_at_20_std": 0.24736058469341143, + "nauc_ndcg_at_3_diff1": -0.06551668971670309, + "nauc_ndcg_at_3_max": 0.25913475590200324, + "nauc_ndcg_at_3_std": 0.22857468838372597, + "nauc_ndcg_at_5_diff1": -0.09363528382908749, + "nauc_ndcg_at_5_max": 0.22976671174652444, + "nauc_ndcg_at_5_std": 0.21649962896068176, + "nauc_precision_at_1000_diff1": -0.1070544461624388, + "nauc_precision_at_1000_max": -0.015855049185558336, + "nauc_precision_at_1000_std": 0.3825799089670327, + "nauc_precision_at_100_diff1": -0.11344935432325645, + "nauc_precision_at_100_max": 0.046676058967742275, + "nauc_precision_at_100_std": 0.38366587142510705, + "nauc_precision_at_10_diff1": -0.1375918042593693, + "nauc_precision_at_10_max": 0.15411443787323376, + "nauc_precision_at_10_std": 0.23976990732178083, + "nauc_precision_at_1_diff1": -0.01576142861272267, + "nauc_precision_at_1_max": 0.27346138963539907, + "nauc_precision_at_1_std": 0.20167829588293482, + "nauc_precision_at_20_diff1": -0.13807638276670767, + "nauc_precision_at_20_max": 0.1352756433134364, + "nauc_precision_at_20_std": 0.27256116025064564, + "nauc_precision_at_3_diff1": -0.08048756851434076, + "nauc_precision_at_3_max": 0.2520884639194972, + "nauc_precision_at_3_std": 0.2351385527942633, + "nauc_precision_at_5_diff1": -0.12081352641053407, + "nauc_precision_at_5_max": 0.2072725253492048, + "nauc_precision_at_5_std": 0.21459248922891003, + "nauc_recall_at_1000_diff1": -0.10705444616243828, + "nauc_recall_at_1000_max": -0.01585504918555754, + "nauc_recall_at_1000_std": 0.3825799089670333, + "nauc_recall_at_100_diff1": -0.11344935432325665, + "nauc_recall_at_100_max": 0.04667605896774203, + "nauc_recall_at_100_std": 0.38366587142510683, + "nauc_recall_at_10_diff1": -0.13759180425936926, + "nauc_recall_at_10_max": 0.15411443787323384, + "nauc_recall_at_10_std": 0.23976990732178086, + "nauc_recall_at_1_diff1": -0.01576142861272267, + "nauc_recall_at_1_max": 0.27346138963539907, + "nauc_recall_at_1_std": 0.20167829588293482, + "nauc_recall_at_20_diff1": -0.13807638276670783, + "nauc_recall_at_20_max": 0.13527564331343628, + "nauc_recall_at_20_std": 0.2725611602506456, + "nauc_recall_at_3_diff1": -0.08048756851434068, + "nauc_recall_at_3_max": 0.2520884639194971, + "nauc_recall_at_3_std": 0.23513855279426318, + "nauc_recall_at_5_diff1": -0.12081352641053414, + "nauc_recall_at_5_max": 0.2072725253492046, + "nauc_recall_at_5_std": 0.21459248922890997, + "ndcg_at_1": 0.0265, + "ndcg_at_10": 0.07284, + "ndcg_at_100": 0.1179, + "ndcg_at_1000": 0.15738, + "ndcg_at_20": 0.08585, + "ndcg_at_3": 0.04809, + "ndcg_at_5": 0.05869, + "precision_at_1": 0.0265, + "precision_at_10": 0.01341, + "precision_at_100": 0.00366, + "precision_at_1000": 0.00069, + "precision_at_20": 0.00929, + "precision_at_3": 0.02143, + "precision_at_5": 0.01801, + "recall_at_1": 0.0265, + "recall_at_10": 0.13415, + "recall_at_100": 0.36557, + "recall_at_1000": 0.68816, + "recall_at_20": 0.18584, + "recall_at_3": 0.06429, + "recall_at_5": 0.09005 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL2Pure.json b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL2Pure.json new file mode 100644 index 000000000..ceda79fcd --- /dev/null +++ b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL2Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 10.996459484100342, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01034, + "map_at_1": 0.00315, + "map_at_10": 0.00728, + "map_at_100": 0.0106, + "map_at_1000": 0.01187, + "map_at_20": 0.0086, + "map_at_3": 0.00544, + "map_at_5": 0.00619, + "mrr_at_1": 0.003149898091532333, + "mrr_at_10": 0.007280058586339855, + "mrr_at_100": 0.010600605126228362, + "mrr_at_1000": 0.011872730821837098, + "mrr_at_20": 0.00860140905109129, + "mrr_at_3": 0.0054351182755852006, + "mrr_at_5": 0.006185535173862021, + "nauc_map_at_1000_diff1": 0.049541868258225596, + "nauc_map_at_1000_max": 0.2197860938891953, + "nauc_map_at_1000_std": 0.40225191269387633, + "nauc_map_at_100_diff1": 0.05376280552457225, + "nauc_map_at_100_max": 0.22687621458753351, + "nauc_map_at_100_std": 0.40241802584153896, + "nauc_map_at_10_diff1": 0.0879291686188845, + "nauc_map_at_10_max": 0.2541887556821548, + "nauc_map_at_10_std": 0.4563982725638618, + "nauc_map_at_1_diff1": 0.19761503827246082, + "nauc_map_at_1_max": 0.45383021172200805, + "nauc_map_at_1_std": 0.7237709039632031, + "nauc_map_at_20_diff1": 0.06343338383412711, + "nauc_map_at_20_max": 0.23915337808525863, + "nauc_map_at_20_std": 0.426997145014829, + "nauc_map_at_3_diff1": 0.12094508106225542, + "nauc_map_at_3_max": 0.2785515824200025, + "nauc_map_at_3_std": 0.5067140061208592, + "nauc_map_at_5_diff1": 0.10109732652222304, + "nauc_map_at_5_max": 0.264103709583348, + "nauc_map_at_5_std": 0.48763679609031435, + "nauc_mrr_at_1000_diff1": 0.049541868258225596, + "nauc_mrr_at_1000_max": 0.2197860938891953, + "nauc_mrr_at_1000_std": 0.40225191269387633, + "nauc_mrr_at_100_diff1": 0.05376280552457225, + "nauc_mrr_at_100_max": 0.22687621458753351, + "nauc_mrr_at_100_std": 0.40241802584153896, + "nauc_mrr_at_10_diff1": 0.0879291686188845, + "nauc_mrr_at_10_max": 0.2541887556821548, + "nauc_mrr_at_10_std": 0.4563982725638618, + "nauc_mrr_at_1_diff1": 0.19761503827246082, + "nauc_mrr_at_1_max": 0.45383021172200805, + "nauc_mrr_at_1_std": 0.7237709039632031, + "nauc_mrr_at_20_diff1": 0.06343338383412711, + "nauc_mrr_at_20_max": 0.23915337808525863, + "nauc_mrr_at_20_std": 0.426997145014829, + "nauc_mrr_at_3_diff1": 0.12094508106225542, + "nauc_mrr_at_3_max": 0.2785515824200025, + "nauc_mrr_at_3_std": 0.5067140061208592, + "nauc_mrr_at_5_diff1": 0.10109732652222304, + "nauc_mrr_at_5_max": 0.264103709583348, + "nauc_mrr_at_5_std": 0.48763679609031435, + "nauc_ndcg_at_1000_diff1": 0.0002606634389197262, + "nauc_ndcg_at_1000_max": 0.14052076483263704, + "nauc_ndcg_at_1000_std": 0.3388106375050361, + "nauc_ndcg_at_100_diff1": 0.013224729313116574, + "nauc_ndcg_at_100_max": 0.1908160363502396, + "nauc_ndcg_at_100_std": 0.33449862574416234, + "nauc_ndcg_at_10_diff1": 0.06436363303841007, + "nauc_ndcg_at_10_max": 0.2260912358762874, + "nauc_ndcg_at_10_std": 0.4037846161979956, + "nauc_ndcg_at_1_diff1": 0.19761503827246082, + "nauc_ndcg_at_1_max": 0.45383021172200805, + "nauc_ndcg_at_1_std": 0.7237709039632031, + "nauc_ndcg_at_20_diff1": 0.024685721977727906, + "nauc_ndcg_at_20_max": 0.20702225919331835, + "nauc_ndcg_at_20_std": 0.3600783077969015, + "nauc_ndcg_at_3_diff1": 0.10615000804074678, + "nauc_ndcg_at_3_max": 0.2519724604991561, + "nauc_ndcg_at_3_std": 0.4744439676488597, + "nauc_ndcg_at_5_diff1": 0.07931409032332687, + "nauc_ndcg_at_5_max": 0.235164480224918, + "nauc_ndcg_at_5_std": 0.4511091503678177, + "nauc_precision_at_1000_diff1": -0.015732887869177193, + "nauc_precision_at_1000_max": 0.09947206551030192, + "nauc_precision_at_1000_std": 0.3213023747576786, + "nauc_precision_at_100_diff1": -0.00250918575884294, + "nauc_precision_at_100_max": 0.17876519370350988, + "nauc_precision_at_100_std": 0.3124265377905229, + "nauc_precision_at_10_diff1": 0.03775935296381738, + "nauc_precision_at_10_max": 0.19575619701866243, + "nauc_precision_at_10_std": 0.34102579417778484, + "nauc_precision_at_1_diff1": 0.19761503827246082, + "nauc_precision_at_1_max": 0.45383021172200805, + "nauc_precision_at_1_std": 0.7237709039632031, + "nauc_precision_at_20_diff1": -0.005939350317831742, + "nauc_precision_at_20_max": 0.18454474827286105, + "nauc_precision_at_20_std": 0.30663058630291773, + "nauc_precision_at_3_diff1": 0.07898461532201533, + "nauc_precision_at_3_max": 0.2045227401248064, + "nauc_precision_at_3_std": 0.41698775167237445, + "nauc_precision_at_5_diff1": 0.04453500813324286, + "nauc_precision_at_5_max": 0.19119653276494195, + "nauc_precision_at_5_std": 0.39526313164391347, + "nauc_recall_at_1000_diff1": -0.01573288786917699, + "nauc_recall_at_1000_max": 0.09947206551030201, + "nauc_recall_at_1000_std": 0.3213023747576786, + "nauc_recall_at_100_diff1": -0.002509185758843092, + "nauc_recall_at_100_max": 0.1787651937035099, + "nauc_recall_at_100_std": 0.3124265377905231, + "nauc_recall_at_10_diff1": 0.037759352963817217, + "nauc_recall_at_10_max": 0.1957561970186621, + "nauc_recall_at_10_std": 0.3410257941777846, + "nauc_recall_at_1_diff1": 0.19761503827246082, + "nauc_recall_at_1_max": 0.45383021172200805, + "nauc_recall_at_1_std": 0.7237709039632031, + "nauc_recall_at_20_diff1": -0.0059393503178317986, + "nauc_recall_at_20_max": 0.18454474827286116, + "nauc_recall_at_20_std": 0.3066305863029174, + "nauc_recall_at_3_diff1": 0.07898461532201538, + "nauc_recall_at_3_max": 0.20452274012480656, + "nauc_recall_at_3_std": 0.4169877516723747, + "nauc_recall_at_5_diff1": 0.04453500813324261, + "nauc_recall_at_5_max": 0.19119653276494156, + "nauc_recall_at_5_std": 0.3952631316439129, + "ndcg_at_1": 0.00315, + "ndcg_at_10": 0.01034, + "ndcg_at_100": 0.03218, + "ndcg_at_1000": 0.07558, + "ndcg_at_20": 0.01532, + "ndcg_at_3": 0.00627, + "ndcg_at_5": 0.00763, + "precision_at_1": 0.00315, + "precision_at_10": 0.00206, + "precision_at_100": 0.00137, + "precision_at_1000": 0.0005, + "precision_at_20": 0.00203, + "precision_at_3": 0.0029, + "precision_at_5": 0.00241, + "recall_at_1": 0.00315, + "recall_at_10": 0.02057, + "recall_at_100": 0.13656, + "recall_at_1000": 0.49917, + "recall_at_20": 0.04058, + "recall_at_3": 0.00871, + "recall_at_5": 0.01204 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL3Fact.json b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL3Fact.json new file mode 100644 index 000000000..af40c16de --- /dev/null +++ b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL3Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 21.516083478927612, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07032, + "map_at_1": 0.01943, + "map_at_10": 0.04979, + "map_at_100": 0.05883, + "map_at_1000": 0.06002, + "map_at_20": 0.05412, + "map_at_3": 0.03747, + "map_at_5": 0.04336, + "mrr_at_1": 0.019430637144148215, + "mrr_at_10": 0.04978831794805582, + "mrr_at_100": 0.05883445367542635, + "mrr_at_1000": 0.060019525027389664, + "mrr_at_20": 0.05411829868788225, + "mrr_at_3": 0.037467992167495114, + "mrr_at_5": 0.043364964603102886, + "nauc_map_at_1000_diff1": -0.05162797260670335, + "nauc_map_at_1000_max": 0.19169535811373906, + "nauc_map_at_1000_std": 0.31803012454450413, + "nauc_map_at_100_diff1": -0.051671807451527316, + "nauc_map_at_100_max": 0.1918667872374215, + "nauc_map_at_100_std": 0.3187235063557153, + "nauc_map_at_10_diff1": -0.050828025235194266, + "nauc_map_at_10_max": 0.20742297083916836, + "nauc_map_at_10_std": 0.29630367713819744, + "nauc_map_at_1_diff1": -0.056372718653567036, + "nauc_map_at_1_max": 0.20378299096120941, + "nauc_map_at_1_std": 0.24508130310130394, + "nauc_map_at_20_diff1": -0.05444054879074532, + "nauc_map_at_20_max": 0.20042785135992455, + "nauc_map_at_20_std": 0.3061601645019103, + "nauc_map_at_3_diff1": -0.03463035651928383, + "nauc_map_at_3_max": 0.2342235128114665, + "nauc_map_at_3_std": 0.2829107280359363, + "nauc_map_at_5_diff1": -0.03232167611177763, + "nauc_map_at_5_max": 0.2306212741426414, + "nauc_map_at_5_std": 0.2813540274560482, + "nauc_mrr_at_1000_diff1": -0.05162797260670335, + "nauc_mrr_at_1000_max": 0.19169535811373906, + "nauc_mrr_at_1000_std": 0.31803012454450413, + "nauc_mrr_at_100_diff1": -0.051671807451527316, + "nauc_mrr_at_100_max": 0.1918667872374215, + "nauc_mrr_at_100_std": 0.3187235063557153, + "nauc_mrr_at_10_diff1": -0.050828025235194266, + "nauc_mrr_at_10_max": 0.20742297083916836, + "nauc_mrr_at_10_std": 0.29630367713819744, + "nauc_mrr_at_1_diff1": -0.056372718653567036, + "nauc_mrr_at_1_max": 0.20378299096120941, + "nauc_mrr_at_1_std": 0.24508130310130394, + "nauc_mrr_at_20_diff1": -0.05444054879074532, + "nauc_mrr_at_20_max": 0.20042785135992455, + "nauc_mrr_at_20_std": 0.3061601645019103, + "nauc_mrr_at_3_diff1": -0.03463035651928383, + "nauc_mrr_at_3_max": 0.2342235128114665, + "nauc_mrr_at_3_std": 0.2829107280359363, + "nauc_mrr_at_5_diff1": -0.03232167611177763, + "nauc_mrr_at_5_max": 0.2306212741426414, + "nauc_mrr_at_5_std": 0.2813540274560482, + "nauc_ndcg_at_1000_diff1": -0.05632905131708492, + "nauc_ndcg_at_1000_max": 0.13452782352547485, + "nauc_ndcg_at_1000_std": 0.37676642002867217, + "nauc_ndcg_at_100_diff1": -0.052337911352557935, + "nauc_ndcg_at_100_max": 0.13935395266606607, + "nauc_ndcg_at_100_std": 0.39384433008325337, + "nauc_ndcg_at_10_diff1": -0.063363691738885, + "nauc_ndcg_at_10_max": 0.1932263248191885, + "nauc_ndcg_at_10_std": 0.3121170857621029, + "nauc_ndcg_at_1_diff1": -0.056372718653567036, + "nauc_ndcg_at_1_max": 0.20378299096120941, + "nauc_ndcg_at_1_std": 0.24508130310130394, + "nauc_ndcg_at_20_diff1": -0.0696687062694561, + "nauc_ndcg_at_20_max": 0.17739054648317024, + "nauc_ndcg_at_20_std": 0.33469453248692865, + "nauc_ndcg_at_3_diff1": -0.033177303256392704, + "nauc_ndcg_at_3_max": 0.23888551556747106, + "nauc_ndcg_at_3_std": 0.2880491423049012, + "nauc_ndcg_at_5_diff1": -0.03055229131392118, + "nauc_ndcg_at_5_max": 0.23205560608243164, + "nauc_ndcg_at_5_std": 0.2842636709829693, + "nauc_precision_at_1000_diff1": -0.06080627706955836, + "nauc_precision_at_1000_max": 0.01908133394239326, + "nauc_precision_at_1000_std": 0.46041332904453497, + "nauc_precision_at_100_diff1": -0.0436424628153559, + "nauc_precision_at_100_max": 0.06828480322831977, + "nauc_precision_at_100_std": 0.49866528826568046, + "nauc_precision_at_10_diff1": -0.08262356756443556, + "nauc_precision_at_10_max": 0.17192294476406977, + "nauc_precision_at_10_std": 0.33484316581175044, + "nauc_precision_at_1_diff1": -0.056372718653567036, + "nauc_precision_at_1_max": 0.20378299096120941, + "nauc_precision_at_1_std": 0.24508130310130394, + "nauc_precision_at_20_diff1": -0.08865776304575618, + "nauc_precision_at_20_max": 0.14748643313948367, + "nauc_precision_at_20_std": 0.3712750295445386, + "nauc_precision_at_3_diff1": -0.031017120615182317, + "nauc_precision_at_3_max": 0.2470365243906701, + "nauc_precision_at_3_std": 0.29690033173578717, + "nauc_precision_at_5_diff1": -0.02829831306624735, + "nauc_precision_at_5_max": 0.2333384206935965, + "nauc_precision_at_5_std": 0.28783824521038986, + "nauc_recall_at_1000_diff1": -0.06080627706955896, + "nauc_recall_at_1000_max": 0.019081333942392028, + "nauc_recall_at_1000_std": 0.46041332904453447, + "nauc_recall_at_100_diff1": -0.04364246281535579, + "nauc_recall_at_100_max": 0.06828480322831972, + "nauc_recall_at_100_std": 0.4986652882656803, + "nauc_recall_at_10_diff1": -0.08262356756443583, + "nauc_recall_at_10_max": 0.1719229447640696, + "nauc_recall_at_10_std": 0.33484316581175, + "nauc_recall_at_1_diff1": -0.056372718653567036, + "nauc_recall_at_1_max": 0.20378299096120941, + "nauc_recall_at_1_std": 0.24508130310130394, + "nauc_recall_at_20_diff1": -0.08865776304575632, + "nauc_recall_at_20_max": 0.14748643313948331, + "nauc_recall_at_20_std": 0.37127502954453856, + "nauc_recall_at_3_diff1": -0.031017120615182265, + "nauc_recall_at_3_max": 0.24703652439067003, + "nauc_recall_at_3_std": 0.2969003317357871, + "nauc_recall_at_5_diff1": -0.028298313066247437, + "nauc_recall_at_5_max": 0.2333384206935964, + "nauc_recall_at_5_std": 0.2878382452103897, + "ndcg_at_1": 0.01943, + "ndcg_at_10": 0.07032, + "ndcg_at_100": 0.12353, + "ndcg_at_1000": 0.15992, + "ndcg_at_20": 0.08605, + "ndcg_at_3": 0.04382, + "ndcg_at_5": 0.05454, + "precision_at_1": 0.01943, + "precision_at_10": 0.01378, + "precision_at_100": 0.00409, + "precision_at_1000": 0.00071, + "precision_at_20": 0.01, + "precision_at_3": 0.02079, + "precision_at_5": 0.01771, + "recall_at_1": 0.01943, + "recall_at_10": 0.13782, + "recall_at_100": 0.40895, + "recall_at_1000": 0.70606, + "recall_at_20": 0.19995, + "recall_at_3": 0.06236, + "recall_at_5": 0.08857 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL3Pure.json b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL3Pure.json new file mode 100644 index 000000000..163e94802 --- /dev/null +++ b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/TempReasonL3Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 9.87415075302124, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.05164, + "map_at_1": 0.00904, + "map_at_10": 0.03406, + "map_at_100": 0.0422, + "map_at_1000": 0.04335, + "map_at_20": 0.03812, + "map_at_3": 0.02297, + "map_at_5": 0.02835, + "mrr_at_1": 0.00903750564844103, + "mrr_at_10": 0.034062520173003694, + "mrr_at_100": 0.04219506814417097, + "mrr_at_1000": 0.043345746828664274, + "mrr_at_20": 0.038122542216726424, + "mrr_at_3": 0.02297032685645428, + "mrr_at_5": 0.028347642717276696, + "nauc_map_at_1000_diff1": -0.10226927798292783, + "nauc_map_at_1000_max": 0.311280903505638, + "nauc_map_at_1000_std": 0.4467180352649543, + "nauc_map_at_100_diff1": -0.1039393196807826, + "nauc_map_at_100_max": 0.3100189207472267, + "nauc_map_at_100_std": 0.4458487310633563, + "nauc_map_at_10_diff1": -0.09841016871905922, + "nauc_map_at_10_max": 0.315173830324495, + "nauc_map_at_10_std": 0.42072736218368945, + "nauc_map_at_1_diff1": -0.235543845897742, + "nauc_map_at_1_max": 0.21699440676940057, + "nauc_map_at_1_std": 0.4821276362953649, + "nauc_map_at_20_diff1": -0.10071243584726804, + "nauc_map_at_20_max": 0.31212269602091025, + "nauc_map_at_20_std": 0.4327762596315706, + "nauc_map_at_3_diff1": -0.10707417624604, + "nauc_map_at_3_max": 0.32433177765009646, + "nauc_map_at_3_std": 0.4304143347272247, + "nauc_map_at_5_diff1": -0.09755101107135854, + "nauc_map_at_5_max": 0.32198347776222835, + "nauc_map_at_5_std": 0.42033142375222654, + "nauc_mrr_at_1000_diff1": -0.10226927218641611, + "nauc_mrr_at_1000_max": 0.31128090712741024, + "nauc_mrr_at_1000_std": 0.4467180482508882, + "nauc_mrr_at_100_diff1": -0.1039393196807826, + "nauc_mrr_at_100_max": 0.3100189207472267, + "nauc_mrr_at_100_std": 0.4458487310633563, + "nauc_mrr_at_10_diff1": -0.09841016871905922, + "nauc_mrr_at_10_max": 0.315173830324495, + "nauc_mrr_at_10_std": 0.42072736218368945, + "nauc_mrr_at_1_diff1": -0.235543845897742, + "nauc_mrr_at_1_max": 0.21699440676940057, + "nauc_mrr_at_1_std": 0.4821276362953649, + "nauc_mrr_at_20_diff1": -0.10071243584726804, + "nauc_mrr_at_20_max": 0.31212269602091025, + "nauc_mrr_at_20_std": 0.4327762596315706, + "nauc_mrr_at_3_diff1": -0.10707417624604, + "nauc_mrr_at_3_max": 0.32433177765009646, + "nauc_mrr_at_3_std": 0.4304143347272247, + "nauc_mrr_at_5_diff1": -0.09755101107135854, + "nauc_mrr_at_5_max": 0.32198347776222835, + "nauc_mrr_at_5_std": 0.42033142375222654, + "nauc_ndcg_at_1000_diff1": -0.08522166970460014, + "nauc_ndcg_at_1000_max": 0.3148002739599331, + "nauc_ndcg_at_1000_std": 0.502606252830811, + "nauc_ndcg_at_100_diff1": -0.10306495589471562, + "nauc_ndcg_at_100_max": 0.3071358057864791, + "nauc_ndcg_at_100_std": 0.5002221920524851, + "nauc_ndcg_at_10_diff1": -0.09161477125724146, + "nauc_ndcg_at_10_max": 0.3162933469163416, + "nauc_ndcg_at_10_std": 0.41914072462084623, + "nauc_ndcg_at_1_diff1": -0.235543845897742, + "nauc_ndcg_at_1_max": 0.21699440676940057, + "nauc_ndcg_at_1_std": 0.4821276362953649, + "nauc_ndcg_at_20_diff1": -0.09827782230150181, + "nauc_ndcg_at_20_max": 0.30979352659717097, + "nauc_ndcg_at_20_std": 0.4463159854903517, + "nauc_ndcg_at_3_diff1": -0.09482211061828492, + "nauc_ndcg_at_3_max": 0.33540867666520413, + "nauc_ndcg_at_3_std": 0.4263238327748354, + "nauc_ndcg_at_5_diff1": -0.08666139460340484, + "nauc_ndcg_at_5_max": 0.3294123113327206, + "nauc_ndcg_at_5_std": 0.4146166803562481, + "nauc_precision_at_1000_diff1": -0.05017501932715478, + "nauc_precision_at_1000_max": 0.31957511748180684, + "nauc_precision_at_1000_std": 0.5764435091155288, + "nauc_precision_at_100_diff1": -0.10130738704552086, + "nauc_precision_at_100_max": 0.3051752066974924, + "nauc_precision_at_100_std": 0.5649943343678312, + "nauc_precision_at_10_diff1": -0.08661924098929072, + "nauc_precision_at_10_max": 0.3154208711841806, + "nauc_precision_at_10_std": 0.41935812228749264, + "nauc_precision_at_1_diff1": -0.235543845897742, + "nauc_precision_at_1_max": 0.21699440676940057, + "nauc_precision_at_1_std": 0.4821276362953649, + "nauc_precision_at_20_diff1": -0.09937975220317193, + "nauc_precision_at_20_max": 0.30527247368396104, + "nauc_precision_at_20_std": 0.4645734355003584, + "nauc_precision_at_3_diff1": -0.07553713173038411, + "nauc_precision_at_3_max": 0.35303467951919676, + "nauc_precision_at_3_std": 0.42007632681797513, + "nauc_precision_at_5_diff1": -0.07340649795511592, + "nauc_precision_at_5_max": 0.33834094208739796, + "nauc_precision_at_5_std": 0.4073617078143493, + "nauc_recall_at_1000_diff1": -0.050175019327155006, + "nauc_recall_at_1000_max": 0.3195751174818071, + "nauc_recall_at_1000_std": 0.5764435091155293, + "nauc_recall_at_100_diff1": -0.10130738704552132, + "nauc_recall_at_100_max": 0.3051752066974921, + "nauc_recall_at_100_std": 0.5649943343678313, + "nauc_recall_at_10_diff1": -0.08661924098929086, + "nauc_recall_at_10_max": 0.31542087118418055, + "nauc_recall_at_10_std": 0.41935812228749264, + "nauc_recall_at_1_diff1": -0.235543845897742, + "nauc_recall_at_1_max": 0.21699440676940057, + "nauc_recall_at_1_std": 0.4821276362953649, + "nauc_recall_at_20_diff1": -0.09937975220317208, + "nauc_recall_at_20_max": 0.305272473683961, + "nauc_recall_at_20_std": 0.4645734355003584, + "nauc_recall_at_3_diff1": -0.07553713173038407, + "nauc_recall_at_3_max": 0.35303467951919687, + "nauc_recall_at_3_std": 0.42007632681797547, + "nauc_recall_at_5_diff1": -0.07340649795511611, + "nauc_recall_at_5_max": 0.33834094208739796, + "nauc_recall_at_5_std": 0.4073617078143492, + "ndcg_at_1": 0.00904, + "ndcg_at_10": 0.05164, + "ndcg_at_100": 0.09824, + "ndcg_at_1000": 0.13507, + "ndcg_at_20": 0.06632, + "ndcg_at_3": 0.02773, + "ndcg_at_5": 0.03751, + "precision_at_1": 0.00904, + "precision_at_10": 0.01098, + "precision_at_100": 0.00345, + "precision_at_1000": 0.00065, + "precision_at_20": 0.00838, + "precision_at_3": 0.01386, + "precision_at_5": 0.0131, + "recall_at_1": 0.00904, + "recall_at_10": 0.10981, + "recall_at_100": 0.34455, + "recall_at_1000": 0.64844, + "recall_at_20": 0.16765, + "recall_at_3": 0.04157, + "recall_at_5": 0.06552 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/WinoGrande.json b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/WinoGrande.json new file mode 100644 index 000000000..568fd3514 --- /dev/null +++ b/results/all-mpnet-base-v2-instruct/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/WinoGrande.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 2.6721534729003906, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.09663, + "map_at_1": 0.02447, + "map_at_10": 0.0667, + "map_at_100": 0.08216, + "map_at_1000": 0.08357, + "map_at_20": 0.07363, + "map_at_3": 0.04709, + "map_at_5": 0.05727, + "mrr_at_1": 0.0244672454617206, + "mrr_at_10": 0.0669259969181043, + "mrr_at_100": 0.08238790332303517, + "mrr_at_1000": 0.0837948771098478, + "mrr_at_20": 0.07385404446833416, + "mrr_at_3": 0.04735595895816892, + "mrr_at_5": 0.05749802683504344, + "nauc_map_at_1000_diff1": -0.0668241906692978, + "nauc_map_at_1000_max": 0.1719893242475886, + "nauc_map_at_1000_std": 0.23357049319434015, + "nauc_map_at_100_diff1": -0.06652083686382482, + "nauc_map_at_100_max": 0.17154073173149903, + "nauc_map_at_100_std": 0.23273472694450206, + "nauc_map_at_10_diff1": -0.07816526008249035, + "nauc_map_at_10_max": 0.16465379256522034, + "nauc_map_at_10_std": 0.24155483843092157, + "nauc_map_at_1_diff1": -0.029505857365671125, + "nauc_map_at_1_max": 0.3199077076035854, + "nauc_map_at_1_std": 0.3257928623609872, + "nauc_map_at_20_diff1": -0.06904711814325859, + "nauc_map_at_20_max": 0.16636638148533156, + "nauc_map_at_20_std": 0.23246639724826762, + "nauc_map_at_3_diff1": -0.05973547707845018, + "nauc_map_at_3_max": 0.23953693124698378, + "nauc_map_at_3_std": 0.28175801559299657, + "nauc_map_at_5_diff1": -0.0836334068009708, + "nauc_map_at_5_max": 0.1802266970860904, + "nauc_map_at_5_std": 0.2688860877207363, + "nauc_mrr_at_1000_diff1": -0.06651520211785601, + "nauc_mrr_at_1000_max": 0.17047484992058196, + "nauc_mrr_at_1000_std": 0.23300983963507052, + "nauc_mrr_at_100_diff1": -0.06621578187781862, + "nauc_mrr_at_100_max": 0.1700412057674403, + "nauc_mrr_at_100_std": 0.23218204507947782, + "nauc_mrr_at_10_diff1": -0.07780329216996903, + "nauc_mrr_at_10_max": 0.16312797133762347, + "nauc_mrr_at_10_std": 0.2409621800353309, + "nauc_mrr_at_1_diff1": -0.029505857365671125, + "nauc_mrr_at_1_max": 0.3199077076035854, + "nauc_mrr_at_1_std": 0.3257928623609872, + "nauc_mrr_at_20_diff1": -0.0687227218334376, + "nauc_mrr_at_20_max": 0.16489268537492938, + "nauc_mrr_at_20_std": 0.2319197979480476, + "nauc_mrr_at_3_diff1": -0.06054707537050731, + "nauc_mrr_at_3_max": 0.23543029588870504, + "nauc_mrr_at_3_std": 0.2807400914047235, + "nauc_mrr_at_5_diff1": -0.08321415425065158, + "nauc_mrr_at_5_max": 0.17848225597661166, + "nauc_mrr_at_5_std": 0.26814346144204, + "nauc_ndcg_at_1000_diff1": -0.05420866853054503, + "nauc_ndcg_at_1000_max": 0.1533837388288174, + "nauc_ndcg_at_1000_std": 0.20932197845958625, + "nauc_ndcg_at_100_diff1": -0.04500187274926999, + "nauc_ndcg_at_100_max": 0.1462303950596911, + "nauc_ndcg_at_100_std": 0.19827047251995178, + "nauc_ndcg_at_10_diff1": -0.08359073789923585, + "nauc_ndcg_at_10_max": 0.12092027590795011, + "nauc_ndcg_at_10_std": 0.21113435851789186, + "nauc_ndcg_at_1_diff1": -0.029505857365671125, + "nauc_ndcg_at_1_max": 0.3199077076035854, + "nauc_ndcg_at_1_std": 0.3257928623609872, + "nauc_ndcg_at_20_diff1": -0.05730309340856969, + "nauc_ndcg_at_20_max": 0.12868926333765618, + "nauc_ndcg_at_20_std": 0.1914610794151881, + "nauc_ndcg_at_3_diff1": -0.06450235864608217, + "nauc_ndcg_at_3_max": 0.22486418097440083, + "nauc_ndcg_at_3_std": 0.2741730449511409, + "nauc_ndcg_at_5_diff1": -0.09696673850057276, + "nauc_ndcg_at_5_max": 0.1421914379117137, + "nauc_ndcg_at_5_std": 0.2552413583383972, + "nauc_precision_at_1000_diff1": 0.061155746215494265, + "nauc_precision_at_1000_max": 0.18303402787903456, + "nauc_precision_at_1000_std": 0.1687608266739442, + "nauc_precision_at_100_diff1": 0.005465934140137009, + "nauc_precision_at_100_max": 0.12403567351573032, + "nauc_precision_at_100_std": 0.1570018937648052, + "nauc_precision_at_10_diff1": -0.08798453148383999, + "nauc_precision_at_10_max": 0.06461431305210592, + "nauc_precision_at_10_std": 0.16986937376354577, + "nauc_precision_at_1_diff1": -0.029505857365671125, + "nauc_precision_at_1_max": 0.3199077076035854, + "nauc_precision_at_1_std": 0.3257928623609872, + "nauc_precision_at_20_diff1": -0.0343703509389339, + "nauc_precision_at_20_max": 0.08874234817648641, + "nauc_precision_at_20_std": 0.14014425921640578, + "nauc_precision_at_3_diff1": -0.07272218299709844, + "nauc_precision_at_3_max": 0.1991754951351244, + "nauc_precision_at_3_std": 0.26096951958482467, + "nauc_precision_at_5_diff1": -0.11726317032445555, + "nauc_precision_at_5_max": 0.08345739150969947, + "nauc_precision_at_5_std": 0.23413671014750048, + "nauc_recall_at_1000_diff1": 0.06115574621549303, + "nauc_recall_at_1000_max": 0.18303402787902823, + "nauc_recall_at_1000_std": 0.16876082667393943, + "nauc_recall_at_100_diff1": 0.005465934140137097, + "nauc_recall_at_100_max": 0.12403567351572972, + "nauc_recall_at_100_std": 0.15700189376480486, + "nauc_recall_at_10_diff1": -0.08798453148384011, + "nauc_recall_at_10_max": 0.06461431305210583, + "nauc_recall_at_10_std": 0.16986937376354577, + "nauc_recall_at_1_diff1": -0.029505857365671125, + "nauc_recall_at_1_max": 0.3199077076035854, + "nauc_recall_at_1_std": 0.3257928623609872, + "nauc_recall_at_20_diff1": -0.034370350938934154, + "nauc_recall_at_20_max": 0.08874234817648621, + "nauc_recall_at_20_std": 0.1401442592164056, + "nauc_recall_at_3_diff1": -0.07272218299709857, + "nauc_recall_at_3_max": 0.19917549513512461, + "nauc_recall_at_3_std": 0.2609695195848247, + "nauc_recall_at_5_diff1": -0.1172631703244555, + "nauc_recall_at_5_max": 0.08345739150969925, + "nauc_recall_at_5_std": 0.23413671014750034, + "ndcg_at_1": 0.02447, + "ndcg_at_10": 0.09663, + "ndcg_at_100": 0.18741, + "ndcg_at_1000": 0.22658, + "ndcg_at_20": 0.12246, + "ndcg_at_3": 0.0554, + "ndcg_at_5": 0.07401, + "precision_at_1": 0.02447, + "precision_at_10": 0.01949, + "precision_at_100": 0.00655, + "precision_at_1000": 0.00097, + "precision_at_20": 0.01492, + "precision_at_3": 0.02657, + "precision_at_5": 0.0251, + "recall_at_1": 0.02447, + "recall_at_10": 0.19495, + "recall_at_100": 0.65509, + "recall_at_1000": 0.96685, + "recall_at_20": 0.29834, + "recall_at_3": 0.07972, + "recall_at_5": 0.12549 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/all-mpnet-base-v2/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/model_metaInstruct.json b/results/all-mpnet-base-v2/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/model_metaInstruct.json new file mode 100644 index 000000000..c61f2fe7e --- /dev/null +++ b/results/all-mpnet-base-v2/84f2bcc00d77236f9e89c8a360a00fb1139bf47d/model_metaInstruct.json @@ -0,0 +1 @@ +{"name": "sentence-transformers/all-mpnet-base-v2", "revision": "84f2bcc00d77236f9e89c8a360a00fb1139bf47d", "release_date": null, "languages": [], "n_parameters": null, "memory_usage": null, "max_tokens": null, "embed_dim": null, "license": null, "open_source": null, "similarity_fn_name": null, "framework": ["Sentence Transformers"], "loader": null} \ No newline at end of file diff --git a/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/ARCChallenge.json b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/ARCChallenge.json new file mode 100644 index 000000000..1d7f778c3 --- /dev/null +++ b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/ARCChallenge.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 4.344338417053223, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.08847, + "map_at_1": 0.02901, + "map_at_10": 0.06583, + "map_at_100": 0.07376, + "map_at_1000": 0.07501, + "map_at_20": 0.06982, + "map_at_3": 0.05247, + "map_at_5": 0.06049, + "mrr_at_1": 0.02901023890784983, + "mrr_at_10": 0.0658293379923073, + "mrr_at_100": 0.07376467945673014, + "mrr_at_1000": 0.07500902844557128, + "mrr_at_20": 0.06982247771843637, + "mrr_at_3": 0.05247440273037545, + "mrr_at_5": 0.0604948805460751, + "nauc_map_at_1000_diff1": 0.02008694148409546, + "nauc_map_at_1000_max": 0.04208195507370021, + "nauc_map_at_1000_std": -0.015131772797674687, + "nauc_map_at_100_diff1": 0.020342048915077834, + "nauc_map_at_100_max": 0.04240731583792526, + "nauc_map_at_100_std": -0.015160541088241294, + "nauc_map_at_10_diff1": 0.0110928258132665, + "nauc_map_at_10_max": 0.04133560243616957, + "nauc_map_at_10_std": -0.02732133518767032, + "nauc_map_at_1_diff1": 0.04147510426517444, + "nauc_map_at_1_max": 0.015814749893090573, + "nauc_map_at_1_std": -0.055421892599856026, + "nauc_map_at_20_diff1": 0.020649422771165563, + "nauc_map_at_20_max": 0.04326375757815727, + "nauc_map_at_20_std": -0.02191522591189752, + "nauc_map_at_3_diff1": -0.006643086266890845, + "nauc_map_at_3_max": 0.03538877262402818, + "nauc_map_at_3_std": -0.02160128973563387, + "nauc_map_at_5_diff1": 0.005548069664532131, + "nauc_map_at_5_max": 0.04415013854664527, + "nauc_map_at_5_std": -0.023239886489857565, + "nauc_mrr_at_1000_diff1": 0.02008704961736538, + "nauc_mrr_at_1000_max": 0.042082101037602584, + "nauc_mrr_at_1000_std": -0.01513205034691004, + "nauc_mrr_at_100_diff1": 0.020342048915077834, + "nauc_mrr_at_100_max": 0.04240731583792526, + "nauc_mrr_at_100_std": -0.015160541088241294, + "nauc_mrr_at_10_diff1": 0.0110928258132665, + "nauc_mrr_at_10_max": 0.04133560243616957, + "nauc_mrr_at_10_std": -0.02732133518767032, + "nauc_mrr_at_1_diff1": 0.04147510426517444, + "nauc_mrr_at_1_max": 0.015814749893090573, + "nauc_mrr_at_1_std": -0.055421892599856026, + "nauc_mrr_at_20_diff1": 0.020649422771165563, + "nauc_mrr_at_20_max": 0.04326375757815727, + "nauc_mrr_at_20_std": -0.02191522591189752, + "nauc_mrr_at_3_diff1": -0.006643086266890845, + "nauc_mrr_at_3_max": 0.03538877262402818, + "nauc_mrr_at_3_std": -0.02160128973563387, + "nauc_mrr_at_5_diff1": 0.005548069664532131, + "nauc_mrr_at_5_max": 0.04415013854664527, + "nauc_mrr_at_5_std": -0.023239886489857565, + "nauc_ndcg_at_1000_diff1": 0.03004468092359935, + "nauc_ndcg_at_1000_max": 0.032366664035787876, + "nauc_ndcg_at_1000_std": 0.020043022280597178, + "nauc_ndcg_at_100_diff1": 0.030031437886497012, + "nauc_ndcg_at_100_max": 0.038751987870486525, + "nauc_ndcg_at_100_std": 0.020372577171131293, + "nauc_ndcg_at_10_diff1": 0.013930129383590818, + "nauc_ndcg_at_10_max": 0.04361433054218669, + "nauc_ndcg_at_10_std": -0.027580421457694848, + "nauc_ndcg_at_1_diff1": 0.04147510426517444, + "nauc_ndcg_at_1_max": 0.015814749893090573, + "nauc_ndcg_at_1_std": -0.055421892599856026, + "nauc_ndcg_at_20_diff1": 0.03794452602742283, + "nauc_ndcg_at_20_max": 0.04662983099589807, + "nauc_ndcg_at_20_std": -0.013460873504720172, + "nauc_ndcg_at_3_diff1": -0.013809734218576838, + "nauc_ndcg_at_3_max": 0.037530992391747564, + "nauc_ndcg_at_3_std": -0.01616540467155038, + "nauc_ndcg_at_5_diff1": 0.003843086456767247, + "nauc_ndcg_at_5_max": 0.04951634417552556, + "nauc_ndcg_at_5_std": -0.019304516120465656, + "nauc_precision_at_1000_diff1": 0.044939034528056754, + "nauc_precision_at_1000_max": -0.009157826714734425, + "nauc_precision_at_1000_std": 0.10415492814527845, + "nauc_precision_at_100_diff1": 0.03768357731825887, + "nauc_precision_at_100_max": 0.026364197854664085, + "nauc_precision_at_100_std": 0.08338128210819319, + "nauc_precision_at_10_diff1": 0.019926875218727862, + "nauc_precision_at_10_max": 0.04590935049392597, + "nauc_precision_at_10_std": -0.02963051399174363, + "nauc_precision_at_1_diff1": 0.04147510426517444, + "nauc_precision_at_1_max": 0.015814749893090573, + "nauc_precision_at_1_std": -0.055421892599856026, + "nauc_precision_at_20_diff1": 0.06683760531346081, + "nauc_precision_at_20_max": 0.049535272315425094, + "nauc_precision_at_20_std": -0.0006049232814754852, + "nauc_precision_at_3_diff1": -0.02622860881031306, + "nauc_precision_at_3_max": 0.0410708473303889, + "nauc_precision_at_3_std": -0.006656843627190506, + "nauc_precision_at_5_diff1": 0.0020793716857578476, + "nauc_precision_at_5_max": 0.0580546628158665, + "nauc_precision_at_5_std": -0.013581000053221496, + "nauc_recall_at_1000_diff1": 0.04493903452805655, + "nauc_recall_at_1000_max": -0.009157826714734946, + "nauc_recall_at_1000_std": 0.10415492814527716, + "nauc_recall_at_100_diff1": 0.0376835773182591, + "nauc_recall_at_100_max": 0.026364197854663755, + "nauc_recall_at_100_std": 0.08338128210819279, + "nauc_recall_at_10_diff1": 0.019926875218727557, + "nauc_recall_at_10_max": 0.04590935049392557, + "nauc_recall_at_10_std": -0.02963051399174372, + "nauc_recall_at_1_diff1": 0.04147510426517444, + "nauc_recall_at_1_max": 0.015814749893090573, + "nauc_recall_at_1_std": -0.055421892599856026, + "nauc_recall_at_20_diff1": 0.06683760531346065, + "nauc_recall_at_20_max": 0.04953527231542496, + "nauc_recall_at_20_std": -0.0006049232814756212, + "nauc_recall_at_3_diff1": -0.026228608810313126, + "nauc_recall_at_3_max": 0.04107084733038889, + "nauc_recall_at_3_std": -0.006656843627190429, + "nauc_recall_at_5_diff1": 0.002079371685757826, + "nauc_recall_at_5_max": 0.058054662815866354, + "nauc_recall_at_5_std": -0.01358100005322149, + "ndcg_at_1": 0.02901, + "ndcg_at_10": 0.08847, + "ndcg_at_100": 0.13331, + "ndcg_at_1000": 0.1721, + "ndcg_at_20": 0.10324, + "ndcg_at_3": 0.06126, + "ndcg_at_5": 0.07551, + "precision_at_1": 0.02901, + "precision_at_10": 0.01613, + "precision_at_100": 0.00386, + "precision_at_1000": 0.0007, + "precision_at_20": 0.01101, + "precision_at_3": 0.02901, + "precision_at_5": 0.02423, + "recall_at_1": 0.02901, + "recall_at_10": 0.16126, + "recall_at_100": 0.38567, + "recall_at_1000": 0.70307, + "recall_at_20": 0.22014, + "recall_at_3": 0.08703, + "recall_at_5": 0.12116 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/AlphaNLI.json b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/AlphaNLI.json new file mode 100644 index 000000000..c399b6541 --- /dev/null +++ b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/AlphaNLI.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 55.416616678237915, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.04127, + "map_at_1": 0.01697, + "map_at_10": 0.03174, + "map_at_100": 0.03658, + "map_at_1000": 0.03737, + "map_at_20": 0.03386, + "map_at_3": 0.026, + "map_at_5": 0.02864, + "mrr_at_1": 0.016971279373368148, + "mrr_at_10": 0.031738001989307485, + "mrr_at_100": 0.03657560958897724, + "mrr_at_1000": 0.037368914401100954, + "mrr_at_20": 0.03385597390856207, + "mrr_at_3": 0.026000870322019153, + "mrr_at_5": 0.028644473455178426, + "nauc_map_at_1000_diff1": 0.1307939111933654, + "nauc_map_at_1000_max": 0.02468955991771351, + "nauc_map_at_1000_std": 0.1498055462489034, + "nauc_map_at_100_diff1": 0.13160858366969538, + "nauc_map_at_100_max": 0.02513786545197126, + "nauc_map_at_100_std": 0.15012576689918822, + "nauc_map_at_10_diff1": 0.14553187983896293, + "nauc_map_at_10_max": 0.030129352872493593, + "nauc_map_at_10_std": 0.17052786986211407, + "nauc_map_at_1_diff1": 0.24320734839619335, + "nauc_map_at_1_max": 0.079525605904931, + "nauc_map_at_1_std": 0.1858196604722081, + "nauc_map_at_20_diff1": 0.13620518332065756, + "nauc_map_at_20_max": 0.026801130070910346, + "nauc_map_at_20_std": 0.1553194681009836, + "nauc_map_at_3_diff1": 0.15811658209530707, + "nauc_map_at_3_max": 0.049617387310641456, + "nauc_map_at_3_std": 0.19318578855093743, + "nauc_map_at_5_diff1": 0.1431141881960533, + "nauc_map_at_5_max": 0.03407210117300336, + "nauc_map_at_5_std": 0.19264233453716692, + "nauc_mrr_at_1000_diff1": 0.1307939111933654, + "nauc_mrr_at_1000_max": 0.02468955991771351, + "nauc_mrr_at_1000_std": 0.1498055462489034, + "nauc_mrr_at_100_diff1": 0.13160858366969538, + "nauc_mrr_at_100_max": 0.02513786545197126, + "nauc_mrr_at_100_std": 0.15012576689918822, + "nauc_mrr_at_10_diff1": 0.14553187983896293, + "nauc_mrr_at_10_max": 0.030129352872493593, + "nauc_mrr_at_10_std": 0.17052786986211407, + "nauc_mrr_at_1_diff1": 0.24320734839619335, + "nauc_mrr_at_1_max": 0.079525605904931, + "nauc_mrr_at_1_std": 0.1858196604722081, + "nauc_mrr_at_20_diff1": 0.13620518332065756, + "nauc_mrr_at_20_max": 0.026801130070910346, + "nauc_mrr_at_20_std": 0.1553194681009836, + "nauc_mrr_at_3_diff1": 0.15811658209530707, + "nauc_mrr_at_3_max": 0.049617387310641456, + "nauc_mrr_at_3_std": 0.19318578855093743, + "nauc_mrr_at_5_diff1": 0.1431141881960533, + "nauc_mrr_at_5_max": 0.03407210117300336, + "nauc_mrr_at_5_std": 0.19264233453716692, + "nauc_ndcg_at_1000_diff1": 0.07561805774450689, + "nauc_ndcg_at_1000_max": 0.0004085119564255939, + "nauc_ndcg_at_1000_std": 0.1075316844290818, + "nauc_ndcg_at_100_diff1": 0.08681481583238183, + "nauc_ndcg_at_100_max": 0.0035912199270794554, + "nauc_ndcg_at_100_std": 0.10947509749754451, + "nauc_ndcg_at_10_diff1": 0.1275665442203892, + "nauc_ndcg_at_10_max": 0.013353300099365879, + "nauc_ndcg_at_10_std": 0.15198632156222733, + "nauc_ndcg_at_1_diff1": 0.24320734839619335, + "nauc_ndcg_at_1_max": 0.079525605904931, + "nauc_ndcg_at_1_std": 0.1858196604722081, + "nauc_ndcg_at_20_diff1": 0.10504136009418609, + "nauc_ndcg_at_20_max": 0.009328225625103959, + "nauc_ndcg_at_20_std": 0.11848314866279049, + "nauc_ndcg_at_3_diff1": 0.14006087209744011, + "nauc_ndcg_at_3_max": 0.042071101916501194, + "nauc_ndcg_at_3_std": 0.19540070029859305, + "nauc_ndcg_at_5_diff1": 0.1191503716844144, + "nauc_ndcg_at_5_max": 0.017521816688721926, + "nauc_ndcg_at_5_std": 0.19333692571985786, + "nauc_precision_at_1000_diff1": 0.020216403485664683, + "nauc_precision_at_1000_max": -0.018585157838078518, + "nauc_precision_at_1000_std": 0.07479795661269607, + "nauc_precision_at_100_diff1": 0.043023755659208365, + "nauc_precision_at_100_max": -0.014772616229624688, + "nauc_precision_at_100_std": 0.07537245631799742, + "nauc_precision_at_10_diff1": 0.10441780421639897, + "nauc_precision_at_10_max": -0.010674418518343201, + "nauc_precision_at_10_std": 0.12100664744346858, + "nauc_precision_at_1_diff1": 0.24320734839619335, + "nauc_precision_at_1_max": 0.079525605904931, + "nauc_precision_at_1_std": 0.1858196604722081, + "nauc_precision_at_20_diff1": 0.06706930582465569, + "nauc_precision_at_20_max": -0.009398511444715004, + "nauc_precision_at_20_std": 0.06889528690703217, + "nauc_precision_at_3_diff1": 0.10375998564227257, + "nauc_precision_at_3_max": 0.026646856189282673, + "nauc_precision_at_3_std": 0.19999092840514796, + "nauc_precision_at_5_diff1": 0.07683318653647003, + "nauc_precision_at_5_max": -0.013338886496931435, + "nauc_precision_at_5_std": 0.19403809160669908, + "nauc_recall_at_1000_diff1": 0.020216403485664752, + "nauc_recall_at_1000_max": -0.018585157838077956, + "nauc_recall_at_1000_std": 0.07479795661269659, + "nauc_recall_at_100_diff1": 0.043023755659208324, + "nauc_recall_at_100_max": -0.01477261622962472, + "nauc_recall_at_100_std": 0.07537245631799754, + "nauc_recall_at_10_diff1": 0.1044178042163988, + "nauc_recall_at_10_max": -0.010674418518343345, + "nauc_recall_at_10_std": 0.12100664744346844, + "nauc_recall_at_1_diff1": 0.24320734839619335, + "nauc_recall_at_1_max": 0.079525605904931, + "nauc_recall_at_1_std": 0.1858196604722081, + "nauc_recall_at_20_diff1": 0.06706930582465544, + "nauc_recall_at_20_max": -0.009398511444715232, + "nauc_recall_at_20_std": 0.06889528690703191, + "nauc_recall_at_3_diff1": 0.10375998564227241, + "nauc_recall_at_3_max": 0.026646856189282583, + "nauc_recall_at_3_std": 0.19999092840514787, + "nauc_recall_at_5_diff1": 0.07683318653646981, + "nauc_recall_at_5_max": -0.013338886496931499, + "nauc_recall_at_5_std": 0.19403809160669885, + "ndcg_at_1": 0.01697, + "ndcg_at_10": 0.04127, + "ndcg_at_100": 0.07023, + "ndcg_at_1000": 0.09725, + "ndcg_at_20": 0.04912, + "ndcg_at_3": 0.02904, + "ndcg_at_5": 0.03384, + "precision_at_1": 0.01697, + "precision_at_10": 0.00725, + "precision_at_100": 0.00221, + "precision_at_1000": 0.00045, + "precision_at_20": 0.00519, + "precision_at_3": 0.01262, + "precision_at_5": 0.00992, + "recall_at_1": 0.01697, + "recall_at_10": 0.07245, + "recall_at_100": 0.22063, + "recall_at_1000": 0.44648, + "recall_at_20": 0.10379, + "recall_at_3": 0.03786, + "recall_at_5": 0.04961 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/HellaSwag.json b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/HellaSwag.json new file mode 100644 index 000000000..c466f3727 --- /dev/null +++ b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/HellaSwag.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 141.99754071235657, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.24032, + "map_at_1": 0.13055, + "map_at_10": 0.20162, + "map_at_100": 0.20903, + "map_at_1000": 0.20979, + "map_at_20": 0.20568, + "map_at_3": 0.18043, + "map_at_5": 0.19286, + "mrr_at_1": 0.13055168293168692, + "mrr_at_10": 0.20162270843409966, + "mrr_at_100": 0.20902628080684515, + "mrr_at_1000": 0.20979363044533741, + "mrr_at_20": 0.2056816750194837, + "mrr_at_3": 0.1804255460399646, + "mrr_at_5": 0.1928583283542451, + "nauc_map_at_1000_diff1": 0.32678010096760496, + "nauc_map_at_1000_max": 0.38510561757861883, + "nauc_map_at_1000_std": 0.0732433603454581, + "nauc_map_at_100_diff1": 0.326611659802891, + "nauc_map_at_100_max": 0.38485735264157955, + "nauc_map_at_100_std": 0.07316807602407738, + "nauc_map_at_10_diff1": 0.32691370684877585, + "nauc_map_at_10_max": 0.38050474740051926, + "nauc_map_at_10_std": 0.06867085446651076, + "nauc_map_at_1_diff1": 0.36092414408863954, + "nauc_map_at_1_max": 0.3331619866641534, + "nauc_map_at_1_std": 0.05357726406088081, + "nauc_map_at_20_diff1": 0.3265183663422, + "nauc_map_at_20_max": 0.3828160623572349, + "nauc_map_at_20_std": 0.07120136971352274, + "nauc_map_at_3_diff1": 0.32821530509389657, + "nauc_map_at_3_max": 0.36655533479910796, + "nauc_map_at_3_std": 0.06136410871861661, + "nauc_map_at_5_diff1": 0.32652848184168665, + "nauc_map_at_5_max": 0.37532986453214656, + "nauc_map_at_5_std": 0.06577493238463779, + "nauc_mrr_at_1000_diff1": 0.3267800555729614, + "nauc_mrr_at_1000_max": 0.38510564331923053, + "nauc_mrr_at_1000_std": 0.07324339361200408, + "nauc_mrr_at_100_diff1": 0.32661161512231135, + "nauc_mrr_at_100_max": 0.3848573799832148, + "nauc_mrr_at_100_std": 0.07316811069492145, + "nauc_mrr_at_10_diff1": 0.32691370684877585, + "nauc_mrr_at_10_max": 0.38050474740051926, + "nauc_mrr_at_10_std": 0.06867085446651076, + "nauc_mrr_at_1_diff1": 0.36092414408863954, + "nauc_mrr_at_1_max": 0.3331619866641534, + "nauc_mrr_at_1_std": 0.05357726406088081, + "nauc_mrr_at_20_diff1": 0.3265183663422, + "nauc_mrr_at_20_max": 0.3828160623572349, + "nauc_mrr_at_20_std": 0.07120136971352274, + "nauc_mrr_at_3_diff1": 0.32821530509389657, + "nauc_mrr_at_3_max": 0.36655533479910796, + "nauc_mrr_at_3_std": 0.06136410871861661, + "nauc_mrr_at_5_diff1": 0.32652848184168665, + "nauc_mrr_at_5_max": 0.37532986453214656, + "nauc_mrr_at_5_std": 0.06577493238463779, + "nauc_ndcg_at_1000_diff1": 0.32283914308665745, + "nauc_ndcg_at_1000_max": 0.4297263476750566, + "nauc_ndcg_at_1000_std": 0.10078547860561472, + "nauc_ndcg_at_100_diff1": 0.31965331759448756, + "nauc_ndcg_at_100_max": 0.424286115085239, + "nauc_ndcg_at_100_std": 0.10057123876597929, + "nauc_ndcg_at_10_diff1": 0.3202725198569539, + "nauc_ndcg_at_10_max": 0.4022170641291852, + "nauc_ndcg_at_10_std": 0.07794111778691158, + "nauc_ndcg_at_1_diff1": 0.36092414408863954, + "nauc_ndcg_at_1_max": 0.3331619866641534, + "nauc_ndcg_at_1_std": 0.05357726406088081, + "nauc_ndcg_at_20_diff1": 0.3188721660891458, + "nauc_ndcg_at_20_max": 0.41015530889613133, + "nauc_ndcg_at_20_std": 0.0870724836797184, + "nauc_ndcg_at_3_diff1": 0.3215355951649192, + "nauc_ndcg_at_3_max": 0.37691484866498426, + "nauc_ndcg_at_3_std": 0.0640661539995593, + "nauc_ndcg_at_5_diff1": 0.3192463925782665, + "nauc_ndcg_at_5_max": 0.3911047039920815, + "nauc_ndcg_at_5_std": 0.07129417805623495, + "nauc_precision_at_1000_diff1": 0.32617435739500644, + "nauc_precision_at_1000_max": 0.6612406536181912, + "nauc_precision_at_1000_std": 0.24034184246324322, + "nauc_precision_at_100_diff1": 0.304743237122063, + "nauc_precision_at_100_max": 0.5516803880898821, + "nauc_precision_at_100_std": 0.19772144530668798, + "nauc_precision_at_10_diff1": 0.3065319167871567, + "nauc_precision_at_10_max": 0.45440932835435355, + "nauc_precision_at_10_std": 0.10116533092649468, + "nauc_precision_at_1_diff1": 0.36092414408863954, + "nauc_precision_at_1_max": 0.3331619866641534, + "nauc_precision_at_1_std": 0.05357726406088081, + "nauc_precision_at_20_diff1": 0.30205059573748166, + "nauc_precision_at_20_max": 0.47963360562183993, + "nauc_precision_at_20_std": 0.13113134765884263, + "nauc_precision_at_3_diff1": 0.3060859786704391, + "nauc_precision_at_3_max": 0.40202418343069435, + "nauc_precision_at_3_std": 0.07067652131455351, + "nauc_precision_at_5_diff1": 0.30330458955496264, + "nauc_precision_at_5_max": 0.4282102450194321, + "nauc_precision_at_5_std": 0.08452841154370541, + "nauc_recall_at_1000_diff1": 0.32617435739500744, + "nauc_recall_at_1000_max": 0.661240653618192, + "nauc_recall_at_1000_std": 0.2403418424632445, + "nauc_recall_at_100_diff1": 0.3047432371220633, + "nauc_recall_at_100_max": 0.5516803880898827, + "nauc_recall_at_100_std": 0.19772144530668878, + "nauc_recall_at_10_diff1": 0.3065319167871567, + "nauc_recall_at_10_max": 0.45440932835435366, + "nauc_recall_at_10_std": 0.1011653309264946, + "nauc_recall_at_1_diff1": 0.36092414408863954, + "nauc_recall_at_1_max": 0.3331619866641534, + "nauc_recall_at_1_std": 0.05357726406088081, + "nauc_recall_at_20_diff1": 0.3020505957374821, + "nauc_recall_at_20_max": 0.47963360562184, + "nauc_recall_at_20_std": 0.1311313476588428, + "nauc_recall_at_3_diff1": 0.30608597867043885, + "nauc_recall_at_3_max": 0.4020241834306945, + "nauc_recall_at_3_std": 0.07067652131455354, + "nauc_recall_at_5_diff1": 0.3033045895549626, + "nauc_recall_at_5_max": 0.4282102450194319, + "nauc_recall_at_5_std": 0.08452841154370566, + "ndcg_at_1": 0.13055, + "ndcg_at_10": 0.24032, + "ndcg_at_100": 0.28018, + "ndcg_at_1000": 0.30399, + "ndcg_at_20": 0.25507, + "ndcg_at_3": 0.19696, + "ndcg_at_5": 0.21923, + "precision_at_1": 0.13055, + "precision_at_10": 0.03636, + "precision_at_100": 0.00559, + "precision_at_1000": 0.00075, + "precision_at_20": 0.02109, + "precision_at_3": 0.08162, + "precision_at_5": 0.05973, + "recall_at_1": 0.13055, + "recall_at_10": 0.36357, + "recall_at_100": 0.55905, + "recall_at_1000": 0.75403, + "recall_at_20": 0.42183, + "recall_at_3": 0.24487, + "recall_at_5": 0.29865 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/PIQA.json b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/PIQA.json new file mode 100644 index 000000000..a77ba675b --- /dev/null +++ b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/PIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 17.822925329208374, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.2303, + "map_at_1": 0.11371, + "map_at_10": 0.19144, + "map_at_100": 0.20018, + "map_at_1000": 0.20086, + "map_at_20": 0.19633, + "map_at_3": 0.17211, + "map_at_5": 0.18302, + "mrr_at_1": 0.11371055495103373, + "mrr_at_10": 0.19143867557904531, + "mrr_at_100": 0.20018140941574397, + "mrr_at_1000": 0.20086432489543876, + "mrr_at_20": 0.19632899761495134, + "mrr_at_3": 0.17210736307580693, + "mrr_at_5": 0.18301595937613319, + "nauc_map_at_1000_diff1": -0.08647579641079739, + "nauc_map_at_1000_max": 0.2247396871976366, + "nauc_map_at_1000_std": 0.12169146873510497, + "nauc_map_at_100_diff1": -0.08627611370815273, + "nauc_map_at_100_max": 0.2250421729600354, + "nauc_map_at_100_std": 0.12155647593013572, + "nauc_map_at_10_diff1": -0.08120968378665933, + "nauc_map_at_10_max": 0.22824371121971873, + "nauc_map_at_10_std": 0.11673818162354503, + "nauc_map_at_1_diff1": -0.024808917273145412, + "nauc_map_at_1_max": 0.23945902935106816, + "nauc_map_at_1_std": 0.11279959301045896, + "nauc_map_at_20_diff1": -0.08431297973794438, + "nauc_map_at_20_max": 0.2256073022217941, + "nauc_map_at_20_std": 0.11814518047166525, + "nauc_map_at_3_diff1": -0.07254248780484275, + "nauc_map_at_3_max": 0.2467712757947556, + "nauc_map_at_3_std": 0.115871849284269, + "nauc_map_at_5_diff1": -0.07879114972991366, + "nauc_map_at_5_max": 0.2378539812076467, + "nauc_map_at_5_std": 0.11552089431483169, + "nauc_mrr_at_1000_diff1": -0.08647584228172688, + "nauc_mrr_at_1000_max": 0.2247396488758694, + "nauc_mrr_at_1000_std": 0.12169146631098786, + "nauc_mrr_at_100_diff1": -0.08627611370815273, + "nauc_mrr_at_100_max": 0.2250421729600354, + "nauc_mrr_at_100_std": 0.12155647593013572, + "nauc_mrr_at_10_diff1": -0.08120968378665933, + "nauc_mrr_at_10_max": 0.22824371121971873, + "nauc_mrr_at_10_std": 0.11673818162354503, + "nauc_mrr_at_1_diff1": -0.024808917273145412, + "nauc_mrr_at_1_max": 0.23945902935106816, + "nauc_mrr_at_1_std": 0.11279959301045896, + "nauc_mrr_at_20_diff1": -0.08431297973794438, + "nauc_mrr_at_20_max": 0.2256073022217941, + "nauc_mrr_at_20_std": 0.11814518047166525, + "nauc_mrr_at_3_diff1": -0.07254248780484275, + "nauc_mrr_at_3_max": 0.2467712757947556, + "nauc_mrr_at_3_std": 0.115871849284269, + "nauc_mrr_at_5_diff1": -0.07879114972991366, + "nauc_mrr_at_5_max": 0.2378539812076467, + "nauc_mrr_at_5_std": 0.11552089431483169, + "nauc_ndcg_at_1000_diff1": -0.1253857788428432, + "nauc_ndcg_at_1000_max": 0.19313993232492244, + "nauc_ndcg_at_1000_std": 0.15278937847497093, + "nauc_ndcg_at_100_diff1": -0.11709546754466743, + "nauc_ndcg_at_100_max": 0.20168967733972076, + "nauc_ndcg_at_100_std": 0.14852556109766465, + "nauc_ndcg_at_10_diff1": -0.09677869305289684, + "nauc_ndcg_at_10_max": 0.21093338908720496, + "nauc_ndcg_at_10_std": 0.11891184697490974, + "nauc_ndcg_at_1_diff1": -0.024808917273145412, + "nauc_ndcg_at_1_max": 0.23945902935106816, + "nauc_ndcg_at_1_std": 0.11279959301045896, + "nauc_ndcg_at_20_diff1": -0.10566011856965701, + "nauc_ndcg_at_20_max": 0.20338473751109323, + "nauc_ndcg_at_20_std": 0.12494033495380784, + "nauc_ndcg_at_3_diff1": -0.0821266790646656, + "nauc_ndcg_at_3_max": 0.24620243445393586, + "nauc_ndcg_at_3_std": 0.11678447862581505, + "nauc_ndcg_at_5_diff1": -0.09254094386634922, + "nauc_ndcg_at_5_max": 0.23179259405397548, + "nauc_ndcg_at_5_std": 0.11657124069169432, + "nauc_precision_at_1000_diff1": -0.3298679894220244, + "nauc_precision_at_1000_max": 0.030784880822039732, + "nauc_precision_at_1000_std": 0.34037678339390465, + "nauc_precision_at_100_diff1": -0.2110873131997825, + "nauc_precision_at_100_max": 0.13549777498324767, + "nauc_precision_at_100_std": 0.2565952288976948, + "nauc_precision_at_10_diff1": -0.13101184324161375, + "nauc_precision_at_10_max": 0.16668660834837307, + "nauc_precision_at_10_std": 0.12417928976381994, + "nauc_precision_at_1_diff1": -0.024808917273145412, + "nauc_precision_at_1_max": 0.23945902935106816, + "nauc_precision_at_1_std": 0.11279959301045896, + "nauc_precision_at_20_diff1": -0.15598517738120138, + "nauc_precision_at_20_max": 0.14565786258251434, + "nauc_precision_at_20_std": 0.1450560542492542, + "nauc_precision_at_3_diff1": -0.10368502857763826, + "nauc_precision_at_3_max": 0.24431146619881255, + "nauc_precision_at_3_std": 0.11892609282774637, + "nauc_precision_at_5_diff1": -0.12331313864921821, + "nauc_precision_at_5_max": 0.21675164017494042, + "nauc_precision_at_5_std": 0.11909496286191393, + "nauc_recall_at_1000_diff1": -0.3298679894220239, + "nauc_recall_at_1000_max": 0.030784880822040162, + "nauc_recall_at_1000_std": 0.34037678339390515, + "nauc_recall_at_100_diff1": -0.21108731319978305, + "nauc_recall_at_100_max": 0.13549777498324753, + "nauc_recall_at_100_std": 0.25659522889769415, + "nauc_recall_at_10_diff1": -0.13101184324161372, + "nauc_recall_at_10_max": 0.16668660834837323, + "nauc_recall_at_10_std": 0.12417928976381984, + "nauc_recall_at_1_diff1": -0.024808917273145412, + "nauc_recall_at_1_max": 0.23945902935106816, + "nauc_recall_at_1_std": 0.11279959301045896, + "nauc_recall_at_20_diff1": -0.15598517738120113, + "nauc_recall_at_20_max": 0.14565786258251442, + "nauc_recall_at_20_std": 0.14505605424925447, + "nauc_recall_at_3_diff1": -0.1036850285776381, + "nauc_recall_at_3_max": 0.24431146619881264, + "nauc_recall_at_3_std": 0.11892609282774648, + "nauc_recall_at_5_diff1": -0.12331313864921833, + "nauc_recall_at_5_max": 0.21675164017494017, + "nauc_recall_at_5_std": 0.11909496286191405, + "ndcg_at_1": 0.11371, + "ndcg_at_10": 0.2303, + "ndcg_at_100": 0.2766, + "ndcg_at_1000": 0.29704, + "ndcg_at_20": 0.24807, + "ndcg_at_3": 0.19042, + "ndcg_at_5": 0.21, + "precision_at_1": 0.11371, + "precision_at_10": 0.03531, + "precision_at_100": 0.00578, + "precision_at_1000": 0.00074, + "precision_at_20": 0.02116, + "precision_at_3": 0.08107, + "precision_at_5": 0.05811, + "recall_at_1": 0.11371, + "recall_at_10": 0.3531, + "recall_at_100": 0.57835, + "recall_at_1000": 0.74374, + "recall_at_20": 0.42329, + "recall_at_3": 0.2432, + "recall_at_5": 0.29053 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/Quail.json b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/Quail.json new file mode 100644 index 000000000..df29979e1 --- /dev/null +++ b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/Quail.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 27.00935935974121, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01246, + "map_at_1": 0.00404, + "map_at_10": 0.00881, + "map_at_100": 0.01108, + "map_at_1000": 0.01176, + "map_at_20": 0.0097, + "map_at_3": 0.00637, + "map_at_5": 0.00738, + "mrr_at_1": 0.004044117647058824, + "mrr_at_10": 0.008808210784313725, + "mrr_at_100": 0.011076548124353002, + "mrr_at_1000": 0.011758303735620253, + "mrr_at_20": 0.009701672632733116, + "mrr_at_3": 0.006372549019607844, + "mrr_at_5": 0.007383578431372549, + "nauc_map_at_1000_diff1": -0.06444626856025794, + "nauc_map_at_1000_max": 0.08298497968678278, + "nauc_map_at_1000_std": 0.23119950058945407, + "nauc_map_at_100_diff1": -0.06286990300573342, + "nauc_map_at_100_max": 0.08772335756431743, + "nauc_map_at_100_std": 0.23603329666887554, + "nauc_map_at_10_diff1": -0.05644819155832809, + "nauc_map_at_10_max": 0.1132976583500958, + "nauc_map_at_10_std": 0.2530559372849127, + "nauc_map_at_1_diff1": -0.10322706539502892, + "nauc_map_at_1_max": 0.10237334439105301, + "nauc_map_at_1_std": 0.342293338536966, + "nauc_map_at_20_diff1": -0.06299067900205214, + "nauc_map_at_20_max": 0.09527085225997506, + "nauc_map_at_20_std": 0.2504173047261177, + "nauc_map_at_3_diff1": -0.06540370683783615, + "nauc_map_at_3_max": 0.1000495345813296, + "nauc_map_at_3_std": 0.2589781428659884, + "nauc_map_at_5_diff1": -0.08275375275409787, + "nauc_map_at_5_max": 0.09174922929792342, + "nauc_map_at_5_std": 0.2460673319179209, + "nauc_mrr_at_1000_diff1": -0.06458503038859191, + "nauc_mrr_at_1000_max": 0.08294709126227434, + "nauc_mrr_at_1000_std": 0.23125671740205278, + "nauc_mrr_at_100_diff1": -0.06301582741000634, + "nauc_mrr_at_100_max": 0.0876812211300217, + "nauc_mrr_at_100_std": 0.2360917295039161, + "nauc_mrr_at_10_diff1": -0.05644819155832809, + "nauc_mrr_at_10_max": 0.1132976583500958, + "nauc_mrr_at_10_std": 0.2530559372849127, + "nauc_mrr_at_1_diff1": -0.10322706539502892, + "nauc_mrr_at_1_max": 0.10237334439105301, + "nauc_mrr_at_1_std": 0.342293338536966, + "nauc_mrr_at_20_diff1": -0.06306215686353735, + "nauc_mrr_at_20_max": 0.0951631619462126, + "nauc_mrr_at_20_std": 0.2503771013353734, + "nauc_mrr_at_3_diff1": -0.06540370683783615, + "nauc_mrr_at_3_max": 0.1000495345813296, + "nauc_mrr_at_3_std": 0.2589781428659884, + "nauc_mrr_at_5_diff1": -0.08275375275409787, + "nauc_mrr_at_5_max": 0.09174922929792342, + "nauc_mrr_at_5_std": 0.2460673319179209, + "nauc_ndcg_at_1000_diff1": -0.07578878510314496, + "nauc_ndcg_at_1000_max": 0.03336326952660554, + "nauc_ndcg_at_1000_std": 0.16213519755429795, + "nauc_ndcg_at_100_diff1": -0.06422670605393042, + "nauc_ndcg_at_100_max": 0.05857260593772215, + "nauc_ndcg_at_100_std": 0.19694543982589774, + "nauc_ndcg_at_10_diff1": -0.040178781241173966, + "nauc_ndcg_at_10_max": 0.13093892608249527, + "nauc_ndcg_at_10_std": 0.24728428722317655, + "nauc_ndcg_at_1_diff1": -0.10322706539502892, + "nauc_ndcg_at_1_max": 0.10237334439105301, + "nauc_ndcg_at_1_std": 0.342293338536966, + "nauc_ndcg_at_20_diff1": -0.05631464056186774, + "nauc_ndcg_at_20_max": 0.08652809054816492, + "nauc_ndcg_at_20_std": 0.24311302804790838, + "nauc_ndcg_at_3_diff1": -0.058103909972056826, + "nauc_ndcg_at_3_max": 0.1070725174877641, + "nauc_ndcg_at_3_std": 0.24554120718520284, + "nauc_ndcg_at_5_diff1": -0.08699641825100571, + "nauc_ndcg_at_5_max": 0.09324598330024496, + "nauc_ndcg_at_5_std": 0.22893208680591165, + "nauc_precision_at_1000_diff1": -0.08394638068641827, + "nauc_precision_at_1000_max": 0.009168071730382298, + "nauc_precision_at_1000_std": 0.12556138513089765, + "nauc_precision_at_100_diff1": -0.06837727535904416, + "nauc_precision_at_100_max": 0.035714790060743636, + "nauc_precision_at_100_std": 0.17074144981450132, + "nauc_precision_at_10_diff1": -0.018509545110508587, + "nauc_precision_at_10_max": 0.15479618275672904, + "nauc_precision_at_10_std": 0.24389589482157248, + "nauc_precision_at_1_diff1": -0.10322706539502892, + "nauc_precision_at_1_max": 0.10237334439105301, + "nauc_precision_at_1_std": 0.342293338536966, + "nauc_precision_at_20_diff1": -0.050955665335627134, + "nauc_precision_at_20_max": 0.07284942418072676, + "nauc_precision_at_20_std": 0.2385428010753537, + "nauc_precision_at_3_diff1": -0.043951621225568095, + "nauc_precision_at_3_max": 0.12231945677075802, + "nauc_precision_at_3_std": 0.2200676972611505, + "nauc_precision_at_5_diff1": -0.09628175617471371, + "nauc_precision_at_5_max": 0.09565334048832856, + "nauc_precision_at_5_std": 0.2017426178808978, + "nauc_recall_at_1000_diff1": -0.08394638068641794, + "nauc_recall_at_1000_max": 0.00916807173038229, + "nauc_recall_at_1000_std": 0.12556138513089796, + "nauc_recall_at_100_diff1": -0.06837727535904424, + "nauc_recall_at_100_max": 0.03571479006074352, + "nauc_recall_at_100_std": 0.17074144981450137, + "nauc_recall_at_10_diff1": -0.01850954511050851, + "nauc_recall_at_10_max": 0.15479618275672885, + "nauc_recall_at_10_std": 0.24389589482157228, + "nauc_recall_at_1_diff1": -0.10322706539502892, + "nauc_recall_at_1_max": 0.10237334439105301, + "nauc_recall_at_1_std": 0.342293338536966, + "nauc_recall_at_20_diff1": -0.05095566533562716, + "nauc_recall_at_20_max": 0.0728494241807268, + "nauc_recall_at_20_std": 0.23854280107535367, + "nauc_recall_at_3_diff1": -0.043951621225568144, + "nauc_recall_at_3_max": 0.12231945677075806, + "nauc_recall_at_3_std": 0.2200676972611504, + "nauc_recall_at_5_diff1": -0.09628175617471371, + "nauc_recall_at_5_max": 0.0956533404883284, + "nauc_recall_at_5_std": 0.2017426178808975, + "ndcg_at_1": 0.00404, + "ndcg_at_10": 0.01246, + "ndcg_at_100": 0.02654, + "ndcg_at_1000": 0.05092, + "ndcg_at_20": 0.01571, + "ndcg_at_3": 0.00719, + "ndcg_at_5": 0.00901, + "precision_at_1": 0.00404, + "precision_at_10": 0.00246, + "precision_at_100": 0.00098, + "precision_at_1000": 0.0003, + "precision_at_20": 0.00187, + "precision_at_3": 0.00319, + "precision_at_5": 0.00279, + "recall_at_1": 0.00404, + "recall_at_10": 0.02463, + "recall_at_100": 0.09779, + "recall_at_1000": 0.30404, + "recall_at_20": 0.0375, + "recall_at_3": 0.00956, + "recall_at_5": 0.01397 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/RARbCode.json b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/RARbCode.json new file mode 100644 index 000000000..dbbe0a103 --- /dev/null +++ b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/RARbCode.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 944.9735860824585, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.46316, + "map_at_1": 0.3221, + "map_at_10": 0.41424, + "map_at_100": 0.42214, + "map_at_1000": 0.42263, + "map_at_20": 0.4186, + "map_at_3": 0.38926, + "map_at_5": 0.40318, + "mrr_at_1": 0.3221024258760108, + "mrr_at_10": 0.4142538933812519, + "mrr_at_100": 0.42215589408959214, + "mrr_at_1000": 0.4226456292677273, + "mrr_at_20": 0.41861551967611027, + "mrr_at_3": 0.3892632524707996, + "mrr_at_5": 0.40317834681042214, + "nauc_map_at_1000_diff1": 0.4719899832616907, + "nauc_map_at_1000_max": 0.2019180688365376, + "nauc_map_at_1000_std": 0.12641073490183902, + "nauc_map_at_100_diff1": 0.4718298044613509, + "nauc_map_at_100_max": 0.20186552231305266, + "nauc_map_at_100_std": 0.12647440985507932, + "nauc_map_at_10_diff1": 0.47150365988284215, + "nauc_map_at_10_max": 0.2009377597292183, + "nauc_map_at_10_std": 0.12455444761286173, + "nauc_map_at_1_diff1": 0.5122807710532171, + "nauc_map_at_1_max": 0.1847175015387979, + "nauc_map_at_1_std": 0.08901191377210078, + "nauc_map_at_20_diff1": 0.47183145041798186, + "nauc_map_at_20_max": 0.20142850486093364, + "nauc_map_at_20_std": 0.12537127090150935, + "nauc_map_at_3_diff1": 0.4746558601016, + "nauc_map_at_3_max": 0.19499099764520172, + "nauc_map_at_3_std": 0.11267630046785998, + "nauc_map_at_5_diff1": 0.47513659037990164, + "nauc_map_at_5_max": 0.20034987924413686, + "nauc_map_at_5_std": 0.1221784396526422, + "nauc_mrr_at_1000_diff1": 0.4719605210174272, + "nauc_mrr_at_1000_max": 0.20188558725811276, + "nauc_mrr_at_1000_std": 0.12638195995234272, + "nauc_mrr_at_100_diff1": 0.4718003758481142, + "nauc_mrr_at_100_max": 0.20183308178083095, + "nauc_mrr_at_100_std": 0.12644566879168945, + "nauc_mrr_at_10_diff1": 0.4714746349793944, + "nauc_mrr_at_10_max": 0.20090535206136823, + "nauc_mrr_at_10_std": 0.12452564828513014, + "nauc_mrr_at_1_diff1": 0.5122807710532171, + "nauc_mrr_at_1_max": 0.1847175015387979, + "nauc_mrr_at_1_std": 0.08901191377210078, + "nauc_mrr_at_20_diff1": 0.4718022246013959, + "nauc_mrr_at_20_max": 0.20139587443486084, + "nauc_mrr_at_20_std": 0.12534227841152168, + "nauc_mrr_at_3_diff1": 0.4746558601016, + "nauc_mrr_at_3_max": 0.19499099764520172, + "nauc_mrr_at_3_std": 0.11267630046785998, + "nauc_mrr_at_5_diff1": 0.47513659037990164, + "nauc_mrr_at_5_max": 0.20034987924413686, + "nauc_mrr_at_5_std": 0.1221784396526422, + "nauc_ndcg_at_1000_diff1": 0.46153674103073544, + "nauc_ndcg_at_1000_max": 0.21630622158114304, + "nauc_ndcg_at_1000_std": 0.15423838645327598, + "nauc_ndcg_at_100_diff1": 0.45727390577664406, + "nauc_ndcg_at_100_max": 0.21536488770239617, + "nauc_ndcg_at_100_std": 0.15842230875145752, + "nauc_ndcg_at_10_diff1": 0.45663321231745013, + "nauc_ndcg_at_10_max": 0.20912857788370917, + "nauc_ndcg_at_10_std": 0.14587929662140825, + "nauc_ndcg_at_1_diff1": 0.5122807710532171, + "nauc_ndcg_at_1_max": 0.1847175015387979, + "nauc_ndcg_at_1_std": 0.08901191377210078, + "nauc_ndcg_at_20_diff1": 0.45715329370464863, + "nauc_ndcg_at_20_max": 0.21083523526007578, + "nauc_ndcg_at_20_std": 0.14926727578221696, + "nauc_ndcg_at_3_diff1": 0.46448433060658645, + "nauc_ndcg_at_3_max": 0.1972665499502973, + "nauc_ndcg_at_3_std": 0.12191740165313567, + "nauc_ndcg_at_5_diff1": 0.46514931363857936, + "nauc_ndcg_at_5_max": 0.20731299037379755, + "nauc_ndcg_at_5_std": 0.1396276482292492, + "nauc_precision_at_1000_diff1": 0.3913851682454326, + "nauc_precision_at_1000_max": 0.49406862539602137, + "nauc_precision_at_1000_std": 0.5651594944479107, + "nauc_precision_at_100_diff1": 0.37229515521065387, + "nauc_precision_at_100_max": 0.3173090944641212, + "nauc_precision_at_100_std": 0.3893178433363403, + "nauc_precision_at_10_diff1": 0.4056660666350512, + "nauc_precision_at_10_max": 0.23832059410713233, + "nauc_precision_at_10_std": 0.22202999756873668, + "nauc_precision_at_1_diff1": 0.5122807710532171, + "nauc_precision_at_1_max": 0.1847175015387979, + "nauc_precision_at_1_std": 0.08901191377210078, + "nauc_precision_at_20_diff1": 0.4007688449225049, + "nauc_precision_at_20_max": 0.24940315924120682, + "nauc_precision_at_20_std": 0.2474716666663671, + "nauc_precision_at_3_diff1": 0.4357184630540142, + "nauc_precision_at_3_max": 0.20351926814729854, + "nauc_precision_at_3_std": 0.1490874253974413, + "nauc_precision_at_5_diff1": 0.43596412115824296, + "nauc_precision_at_5_max": 0.2294959170632865, + "nauc_precision_at_5_std": 0.19518085911220104, + "nauc_recall_at_1000_diff1": 0.3913851682454326, + "nauc_recall_at_1000_max": 0.49406862539602275, + "nauc_recall_at_1000_std": 0.5651594944479117, + "nauc_recall_at_100_diff1": 0.37229515521065293, + "nauc_recall_at_100_max": 0.3173090944641212, + "nauc_recall_at_100_std": 0.3893178433363389, + "nauc_recall_at_10_diff1": 0.4056660666350511, + "nauc_recall_at_10_max": 0.23832059410713297, + "nauc_recall_at_10_std": 0.2220299975687368, + "nauc_recall_at_1_diff1": 0.5122807710532171, + "nauc_recall_at_1_max": 0.1847175015387979, + "nauc_recall_at_1_std": 0.08901191377210078, + "nauc_recall_at_20_diff1": 0.40076884492250464, + "nauc_recall_at_20_max": 0.24940315924120657, + "nauc_recall_at_20_std": 0.24747166666636697, + "nauc_recall_at_3_diff1": 0.43571846305401446, + "nauc_recall_at_3_max": 0.20351926814729868, + "nauc_recall_at_3_std": 0.14908742539744135, + "nauc_recall_at_5_diff1": 0.43596412115824307, + "nauc_recall_at_5_max": 0.22949591706328606, + "nauc_recall_at_5_std": 0.19518085911220087, + "ndcg_at_1": 0.3221, + "ndcg_at_10": 0.46316, + "ndcg_at_100": 0.50468, + "ndcg_at_1000": 0.51876, + "ndcg_at_20": 0.47913, + "ndcg_at_3": 0.41145, + "ndcg_at_5": 0.43648, + "precision_at_1": 0.3221, + "precision_at_10": 0.06186, + "precision_at_100": 0.00819, + "precision_at_1000": 0.00093, + "precision_at_20": 0.0341, + "precision_at_3": 0.15858, + "precision_at_5": 0.10728, + "recall_at_1": 0.3221, + "recall_at_10": 0.6186, + "recall_at_100": 0.81941, + "recall_at_1000": 0.93261, + "recall_at_20": 0.68194, + "recall_at_3": 0.47574, + "recall_at_5": 0.53639 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/RARbMath.json b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/RARbMath.json new file mode 100644 index 000000000..e8344c681 --- /dev/null +++ b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/RARbMath.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 1454.9709470272064, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.45618, + "map_at_1": 0.38424, + "map_at_10": 0.42998, + "map_at_100": 0.43727, + "map_at_1000": 0.43802, + "map_at_20": 0.43378, + "map_at_3": 0.41544, + "map_at_5": 0.42327, + "mrr_at_1": 0.3842380123437253, + "mrr_at_10": 0.4299768021361626, + "mrr_at_100": 0.43727496444789216, + "mrr_at_1000": 0.4380177813579765, + "mrr_at_20": 0.4337814542296132, + "mrr_at_3": 0.41544020678377347, + "mrr_at_5": 0.4232658121010707, + "nauc_map_at_1000_diff1": 0.7360936248017108, + "nauc_map_at_1000_max": 0.3906255308421715, + "nauc_map_at_1000_std": -0.16788301019894555, + "nauc_map_at_100_diff1": 0.735896096870267, + "nauc_map_at_100_max": 0.3903926799164888, + "nauc_map_at_100_std": -0.16814261978810296, + "nauc_map_at_10_diff1": 0.7385068075198897, + "nauc_map_at_10_max": 0.39110587279349207, + "nauc_map_at_10_std": -0.16969044212253612, + "nauc_map_at_1_diff1": 0.7823980398219487, + "nauc_map_at_1_max": 0.4150565588223352, + "nauc_map_at_1_std": -0.17129962973650165, + "nauc_map_at_20_diff1": 0.7363958370423807, + "nauc_map_at_20_max": 0.38960529050628284, + "nauc_map_at_20_std": -0.16984339759924386, + "nauc_map_at_3_diff1": 0.7499893608204462, + "nauc_map_at_3_max": 0.39552523845925636, + "nauc_map_at_3_std": -0.17183443919261146, + "nauc_map_at_5_diff1": 0.7430248278377909, + "nauc_map_at_5_max": 0.39299414960959306, + "nauc_map_at_5_std": -0.1699135740007538, + "nauc_mrr_at_1000_diff1": 0.7360936243292217, + "nauc_mrr_at_1000_max": 0.39062553189447974, + "nauc_mrr_at_1000_std": -0.16788301014657192, + "nauc_mrr_at_100_diff1": 0.735896096870267, + "nauc_mrr_at_100_max": 0.3903926799164888, + "nauc_mrr_at_100_std": -0.16814261978810296, + "nauc_mrr_at_10_diff1": 0.7385068075198897, + "nauc_mrr_at_10_max": 0.39110587279349207, + "nauc_mrr_at_10_std": -0.16969044212253612, + "nauc_mrr_at_1_diff1": 0.7823980398219487, + "nauc_mrr_at_1_max": 0.4150565588223352, + "nauc_mrr_at_1_std": -0.17129962973650165, + "nauc_mrr_at_20_diff1": 0.7363958370423807, + "nauc_mrr_at_20_max": 0.38960529050628284, + "nauc_mrr_at_20_std": -0.16984339759924386, + "nauc_mrr_at_3_diff1": 0.7499893608204462, + "nauc_mrr_at_3_max": 0.39552523845925636, + "nauc_mrr_at_3_std": -0.17183443919261146, + "nauc_mrr_at_5_diff1": 0.7430248278377909, + "nauc_mrr_at_5_max": 0.39299414960959306, + "nauc_mrr_at_5_std": -0.1699135740007538, + "nauc_ndcg_at_1000_diff1": 0.710107676640611, + "nauc_ndcg_at_1000_max": 0.3871377826324383, + "nauc_ndcg_at_1000_std": -0.14880164010590555, + "nauc_ndcg_at_100_diff1": 0.7033931957491567, + "nauc_ndcg_at_100_max": 0.38070398047411513, + "nauc_ndcg_at_100_std": -0.15373965855865607, + "nauc_ndcg_at_10_diff1": 0.7156285182341281, + "nauc_ndcg_at_10_max": 0.3801264786038057, + "nauc_ndcg_at_10_std": -0.1676929307893043, + "nauc_ndcg_at_1_diff1": 0.7823980398219487, + "nauc_ndcg_at_1_max": 0.4150565588223352, + "nauc_ndcg_at_1_std": -0.17129962973650165, + "nauc_ndcg_at_20_diff1": 0.7075841926845738, + "nauc_ndcg_at_20_max": 0.3743169205762502, + "nauc_ndcg_at_20_std": -0.1682819030666637, + "nauc_ndcg_at_3_diff1": 0.7395816473755886, + "nauc_ndcg_at_3_max": 0.3891888740598718, + "nauc_ndcg_at_3_std": -0.17215502198388025, + "nauc_ndcg_at_5_diff1": 0.7268775137916277, + "nauc_ndcg_at_5_max": 0.3844925032006811, + "nauc_ndcg_at_5_std": -0.1685401556095735, + "nauc_precision_at_1000_diff1": 0.4538454458515229, + "nauc_precision_at_1000_max": 0.4737938960248283, + "nauc_precision_at_1000_std": 0.24670214909926055, + "nauc_precision_at_100_diff1": 0.5303426757673299, + "nauc_precision_at_100_max": 0.34725132771170636, + "nauc_precision_at_100_std": -0.04461398585662318, + "nauc_precision_at_10_diff1": 0.6390568109302082, + "nauc_precision_at_10_max": 0.34435267086070404, + "nauc_precision_at_10_std": -0.16031326181077185, + "nauc_precision_at_1_diff1": 0.7823980398219487, + "nauc_precision_at_1_max": 0.4150565588223352, + "nauc_precision_at_1_std": -0.17129962973650165, + "nauc_precision_at_20_diff1": 0.5998709489564894, + "nauc_precision_at_20_max": 0.3168229873759083, + "nauc_precision_at_20_std": -0.16257208012646243, + "nauc_precision_at_3_diff1": 0.7093096803282699, + "nauc_precision_at_3_max": 0.37073876348579643, + "nauc_precision_at_3_std": -0.17313416749838212, + "nauc_precision_at_5_diff1": 0.6775914504724735, + "nauc_precision_at_5_max": 0.3587712995154008, + "nauc_precision_at_5_std": -0.16393053567139493, + "nauc_recall_at_1000_diff1": 0.45384544585152276, + "nauc_recall_at_1000_max": 0.4737938960248304, + "nauc_recall_at_1000_std": 0.24670214909926305, + "nauc_recall_at_100_diff1": 0.5303426757673292, + "nauc_recall_at_100_max": 0.347251327711706, + "nauc_recall_at_100_std": -0.04461398585662317, + "nauc_recall_at_10_diff1": 0.6390568109302084, + "nauc_recall_at_10_max": 0.34435267086070354, + "nauc_recall_at_10_std": -0.16031326181077177, + "nauc_recall_at_1_diff1": 0.7823980398219487, + "nauc_recall_at_1_max": 0.4150565588223352, + "nauc_recall_at_1_std": -0.17129962973650165, + "nauc_recall_at_20_diff1": 0.5998709489564893, + "nauc_recall_at_20_max": 0.3168229873759086, + "nauc_recall_at_20_std": -0.16257208012646165, + "nauc_recall_at_3_diff1": 0.7093096803282699, + "nauc_recall_at_3_max": 0.37073876348579654, + "nauc_recall_at_3_std": -0.17313416749838195, + "nauc_recall_at_5_diff1": 0.6775914504724734, + "nauc_recall_at_5_max": 0.3587712995154006, + "nauc_recall_at_5_std": -0.16393053567139482, + "ndcg_at_1": 0.38424, + "ndcg_at_10": 0.45618, + "ndcg_at_100": 0.49633, + "ndcg_at_1000": 0.51789, + "ndcg_at_20": 0.47, + "ndcg_at_3": 0.42578, + "ndcg_at_5": 0.43991, + "precision_at_1": 0.38424, + "precision_at_10": 0.05404, + "precision_at_100": 0.00739, + "precision_at_1000": 0.00091, + "precision_at_20": 0.02975, + "precision_at_3": 0.15192, + "precision_at_5": 0.09802, + "recall_at_1": 0.38424, + "recall_at_10": 0.54043, + "recall_at_100": 0.73904, + "recall_at_1000": 0.91264, + "recall_at_20": 0.59503, + "recall_at_3": 0.45577, + "recall_at_5": 0.49011 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/SIQA.json b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/SIQA.json new file mode 100644 index 000000000..8e9ff7f72 --- /dev/null +++ b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/SIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 13.3722825050354, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.00244, + "map_at_1": 0.0, + "map_at_10": 0.00109, + "map_at_100": 0.0021, + "map_at_1000": 0.0026, + "map_at_20": 0.00148, + "map_at_3": 0.00017, + "map_at_5": 0.00048, + "mrr_at_1": 0.0, + "mrr_at_10": 0.0010917775503241215, + "mrr_at_100": 0.0021008336737821515, + "mrr_at_1000": 0.0025986310995387367, + "mrr_at_20": 0.0014808603626373634, + "mrr_at_3": 0.00017059024223814396, + "mrr_at_5": 0.00047765267826680314, + "nauc_map_at_1000_diff1": -0.007456474423072567, + "nauc_map_at_1000_max": 0.0437398318378665, + "nauc_map_at_1000_std": -0.007620616126891872, + "nauc_map_at_100_diff1": -0.01723950299199308, + "nauc_map_at_100_max": 0.04631329298836163, + "nauc_map_at_100_std": -0.00607895171841584, + "nauc_map_at_10_diff1": -0.042540367091281533, + "nauc_map_at_10_max": 0.03689201201371712, + "nauc_map_at_10_std": -0.0774230906883135, + "nauc_map_at_1_diff1": NaN, + "nauc_map_at_1_max": NaN, + "nauc_map_at_1_std": NaN, + "nauc_map_at_20_diff1": -0.023597010528879712, + "nauc_map_at_20_max": 0.01674361727112451, + "nauc_map_at_20_std": -0.06198121974581448, + "nauc_map_at_3_diff1": -0.5744210621882534, + "nauc_map_at_3_max": -0.5744210621882534, + "nauc_map_at_3_std": -0.5744210621882534, + "nauc_map_at_5_diff1": -0.08295685392251745, + "nauc_map_at_5_max": -0.00916646262772423, + "nauc_map_at_5_std": -0.2754092744994878, + "nauc_mrr_at_1000_diff1": -0.007442451151277766, + "nauc_mrr_at_1000_max": 0.043753769184681116, + "nauc_mrr_at_1000_std": -0.007622863324340534, + "nauc_mrr_at_100_diff1": -0.017223639100560337, + "nauc_mrr_at_100_max": 0.04632882894734482, + "nauc_mrr_at_100_std": -0.006081924990858766, + "nauc_mrr_at_10_diff1": -0.042540367091281533, + "nauc_mrr_at_10_max": 0.03689201201371712, + "nauc_mrr_at_10_std": -0.0774230906883135, + "nauc_mrr_at_1_diff1": NaN, + "nauc_mrr_at_1_max": NaN, + "nauc_mrr_at_1_std": NaN, + "nauc_mrr_at_20_diff1": -0.023597010528879712, + "nauc_mrr_at_20_max": 0.01674361727112451, + "nauc_mrr_at_20_std": -0.06198121974581448, + "nauc_mrr_at_3_diff1": -0.5744210621882534, + "nauc_mrr_at_3_max": -0.5744210621882534, + "nauc_mrr_at_3_std": -0.5744210621882534, + "nauc_mrr_at_5_diff1": -0.08295685392251745, + "nauc_mrr_at_5_max": -0.00916646262772423, + "nauc_mrr_at_5_std": -0.2754092744994878, + "nauc_ndcg_at_1000_diff1": 0.016142154924702026, + "nauc_ndcg_at_1000_max": 0.04324785721857796, + "nauc_ndcg_at_1000_std": 0.0058123254574327585, + "nauc_ndcg_at_100_diff1": 0.005294615132611137, + "nauc_ndcg_at_100_max": 0.05184893900230378, + "nauc_ndcg_at_100_std": 0.02950374207178283, + "nauc_ndcg_at_10_diff1": -0.04230065058035591, + "nauc_ndcg_at_10_max": 0.04892834860435886, + "nauc_ndcg_at_10_std": -0.03252828498801491, + "nauc_ndcg_at_1_diff1": NaN, + "nauc_ndcg_at_1_max": NaN, + "nauc_ndcg_at_1_std": NaN, + "nauc_ndcg_at_20_diff1": -0.021839734628460446, + "nauc_ndcg_at_20_max": 0.010085073698889795, + "nauc_ndcg_at_20_std": -0.023001585025728095, + "nauc_ndcg_at_3_diff1": -0.5744210621882535, + "nauc_ndcg_at_3_max": -0.5744210621882535, + "nauc_ndcg_at_3_std": -0.5744210621882535, + "nauc_ndcg_at_5_diff1": -0.04011479390093681, + "nauc_ndcg_at_5_max": 0.040108074713055296, + "nauc_ndcg_at_5_std": -0.24934373251317152, + "nauc_precision_at_1000_diff1": 0.019589145988868257, + "nauc_precision_at_1000_max": 0.04311741257626936, + "nauc_precision_at_1000_std": 0.0038955724760601695, + "nauc_precision_at_100_diff1": 0.01620398034543866, + "nauc_precision_at_100_max": 0.04990003029844897, + "nauc_precision_at_100_std": 0.0349042144692656, + "nauc_precision_at_10_diff1": -0.04599310587813965, + "nauc_precision_at_10_max": 0.054545403047118586, + "nauc_precision_at_10_std": -0.0015561115190892922, + "nauc_precision_at_1_diff1": NaN, + "nauc_precision_at_1_max": NaN, + "nauc_precision_at_1_std": NaN, + "nauc_precision_at_20_diff1": -0.02368565399955108, + "nauc_precision_at_20_max": 0.0015427507829878693, + "nauc_precision_at_20_std": -0.0011631760177167115, + "nauc_precision_at_3_diff1": -0.5744210621882534, + "nauc_precision_at_3_max": -0.5744210621882534, + "nauc_precision_at_3_std": -0.5744210621882534, + "nauc_precision_at_5_diff1": -0.001046152544894711, + "nauc_precision_at_5_max": 0.08504263729903054, + "nauc_precision_at_5_std": -0.22557397655136024, + "nauc_recall_at_1000_diff1": 0.019589145988868455, + "nauc_recall_at_1000_max": 0.043117412576269595, + "nauc_recall_at_1000_std": 0.0038955724760603504, + "nauc_recall_at_100_diff1": 0.016203980345438646, + "nauc_recall_at_100_max": 0.04990003029844908, + "nauc_recall_at_100_std": 0.03490421446926561, + "nauc_recall_at_10_diff1": -0.04599310587813947, + "nauc_recall_at_10_max": 0.05454540304711874, + "nauc_recall_at_10_std": -0.0015561115190892104, + "nauc_recall_at_1_diff1": NaN, + "nauc_recall_at_1_max": NaN, + "nauc_recall_at_1_std": NaN, + "nauc_recall_at_20_diff1": -0.023685653999550988, + "nauc_recall_at_20_max": 0.0015427507829879612, + "nauc_recall_at_20_std": -0.0011631760177165512, + "nauc_recall_at_3_diff1": -0.5744210621882535, + "nauc_recall_at_3_max": -0.5744210621882535, + "nauc_recall_at_3_std": -0.5744210621882535, + "nauc_recall_at_5_diff1": -0.0010461525448946575, + "nauc_recall_at_5_max": 0.08504263729903067, + "nauc_recall_at_5_std": -0.22557397655136016, + "ndcg_at_1": 0.0, + "ndcg_at_10": 0.00244, + "ndcg_at_100": 0.00908, + "ndcg_at_1000": 0.02856, + "ndcg_at_20": 0.00386, + "ndcg_at_3": 0.00026, + "ndcg_at_5": 0.00085, + "precision_at_1": 0.0, + "precision_at_10": 0.00072, + "precision_at_100": 0.00042, + "precision_at_1000": 0.00021, + "precision_at_20": 0.00064, + "precision_at_3": 0.00017, + "precision_at_5": 0.00041, + "recall_at_1": 0.0, + "recall_at_10": 0.00716, + "recall_at_100": 0.04248, + "recall_at_1000": 0.20983, + "recall_at_20": 0.01279, + "recall_at_3": 0.00051, + "recall_at_5": 0.00205 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/SpartQA.json b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/SpartQA.json new file mode 100644 index 000000000..591e14d73 --- /dev/null +++ b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/SpartQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 12.25787615776062, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02671, + "map_at_1": 0.00028, + "map_at_10": 0.01333, + "map_at_100": 0.02005, + "map_at_1000": 0.02123, + "map_at_20": 0.01617, + "map_at_3": 0.00665, + "map_at_5": 0.00938, + "mrr_at_1": 0.0002782415136338342, + "mrr_at_10": 0.021795916474547566, + "mrr_at_100": 0.031155874807351637, + "mrr_at_1000": 0.03242780610875695, + "mrr_at_20": 0.02605962463293702, + "mrr_at_3": 0.011036913374142091, + "mrr_at_5": 0.015474865516601767, + "nauc_map_at_1000_diff1": 0.12407572499270252, + "nauc_map_at_1000_max": 0.05893953506538936, + "nauc_map_at_1000_std": 0.2614227789193683, + "nauc_map_at_100_diff1": 0.11643272448011871, + "nauc_map_at_100_max": 0.05747831461734302, + "nauc_map_at_100_std": 0.2569850995498979, + "nauc_map_at_10_diff1": 0.11363441082399636, + "nauc_map_at_10_max": 0.126436462528036, + "nauc_map_at_10_std": 0.3050619476387682, + "nauc_map_at_1_diff1": -0.5745599329284906, + "nauc_map_at_1_max": 0.0984051515815584, + "nauc_map_at_1_std": 1.0, + "nauc_map_at_20_diff1": 0.09705493344225852, + "nauc_map_at_20_max": 0.07021787814837423, + "nauc_map_at_20_std": 0.269142887600497, + "nauc_map_at_3_diff1": 0.1961496322987469, + "nauc_map_at_3_max": 0.22204254752232483, + "nauc_map_at_3_std": 0.41927668425130077, + "nauc_map_at_5_diff1": 0.14754648578422194, + "nauc_map_at_5_max": 0.16110837153570115, + "nauc_map_at_5_std": 0.3466993538430015, + "nauc_mrr_at_1000_diff1": 0.16953072669981703, + "nauc_mrr_at_1000_max": 0.12675779471603227, + "nauc_mrr_at_1000_std": 0.29237528958819725, + "nauc_mrr_at_100_diff1": 0.16529002276962565, + "nauc_mrr_at_100_max": 0.12443308380530989, + "nauc_mrr_at_100_std": 0.2896494517574938, + "nauc_mrr_at_10_diff1": 0.1567785320258122, + "nauc_mrr_at_10_max": 0.1827830107321144, + "nauc_mrr_at_10_std": 0.33424048927531863, + "nauc_mrr_at_1_diff1": -0.5745599329284906, + "nauc_mrr_at_1_max": 0.0984051515815584, + "nauc_mrr_at_1_std": 1.0, + "nauc_mrr_at_20_diff1": 0.15085380404095566, + "nauc_mrr_at_20_max": 0.1361028875918774, + "nauc_mrr_at_20_std": 0.3008672042784619, + "nauc_mrr_at_3_diff1": 0.2509046970616496, + "nauc_mrr_at_3_max": 0.3064094221566434, + "nauc_mrr_at_3_std": 0.4536488403432462, + "nauc_mrr_at_5_diff1": 0.18872234930917697, + "nauc_mrr_at_5_max": 0.22867501188816863, + "nauc_mrr_at_5_std": 0.3804509068102703, + "nauc_ndcg_at_1000_diff1": 0.22412654879855426, + "nauc_ndcg_at_1000_max": 0.03382890310693224, + "nauc_ndcg_at_1000_std": 0.25916710778255325, + "nauc_ndcg_at_100_diff1": 0.1486931710928629, + "nauc_ndcg_at_100_max": 0.009553336736917979, + "nauc_ndcg_at_100_std": 0.20176194884475948, + "nauc_ndcg_at_10_diff1": 0.10625779395728285, + "nauc_ndcg_at_10_max": 0.11767423425355446, + "nauc_ndcg_at_10_std": 0.2897103839488597, + "nauc_ndcg_at_1_diff1": -0.5745599329284906, + "nauc_ndcg_at_1_max": 0.0984051515815584, + "nauc_ndcg_at_1_std": 1.0, + "nauc_ndcg_at_20_diff1": 0.08861628874558365, + "nauc_ndcg_at_20_max": 0.03103330661602805, + "nauc_ndcg_at_20_std": 0.23112852857402053, + "nauc_ndcg_at_3_diff1": 0.21671457892570703, + "nauc_ndcg_at_3_max": 0.2482620284708805, + "nauc_ndcg_at_3_std": 0.4246182944520406, + "nauc_ndcg_at_5_diff1": 0.15072970571858874, + "nauc_ndcg_at_5_max": 0.168198606063229, + "nauc_ndcg_at_5_std": 0.3383848869439051, + "nauc_precision_at_1000_diff1": 0.264991461953303, + "nauc_precision_at_1000_max": 0.03406245991994215, + "nauc_precision_at_1000_std": 0.243626811309637, + "nauc_precision_at_100_diff1": 0.19884000611637417, + "nauc_precision_at_100_max": -0.005768883204601079, + "nauc_precision_at_100_std": 0.1786364882551347, + "nauc_precision_at_10_diff1": 0.10992438536490934, + "nauc_precision_at_10_max": 0.12358818793597108, + "nauc_precision_at_10_std": 0.2918799884073785, + "nauc_precision_at_1_diff1": -0.5745599329284906, + "nauc_precision_at_1_max": 0.0984051515815584, + "nauc_precision_at_1_std": 1.0, + "nauc_precision_at_20_diff1": 0.10402065443868264, + "nauc_precision_at_20_max": 0.017632464881593195, + "nauc_precision_at_20_std": 0.21992899649065129, + "nauc_precision_at_3_diff1": 0.2546190787904961, + "nauc_precision_at_3_max": 0.310961992275947, + "nauc_precision_at_3_std": 0.4503335068651704, + "nauc_precision_at_5_diff1": 0.16052509549189348, + "nauc_precision_at_5_max": 0.19568753845531972, + "nauc_precision_at_5_std": 0.34594626755053465, + "nauc_recall_at_1000_diff1": 0.26339696288158265, + "nauc_recall_at_1000_max": 0.01306898016688568, + "nauc_recall_at_1000_std": 0.2156003445303253, + "nauc_recall_at_100_diff1": 0.14251215384093907, + "nauc_recall_at_100_max": -0.03583152653467331, + "nauc_recall_at_100_std": 0.13498246469262173, + "nauc_recall_at_10_diff1": 0.07662424055928263, + "nauc_recall_at_10_max": 0.08084886856176678, + "nauc_recall_at_10_std": 0.25982082812686397, + "nauc_recall_at_1_diff1": -0.5745599329284906, + "nauc_recall_at_1_max": 0.0984051515815584, + "nauc_recall_at_1_std": 1.0, + "nauc_recall_at_20_diff1": 0.05572048462668682, + "nauc_recall_at_20_max": -0.03029513343994789, + "nauc_recall_at_20_std": 0.18181616647796767, + "nauc_recall_at_3_diff1": 0.20657466126146165, + "nauc_recall_at_3_max": 0.22272587985546644, + "nauc_recall_at_3_std": 0.4054215544209147, + "nauc_recall_at_5_diff1": 0.12954530712211454, + "nauc_recall_at_5_max": 0.13411970673159698, + "nauc_recall_at_5_std": 0.3052302189406524, + "ndcg_at_1": 0.00028, + "ndcg_at_10": 0.02671, + "ndcg_at_100": 0.06956, + "ndcg_at_1000": 0.10846, + "ndcg_at_20": 0.03816, + "ndcg_at_3": 0.01043, + "ndcg_at_5": 0.016, + "precision_at_1": 0.00028, + "precision_at_10": 0.00954, + "precision_at_100": 0.00412, + "precision_at_1000": 0.0009, + "precision_at_20": 0.0081, + "precision_at_3": 0.00937, + "precision_at_5": 0.00952, + "recall_at_1": 0.00028, + "recall_at_10": 0.05797, + "recall_at_100": 0.25162, + "recall_at_1000": 0.53367, + "recall_at_20": 0.09813, + "recall_at_3": 0.0166, + "recall_at_5": 0.02866 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL1.json b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL1.json new file mode 100644 index 000000000..85c0abdf9 --- /dev/null +++ b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL1.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 8.015006065368652, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.00798, + "map_at_1": 0.00225, + "map_at_10": 0.00574, + "map_at_100": 0.00796, + "map_at_1000": 0.00887, + "map_at_20": 0.00656, + "map_at_3": 0.00438, + "map_at_5": 0.00506, + "mrr_at_1": 0.00225, + "mrr_at_10": 0.00574047619047619, + "mrr_at_100": 0.007957562868386106, + "mrr_at_1000": 0.008872577789958494, + "mrr_at_20": 0.006558613271403522, + "mrr_at_3": 0.004375, + "mrr_at_5": 0.005062499999999999, + "nauc_map_at_1000_diff1": 0.01474184034203837, + "nauc_map_at_1000_max": 0.16499994893339276, + "nauc_map_at_1000_std": 0.1025868622306911, + "nauc_map_at_100_diff1": 0.015998667586142386, + "nauc_map_at_100_max": 0.16466875833179767, + "nauc_map_at_100_std": 0.10700631877684227, + "nauc_map_at_10_diff1": -0.0190295028921755, + "nauc_map_at_10_max": 0.12425026127342954, + "nauc_map_at_10_std": 0.156254818947427, + "nauc_map_at_1_diff1": -0.31988790507706527, + "nauc_map_at_1_max": -0.17663894106072794, + "nauc_map_at_1_std": 0.35998569000983827, + "nauc_map_at_20_diff1": 0.013660223428190052, + "nauc_map_at_20_max": 0.1665832766473899, + "nauc_map_at_20_std": 0.14065426910454656, + "nauc_map_at_3_diff1": -0.07393154202920792, + "nauc_map_at_3_max": 0.04143508758480571, + "nauc_map_at_3_std": 0.20708600048551729, + "nauc_map_at_5_diff1": -0.05158287703677205, + "nauc_map_at_5_max": 0.09118643730932428, + "nauc_map_at_5_std": 0.18484156875475466, + "nauc_mrr_at_1000_diff1": 0.01474184034203837, + "nauc_mrr_at_1000_max": 0.16499994893339276, + "nauc_mrr_at_1000_std": 0.1025868622306911, + "nauc_mrr_at_100_diff1": 0.015998667586142386, + "nauc_mrr_at_100_max": 0.16466875833179767, + "nauc_mrr_at_100_std": 0.10700631877684227, + "nauc_mrr_at_10_diff1": -0.0190295028921755, + "nauc_mrr_at_10_max": 0.12425026127342954, + "nauc_mrr_at_10_std": 0.156254818947427, + "nauc_mrr_at_1_diff1": -0.31988790507706527, + "nauc_mrr_at_1_max": -0.17663894106072794, + "nauc_mrr_at_1_std": 0.35998569000983827, + "nauc_mrr_at_20_diff1": 0.013660223428190052, + "nauc_mrr_at_20_max": 0.1665832766473899, + "nauc_mrr_at_20_std": 0.14065426910454656, + "nauc_mrr_at_3_diff1": -0.07393154202920792, + "nauc_mrr_at_3_max": 0.04143508758480571, + "nauc_mrr_at_3_std": 0.20708600048551729, + "nauc_mrr_at_5_diff1": -0.05158287703677205, + "nauc_mrr_at_5_max": 0.09118643730932428, + "nauc_mrr_at_5_std": 0.18484156875475466, + "nauc_ndcg_at_1000_diff1": 0.03553637881439664, + "nauc_ndcg_at_1000_max": 0.19130468256707314, + "nauc_ndcg_at_1000_std": 0.031084869953396235, + "nauc_ndcg_at_100_diff1": 0.055717528939652, + "nauc_ndcg_at_100_max": 0.20506269015331752, + "nauc_ndcg_at_100_std": 0.019315253358909202, + "nauc_ndcg_at_10_diff1": 0.03748058323368757, + "nauc_ndcg_at_10_max": 0.18817477730736676, + "nauc_ndcg_at_10_std": 0.11158643671728231, + "nauc_ndcg_at_1_diff1": -0.31988790507706527, + "nauc_ndcg_at_1_max": -0.17663894106072794, + "nauc_ndcg_at_1_std": 0.35998569000983827, + "nauc_ndcg_at_20_diff1": 0.10133326398309024, + "nauc_ndcg_at_20_max": 0.2643773023314351, + "nauc_ndcg_at_20_std": 0.08689027801200448, + "nauc_ndcg_at_3_diff1": -0.033245286724570736, + "nauc_ndcg_at_3_max": 0.07846291741876096, + "nauc_ndcg_at_3_std": 0.1879477248555728, + "nauc_ndcg_at_5_diff1": -0.008224892184789962, + "nauc_ndcg_at_5_max": 0.14176908931804344, + "nauc_ndcg_at_5_std": 0.15847085161568106, + "nauc_precision_at_1000_diff1": 0.030399561882764506, + "nauc_precision_at_1000_max": 0.1866144438862961, + "nauc_precision_at_1000_std": 0.021444634617475637, + "nauc_precision_at_100_diff1": 0.05979531603357734, + "nauc_precision_at_100_max": 0.20749840645198844, + "nauc_precision_at_100_std": -0.01885071471870509, + "nauc_precision_at_10_diff1": 0.10673551883244568, + "nauc_precision_at_10_max": 0.26768332109066756, + "nauc_precision_at_10_std": 0.05327538960267783, + "nauc_precision_at_1_diff1": -0.31988790507706527, + "nauc_precision_at_1_max": -0.17663894106072794, + "nauc_precision_at_1_std": 0.35998569000983827, + "nauc_precision_at_20_diff1": 0.1825386178082717, + "nauc_precision_at_20_max": 0.35286183832266466, + "nauc_precision_at_20_std": 0.038411782743684925, + "nauc_precision_at_3_diff1": 0.03888678145499293, + "nauc_precision_at_3_max": 0.1442872607163014, + "nauc_precision_at_3_std": 0.15516778771869777, + "nauc_precision_at_5_diff1": 0.05658772176667319, + "nauc_precision_at_5_max": 0.21881196542043246, + "nauc_precision_at_5_std": 0.11867911810322843, + "nauc_recall_at_1000_diff1": 0.030399561882764763, + "nauc_recall_at_1000_max": 0.1866144438862966, + "nauc_recall_at_1000_std": 0.02144463461747596, + "nauc_recall_at_100_diff1": 0.05979531603357747, + "nauc_recall_at_100_max": 0.20749840645198842, + "nauc_recall_at_100_std": -0.01885071471870515, + "nauc_recall_at_10_diff1": 0.10673551883244557, + "nauc_recall_at_10_max": 0.2676833210906677, + "nauc_recall_at_10_std": 0.05327538960267798, + "nauc_recall_at_1_diff1": -0.31988790507706527, + "nauc_recall_at_1_max": -0.17663894106072794, + "nauc_recall_at_1_std": 0.35998569000983827, + "nauc_recall_at_20_diff1": 0.18253861780827155, + "nauc_recall_at_20_max": 0.35286183832266454, + "nauc_recall_at_20_std": 0.0384117827436851, + "nauc_recall_at_3_diff1": 0.03888678145499296, + "nauc_recall_at_3_max": 0.14428726071630124, + "nauc_recall_at_3_std": 0.15516778771869766, + "nauc_recall_at_5_diff1": 0.05658772176667304, + "nauc_recall_at_5_max": 0.21881196542043227, + "nauc_recall_at_5_std": 0.11867911810322823, + "ndcg_at_1": 0.00225, + "ndcg_at_10": 0.00798, + "ndcg_at_100": 0.02284, + "ndcg_at_1000": 0.05721, + "ndcg_at_20": 0.01111, + "ndcg_at_3": 0.00511, + "ndcg_at_5": 0.00635, + "precision_at_1": 0.00225, + "precision_at_10": 0.00152, + "precision_at_100": 0.00094, + "precision_at_1000": 0.00039, + "precision_at_20": 0.0014, + "precision_at_3": 0.00242, + "precision_at_5": 0.00205, + "recall_at_1": 0.00225, + "recall_at_10": 0.01525, + "recall_at_100": 0.0945, + "recall_at_1000": 0.388, + "recall_at_20": 0.028, + "recall_at_3": 0.00725, + "recall_at_5": 0.01025 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL2Fact.json b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL2Fact.json new file mode 100644 index 000000000..e2eeef04f --- /dev/null +++ b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL2Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 25.660129070281982, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.16555, + "map_at_1": 0.068, + "map_at_10": 0.12848, + "map_at_100": 0.13911, + "map_at_1000": 0.14015, + "map_at_20": 0.13405, + "map_at_3": 0.10614, + "map_at_5": 0.11868, + "mrr_at_1": 0.06800074115249212, + "mrr_at_10": 0.1284810638479343, + "mrr_at_100": 0.1391059578524182, + "mrr_at_1000": 0.14014698664040082, + "mrr_at_20": 0.1340487352056171, + "mrr_at_3": 0.10613921314310414, + "mrr_at_5": 0.11868321907232421, + "nauc_map_at_1000_diff1": -0.03475384938078055, + "nauc_map_at_1000_max": -0.0780076022030476, + "nauc_map_at_1000_std": 0.04163011047184887, + "nauc_map_at_100_diff1": -0.03452640874602977, + "nauc_map_at_100_max": -0.07769590197354528, + "nauc_map_at_100_std": 0.04197067079101758, + "nauc_map_at_10_diff1": -0.027401306747497124, + "nauc_map_at_10_max": -0.06826693259728153, + "nauc_map_at_10_std": 0.03127290682768459, + "nauc_map_at_1_diff1": 0.015120516198455985, + "nauc_map_at_1_max": -0.0727075720153639, + "nauc_map_at_1_std": 0.018913085028359998, + "nauc_map_at_20_diff1": -0.03172703342277339, + "nauc_map_at_20_max": -0.07339877473504865, + "nauc_map_at_20_std": 0.036214959172208135, + "nauc_map_at_3_diff1": -0.018882584825474072, + "nauc_map_at_3_max": -0.06286930939237032, + "nauc_map_at_3_std": 0.0181436522882491, + "nauc_map_at_5_diff1": -0.02372403856200923, + "nauc_map_at_5_max": -0.061913970163341325, + "nauc_map_at_5_std": 0.02896127426978015, + "nauc_mrr_at_1000_diff1": -0.03475384938078055, + "nauc_mrr_at_1000_max": -0.0780076022030476, + "nauc_mrr_at_1000_std": 0.04163011047184887, + "nauc_mrr_at_100_diff1": -0.03452640874602977, + "nauc_mrr_at_100_max": -0.07769590197354528, + "nauc_mrr_at_100_std": 0.04197067079101758, + "nauc_mrr_at_10_diff1": -0.027401306747497124, + "nauc_mrr_at_10_max": -0.06826693259728153, + "nauc_mrr_at_10_std": 0.03127290682768459, + "nauc_mrr_at_1_diff1": 0.015120516198455985, + "nauc_mrr_at_1_max": -0.0727075720153639, + "nauc_mrr_at_1_std": 0.018913085028359998, + "nauc_mrr_at_20_diff1": -0.03172703342277339, + "nauc_mrr_at_20_max": -0.07339877473504865, + "nauc_mrr_at_20_std": 0.036214959172208135, + "nauc_mrr_at_3_diff1": -0.018882584825474072, + "nauc_mrr_at_3_max": -0.06286930939237032, + "nauc_mrr_at_3_std": 0.0181436522882491, + "nauc_mrr_at_5_diff1": -0.02372403856200923, + "nauc_mrr_at_5_max": -0.061913970163341325, + "nauc_mrr_at_5_std": 0.02896127426978015, + "nauc_ndcg_at_1000_diff1": -0.07381868257681913, + "nauc_ndcg_at_1000_max": -0.12222024366818089, + "nauc_ndcg_at_1000_std": 0.07683858864933756, + "nauc_ndcg_at_100_diff1": -0.06928396384170739, + "nauc_ndcg_at_100_max": -0.11572203641804485, + "nauc_ndcg_at_100_std": 0.08974220016120574, + "nauc_ndcg_at_10_diff1": -0.04041348026062106, + "nauc_ndcg_at_10_max": -0.07271883151709602, + "nauc_ndcg_at_10_std": 0.040048415951363284, + "nauc_ndcg_at_1_diff1": 0.015120516198455985, + "nauc_ndcg_at_1_max": -0.0727075720153639, + "nauc_ndcg_at_1_std": 0.018913085028359998, + "nauc_ndcg_at_20_diff1": -0.05332877992019192, + "nauc_ndcg_at_20_max": -0.08911541093638169, + "nauc_ndcg_at_20_std": 0.05433031934115885, + "nauc_ndcg_at_3_diff1": -0.02639324258329114, + "nauc_ndcg_at_3_max": -0.060832354630425675, + "nauc_ndcg_at_3_std": 0.01814330690858396, + "nauc_ndcg_at_5_diff1": -0.03326303687022615, + "nauc_ndcg_at_5_max": -0.05965828378484914, + "nauc_ndcg_at_5_std": 0.034949329150079055, + "nauc_precision_at_1000_diff1": -0.2819252723351435, + "nauc_precision_at_1000_max": -0.3980068827463751, + "nauc_precision_at_1000_std": 0.2184050663259188, + "nauc_precision_at_100_diff1": -0.15761258751505436, + "nauc_precision_at_100_max": -0.22883071775776648, + "nauc_precision_at_100_std": 0.22842005552824088, + "nauc_precision_at_10_diff1": -0.0641647483961982, + "nauc_precision_at_10_max": -0.0830033622872858, + "nauc_precision_at_10_std": 0.05734435853662671, + "nauc_precision_at_1_diff1": 0.015120516198455985, + "nauc_precision_at_1_max": -0.0727075720153639, + "nauc_precision_at_1_std": 0.018913085028359998, + "nauc_precision_at_20_diff1": -0.0960741355215555, + "nauc_precision_at_20_max": -0.1256837095215487, + "nauc_precision_at_20_std": 0.09232019151068259, + "nauc_precision_at_3_diff1": -0.04210249363882294, + "nauc_precision_at_3_max": -0.05660218222252794, + "nauc_precision_at_3_std": 0.018180348333458423, + "nauc_precision_at_5_diff1": -0.05126817855971192, + "nauc_precision_at_5_max": -0.05552367693650251, + "nauc_precision_at_5_std": 0.047226160965930845, + "nauc_recall_at_1000_diff1": -0.281925272335142, + "nauc_recall_at_1000_max": -0.3980068827463734, + "nauc_recall_at_1000_std": 0.21840506632592085, + "nauc_recall_at_100_diff1": -0.15761258751505455, + "nauc_recall_at_100_max": -0.22883071775776717, + "nauc_recall_at_100_std": 0.22842005552824063, + "nauc_recall_at_10_diff1": -0.06416474839619818, + "nauc_recall_at_10_max": -0.08300336228728562, + "nauc_recall_at_10_std": 0.057344358536626616, + "nauc_recall_at_1_diff1": 0.015120516198455985, + "nauc_recall_at_1_max": -0.0727075720153639, + "nauc_recall_at_1_std": 0.018913085028359998, + "nauc_recall_at_20_diff1": -0.09607413552155557, + "nauc_recall_at_20_max": -0.12568370952154892, + "nauc_recall_at_20_std": 0.09232019151068267, + "nauc_recall_at_3_diff1": -0.04210249363882283, + "nauc_recall_at_3_max": -0.056602182222527976, + "nauc_recall_at_3_std": 0.018180348333458524, + "nauc_recall_at_5_diff1": -0.05126817855971199, + "nauc_recall_at_5_max": -0.05552367693650274, + "nauc_recall_at_5_std": 0.0472261609659305, + "ndcg_at_1": 0.068, + "ndcg_at_10": 0.16555, + "ndcg_at_100": 0.22372, + "ndcg_at_1000": 0.25539, + "ndcg_at_20": 0.18577, + "ndcg_at_3": 0.11914, + "ndcg_at_5": 0.14182, + "precision_at_1": 0.068, + "precision_at_10": 0.02855, + "precision_at_100": 0.00573, + "precision_at_1000": 0.00083, + "precision_at_20": 0.01827, + "precision_at_3": 0.05231, + "precision_at_5": 0.04243, + "recall_at_1": 0.068, + "recall_at_10": 0.28553, + "recall_at_100": 0.57273, + "recall_at_1000": 0.83083, + "recall_at_20": 0.36539, + "recall_at_3": 0.15694, + "recall_at_5": 0.21215 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL2Pure.json b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL2Pure.json new file mode 100644 index 000000000..b5e0e0661 --- /dev/null +++ b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL2Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 11.686608791351318, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.0133, + "map_at_1": 0.00259, + "map_at_10": 0.0089, + "map_at_100": 0.01193, + "map_at_1000": 0.01314, + "map_at_20": 0.00998, + "map_at_3": 0.00624, + "map_at_5": 0.00755, + "mrr_at_1": 0.0025940337224383916, + "mrr_at_10": 0.008898535635611795, + "mrr_at_100": 0.011927953576586402, + "mrr_at_1000": 0.01314458424645019, + "mrr_at_20": 0.009979083915735187, + "mrr_at_3": 0.006238033475387558, + "mrr_at_5": 0.007553579148909889, + "nauc_map_at_1000_diff1": -0.025576765347923008, + "nauc_map_at_1000_max": 0.004996114478094064, + "nauc_map_at_1000_std": 0.24293104506902025, + "nauc_map_at_100_diff1": -0.020827050594413126, + "nauc_map_at_100_max": 0.00870031950287926, + "nauc_map_at_100_std": 0.2418415671052428, + "nauc_map_at_10_diff1": -0.0036703285812777174, + "nauc_map_at_10_max": 0.030574622369065885, + "nauc_map_at_10_std": 0.25919175511947773, + "nauc_map_at_1_diff1": -0.14852831285035062, + "nauc_map_at_1_max": -0.14122258106103788, + "nauc_map_at_1_std": 0.38888812143971696, + "nauc_map_at_20_diff1": -0.011569314203601343, + "nauc_map_at_20_max": 0.022746378189641047, + "nauc_map_at_20_std": 0.2521024216671209, + "nauc_map_at_3_diff1": 0.0012020193794218049, + "nauc_map_at_3_max": 0.008419890162180789, + "nauc_map_at_3_std": 0.29457889737126625, + "nauc_map_at_5_diff1": -0.005198377139489424, + "nauc_map_at_5_max": 0.029543479468575926, + "nauc_map_at_5_std": 0.27584472135362964, + "nauc_mrr_at_1000_diff1": -0.025576759631749373, + "nauc_mrr_at_1000_max": 0.00499610869263821, + "nauc_mrr_at_1000_std": 0.24293102691812524, + "nauc_mrr_at_100_diff1": -0.020827050594413126, + "nauc_mrr_at_100_max": 0.00870031950287926, + "nauc_mrr_at_100_std": 0.2418415671052428, + "nauc_mrr_at_10_diff1": -0.0036703285812777174, + "nauc_mrr_at_10_max": 0.030574622369065885, + "nauc_mrr_at_10_std": 0.25919175511947773, + "nauc_mrr_at_1_diff1": -0.14852831285035062, + "nauc_mrr_at_1_max": -0.14122258106103788, + "nauc_mrr_at_1_std": 0.38888812143971696, + "nauc_mrr_at_20_diff1": -0.011569314203601343, + "nauc_mrr_at_20_max": 0.022746378189641047, + "nauc_mrr_at_20_std": 0.2521024216671209, + "nauc_mrr_at_3_diff1": 0.0012020193794218049, + "nauc_mrr_at_3_max": 0.008419890162180789, + "nauc_mrr_at_3_std": 0.29457889737126625, + "nauc_mrr_at_5_diff1": -0.005198377139489424, + "nauc_mrr_at_5_max": 0.029543479468575926, + "nauc_mrr_at_5_std": 0.27584472135362964, + "nauc_ndcg_at_1000_diff1": -0.0860184120818062, + "nauc_ndcg_at_1000_max": -0.05336480904904239, + "nauc_ndcg_at_1000_std": 0.22387302545408433, + "nauc_ndcg_at_100_diff1": -0.04130183466565196, + "nauc_ndcg_at_100_max": -0.01827891041403201, + "nauc_ndcg_at_100_std": 0.20785311467879675, + "nauc_ndcg_at_10_diff1": 0.013169827686106516, + "nauc_ndcg_at_10_max": 0.05278070780170644, + "nauc_ndcg_at_10_std": 0.23928584059511607, + "nauc_ndcg_at_1_diff1": -0.14852831285035062, + "nauc_ndcg_at_1_max": -0.14122258106103788, + "nauc_ndcg_at_1_std": 0.38888812143971696, + "nauc_ndcg_at_20_diff1": -0.010272396764703458, + "nauc_ndcg_at_20_max": 0.027145329569887938, + "nauc_ndcg_at_20_std": 0.2265988518244755, + "nauc_ndcg_at_3_diff1": 0.026384875523631095, + "nauc_ndcg_at_3_max": 0.03499776029029969, + "nauc_ndcg_at_3_std": 0.2880765639988162, + "nauc_ndcg_at_5_diff1": 0.013607860837935788, + "nauc_ndcg_at_5_max": 0.05875378209659244, + "nauc_ndcg_at_5_std": 0.26467108063534733, + "nauc_precision_at_1000_diff1": -0.1310629760513816, + "nauc_precision_at_1000_max": -0.09607644761503628, + "nauc_precision_at_1000_std": 0.22360654492770574, + "nauc_precision_at_100_diff1": -0.05801239735775522, + "nauc_precision_at_100_max": -0.04043297894107592, + "nauc_precision_at_100_std": 0.19189384166454207, + "nauc_precision_at_10_diff1": 0.030330033013752315, + "nauc_precision_at_10_max": 0.07439615892677479, + "nauc_precision_at_10_std": 0.21686031097481323, + "nauc_precision_at_1_diff1": -0.14852831285035062, + "nauc_precision_at_1_max": -0.14122258106103788, + "nauc_precision_at_1_std": 0.38888812143971696, + "nauc_precision_at_20_diff1": -0.015110565786916292, + "nauc_precision_at_20_max": 0.02300916606474544, + "nauc_precision_at_20_std": 0.20332003258602535, + "nauc_precision_at_3_diff1": 0.06690708295715488, + "nauc_precision_at_3_max": 0.07795023938746791, + "nauc_precision_at_3_std": 0.27884522738327056, + "nauc_precision_at_5_diff1": 0.03829304342850513, + "nauc_precision_at_5_max": 0.09853605601356219, + "nauc_precision_at_5_std": 0.25007766969318435, + "nauc_recall_at_1000_diff1": -0.13106297605138129, + "nauc_recall_at_1000_max": -0.09607644761503589, + "nauc_recall_at_1000_std": 0.22360654492770593, + "nauc_recall_at_100_diff1": -0.05801239735775539, + "nauc_recall_at_100_max": -0.04043297894107608, + "nauc_recall_at_100_std": 0.1918938416645419, + "nauc_recall_at_10_diff1": 0.030330033013752138, + "nauc_recall_at_10_max": 0.07439615892677466, + "nauc_recall_at_10_std": 0.2168603109748131, + "nauc_recall_at_1_diff1": -0.14852831285035062, + "nauc_recall_at_1_max": -0.14122258106103788, + "nauc_recall_at_1_std": 0.38888812143971696, + "nauc_recall_at_20_diff1": -0.015110565786916413, + "nauc_recall_at_20_max": 0.023009166064745467, + "nauc_recall_at_20_std": 0.20332003258602518, + "nauc_recall_at_3_diff1": 0.06690708295715458, + "nauc_recall_at_3_max": 0.07795023938746772, + "nauc_recall_at_3_std": 0.27884522738327033, + "nauc_recall_at_5_diff1": 0.03829304342850491, + "nauc_recall_at_5_max": 0.09853605601356212, + "nauc_recall_at_5_std": 0.25007766969318407, + "ndcg_at_1": 0.00259, + "ndcg_at_10": 0.0133, + "ndcg_at_100": 0.03304, + "ndcg_at_1000": 0.07649, + "ndcg_at_20": 0.01733, + "ndcg_at_3": 0.00762, + "ndcg_at_5": 0.00999, + "precision_at_1": 0.00259, + "precision_at_10": 0.00278, + "precision_at_100": 0.00132, + "precision_at_1000": 0.0005, + "precision_at_20": 0.0022, + "precision_at_3": 0.00389, + "precision_at_5": 0.00348, + "recall_at_1": 0.00259, + "recall_at_10": 0.02779, + "recall_at_100": 0.13193, + "recall_at_1000": 0.49843, + "recall_at_20": 0.04391, + "recall_at_3": 0.01167, + "recall_at_5": 0.01742 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL3Fact.json b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL3Fact.json new file mode 100644 index 000000000..338190dfe --- /dev/null +++ b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL3Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 22.651365995407104, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.12676, + "map_at_1": 0.01898, + "map_at_10": 0.08568, + "map_at_100": 0.09744, + "map_at_1000": 0.09847, + "map_at_20": 0.09236, + "map_at_3": 0.06066, + "map_at_5": 0.07439, + "mrr_at_1": 0.018978761861726163, + "mrr_at_10": 0.08568263651295718, + "mrr_at_100": 0.09743714301086329, + "mrr_at_1000": 0.09846747851109595, + "mrr_at_20": 0.09235828623450143, + "mrr_at_3": 0.060664256665160544, + "mrr_at_5": 0.07438996836873008, + "nauc_map_at_1000_diff1": -0.04835953077944061, + "nauc_map_at_1000_max": 0.051733335789727795, + "nauc_map_at_1000_std": 0.17759953608175788, + "nauc_map_at_100_diff1": -0.047652690544570275, + "nauc_map_at_100_max": 0.05186334156187543, + "nauc_map_at_100_std": 0.1782226034566409, + "nauc_map_at_10_diff1": -0.04380234360110789, + "nauc_map_at_10_max": 0.06145858810805046, + "nauc_map_at_10_std": 0.15680426811229609, + "nauc_map_at_1_diff1": -0.24704603196961017, + "nauc_map_at_1_max": -0.03505086761168724, + "nauc_map_at_1_std": 0.12338720630140261, + "nauc_map_at_20_diff1": -0.04558909351084389, + "nauc_map_at_20_max": 0.055693415938518114, + "nauc_map_at_20_std": 0.1693550003809293, + "nauc_map_at_3_diff1": -0.04805298055257498, + "nauc_map_at_3_max": 0.07052802537022491, + "nauc_map_at_3_std": 0.1287057369065251, + "nauc_map_at_5_diff1": -0.03988930710565102, + "nauc_map_at_5_max": 0.0694633762155233, + "nauc_map_at_5_std": 0.1451006490900182, + "nauc_mrr_at_1000_diff1": -0.04835944420845055, + "nauc_mrr_at_1000_max": 0.05173345068260386, + "nauc_mrr_at_1000_std": 0.17759964569850065, + "nauc_mrr_at_100_diff1": -0.047652690544570275, + "nauc_mrr_at_100_max": 0.05186334156187543, + "nauc_mrr_at_100_std": 0.1782226034566409, + "nauc_mrr_at_10_diff1": -0.04380234360110789, + "nauc_mrr_at_10_max": 0.06145858810805046, + "nauc_mrr_at_10_std": 0.15680426811229609, + "nauc_mrr_at_1_diff1": -0.24704603196961017, + "nauc_mrr_at_1_max": -0.03505086761168724, + "nauc_mrr_at_1_std": 0.12338720630140261, + "nauc_mrr_at_20_diff1": -0.04558909351084389, + "nauc_mrr_at_20_max": 0.055693415938518114, + "nauc_mrr_at_20_std": 0.1693550003809293, + "nauc_mrr_at_3_diff1": -0.04805298055257498, + "nauc_mrr_at_3_max": 0.07052802537022491, + "nauc_mrr_at_3_std": 0.1287057369065251, + "nauc_mrr_at_5_diff1": -0.03988930710565102, + "nauc_mrr_at_5_max": 0.0694633762155233, + "nauc_mrr_at_5_std": 0.1451006490900182, + "nauc_ndcg_at_1000_diff1": -0.059563715466587355, + "nauc_ndcg_at_1000_max": 0.01489941438898806, + "nauc_ndcg_at_1000_std": 0.2303810874807862, + "nauc_ndcg_at_100_diff1": -0.04621640063121605, + "nauc_ndcg_at_100_max": 0.023236933927272538, + "nauc_ndcg_at_100_std": 0.2464037056813108, + "nauc_ndcg_at_10_diff1": -0.03302944152105421, + "nauc_ndcg_at_10_max": 0.0602228588748537, + "nauc_ndcg_at_10_std": 0.17323824918705877, + "nauc_ndcg_at_1_diff1": -0.24704603196961017, + "nauc_ndcg_at_1_max": -0.03505086761168724, + "nauc_ndcg_at_1_std": 0.12338720630140261, + "nauc_ndcg_at_20_diff1": -0.038236762172175996, + "nauc_ndcg_at_20_max": 0.044807481973348544, + "nauc_ndcg_at_20_std": 0.20432874634971498, + "nauc_ndcg_at_3_diff1": -0.033969039806164815, + "nauc_ndcg_at_3_max": 0.07817693712938516, + "nauc_ndcg_at_3_std": 0.13007343283068043, + "nauc_ndcg_at_5_diff1": -0.025389556095757628, + "nauc_ndcg_at_5_max": 0.07469397019353285, + "nauc_ndcg_at_5_std": 0.15252431902433494, + "nauc_precision_at_1000_diff1": -0.15310294476789094, + "nauc_precision_at_1000_max": -0.16996545011612277, + "nauc_precision_at_1000_std": 0.36700586066540103, + "nauc_precision_at_100_diff1": -0.05324976314452628, + "nauc_precision_at_100_max": -0.04203683146802579, + "nauc_precision_at_100_std": 0.380256644894637, + "nauc_precision_at_10_diff1": -0.021486454053071438, + "nauc_precision_at_10_max": 0.055896478004981424, + "nauc_precision_at_10_std": 0.1974600695865811, + "nauc_precision_at_1_diff1": -0.24704603196961017, + "nauc_precision_at_1_max": -0.03505086761168724, + "nauc_precision_at_1_std": 0.12338720630140261, + "nauc_precision_at_20_diff1": -0.033182852905331364, + "nauc_precision_at_20_max": 0.02431324768007818, + "nauc_precision_at_20_std": 0.25813199303542567, + "nauc_precision_at_3_diff1": -0.012907628582401272, + "nauc_precision_at_3_max": 0.08965784330880645, + "nauc_precision_at_3_std": 0.1323578471899761, + "nauc_precision_at_5_diff1": -0.006308669295973008, + "nauc_precision_at_5_max": 0.08086069769899885, + "nauc_precision_at_5_std": 0.1638929437426381, + "nauc_recall_at_1000_diff1": -0.1531029447678911, + "nauc_recall_at_1000_max": -0.16996545011612282, + "nauc_recall_at_1000_std": 0.3670058606654006, + "nauc_recall_at_100_diff1": -0.05324976314452615, + "nauc_recall_at_100_max": -0.04203683146802576, + "nauc_recall_at_100_std": 0.38025664489463706, + "nauc_recall_at_10_diff1": -0.02148645405307159, + "nauc_recall_at_10_max": 0.05589647800498135, + "nauc_recall_at_10_std": 0.1974600695865809, + "nauc_recall_at_1_diff1": -0.24704603196961017, + "nauc_recall_at_1_max": -0.03505086761168724, + "nauc_recall_at_1_std": 0.12338720630140261, + "nauc_recall_at_20_diff1": -0.03318285290533171, + "nauc_recall_at_20_max": 0.024313247680078136, + "nauc_recall_at_20_std": 0.25813199303542533, + "nauc_recall_at_3_diff1": -0.01290762858240123, + "nauc_recall_at_3_max": 0.08965784330880645, + "nauc_recall_at_3_std": 0.132357847189976, + "nauc_recall_at_5_diff1": -0.0063086692959732895, + "nauc_recall_at_5_max": 0.08086069769899855, + "nauc_recall_at_5_std": 0.16389294374263788, + "ndcg_at_1": 0.01898, + "ndcg_at_10": 0.12676, + "ndcg_at_100": 0.18831, + "ndcg_at_1000": 0.22005, + "ndcg_at_20": 0.1509, + "ndcg_at_3": 0.07486, + "ndcg_at_5": 0.09946, + "precision_at_1": 0.01898, + "precision_at_10": 0.02598, + "precision_at_100": 0.00558, + "precision_at_1000": 0.00082, + "precision_at_20": 0.01775, + "precision_at_3": 0.03871, + "precision_at_5": 0.03511, + "recall_at_1": 0.01898, + "recall_at_10": 0.25983, + "recall_at_100": 0.55807, + "recall_at_1000": 0.81744, + "recall_at_20": 0.35495, + "recall_at_3": 0.11613, + "recall_at_5": 0.17555 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL3Pure.json b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL3Pure.json new file mode 100644 index 000000000..abe22f716 --- /dev/null +++ b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL3Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 10.28584909439087, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.05078, + "map_at_1": 0.00136, + "map_at_10": 0.0306, + "map_at_100": 0.03958, + "map_at_1000": 0.04084, + "map_at_20": 0.03507, + "map_at_3": 0.01743, + "map_at_5": 0.02376, + "mrr_at_1": 0.0013556258472661546, + "mrr_at_10": 0.030598949927915148, + "mrr_at_100": 0.03958400500009361, + "mrr_at_1000": 0.04083708981457393, + "mrr_at_20": 0.03506736030933395, + "mrr_at_3": 0.017434854646784154, + "mrr_at_5": 0.023761108600692884, + "nauc_map_at_1000_diff1": -0.056964209828068435, + "nauc_map_at_1000_max": 0.18307589677772992, + "nauc_map_at_1000_std": 0.37498763772043087, + "nauc_map_at_100_diff1": -0.05716083814572068, + "nauc_map_at_100_max": 0.18407910980385803, + "nauc_map_at_100_std": 0.37467599480961805, + "nauc_map_at_10_diff1": -0.05721561837377563, + "nauc_map_at_10_max": 0.1776383689752796, + "nauc_map_at_10_std": 0.32627526811322743, + "nauc_map_at_1_diff1": -0.49081397991627407, + "nauc_map_at_1_max": -0.16460526964842295, + "nauc_map_at_1_std": -0.0660072557554571, + "nauc_map_at_20_diff1": -0.05902918512331495, + "nauc_map_at_20_max": 0.178734011786161, + "nauc_map_at_20_std": 0.3517427123626063, + "nauc_map_at_3_diff1": -0.05181451855668546, + "nauc_map_at_3_max": 0.15440388012321024, + "nauc_map_at_3_std": 0.2515637702450778, + "nauc_map_at_5_diff1": -0.052009660557586344, + "nauc_map_at_5_max": 0.17449487365328287, + "nauc_map_at_5_std": 0.28685313330132856, + "nauc_mrr_at_1000_diff1": -0.056964209828068435, + "nauc_mrr_at_1000_max": 0.18307589677772992, + "nauc_mrr_at_1000_std": 0.37498763772043087, + "nauc_mrr_at_100_diff1": -0.05716083814572068, + "nauc_mrr_at_100_max": 0.18407910980385803, + "nauc_mrr_at_100_std": 0.37467599480961805, + "nauc_mrr_at_10_diff1": -0.05721561837377563, + "nauc_mrr_at_10_max": 0.1776383689752796, + "nauc_mrr_at_10_std": 0.32627526811322743, + "nauc_mrr_at_1_diff1": -0.49081397991627407, + "nauc_mrr_at_1_max": -0.16460526964842295, + "nauc_mrr_at_1_std": -0.0660072557554571, + "nauc_mrr_at_20_diff1": -0.05902918512331495, + "nauc_mrr_at_20_max": 0.178734011786161, + "nauc_mrr_at_20_std": 0.3517427123626063, + "nauc_mrr_at_3_diff1": -0.05181451855668546, + "nauc_mrr_at_3_max": 0.15440388012321024, + "nauc_mrr_at_3_std": 0.2515637702450778, + "nauc_mrr_at_5_diff1": -0.052009660557586344, + "nauc_mrr_at_5_max": 0.17449487365328287, + "nauc_mrr_at_5_std": 0.28685313330132856, + "nauc_ndcg_at_1000_diff1": -0.04890023461117774, + "nauc_ndcg_at_1000_max": 0.19138069390184625, + "nauc_ndcg_at_1000_std": 0.4748400274609754, + "nauc_ndcg_at_100_diff1": -0.050418465388860516, + "nauc_ndcg_at_100_max": 0.20380567533916713, + "nauc_ndcg_at_100_std": 0.47176155192125246, + "nauc_ndcg_at_10_diff1": -0.059239871999676806, + "nauc_ndcg_at_10_max": 0.18435392595015826, + "nauc_ndcg_at_10_std": 0.3544911806142982, + "nauc_ndcg_at_1_diff1": -0.49081397991627407, + "nauc_ndcg_at_1_max": -0.16460526964842295, + "nauc_ndcg_at_1_std": -0.0660072557554571, + "nauc_ndcg_at_20_diff1": -0.06240018189728911, + "nauc_ndcg_at_20_max": 0.18661387250055533, + "nauc_ndcg_at_20_std": 0.40122295375747813, + "nauc_ndcg_at_3_diff1": -0.04709875560460691, + "nauc_ndcg_at_3_max": 0.15954833139219238, + "nauc_ndcg_at_3_std": 0.25942806118790046, + "nauc_ndcg_at_5_diff1": -0.04988568656443706, + "nauc_ndcg_at_5_max": 0.18352862282933055, + "nauc_ndcg_at_5_std": 0.30206413753324, + "nauc_precision_at_1000_diff1": -0.03221661345442819, + "nauc_precision_at_1000_max": 0.18701215198800172, + "nauc_precision_at_1000_std": 0.5996936093925418, + "nauc_precision_at_100_diff1": -0.04063083452963499, + "nauc_precision_at_100_max": 0.22205146229987122, + "nauc_precision_at_100_std": 0.5618255745728681, + "nauc_precision_at_10_diff1": -0.06282528664175314, + "nauc_precision_at_10_max": 0.18996671913796787, + "nauc_precision_at_10_std": 0.38313873316677227, + "nauc_precision_at_1_diff1": -0.49081397991627407, + "nauc_precision_at_1_max": -0.16460526964842295, + "nauc_precision_at_1_std": -0.0660072557554571, + "nauc_precision_at_20_diff1": -0.06658251145759077, + "nauc_precision_at_20_max": 0.19293275369319413, + "nauc_precision_at_20_std": 0.447278561675514, + "nauc_precision_at_3_diff1": -0.04159718690342368, + "nauc_precision_at_3_max": 0.1661121151988986, + "nauc_precision_at_3_std": 0.2700600211126549, + "nauc_precision_at_5_diff1": -0.04856661430595551, + "nauc_precision_at_5_max": 0.19410083073266965, + "nauc_precision_at_5_std": 0.32039458227690026, + "nauc_recall_at_1000_diff1": -0.03221661345442764, + "nauc_recall_at_1000_max": 0.1870121519880022, + "nauc_recall_at_1000_std": 0.5996936093925427, + "nauc_recall_at_100_diff1": -0.04063083452963527, + "nauc_recall_at_100_max": 0.22205146229987094, + "nauc_recall_at_100_std": 0.5618255745728679, + "nauc_recall_at_10_diff1": -0.06282528664175331, + "nauc_recall_at_10_max": 0.18996671913796748, + "nauc_recall_at_10_std": 0.38313873316677194, + "nauc_recall_at_1_diff1": -0.49081397991627407, + "nauc_recall_at_1_max": -0.16460526964842295, + "nauc_recall_at_1_std": -0.0660072557554571, + "nauc_recall_at_20_diff1": -0.06658251145759095, + "nauc_recall_at_20_max": 0.19293275369319388, + "nauc_recall_at_20_std": 0.44727856167551394, + "nauc_recall_at_3_diff1": -0.04159718690342369, + "nauc_recall_at_3_max": 0.16611211519889868, + "nauc_recall_at_3_std": 0.2700600211126549, + "nauc_recall_at_5_diff1": -0.04856661430595575, + "nauc_recall_at_5_max": 0.19410083073266937, + "nauc_recall_at_5_std": 0.32039458227689993, + "ndcg_at_1": 0.00136, + "ndcg_at_10": 0.05078, + "ndcg_at_100": 0.10151, + "ndcg_at_1000": 0.14141, + "ndcg_at_20": 0.06725, + "ndcg_at_3": 0.02281, + "ndcg_at_5": 0.03428, + "precision_at_1": 0.00136, + "precision_at_10": 0.01173, + "precision_at_100": 0.00371, + "precision_at_1000": 0.0007, + "precision_at_20": 0.00914, + "precision_at_3": 0.0128, + "precision_at_5": 0.01329, + "recall_at_1": 0.00136, + "recall_at_10": 0.11726, + "recall_at_100": 0.37054, + "recall_at_1000": 0.69883, + "recall_at_20": 0.18278, + "recall_at_3": 0.03841, + "recall_at_5": 0.06643 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/WinoGrande.json b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/WinoGrande.json new file mode 100644 index 000000000..b9c13517e --- /dev/null +++ b/results/bge-base-en-v1.5-instruct/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/WinoGrande.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 2.8883323669433594, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.10271, + "map_at_1": 0.015, + "map_at_10": 0.06172, + "map_at_100": 0.08157, + "map_at_1000": 0.08278, + "map_at_20": 0.07249, + "map_at_3": 0.03223, + "map_at_5": 0.04415, + "mrr_at_1": 0.01499605367008682, + "mrr_at_10": 0.06197116047155516, + "mrr_at_100": 0.08169613369813844, + "mrr_at_1000": 0.08290172719815347, + "mrr_at_20": 0.0726100242744776, + "mrr_at_3": 0.03249144961852144, + "mrr_at_5": 0.04425151275980008, + "nauc_map_at_1000_diff1": 0.05489727130993058, + "nauc_map_at_1000_max": -0.18076246250406977, + "nauc_map_at_1000_std": 0.043146797422347574, + "nauc_map_at_100_diff1": 0.055644624363084934, + "nauc_map_at_100_max": -0.180747417270204, + "nauc_map_at_100_std": 0.04290060655065701, + "nauc_map_at_10_diff1": 0.05914141760254415, + "nauc_map_at_10_max": -0.1784181349068122, + "nauc_map_at_10_std": 0.031147779129862368, + "nauc_map_at_1_diff1": 0.2150868572064556, + "nauc_map_at_1_max": -0.22294267974136833, + "nauc_map_at_1_std": 0.15986804197413793, + "nauc_map_at_20_diff1": 0.05194303340439235, + "nauc_map_at_20_max": -0.1742138250176015, + "nauc_map_at_20_std": 0.03496528298885216, + "nauc_map_at_3_diff1": 0.06277861978516315, + "nauc_map_at_3_max": -0.18774607923647374, + "nauc_map_at_3_std": 0.10768385600800294, + "nauc_map_at_5_diff1": 0.044159386715590256, + "nauc_map_at_5_max": -0.18659565926333205, + "nauc_map_at_5_std": 0.053197036723145345, + "nauc_mrr_at_1000_diff1": 0.055644920085238275, + "nauc_mrr_at_1000_max": -0.1831770955955253, + "nauc_mrr_at_1000_std": 0.038405235326263894, + "nauc_mrr_at_100_diff1": 0.056382147358113366, + "nauc_mrr_at_100_max": -0.183135625805258, + "nauc_mrr_at_100_std": 0.03821062216949412, + "nauc_mrr_at_10_diff1": 0.061903526590535156, + "nauc_mrr_at_10_max": -0.17987950539360176, + "nauc_mrr_at_10_std": 0.02607887911962339, + "nauc_mrr_at_1_diff1": 0.2150868572064556, + "nauc_mrr_at_1_max": -0.2448949763750307, + "nauc_mrr_at_1_std": 0.1328316955236998, + "nauc_mrr_at_20_diff1": 0.0526271932923178, + "nauc_mrr_at_20_max": -0.17648833085238763, + "nauc_mrr_at_20_std": 0.030415648592850508, + "nauc_mrr_at_3_diff1": 0.0703674568719228, + "nauc_mrr_at_3_max": -0.1859260232183394, + "nauc_mrr_at_3_std": 0.09799331589317511, + "nauc_mrr_at_5_diff1": 0.04503972987244179, + "nauc_mrr_at_5_max": -0.18929252263720567, + "nauc_mrr_at_5_std": 0.04757126944171959, + "nauc_ndcg_at_1000_diff1": 0.05224518148964177, + "nauc_ndcg_at_1000_max": -0.1884357428309219, + "nauc_ndcg_at_1000_std": 0.04111463924157843, + "nauc_ndcg_at_100_diff1": 0.05998190472520817, + "nauc_ndcg_at_100_max": -0.19024677397150677, + "nauc_ndcg_at_100_std": 0.04188956308881961, + "nauc_ndcg_at_10_diff1": 0.05629934415935614, + "nauc_ndcg_at_10_max": -0.17467407995879447, + "nauc_ndcg_at_10_std": 0.001841065381085781, + "nauc_ndcg_at_1_diff1": 0.2150868572064556, + "nauc_ndcg_at_1_max": -0.22294267974136833, + "nauc_ndcg_at_1_std": 0.15986804197413793, + "nauc_ndcg_at_20_diff1": 0.04012255072543604, + "nauc_ndcg_at_20_max": -0.16788783606845364, + "nauc_ndcg_at_20_std": 0.012508866329703376, + "nauc_ndcg_at_3_diff1": 0.05214826130890887, + "nauc_ndcg_at_3_max": -0.18084460016277212, + "nauc_ndcg_at_3_std": 0.10139956840639443, + "nauc_ndcg_at_5_diff1": 0.028170443143465427, + "nauc_ndcg_at_5_max": -0.18355665064277382, + "nauc_ndcg_at_5_std": 0.03143512027464653, + "nauc_precision_at_1000_diff1": 0.20462087462806028, + "nauc_precision_at_1000_max": -0.48496109459014575, + "nauc_precision_at_1000_std": 0.2853632162324012, + "nauc_precision_at_100_diff1": 0.08845142796772146, + "nauc_precision_at_100_max": -0.220479409707237, + "nauc_precision_at_100_std": 0.06578435196395639, + "nauc_precision_at_10_diff1": 0.05612412169800908, + "nauc_precision_at_10_max": -0.17222993904957515, + "nauc_precision_at_10_std": -0.029566540045228733, + "nauc_precision_at_1_diff1": 0.2150868572064556, + "nauc_precision_at_1_max": -0.22294267974136833, + "nauc_precision_at_1_std": 0.15986804197413793, + "nauc_precision_at_20_diff1": 0.02833278683853736, + "nauc_precision_at_20_max": -0.1630597245291863, + "nauc_precision_at_20_std": -0.007511039015002469, + "nauc_precision_at_3_diff1": 0.036543077250143705, + "nauc_precision_at_3_max": -0.16903946447891374, + "nauc_precision_at_3_std": 0.09117937718367594, + "nauc_precision_at_5_diff1": 0.007868359634533152, + "nauc_precision_at_5_max": -0.18053223139166175, + "nauc_precision_at_5_std": 0.002354923255793, + "nauc_recall_at_1000_diff1": 0.2046208746280569, + "nauc_recall_at_1000_max": -0.4849610945901529, + "nauc_recall_at_1000_std": 0.2853632162324197, + "nauc_recall_at_100_diff1": 0.08845142796772114, + "nauc_recall_at_100_max": -0.2204794097072374, + "nauc_recall_at_100_std": 0.06578435196395564, + "nauc_recall_at_10_diff1": 0.05612412169800873, + "nauc_recall_at_10_max": -0.17222993904957556, + "nauc_recall_at_10_std": -0.02956654004522882, + "nauc_recall_at_1_diff1": 0.2150868572064556, + "nauc_recall_at_1_max": -0.22294267974136833, + "nauc_recall_at_1_std": 0.15986804197413793, + "nauc_recall_at_20_diff1": 0.02833278683853758, + "nauc_recall_at_20_max": -0.1630597245291863, + "nauc_recall_at_20_std": -0.007511039015002782, + "nauc_recall_at_3_diff1": 0.03654307725014361, + "nauc_recall_at_3_max": -0.16903946447891374, + "nauc_recall_at_3_std": 0.09117937718367582, + "nauc_recall_at_5_diff1": 0.007868359634533128, + "nauc_recall_at_5_max": -0.18053223139166177, + "nauc_recall_at_5_std": 0.0023549232557929555, + "ndcg_at_1": 0.015, + "ndcg_at_10": 0.10271, + "ndcg_at_100": 0.20866, + "ndcg_at_1000": 0.23842, + "ndcg_at_20": 0.14239, + "ndcg_at_3": 0.0385, + "ndcg_at_5": 0.05996, + "precision_at_1": 0.015, + "precision_at_10": 0.02415, + "precision_at_100": 0.00758, + "precision_at_1000": 0.00099, + "precision_at_20": 0.01997, + "precision_at_3": 0.01894, + "precision_at_5": 0.02178, + "recall_at_1": 0.015, + "recall_at_10": 0.24152, + "recall_at_100": 0.7577, + "recall_at_1000": 0.98737, + "recall_at_20": 0.39937, + "recall_at_3": 0.05683, + "recall_at_5": 0.10892 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/ARCChallenge.json b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/ARCChallenge.json new file mode 100644 index 000000000..c8f89ab1e --- /dev/null +++ b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/ARCChallenge.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 4.141490936279297, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.09661, + "map_at_1": 0.03157, + "map_at_10": 0.07252, + "map_at_100": 0.08071, + "map_at_1000": 0.08195, + "map_at_20": 0.07674, + "map_at_3": 0.05916, + "map_at_5": 0.06633, + "mrr_at_1": 0.031569965870307165, + "mrr_at_10": 0.0725184869169511, + "mrr_at_100": 0.08070630541883014, + "mrr_at_1000": 0.08194862491063373, + "mrr_at_20": 0.07674359359635125, + "mrr_at_3": 0.05915813424345847, + "mrr_at_5": 0.06632536973833902, + "nauc_map_at_1000_diff1": -0.03603030599179797, + "nauc_map_at_1000_max": -0.02220054607995334, + "nauc_map_at_1000_std": -0.09259400841468371, + "nauc_map_at_100_diff1": -0.03577283744008322, + "nauc_map_at_100_max": -0.022229643755584918, + "nauc_map_at_100_std": -0.09307681947485939, + "nauc_map_at_10_diff1": -0.04013994875751633, + "nauc_map_at_10_max": -0.026176862866840084, + "nauc_map_at_10_std": -0.09997585777206815, + "nauc_map_at_1_diff1": 0.022714733390377655, + "nauc_map_at_1_max": -0.020355648975984512, + "nauc_map_at_1_std": -0.12339620786605068, + "nauc_map_at_20_diff1": -0.034805712508546915, + "nauc_map_at_20_max": -0.020131926007922882, + "nauc_map_at_20_std": -0.0961045730517076, + "nauc_map_at_3_diff1": -0.05100269228394475, + "nauc_map_at_3_max": -0.021135400036470207, + "nauc_map_at_3_std": -0.09039973084738344, + "nauc_map_at_5_diff1": -0.0496988769774354, + "nauc_map_at_5_max": -0.017641931291953544, + "nauc_map_at_5_std": -0.09205515156878971, + "nauc_mrr_at_1000_diff1": -0.03603023339011413, + "nauc_mrr_at_1000_max": -0.022200290775124632, + "nauc_mrr_at_1000_std": -0.09259408086825871, + "nauc_mrr_at_100_diff1": -0.03577283744008322, + "nauc_mrr_at_100_max": -0.022229643755584918, + "nauc_mrr_at_100_std": -0.09307681947485939, + "nauc_mrr_at_10_diff1": -0.04013994875751633, + "nauc_mrr_at_10_max": -0.026176862866840084, + "nauc_mrr_at_10_std": -0.09997585777206815, + "nauc_mrr_at_1_diff1": 0.022714733390377655, + "nauc_mrr_at_1_max": -0.020355648975984512, + "nauc_mrr_at_1_std": -0.12339620786605068, + "nauc_mrr_at_20_diff1": -0.034805712508546915, + "nauc_mrr_at_20_max": -0.020131926007922882, + "nauc_mrr_at_20_std": -0.0961045730517076, + "nauc_mrr_at_3_diff1": -0.05100269228394475, + "nauc_mrr_at_3_max": -0.021135400036470207, + "nauc_mrr_at_3_std": -0.09039973084738344, + "nauc_mrr_at_5_diff1": -0.0496988769774354, + "nauc_mrr_at_5_max": -0.017641931291953544, + "nauc_mrr_at_5_std": -0.09205515156878971, + "nauc_ndcg_at_1000_diff1": -0.036674478701088316, + "nauc_ndcg_at_1000_max": -0.028936087561309214, + "nauc_ndcg_at_1000_std": -0.06627497754493279, + "nauc_ndcg_at_100_diff1": -0.0333625063427686, + "nauc_ndcg_at_100_max": -0.029755239545094108, + "nauc_ndcg_at_100_std": -0.07352523876594064, + "nauc_ndcg_at_10_diff1": -0.041736198904629984, + "nauc_ndcg_at_10_max": -0.03410422808160417, + "nauc_ndcg_at_10_std": -0.10476668694852363, + "nauc_ndcg_at_1_diff1": 0.022714733390377655, + "nauc_ndcg_at_1_max": -0.020355648975984512, + "nauc_ndcg_at_1_std": -0.12339620786605068, + "nauc_ndcg_at_20_diff1": -0.03025227766763927, + "nauc_ndcg_at_20_max": -0.018742767185626848, + "nauc_ndcg_at_20_std": -0.092463105606167, + "nauc_ndcg_at_3_diff1": -0.06605181424978844, + "nauc_ndcg_at_3_max": -0.021430517009410288, + "nauc_ndcg_at_3_std": -0.08447269035956716, + "nauc_ndcg_at_5_diff1": -0.06245647828878699, + "nauc_ndcg_at_5_max": -0.017769708389278407, + "nauc_ndcg_at_5_std": -0.08752280227791483, + "nauc_precision_at_1000_diff1": -0.035481504746964064, + "nauc_precision_at_1000_max": -0.0469628285368817, + "nauc_precision_at_1000_std": 0.015530421439251577, + "nauc_precision_at_100_diff1": -0.026123740643119328, + "nauc_precision_at_100_max": -0.04394528479400034, + "nauc_precision_at_100_std": -0.03389295714105493, + "nauc_precision_at_10_diff1": -0.039479964523333064, + "nauc_precision_at_10_max": -0.048412986575632956, + "nauc_precision_at_10_std": -0.115687892348956, + "nauc_precision_at_1_diff1": 0.022714733390377655, + "nauc_precision_at_1_max": -0.020355648975984512, + "nauc_precision_at_1_std": -0.12339620786605068, + "nauc_precision_at_20_diff1": -0.018918017670857264, + "nauc_precision_at_20_max": -0.015310926024548357, + "nauc_precision_at_20_std": -0.08620147531723547, + "nauc_precision_at_3_diff1": -0.09337518612957894, + "nauc_precision_at_3_max": -0.021987860220604304, + "nauc_precision_at_3_std": -0.07383959742504578, + "nauc_precision_at_5_diff1": -0.08287161577763426, + "nauc_precision_at_5_max": -0.01842045913632721, + "nauc_precision_at_5_std": -0.080460399462556, + "nauc_recall_at_1000_diff1": -0.03548150474696454, + "nauc_recall_at_1000_max": -0.04696282853688179, + "nauc_recall_at_1000_std": 0.015530421439251112, + "nauc_recall_at_100_diff1": -0.026123740643119515, + "nauc_recall_at_100_max": -0.043945284794000436, + "nauc_recall_at_100_std": -0.03389295714105509, + "nauc_recall_at_10_diff1": -0.03947996452333342, + "nauc_recall_at_10_max": -0.04841298657563327, + "nauc_recall_at_10_std": -0.11568789234895639, + "nauc_recall_at_1_diff1": 0.022714733390377655, + "nauc_recall_at_1_max": -0.020355648975984512, + "nauc_recall_at_1_std": -0.12339620786605068, + "nauc_recall_at_20_diff1": -0.018918017670857424, + "nauc_recall_at_20_max": -0.015310926024548517, + "nauc_recall_at_20_std": -0.08620147531723574, + "nauc_recall_at_3_diff1": -0.09337518612957904, + "nauc_recall_at_3_max": -0.021987860220604526, + "nauc_recall_at_3_std": -0.073839597425046, + "nauc_recall_at_5_diff1": -0.08287161577763433, + "nauc_recall_at_5_max": -0.01842045913632721, + "nauc_recall_at_5_std": -0.08046039946255612, + "ndcg_at_1": 0.03157, + "ndcg_at_10": 0.09661, + "ndcg_at_100": 0.14194, + "ndcg_at_1000": 0.18084, + "ndcg_at_20": 0.11167, + "ndcg_at_3": 0.06889, + "ndcg_at_5": 0.08167, + "precision_at_1": 0.03157, + "precision_at_10": 0.01741, + "precision_at_100": 0.00399, + "precision_at_1000": 0.00072, + "precision_at_20": 0.01165, + "precision_at_3": 0.03242, + "precision_at_5": 0.0256, + "recall_at_1": 0.03157, + "recall_at_10": 0.17406, + "recall_at_100": 0.39932, + "recall_at_1000": 0.71843, + "recall_at_20": 0.23294, + "recall_at_3": 0.09727, + "recall_at_5": 0.12799 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/AlphaNLI.json b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/AlphaNLI.json new file mode 100644 index 000000000..91b0b2516 --- /dev/null +++ b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/AlphaNLI.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 55.149972438812256, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.10986, + "map_at_1": 0.06201, + "map_at_10": 0.09127, + "map_at_100": 0.09732, + "map_at_1000": 0.0983, + "map_at_20": 0.09433, + "map_at_3": 0.08083, + "map_at_5": 0.08586, + "mrr_at_1": 0.06201044386422976, + "mrr_at_10": 0.09127113639189356, + "mrr_at_100": 0.0973217113757597, + "mrr_at_1000": 0.09829642276653426, + "mrr_at_20": 0.09433292348626923, + "mrr_at_3": 0.08083115752828543, + "mrr_at_5": 0.08585726718885987, + "nauc_map_at_1000_diff1": 0.3106320385545239, + "nauc_map_at_1000_max": 0.17905400698096768, + "nauc_map_at_1000_std": -0.013284477744840763, + "nauc_map_at_100_diff1": 0.3105028326737514, + "nauc_map_at_100_max": 0.17886956880085148, + "nauc_map_at_100_std": -0.01355344248086588, + "nauc_map_at_10_diff1": 0.3200265615418434, + "nauc_map_at_10_max": 0.1846454897096423, + "nauc_map_at_10_std": -0.015094723198003306, + "nauc_map_at_1_diff1": 0.4293646899961472, + "nauc_map_at_1_max": 0.24902857855835786, + "nauc_map_at_1_std": -0.0038242811766893946, + "nauc_map_at_20_diff1": 0.31422114402044016, + "nauc_map_at_20_max": 0.1813392467567099, + "nauc_map_at_20_std": -0.015133288831408784, + "nauc_map_at_3_diff1": 0.34902909009302846, + "nauc_map_at_3_max": 0.1922514746139319, + "nauc_map_at_3_std": -0.01928593712665105, + "nauc_map_at_5_diff1": 0.3335334629598783, + "nauc_map_at_5_max": 0.19412860755646913, + "nauc_map_at_5_std": -0.014756098086233946, + "nauc_mrr_at_1000_diff1": 0.3106320385545239, + "nauc_mrr_at_1000_max": 0.17905400698096768, + "nauc_mrr_at_1000_std": -0.013284477744840763, + "nauc_mrr_at_100_diff1": 0.3105028326737514, + "nauc_mrr_at_100_max": 0.17886956880085148, + "nauc_mrr_at_100_std": -0.01355344248086588, + "nauc_mrr_at_10_diff1": 0.3200265615418434, + "nauc_mrr_at_10_max": 0.1846454897096423, + "nauc_mrr_at_10_std": -0.015094723198003306, + "nauc_mrr_at_1_diff1": 0.4293646899961472, + "nauc_mrr_at_1_max": 0.24902857855835786, + "nauc_mrr_at_1_std": -0.0038242811766893946, + "nauc_mrr_at_20_diff1": 0.31422114402044016, + "nauc_mrr_at_20_max": 0.1813392467567099, + "nauc_mrr_at_20_std": -0.015133288831408784, + "nauc_mrr_at_3_diff1": 0.34902909009302846, + "nauc_mrr_at_3_max": 0.1922514746139319, + "nauc_mrr_at_3_std": -0.01928593712665105, + "nauc_mrr_at_5_diff1": 0.3335334629598783, + "nauc_mrr_at_5_max": 0.19412860755646913, + "nauc_mrr_at_5_std": -0.014756098086233946, + "nauc_ndcg_at_1000_diff1": 0.24332844214443558, + "nauc_ndcg_at_1000_max": 0.14912051363581252, + "nauc_ndcg_at_1000_std": 0.0034464919465688358, + "nauc_ndcg_at_100_diff1": 0.24213256607653708, + "nauc_ndcg_at_100_max": 0.14177949538383877, + "nauc_ndcg_at_100_std": -0.007348490951637272, + "nauc_ndcg_at_10_diff1": 0.27764919097871943, + "nauc_ndcg_at_10_max": 0.16265513081993685, + "nauc_ndcg_at_10_std": -0.015432997256599544, + "nauc_ndcg_at_1_diff1": 0.4293646899961472, + "nauc_ndcg_at_1_max": 0.24902857855835786, + "nauc_ndcg_at_1_std": -0.0038242811766893946, + "nauc_ndcg_at_20_diff1": 0.263579950270951, + "nauc_ndcg_at_20_max": 0.15452370565840562, + "nauc_ndcg_at_20_std": -0.01464639647130329, + "nauc_ndcg_at_3_diff1": 0.32825843274355465, + "nauc_ndcg_at_3_max": 0.17887438710148765, + "nauc_ndcg_at_3_std": -0.02257637368503055, + "nauc_ndcg_at_5_diff1": 0.30362421062226075, + "nauc_ndcg_at_5_max": 0.18195459492853253, + "nauc_ndcg_at_5_std": -0.015564943591202134, + "nauc_precision_at_1000_diff1": 0.11003851071974964, + "nauc_precision_at_1000_max": 0.10664738112609039, + "nauc_precision_at_1000_std": 0.06662505716322109, + "nauc_precision_at_100_diff1": 0.11942993786840321, + "nauc_precision_at_100_max": 0.0748167226724706, + "nauc_precision_at_100_std": 0.007366048482631437, + "nauc_precision_at_10_diff1": 0.19568865777887706, + "nauc_precision_at_10_max": 0.11969706915851125, + "nauc_precision_at_10_std": -0.01500564816239971, + "nauc_precision_at_1_diff1": 0.4293646899961472, + "nauc_precision_at_1_max": 0.24902857855835786, + "nauc_precision_at_1_std": -0.0038242811766893946, + "nauc_precision_at_20_diff1": 0.1734196032381467, + "nauc_precision_at_20_max": 0.10615097483249995, + "nauc_precision_at_20_std": -0.012029595216917755, + "nauc_precision_at_3_diff1": 0.2818194518786715, + "nauc_precision_at_3_max": 0.1492633461998242, + "nauc_precision_at_3_std": -0.029771656638105257, + "nauc_precision_at_5_diff1": 0.2401032087891313, + "nauc_precision_at_5_max": 0.15728703818782291, + "nauc_precision_at_5_std": -0.016724536024854738, + "nauc_recall_at_1000_diff1": 0.11003851071975013, + "nauc_recall_at_1000_max": 0.10664738112608996, + "nauc_recall_at_1000_std": 0.06662505716322127, + "nauc_recall_at_100_diff1": 0.11942993786840311, + "nauc_recall_at_100_max": 0.07481672267247023, + "nauc_recall_at_100_std": 0.0073660484826312675, + "nauc_recall_at_10_diff1": 0.1956886577788771, + "nauc_recall_at_10_max": 0.11969706915851122, + "nauc_recall_at_10_std": -0.015005648162399802, + "nauc_recall_at_1_diff1": 0.4293646899961472, + "nauc_recall_at_1_max": 0.24902857855835786, + "nauc_recall_at_1_std": -0.0038242811766893946, + "nauc_recall_at_20_diff1": 0.17341960323814656, + "nauc_recall_at_20_max": 0.10615097483249977, + "nauc_recall_at_20_std": -0.012029595216917946, + "nauc_recall_at_3_diff1": 0.28181945187867175, + "nauc_recall_at_3_max": 0.14926334619982434, + "nauc_recall_at_3_std": -0.029771656638105336, + "nauc_recall_at_5_diff1": 0.2401032087891309, + "nauc_recall_at_5_max": 0.15728703818782275, + "nauc_recall_at_5_std": -0.016724536024854852, + "ndcg_at_1": 0.06201, + "ndcg_at_10": 0.10986, + "ndcg_at_100": 0.14349, + "ndcg_at_1000": 0.17488, + "ndcg_at_20": 0.12096, + "ndcg_at_3": 0.08752, + "ndcg_at_5": 0.09676, + "precision_at_1": 0.06201, + "precision_at_10": 0.01704, + "precision_at_100": 0.00337, + "precision_at_1000": 0.0006, + "precision_at_20": 0.0107, + "precision_at_3": 0.03568, + "precision_at_5": 0.02598, + "recall_at_1": 0.06201, + "recall_at_10": 0.17037, + "recall_at_100": 0.33747, + "recall_at_1000": 0.59661, + "recall_at_20": 0.2141, + "recall_at_3": 0.10705, + "recall_at_5": 0.1299 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/HellaSwag.json b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/HellaSwag.json new file mode 100644 index 000000000..0f44e7468 --- /dev/null +++ b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/HellaSwag.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 140.94582438468933, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.26638, + "map_at_1": 0.1433, + "map_at_10": 0.2234, + "map_at_100": 0.2322, + "map_at_1000": 0.23305, + "map_at_20": 0.22815, + "map_at_3": 0.20081, + "map_at_5": 0.21392, + "mrr_at_1": 0.14329814777932684, + "mrr_at_10": 0.22340250313761525, + "mrr_at_100": 0.2321986083128451, + "mrr_at_1000": 0.2330477077184162, + "mrr_at_20": 0.22814873668903507, + "mrr_at_3": 0.2008066122286383, + "mrr_at_5": 0.21392152957578128, + "nauc_map_at_1000_diff1": 0.19621193768025336, + "nauc_map_at_1000_max": 0.10369815311591503, + "nauc_map_at_1000_std": -0.21287727232754447, + "nauc_map_at_100_diff1": 0.1960220617433897, + "nauc_map_at_100_max": 0.10355239356333247, + "nauc_map_at_100_std": -0.21315445192549873, + "nauc_map_at_10_diff1": 0.19762892090239048, + "nauc_map_at_10_max": 0.10570008040182532, + "nauc_map_at_10_std": -0.21248689482605537, + "nauc_map_at_1_diff1": 0.23861926584852575, + "nauc_map_at_1_max": 0.08213047713888232, + "nauc_map_at_1_std": -0.1913657130596874, + "nauc_map_at_20_diff1": 0.19674709482171934, + "nauc_map_at_20_max": 0.10410775225975911, + "nauc_map_at_20_std": -0.21392217959541518, + "nauc_map_at_3_diff1": 0.20428623491394418, + "nauc_map_at_3_max": 0.1059103211384417, + "nauc_map_at_3_std": -0.20467365166789314, + "nauc_map_at_5_diff1": 0.2001576710329499, + "nauc_map_at_5_max": 0.1069375355634236, + "nauc_map_at_5_std": -0.20926604718835226, + "nauc_mrr_at_1000_diff1": 0.19621193768025336, + "nauc_mrr_at_1000_max": 0.10369815311591503, + "nauc_mrr_at_1000_std": -0.21287727232754447, + "nauc_mrr_at_100_diff1": 0.1960220617433897, + "nauc_mrr_at_100_max": 0.10355239356333247, + "nauc_mrr_at_100_std": -0.21315445192549873, + "nauc_mrr_at_10_diff1": 0.19762892090239048, + "nauc_mrr_at_10_max": 0.10570008040182532, + "nauc_mrr_at_10_std": -0.21248689482605537, + "nauc_mrr_at_1_diff1": 0.23861926584852575, + "nauc_mrr_at_1_max": 0.08213047713888232, + "nauc_mrr_at_1_std": -0.1913657130596874, + "nauc_mrr_at_20_diff1": 0.19674709482171934, + "nauc_mrr_at_20_max": 0.10410775225975911, + "nauc_mrr_at_20_std": -0.21392217959541518, + "nauc_mrr_at_3_diff1": 0.20428623491394418, + "nauc_mrr_at_3_max": 0.1059103211384417, + "nauc_mrr_at_3_std": -0.20467365166789314, + "nauc_mrr_at_5_diff1": 0.2001576710329499, + "nauc_mrr_at_5_max": 0.1069375355634236, + "nauc_mrr_at_5_std": -0.20926604718835226, + "nauc_ndcg_at_1000_diff1": 0.17894127155391132, + "nauc_ndcg_at_1000_max": 0.10475122331769127, + "nauc_ndcg_at_1000_std": -0.21791306540287214, + "nauc_ndcg_at_100_diff1": 0.1750452534498411, + "nauc_ndcg_at_100_max": 0.10145074731122938, + "nauc_ndcg_at_100_std": -0.2221649735468156, + "nauc_ndcg_at_10_diff1": 0.18382690634086252, + "nauc_ndcg_at_10_max": 0.11044381877344829, + "nauc_ndcg_at_10_std": -0.22354554771035365, + "nauc_ndcg_at_1_diff1": 0.23861926584852575, + "nauc_ndcg_at_1_max": 0.08213047713888232, + "nauc_ndcg_at_1_std": -0.1913657130596874, + "nauc_ndcg_at_20_diff1": 0.18055249572093787, + "nauc_ndcg_at_20_max": 0.10489455100261631, + "nauc_ndcg_at_20_std": -0.22807654506494615, + "nauc_ndcg_at_3_diff1": 0.1965106987923077, + "nauc_ndcg_at_3_max": 0.11223509241305754, + "nauc_ndcg_at_3_std": -0.20882149734013034, + "nauc_ndcg_at_5_diff1": 0.18981345974481845, + "nauc_ndcg_at_5_max": 0.11364724357376785, + "nauc_ndcg_at_5_std": -0.21649234507310952, + "nauc_precision_at_1000_diff1": 0.08696261840049306, + "nauc_precision_at_1000_max": 0.10949049232633232, + "nauc_precision_at_1000_std": -0.21135001344986754, + "nauc_precision_at_100_diff1": 0.10132253797475022, + "nauc_precision_at_100_max": 0.08333738206384435, + "nauc_precision_at_100_std": -0.24116543714668306, + "nauc_precision_at_10_diff1": 0.1502935004445975, + "nauc_precision_at_10_max": 0.11990388380905101, + "nauc_precision_at_10_std": -0.25143627685877235, + "nauc_precision_at_1_diff1": 0.23861926584852575, + "nauc_precision_at_1_max": 0.08213047713888232, + "nauc_precision_at_1_std": -0.1913657130596874, + "nauc_precision_at_20_diff1": 0.1383362718638513, + "nauc_precision_at_20_max": 0.10137930192491947, + "nauc_precision_at_20_std": -0.26639083390633966, + "nauc_precision_at_3_diff1": 0.17821447094663723, + "nauc_precision_at_3_max": 0.1273967055029564, + "nauc_precision_at_3_std": -0.21891854803672844, + "nauc_precision_at_5_diff1": 0.16561827824894138, + "nauc_precision_at_5_max": 0.12916447865193442, + "nauc_precision_at_5_std": -0.23413845064937236, + "nauc_recall_at_1000_diff1": 0.08696261840049505, + "nauc_recall_at_1000_max": 0.10949049232633289, + "nauc_recall_at_1000_std": -0.2113500134498662, + "nauc_recall_at_100_diff1": 0.10132253797474934, + "nauc_recall_at_100_max": 0.08333738206384378, + "nauc_recall_at_100_std": -0.24116543714668345, + "nauc_recall_at_10_diff1": 0.15029350044459752, + "nauc_recall_at_10_max": 0.11990388380905097, + "nauc_recall_at_10_std": -0.2514362768587722, + "nauc_recall_at_1_diff1": 0.23861926584852575, + "nauc_recall_at_1_max": 0.08213047713888232, + "nauc_recall_at_1_std": -0.1913657130596874, + "nauc_recall_at_20_diff1": 0.13833627186385156, + "nauc_recall_at_20_max": 0.10137930192491987, + "nauc_recall_at_20_std": -0.26639083390633933, + "nauc_recall_at_3_diff1": 0.17821447094663698, + "nauc_recall_at_3_max": 0.12739670550295645, + "nauc_recall_at_3_std": -0.2189185480367287, + "nauc_recall_at_5_diff1": 0.16561827824894151, + "nauc_recall_at_5_max": 0.12916447865193464, + "nauc_recall_at_5_std": -0.2341384506493722, + "ndcg_at_1": 0.1433, + "ndcg_at_10": 0.26638, + "ndcg_at_100": 0.31361, + "ndcg_at_1000": 0.33878, + "ndcg_at_20": 0.28367, + "ndcg_at_3": 0.2198, + "ndcg_at_5": 0.24347, + "precision_at_1": 0.1433, + "precision_at_10": 0.04031, + "precision_at_100": 0.00634, + "precision_at_1000": 0.00084, + "precision_at_20": 0.02357, + "precision_at_3": 0.09162, + "precision_at_5": 0.06648, + "recall_at_1": 0.1433, + "recall_at_10": 0.40311, + "recall_at_100": 0.63424, + "recall_at_1000": 0.83798, + "recall_at_20": 0.47142, + "recall_at_3": 0.27485, + "recall_at_5": 0.3324 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/PIQA.json b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/PIQA.json new file mode 100644 index 000000000..feae724cb --- /dev/null +++ b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/PIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 17.5070903301239, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.25695, + "map_at_1": 0.13275, + "map_at_10": 0.21528, + "map_at_100": 0.22416, + "map_at_1000": 0.22485, + "map_at_20": 0.22006, + "map_at_3": 0.19568, + "map_at_5": 0.20531, + "mrr_at_1": 0.13275299238302501, + "mrr_at_10": 0.21528295939340547, + "mrr_at_100": 0.22415515577115205, + "mrr_at_1000": 0.22485049354731743, + "mrr_at_20": 0.22005704174152244, + "mrr_at_3": 0.19568371418208183, + "mrr_at_5": 0.20531374682626014, + "nauc_map_at_1000_diff1": -0.008799414079743419, + "nauc_map_at_1000_max": 0.11513065098550922, + "nauc_map_at_1000_std": -0.04659133418115611, + "nauc_map_at_100_diff1": -0.008906198844110367, + "nauc_map_at_100_max": 0.11528094924959592, + "nauc_map_at_100_std": -0.0464417760093519, + "nauc_map_at_10_diff1": -0.007632653353608575, + "nauc_map_at_10_max": 0.11824995179866024, + "nauc_map_at_10_std": -0.04846044712483079, + "nauc_map_at_1_diff1": 0.05896498060391847, + "nauc_map_at_1_max": 0.12610661927094835, + "nauc_map_at_1_std": -0.031194975125453914, + "nauc_map_at_20_diff1": -0.008282571522718035, + "nauc_map_at_20_max": 0.11702775841628608, + "nauc_map_at_20_std": -0.04753375519630339, + "nauc_map_at_3_diff1": -0.0011720712778507407, + "nauc_map_at_3_max": 0.1285431053921007, + "nauc_map_at_3_std": -0.048527885943830514, + "nauc_map_at_5_diff1": -0.005768497719335593, + "nauc_map_at_5_max": 0.12583488584753577, + "nauc_map_at_5_std": -0.04864588723825299, + "nauc_mrr_at_1000_diff1": -0.008799414079743419, + "nauc_mrr_at_1000_max": 0.11513065098550922, + "nauc_mrr_at_1000_std": -0.04659133418115611, + "nauc_mrr_at_100_diff1": -0.008906198844110367, + "nauc_mrr_at_100_max": 0.11528094924959592, + "nauc_mrr_at_100_std": -0.0464417760093519, + "nauc_mrr_at_10_diff1": -0.007632653353608575, + "nauc_mrr_at_10_max": 0.11824995179866024, + "nauc_mrr_at_10_std": -0.04846044712483079, + "nauc_mrr_at_1_diff1": 0.05896498060391847, + "nauc_mrr_at_1_max": 0.12610661927094835, + "nauc_mrr_at_1_std": -0.031194975125453914, + "nauc_mrr_at_20_diff1": -0.008282571522718035, + "nauc_mrr_at_20_max": 0.11702775841628608, + "nauc_mrr_at_20_std": -0.04753375519630339, + "nauc_mrr_at_3_diff1": -0.0011720712778507407, + "nauc_mrr_at_3_max": 0.1285431053921007, + "nauc_mrr_at_3_std": -0.048527885943830514, + "nauc_mrr_at_5_diff1": -0.005768497719335593, + "nauc_mrr_at_5_max": 0.12583488584753577, + "nauc_mrr_at_5_std": -0.04864588723825299, + "nauc_ndcg_at_1000_diff1": -0.032470669722917476, + "nauc_ndcg_at_1000_max": 0.0864231564466629, + "nauc_ndcg_at_1000_std": -0.047245176351382576, + "nauc_ndcg_at_100_diff1": -0.03429036944025413, + "nauc_ndcg_at_100_max": 0.08929755099622744, + "nauc_ndcg_at_100_std": -0.0414850871923123, + "nauc_ndcg_at_10_diff1": -0.025249925991435603, + "nauc_ndcg_at_10_max": 0.10592569104655497, + "nauc_ndcg_at_10_std": -0.0515766898097552, + "nauc_ndcg_at_1_diff1": 0.05896498060391847, + "nauc_ndcg_at_1_max": 0.12610661927094835, + "nauc_ndcg_at_1_std": -0.031194975125453914, + "nauc_ndcg_at_20_diff1": -0.02752650224361076, + "nauc_ndcg_at_20_max": 0.10186469586541168, + "nauc_ndcg_at_20_std": -0.04845942405005804, + "nauc_ndcg_at_3_diff1": -0.012857454204577628, + "nauc_ndcg_at_3_max": 0.127800748047988, + "nauc_ndcg_at_3_std": -0.052976600824661525, + "nauc_ndcg_at_5_diff1": -0.020189442483820024, + "nauc_ndcg_at_5_max": 0.12310074098746722, + "nauc_ndcg_at_5_std": -0.05311648951799445, + "nauc_precision_at_1000_diff1": -0.1542131670325154, + "nauc_precision_at_1000_max": -0.10375002551693592, + "nauc_precision_at_1000_std": -0.06654903270319058, + "nauc_precision_at_100_diff1": -0.12047885471369472, + "nauc_precision_at_100_max": -0.013430299125563221, + "nauc_precision_at_100_std": -0.01222081453216282, + "nauc_precision_at_10_diff1": -0.0663471661757162, + "nauc_precision_at_10_max": 0.07239143260549642, + "nauc_precision_at_10_std": -0.057203448854623445, + "nauc_precision_at_1_diff1": 0.05896498060391847, + "nauc_precision_at_1_max": 0.12610661927094835, + "nauc_precision_at_1_std": -0.031194975125453914, + "nauc_precision_at_20_diff1": -0.07438627213824271, + "nauc_precision_at_20_max": 0.05882132574013737, + "nauc_precision_at_20_std": -0.046986936536917226, + "nauc_precision_at_3_diff1": -0.03941787397485452, + "nauc_precision_at_3_max": 0.12571421275651623, + "nauc_precision_at_3_std": -0.06344318976033086, + "nauc_precision_at_5_diff1": -0.0527651715681665, + "nauc_precision_at_5_max": 0.11596522424052763, + "nauc_precision_at_5_std": -0.06330350252542756, + "nauc_recall_at_1000_diff1": -0.15421316703251486, + "nauc_recall_at_1000_max": -0.10375002551693503, + "nauc_recall_at_1000_std": -0.06654903270318935, + "nauc_recall_at_100_diff1": -0.12047885471369522, + "nauc_recall_at_100_max": -0.013430299125563719, + "nauc_recall_at_100_std": -0.012220814532163225, + "nauc_recall_at_10_diff1": -0.0663471661757162, + "nauc_recall_at_10_max": 0.07239143260549634, + "nauc_recall_at_10_std": -0.05720344885462354, + "nauc_recall_at_1_diff1": 0.05896498060391847, + "nauc_recall_at_1_max": 0.12610661927094835, + "nauc_recall_at_1_std": -0.031194975125453914, + "nauc_recall_at_20_diff1": -0.07438627213824289, + "nauc_recall_at_20_max": 0.05882132574013741, + "nauc_recall_at_20_std": -0.046986936536917316, + "nauc_recall_at_3_diff1": -0.039417873974854814, + "nauc_recall_at_3_max": 0.12571421275651617, + "nauc_recall_at_3_std": -0.06344318976033085, + "nauc_recall_at_5_diff1": -0.052765171568166576, + "nauc_recall_at_5_max": 0.11596522424052763, + "nauc_recall_at_5_std": -0.06330350252542759, + "ndcg_at_1": 0.13275, + "ndcg_at_10": 0.25695, + "ndcg_at_100": 0.30501, + "ndcg_at_1000": 0.32674, + "ndcg_at_20": 0.2744, + "ndcg_at_3": 0.21562, + "ndcg_at_5": 0.23304, + "precision_at_1": 0.13275, + "precision_at_10": 0.0389, + "precision_at_100": 0.00625, + "precision_at_1000": 0.0008, + "precision_at_20": 0.02291, + "precision_at_3": 0.09104, + "precision_at_5": 0.06311, + "recall_at_1": 0.13275, + "recall_at_10": 0.38901, + "recall_at_100": 0.62514, + "recall_at_1000": 0.80359, + "recall_at_20": 0.45811, + "recall_at_3": 0.27312, + "recall_at_5": 0.31556 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/Quail.json b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/Quail.json new file mode 100644 index 000000000..9e851cee4 --- /dev/null +++ b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/Quail.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 26.725777864456177, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01416, + "map_at_1": 0.00441, + "map_at_10": 0.01, + "map_at_100": 0.01257, + "map_at_1000": 0.01325, + "map_at_20": 0.01118, + "map_at_3": 0.00729, + "map_at_5": 0.0085, + "mrr_at_1": 0.004411764705882353, + "mrr_at_10": 0.0101031454248366, + "mrr_at_100": 0.012642550753230236, + "mrr_at_1000": 0.013322213072026946, + "mrr_at_20": 0.011252431696624465, + "mrr_at_3": 0.007352941176470588, + "mrr_at_5": 0.008566176470588233, + "nauc_map_at_1000_diff1": 0.04592837659929379, + "nauc_map_at_1000_max": 0.22915640159862083, + "nauc_map_at_1000_std": 0.17378710726752897, + "nauc_map_at_100_diff1": 0.044436950963768346, + "nauc_map_at_100_max": 0.23027780123212627, + "nauc_map_at_100_std": 0.1736617011452022, + "nauc_map_at_10_diff1": 0.033309157010655836, + "nauc_map_at_10_max": 0.2547324605495276, + "nauc_map_at_10_std": 0.18276308268401803, + "nauc_map_at_1_diff1": -0.11904123065915391, + "nauc_map_at_1_max": 0.31915749932921916, + "nauc_map_at_1_std": 0.25992755567480536, + "nauc_map_at_20_diff1": 0.039236948068879854, + "nauc_map_at_20_max": 0.24561870267667166, + "nauc_map_at_20_std": 0.1799187671365048, + "nauc_map_at_3_diff1": 0.01144498582905118, + "nauc_map_at_3_max": 0.28195565857145105, + "nauc_map_at_3_std": 0.1911330671254281, + "nauc_map_at_5_diff1": 0.03462910655091867, + "nauc_map_at_5_max": 0.27489389291786936, + "nauc_map_at_5_std": 0.18697192927380152, + "nauc_mrr_at_1000_diff1": 0.04742001658758396, + "nauc_mrr_at_1000_max": 0.22611587231040997, + "nauc_mrr_at_1000_std": 0.17143801000784134, + "nauc_mrr_at_100_diff1": 0.04582942322988224, + "nauc_mrr_at_100_max": 0.2272850338848359, + "nauc_mrr_at_100_std": 0.1714966955280364, + "nauc_mrr_at_10_diff1": 0.037547571425615205, + "nauc_mrr_at_10_max": 0.24903920684506795, + "nauc_mrr_at_10_std": 0.17763922721636202, + "nauc_mrr_at_1_diff1": -0.11904123065915391, + "nauc_mrr_at_1_max": 0.31915749932921916, + "nauc_mrr_at_1_std": 0.25992755567480536, + "nauc_mrr_at_20_diff1": 0.04098369144547034, + "nauc_mrr_at_20_max": 0.24191310761658072, + "nauc_mrr_at_20_std": 0.17707634852113532, + "nauc_mrr_at_3_diff1": 0.014048385654234871, + "nauc_mrr_at_3_max": 0.27614703514891337, + "nauc_mrr_at_3_std": 0.18688623557821296, + "nauc_mrr_at_5_diff1": 0.036697946739045764, + "nauc_mrr_at_5_max": 0.2699584634110671, + "nauc_mrr_at_5_std": 0.18335634524079616, + "nauc_ndcg_at_1000_diff1": 0.05634144663836361, + "nauc_ndcg_at_1000_max": 0.15663407022357415, + "nauc_ndcg_at_1000_std": 0.147218785850073, + "nauc_ndcg_at_100_diff1": 0.06566204452341619, + "nauc_ndcg_at_100_max": 0.16187546793417465, + "nauc_ndcg_at_100_std": 0.14454719820444348, + "nauc_ndcg_at_10_diff1": 0.05612134125229386, + "nauc_ndcg_at_10_max": 0.23269399289775736, + "nauc_ndcg_at_10_std": 0.16978559656865647, + "nauc_ndcg_at_1_diff1": -0.11904123065915391, + "nauc_ndcg_at_1_max": 0.31915749932921916, + "nauc_ndcg_at_1_std": 0.25992755567480536, + "nauc_ndcg_at_20_diff1": 0.06076176349392271, + "nauc_ndcg_at_20_max": 0.21336506189480725, + "nauc_ndcg_at_20_std": 0.1636118232842824, + "nauc_ndcg_at_3_diff1": 0.04281472239181613, + "nauc_ndcg_at_3_max": 0.26847671623107866, + "nauc_ndcg_at_3_std": 0.17397628498294446, + "nauc_ndcg_at_5_diff1": 0.069563870285329, + "nauc_ndcg_at_5_max": 0.2615258125649662, + "nauc_ndcg_at_5_std": 0.1725479720390688, + "nauc_precision_at_1000_diff1": 0.04605684668546154, + "nauc_precision_at_1000_max": 0.1221808624939221, + "nauc_precision_at_1000_std": 0.13612764014857798, + "nauc_precision_at_100_diff1": 0.0711789515967063, + "nauc_precision_at_100_max": 0.11437899643619494, + "nauc_precision_at_100_std": 0.12595599191020904, + "nauc_precision_at_10_diff1": 0.0784072133647778, + "nauc_precision_at_10_max": 0.20620507533927424, + "nauc_precision_at_10_std": 0.1560730374366291, + "nauc_precision_at_1_diff1": -0.11904123065915391, + "nauc_precision_at_1_max": 0.31915749932921916, + "nauc_precision_at_1_std": 0.25992755567480536, + "nauc_precision_at_20_diff1": 0.07476315439301441, + "nauc_precision_at_20_max": 0.18121115742952454, + "nauc_precision_at_20_std": 0.14872137183942297, + "nauc_precision_at_3_diff1": 0.10278092732198352, + "nauc_precision_at_3_max": 0.2419830876688852, + "nauc_precision_at_3_std": 0.14108034655564894, + "nauc_precision_at_5_diff1": 0.12325451172991445, + "nauc_precision_at_5_max": 0.24079863744006724, + "nauc_precision_at_5_std": 0.15115899254558407, + "nauc_recall_at_1000_diff1": 0.046056846685461776, + "nauc_recall_at_1000_max": 0.1221808624939222, + "nauc_recall_at_1000_std": 0.13612764014857812, + "nauc_recall_at_100_diff1": 0.07117895159670617, + "nauc_recall_at_100_max": 0.11437899643619484, + "nauc_recall_at_100_std": 0.12595599191020895, + "nauc_recall_at_10_diff1": 0.07840721336477761, + "nauc_recall_at_10_max": 0.20620507533927385, + "nauc_recall_at_10_std": 0.1560730374366287, + "nauc_recall_at_1_diff1": -0.11904123065915391, + "nauc_recall_at_1_max": 0.31915749932921916, + "nauc_recall_at_1_std": 0.25992755567480536, + "nauc_recall_at_20_diff1": 0.07476315439301441, + "nauc_recall_at_20_max": 0.18121115742952446, + "nauc_recall_at_20_std": 0.14872137183942274, + "nauc_recall_at_3_diff1": 0.10278092732198338, + "nauc_recall_at_3_max": 0.24198308766888527, + "nauc_recall_at_3_std": 0.14108034655564874, + "nauc_recall_at_5_diff1": 0.12325451172991465, + "nauc_recall_at_5_max": 0.24079863744006716, + "nauc_recall_at_5_std": 0.15115899254558396, + "ndcg_at_1": 0.00441, + "ndcg_at_10": 0.01416, + "ndcg_at_100": 0.02977, + "ndcg_at_1000": 0.05337, + "ndcg_at_20": 0.01851, + "ndcg_at_3": 0.00834, + "ndcg_at_5": 0.01057, + "precision_at_1": 0.00441, + "precision_at_10": 0.00279, + "precision_at_100": 0.00108, + "precision_at_1000": 0.00031, + "precision_at_20": 0.00226, + "precision_at_3": 0.0038, + "precision_at_5": 0.00338, + "recall_at_1": 0.00441, + "recall_at_10": 0.02794, + "recall_at_100": 0.10846, + "recall_at_1000": 0.30662, + "recall_at_20": 0.04522, + "recall_at_3": 0.0114, + "recall_at_5": 0.01691 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/RARbCode.json b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/RARbCode.json new file mode 100644 index 000000000..0570d80d0 --- /dev/null +++ b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/RARbCode.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 944.7233462333679, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.46469, + "map_at_1": 0.32951, + "map_at_10": 0.41774, + "map_at_100": 0.42635, + "map_at_1000": 0.42678, + "map_at_20": 0.4224, + "map_at_3": 0.39499, + "map_at_5": 0.40668, + "mrr_at_1": 0.3288409703504043, + "mrr_at_10": 0.4173993496769775, + "mrr_at_100": 0.4260154298424324, + "mrr_at_1000": 0.42644505702162566, + "mrr_at_20": 0.4220979223755481, + "mrr_at_3": 0.3946540880503145, + "mrr_at_5": 0.40634546271338706, + "nauc_map_at_1000_diff1": 0.5029136010665783, + "nauc_map_at_1000_max": 0.41741961137717615, + "nauc_map_at_1000_std": 0.3381711397357424, + "nauc_map_at_100_diff1": 0.5028746890270769, + "nauc_map_at_100_max": 0.41740546853809396, + "nauc_map_at_100_std": 0.3382606478678912, + "nauc_map_at_10_diff1": 0.5011141814008917, + "nauc_map_at_10_max": 0.41842752582199055, + "nauc_map_at_10_std": 0.33837008173116473, + "nauc_map_at_1_diff1": 0.5426612969320858, + "nauc_map_at_1_max": 0.40431910331365833, + "nauc_map_at_1_std": 0.299442275293235, + "nauc_map_at_20_diff1": 0.5026833183460814, + "nauc_map_at_20_max": 0.4179614679155892, + "nauc_map_at_20_std": 0.3379820841385243, + "nauc_map_at_3_diff1": 0.5010481784457431, + "nauc_map_at_3_max": 0.40966224232280873, + "nauc_map_at_3_std": 0.3272443125060573, + "nauc_map_at_5_diff1": 0.5038569396974842, + "nauc_map_at_5_max": 0.41685655440079844, + "nauc_map_at_5_std": 0.3358164826947896, + "nauc_mrr_at_1000_diff1": 0.5039919008260132, + "nauc_mrr_at_1000_max": 0.4157603642145568, + "nauc_mrr_at_1000_std": 0.336496240945377, + "nauc_mrr_at_100_diff1": 0.5039517724011631, + "nauc_mrr_at_100_max": 0.41574808017696363, + "nauc_mrr_at_100_std": 0.336587643537759, + "nauc_mrr_at_10_diff1": 0.5021725395654753, + "nauc_mrr_at_10_max": 0.4168001408788086, + "nauc_mrr_at_10_std": 0.3367293387736503, + "nauc_mrr_at_1_diff1": 0.5447629891398887, + "nauc_mrr_at_1_max": 0.40110382100359626, + "nauc_mrr_at_1_std": 0.29619246900937607, + "nauc_mrr_at_20_diff1": 0.503765280228407, + "nauc_mrr_at_20_max": 0.4162734677740175, + "nauc_mrr_at_20_std": 0.33626183867044696, + "nauc_mrr_at_3_diff1": 0.5020850171661246, + "nauc_mrr_at_3_max": 0.4080664973614731, + "nauc_mrr_at_3_std": 0.3256350951453594, + "nauc_mrr_at_5_diff1": 0.5049028863708088, + "nauc_mrr_at_5_max": 0.41524869019758953, + "nauc_mrr_at_5_std": 0.33419526087026763, + "nauc_ndcg_at_1000_diff1": 0.4964794192307132, + "nauc_ndcg_at_1000_max": 0.4258995202126858, + "nauc_ndcg_at_1000_std": 0.35972415960141224, + "nauc_ndcg_at_100_diff1": 0.49528249960277215, + "nauc_ndcg_at_100_max": 0.4253925588791493, + "nauc_ndcg_at_100_std": 0.3630286808432581, + "nauc_ndcg_at_10_diff1": 0.48754222694547933, + "nauc_ndcg_at_10_max": 0.4274356910700709, + "nauc_ndcg_at_10_std": 0.3574733349702181, + "nauc_ndcg_at_1_diff1": 0.5426612969320858, + "nauc_ndcg_at_1_max": 0.40431910331365833, + "nauc_ndcg_at_1_std": 0.299442275293235, + "nauc_ndcg_at_20_diff1": 0.49283609532923484, + "nauc_ndcg_at_20_max": 0.4261303349833256, + "nauc_ndcg_at_20_std": 0.35679439735888174, + "nauc_ndcg_at_3_diff1": 0.48935781821827506, + "nauc_ndcg_at_3_max": 0.40998411783248656, + "nauc_ndcg_at_3_std": 0.3349003491372047, + "nauc_ndcg_at_5_diff1": 0.49493932063260154, + "nauc_ndcg_at_5_max": 0.4235125950103925, + "nauc_ndcg_at_5_std": 0.3511958518412034, + "nauc_precision_at_1000_diff1": 0.47691304792165884, + "nauc_precision_at_1000_max": 0.5915828225503998, + "nauc_precision_at_1000_std": 0.7071492365936988, + "nauc_precision_at_100_diff1": 0.46900015526717054, + "nauc_precision_at_100_max": 0.48822689074271886, + "nauc_precision_at_100_std": 0.5589827932465982, + "nauc_precision_at_10_diff1": 0.4415608650245783, + "nauc_precision_at_10_max": 0.4604216655155358, + "nauc_precision_at_10_std": 0.42464621007421327, + "nauc_precision_at_1_diff1": 0.5426612969320858, + "nauc_precision_at_1_max": 0.40431910331365833, + "nauc_precision_at_1_std": 0.299442275293235, + "nauc_precision_at_20_diff1": 0.45982919862125965, + "nauc_precision_at_20_max": 0.45919509783246465, + "nauc_precision_at_20_std": 0.43132542348755004, + "nauc_precision_at_3_diff1": 0.45608187367189595, + "nauc_precision_at_3_max": 0.41048523543552035, + "nauc_precision_at_3_std": 0.35663847736419907, + "nauc_precision_at_5_diff1": 0.47018717489688183, + "nauc_precision_at_5_max": 0.44523108827601, + "nauc_precision_at_5_std": 0.399472580331525, + "nauc_recall_at_1000_diff1": 0.47691304792166006, + "nauc_recall_at_1000_max": 0.591582822550403, + "nauc_recall_at_1000_std": 0.7071492365937008, + "nauc_recall_at_100_diff1": 0.4690001552671697, + "nauc_recall_at_100_max": 0.48822689074271874, + "nauc_recall_at_100_std": 0.5589827932465993, + "nauc_recall_at_10_diff1": 0.4415608650245777, + "nauc_recall_at_10_max": 0.4604216655155359, + "nauc_recall_at_10_std": 0.4246462100742137, + "nauc_recall_at_1_diff1": 0.5426612969320858, + "nauc_recall_at_1_max": 0.40431910331365833, + "nauc_recall_at_1_std": 0.299442275293235, + "nauc_recall_at_20_diff1": 0.4598291986212596, + "nauc_recall_at_20_max": 0.45919509783246404, + "nauc_recall_at_20_std": 0.43132542348755026, + "nauc_recall_at_3_diff1": 0.4560818736718965, + "nauc_recall_at_3_max": 0.41048523543552073, + "nauc_recall_at_3_std": 0.3566384773641991, + "nauc_recall_at_5_diff1": 0.47018717489688244, + "nauc_recall_at_5_max": 0.4452310882760099, + "nauc_recall_at_5_std": 0.39947258033152483, + "ndcg_at_1": 0.32951, + "ndcg_at_10": 0.46469, + "ndcg_at_100": 0.50994, + "ndcg_at_1000": 0.52251, + "ndcg_at_20": 0.48172, + "ndcg_at_3": 0.41642, + "ndcg_at_5": 0.43764, + "precision_at_1": 0.32951, + "precision_at_10": 0.06146, + "precision_at_100": 0.00834, + "precision_at_1000": 0.00093, + "precision_at_20": 0.0341, + "precision_at_3": 0.15948, + "precision_at_5": 0.10606, + "recall_at_1": 0.32951, + "recall_at_10": 0.61456, + "recall_at_100": 0.83356, + "recall_at_1000": 0.93464, + "recall_at_20": 0.68194, + "recall_at_3": 0.47844, + "recall_at_5": 0.53032 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/RARbMath.json b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/RARbMath.json new file mode 100644 index 000000000..c69de5819 --- /dev/null +++ b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/RARbMath.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 1453.8941411972046, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.46861, + "map_at_1": 0.38819, + "map_at_10": 0.43887, + "map_at_100": 0.4463, + "map_at_1000": 0.447, + "map_at_20": 0.44286, + "map_at_3": 0.42264, + "map_at_5": 0.43084, + "mrr_at_1": 0.38819433454660546, + "mrr_at_10": 0.43887237281366087, + "mrr_at_100": 0.4462988202349737, + "mrr_at_1000": 0.4469969787626024, + "mrr_at_20": 0.4428574201858376, + "mrr_at_3": 0.42264071319301544, + "mrr_at_5": 0.43083821279738344, + "nauc_map_at_1000_diff1": 0.7270479680355493, + "nauc_map_at_1000_max": 0.3550983671999909, + "nauc_map_at_1000_std": -0.16991294023349415, + "nauc_map_at_100_diff1": 0.7267537987185804, + "nauc_map_at_100_max": 0.3549167290213494, + "nauc_map_at_100_std": -0.17005115231829745, + "nauc_map_at_10_diff1": 0.7289386317718692, + "nauc_map_at_10_max": 0.354845589902454, + "nauc_map_at_10_std": -0.17259820746736876, + "nauc_map_at_1_diff1": 0.7759548944030574, + "nauc_map_at_1_max": 0.37996688565218467, + "nauc_map_at_1_std": -0.17473756609491728, + "nauc_map_at_20_diff1": 0.7272790872992854, + "nauc_map_at_20_max": 0.35438838192273886, + "nauc_map_at_20_std": -0.17117759078228173, + "nauc_map_at_3_diff1": 0.7416372936162879, + "nauc_map_at_3_max": 0.36049947603434074, + "nauc_map_at_3_std": -0.1736959878851694, + "nauc_map_at_5_diff1": 0.7337964637560175, + "nauc_map_at_5_max": 0.35745895533388033, + "nauc_map_at_5_std": -0.17293556156761453, + "nauc_mrr_at_1000_diff1": 0.7270479680355493, + "nauc_mrr_at_1000_max": 0.3550983671999909, + "nauc_mrr_at_1000_std": -0.16991294023349415, + "nauc_mrr_at_100_diff1": 0.7267537987185804, + "nauc_mrr_at_100_max": 0.3549167290213494, + "nauc_mrr_at_100_std": -0.17005115231829745, + "nauc_mrr_at_10_diff1": 0.7289386317718692, + "nauc_mrr_at_10_max": 0.354845589902454, + "nauc_mrr_at_10_std": -0.17259820746736876, + "nauc_mrr_at_1_diff1": 0.7759548944030574, + "nauc_mrr_at_1_max": 0.37996688565218467, + "nauc_mrr_at_1_std": -0.17473756609491728, + "nauc_mrr_at_20_diff1": 0.7272790872992854, + "nauc_mrr_at_20_max": 0.35438838192273886, + "nauc_mrr_at_20_std": -0.17117759078228173, + "nauc_mrr_at_3_diff1": 0.7416372936162879, + "nauc_mrr_at_3_max": 0.36049947603434074, + "nauc_mrr_at_3_std": -0.1736959878851694, + "nauc_mrr_at_5_diff1": 0.7337964637560175, + "nauc_mrr_at_5_max": 0.35745895533388033, + "nauc_mrr_at_5_std": -0.17293556156761453, + "nauc_ndcg_at_1000_diff1": 0.7022926438875192, + "nauc_ndcg_at_1000_max": 0.3489856999119827, + "nauc_ndcg_at_1000_std": -0.15085854929819162, + "nauc_ndcg_at_100_diff1": 0.6929840017981836, + "nauc_ndcg_at_100_max": 0.34397988896567466, + "nauc_ndcg_at_100_std": -0.15410950167443307, + "nauc_ndcg_at_10_diff1": 0.7035604650075299, + "nauc_ndcg_at_10_max": 0.34115003652684217, + "nauc_ndcg_at_10_std": -0.17025815114784082, + "nauc_ndcg_at_1_diff1": 0.7759548944030574, + "nauc_ndcg_at_1_max": 0.37996688565218467, + "nauc_ndcg_at_1_std": -0.17473756609491728, + "nauc_ndcg_at_20_diff1": 0.697083737925657, + "nauc_ndcg_at_20_max": 0.33939986582756915, + "nauc_ndcg_at_20_std": -0.16471119820099933, + "nauc_ndcg_at_3_diff1": 0.7301811438091298, + "nauc_ndcg_at_3_max": 0.35364038705725903, + "nauc_ndcg_at_3_std": -0.17285431185444136, + "nauc_ndcg_at_5_diff1": 0.7159860152739107, + "nauc_ndcg_at_5_max": 0.34806443367807666, + "nauc_ndcg_at_5_std": -0.17159573535865316, + "nauc_precision_at_1000_diff1": 0.46804925724784163, + "nauc_precision_at_1000_max": 0.38269867472204616, + "nauc_precision_at_1000_std": 0.2872999625765782, + "nauc_precision_at_100_diff1": 0.5022926988923171, + "nauc_precision_at_100_max": 0.3009021021636884, + "nauc_precision_at_100_std": -0.031271758823701735, + "nauc_precision_at_10_diff1": 0.6165397633701636, + "nauc_precision_at_10_max": 0.2939998911653996, + "nauc_precision_at_10_std": -0.16161998361183114, + "nauc_precision_at_1_diff1": 0.7759548944030574, + "nauc_precision_at_1_max": 0.37996688565218467, + "nauc_precision_at_1_std": -0.17473756609491728, + "nauc_precision_at_20_diff1": 0.5806436051131314, + "nauc_precision_at_20_max": 0.2827062152173538, + "nauc_precision_at_20_std": -0.13566400354725378, + "nauc_precision_at_3_diff1": 0.6966228108276521, + "nauc_precision_at_3_max": 0.3334387365414906, + "nauc_precision_at_3_std": -0.17023880270424888, + "nauc_precision_at_5_diff1": 0.6612355315333773, + "nauc_precision_at_5_max": 0.31929635084361246, + "nauc_precision_at_5_std": -0.1673808456232149, + "nauc_recall_at_1000_diff1": 0.4680492572478457, + "nauc_recall_at_1000_max": 0.3826986747220508, + "nauc_recall_at_1000_std": 0.2872999625765805, + "nauc_recall_at_100_diff1": 0.5022926988923171, + "nauc_recall_at_100_max": 0.30090210216368757, + "nauc_recall_at_100_std": -0.0312717588237027, + "nauc_recall_at_10_diff1": 0.616539763370164, + "nauc_recall_at_10_max": 0.2939998911653995, + "nauc_recall_at_10_std": -0.16161998361183028, + "nauc_recall_at_1_diff1": 0.7759548944030574, + "nauc_recall_at_1_max": 0.37996688565218467, + "nauc_recall_at_1_std": -0.17473756609491728, + "nauc_recall_at_20_diff1": 0.5806436051131316, + "nauc_recall_at_20_max": 0.28270621521735395, + "nauc_recall_at_20_std": -0.13566400354725347, + "nauc_recall_at_3_diff1": 0.6966228108276523, + "nauc_recall_at_3_max": 0.33343873654149114, + "nauc_recall_at_3_std": -0.17023880270424846, + "nauc_recall_at_5_diff1": 0.6612355315333774, + "nauc_recall_at_5_max": 0.3192963508436127, + "nauc_recall_at_5_std": -0.16738084562321442, + "ndcg_at_1": 0.38819, + "ndcg_at_10": 0.46861, + "ndcg_at_100": 0.50919, + "ndcg_at_1000": 0.5293, + "ndcg_at_20": 0.48335, + "ndcg_at_3": 0.43425, + "ndcg_at_5": 0.44907, + "precision_at_1": 0.38819, + "precision_at_10": 0.05646, + "precision_at_100": 0.00765, + "precision_at_1000": 0.00093, + "precision_at_20": 0.03117, + "precision_at_3": 0.15598, + "precision_at_5": 0.10081, + "recall_at_1": 0.38819, + "recall_at_10": 0.56465, + "recall_at_100": 0.76452, + "recall_at_1000": 0.92594, + "recall_at_20": 0.62336, + "recall_at_3": 0.46795, + "recall_at_5": 0.50404 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/SIQA.json b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/SIQA.json new file mode 100644 index 000000000..f06e62b72 --- /dev/null +++ b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/SIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 13.163275957107544, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.0094, + "map_at_1": 0.00051, + "map_at_10": 0.0056, + "map_at_100": 0.00845, + "map_at_1000": 0.00906, + "map_at_20": 0.00713, + "map_at_3": 0.00316, + "map_at_5": 0.00436, + "mrr_at_1": 0.0005117707267144319, + "mrr_at_10": 0.0055876427677860625, + "mrr_at_100": 0.008435601737587515, + "mrr_at_1000": 0.009041498232684159, + "mrr_at_20": 0.00710890052058521, + "mrr_at_3": 0.0031559194814056632, + "mrr_at_5": 0.004256226543841692, + "nauc_map_at_1000_diff1": -0.03972231073948161, + "nauc_map_at_1000_max": -0.03706067385931069, + "nauc_map_at_1000_std": -0.03498002632266371, + "nauc_map_at_100_diff1": -0.04276424208634857, + "nauc_map_at_100_max": -0.04268578611800295, + "nauc_map_at_100_std": -0.04165589979216519, + "nauc_map_at_10_diff1": -0.08039364337289916, + "nauc_map_at_10_max": -0.03387473137777456, + "nauc_map_at_10_std": -0.024473908112089094, + "nauc_map_at_1_diff1": -0.31833868118838016, + "nauc_map_at_1_max": -0.20566865955458707, + "nauc_map_at_1_std": 0.32369023383760825, + "nauc_map_at_20_diff1": -0.04861229270206693, + "nauc_map_at_20_max": -0.03499310432276828, + "nauc_map_at_20_std": -0.04396282189619557, + "nauc_map_at_3_diff1": -0.08760070268997376, + "nauc_map_at_3_max": -0.06207910930464921, + "nauc_map_at_3_std": -0.11678994962199829, + "nauc_map_at_5_diff1": -0.09713937562655835, + "nauc_map_at_5_max": -0.0743623922542478, + "nauc_map_at_5_std": -0.08426553372186005, + "nauc_mrr_at_1000_diff1": -0.03899545782489761, + "nauc_mrr_at_1000_max": -0.03631770991000926, + "nauc_mrr_at_1000_std": -0.035231609425806436, + "nauc_mrr_at_100_diff1": -0.042012179578380916, + "nauc_mrr_at_100_max": -0.041922002705038375, + "nauc_mrr_at_100_std": -0.0419306266944566, + "nauc_mrr_at_10_diff1": -0.07937250244827758, + "nauc_mrr_at_10_max": -0.03271156862398999, + "nauc_mrr_at_10_std": -0.024848889005063605, + "nauc_mrr_at_1_diff1": -0.31833868118838016, + "nauc_mrr_at_1_max": -0.20566865955458707, + "nauc_mrr_at_1_std": 0.32369023383760825, + "nauc_mrr_at_20_diff1": -0.047733404396453516, + "nauc_mrr_at_20_max": -0.03408153444230396, + "nauc_mrr_at_20_std": -0.04430432634122134, + "nauc_mrr_at_3_diff1": -0.08760070268997376, + "nauc_mrr_at_3_max": -0.06207910930464921, + "nauc_mrr_at_3_std": -0.11678994962199829, + "nauc_mrr_at_5_diff1": -0.0894986570778227, + "nauc_mrr_at_5_max": -0.06617393061840247, + "nauc_mrr_at_5_std": -0.08865709422587316, + "nauc_ndcg_at_1000_diff1": -0.0029450520520231693, + "nauc_ndcg_at_1000_max": 0.0011707810719223722, + "nauc_ndcg_at_1000_std": 0.0032002039346220035, + "nauc_ndcg_at_100_diff1": -0.021489405553188345, + "nauc_ndcg_at_100_max": -0.044040762419615465, + "nauc_ndcg_at_100_std": -0.03310761377394232, + "nauc_ndcg_at_10_diff1": -0.08341938098494113, + "nauc_ndcg_at_10_max": -0.025467845912925512, + "nauc_ndcg_at_10_std": -0.0010235769116684653, + "nauc_ndcg_at_1_diff1": -0.31833868118838016, + "nauc_ndcg_at_1_max": -0.20566865955458707, + "nauc_ndcg_at_1_std": 0.32369023383760825, + "nauc_ndcg_at_20_diff1": -0.024349581733427227, + "nauc_ndcg_at_20_max": -0.029235876514679876, + "nauc_ndcg_at_20_std": -0.04454557180028101, + "nauc_ndcg_at_3_diff1": -0.1041266924526749, + "nauc_ndcg_at_3_max": -0.07467736531118613, + "nauc_ndcg_at_3_std": -0.14099545480783707, + "nauc_ndcg_at_5_diff1": -0.11261577838225528, + "nauc_ndcg_at_5_max": -0.08865928537099634, + "nauc_ndcg_at_5_std": -0.09200113376183756, + "nauc_precision_at_1000_diff1": 0.01316888972086069, + "nauc_precision_at_1000_max": 0.027202402830459764, + "nauc_precision_at_1000_std": 0.0235905103623584, + "nauc_precision_at_100_diff1": -0.011837551716420154, + "nauc_precision_at_100_max": -0.043545541376498596, + "nauc_precision_at_100_std": -0.02670372266327017, + "nauc_precision_at_10_diff1": -0.08499192884326233, + "nauc_precision_at_10_max": -0.015391667844571721, + "nauc_precision_at_10_std": 0.02660814563838991, + "nauc_precision_at_1_diff1": -0.31833868118838016, + "nauc_precision_at_1_max": -0.20566865955458707, + "nauc_precision_at_1_std": 0.32369023383760825, + "nauc_precision_at_20_diff1": -0.0032599268441873505, + "nauc_precision_at_20_max": -0.024609582926197613, + "nauc_precision_at_20_std": -0.04640350424489374, + "nauc_precision_at_3_diff1": -0.1296636636222954, + "nauc_precision_at_3_max": -0.09391510486134041, + "nauc_precision_at_3_std": -0.17286118334510583, + "nauc_precision_at_5_diff1": -0.13231867652963783, + "nauc_precision_at_5_max": -0.10690521477107023, + "nauc_precision_at_5_std": -0.09824171981207311, + "nauc_recall_at_1000_diff1": 0.013168889720860909, + "nauc_recall_at_1000_max": 0.02720240283045998, + "nauc_recall_at_1000_std": 0.02359051036235859, + "nauc_recall_at_100_diff1": -0.011837551716420154, + "nauc_recall_at_100_max": -0.04354554137649854, + "nauc_recall_at_100_std": -0.026703722663270143, + "nauc_recall_at_10_diff1": -0.08499192884326248, + "nauc_recall_at_10_max": -0.015391667844571829, + "nauc_recall_at_10_std": 0.02660814563838978, + "nauc_recall_at_1_diff1": -0.31833868118838016, + "nauc_recall_at_1_max": -0.20566865955458707, + "nauc_recall_at_1_std": 0.32369023383760825, + "nauc_recall_at_20_diff1": -0.003259926844187662, + "nauc_recall_at_20_max": -0.024609582926197752, + "nauc_recall_at_20_std": -0.046403504244893874, + "nauc_recall_at_3_diff1": -0.12966366362229542, + "nauc_recall_at_3_max": -0.09391510486134044, + "nauc_recall_at_3_std": -0.17286118334510586, + "nauc_recall_at_5_diff1": -0.13231867652963775, + "nauc_recall_at_5_max": -0.10690521477107008, + "nauc_recall_at_5_std": -0.09824171981207307, + "ndcg_at_1": 0.00051, + "ndcg_at_10": 0.0094, + "ndcg_at_100": 0.02595, + "ndcg_at_1000": 0.0473, + "ndcg_at_20": 0.01513, + "ndcg_at_3": 0.00417, + "ndcg_at_5": 0.00631, + "precision_at_1": 0.00051, + "precision_at_10": 0.0022, + "precision_at_100": 0.00106, + "precision_at_1000": 0.00029, + "precision_at_20": 0.00225, + "precision_at_3": 0.00239, + "precision_at_5": 0.00246, + "recall_at_1": 0.00051, + "recall_at_10": 0.02201, + "recall_at_100": 0.10594, + "recall_at_1000": 0.28557, + "recall_at_20": 0.04504, + "recall_at_3": 0.00716, + "recall_at_5": 0.01228 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/SpartQA.json b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/SpartQA.json new file mode 100644 index 000000000..e491380cb --- /dev/null +++ b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/SpartQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 11.5577392578125, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.03367, + "map_at_1": 0.00288, + "map_at_10": 0.01795, + "map_at_100": 0.02496, + "map_at_1000": 0.02617, + "map_at_20": 0.02136, + "map_at_3": 0.01019, + "map_at_5": 0.01363, + "mrr_at_1": 0.003617139677239844, + "mrr_at_10": 0.02859715487010978, + "mrr_at_100": 0.03821388564302711, + "mrr_at_1000": 0.03948070875408114, + "mrr_at_20": 0.03350270526275299, + "mrr_at_3": 0.016369875718790592, + "mrr_at_5": 0.021670376553515124, + "nauc_map_at_1000_diff1": 0.030538587981634873, + "nauc_map_at_1000_max": -0.09654714636473932, + "nauc_map_at_1000_std": 0.18629342606024413, + "nauc_map_at_100_diff1": 0.02315620351047599, + "nauc_map_at_100_max": -0.09745699459330771, + "nauc_map_at_100_std": 0.18302741211166015, + "nauc_map_at_10_diff1": -0.00234752474271696, + "nauc_map_at_10_max": -0.06643307250300046, + "nauc_map_at_10_std": 0.20028341693752613, + "nauc_map_at_1_diff1": -0.4196336078511131, + "nauc_map_at_1_max": -0.4481442608023188, + "nauc_map_at_1_std": -0.1117849103049858, + "nauc_map_at_20_diff1": 0.010450002382900598, + "nauc_map_at_20_max": -0.08741912924948932, + "nauc_map_at_20_std": 0.18955569763522578, + "nauc_map_at_3_diff1": -0.005310115615707683, + "nauc_map_at_3_max": -0.03569202507662241, + "nauc_map_at_3_std": 0.2355387828530919, + "nauc_map_at_5_diff1": -0.000742238331867972, + "nauc_map_at_5_max": -0.03683982357178744, + "nauc_map_at_5_std": 0.22974255178428563, + "nauc_mrr_at_1000_diff1": 0.06896590170592322, + "nauc_mrr_at_1000_max": -0.04065331208852265, + "nauc_mrr_at_1000_std": 0.24488581662563288, + "nauc_mrr_at_100_diff1": 0.06529462135329844, + "nauc_mrr_at_100_max": -0.04207001507041081, + "nauc_mrr_at_100_std": 0.24296319449123388, + "nauc_mrr_at_10_diff1": 0.03649956616423059, + "nauc_mrr_at_10_max": -0.022076529758179888, + "nauc_mrr_at_10_std": 0.25796595175200354, + "nauc_mrr_at_1_diff1": -0.4432289272229514, + "nauc_mrr_at_1_max": -0.3983092719826059, + "nauc_mrr_at_1_std": -0.08777202960680201, + "nauc_mrr_at_20_diff1": 0.05430877110077811, + "nauc_mrr_at_20_max": -0.03558579305316362, + "nauc_mrr_at_20_std": 0.2480023819898197, + "nauc_mrr_at_3_diff1": 0.03725950447399401, + "nauc_mrr_at_3_max": 0.02002183997560916, + "nauc_mrr_at_3_std": 0.30156733731836, + "nauc_mrr_at_5_diff1": 0.03307978850927229, + "nauc_mrr_at_5_max": 0.000747839794624817, + "nauc_mrr_at_5_std": 0.28173960625960587, + "nauc_ndcg_at_1000_diff1": 0.17308420579576708, + "nauc_ndcg_at_1000_max": -0.09574384036257691, + "nauc_ndcg_at_1000_std": 0.22179659696835696, + "nauc_ndcg_at_100_diff1": 0.08381046247006656, + "nauc_ndcg_at_100_max": -0.10848184652272919, + "nauc_ndcg_at_100_std": 0.17640535399431478, + "nauc_ndcg_at_10_diff1": 0.026823525658104346, + "nauc_ndcg_at_10_max": -0.05075300581433591, + "nauc_ndcg_at_10_std": 0.2164845823795444, + "nauc_ndcg_at_1_diff1": -0.4432289272229514, + "nauc_ndcg_at_1_max": -0.3983092719826059, + "nauc_ndcg_at_1_std": -0.08777202960680201, + "nauc_ndcg_at_20_diff1": 0.05110202272763238, + "nauc_ndcg_at_20_max": -0.08612042637614842, + "nauc_ndcg_at_20_std": 0.19402918698359392, + "nauc_ndcg_at_3_diff1": 0.04688681919617768, + "nauc_ndcg_at_3_max": 0.023810403906683725, + "nauc_ndcg_at_3_std": 0.28798424101770703, + "nauc_ndcg_at_5_diff1": 0.036344528928043233, + "nauc_ndcg_at_5_max": -0.0005273328622012489, + "nauc_ndcg_at_5_std": 0.2639880594598804, + "nauc_precision_at_1000_diff1": 0.26324254244263723, + "nauc_precision_at_1000_max": -0.06754057830687253, + "nauc_precision_at_1000_std": 0.24754608371037845, + "nauc_precision_at_100_diff1": 0.1414670564417372, + "nauc_precision_at_100_max": -0.10600957783100387, + "nauc_precision_at_100_std": 0.20494590149906974, + "nauc_precision_at_10_diff1": 0.0681848255656026, + "nauc_precision_at_10_max": -0.026636030503315, + "nauc_precision_at_10_std": 0.25455582967335716, + "nauc_precision_at_1_diff1": -0.4432289272229514, + "nauc_precision_at_1_max": -0.3983092719826059, + "nauc_precision_at_1_std": -0.08777202960680201, + "nauc_precision_at_20_diff1": 0.10516070625126736, + "nauc_precision_at_20_max": -0.07414939626096223, + "nauc_precision_at_20_std": 0.22157340936088996, + "nauc_precision_at_3_diff1": 0.13176840136878046, + "nauc_precision_at_3_max": 0.11328416221591917, + "nauc_precision_at_3_std": 0.37070133005157163, + "nauc_precision_at_5_diff1": 0.08797572759040405, + "nauc_precision_at_5_max": 0.044054577422391265, + "nauc_precision_at_5_std": 0.31395949876158447, + "nauc_recall_at_1000_diff1": 0.2704358848608567, + "nauc_recall_at_1000_max": -0.07712049378495246, + "nauc_recall_at_1000_std": 0.18423174159679775, + "nauc_recall_at_100_diff1": 0.09557835884440227, + "nauc_recall_at_100_max": -0.12570054245733628, + "nauc_recall_at_100_std": 0.11899231585305547, + "nauc_recall_at_10_diff1": 0.0275895993259049, + "nauc_recall_at_10_max": -0.06545683998092167, + "nauc_recall_at_10_std": 0.19378474058640072, + "nauc_recall_at_1_diff1": -0.4196336078511131, + "nauc_recall_at_1_max": -0.4481442608023188, + "nauc_recall_at_1_std": -0.1117849103049858, + "nauc_recall_at_20_diff1": 0.05614822554360719, + "nauc_recall_at_20_max": -0.11195435227988487, + "nauc_recall_at_20_std": 0.15727463093437757, + "nauc_recall_at_3_diff1": 0.09105559525080674, + "nauc_recall_at_3_max": 0.07401117397665989, + "nauc_recall_at_3_std": 0.3197021446293945, + "nauc_recall_at_5_diff1": 0.05730959149773282, + "nauc_recall_at_5_max": 0.01956422113226323, + "nauc_recall_at_5_std": 0.27230655327926506, + "ndcg_at_1": 0.00362, + "ndcg_at_10": 0.03367, + "ndcg_at_100": 0.07691, + "ndcg_at_1000": 0.11573, + "ndcg_at_20": 0.04719, + "ndcg_at_3": 0.01466, + "ndcg_at_5": 0.02154, + "precision_at_1": 0.00362, + "precision_at_10": 0.01149, + "precision_at_100": 0.00434, + "precision_at_1000": 0.00092, + "precision_at_20": 0.00959, + "precision_at_3": 0.01187, + "precision_at_5": 0.01185, + "recall_at_1": 0.00288, + "recall_at_10": 0.07002, + "recall_at_100": 0.26294, + "recall_at_1000": 0.5435, + "recall_at_20": 0.1177, + "recall_at_3": 0.02115, + "recall_at_5": 0.03608 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL1.json b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL1.json new file mode 100644 index 000000000..7fb69c3e0 --- /dev/null +++ b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL1.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 7.117517709732056, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01073, + "map_at_1": 0.0015, + "map_at_10": 0.00675, + "map_at_100": 0.01021, + "map_at_1000": 0.01128, + "map_at_20": 0.00832, + "map_at_3": 0.004, + "map_at_5": 0.00534, + "mrr_at_1": 0.0015, + "mrr_at_10": 0.006750099206349204, + "mrr_at_100": 0.0102063218548196, + "mrr_at_1000": 0.011277471259822314, + "mrr_at_20": 0.008320084018149033, + "mrr_at_3": 0.004, + "mrr_at_5": 0.005337499999999998, + "nauc_map_at_1000_diff1": 0.04524111061911352, + "nauc_map_at_1000_max": 0.3311246479246325, + "nauc_map_at_1000_std": 0.16858281602997446, + "nauc_map_at_100_diff1": 0.04966789302633865, + "nauc_map_at_100_max": 0.3387993351897158, + "nauc_map_at_100_std": 0.1718362440798009, + "nauc_map_at_10_diff1": 0.03958426682452112, + "nauc_map_at_10_max": 0.3270662060411839, + "nauc_map_at_10_std": 0.2295335101284658, + "nauc_map_at_1_diff1": -0.5069761202039174, + "nauc_map_at_1_max": -0.07284679366782934, + "nauc_map_at_1_std": 0.3539039441910383, + "nauc_map_at_20_diff1": 0.06220451943800992, + "nauc_map_at_20_max": 0.35257555108171296, + "nauc_map_at_20_std": 0.19597154091665264, + "nauc_map_at_3_diff1": -0.057784970038458276, + "nauc_map_at_3_max": 0.13627750201234223, + "nauc_map_at_3_std": 0.21295892585636336, + "nauc_map_at_5_diff1": 0.003929382544451064, + "nauc_map_at_5_max": 0.264382514080113, + "nauc_map_at_5_std": 0.24259915669083157, + "nauc_mrr_at_1000_diff1": 0.04524111061911352, + "nauc_mrr_at_1000_max": 0.3311246479246325, + "nauc_mrr_at_1000_std": 0.16858281602997446, + "nauc_mrr_at_100_diff1": 0.04966789302633865, + "nauc_mrr_at_100_max": 0.3387993351897158, + "nauc_mrr_at_100_std": 0.1718362440798009, + "nauc_mrr_at_10_diff1": 0.03958426682452112, + "nauc_mrr_at_10_max": 0.3270662060411839, + "nauc_mrr_at_10_std": 0.2295335101284658, + "nauc_mrr_at_1_diff1": -0.5069761202039174, + "nauc_mrr_at_1_max": -0.07284679366782934, + "nauc_mrr_at_1_std": 0.3539039441910383, + "nauc_mrr_at_20_diff1": 0.06220451943800992, + "nauc_mrr_at_20_max": 0.35257555108171296, + "nauc_mrr_at_20_std": 0.19597154091665264, + "nauc_mrr_at_3_diff1": -0.057784970038458276, + "nauc_mrr_at_3_max": 0.13627750201234223, + "nauc_mrr_at_3_std": 0.21295892585636336, + "nauc_mrr_at_5_diff1": 0.003929382544451064, + "nauc_mrr_at_5_max": 0.264382514080113, + "nauc_mrr_at_5_std": 0.24259915669083157, + "nauc_ndcg_at_1000_diff1": 0.018130972377099076, + "nauc_ndcg_at_1000_max": 0.2976645743353398, + "nauc_ndcg_at_1000_std": 0.10972158204205798, + "nauc_ndcg_at_100_diff1": 0.04971662236866494, + "nauc_ndcg_at_100_max": 0.35559860527570547, + "nauc_ndcg_at_100_std": 0.11882508967854212, + "nauc_ndcg_at_10_diff1": 0.09034445974096947, + "nauc_ndcg_at_10_max": 0.40158399476593526, + "nauc_ndcg_at_10_std": 0.21947384482363894, + "nauc_ndcg_at_1_diff1": -0.5069761202039174, + "nauc_ndcg_at_1_max": -0.07284679366782934, + "nauc_ndcg_at_1_std": 0.3539039441910383, + "nauc_ndcg_at_20_diff1": 0.1125926898248508, + "nauc_ndcg_at_20_max": 0.4191977841087722, + "nauc_ndcg_at_20_std": 0.15696322131454873, + "nauc_ndcg_at_3_diff1": -0.01390790579135476, + "nauc_ndcg_at_3_max": 0.15505532647495132, + "nauc_ndcg_at_3_std": 0.18796402660075032, + "nauc_ndcg_at_5_diff1": 0.05116237763400455, + "nauc_ndcg_at_5_max": 0.3129319131162279, + "nauc_ndcg_at_5_std": 0.23382439268129476, + "nauc_precision_at_1000_diff1": -0.010364555909337887, + "nauc_precision_at_1000_max": 0.26106966765132666, + "nauc_precision_at_1000_std": 0.09074646816114265, + "nauc_precision_at_100_diff1": 0.03519509042455968, + "nauc_precision_at_100_max": 0.35074401395978816, + "nauc_precision_at_100_std": 0.09672696778714913, + "nauc_precision_at_10_diff1": 0.13716908147750662, + "nauc_precision_at_10_max": 0.47848750111796806, + "nauc_precision_at_10_std": 0.2114915928807798, + "nauc_precision_at_1_diff1": -0.5069761202039174, + "nauc_precision_at_1_max": -0.07284679366782934, + "nauc_precision_at_1_std": 0.3539039441910383, + "nauc_precision_at_20_diff1": 0.14360075127448352, + "nauc_precision_at_20_max": 0.46239249855252584, + "nauc_precision_at_20_std": 0.1256040557524748, + "nauc_precision_at_3_diff1": 0.053465700742330764, + "nauc_precision_at_3_max": 0.18355245505768703, + "nauc_precision_at_3_std": 0.14729451748501907, + "nauc_precision_at_5_diff1": 0.10861080033007477, + "nauc_precision_at_5_max": 0.3753486794477829, + "nauc_precision_at_5_std": 0.22415215839539104, + "nauc_recall_at_1000_diff1": -0.010364555909337153, + "nauc_recall_at_1000_max": 0.2610696676513276, + "nauc_recall_at_1000_std": 0.09074646816114326, + "nauc_recall_at_100_diff1": 0.035195090424559476, + "nauc_recall_at_100_max": 0.350744013959788, + "nauc_recall_at_100_std": 0.09672696778714893, + "nauc_recall_at_10_diff1": 0.1371690814775064, + "nauc_recall_at_10_max": 0.478487501117968, + "nauc_recall_at_10_std": 0.2114915928807799, + "nauc_recall_at_1_diff1": -0.5069761202039174, + "nauc_recall_at_1_max": -0.07284679366782934, + "nauc_recall_at_1_std": 0.3539039441910383, + "nauc_recall_at_20_diff1": 0.1436007512744835, + "nauc_recall_at_20_max": 0.4623924985525256, + "nauc_recall_at_20_std": 0.12560405575247477, + "nauc_recall_at_3_diff1": 0.05346570074233078, + "nauc_recall_at_3_max": 0.1835524550576871, + "nauc_recall_at_3_std": 0.14729451748501923, + "nauc_recall_at_5_diff1": 0.10861080033007477, + "nauc_recall_at_5_max": 0.3753486794477827, + "nauc_recall_at_5_std": 0.22415215839539104, + "ndcg_at_1": 0.0015, + "ndcg_at_10": 0.01073, + "ndcg_at_100": 0.03221, + "ndcg_at_1000": 0.07229, + "ndcg_at_20": 0.0166, + "ndcg_at_3": 0.00489, + "ndcg_at_5": 0.00728, + "precision_at_1": 0.0015, + "precision_at_10": 0.0024, + "precision_at_100": 0.00136, + "precision_at_1000": 0.00048, + "precision_at_20": 0.00237, + "precision_at_3": 0.0025, + "precision_at_5": 0.00265, + "recall_at_1": 0.0015, + "recall_at_10": 0.024, + "recall_at_100": 0.13575, + "recall_at_1000": 0.47775, + "recall_at_20": 0.0475, + "recall_at_3": 0.0075, + "recall_at_5": 0.01325 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL2Fact.json b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL2Fact.json new file mode 100644 index 000000000..e094dd654 --- /dev/null +++ b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL2Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 24.800501346588135, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.17234, + "map_at_1": 0.07282, + "map_at_10": 0.13437, + "map_at_100": 0.14422, + "map_at_1000": 0.14523, + "map_at_20": 0.13925, + "map_at_3": 0.1117, + "map_at_5": 0.12408, + "mrr_at_1": 0.07281823235130629, + "mrr_at_10": 0.13437160856560554, + "mrr_at_100": 0.1442238816419011, + "mrr_at_1000": 0.14522968594838015, + "mrr_at_20": 0.13925479430825577, + "mrr_at_3": 0.11169785683404355, + "mrr_at_5": 0.12408436785868728, + "nauc_map_at_1000_diff1": -0.023341555299501247, + "nauc_map_at_1000_max": -0.1432763272373582, + "nauc_map_at_1000_std": 0.04116132683798019, + "nauc_map_at_100_diff1": -0.02341493515384485, + "nauc_map_at_100_max": -0.14322311462163648, + "nauc_map_at_100_std": 0.04135222316276078, + "nauc_map_at_10_diff1": -0.015747231245913065, + "nauc_map_at_10_max": -0.13046559817769754, + "nauc_map_at_10_std": 0.03133853057541516, + "nauc_map_at_1_diff1": 0.027254277795296683, + "nauc_map_at_1_max": -0.13287748172989616, + "nauc_map_at_1_std": 0.0025000652732769524, + "nauc_map_at_20_diff1": -0.01965791414443642, + "nauc_map_at_20_max": -0.13666162166461332, + "nauc_map_at_20_std": 0.03559944348941767, + "nauc_map_at_3_diff1": -0.001825169816404469, + "nauc_map_at_3_max": -0.11783170616235894, + "nauc_map_at_3_std": 0.01700966247005145, + "nauc_map_at_5_diff1": -0.008857124499499224, + "nauc_map_at_5_max": -0.12273263621547953, + "nauc_map_at_5_std": 0.02894213827405866, + "nauc_mrr_at_1000_diff1": -0.023341555299501247, + "nauc_mrr_at_1000_max": -0.1432763272373582, + "nauc_mrr_at_1000_std": 0.04116132683798019, + "nauc_mrr_at_100_diff1": -0.02341493515384485, + "nauc_mrr_at_100_max": -0.14322311462163648, + "nauc_mrr_at_100_std": 0.04135222316276078, + "nauc_mrr_at_10_diff1": -0.015747231245913065, + "nauc_mrr_at_10_max": -0.13046559817769754, + "nauc_mrr_at_10_std": 0.03133853057541516, + "nauc_mrr_at_1_diff1": 0.027254277795296683, + "nauc_mrr_at_1_max": -0.13287748172989616, + "nauc_mrr_at_1_std": 0.0025000652732769524, + "nauc_mrr_at_20_diff1": -0.01965791414443642, + "nauc_mrr_at_20_max": -0.13666162166461332, + "nauc_mrr_at_20_std": 0.03559944348941767, + "nauc_mrr_at_3_diff1": -0.001825169816404469, + "nauc_mrr_at_3_max": -0.11783170616235894, + "nauc_mrr_at_3_std": 0.01700966247005145, + "nauc_mrr_at_5_diff1": -0.008857124499499224, + "nauc_mrr_at_5_max": -0.12273263621547953, + "nauc_mrr_at_5_std": 0.02894213827405866, + "nauc_ndcg_at_1000_diff1": -0.06424313045673512, + "nauc_ndcg_at_1000_max": -0.19692497307734272, + "nauc_ndcg_at_1000_std": 0.08496825389522297, + "nauc_ndcg_at_100_diff1": -0.06577378294431122, + "nauc_ndcg_at_100_max": -0.19603658088641876, + "nauc_ndcg_at_100_std": 0.09590216716067357, + "nauc_ndcg_at_10_diff1": -0.032011613684346865, + "nauc_ndcg_at_10_max": -0.1378960553717509, + "nauc_ndcg_at_10_std": 0.044448335060522155, + "nauc_ndcg_at_1_diff1": 0.027254277795296683, + "nauc_ndcg_at_1_max": -0.13287748172989616, + "nauc_ndcg_at_1_std": 0.0025000652732769524, + "nauc_ndcg_at_20_diff1": -0.04390874636746493, + "nauc_ndcg_at_20_max": -0.15631660972070457, + "nauc_ndcg_at_20_std": 0.05793105433323184, + "nauc_ndcg_at_3_diff1": -0.008490122562627562, + "nauc_ndcg_at_3_max": -0.11408152756765327, + "nauc_ndcg_at_3_std": 0.021616444441209363, + "nauc_ndcg_at_5_diff1": -0.018898012849085242, + "nauc_ndcg_at_5_max": -0.12226729399376482, + "nauc_ndcg_at_5_std": 0.03995861237972247, + "nauc_precision_at_1000_diff1": -0.2597318923902982, + "nauc_precision_at_1000_max": -0.5000154770620001, + "nauc_precision_at_1000_std": 0.27147199069723343, + "nauc_precision_at_100_diff1": -0.17899374730200124, + "nauc_precision_at_100_max": -0.35608733742043974, + "nauc_precision_at_100_std": 0.257542658612006, + "nauc_precision_at_10_diff1": -0.0628996094203503, + "nauc_precision_at_10_max": -0.1544196316075447, + "nauc_precision_at_10_std": 0.06924194321106457, + "nauc_precision_at_1_diff1": 0.027254277795296683, + "nauc_precision_at_1_max": -0.13287748172989616, + "nauc_precision_at_1_std": 0.0025000652732769524, + "nauc_precision_at_20_diff1": -0.09308345821236005, + "nauc_precision_at_20_max": -0.20141607168164644, + "nauc_precision_at_20_std": 0.10447134927558155, + "nauc_precision_at_3_diff1": -0.02266075085875917, + "nauc_precision_at_3_max": -0.10604077233060344, + "nauc_precision_at_3_std": 0.03169709618729765, + "nauc_precision_at_5_diff1": -0.038567623568294074, + "nauc_precision_at_5_max": -0.12207356318711393, + "nauc_precision_at_5_std": 0.0623615125440883, + "nauc_recall_at_1000_diff1": -0.25973189239029754, + "nauc_recall_at_1000_max": -0.5000154770620012, + "nauc_recall_at_1000_std": 0.27147199069723404, + "nauc_recall_at_100_diff1": -0.1789937473020014, + "nauc_recall_at_100_max": -0.35608733742043996, + "nauc_recall_at_100_std": 0.2575426586120054, + "nauc_recall_at_10_diff1": -0.0628996094203503, + "nauc_recall_at_10_max": -0.1544196316075446, + "nauc_recall_at_10_std": 0.06924194321106447, + "nauc_recall_at_1_diff1": 0.027254277795296683, + "nauc_recall_at_1_max": -0.13287748172989616, + "nauc_recall_at_1_std": 0.0025000652732769524, + "nauc_recall_at_20_diff1": -0.09308345821236001, + "nauc_recall_at_20_max": -0.20141607168164655, + "nauc_recall_at_20_std": 0.10447134927558127, + "nauc_recall_at_3_diff1": -0.0226607508587593, + "nauc_recall_at_3_max": -0.10604077233060348, + "nauc_recall_at_3_std": 0.03169709618729752, + "nauc_recall_at_5_diff1": -0.03856762356829424, + "nauc_recall_at_5_max": -0.12207356318711417, + "nauc_recall_at_5_std": 0.062361512544087984, + "ndcg_at_1": 0.07282, + "ndcg_at_10": 0.17234, + "ndcg_at_100": 0.22741, + "ndcg_at_1000": 0.25801, + "ndcg_at_20": 0.19007, + "ndcg_at_3": 0.12485, + "ndcg_at_5": 0.14727, + "precision_at_1": 0.07282, + "precision_at_10": 0.02955, + "precision_at_100": 0.0057, + "precision_at_1000": 0.00082, + "precision_at_20": 0.01828, + "precision_at_3": 0.05435, + "precision_at_5": 0.04354, + "recall_at_1": 0.07282, + "recall_at_10": 0.29553, + "recall_at_100": 0.56976, + "recall_at_1000": 0.81934, + "recall_at_20": 0.36557, + "recall_at_3": 0.16305, + "recall_at_5": 0.21771 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL2Pure.json b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL2Pure.json new file mode 100644 index 000000000..92ee69432 --- /dev/null +++ b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL2Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 11.105794429779053, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01291, + "map_at_1": 0.00296, + "map_at_10": 0.00865, + "map_at_100": 0.0118, + "map_at_1000": 0.01299, + "map_at_20": 0.00975, + "map_at_3": 0.00615, + "map_at_5": 0.00717, + "mrr_at_1": 0.002964609968501019, + "mrr_at_10": 0.008652146548199922, + "mrr_at_100": 0.011796953236244828, + "mrr_at_1000": 0.012989497645381159, + "mrr_at_20": 0.009750626539322384, + "mrr_at_3": 0.006145389413871901, + "mrr_at_5": 0.0071737384966956965, + "nauc_map_at_1000_diff1": -0.02443191930081502, + "nauc_map_at_1000_max": -0.00790844482673011, + "nauc_map_at_1000_std": 0.25629561242213894, + "nauc_map_at_100_diff1": -0.020449380600086928, + "nauc_map_at_100_max": -0.007534371004583164, + "nauc_map_at_100_std": 0.25468641523277524, + "nauc_map_at_10_diff1": -0.008256693694761142, + "nauc_map_at_10_max": -0.0006074989587536259, + "nauc_map_at_10_std": 0.29674036589144825, + "nauc_map_at_1_diff1": -0.13683209290464454, + "nauc_map_at_1_max": -0.18486290886193638, + "nauc_map_at_1_std": 0.36663767316763907, + "nauc_map_at_20_diff1": -0.009254338561976471, + "nauc_map_at_20_max": 0.0012658422838981178, + "nauc_map_at_20_std": 0.27249386904928163, + "nauc_map_at_3_diff1": -0.01678166588969551, + "nauc_map_at_3_max": -0.017259325163956635, + "nauc_map_at_3_std": 0.343478610538797, + "nauc_map_at_5_diff1": -0.00555390972262987, + "nauc_map_at_5_max": -0.00026665699393350087, + "nauc_map_at_5_std": 0.3356017858689962, + "nauc_mrr_at_1000_diff1": -0.02443191930081502, + "nauc_mrr_at_1000_max": -0.00790844482673011, + "nauc_mrr_at_1000_std": 0.25629561242213894, + "nauc_mrr_at_100_diff1": -0.020449380600086928, + "nauc_mrr_at_100_max": -0.007534371004583164, + "nauc_mrr_at_100_std": 0.25468641523277524, + "nauc_mrr_at_10_diff1": -0.008256693694761142, + "nauc_mrr_at_10_max": -0.0006074989587536259, + "nauc_mrr_at_10_std": 0.29674036589144825, + "nauc_mrr_at_1_diff1": -0.13683209290464454, + "nauc_mrr_at_1_max": -0.18486290886193638, + "nauc_mrr_at_1_std": 0.36663767316763907, + "nauc_mrr_at_20_diff1": -0.009254338561976471, + "nauc_mrr_at_20_max": 0.0012658422838981178, + "nauc_mrr_at_20_std": 0.27249386904928163, + "nauc_mrr_at_3_diff1": -0.01678166588969551, + "nauc_mrr_at_3_max": -0.017259325163956635, + "nauc_mrr_at_3_std": 0.343478610538797, + "nauc_mrr_at_5_diff1": -0.00555390972262987, + "nauc_mrr_at_5_max": -0.00026665699393350087, + "nauc_mrr_at_5_std": 0.3356017858689962, + "nauc_ndcg_at_1000_diff1": -0.06598194230105038, + "nauc_ndcg_at_1000_max": -0.012270829621222347, + "nauc_ndcg_at_1000_std": 0.2401402536898259, + "nauc_ndcg_at_100_diff1": -0.03345731274020595, + "nauc_ndcg_at_100_max": -0.013335468455598035, + "nauc_ndcg_at_100_std": 0.2061077557465, + "nauc_ndcg_at_10_diff1": 0.0032717673477353575, + "nauc_ndcg_at_10_max": 0.022100558263427238, + "nauc_ndcg_at_10_std": 0.26734736660419123, + "nauc_ndcg_at_1_diff1": -0.13683209290464454, + "nauc_ndcg_at_1_max": -0.18486290886193638, + "nauc_ndcg_at_1_std": 0.36663767316763907, + "nauc_ndcg_at_20_diff1": -0.001403993231200603, + "nauc_ndcg_at_20_max": 0.017947947413485068, + "nauc_ndcg_at_20_std": 0.22231233652477844, + "nauc_ndcg_at_3_diff1": 0.0020852313993360324, + "nauc_ndcg_at_3_max": 0.011668450008678484, + "nauc_ndcg_at_3_std": 0.3410893739777248, + "nauc_ndcg_at_5_diff1": 0.015941530258194368, + "nauc_ndcg_at_5_max": 0.030658088323720974, + "nauc_ndcg_at_5_std": 0.3304320261312386, + "nauc_precision_at_1000_diff1": -0.09552775706917073, + "nauc_precision_at_1000_max": -0.015862554122110704, + "nauc_precision_at_1000_std": 0.25399313989504607, + "nauc_precision_at_100_diff1": -0.04348918437344586, + "nauc_precision_at_100_max": -0.022060680407863898, + "nauc_precision_at_100_std": 0.1891181808120841, + "nauc_precision_at_10_diff1": 0.01245507916215785, + "nauc_precision_at_10_max": 0.04383503378275957, + "nauc_precision_at_10_std": 0.23150340769473954, + "nauc_precision_at_1_diff1": -0.13683209290464454, + "nauc_precision_at_1_max": -0.18486290886193638, + "nauc_precision_at_1_std": 0.36663767316763907, + "nauc_precision_at_20_diff1": 0.002039416730827059, + "nauc_precision_at_20_max": 0.027108491447878153, + "nauc_precision_at_20_std": 0.17367292224675238, + "nauc_precision_at_3_diff1": 0.03279943201461434, + "nauc_precision_at_3_max": 0.05919846744947032, + "nauc_precision_at_3_std": 0.33741115861887744, + "nauc_precision_at_5_diff1": 0.04629967493845306, + "nauc_precision_at_5_max": 0.0739023418453215, + "nauc_precision_at_5_std": 0.323008612815724, + "nauc_recall_at_1000_diff1": -0.09552775706917058, + "nauc_recall_at_1000_max": -0.015862554122110333, + "nauc_recall_at_1000_std": 0.25399313989504685, + "nauc_recall_at_100_diff1": -0.043489184373445886, + "nauc_recall_at_100_max": -0.022060680407863884, + "nauc_recall_at_100_std": 0.18911818081208398, + "nauc_recall_at_10_diff1": 0.012455079162157717, + "nauc_recall_at_10_max": 0.0438350337827594, + "nauc_recall_at_10_std": 0.23150340769473926, + "nauc_recall_at_1_diff1": -0.13683209290464454, + "nauc_recall_at_1_max": -0.18486290886193638, + "nauc_recall_at_1_std": 0.36663767316763907, + "nauc_recall_at_20_diff1": 0.0020394167308270318, + "nauc_recall_at_20_max": 0.027108491447877945, + "nauc_recall_at_20_std": 0.17367292224675238, + "nauc_recall_at_3_diff1": 0.03279943201461403, + "nauc_recall_at_3_max": 0.05919846744947008, + "nauc_recall_at_3_std": 0.33741115861887705, + "nauc_recall_at_5_diff1": 0.04629967493845291, + "nauc_recall_at_5_max": 0.0739023418453212, + "nauc_recall_at_5_std": 0.32300861281572385, + "ndcg_at_1": 0.00296, + "ndcg_at_10": 0.01291, + "ndcg_at_100": 0.03394, + "ndcg_at_1000": 0.07577, + "ndcg_at_20": 0.01693, + "ndcg_at_3": 0.0074, + "ndcg_at_5": 0.00929, + "precision_at_1": 0.00296, + "precision_at_10": 0.00271, + "precision_at_100": 0.00139, + "precision_at_1000": 0.00049, + "precision_at_20": 0.00215, + "precision_at_3": 0.00371, + "precision_at_5": 0.00315, + "recall_at_1": 0.00296, + "recall_at_10": 0.02705, + "recall_at_100": 0.13934, + "recall_at_1000": 0.49101, + "recall_at_20": 0.04299, + "recall_at_3": 0.01112, + "recall_at_5": 0.01575 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL3Fact.json b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL3Fact.json new file mode 100644 index 000000000..6a5a10c86 --- /dev/null +++ b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL3Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 21.662900924682617, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.13364, + "map_at_1": 0.02756, + "map_at_10": 0.09334, + "map_at_100": 0.10468, + "map_at_1000": 0.10569, + "map_at_20": 0.09964, + "map_at_3": 0.06936, + "map_at_5": 0.08225, + "mrr_at_1": 0.027564392227745142, + "mrr_at_10": 0.09334398467927602, + "mrr_at_100": 0.10467902958467411, + "mrr_at_1000": 0.10569171004053267, + "mrr_at_20": 0.09964094900375037, + "mrr_at_3": 0.06936285585178491, + "mrr_at_5": 0.08225259828287367, + "nauc_map_at_1000_diff1": -0.053305016238523975, + "nauc_map_at_1000_max": -0.054306114039839114, + "nauc_map_at_1000_std": 0.14995388967370177, + "nauc_map_at_100_diff1": -0.05305219914605028, + "nauc_map_at_100_max": -0.0543555636074386, + "nauc_map_at_100_std": 0.15059378633757087, + "nauc_map_at_10_diff1": -0.050027829736358456, + "nauc_map_at_10_max": -0.04145020275982021, + "nauc_map_at_10_std": 0.12945812554151087, + "nauc_map_at_1_diff1": -0.21793742490399207, + "nauc_map_at_1_max": -0.11194686116190082, + "nauc_map_at_1_std": 0.058603973997665364, + "nauc_map_at_20_diff1": -0.05106622263314463, + "nauc_map_at_20_max": -0.04736328154054428, + "nauc_map_at_20_std": 0.14095548041533468, + "nauc_map_at_3_diff1": -0.04823541203444017, + "nauc_map_at_3_max": -0.022665308405938875, + "nauc_map_at_3_std": 0.1050648019487536, + "nauc_map_at_5_diff1": -0.049524761977694946, + "nauc_map_at_5_max": -0.03515905861658748, + "nauc_map_at_5_std": 0.1239854065822755, + "nauc_mrr_at_1000_diff1": -0.05330507331483881, + "nauc_mrr_at_1000_max": -0.05430617125220653, + "nauc_mrr_at_1000_std": 0.14995435932699921, + "nauc_mrr_at_100_diff1": -0.0530522538945697, + "nauc_mrr_at_100_max": -0.05435561853616601, + "nauc_mrr_at_100_std": 0.15059425190571885, + "nauc_mrr_at_10_diff1": -0.050027829736358456, + "nauc_mrr_at_10_max": -0.04145020275982021, + "nauc_mrr_at_10_std": 0.12945812554151087, + "nauc_mrr_at_1_diff1": -0.21793742490399207, + "nauc_mrr_at_1_max": -0.11194686116190082, + "nauc_mrr_at_1_std": 0.058603973997665364, + "nauc_mrr_at_20_diff1": -0.05106622263314463, + "nauc_mrr_at_20_max": -0.04736328154054428, + "nauc_mrr_at_20_std": 0.14095548041533468, + "nauc_mrr_at_3_diff1": -0.04823541203444017, + "nauc_mrr_at_3_max": -0.022665308405938875, + "nauc_mrr_at_3_std": 0.1050648019487536, + "nauc_mrr_at_5_diff1": -0.049524761977694946, + "nauc_mrr_at_5_max": -0.03515905861658748, + "nauc_mrr_at_5_std": 0.1239854065822755, + "nauc_ndcg_at_1000_diff1": -0.05632732998860106, + "nauc_ndcg_at_1000_max": -0.09876494566182967, + "nauc_ndcg_at_1000_std": 0.21186500162519414, + "nauc_ndcg_at_100_diff1": -0.05154060197319322, + "nauc_ndcg_at_100_max": -0.09854255588004471, + "nauc_ndcg_at_100_std": 0.2281848566789312, + "nauc_ndcg_at_10_diff1": -0.03706597457709091, + "nauc_ndcg_at_10_max": -0.04309943912562786, + "nauc_ndcg_at_10_std": 0.14765477721922302, + "nauc_ndcg_at_1_diff1": -0.21793742490399207, + "nauc_ndcg_at_1_max": -0.11194686116190082, + "nauc_ndcg_at_1_std": 0.058603973997665364, + "nauc_ndcg_at_20_diff1": -0.04066643036016427, + "nauc_ndcg_at_20_max": -0.059202291564267866, + "nauc_ndcg_at_20_std": 0.1778214406508513, + "nauc_ndcg_at_3_diff1": -0.03003988403841928, + "nauc_ndcg_at_3_max": -0.011180651926676215, + "nauc_ndcg_at_3_std": 0.11163659216570025, + "nauc_ndcg_at_5_diff1": -0.03502074613030481, + "nauc_ndcg_at_5_max": -0.030991410680821053, + "nauc_ndcg_at_5_std": 0.13771375287015425, + "nauc_precision_at_1000_diff1": -0.10801984119324431, + "nauc_precision_at_1000_max": -0.2938944232783808, + "nauc_precision_at_1000_std": 0.39129009759170247, + "nauc_precision_at_100_diff1": -0.06380477792149579, + "nauc_precision_at_100_max": -0.2062862499451367, + "nauc_precision_at_100_std": 0.3926547385647123, + "nauc_precision_at_10_diff1": -0.02169680841524617, + "nauc_precision_at_10_max": -0.04851612832331218, + "nauc_precision_at_10_std": 0.17451629411396163, + "nauc_precision_at_1_diff1": -0.21793742490399207, + "nauc_precision_at_1_max": -0.11194686116190082, + "nauc_precision_at_1_std": 0.058603973997665364, + "nauc_precision_at_20_diff1": -0.030888144471197896, + "nauc_precision_at_20_max": -0.08277418293221608, + "nauc_precision_at_20_std": 0.23681409478530926, + "nauc_precision_at_3_diff1": -0.0002359800642435626, + "nauc_precision_at_3_max": 0.008050478676934177, + "nauc_precision_at_3_std": 0.12274998067539611, + "nauc_precision_at_5_diff1": -0.015176196059769971, + "nauc_precision_at_5_max": -0.02637346053238915, + "nauc_precision_at_5_std": 0.15920288212099373, + "nauc_recall_at_1000_diff1": -0.10801984119324486, + "nauc_recall_at_1000_max": -0.29389442327838156, + "nauc_recall_at_1000_std": 0.3912900975917031, + "nauc_recall_at_100_diff1": -0.06380477792149565, + "nauc_recall_at_100_max": -0.20628624994513667, + "nauc_recall_at_100_std": 0.39265473856471245, + "nauc_recall_at_10_diff1": -0.021696808415246207, + "nauc_recall_at_10_max": -0.04851612832331259, + "nauc_recall_at_10_std": 0.17451629411396155, + "nauc_recall_at_1_diff1": -0.21793742490399207, + "nauc_recall_at_1_max": -0.11194686116190082, + "nauc_recall_at_1_std": 0.058603973997665364, + "nauc_recall_at_20_diff1": -0.03088814447119829, + "nauc_recall_at_20_max": -0.08277418293221632, + "nauc_recall_at_20_std": 0.23681409478530915, + "nauc_recall_at_3_diff1": -0.00023598006424348217, + "nauc_recall_at_3_max": 0.008050478676934057, + "nauc_recall_at_3_std": 0.12274998067539607, + "nauc_recall_at_5_diff1": -0.015176196059770159, + "nauc_recall_at_5_max": -0.02637346053238916, + "nauc_recall_at_5_std": 0.1592028821209935, + "ndcg_at_1": 0.02756, + "ndcg_at_10": 0.13364, + "ndcg_at_100": 0.19353, + "ndcg_at_1000": 0.22456, + "ndcg_at_20": 0.1566, + "ndcg_at_3": 0.08364, + "ndcg_at_5": 0.10689, + "precision_at_1": 0.02756, + "precision_at_10": 0.02641, + "precision_at_100": 0.00555, + "precision_at_1000": 0.00081, + "precision_at_20": 0.01775, + "precision_at_3": 0.04172, + "precision_at_5": 0.03633, + "recall_at_1": 0.02756, + "recall_at_10": 0.26412, + "recall_at_100": 0.55513, + "recall_at_1000": 0.80863, + "recall_at_20": 0.35495, + "recall_at_3": 0.12517, + "recall_at_5": 0.18165 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL3Pure.json b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL3Pure.json new file mode 100644 index 000000000..5469d0afd --- /dev/null +++ b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/TempReasonL3Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 9.68999433517456, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.05205, + "map_at_1": 0.00113, + "map_at_10": 0.0312, + "map_at_100": 0.04011, + "map_at_1000": 0.04139, + "map_at_20": 0.03551, + "map_at_3": 0.018, + "map_at_5": 0.0245, + "mrr_at_1": 0.0011296882060551287, + "mrr_at_10": 0.031198850228448077, + "mrr_at_100": 0.04010579083542019, + "mrr_at_1000": 0.04139347060169085, + "mrr_at_20": 0.035505679562916295, + "mrr_at_3": 0.017999698749811718, + "mrr_at_5": 0.02449540593462871, + "nauc_map_at_1000_diff1": -0.05852003060583892, + "nauc_map_at_1000_max": 0.10615373642454473, + "nauc_map_at_1000_std": 0.3784809751829919, + "nauc_map_at_100_diff1": -0.058365271939151364, + "nauc_map_at_100_max": 0.10676875516625342, + "nauc_map_at_100_std": 0.37866578194103134, + "nauc_map_at_10_diff1": -0.05791231072471037, + "nauc_map_at_10_max": 0.11555146187475822, + "nauc_map_at_10_std": 0.34021049626409594, + "nauc_map_at_1_diff1": -0.39510201924907473, + "nauc_map_at_1_max": 0.0025459249960689333, + "nauc_map_at_1_std": -0.014377009164390905, + "nauc_map_at_20_diff1": -0.05880821688406617, + "nauc_map_at_20_max": 0.1094620863251422, + "nauc_map_at_20_std": 0.35651129221936473, + "nauc_map_at_3_diff1": -0.08079104546431225, + "nauc_map_at_3_max": 0.12149780327982275, + "nauc_map_at_3_std": 0.2910849009431667, + "nauc_map_at_5_diff1": -0.06542305274952133, + "nauc_map_at_5_max": 0.11834718877297312, + "nauc_map_at_5_std": 0.31184840681117776, + "nauc_mrr_at_1000_diff1": -0.05852027728996544, + "nauc_mrr_at_1000_max": 0.10615350317071191, + "nauc_mrr_at_1000_std": 0.378481053265143, + "nauc_mrr_at_100_diff1": -0.058365521790568156, + "nauc_mrr_at_100_max": 0.1067685176451309, + "nauc_mrr_at_100_std": 0.37866586371397987, + "nauc_mrr_at_10_diff1": -0.05791231072471037, + "nauc_mrr_at_10_max": 0.11555146187475822, + "nauc_mrr_at_10_std": 0.34021049626409594, + "nauc_mrr_at_1_diff1": -0.39510201924907473, + "nauc_mrr_at_1_max": 0.0025459249960689333, + "nauc_mrr_at_1_std": -0.014377009164390905, + "nauc_mrr_at_20_diff1": -0.05880821688406617, + "nauc_mrr_at_20_max": 0.1094620863251422, + "nauc_mrr_at_20_std": 0.35651129221936473, + "nauc_mrr_at_3_diff1": -0.08079104546431225, + "nauc_mrr_at_3_max": 0.12149780327982275, + "nauc_mrr_at_3_std": 0.2910849009431667, + "nauc_mrr_at_5_diff1": -0.06542305274952133, + "nauc_mrr_at_5_max": 0.11834718877297312, + "nauc_mrr_at_5_std": 0.31184840681117776, + "nauc_ndcg_at_1000_diff1": -0.04908475688665847, + "nauc_ndcg_at_1000_max": 0.0891696134093472, + "nauc_ndcg_at_1000_std": 0.45942341013748156, + "nauc_ndcg_at_100_diff1": -0.04790591439991855, + "nauc_ndcg_at_100_max": 0.09655202299809722, + "nauc_ndcg_at_100_std": 0.46323517279692966, + "nauc_ndcg_at_10_diff1": -0.04903133771082219, + "nauc_ndcg_at_10_max": 0.11686882569287746, + "nauc_ndcg_at_10_std": 0.3626659341903513, + "nauc_ndcg_at_1_diff1": -0.39510201924907473, + "nauc_ndcg_at_1_max": 0.0025459249960689333, + "nauc_ndcg_at_1_std": -0.014377009164390905, + "nauc_ndcg_at_20_diff1": -0.0506881965044742, + "nauc_ndcg_at_20_max": 0.10590575775744539, + "nauc_ndcg_at_20_std": 0.39261717576582067, + "nauc_ndcg_at_3_diff1": -0.07516842847431512, + "nauc_ndcg_at_3_max": 0.12425740943091701, + "nauc_ndcg_at_3_std": 0.2965613456786968, + "nauc_ndcg_at_5_diff1": -0.05817678846113857, + "nauc_ndcg_at_5_max": 0.12041619982514805, + "nauc_ndcg_at_5_std": 0.32214686967706, + "nauc_precision_at_1000_diff1": -0.03956665374778772, + "nauc_precision_at_1000_max": 0.05780410168374759, + "nauc_precision_at_1000_std": 0.5595424523202738, + "nauc_precision_at_100_diff1": -0.03871613590211941, + "nauc_precision_at_100_max": 0.08556196701500218, + "nauc_precision_at_100_std": 0.5461689003281183, + "nauc_precision_at_10_diff1": -0.04058047515733943, + "nauc_precision_at_10_max": 0.11815968358768765, + "nauc_precision_at_10_std": 0.38638582022922546, + "nauc_precision_at_1_diff1": -0.39510201924907473, + "nauc_precision_at_1_max": 0.0025459249960689333, + "nauc_precision_at_1_std": -0.014377009164390905, + "nauc_precision_at_20_diff1": -0.04404052378370376, + "nauc_precision_at_20_max": 0.10210766983191914, + "nauc_precision_at_20_std": 0.427039480697996, + "nauc_precision_at_3_diff1": -0.06800363869919726, + "nauc_precision_at_3_max": 0.12786949838138842, + "nauc_precision_at_3_std": 0.30354170569940614, + "nauc_precision_at_5_diff1": -0.05007700751467333, + "nauc_precision_at_5_max": 0.1227568912520956, + "nauc_precision_at_5_std": 0.33437837164452416, + "nauc_recall_at_1000_diff1": -0.03956665374778793, + "nauc_recall_at_1000_max": 0.057804101683746605, + "nauc_recall_at_1000_std": 0.5595424523202743, + "nauc_recall_at_100_diff1": -0.03871613590211949, + "nauc_recall_at_100_max": 0.08556196701500196, + "nauc_recall_at_100_std": 0.5461689003281182, + "nauc_recall_at_10_diff1": -0.04058047515733966, + "nauc_recall_at_10_max": 0.11815968358768744, + "nauc_recall_at_10_std": 0.3863858202292252, + "nauc_recall_at_1_diff1": -0.39510201924907473, + "nauc_recall_at_1_max": 0.0025459249960689333, + "nauc_recall_at_1_std": -0.014377009164390905, + "nauc_recall_at_20_diff1": -0.04404052378370395, + "nauc_recall_at_20_max": 0.10210766983191888, + "nauc_recall_at_20_std": 0.42703948069799585, + "nauc_recall_at_3_diff1": -0.06800363869919727, + "nauc_recall_at_3_max": 0.12786949838138856, + "nauc_recall_at_3_std": 0.3035417056994062, + "nauc_recall_at_5_diff1": -0.050077007514673526, + "nauc_recall_at_5_max": 0.12275689125209559, + "nauc_recall_at_5_std": 0.33437837164452405, + "ndcg_at_1": 0.00113, + "ndcg_at_10": 0.05205, + "ndcg_at_100": 0.10201, + "ndcg_at_1000": 0.14266, + "ndcg_at_20": 0.06775, + "ndcg_at_3": 0.02401, + "ndcg_at_5": 0.03578, + "precision_at_1": 0.00113, + "precision_at_10": 0.01207, + "precision_at_100": 0.0037, + "precision_at_1000": 0.0007, + "precision_at_20": 0.00914, + "precision_at_3": 0.01386, + "precision_at_5": 0.01405, + "recall_at_1": 0.00113, + "recall_at_10": 0.12065, + "recall_at_100": 0.36963, + "recall_at_1000": 0.70334, + "recall_at_20": 0.18278, + "recall_at_3": 0.04157, + "recall_at_5": 0.07027 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/WinoGrande.json b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/WinoGrande.json new file mode 100644 index 000000000..8f6a461f2 --- /dev/null +++ b/results/bge-base-en-v1.5/a5beb1e3e68b9ab74eb54cfd186867f64f240e1a/WinoGrande.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 2.551337480545044, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.13762, + "map_at_1": 0.00947, + "map_at_10": 0.07916, + "map_at_100": 0.09727, + "map_at_1000": 0.09827, + "map_at_20": 0.08972, + "map_at_3": 0.03802, + "map_at_5": 0.05937, + "mrr_at_1": 0.009471191791633781, + "mrr_at_10": 0.07938073940441746, + "mrr_at_100": 0.09749620641279544, + "mrr_at_1000": 0.09849443153067806, + "mrr_at_20": 0.08994381718455077, + "mrr_at_3": 0.0386740331491713, + "mrr_at_5": 0.05990528808208374, + "nauc_map_at_1000_diff1": -0.05481787154997414, + "nauc_map_at_1000_max": -0.03161909308043464, + "nauc_map_at_1000_std": 0.05906341651106117, + "nauc_map_at_100_diff1": -0.05334521444951347, + "nauc_map_at_100_max": -0.03208524477607782, + "nauc_map_at_100_std": 0.058584078180577946, + "nauc_map_at_10_diff1": -0.05336631199680913, + "nauc_map_at_10_max": -0.028445890528511843, + "nauc_map_at_10_std": 0.05749881078133129, + "nauc_map_at_1_diff1": -0.4765349298331586, + "nauc_map_at_1_max": -0.030791941378733693, + "nauc_map_at_1_std": 0.27812040598556814, + "nauc_map_at_20_diff1": -0.05008837880173707, + "nauc_map_at_20_max": -0.027572384335826875, + "nauc_map_at_20_std": 0.05925448133346872, + "nauc_map_at_3_diff1": -0.1768981566117068, + "nauc_map_at_3_max": -0.038727672147925954, + "nauc_map_at_3_std": 0.03418756217863794, + "nauc_map_at_5_diff1": -0.09888197552756409, + "nauc_map_at_5_max": -0.02869768559056345, + "nauc_map_at_5_std": 0.03171986784845296, + "nauc_mrr_at_1000_diff1": -0.050907789494509297, + "nauc_mrr_at_1000_max": -0.029532277496721836, + "nauc_mrr_at_1000_std": 0.05839647800987551, + "nauc_mrr_at_100_diff1": -0.049472100007599586, + "nauc_mrr_at_100_max": -0.030014802636325645, + "nauc_mrr_at_100_std": 0.057923847442026416, + "nauc_mrr_at_10_diff1": -0.04960836339595183, + "nauc_mrr_at_10_max": -0.02644674545754746, + "nauc_mrr_at_10_std": 0.057038406508802555, + "nauc_mrr_at_1_diff1": -0.4765349298331586, + "nauc_mrr_at_1_max": -0.030791941378733693, + "nauc_mrr_at_1_std": 0.27812040598556814, + "nauc_mrr_at_20_diff1": -0.04634851384475873, + "nauc_mrr_at_20_max": -0.02557828756553607, + "nauc_mrr_at_20_std": 0.05862567418536405, + "nauc_mrr_at_3_diff1": -0.16202399448159163, + "nauc_mrr_at_3_max": -0.027225922381135755, + "nauc_mrr_at_3_std": 0.03155572682262683, + "nauc_mrr_at_5_diff1": -0.09323045987051927, + "nauc_mrr_at_5_max": -0.029253160977118116, + "nauc_mrr_at_5_std": 0.030721125492859824, + "nauc_ndcg_at_1000_diff1": -0.019902036353043686, + "nauc_ndcg_at_1000_max": -0.03633683219898558, + "nauc_ndcg_at_1000_std": 0.06635566573301492, + "nauc_ndcg_at_100_diff1": 0.005628310266290074, + "nauc_ndcg_at_100_max": -0.04665595814030099, + "nauc_ndcg_at_100_std": 0.061765719154427905, + "nauc_ndcg_at_10_diff1": -0.0018083299052853558, + "nauc_ndcg_at_10_max": -0.030370566083188492, + "nauc_ndcg_at_10_std": 0.05646359894255037, + "nauc_ndcg_at_1_diff1": -0.4765349298331586, + "nauc_ndcg_at_1_max": -0.030791941378733693, + "nauc_ndcg_at_1_std": 0.27812040598556814, + "nauc_ndcg_at_20_diff1": 0.007231391380035929, + "nauc_ndcg_at_20_max": -0.023538635697539757, + "nauc_ndcg_at_20_std": 0.06524404091094953, + "nauc_ndcg_at_3_diff1": -0.1504817248930046, + "nauc_ndcg_at_3_max": -0.0418403437323441, + "nauc_ndcg_at_3_std": 0.004987995305342811, + "nauc_ndcg_at_5_diff1": -0.066373863950637, + "nauc_ndcg_at_5_max": -0.02977315112692946, + "nauc_ndcg_at_5_std": 0.012920438539129239, + "nauc_precision_at_1000_diff1": 0.0018102225312471758, + "nauc_precision_at_1000_max": -0.04993073211651241, + "nauc_precision_at_1000_std": 0.32982327831978503, + "nauc_precision_at_100_diff1": 0.11982888686995906, + "nauc_precision_at_100_max": -0.09453226173796951, + "nauc_precision_at_100_std": 0.07812164383730406, + "nauc_precision_at_10_diff1": 0.052986196232881984, + "nauc_precision_at_10_max": -0.032805945654326985, + "nauc_precision_at_10_std": 0.06101394873283485, + "nauc_precision_at_1_diff1": -0.4765349298331586, + "nauc_precision_at_1_max": -0.030791941378733693, + "nauc_precision_at_1_std": 0.27812040598556814, + "nauc_precision_at_20_diff1": 0.07118265887359863, + "nauc_precision_at_20_max": -0.015625362354289, + "nauc_precision_at_20_std": 0.08163510111502535, + "nauc_precision_at_3_diff1": -0.11708114530775977, + "nauc_precision_at_3_max": -0.046062926890806495, + "nauc_precision_at_3_std": -0.03284653484417385, + "nauc_precision_at_5_diff1": -0.03120854161158967, + "nauc_precision_at_5_max": -0.031054353061292488, + "nauc_precision_at_5_std": -0.006246108780428384, + "nauc_recall_at_1000_diff1": 0.0018102225312451703, + "nauc_recall_at_1000_max": -0.04993073211651433, + "nauc_recall_at_1000_std": 0.3298232783197853, + "nauc_recall_at_100_diff1": 0.11982888686995925, + "nauc_recall_at_100_max": -0.09453226173796932, + "nauc_recall_at_100_std": 0.07812164383730431, + "nauc_recall_at_10_diff1": 0.05298619623288179, + "nauc_recall_at_10_max": -0.03280594565432727, + "nauc_recall_at_10_std": 0.06101394873283493, + "nauc_recall_at_1_diff1": -0.4765349298331586, + "nauc_recall_at_1_max": -0.030791941378733693, + "nauc_recall_at_1_std": 0.27812040598556814, + "nauc_recall_at_20_diff1": 0.07118265887359841, + "nauc_recall_at_20_max": -0.015625362354289237, + "nauc_recall_at_20_std": 0.08163510111502542, + "nauc_recall_at_3_diff1": -0.11708114530775966, + "nauc_recall_at_3_max": -0.04606292689080635, + "nauc_recall_at_3_std": -0.03284653484417377, + "nauc_recall_at_5_diff1": -0.031208541611589907, + "nauc_recall_at_5_max": -0.031054353061292696, + "nauc_recall_at_5_std": -0.006246108780428262, + "ndcg_at_1": 0.00947, + "ndcg_at_10": 0.13762, + "ndcg_at_100": 0.23084, + "ndcg_at_1000": 0.25644, + "ndcg_at_20": 0.17638, + "ndcg_at_3": 0.05107, + "ndcg_at_5": 0.08965, + "precision_at_1": 0.00947, + "precision_at_10": 0.03323, + "precision_at_100": 0.00779, + "precision_at_1000": 0.00098, + "precision_at_20": 0.02431, + "precision_at_3": 0.02999, + "precision_at_5": 0.03678, + "recall_at_1": 0.00947, + "recall_at_10": 0.33228, + "recall_at_100": 0.77901, + "recall_at_1000": 0.97869, + "recall_at_20": 0.48619, + "recall_at_3": 0.08998, + "recall_at_5": 0.1839 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/ARCChallenge.json b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/ARCChallenge.json new file mode 100644 index 000000000..20bbae6ac --- /dev/null +++ b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/ARCChallenge.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 10.723093748092651, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.08863, + "map_at_1": 0.03072, + "map_at_10": 0.06625, + "map_at_100": 0.07499, + "map_at_1000": 0.07633, + "map_at_20": 0.07036, + "map_at_3": 0.05219, + "map_at_5": 0.05995, + "mrr_at_1": 0.030716723549488054, + "mrr_at_10": 0.06625460479982666, + "mrr_at_100": 0.074987510847297, + "mrr_at_1000": 0.07633397394986831, + "mrr_at_20": 0.07035530809368107, + "mrr_at_3": 0.05218998862343575, + "mrr_at_5": 0.05995449374288967, + "nauc_map_at_1000_diff1": -0.018833960504277367, + "nauc_map_at_1000_max": 0.05347091887214511, + "nauc_map_at_1000_std": -0.02669131209112025, + "nauc_map_at_100_diff1": -0.018874528784896163, + "nauc_map_at_100_max": 0.05359849414543082, + "nauc_map_at_100_std": -0.027669820569005264, + "nauc_map_at_10_diff1": -0.025608614686471617, + "nauc_map_at_10_max": 0.05508073316910348, + "nauc_map_at_10_std": -0.0350962825479151, + "nauc_map_at_1_diff1": -0.02669410635940023, + "nauc_map_at_1_max": 0.09011145552562388, + "nauc_map_at_1_std": 0.009899547328317502, + "nauc_map_at_20_diff1": -0.020578037537383142, + "nauc_map_at_20_max": 0.05681118519234166, + "nauc_map_at_20_std": -0.029706625993005668, + "nauc_map_at_3_diff1": -0.029284185538978408, + "nauc_map_at_3_max": 0.07448143010612926, + "nauc_map_at_3_std": -0.03697325171196355, + "nauc_map_at_5_diff1": -0.029725702189223057, + "nauc_map_at_5_max": 0.06398429867623603, + "nauc_map_at_5_std": -0.037764921128930005, + "nauc_mrr_at_1000_diff1": -0.01883346017700692, + "nauc_mrr_at_1000_max": 0.0534724851845147, + "nauc_mrr_at_1000_std": -0.026692922280104777, + "nauc_mrr_at_100_diff1": -0.018874262428054452, + "nauc_mrr_at_100_max": 0.05359933948998254, + "nauc_mrr_at_100_std": -0.027671140301104822, + "nauc_mrr_at_10_diff1": -0.025608614686471617, + "nauc_mrr_at_10_max": 0.05508073316910348, + "nauc_mrr_at_10_std": -0.0350962825479151, + "nauc_mrr_at_1_diff1": -0.02669410635940023, + "nauc_mrr_at_1_max": 0.09011145552562388, + "nauc_mrr_at_1_std": 0.009899547328317502, + "nauc_mrr_at_20_diff1": -0.020578037537383142, + "nauc_mrr_at_20_max": 0.05681118519234166, + "nauc_mrr_at_20_std": -0.029706625993005668, + "nauc_mrr_at_3_diff1": -0.029284185538978408, + "nauc_mrr_at_3_max": 0.07448143010612926, + "nauc_mrr_at_3_std": -0.03697325171196355, + "nauc_mrr_at_5_diff1": -0.029725702189223057, + "nauc_mrr_at_5_max": 0.06398429867623603, + "nauc_mrr_at_5_std": -0.037764921128930005, + "nauc_ndcg_at_1000_diff1": 0.0034849145731990893, + "nauc_ndcg_at_1000_max": 0.030889055715176247, + "nauc_ndcg_at_1000_std": 0.004660864658602623, + "nauc_ndcg_at_100_diff1": -0.0026701299273612193, + "nauc_ndcg_at_100_max": 0.036248859060157325, + "nauc_ndcg_at_100_std": -0.009802388561390383, + "nauc_ndcg_at_10_diff1": -0.018662632002905084, + "nauc_ndcg_at_10_max": 0.04659146606953084, + "nauc_ndcg_at_10_std": -0.037069711729169626, + "nauc_ndcg_at_1_diff1": -0.02669410635940023, + "nauc_ndcg_at_1_max": 0.09011145552562388, + "nauc_ndcg_at_1_std": 0.009899547328317502, + "nauc_ndcg_at_20_diff1": -0.005608669003707554, + "nauc_ndcg_at_20_max": 0.050142887116200276, + "nauc_ndcg_at_20_std": -0.02413345135506636, + "nauc_ndcg_at_3_diff1": -0.026234182563771098, + "nauc_ndcg_at_3_max": 0.07740094067426521, + "nauc_ndcg_at_3_std": -0.0405254423288232, + "nauc_ndcg_at_5_diff1": -0.025831974092600005, + "nauc_ndcg_at_5_max": 0.06280621937960855, + "nauc_ndcg_at_5_std": -0.04152257833374391, + "nauc_precision_at_1000_diff1": 0.06523993272729768, + "nauc_precision_at_1000_max": -0.03465237722025224, + "nauc_precision_at_1000_std": 0.1149036740959931, + "nauc_precision_at_100_diff1": 0.01714513491938749, + "nauc_precision_at_100_max": 0.009606953822825346, + "nauc_precision_at_100_std": 0.024473934194254535, + "nauc_precision_at_10_diff1": -0.007257381117265731, + "nauc_precision_at_10_max": 0.033123071058056286, + "nauc_precision_at_10_std": -0.03898333569562879, + "nauc_precision_at_1_diff1": -0.02669410635940023, + "nauc_precision_at_1_max": 0.09011145552562388, + "nauc_precision_at_1_std": 0.009899547328317502, + "nauc_precision_at_20_diff1": 0.0177039008090276, + "nauc_precision_at_20_max": 0.040914341831215784, + "nauc_precision_at_20_std": -0.013696040359271102, + "nauc_precision_at_3_diff1": -0.019773439068590856, + "nauc_precision_at_3_max": 0.0840816213141631, + "nauc_precision_at_3_std": -0.046166958345805746, + "nauc_precision_at_5_diff1": -0.01844522618106544, + "nauc_precision_at_5_max": 0.06144999829911358, + "nauc_precision_at_5_std": -0.046921408578522984, + "nauc_recall_at_1000_diff1": 0.06523993272729751, + "nauc_recall_at_1000_max": -0.034652377220252, + "nauc_recall_at_1000_std": 0.11490367409599307, + "nauc_recall_at_100_diff1": 0.017145134919387524, + "nauc_recall_at_100_max": 0.009606953822825077, + "nauc_recall_at_100_std": 0.02447393419425433, + "nauc_recall_at_10_diff1": -0.0072573811172659455, + "nauc_recall_at_10_max": 0.03312307105805614, + "nauc_recall_at_10_std": -0.03898333569562888, + "nauc_recall_at_1_diff1": -0.02669410635940023, + "nauc_recall_at_1_max": 0.09011145552562388, + "nauc_recall_at_1_std": 0.009899547328317502, + "nauc_recall_at_20_diff1": 0.017703900809027548, + "nauc_recall_at_20_max": 0.040914341831215756, + "nauc_recall_at_20_std": -0.013696040359271076, + "nauc_recall_at_3_diff1": -0.0197734390685908, + "nauc_recall_at_3_max": 0.08408162131416301, + "nauc_recall_at_3_std": -0.046166958345805864, + "nauc_recall_at_5_diff1": -0.018445226181065397, + "nauc_recall_at_5_max": 0.06144999829911354, + "nauc_recall_at_5_std": -0.04692140857852314, + "ndcg_at_1": 0.03072, + "ndcg_at_10": 0.08863, + "ndcg_at_100": 0.13851, + "ndcg_at_1000": 0.17906, + "ndcg_at_20": 0.10368, + "ndcg_at_3": 0.05957, + "ndcg_at_5": 0.07342, + "precision_at_1": 0.03072, + "precision_at_10": 0.01613, + "precision_at_100": 0.00411, + "precision_at_1000": 0.00074, + "precision_at_20": 0.01105, + "precision_at_3": 0.02702, + "precision_at_5": 0.02287, + "recall_at_1": 0.03072, + "recall_at_10": 0.16126, + "recall_at_100": 0.41126, + "recall_at_1000": 0.74147, + "recall_at_20": 0.22099, + "recall_at_3": 0.08106, + "recall_at_5": 0.11433 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/AlphaNLI.json b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/AlphaNLI.json new file mode 100644 index 000000000..e41e77f3e --- /dev/null +++ b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/AlphaNLI.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 164.51641082763672, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.00859, + "map_at_1": 0.0, + "map_at_10": 0.00454, + "map_at_100": 0.00803, + "map_at_1000": 0.00893, + "map_at_20": 0.00608, + "map_at_3": 0.00152, + "map_at_5": 0.00315, + "mrr_at_1": 0.0, + "mrr_at_10": 0.0045409569397820045, + "mrr_at_100": 0.00802856671479267, + "mrr_at_1000": 0.008930458822367822, + "mrr_at_20": 0.0060825119079267916, + "mrr_at_3": 0.0015230635335073978, + "mrr_at_5": 0.0031549173194081815, + "nauc_map_at_1000_diff1": -0.05811746354120348, + "nauc_map_at_1000_max": -0.13950751051697377, + "nauc_map_at_1000_std": 0.08409034437779077, + "nauc_map_at_100_diff1": -0.05988967750790636, + "nauc_map_at_100_max": -0.14341133538658704, + "nauc_map_at_100_std": 0.08676188666161246, + "nauc_map_at_10_diff1": -0.08997459480171606, + "nauc_map_at_10_max": -0.20390407885608888, + "nauc_map_at_10_std": 0.11380153624484698, + "nauc_map_at_1_diff1": NaN, + "nauc_map_at_1_max": NaN, + "nauc_map_at_1_std": NaN, + "nauc_map_at_20_diff1": -0.0777478217532052, + "nauc_map_at_20_max": -0.18145105075407145, + "nauc_map_at_20_std": 0.08417887830751848, + "nauc_map_at_3_diff1": 0.00654661709218347, + "nauc_map_at_3_max": -0.2295605442639443, + "nauc_map_at_3_std": -0.009854802179821633, + "nauc_map_at_5_diff1": -0.05644927602898418, + "nauc_map_at_5_max": -0.2071572697011192, + "nauc_map_at_5_std": 0.10222275468905447, + "nauc_mrr_at_1000_diff1": -0.05811746354120348, + "nauc_mrr_at_1000_max": -0.13950751051697377, + "nauc_mrr_at_1000_std": 0.08409034437779077, + "nauc_mrr_at_100_diff1": -0.05988967750790636, + "nauc_mrr_at_100_max": -0.14341133538658704, + "nauc_mrr_at_100_std": 0.08676188666161246, + "nauc_mrr_at_10_diff1": -0.08997459480171606, + "nauc_mrr_at_10_max": -0.20390407885608888, + "nauc_mrr_at_10_std": 0.11380153624484698, + "nauc_mrr_at_1_diff1": NaN, + "nauc_mrr_at_1_max": NaN, + "nauc_mrr_at_1_std": NaN, + "nauc_mrr_at_20_diff1": -0.0777478217532052, + "nauc_mrr_at_20_max": -0.18145105075407145, + "nauc_mrr_at_20_std": 0.08417887830751848, + "nauc_mrr_at_3_diff1": 0.00654661709218347, + "nauc_mrr_at_3_max": -0.2295605442639443, + "nauc_mrr_at_3_std": -0.009854802179821633, + "nauc_mrr_at_5_diff1": -0.05644927602898418, + "nauc_mrr_at_5_max": -0.2071572697011192, + "nauc_mrr_at_5_std": 0.10222275468905447, + "nauc_ndcg_at_1000_diff1": -0.024066700930842854, + "nauc_ndcg_at_1000_max": -0.06756578269066983, + "nauc_ndcg_at_1000_std": 0.06757167066197091, + "nauc_ndcg_at_100_diff1": -0.02922067330738863, + "nauc_ndcg_at_100_max": -0.083988299951257, + "nauc_ndcg_at_100_std": 0.0660233891075442, + "nauc_ndcg_at_10_diff1": -0.10021241216437139, + "nauc_ndcg_at_10_max": -0.1969176773631187, + "nauc_ndcg_at_10_std": 0.1124314388079547, + "nauc_ndcg_at_1_diff1": NaN, + "nauc_ndcg_at_1_max": NaN, + "nauc_ndcg_at_1_std": NaN, + "nauc_ndcg_at_20_diff1": -0.07755207515309054, + "nauc_ndcg_at_20_max": -0.16111363192774825, + "nauc_ndcg_at_20_std": 0.06592041876870637, + "nauc_ndcg_at_3_diff1": -0.011253555301738912, + "nauc_ndcg_at_3_max": -0.23168553031195266, + "nauc_ndcg_at_3_std": -0.03832005267446098, + "nauc_ndcg_at_5_diff1": -0.06947430570045438, + "nauc_ndcg_at_5_max": -0.2001531103342405, + "nauc_ndcg_at_5_std": 0.10669078867330037, + "nauc_precision_at_1000_diff1": -0.006541984895950116, + "nauc_precision_at_1000_max": -0.036410747959933994, + "nauc_precision_at_1000_std": 0.06331620735053162, + "nauc_precision_at_100_diff1": -0.010051075294483553, + "nauc_precision_at_100_max": -0.054800121374265105, + "nauc_precision_at_100_std": 0.05351077175065187, + "nauc_precision_at_10_diff1": -0.10647840197110614, + "nauc_precision_at_10_max": -0.19069481804559435, + "nauc_precision_at_10_std": 0.11042527153265393, + "nauc_precision_at_1_diff1": NaN, + "nauc_precision_at_1_max": NaN, + "nauc_precision_at_1_std": NaN, + "nauc_precision_at_20_diff1": -0.07476616119392165, + "nauc_precision_at_20_max": -0.14608060917408677, + "nauc_precision_at_20_std": 0.05221636851351203, + "nauc_precision_at_3_diff1": -0.03408882241616794, + "nauc_precision_at_3_max": -0.23441160638283792, + "nauc_precision_at_3_std": -0.07483720453902151, + "nauc_precision_at_5_diff1": -0.08121218297720838, + "nauc_precision_at_5_max": -0.1925642432110704, + "nauc_precision_at_5_std": 0.1127733291916226, + "nauc_recall_at_1000_diff1": -0.006541984895949962, + "nauc_recall_at_1000_max": -0.0364107479599339, + "nauc_recall_at_1000_std": 0.06331620735053187, + "nauc_recall_at_100_diff1": -0.010051075294483852, + "nauc_recall_at_100_max": -0.05480012137426548, + "nauc_recall_at_100_std": 0.053510771750651526, + "nauc_recall_at_10_diff1": -0.1064784019711062, + "nauc_recall_at_10_max": -0.19069481804559438, + "nauc_recall_at_10_std": 0.11042527153265383, + "nauc_recall_at_1_diff1": NaN, + "nauc_recall_at_1_max": NaN, + "nauc_recall_at_1_std": NaN, + "nauc_recall_at_20_diff1": -0.07476616119392178, + "nauc_recall_at_20_max": -0.14608060917408694, + "nauc_recall_at_20_std": 0.05221636851351186, + "nauc_recall_at_3_diff1": -0.03408882241616787, + "nauc_recall_at_3_max": -0.2344116063828379, + "nauc_recall_at_3_std": -0.07483720453902167, + "nauc_recall_at_5_diff1": -0.08121218297720827, + "nauc_recall_at_5_max": -0.1925642432110703, + "nauc_recall_at_5_std": 0.11277332919162274, + "ndcg_at_1": 0.0, + "ndcg_at_10": 0.00859, + "ndcg_at_100": 0.03018, + "ndcg_at_1000": 0.05869, + "ndcg_at_20": 0.01431, + "ndcg_at_3": 0.00213, + "ndcg_at_5": 0.00522, + "precision_at_1": 0.0, + "precision_at_10": 0.00222, + "precision_at_100": 0.00134, + "precision_at_1000": 0.00037, + "precision_at_20": 0.00225, + "precision_at_3": 0.00131, + "precision_at_5": 0.00235, + "recall_at_1": 0.0, + "recall_at_10": 0.02219, + "recall_at_100": 0.13446, + "recall_at_1000": 0.36945, + "recall_at_20": 0.04504, + "recall_at_3": 0.00392, + "recall_at_5": 0.01175 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/HellaSwag.json b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/HellaSwag.json new file mode 100644 index 000000000..bf0ee532a --- /dev/null +++ b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/HellaSwag.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 396.79186391830444, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.26238, + "map_at_1": 0.14509, + "map_at_10": 0.22144, + "map_at_100": 0.22913, + "map_at_1000": 0.22991, + "map_at_20": 0.22585, + "map_at_3": 0.19989, + "map_at_5": 0.2126, + "mrr_at_1": 0.1450906193985262, + "mrr_at_10": 0.22143568441118658, + "mrr_at_100": 0.22912897936710358, + "mrr_at_1000": 0.2299109646271593, + "mrr_at_20": 0.22584552747166847, + "mrr_at_3": 0.19989377945960168, + "mrr_at_5": 0.21260041160459345, + "nauc_map_at_1000_diff1": 0.32455194083905986, + "nauc_map_at_1000_max": 0.3786322349122283, + "nauc_map_at_1000_std": 0.15169531895010976, + "nauc_map_at_100_diff1": 0.3244851840014113, + "nauc_map_at_100_max": 0.37856041800822365, + "nauc_map_at_100_std": 0.15175756568266466, + "nauc_map_at_10_diff1": 0.3238878176844043, + "nauc_map_at_10_max": 0.373810310357729, + "nauc_map_at_10_std": 0.14481119276751814, + "nauc_map_at_1_diff1": 0.3514910552490034, + "nauc_map_at_1_max": 0.3259628876339468, + "nauc_map_at_1_std": 0.10566929130044017, + "nauc_map_at_20_diff1": 0.3240512129790747, + "nauc_map_at_20_max": 0.37710400109019593, + "nauc_map_at_20_std": 0.14891642815089962, + "nauc_map_at_3_diff1": 0.32585607609878714, + "nauc_map_at_3_max": 0.3580254654288487, + "nauc_map_at_3_std": 0.12887761509449372, + "nauc_map_at_5_diff1": 0.32456148156401327, + "nauc_map_at_5_max": 0.36815917382714997, + "nauc_map_at_5_std": 0.1377597421580578, + "nauc_mrr_at_1000_diff1": 0.32455194083905986, + "nauc_mrr_at_1000_max": 0.3786322349122283, + "nauc_mrr_at_1000_std": 0.15169531895010976, + "nauc_mrr_at_100_diff1": 0.3244851840014113, + "nauc_mrr_at_100_max": 0.37856041800822365, + "nauc_mrr_at_100_std": 0.15175756568266466, + "nauc_mrr_at_10_diff1": 0.3238878176844043, + "nauc_mrr_at_10_max": 0.373810310357729, + "nauc_mrr_at_10_std": 0.14481119276751814, + "nauc_mrr_at_1_diff1": 0.3514910552490034, + "nauc_mrr_at_1_max": 0.3259628876339468, + "nauc_mrr_at_1_std": 0.10566929130044017, + "nauc_mrr_at_20_diff1": 0.3240512129790747, + "nauc_mrr_at_20_max": 0.37710400109019593, + "nauc_mrr_at_20_std": 0.14891642815089962, + "nauc_mrr_at_3_diff1": 0.32585607609878714, + "nauc_mrr_at_3_max": 0.3580254654288487, + "nauc_mrr_at_3_std": 0.12887761509449372, + "nauc_mrr_at_5_diff1": 0.32456148156401327, + "nauc_mrr_at_5_max": 0.36815917382714997, + "nauc_mrr_at_5_std": 0.1377597421580578, + "nauc_ndcg_at_1000_diff1": 0.3217936869251408, + "nauc_ndcg_at_1000_max": 0.4212725889986294, + "nauc_ndcg_at_1000_std": 0.19729416295739272, + "nauc_ndcg_at_100_diff1": 0.3193568774140862, + "nauc_ndcg_at_100_max": 0.41967392192512504, + "nauc_ndcg_at_100_std": 0.19981871697772616, + "nauc_ndcg_at_10_diff1": 0.3168205309837404, + "nauc_ndcg_at_10_max": 0.3972612411326068, + "nauc_ndcg_at_10_std": 0.16650508846354672, + "nauc_ndcg_at_1_diff1": 0.3514910552490034, + "nauc_ndcg_at_1_max": 0.3259628876339468, + "nauc_ndcg_at_1_std": 0.10566929130044017, + "nauc_ndcg_at_20_diff1": 0.3176711357845581, + "nauc_ndcg_at_20_max": 0.40878005162885955, + "nauc_ndcg_at_20_std": 0.1804032237716874, + "nauc_ndcg_at_3_diff1": 0.3200248031458428, + "nauc_ndcg_at_3_max": 0.36818042332932993, + "nauc_ndcg_at_3_std": 0.13605230075332542, + "nauc_ndcg_at_5_diff1": 0.31828438985071783, + "nauc_ndcg_at_5_max": 0.38502954660045646, + "nauc_ndcg_at_5_std": 0.15078692613412012, + "nauc_precision_at_1000_diff1": 0.3311445222663205, + "nauc_precision_at_1000_max": 0.6550299624106116, + "nauc_precision_at_1000_std": 0.44096121449353404, + "nauc_precision_at_100_diff1": 0.3082761705323225, + "nauc_precision_at_100_max": 0.5597597184233869, + "nauc_precision_at_100_std": 0.3736179053899826, + "nauc_precision_at_10_diff1": 0.30063055470301425, + "nauc_precision_at_10_max": 0.4557862444220881, + "nauc_precision_at_10_std": 0.22198411059468534, + "nauc_precision_at_1_diff1": 0.3514910552490034, + "nauc_precision_at_1_max": 0.3259628876339468, + "nauc_precision_at_1_std": 0.10566929130044017, + "nauc_precision_at_20_diff1": 0.3037572881050044, + "nauc_precision_at_20_max": 0.4952475218197893, + "nauc_precision_at_20_std": 0.2686421707077076, + "nauc_precision_at_3_diff1": 0.30623059290302806, + "nauc_precision_at_3_max": 0.3930622119069662, + "nauc_precision_at_3_std": 0.1535938362313337, + "nauc_precision_at_5_diff1": 0.30400185417167785, + "nauc_precision_at_5_max": 0.4262493788157118, + "nauc_precision_at_5_std": 0.18269957572496784, + "nauc_recall_at_1000_diff1": 0.33114452226632124, + "nauc_recall_at_1000_max": 0.6550299624106134, + "nauc_recall_at_1000_std": 0.44096121449353487, + "nauc_recall_at_100_diff1": 0.3082761705323224, + "nauc_recall_at_100_max": 0.5597597184233868, + "nauc_recall_at_100_std": 0.37361790538998224, + "nauc_recall_at_10_diff1": 0.30063055470301453, + "nauc_recall_at_10_max": 0.4557862444220886, + "nauc_recall_at_10_std": 0.2219841105946856, + "nauc_recall_at_1_diff1": 0.3514910552490034, + "nauc_recall_at_1_max": 0.3259628876339468, + "nauc_recall_at_1_std": 0.10566929130044017, + "nauc_recall_at_20_diff1": 0.30375728810500474, + "nauc_recall_at_20_max": 0.4952475218197899, + "nauc_recall_at_20_std": 0.268642170707708, + "nauc_recall_at_3_diff1": 0.30623059290302795, + "nauc_recall_at_3_max": 0.3930622119069661, + "nauc_recall_at_3_std": 0.15359383623133366, + "nauc_recall_at_5_diff1": 0.3040018541716781, + "nauc_recall_at_5_max": 0.42624937881571195, + "nauc_recall_at_5_std": 0.18269957572496756, + "ndcg_at_1": 0.14509, + "ndcg_at_10": 0.26238, + "ndcg_at_100": 0.30292, + "ndcg_at_1000": 0.32663, + "ndcg_at_20": 0.27823, + "ndcg_at_3": 0.21819, + "ndcg_at_5": 0.24108, + "precision_at_1": 0.14509, + "precision_at_10": 0.03925, + "precision_at_100": 0.0059, + "precision_at_1000": 0.00078, + "precision_at_20": 0.02273, + "precision_at_3": 0.09042, + "precision_at_5": 0.06537, + "recall_at_1": 0.14509, + "recall_at_10": 0.39245, + "recall_at_100": 0.58972, + "recall_at_1000": 0.78261, + "recall_at_20": 0.45469, + "recall_at_3": 0.27126, + "recall_at_5": 0.32683 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/PIQA.json b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/PIQA.json new file mode 100644 index 000000000..e767c714d --- /dev/null +++ b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/PIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 52.2050256729126, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.2326, + "map_at_1": 0.11425, + "map_at_10": 0.19171, + "map_at_100": 0.20008, + "map_at_1000": 0.20086, + "map_at_20": 0.19613, + "map_at_3": 0.16984, + "map_at_5": 0.18317, + "mrr_at_1": 0.11425462459194777, + "mrr_at_10": 0.19171135810145584, + "mrr_at_100": 0.2000786310186117, + "mrr_at_1000": 0.20086082476275902, + "mrr_at_20": 0.1961340787943012, + "mrr_at_3": 0.16984040623866517, + "mrr_at_5": 0.1831701124410589, + "nauc_map_at_1000_diff1": -0.1347374060486915, + "nauc_map_at_1000_max": 0.1342589944892556, + "nauc_map_at_1000_std": 0.13553802891784217, + "nauc_map_at_100_diff1": -0.1344327283048182, + "nauc_map_at_100_max": 0.13452114826883665, + "nauc_map_at_100_std": 0.13553695165718657, + "nauc_map_at_10_diff1": -0.1308578047512318, + "nauc_map_at_10_max": 0.1390179419550439, + "nauc_map_at_10_std": 0.13151789529149063, + "nauc_map_at_1_diff1": -0.09401485852093243, + "nauc_map_at_1_max": 0.1390244933399154, + "nauc_map_at_1_std": 0.11898354326986076, + "nauc_map_at_20_diff1": -0.13231308133757075, + "nauc_map_at_20_max": 0.13613359673404452, + "nauc_map_at_20_std": 0.13323454235414253, + "nauc_map_at_3_diff1": -0.12671772507402798, + "nauc_map_at_3_max": 0.1503129309124901, + "nauc_map_at_3_std": 0.12298212690711063, + "nauc_map_at_5_diff1": -0.13231354940428086, + "nauc_map_at_5_max": 0.14432692927788657, + "nauc_map_at_5_std": 0.12920402727425292, + "nauc_mrr_at_1000_diff1": -0.1347374062068066, + "nauc_mrr_at_1000_max": 0.1342589964166839, + "nauc_mrr_at_1000_std": 0.135538030843299, + "nauc_mrr_at_100_diff1": -0.1344327283048182, + "nauc_mrr_at_100_max": 0.13452114826883665, + "nauc_mrr_at_100_std": 0.13553695165718657, + "nauc_mrr_at_10_diff1": -0.1308578047512318, + "nauc_mrr_at_10_max": 0.1390179419550439, + "nauc_mrr_at_10_std": 0.13151789529149063, + "nauc_mrr_at_1_diff1": -0.09401485852093243, + "nauc_mrr_at_1_max": 0.1390244933399154, + "nauc_mrr_at_1_std": 0.11898354326986076, + "nauc_mrr_at_20_diff1": -0.13231308133757075, + "nauc_mrr_at_20_max": 0.13613359673404452, + "nauc_mrr_at_20_std": 0.13323454235414253, + "nauc_mrr_at_3_diff1": -0.12671772507402798, + "nauc_mrr_at_3_max": 0.1503129309124901, + "nauc_mrr_at_3_std": 0.12298212690711063, + "nauc_mrr_at_5_diff1": -0.13231354940428086, + "nauc_mrr_at_5_max": 0.14432692927788657, + "nauc_mrr_at_5_std": 0.12920402727425292, + "nauc_ndcg_at_1000_diff1": -0.16885717942923326, + "nauc_ndcg_at_1000_max": 0.10150237086190814, + "nauc_ndcg_at_1000_std": 0.16570008813406653, + "nauc_ndcg_at_100_diff1": -0.15938686659376988, + "nauc_ndcg_at_100_max": 0.11066950710708427, + "nauc_ndcg_at_100_std": 0.16687100470128838, + "nauc_ndcg_at_10_diff1": -0.14027895814890573, + "nauc_ndcg_at_10_max": 0.12912464087547643, + "nauc_ndcg_at_10_std": 0.14194265785687057, + "nauc_ndcg_at_1_diff1": -0.09401485852093243, + "nauc_ndcg_at_1_max": 0.1390244933399154, + "nauc_ndcg_at_1_std": 0.11898354326986076, + "nauc_ndcg_at_20_diff1": -0.14504556366225568, + "nauc_ndcg_at_20_max": 0.11934313151618425, + "nauc_ndcg_at_20_std": 0.14784014254730862, + "nauc_ndcg_at_3_diff1": -0.1346547513950229, + "nauc_ndcg_at_3_max": 0.15176239392978508, + "nauc_ndcg_at_3_std": 0.12709559599712256, + "nauc_ndcg_at_5_diff1": -0.1436764417549981, + "nauc_ndcg_at_5_max": 0.14146458189398853, + "nauc_ndcg_at_5_std": 0.1373887101102375, + "nauc_precision_at_1000_diff1": -0.39223803112633676, + "nauc_precision_at_1000_max": -0.11428120748928117, + "nauc_precision_at_1000_std": 0.33256858288036273, + "nauc_precision_at_100_diff1": -0.24445002183499748, + "nauc_precision_at_100_max": 0.030097505648119496, + "nauc_precision_at_100_std": 0.2842582839779262, + "nauc_precision_at_10_diff1": -0.15984695878470023, + "nauc_precision_at_10_max": 0.10277283522355189, + "nauc_precision_at_10_std": 0.16658431893310635, + "nauc_precision_at_1_diff1": -0.09401485852093243, + "nauc_precision_at_1_max": 0.1390244933399154, + "nauc_precision_at_1_std": 0.11898354326986076, + "nauc_precision_at_20_diff1": -0.174405814322811, + "nauc_precision_at_20_max": 0.07218701487677671, + "nauc_precision_at_20_std": 0.1850909663579734, + "nauc_precision_at_3_diff1": -0.15297486002249785, + "nauc_precision_at_3_max": 0.15478370981534928, + "nauc_precision_at_3_std": 0.1373802407560988, + "nauc_precision_at_5_diff1": -0.16915422412986766, + "nauc_precision_at_5_max": 0.1337509622911511, + "nauc_precision_at_5_std": 0.1569046397368108, + "nauc_recall_at_1000_diff1": -0.3922380311263346, + "nauc_recall_at_1000_max": -0.11428120748927992, + "nauc_recall_at_1000_std": 0.3325685828803644, + "nauc_recall_at_100_diff1": -0.244450021834998, + "nauc_recall_at_100_max": 0.03009750564811899, + "nauc_recall_at_100_std": 0.28425828397792546, + "nauc_recall_at_10_diff1": -0.15984695878470012, + "nauc_recall_at_10_max": 0.10277283522355225, + "nauc_recall_at_10_std": 0.16658431893310643, + "nauc_recall_at_1_diff1": -0.09401485852093243, + "nauc_recall_at_1_max": 0.1390244933399154, + "nauc_recall_at_1_std": 0.11898354326986076, + "nauc_recall_at_20_diff1": -0.17440581432281113, + "nauc_recall_at_20_max": 0.07218701487677659, + "nauc_recall_at_20_std": 0.18509096635797312, + "nauc_recall_at_3_diff1": -0.1529748600224978, + "nauc_recall_at_3_max": 0.15478370981534917, + "nauc_recall_at_3_std": 0.13738024075609892, + "nauc_recall_at_5_diff1": -0.1691542241298678, + "nauc_recall_at_5_max": 0.1337509622911512, + "nauc_recall_at_5_std": 0.15690463973681065, + "ndcg_at_1": 0.11425, + "ndcg_at_10": 0.2326, + "ndcg_at_100": 0.2785, + "ndcg_at_1000": 0.3021, + "ndcg_at_20": 0.24889, + "ndcg_at_3": 0.18746, + "ndcg_at_5": 0.21146, + "precision_at_1": 0.11425, + "precision_at_10": 0.03629, + "precision_at_100": 0.0059, + "precision_at_1000": 0.00078, + "precision_at_20": 0.02138, + "precision_at_3": 0.07943, + "precision_at_5": 0.0593, + "recall_at_1": 0.11425, + "recall_at_10": 0.36289, + "recall_at_100": 0.58977, + "recall_at_1000": 0.78183, + "recall_at_20": 0.42764, + "recall_at_3": 0.2383, + "recall_at_5": 0.29652 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/Quail.json b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/Quail.json new file mode 100644 index 000000000..be99ec79f --- /dev/null +++ b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/Quail.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 78.06833505630493, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02724, + "map_at_1": 0.00882, + "map_at_10": 0.01969, + "map_at_100": 0.02399, + "map_at_1000": 0.0248, + "map_at_20": 0.02176, + "map_at_3": 0.01464, + "map_at_5": 0.01731, + "mrr_at_1": 0.008823529411764706, + "mrr_at_10": 0.01968035130718956, + "mrr_at_100": 0.023985330048944445, + "mrr_at_1000": 0.02478997345573462, + "mrr_at_20": 0.02175482087148624, + "mrr_at_3": 0.014644607843137255, + "mrr_at_5": 0.017310049019607848, + "nauc_map_at_1000_diff1": 0.06394264925407264, + "nauc_map_at_1000_max": 0.010923189243347325, + "nauc_map_at_1000_std": 0.1929424787879528, + "nauc_map_at_100_diff1": 0.0633593986250753, + "nauc_map_at_100_max": 0.010245627062426226, + "nauc_map_at_100_std": 0.1933583367502744, + "nauc_map_at_10_diff1": 0.06821267394357258, + "nauc_map_at_10_max": 0.0011467524862616998, + "nauc_map_at_10_std": 0.20848598549627162, + "nauc_map_at_1_diff1": 0.18285484303729532, + "nauc_map_at_1_max": -0.034478132546283964, + "nauc_map_at_1_std": 0.24728333780520512, + "nauc_map_at_20_diff1": 0.06813612073624473, + "nauc_map_at_20_max": 0.006749427628788959, + "nauc_map_at_20_std": 0.19903586961780045, + "nauc_map_at_3_diff1": 0.09861095051041092, + "nauc_map_at_3_max": -0.048142414339328546, + "nauc_map_at_3_std": 0.1947262596926422, + "nauc_map_at_5_diff1": 0.07413122609230416, + "nauc_map_at_5_max": -0.00823695064240612, + "nauc_map_at_5_std": 0.20481376038523014, + "nauc_mrr_at_1000_diff1": 0.06421848356171371, + "nauc_mrr_at_1000_max": 0.01097912407545274, + "nauc_mrr_at_1000_std": 0.19303291044632437, + "nauc_mrr_at_100_diff1": 0.06363825103051349, + "nauc_mrr_at_100_max": 0.010301999131118697, + "nauc_mrr_at_100_std": 0.19345013167094327, + "nauc_mrr_at_10_diff1": 0.06846522672330996, + "nauc_mrr_at_10_max": 0.0011034644069204994, + "nauc_mrr_at_10_std": 0.2086702512093025, + "nauc_mrr_at_1_diff1": 0.18285484303729532, + "nauc_mrr_at_1_max": -0.034478132546283964, + "nauc_mrr_at_1_std": 0.24728333780520512, + "nauc_mrr_at_20_diff1": 0.06838980865521999, + "nauc_mrr_at_20_max": 0.006735040251292076, + "nauc_mrr_at_20_std": 0.1991781759735677, + "nauc_mrr_at_3_diff1": 0.09861095051041092, + "nauc_mrr_at_3_max": -0.048142414339328546, + "nauc_mrr_at_3_std": 0.1947262596926422, + "nauc_mrr_at_5_diff1": 0.07413122609230416, + "nauc_mrr_at_5_max": -0.00823695064240612, + "nauc_mrr_at_5_std": 0.20481376038523014, + "nauc_ndcg_at_1000_diff1": 0.037313887600319916, + "nauc_ndcg_at_1000_max": 0.03128676315378829, + "nauc_ndcg_at_1000_std": 0.16836891101250556, + "nauc_ndcg_at_100_diff1": 0.032709064650506166, + "nauc_ndcg_at_100_max": 0.03458087396626824, + "nauc_ndcg_at_100_std": 0.17740991073892234, + "nauc_ndcg_at_10_diff1": 0.043375324141259004, + "nauc_ndcg_at_10_max": 0.017638792221325948, + "nauc_ndcg_at_10_std": 0.21023898591991044, + "nauc_ndcg_at_1_diff1": 0.18285484303729532, + "nauc_ndcg_at_1_max": -0.034478132546283964, + "nauc_ndcg_at_1_std": 0.24728333780520512, + "nauc_ndcg_at_20_diff1": 0.04822162349598089, + "nauc_ndcg_at_20_max": 0.025851189942154587, + "nauc_ndcg_at_20_std": 0.19056164659005792, + "nauc_ndcg_at_3_diff1": 0.08225924017986844, + "nauc_ndcg_at_3_max": -0.049877291874473866, + "nauc_ndcg_at_3_std": 0.18801046619127976, + "nauc_ndcg_at_5_diff1": 0.05074508450202534, + "nauc_ndcg_at_5_max": 0.009873611584612176, + "nauc_ndcg_at_5_std": 0.20410207572772968, + "nauc_precision_at_1000_diff1": 0.023777066620351756, + "nauc_precision_at_1000_max": 0.03599387537270936, + "nauc_precision_at_1000_std": 0.1465974107274498, + "nauc_precision_at_100_diff1": 0.011459037378888162, + "nauc_precision_at_100_max": 0.05067643244422677, + "nauc_precision_at_100_std": 0.1664462136631802, + "nauc_precision_at_10_diff1": 0.012807189258437785, + "nauc_precision_at_10_max": 0.037338870896427685, + "nauc_precision_at_10_std": 0.2136276202965041, + "nauc_precision_at_1_diff1": 0.18285484303729532, + "nauc_precision_at_1_max": -0.034478132546283964, + "nauc_precision_at_1_std": 0.24728333780520512, + "nauc_precision_at_20_diff1": 0.03189203304074517, + "nauc_precision_at_20_max": 0.04303897236383156, + "nauc_precision_at_20_std": 0.18137074054199095, + "nauc_precision_at_3_diff1": 0.050456130936409944, + "nauc_precision_at_3_max": -0.05306323226902789, + "nauc_precision_at_3_std": 0.17566407298094985, + "nauc_precision_at_5_diff1": 0.013952240407834725, + "nauc_precision_at_5_max": 0.04134051165992009, + "nauc_precision_at_5_std": 0.2044423186850364, + "nauc_recall_at_1000_diff1": 0.023777066620351832, + "nauc_recall_at_1000_max": 0.03599387537270945, + "nauc_recall_at_1000_std": 0.1465974107274497, + "nauc_recall_at_100_diff1": 0.011459037378888095, + "nauc_recall_at_100_max": 0.05067643244422672, + "nauc_recall_at_100_std": 0.1664462136631801, + "nauc_recall_at_10_diff1": 0.012807189258437695, + "nauc_recall_at_10_max": 0.037338870896427505, + "nauc_recall_at_10_std": 0.21362762029650392, + "nauc_recall_at_1_diff1": 0.18285484303729532, + "nauc_recall_at_1_max": -0.034478132546283964, + "nauc_recall_at_1_std": 0.24728333780520512, + "nauc_recall_at_20_diff1": 0.03189203304074526, + "nauc_recall_at_20_max": 0.043038972363831446, + "nauc_recall_at_20_std": 0.181370740541991, + "nauc_recall_at_3_diff1": 0.050456130936409875, + "nauc_recall_at_3_max": -0.05306323226902787, + "nauc_recall_at_3_std": 0.1756640729809498, + "nauc_recall_at_5_diff1": 0.013952240407834727, + "nauc_recall_at_5_max": 0.04134051165991997, + "nauc_recall_at_5_std": 0.20444231868503634, + "ndcg_at_1": 0.00882, + "ndcg_at_10": 0.02724, + "ndcg_at_100": 0.05236, + "ndcg_at_1000": 0.08121, + "ndcg_at_20": 0.03485, + "ndcg_at_3": 0.01655, + "ndcg_at_5": 0.02137, + "precision_at_1": 0.00882, + "precision_at_10": 0.00522, + "precision_at_100": 0.0018, + "precision_at_1000": 0.00042, + "precision_at_20": 0.00412, + "precision_at_3": 0.00735, + "precision_at_5": 0.00676, + "recall_at_1": 0.00882, + "recall_at_10": 0.05221, + "recall_at_100": 0.17978, + "recall_at_1000": 0.4239, + "recall_at_20": 0.08235, + "recall_at_3": 0.02206, + "recall_at_5": 0.03382 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/RARbCode.json b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/RARbCode.json new file mode 100644 index 000000000..3853d83be --- /dev/null +++ b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/RARbCode.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 3020.982394218445, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.45249, + "map_at_1": 0.30997, + "map_at_10": 0.40337, + "map_at_100": 0.41181, + "map_at_1000": 0.41239, + "map_at_20": 0.40836, + "map_at_3": 0.37736, + "map_at_5": 0.39265, + "mrr_at_1": 0.3106469002695418, + "mrr_at_10": 0.40364870791083723, + "mrr_at_100": 0.412098666227675, + "mrr_at_1000": 0.4126765213524214, + "mrr_at_20": 0.4086428734584136, + "mrr_at_3": 0.3774707996406109, + "mrr_at_5": 0.3929357592093441, + "nauc_map_at_1000_diff1": 0.45894431762809035, + "nauc_map_at_1000_max": 0.33573003284526365, + "nauc_map_at_1000_std": 0.27974154414617625, + "nauc_map_at_100_diff1": 0.45863151505958827, + "nauc_map_at_100_max": 0.3356486136422277, + "nauc_map_at_100_std": 0.2798183625593351, + "nauc_map_at_10_diff1": 0.4583117862212378, + "nauc_map_at_10_max": 0.3373760773801379, + "nauc_map_at_10_std": 0.28088412069471463, + "nauc_map_at_1_diff1": 0.5402655679172332, + "nauc_map_at_1_max": 0.318110546204684, + "nauc_map_at_1_std": 0.2301041789941552, + "nauc_map_at_20_diff1": 0.4577419831755446, + "nauc_map_at_20_max": 0.3357976509252588, + "nauc_map_at_20_std": 0.2803214632819699, + "nauc_map_at_3_diff1": 0.466621304619182, + "nauc_map_at_3_max": 0.33165566110055605, + "nauc_map_at_3_std": 0.2665481007805448, + "nauc_map_at_5_diff1": 0.4614641908453281, + "nauc_map_at_5_max": 0.33520316968253433, + "nauc_map_at_5_std": 0.2740702046079271, + "nauc_mrr_at_1000_diff1": 0.4579647058008307, + "nauc_mrr_at_1000_max": 0.33661083563699173, + "nauc_mrr_at_1000_std": 0.2799595331953161, + "nauc_mrr_at_100_diff1": 0.45765342251727825, + "nauc_mrr_at_100_max": 0.33652813719382946, + "nauc_mrr_at_100_std": 0.2800360033306211, + "nauc_mrr_at_10_diff1": 0.4573395990305443, + "nauc_mrr_at_10_max": 0.3382499620111471, + "nauc_mrr_at_10_std": 0.2810984772340261, + "nauc_mrr_at_1_diff1": 0.5381458240246075, + "nauc_mrr_at_1_max": 0.32023885703420296, + "nauc_mrr_at_1_std": 0.23112113502503562, + "nauc_mrr_at_20_diff1": 0.4567708819640221, + "nauc_mrr_at_20_max": 0.3366715092830219, + "nauc_mrr_at_20_std": 0.2805380124437784, + "nauc_mrr_at_3_diff1": 0.46590530359974985, + "nauc_mrr_at_3_max": 0.3319424792112494, + "nauc_mrr_at_3_std": 0.26591232773859763, + "nauc_mrr_at_5_diff1": 0.46050258373041003, + "nauc_mrr_at_5_max": 0.3360674217994229, + "nauc_mrr_at_5_std": 0.2742833603792264, + "nauc_ndcg_at_1000_diff1": 0.4387939650671349, + "nauc_ndcg_at_1000_max": 0.34672023460130125, + "nauc_ndcg_at_1000_std": 0.3019449529843897, + "nauc_ndcg_at_100_diff1": 0.43117235139304183, + "nauc_ndcg_at_100_max": 0.3465676101107515, + "nauc_ndcg_at_100_std": 0.30609161790855455, + "nauc_ndcg_at_10_diff1": 0.4267827488717999, + "nauc_ndcg_at_10_max": 0.3492451925992213, + "nauc_ndcg_at_10_std": 0.3081311389055587, + "nauc_ndcg_at_1_diff1": 0.5402655679172332, + "nauc_ndcg_at_1_max": 0.318110546204684, + "nauc_ndcg_at_1_std": 0.2301041789941552, + "nauc_ndcg_at_20_diff1": 0.42516501593997985, + "nauc_ndcg_at_20_max": 0.34452102612133667, + "nauc_ndcg_at_20_std": 0.3068928719834255, + "nauc_ndcg_at_3_diff1": 0.4448310063404949, + "nauc_ndcg_at_3_max": 0.33708604949766735, + "nauc_ndcg_at_3_std": 0.2773529057973091, + "nauc_ndcg_at_5_diff1": 0.4353466500818617, + "nauc_ndcg_at_5_max": 0.3434798009039095, + "nauc_ndcg_at_5_std": 0.2910532659695847, + "nauc_precision_at_1000_diff1": 0.3139949321983628, + "nauc_precision_at_1000_max": 0.5574046676030955, + "nauc_precision_at_1000_std": 0.6011412089066575, + "nauc_precision_at_100_diff1": 0.29337421323628343, + "nauc_precision_at_100_max": 0.4249410927223618, + "nauc_precision_at_100_std": 0.46963363644899514, + "nauc_precision_at_10_diff1": 0.32070090342003194, + "nauc_precision_at_10_max": 0.3914977261538201, + "nauc_precision_at_10_std": 0.40498949489688085, + "nauc_precision_at_1_diff1": 0.5402655679172332, + "nauc_precision_at_1_max": 0.318110546204684, + "nauc_precision_at_1_std": 0.2301041789941552, + "nauc_precision_at_20_diff1": 0.30087115746058585, + "nauc_precision_at_20_max": 0.37748946510559156, + "nauc_precision_at_20_std": 0.41363835574171265, + "nauc_precision_at_3_diff1": 0.38283555905521227, + "nauc_precision_at_3_max": 0.35300418904175684, + "nauc_precision_at_3_std": 0.30810068829150977, + "nauc_precision_at_5_diff1": 0.3571247009524796, + "nauc_precision_at_5_max": 0.3692527488375891, + "nauc_precision_at_5_std": 0.34313893097711967, + "nauc_recall_at_1000_diff1": 0.3139949321983662, + "nauc_recall_at_1000_max": 0.5574046676030987, + "nauc_recall_at_1000_std": 0.6011412089066602, + "nauc_recall_at_100_diff1": 0.2933742132362833, + "nauc_recall_at_100_max": 0.42494109272236175, + "nauc_recall_at_100_std": 0.4696336364489956, + "nauc_recall_at_10_diff1": 0.3207009034200313, + "nauc_recall_at_10_max": 0.3914977261538204, + "nauc_recall_at_10_std": 0.4049894948968809, + "nauc_recall_at_1_diff1": 0.5402655679172332, + "nauc_recall_at_1_max": 0.318110546204684, + "nauc_recall_at_1_std": 0.2301041789941552, + "nauc_recall_at_20_diff1": 0.3008711574605856, + "nauc_recall_at_20_max": 0.3774894651055924, + "nauc_recall_at_20_std": 0.41363835574171287, + "nauc_recall_at_3_diff1": 0.38283555905521255, + "nauc_recall_at_3_max": 0.353004189041757, + "nauc_recall_at_3_std": 0.30810068829150944, + "nauc_recall_at_5_diff1": 0.35712470095247956, + "nauc_recall_at_5_max": 0.36925274883758924, + "nauc_recall_at_5_std": 0.34313893097712, + "ndcg_at_1": 0.30997, + "ndcg_at_10": 0.45249, + "ndcg_at_100": 0.49566, + "ndcg_at_1000": 0.5116, + "ndcg_at_20": 0.47082, + "ndcg_at_3": 0.39902, + "ndcg_at_5": 0.42668, + "precision_at_1": 0.30997, + "precision_at_10": 0.06085, + "precision_at_100": 0.00815, + "precision_at_1000": 0.00094, + "precision_at_20": 0.03406, + "precision_at_3": 0.15386, + "precision_at_5": 0.1058, + "recall_at_1": 0.30997, + "recall_at_10": 0.60849, + "recall_at_100": 0.81469, + "recall_at_1000": 0.94137, + "recall_at_20": 0.68127, + "recall_at_3": 0.46159, + "recall_at_5": 0.52898 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/RARbMath.json b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/RARbMath.json new file mode 100644 index 000000000..ff901336a --- /dev/null +++ b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/RARbMath.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 4603.876984596252, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.49823, + "map_at_1": 0.42475, + "map_at_10": 0.47089, + "map_at_100": 0.4786, + "map_at_1000": 0.4792, + "map_at_20": 0.47502, + "map_at_3": 0.45537, + "map_at_5": 0.46333, + "mrr_at_1": 0.42475075170121857, + "mrr_at_10": 0.4708885648472602, + "mrr_at_100": 0.47859979377158696, + "mrr_at_1000": 0.47920268060116566, + "mrr_at_20": 0.47502372809036075, + "mrr_at_3": 0.4553726855515109, + "mrr_at_5": 0.4633328058237061, + "nauc_map_at_1000_diff1": 0.7650903418552825, + "nauc_map_at_1000_max": 0.41767488047755125, + "nauc_map_at_1000_std": -0.16742038949035226, + "nauc_map_at_100_diff1": 0.7648368419507523, + "nauc_map_at_100_max": 0.41744600060585946, + "nauc_map_at_100_std": -0.1674994897309077, + "nauc_map_at_10_diff1": 0.7664068746385415, + "nauc_map_at_10_max": 0.41620738675937724, + "nauc_map_at_10_std": -0.17040054842212388, + "nauc_map_at_1_diff1": 0.8057157946656828, + "nauc_map_at_1_max": 0.44293272574474685, + "nauc_map_at_1_std": -0.16883949603194093, + "nauc_map_at_20_diff1": 0.7650951280890331, + "nauc_map_at_20_max": 0.4169773528290185, + "nauc_map_at_20_std": -0.16914580870053733, + "nauc_map_at_3_diff1": 0.7754128717579319, + "nauc_map_at_3_max": 0.42274488598334653, + "nauc_map_at_3_std": -0.1695493686808079, + "nauc_map_at_5_diff1": 0.7711895202494735, + "nauc_map_at_5_max": 0.4188929968472289, + "nauc_map_at_5_std": -0.16901143160273877, + "nauc_mrr_at_1000_diff1": 0.7650903373030797, + "nauc_mrr_at_1000_max": 0.4176748735973539, + "nauc_mrr_at_1000_std": -0.16742039313621093, + "nauc_mrr_at_100_diff1": 0.7648368419507523, + "nauc_mrr_at_100_max": 0.41744600060585946, + "nauc_mrr_at_100_std": -0.1674994897309077, + "nauc_mrr_at_10_diff1": 0.7664068746385415, + "nauc_mrr_at_10_max": 0.41620738675937724, + "nauc_mrr_at_10_std": -0.17040054842212388, + "nauc_mrr_at_1_diff1": 0.8057157946656828, + "nauc_mrr_at_1_max": 0.44293272574474685, + "nauc_mrr_at_1_std": -0.16883949603194093, + "nauc_mrr_at_20_diff1": 0.7650951280890331, + "nauc_mrr_at_20_max": 0.4169773528290185, + "nauc_mrr_at_20_std": -0.16914580870053733, + "nauc_mrr_at_3_diff1": 0.7754128717579319, + "nauc_mrr_at_3_max": 0.42274488598334653, + "nauc_mrr_at_3_std": -0.1695493686808079, + "nauc_mrr_at_5_diff1": 0.7711895202494735, + "nauc_mrr_at_5_max": 0.4188929968472289, + "nauc_mrr_at_5_std": -0.16901143160273877, + "nauc_ndcg_at_1000_diff1": 0.7449521874950024, + "nauc_ndcg_at_1000_max": 0.4149682976926838, + "nauc_ndcg_at_1000_std": -0.15166704679337933, + "nauc_ndcg_at_100_diff1": 0.7368337781831539, + "nauc_ndcg_at_100_max": 0.40864849502900474, + "nauc_ndcg_at_100_std": -0.1523394950751538, + "nauc_ndcg_at_10_diff1": 0.7448504101868347, + "nauc_ndcg_at_10_max": 0.40159883934289325, + "nauc_ndcg_at_10_std": -0.17136654722145206, + "nauc_ndcg_at_1_diff1": 0.8057157946656828, + "nauc_ndcg_at_1_max": 0.44293272574474685, + "nauc_ndcg_at_1_std": -0.16883949603194093, + "nauc_ndcg_at_20_diff1": 0.7395503879615968, + "nauc_ndcg_at_20_max": 0.404422463362805, + "nauc_ndcg_at_20_std": -0.16637577661348238, + "nauc_ndcg_at_3_diff1": 0.7649734630476325, + "nauc_ndcg_at_3_max": 0.4154767033612001, + "nauc_ndcg_at_3_std": -0.1693215379914285, + "nauc_ndcg_at_5_diff1": 0.7570908280403358, + "nauc_ndcg_at_5_max": 0.40831855226408864, + "nauc_ndcg_at_5_std": -0.1682510444897883, + "nauc_precision_at_1000_diff1": 0.5497711151357544, + "nauc_precision_at_1000_max": 0.5398339131678391, + "nauc_precision_at_1000_std": 0.22688399925736025, + "nauc_precision_at_100_diff1": 0.5643097287746738, + "nauc_precision_at_100_max": 0.37801201126492473, + "nauc_precision_at_100_std": -0.01705350562850382, + "nauc_precision_at_10_diff1": 0.6695014808662709, + "nauc_precision_at_10_max": 0.3510347431294198, + "nauc_precision_at_10_std": -0.17508488679306153, + "nauc_precision_at_1_diff1": 0.8057157946656828, + "nauc_precision_at_1_max": 0.44293272574474685, + "nauc_precision_at_1_std": -0.16883949603194093, + "nauc_precision_at_20_diff1": 0.6374779171996061, + "nauc_precision_at_20_max": 0.3592030500242354, + "nauc_precision_at_20_std": -0.15190507613806853, + "nauc_precision_at_3_diff1": 0.7342163392889105, + "nauc_precision_at_3_max": 0.39396996377048615, + "nauc_precision_at_3_std": -0.16851036353217058, + "nauc_precision_at_5_diff1": 0.7133208883362363, + "nauc_precision_at_5_max": 0.375212844369422, + "nauc_precision_at_5_std": -0.1655946730484267, + "nauc_recall_at_1000_diff1": 0.5497711151357583, + "nauc_recall_at_1000_max": 0.5398339131678408, + "nauc_recall_at_1000_std": 0.22688399925736355, + "nauc_recall_at_100_diff1": 0.5643097287746736, + "nauc_recall_at_100_max": 0.3780120112649244, + "nauc_recall_at_100_std": -0.017053505628504797, + "nauc_recall_at_10_diff1": 0.669501480866271, + "nauc_recall_at_10_max": 0.35103474312942007, + "nauc_recall_at_10_std": -0.1750848867930609, + "nauc_recall_at_1_diff1": 0.8057157946656828, + "nauc_recall_at_1_max": 0.44293272574474685, + "nauc_recall_at_1_std": -0.16883949603194093, + "nauc_recall_at_20_diff1": 0.6374779171996059, + "nauc_recall_at_20_max": 0.3592030500242349, + "nauc_recall_at_20_std": -0.15190507613806806, + "nauc_recall_at_3_diff1": 0.7342163392889104, + "nauc_recall_at_3_max": 0.39396996377048604, + "nauc_recall_at_3_std": -0.16851036353217075, + "nauc_recall_at_5_diff1": 0.7133208883362353, + "nauc_recall_at_5_max": 0.37521284436942165, + "nauc_recall_at_5_std": -0.16559467304842646, + "ndcg_at_1": 0.42475, + "ndcg_at_10": 0.49823, + "ndcg_at_100": 0.54005, + "ndcg_at_1000": 0.55743, + "ndcg_at_20": 0.51336, + "ndcg_at_3": 0.46554, + "ndcg_at_5": 0.47992, + "precision_at_1": 0.42475, + "precision_at_10": 0.05866, + "precision_at_100": 0.00792, + "precision_at_1000": 0.00093, + "precision_at_20": 0.03233, + "precision_at_3": 0.16501, + "precision_at_5": 0.106, + "recall_at_1": 0.42475, + "recall_at_10": 0.58664, + "recall_at_100": 0.79206, + "recall_at_1000": 0.93163, + "recall_at_20": 0.64662, + "recall_at_3": 0.49502, + "recall_at_5": 0.52999 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/SIQA.json b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/SIQA.json new file mode 100644 index 000000000..37e2b167a --- /dev/null +++ b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/SIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 34.895793437957764, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.00593, + "map_at_1": 0.00205, + "map_at_10": 0.00419, + "map_at_100": 0.00558, + "map_at_1000": 0.00611, + "map_at_20": 0.00484, + "map_at_3": 0.00324, + "map_at_5": 0.00345, + "mrr_at_1": 0.0020470829068577278, + "mrr_at_10": 0.004190630534028691, + "mrr_at_100": 0.005575146742258511, + "mrr_at_1000": 0.006114721231294308, + "mrr_at_20": 0.004839457507359499, + "mrr_at_3": 0.0032412146025247355, + "mrr_at_5": 0.003445922893210508, + "nauc_map_at_1000_diff1": -0.0676900959731138, + "nauc_map_at_1000_max": -0.1456968424226514, + "nauc_map_at_1000_std": 0.07775995708582069, + "nauc_map_at_100_diff1": -0.07246825085607127, + "nauc_map_at_100_max": -0.1565928842730582, + "nauc_map_at_100_std": 0.08844085252861282, + "nauc_map_at_10_diff1": -0.08083121293463497, + "nauc_map_at_10_max": -0.20582893488195972, + "nauc_map_at_10_std": 0.13033835990843656, + "nauc_map_at_1_diff1": -0.1944247218787479, + "nauc_map_at_1_max": -0.3354241096662269, + "nauc_map_at_1_std": 0.4450028773454104, + "nauc_map_at_20_diff1": -0.08424470192582584, + "nauc_map_at_20_max": -0.17795503904852394, + "nauc_map_at_20_std": 0.1104902953039136, + "nauc_map_at_3_diff1": -0.1402248948467282, + "nauc_map_at_3_max": -0.31580974220123603, + "nauc_map_at_3_std": 0.17416556190835358, + "nauc_map_at_5_diff1": -0.15841231921355517, + "nauc_map_at_5_max": -0.3179899280988303, + "nauc_map_at_5_std": 0.1366641521312719, + "nauc_mrr_at_1000_diff1": -0.06768861885961028, + "nauc_mrr_at_1000_max": -0.14569390365580398, + "nauc_mrr_at_1000_std": 0.07775757099957224, + "nauc_mrr_at_100_diff1": -0.07246825085607127, + "nauc_mrr_at_100_max": -0.1565928842730582, + "nauc_mrr_at_100_std": 0.08844085252861282, + "nauc_mrr_at_10_diff1": -0.08083121293463497, + "nauc_mrr_at_10_max": -0.20582893488195972, + "nauc_mrr_at_10_std": 0.13033835990843656, + "nauc_mrr_at_1_diff1": -0.1944247218787479, + "nauc_mrr_at_1_max": -0.3354241096662269, + "nauc_mrr_at_1_std": 0.4450028773454104, + "nauc_mrr_at_20_diff1": -0.08424470192582584, + "nauc_mrr_at_20_max": -0.17795503904852394, + "nauc_mrr_at_20_std": 0.1104902953039136, + "nauc_mrr_at_3_diff1": -0.1402248948467282, + "nauc_mrr_at_3_max": -0.31580974220123603, + "nauc_mrr_at_3_std": 0.17416556190835358, + "nauc_mrr_at_5_diff1": -0.15841231921355517, + "nauc_mrr_at_5_max": -0.3179899280988303, + "nauc_mrr_at_5_std": 0.1366641521312719, + "nauc_ndcg_at_1000_diff1": -0.018919117530337048, + "nauc_ndcg_at_1000_max": -0.02542094365829901, + "nauc_ndcg_at_1000_std": -0.021534573642249994, + "nauc_ndcg_at_100_diff1": -0.017686450068465382, + "nauc_ndcg_at_100_max": -0.04548959801591481, + "nauc_ndcg_at_100_std": 0.015454458439745997, + "nauc_ndcg_at_10_diff1": -0.028552771179410356, + "nauc_ndcg_at_10_max": -0.12273586953062708, + "nauc_ndcg_at_10_std": 0.08014029086775175, + "nauc_ndcg_at_1_diff1": -0.1944247218787479, + "nauc_ndcg_at_1_max": -0.3354241096662269, + "nauc_ndcg_at_1_std": 0.4450028773454104, + "nauc_ndcg_at_20_diff1": -0.05214858732360392, + "nauc_ndcg_at_20_max": -0.08963785551621077, + "nauc_ndcg_at_20_std": 0.045550057719749015, + "nauc_ndcg_at_3_diff1": -0.12332101174063706, + "nauc_ndcg_at_3_max": -0.3071593376687786, + "nauc_ndcg_at_3_std": 0.12412247819018539, + "nauc_ndcg_at_5_diff1": -0.1544267833898822, + "nauc_ndcg_at_5_max": -0.3115258886448467, + "nauc_ndcg_at_5_std": 0.06815859656031897, + "nauc_precision_at_1000_diff1": -0.012237663026954395, + "nauc_precision_at_1000_max": -0.0008948933508857579, + "nauc_precision_at_1000_std": -0.042588574358361955, + "nauc_precision_at_100_diff1": 0.011990603019429898, + "nauc_precision_at_100_max": 0.010418393816588597, + "nauc_precision_at_100_std": -0.01217910970162782, + "nauc_precision_at_10_diff1": 0.03798473997134296, + "nauc_precision_at_10_max": -0.01304984986946212, + "nauc_precision_at_10_std": 0.027930405132488848, + "nauc_precision_at_1_diff1": -0.1944247218787479, + "nauc_precision_at_1_max": -0.3354241096662269, + "nauc_precision_at_1_std": 0.4450028773454104, + "nauc_precision_at_20_diff1": -0.029722434420407465, + "nauc_precision_at_20_max": -0.0137836750576958, + "nauc_precision_at_20_std": -0.007231672553960966, + "nauc_precision_at_3_diff1": -0.09083751139760847, + "nauc_precision_at_3_max": -0.2902126302548852, + "nauc_precision_at_3_std": 0.03235437196836829, + "nauc_precision_at_5_diff1": -0.15009457144605992, + "nauc_precision_at_5_max": -0.30059544823641665, + "nauc_precision_at_5_std": -0.04922271824955771, + "nauc_recall_at_1000_diff1": -0.01223766302695396, + "nauc_recall_at_1000_max": -0.0008948933508855049, + "nauc_recall_at_1000_std": -0.04258857435836172, + "nauc_recall_at_100_diff1": 0.01199060301942994, + "nauc_recall_at_100_max": 0.010418393816588784, + "nauc_recall_at_100_std": -0.012179109701627644, + "nauc_recall_at_10_diff1": 0.03798473997134306, + "nauc_recall_at_10_max": -0.01304984986946202, + "nauc_recall_at_10_std": 0.027930405132488848, + "nauc_recall_at_1_diff1": -0.1944247218787479, + "nauc_recall_at_1_max": -0.3354241096662269, + "nauc_recall_at_1_std": 0.4450028773454104, + "nauc_recall_at_20_diff1": -0.02972243442040767, + "nauc_recall_at_20_max": -0.0137836750576961, + "nauc_recall_at_20_std": -0.007231672553961062, + "nauc_recall_at_3_diff1": -0.09083751139760841, + "nauc_recall_at_3_max": -0.29021263025488525, + "nauc_recall_at_3_std": 0.032354371968368316, + "nauc_recall_at_5_diff1": -0.15009457144605967, + "nauc_recall_at_5_max": -0.3005954482364166, + "nauc_recall_at_5_std": -0.04922271824955771, + "ndcg_at_1": 0.00205, + "ndcg_at_10": 0.00593, + "ndcg_at_100": 0.01448, + "ndcg_at_1000": 0.03595, + "ndcg_at_20": 0.00836, + "ndcg_at_3": 0.00372, + "ndcg_at_5": 0.00411, + "precision_at_1": 0.00205, + "precision_at_10": 0.00118, + "precision_at_100": 0.00056, + "precision_at_1000": 0.00024, + "precision_at_20": 0.00107, + "precision_at_3": 0.00171, + "precision_at_5": 0.00123, + "recall_at_1": 0.00205, + "recall_at_10": 0.01177, + "recall_at_100": 0.05629, + "recall_at_1000": 0.24156, + "recall_at_20": 0.02149, + "recall_at_3": 0.00512, + "recall_at_5": 0.00614 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/SpartQA.json b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/SpartQA.json new file mode 100644 index 000000000..e298941a1 --- /dev/null +++ b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/SpartQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 29.238372802734375, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02339, + "map_at_1": 0.00352, + "map_at_10": 0.01248, + "map_at_100": 0.0196, + "map_at_1000": 0.02093, + "map_at_20": 0.01583, + "map_at_3": 0.00668, + "map_at_5": 0.00904, + "mrr_at_1": 0.006121313299944352, + "mrr_at_10": 0.021177712413104774, + "mrr_at_100": 0.030813440560605827, + "mrr_at_1000": 0.032282710222212185, + "mrr_at_20": 0.02575921517359008, + "mrr_at_3": 0.012057132257466147, + "mrr_at_5": 0.015604711556297552, + "nauc_map_at_1000_diff1": -0.07875166338651592, + "nauc_map_at_1000_max": -0.2276488843594935, + "nauc_map_at_1000_std": 0.3160724552136133, + "nauc_map_at_100_diff1": -0.08048268700520521, + "nauc_map_at_100_max": -0.2219796517356918, + "nauc_map_at_100_std": 0.3059076597793812, + "nauc_map_at_10_diff1": -0.15194131688163193, + "nauc_map_at_10_max": -0.21962730412441314, + "nauc_map_at_10_std": 0.3264894052199617, + "nauc_map_at_1_diff1": -0.4018543909187729, + "nauc_map_at_1_max": -0.44594132873458275, + "nauc_map_at_1_std": 0.3863588743284308, + "nauc_map_at_20_diff1": -0.10960635258239915, + "nauc_map_at_20_max": -0.21280344689327685, + "nauc_map_at_20_std": 0.30935406003394916, + "nauc_map_at_3_diff1": -0.30073108044350866, + "nauc_map_at_3_max": -0.3404731084884786, + "nauc_map_at_3_std": 0.3779976709697113, + "nauc_map_at_5_diff1": -0.2188339448035192, + "nauc_map_at_5_max": -0.24215420155633974, + "nauc_map_at_5_std": 0.37447141078692986, + "nauc_mrr_at_1000_diff1": -0.06798316575887926, + "nauc_mrr_at_1000_max": -0.17828293231547765, + "nauc_mrr_at_1000_std": 0.3049615926072812, + "nauc_mrr_at_100_diff1": -0.06749605345116287, + "nauc_mrr_at_100_max": -0.17697400483681655, + "nauc_mrr_at_100_std": 0.29861686962155665, + "nauc_mrr_at_10_diff1": -0.1365938090968957, + "nauc_mrr_at_10_max": -0.17647121236131913, + "nauc_mrr_at_10_std": 0.31984216203885646, + "nauc_mrr_at_1_diff1": -0.4292410034632611, + "nauc_mrr_at_1_max": -0.40189897167442956, + "nauc_mrr_at_1_std": 0.40521548077476666, + "nauc_mrr_at_20_diff1": -0.09551334375376612, + "nauc_mrr_at_20_max": -0.17174388697994067, + "nauc_mrr_at_20_std": 0.30428754535206626, + "nauc_mrr_at_3_diff1": -0.2717616628582739, + "nauc_mrr_at_3_max": -0.2770234392574547, + "nauc_mrr_at_3_std": 0.36912833856215405, + "nauc_mrr_at_5_diff1": -0.2111247263854943, + "nauc_mrr_at_5_max": -0.1905882152495958, + "nauc_mrr_at_5_std": 0.36388084524630265, + "nauc_ndcg_at_1000_diff1": 0.05773992344590306, + "nauc_ndcg_at_1000_max": -0.2673913063123951, + "nauc_ndcg_at_1000_std": 0.3849086592707392, + "nauc_ndcg_at_100_diff1": 0.02848753491718586, + "nauc_ndcg_at_100_max": -0.19836959364824855, + "nauc_ndcg_at_100_std": 0.2746853860835464, + "nauc_ndcg_at_10_diff1": -0.0837150116018595, + "nauc_ndcg_at_10_max": -0.1657310452680158, + "nauc_ndcg_at_10_std": 0.29318121532899016, + "nauc_ndcg_at_1_diff1": -0.4292410034632611, + "nauc_ndcg_at_1_max": -0.40189897167442956, + "nauc_ndcg_at_1_std": 0.40521548077476666, + "nauc_ndcg_at_20_diff1": -0.02588201077241353, + "nauc_ndcg_at_20_max": -0.16963471958431117, + "nauc_ndcg_at_20_std": 0.27180314608303474, + "nauc_ndcg_at_3_diff1": -0.26534329461219613, + "nauc_ndcg_at_3_max": -0.29786725719048796, + "nauc_ndcg_at_3_std": 0.36656780125794625, + "nauc_ndcg_at_5_diff1": -0.17044133898741426, + "nauc_ndcg_at_5_max": -0.17614577186648855, + "nauc_ndcg_at_5_std": 0.362709720044383, + "nauc_precision_at_1000_diff1": 0.15763615256509902, + "nauc_precision_at_1000_max": -0.2680316830029179, + "nauc_precision_at_1000_std": 0.3430650651696016, + "nauc_precision_at_100_diff1": 0.11419644620599007, + "nauc_precision_at_100_max": -0.18431802719883553, + "nauc_precision_at_100_std": 0.2494193809932485, + "nauc_precision_at_10_diff1": -0.0037100534481429534, + "nauc_precision_at_10_max": -0.10928945812109546, + "nauc_precision_at_10_std": 0.253736348813989, + "nauc_precision_at_1_diff1": -0.4292410034632611, + "nauc_precision_at_1_max": -0.40189897167442956, + "nauc_precision_at_1_std": 0.40521548077476666, + "nauc_precision_at_20_diff1": 0.04741702735722637, + "nauc_precision_at_20_max": -0.13418079225923288, + "nauc_precision_at_20_std": 0.23942166284901578, + "nauc_precision_at_3_diff1": -0.1832564242813036, + "nauc_precision_at_3_max": -0.21124394289288778, + "nauc_precision_at_3_std": 0.34348782557621393, + "nauc_precision_at_5_diff1": -0.10207509270523334, + "nauc_precision_at_5_max": -0.07292549974168683, + "nauc_precision_at_5_std": 0.3403104412988971, + "nauc_recall_at_1000_diff1": 0.11494672842609896, + "nauc_recall_at_1000_max": -0.2814747895374758, + "nauc_recall_at_1000_std": 0.4059799996356247, + "nauc_recall_at_100_diff1": 0.06521981028453704, + "nauc_recall_at_100_max": -0.18649378667742192, + "nauc_recall_at_100_std": 0.24215892275075387, + "nauc_recall_at_10_diff1": -0.033549853674881475, + "nauc_recall_at_10_max": -0.13989678521528812, + "nauc_recall_at_10_std": 0.26477673423125947, + "nauc_recall_at_1_diff1": -0.4018543909187729, + "nauc_recall_at_1_max": -0.44594132873458275, + "nauc_recall_at_1_std": 0.3863588743284308, + "nauc_recall_at_20_diff1": 0.022541953332463737, + "nauc_recall_at_20_max": -0.1593542268510809, + "nauc_recall_at_20_std": 0.24606669939073547, + "nauc_recall_at_3_diff1": -0.2343742058124998, + "nauc_recall_at_3_max": -0.27983886975062533, + "nauc_recall_at_3_std": 0.35423255782382984, + "nauc_recall_at_5_diff1": -0.10982508185762525, + "nauc_recall_at_5_max": -0.12218720966965085, + "nauc_recall_at_5_std": 0.3558657250852396, + "ndcg_at_1": 0.00612, + "ndcg_at_10": 0.02339, + "ndcg_at_100": 0.0675, + "ndcg_at_1000": 0.11209, + "ndcg_at_20": 0.03663, + "ndcg_at_3": 0.00904, + "ndcg_at_5": 0.01377, + "precision_at_1": 0.00612, + "precision_at_10": 0.00818, + "precision_at_100": 0.00401, + "precision_at_1000": 0.00097, + "precision_at_20": 0.00775, + "precision_at_3": 0.00686, + "precision_at_5": 0.00729, + "recall_at_1": 0.00352, + "recall_at_10": 0.04767, + "recall_at_100": 0.24643, + "recall_at_1000": 0.56928, + "recall_at_20": 0.09525, + "recall_at_3": 0.01076, + "recall_at_5": 0.02124 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL1.json b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL1.json new file mode 100644 index 000000000..cd8d6c8fc --- /dev/null +++ b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL1.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 12.97503399848938, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01167, + "map_at_1": 0.00275, + "map_at_10": 0.00782, + "map_at_100": 0.01099, + "map_at_1000": 0.01204, + "map_at_20": 0.00918, + "map_at_3": 0.00542, + "map_at_5": 0.00638, + "mrr_at_1": 0.00275, + "mrr_at_10": 0.00782380952380952, + "mrr_at_100": 0.010992834031401257, + "mrr_at_1000": 0.012039808288493768, + "mrr_at_20": 0.00917694926869657, + "mrr_at_3": 0.005416666666666664, + "mrr_at_5": 0.006379166666666663, + "nauc_map_at_1000_diff1": 0.034716353908599625, + "nauc_map_at_1000_max": 0.08244310373594997, + "nauc_map_at_1000_std": 0.055180697283908973, + "nauc_map_at_100_diff1": 0.03540846674409166, + "nauc_map_at_100_max": 0.0818801088851083, + "nauc_map_at_100_std": 0.05639826520917934, + "nauc_map_at_10_diff1": 0.05933569471578252, + "nauc_map_at_10_max": 0.08715101027017248, + "nauc_map_at_10_std": 0.08900324097761056, + "nauc_map_at_1_diff1": 0.09686074590823739, + "nauc_map_at_1_max": 0.16908554284459842, + "nauc_map_at_1_std": 0.15152328219137984, + "nauc_map_at_20_diff1": 0.045262272968292924, + "nauc_map_at_20_max": 0.08515575632606956, + "nauc_map_at_20_std": 0.06826460352169186, + "nauc_map_at_3_diff1": 0.13590844358217588, + "nauc_map_at_3_max": 0.11982828011805738, + "nauc_map_at_3_std": 0.13474850880270797, + "nauc_map_at_5_diff1": 0.10442659239678966, + "nauc_map_at_5_max": 0.08778369295537347, + "nauc_map_at_5_std": 0.10833333187289182, + "nauc_mrr_at_1000_diff1": 0.03471611597990856, + "nauc_mrr_at_1000_max": 0.08244324999448054, + "nauc_mrr_at_1000_std": 0.05518122058853734, + "nauc_mrr_at_100_diff1": 0.03540846674409166, + "nauc_mrr_at_100_max": 0.0818801088851083, + "nauc_mrr_at_100_std": 0.05639826520917934, + "nauc_mrr_at_10_diff1": 0.05933569471578252, + "nauc_mrr_at_10_max": 0.08715101027017248, + "nauc_mrr_at_10_std": 0.08900324097761056, + "nauc_mrr_at_1_diff1": 0.09686074590823739, + "nauc_mrr_at_1_max": 0.16908554284459842, + "nauc_mrr_at_1_std": 0.15152328219137984, + "nauc_mrr_at_20_diff1": 0.045262272968292924, + "nauc_mrr_at_20_max": 0.08515575632606956, + "nauc_mrr_at_20_std": 0.06826460352169186, + "nauc_mrr_at_3_diff1": 0.13590844358217588, + "nauc_mrr_at_3_max": 0.11982828011805738, + "nauc_mrr_at_3_std": 0.13474850880270797, + "nauc_mrr_at_5_diff1": 0.10442659239678966, + "nauc_mrr_at_5_max": 0.08778369295537347, + "nauc_mrr_at_5_std": 0.10833333187289182, + "nauc_ndcg_at_1000_diff1": 0.004571806873222059, + "nauc_ndcg_at_1000_max": 0.08640273993727109, + "nauc_ndcg_at_1000_std": 0.026283022768352832, + "nauc_ndcg_at_100_diff1": -0.003363780801955333, + "nauc_ndcg_at_100_max": 0.07045644694210323, + "nauc_ndcg_at_100_std": 0.015214347811911076, + "nauc_ndcg_at_10_diff1": 0.02480977822960526, + "nauc_ndcg_at_10_max": 0.07108721838538748, + "nauc_ndcg_at_10_std": 0.06610674548265089, + "nauc_ndcg_at_1_diff1": 0.09686074590823739, + "nauc_ndcg_at_1_max": 0.16908554284459842, + "nauc_ndcg_at_1_std": 0.15152328219137984, + "nauc_ndcg_at_20_diff1": 0.005111409599225415, + "nauc_ndcg_at_20_max": 0.07529693852824443, + "nauc_ndcg_at_20_std": 0.031333978730454064, + "nauc_ndcg_at_3_diff1": 0.14228727873789113, + "nauc_ndcg_at_3_max": 0.11097186160744242, + "nauc_ndcg_at_3_std": 0.12748667608036934, + "nauc_ndcg_at_5_diff1": 0.09631910360051114, + "nauc_ndcg_at_5_max": 0.0669452612164149, + "nauc_ndcg_at_5_std": 0.09019281080279343, + "nauc_precision_at_1000_diff1": 0.0018317616992713963, + "nauc_precision_at_1000_max": 0.09799368025829432, + "nauc_precision_at_1000_std": 0.02656971983221125, + "nauc_precision_at_100_diff1": -0.018813000476445723, + "nauc_precision_at_100_max": 0.06697598287783617, + "nauc_precision_at_100_std": -0.0024626903843577223, + "nauc_precision_at_10_diff1": -0.017297930709713385, + "nauc_precision_at_10_max": 0.05443454548441323, + "nauc_precision_at_10_std": 0.041122969176938244, + "nauc_precision_at_1_diff1": 0.09686074590823739, + "nauc_precision_at_1_max": 0.16908554284459842, + "nauc_precision_at_1_std": 0.15152328219137984, + "nauc_precision_at_20_diff1": -0.028405528123133128, + "nauc_precision_at_20_max": 0.07087744056733979, + "nauc_precision_at_20_std": 0.0012659597650117767, + "nauc_precision_at_3_diff1": 0.1532643456442759, + "nauc_precision_at_3_max": 0.09558444948839373, + "nauc_precision_at_3_std": 0.11417051610236478, + "nauc_precision_at_5_diff1": 0.08238181836249997, + "nauc_precision_at_5_max": 0.03513400709537021, + "nauc_precision_at_5_std": 0.06169692633336321, + "nauc_recall_at_1000_diff1": 0.0018317616992719712, + "nauc_recall_at_1000_max": 0.09799368025829494, + "nauc_recall_at_1000_std": 0.026569719832212072, + "nauc_recall_at_100_diff1": -0.018813000476445792, + "nauc_recall_at_100_max": 0.06697598287783615, + "nauc_recall_at_100_std": -0.002462690384357907, + "nauc_recall_at_10_diff1": -0.01729793070971348, + "nauc_recall_at_10_max": 0.05443454548441328, + "nauc_recall_at_10_std": 0.04112296917693836, + "nauc_recall_at_1_diff1": 0.09686074590823739, + "nauc_recall_at_1_max": 0.16908554284459842, + "nauc_recall_at_1_std": 0.15152328219137984, + "nauc_recall_at_20_diff1": -0.028405528123133118, + "nauc_recall_at_20_max": 0.07087744056733979, + "nauc_recall_at_20_std": 0.001265959765011777, + "nauc_recall_at_3_diff1": 0.15326434564427602, + "nauc_recall_at_3_max": 0.09558444948839386, + "nauc_recall_at_3_std": 0.11417051610236484, + "nauc_recall_at_5_diff1": 0.08238181836249991, + "nauc_recall_at_5_max": 0.03513400709537014, + "nauc_recall_at_5_std": 0.06169692633336318, + "ndcg_at_1": 0.00275, + "ndcg_at_10": 0.01167, + "ndcg_at_100": 0.03117, + "ndcg_at_1000": 0.0697, + "ndcg_at_20": 0.01681, + "ndcg_at_3": 0.00639, + "ndcg_at_5": 0.00814, + "precision_at_1": 0.00275, + "precision_at_10": 0.00245, + "precision_at_100": 0.00125, + "precision_at_1000": 0.00045, + "precision_at_20": 0.00226, + "precision_at_3": 0.00308, + "precision_at_5": 0.0027, + "recall_at_1": 0.00275, + "recall_at_10": 0.0245, + "recall_at_100": 0.12525, + "recall_at_1000": 0.45275, + "recall_at_20": 0.04525, + "recall_at_3": 0.00925, + "recall_at_5": 0.0135 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL2Fact.json b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL2Fact.json new file mode 100644 index 000000000..3c77568c5 --- /dev/null +++ b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL2Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 66.94777202606201, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.21191, + "map_at_1": 0.09116, + "map_at_10": 0.16689, + "map_at_100": 0.17895, + "map_at_1000": 0.17984, + "map_at_20": 0.17377, + "map_at_3": 0.1407, + "map_at_5": 0.15499, + "mrr_at_1": 0.09116175653140633, + "mrr_at_10": 0.16688504195452533, + "mrr_at_100": 0.17895134426376777, + "mrr_at_1000": 0.1798432507685984, + "mrr_at_20": 0.1737738848129987, + "mrr_at_3": 0.14069544808844453, + "mrr_at_5": 0.15499042678031066, + "nauc_map_at_1000_diff1": -0.006298483104379233, + "nauc_map_at_1000_max": 0.007931154837958572, + "nauc_map_at_1000_std": 0.07951130090010758, + "nauc_map_at_100_diff1": -0.006416052635138902, + "nauc_map_at_100_max": 0.008282209458923693, + "nauc_map_at_100_std": 0.0802200373976459, + "nauc_map_at_10_diff1": -0.0025176579929753885, + "nauc_map_at_10_max": 0.011153128613947298, + "nauc_map_at_10_std": 0.07064485463961155, + "nauc_map_at_1_diff1": 0.036917069537459386, + "nauc_map_at_1_max": -0.008425340955864133, + "nauc_map_at_1_std": 0.041665421147666186, + "nauc_map_at_20_diff1": -0.004682414546597479, + "nauc_map_at_20_max": 0.010395357727280575, + "nauc_map_at_20_std": 0.07783954574970528, + "nauc_map_at_3_diff1": 0.009331074536612766, + "nauc_map_at_3_max": 0.014051600247510032, + "nauc_map_at_3_std": 0.054955310956154135, + "nauc_map_at_5_diff1": -3.701787472447933e-05, + "nauc_map_at_5_max": 0.012262902274507444, + "nauc_map_at_5_std": 0.060158549456079034, + "nauc_mrr_at_1000_diff1": -0.006298483104379233, + "nauc_mrr_at_1000_max": 0.007931154837958572, + "nauc_mrr_at_1000_std": 0.07951130090010758, + "nauc_mrr_at_100_diff1": -0.006416052635138902, + "nauc_mrr_at_100_max": 0.008282209458923693, + "nauc_mrr_at_100_std": 0.0802200373976459, + "nauc_mrr_at_10_diff1": -0.0025176579929753885, + "nauc_mrr_at_10_max": 0.011153128613947298, + "nauc_mrr_at_10_std": 0.07064485463961155, + "nauc_mrr_at_1_diff1": 0.036917069537459386, + "nauc_mrr_at_1_max": -0.008425340955864133, + "nauc_mrr_at_1_std": 0.041665421147666186, + "nauc_mrr_at_20_diff1": -0.004682414546597479, + "nauc_mrr_at_20_max": 0.010395357727280575, + "nauc_mrr_at_20_std": 0.07783954574970528, + "nauc_mrr_at_3_diff1": 0.009331074536612766, + "nauc_mrr_at_3_max": 0.014051600247510032, + "nauc_mrr_at_3_std": 0.054955310956154135, + "nauc_mrr_at_5_diff1": -3.701787472447933e-05, + "nauc_mrr_at_5_max": 0.012262902274507444, + "nauc_mrr_at_5_std": 0.060158549456079034, + "nauc_ndcg_at_1000_diff1": -0.03341897238356552, + "nauc_ndcg_at_1000_max": -0.01174508432507716, + "nauc_ndcg_at_1000_std": 0.10806491058955774, + "nauc_ndcg_at_100_diff1": -0.03597893524763694, + "nauc_ndcg_at_100_max": -0.005219988855532889, + "nauc_ndcg_at_100_std": 0.1249568077357945, + "nauc_ndcg_at_10_diff1": -0.016624353737639087, + "nauc_ndcg_at_10_max": 0.013028514280363706, + "nauc_ndcg_at_10_std": 0.08936959631755693, + "nauc_ndcg_at_1_diff1": 0.036917069537459386, + "nauc_ndcg_at_1_max": -0.008425340955864133, + "nauc_ndcg_at_1_std": 0.041665421147666186, + "nauc_ndcg_at_20_diff1": -0.02322021838273366, + "nauc_ndcg_at_20_max": 0.010571181978338133, + "nauc_ndcg_at_20_std": 0.1120774027263262, + "nauc_ndcg_at_3_diff1": 0.002999040242136016, + "nauc_ndcg_at_3_max": 0.018650109514134684, + "nauc_ndcg_at_3_std": 0.05839445711058803, + "nauc_ndcg_at_5_diff1": -0.011653168829267922, + "nauc_ndcg_at_5_max": 0.015384641033591856, + "nauc_ndcg_at_5_std": 0.06661507734209272, + "nauc_precision_at_1000_diff1": -0.2345266998146466, + "nauc_precision_at_1000_max": -0.25140977916865, + "nauc_precision_at_1000_std": 0.21603126527901415, + "nauc_precision_at_100_diff1": -0.13565851089710257, + "nauc_precision_at_100_max": -0.06985480820821136, + "nauc_precision_at_100_std": 0.2713685940905183, + "nauc_precision_at_10_diff1": -0.04581695143688483, + "nauc_precision_at_10_max": 0.015570848754307453, + "nauc_precision_at_10_std": 0.1319249032342841, + "nauc_precision_at_1_diff1": 0.036917069537459386, + "nauc_precision_at_1_max": -0.008425340955864133, + "nauc_precision_at_1_std": 0.041665421147666186, + "nauc_precision_at_20_diff1": -0.06438780611001234, + "nauc_precision_at_20_max": 0.008432806445550178, + "nauc_precision_at_20_std": 0.19718479649515586, + "nauc_precision_at_3_diff1": -0.010705591981406052, + "nauc_precision_at_3_max": 0.028470659323329133, + "nauc_precision_at_3_std": 0.06592949400451852, + "nauc_precision_at_5_diff1": -0.03627097650940208, + "nauc_precision_at_5_max": 0.02114828070100837, + "nauc_precision_at_5_std": 0.08042835128443585, + "nauc_recall_at_1000_diff1": -0.23452669981464444, + "nauc_recall_at_1000_max": -0.2514097791686471, + "nauc_recall_at_1000_std": 0.21603126527901617, + "nauc_recall_at_100_diff1": -0.13565851089710326, + "nauc_recall_at_100_max": -0.06985480820821136, + "nauc_recall_at_100_std": 0.27136859409051767, + "nauc_recall_at_10_diff1": -0.04581695143688501, + "nauc_recall_at_10_max": 0.015570848754307497, + "nauc_recall_at_10_std": 0.13192490323428366, + "nauc_recall_at_1_diff1": 0.036917069537459386, + "nauc_recall_at_1_max": -0.008425340955864133, + "nauc_recall_at_1_std": 0.041665421147666186, + "nauc_recall_at_20_diff1": -0.06438780611001253, + "nauc_recall_at_20_max": 0.00843280644554995, + "nauc_recall_at_20_std": 0.19718479649515605, + "nauc_recall_at_3_diff1": -0.010705591981405771, + "nauc_recall_at_3_max": 0.028470659323329213, + "nauc_recall_at_3_std": 0.06592949400451864, + "nauc_recall_at_5_diff1": -0.03627097650940234, + "nauc_recall_at_5_max": 0.021148280701008163, + "nauc_recall_at_5_std": 0.08042835128443565, + "ndcg_at_1": 0.09116, + "ndcg_at_10": 0.21191, + "ndcg_at_100": 0.27443, + "ndcg_at_1000": 0.30197, + "ndcg_at_20": 0.23692, + "ndcg_at_3": 0.15721, + "ndcg_at_5": 0.18295, + "precision_at_1": 0.09116, + "precision_at_10": 0.03574, + "precision_at_100": 0.00659, + "precision_at_1000": 0.00088, + "precision_at_20": 0.02281, + "precision_at_3": 0.06837, + "precision_at_5": 0.05351, + "recall_at_1": 0.09116, + "recall_at_10": 0.35742, + "recall_at_100": 0.65851, + "recall_at_1000": 0.88382, + "recall_at_20": 0.45618, + "recall_at_3": 0.20511, + "recall_at_5": 0.26756 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL2Pure.json b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL2Pure.json new file mode 100644 index 000000000..ae1d17ca8 --- /dev/null +++ b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL2Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 21.459189653396606, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02101, + "map_at_1": 0.00723, + "map_at_10": 0.01538, + "map_at_100": 0.01905, + "map_at_1000": 0.02028, + "map_at_20": 0.01685, + "map_at_3": 0.01152, + "map_at_5": 0.01384, + "mrr_at_1": 0.007226236798221234, + "mrr_at_10": 0.015380752387422765, + "mrr_at_100": 0.019049568108420976, + "mrr_at_1000": 0.020284746216616602, + "mrr_at_20": 0.016846622043803314, + "mrr_at_3": 0.011518744981780005, + "mrr_at_5": 0.013844110925822994, + "nauc_map_at_1000_diff1": 0.008495991707315305, + "nauc_map_at_1000_max": 0.18117204618244187, + "nauc_map_at_1000_std": 0.32257149136725094, + "nauc_map_at_100_diff1": 0.01277433223514697, + "nauc_map_at_100_max": 0.1876003770353277, + "nauc_map_at_100_std": 0.32718550202875807, + "nauc_map_at_10_diff1": 0.019290805599994725, + "nauc_map_at_10_max": 0.21580568699007435, + "nauc_map_at_10_std": 0.35509376958832817, + "nauc_map_at_1_diff1": 0.09142396603879664, + "nauc_map_at_1_max": 0.2228673636995562, + "nauc_map_at_1_std": 0.38123545748169413, + "nauc_map_at_20_diff1": 0.00999571855351165, + "nauc_map_at_20_max": 0.2047232984419753, + "nauc_map_at_20_std": 0.337714541757184, + "nauc_map_at_3_diff1": 0.03469441290092779, + "nauc_map_at_3_max": 0.24693373925137505, + "nauc_map_at_3_std": 0.40708905966916986, + "nauc_map_at_5_diff1": 0.024800707091369563, + "nauc_map_at_5_max": 0.22394980186285074, + "nauc_map_at_5_std": 0.3662486844124969, + "nauc_mrr_at_1000_diff1": 0.008495996965834305, + "nauc_mrr_at_1000_max": 0.18117205185920013, + "nauc_mrr_at_1000_std": 0.32257149403017177, + "nauc_mrr_at_100_diff1": 0.01277433223514697, + "nauc_mrr_at_100_max": 0.1876003770353277, + "nauc_mrr_at_100_std": 0.32718550202875807, + "nauc_mrr_at_10_diff1": 0.019290805599994725, + "nauc_mrr_at_10_max": 0.21580568699007435, + "nauc_mrr_at_10_std": 0.35509376958832817, + "nauc_mrr_at_1_diff1": 0.09142396603879664, + "nauc_mrr_at_1_max": 0.2228673636995562, + "nauc_mrr_at_1_std": 0.38123545748169413, + "nauc_mrr_at_20_diff1": 0.00999571855351165, + "nauc_mrr_at_20_max": 0.2047232984419753, + "nauc_mrr_at_20_std": 0.337714541757184, + "nauc_mrr_at_3_diff1": 0.03469441290092779, + "nauc_mrr_at_3_max": 0.24693373925137505, + "nauc_mrr_at_3_std": 0.40708905966916986, + "nauc_mrr_at_5_diff1": 0.024800707091369563, + "nauc_mrr_at_5_max": 0.22394980186285074, + "nauc_mrr_at_5_std": 0.3662486844124969, + "nauc_ndcg_at_1000_diff1": -0.05329878015255362, + "nauc_ndcg_at_1000_max": 0.05872494047133727, + "nauc_ndcg_at_1000_std": 0.22248237074303912, + "nauc_ndcg_at_100_diff1": -0.005102946703490659, + "nauc_ndcg_at_100_max": 0.1273609669383053, + "nauc_ndcg_at_100_std": 0.26925439219022457, + "nauc_ndcg_at_10_diff1": 0.0036015201392425636, + "nauc_ndcg_at_10_max": 0.20107849955726673, + "nauc_ndcg_at_10_std": 0.32950708620676394, + "nauc_ndcg_at_1_diff1": 0.09142396603879664, + "nauc_ndcg_at_1_max": 0.2228673636995562, + "nauc_ndcg_at_1_std": 0.38123545748169413, + "nauc_ndcg_at_20_diff1": -0.01545059584423381, + "nauc_ndcg_at_20_max": 0.17788511930101825, + "nauc_ndcg_at_20_std": 0.2957905586136637, + "nauc_ndcg_at_3_diff1": 0.02222697893976097, + "nauc_ndcg_at_3_max": 0.2492138787642006, + "nauc_ndcg_at_3_std": 0.4071176596934938, + "nauc_ndcg_at_5_diff1": 0.011209311392280734, + "nauc_ndcg_at_5_max": 0.21535936786037033, + "nauc_ndcg_at_5_std": 0.34721105115302253, + "nauc_precision_at_1000_diff1": -0.11145742059878702, + "nauc_precision_at_1000_max": -0.04636315809593957, + "nauc_precision_at_1000_std": 0.14399267401653956, + "nauc_precision_at_100_diff1": -0.01531365912419819, + "nauc_precision_at_100_max": 0.0837728439816157, + "nauc_precision_at_100_std": 0.23094777743722741, + "nauc_precision_at_10_diff1": -0.016004578742944357, + "nauc_precision_at_10_max": 0.17976636759747613, + "nauc_precision_at_10_std": 0.2938798466797885, + "nauc_precision_at_1_diff1": 0.09142396603879664, + "nauc_precision_at_1_max": 0.2228673636995562, + "nauc_precision_at_1_std": 0.38123545748169413, + "nauc_precision_at_20_diff1": -0.04216094375449059, + "nauc_precision_at_20_max": 0.14725182694072175, + "nauc_precision_at_20_std": 0.25014897131460656, + "nauc_precision_at_3_diff1": -0.0021131793893935736, + "nauc_precision_at_3_max": 0.25309961876540793, + "nauc_precision_at_3_std": 0.4061105044011794, + "nauc_precision_at_5_diff1": -0.00940681656725155, + "nauc_precision_at_5_max": 0.2004014540779532, + "nauc_precision_at_5_std": 0.3147236724513099, + "nauc_recall_at_1000_diff1": -0.11145742059878659, + "nauc_recall_at_1000_max": -0.04636315809593879, + "nauc_recall_at_1000_std": 0.14399267401654042, + "nauc_recall_at_100_diff1": -0.015313659124198284, + "nauc_recall_at_100_max": 0.08377284398161564, + "nauc_recall_at_100_std": 0.23094777743722716, + "nauc_recall_at_10_diff1": -0.016004578742944555, + "nauc_recall_at_10_max": 0.1797663675974761, + "nauc_recall_at_10_std": 0.29387984667978845, + "nauc_recall_at_1_diff1": 0.09142396603879664, + "nauc_recall_at_1_max": 0.2228673636995562, + "nauc_recall_at_1_std": 0.38123545748169413, + "nauc_recall_at_20_diff1": -0.04216094375449059, + "nauc_recall_at_20_max": 0.14725182694072153, + "nauc_recall_at_20_std": 0.2501489713146063, + "nauc_recall_at_3_diff1": -0.0021131793893935393, + "nauc_recall_at_3_max": 0.25309961876540804, + "nauc_recall_at_3_std": 0.4061105044011796, + "nauc_recall_at_5_diff1": -0.009406816567251656, + "nauc_recall_at_5_max": 0.20040145407795323, + "nauc_recall_at_5_std": 0.3147236724513096, + "ndcg_at_1": 0.00723, + "ndcg_at_10": 0.02101, + "ndcg_at_100": 0.04461, + "ndcg_at_1000": 0.0893, + "ndcg_at_20": 0.02644, + "ndcg_at_3": 0.01303, + "ndcg_at_5": 0.01722, + "precision_at_1": 0.00723, + "precision_at_10": 0.00395, + "precision_at_100": 0.00164, + "precision_at_1000": 0.00054, + "precision_at_20": 0.00306, + "precision_at_3": 0.00581, + "precision_at_5": 0.00552, + "recall_at_1": 0.00723, + "recall_at_10": 0.03947, + "recall_at_100": 0.16379, + "recall_at_1000": 0.54215, + "recall_at_20": 0.06115, + "recall_at_3": 0.01742, + "recall_at_5": 0.02761 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL3Fact.json b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL3Fact.json new file mode 100644 index 000000000..0a0b7ac5d --- /dev/null +++ b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL3Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 59.28880548477173, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.17588, + "map_at_1": 0.03818, + "map_at_10": 0.12463, + "map_at_100": 0.13632, + "map_at_1000": 0.13726, + "map_at_20": 0.1314, + "map_at_3": 0.09538, + "map_at_5": 0.11107, + "mrr_at_1": 0.03818346136466335, + "mrr_at_10": 0.12462594768288394, + "mrr_at_100": 0.1363221058538187, + "mrr_at_1000": 0.13725905177832476, + "mrr_at_20": 0.1314036153598655, + "mrr_at_3": 0.09538334086458777, + "mrr_at_5": 0.11107471004669313, + "nauc_map_at_1000_diff1": -0.053070523093381304, + "nauc_map_at_1000_max": 0.052422813326682, + "nauc_map_at_1000_std": 0.1625654223045779, + "nauc_map_at_100_diff1": -0.05288457239987588, + "nauc_map_at_100_max": 0.052986695556824275, + "nauc_map_at_100_std": 0.1635455219398681, + "nauc_map_at_10_diff1": -0.04908263841513179, + "nauc_map_at_10_max": 0.055413623843405674, + "nauc_map_at_10_std": 0.15193273794835846, + "nauc_map_at_1_diff1": -0.14961383675407514, + "nauc_map_at_1_max": -0.052581448998465743, + "nauc_map_at_1_std": 0.04057950375661227, + "nauc_map_at_20_diff1": -0.05153989606009416, + "nauc_map_at_20_max": 0.054158926581728495, + "nauc_map_at_20_std": 0.16159760243722726, + "nauc_map_at_3_diff1": -0.054119632396056654, + "nauc_map_at_3_max": 0.02889276543965853, + "nauc_map_at_3_std": 0.09815928167736486, + "nauc_map_at_5_diff1": -0.05026282965982091, + "nauc_map_at_5_max": 0.04626213588594972, + "nauc_map_at_5_std": 0.12033438192831708, + "nauc_mrr_at_1000_diff1": -0.053070523093381304, + "nauc_mrr_at_1000_max": 0.052422813326682, + "nauc_mrr_at_1000_std": 0.1625654223045779, + "nauc_mrr_at_100_diff1": -0.05288457239987588, + "nauc_mrr_at_100_max": 0.052986695556824275, + "nauc_mrr_at_100_std": 0.1635455219398681, + "nauc_mrr_at_10_diff1": -0.04908263841513179, + "nauc_mrr_at_10_max": 0.055413623843405674, + "nauc_mrr_at_10_std": 0.15193273794835846, + "nauc_mrr_at_1_diff1": -0.14961383675407514, + "nauc_mrr_at_1_max": -0.052581448998465743, + "nauc_mrr_at_1_std": 0.04057950375661227, + "nauc_mrr_at_20_diff1": -0.05153989606009416, + "nauc_mrr_at_20_max": 0.054158926581728495, + "nauc_mrr_at_20_std": 0.16159760243722726, + "nauc_mrr_at_3_diff1": -0.054119632396056654, + "nauc_mrr_at_3_max": 0.02889276543965853, + "nauc_mrr_at_3_std": 0.09815928167736486, + "nauc_mrr_at_5_diff1": -0.05026282965982091, + "nauc_mrr_at_5_max": 0.04626213588594972, + "nauc_mrr_at_5_std": 0.12033438192831708, + "nauc_ndcg_at_1000_diff1": -0.05533520296108899, + "nauc_ndcg_at_1000_max": 0.05458926859930551, + "nauc_ndcg_at_1000_std": 0.2141880978510369, + "nauc_ndcg_at_100_diff1": -0.05387271141314774, + "nauc_ndcg_at_100_max": 0.06447468101013772, + "nauc_ndcg_at_100_std": 0.2344323691462935, + "nauc_ndcg_at_10_diff1": -0.03916662052099964, + "nauc_ndcg_at_10_max": 0.07803927382891512, + "nauc_ndcg_at_10_std": 0.19816865701000072, + "nauc_ndcg_at_1_diff1": -0.14961383675407514, + "nauc_ndcg_at_1_max": -0.052581448998465743, + "nauc_ndcg_at_1_std": 0.04057950375661227, + "nauc_ndcg_at_20_diff1": -0.04678290475804036, + "nauc_ndcg_at_20_max": 0.07400013483450062, + "nauc_ndcg_at_20_std": 0.22554969444640954, + "nauc_ndcg_at_3_diff1": -0.04436160617149038, + "nauc_ndcg_at_3_max": 0.03752030540601134, + "nauc_ndcg_at_3_std": 0.10585842363299591, + "nauc_ndcg_at_5_diff1": -0.04021333546083567, + "nauc_ndcg_at_5_max": 0.06181098230616475, + "nauc_ndcg_at_5_std": 0.13838905858978554, + "nauc_precision_at_1000_diff1": -0.09926270265458068, + "nauc_precision_at_1000_max": -0.030161291935817767, + "nauc_precision_at_1000_std": 0.36126900741417955, + "nauc_precision_at_100_diff1": -0.0702895473899863, + "nauc_precision_at_100_max": 0.06911582231757087, + "nauc_precision_at_100_std": 0.3919443012309784, + "nauc_precision_at_10_diff1": -0.025642260485227195, + "nauc_precision_at_10_max": 0.11432904086043631, + "nauc_precision_at_10_std": 0.2785584407402518, + "nauc_precision_at_1_diff1": -0.14961383675407514, + "nauc_precision_at_1_max": -0.052581448998465743, + "nauc_precision_at_1_std": 0.04057950375661227, + "nauc_precision_at_20_diff1": -0.04468435309276077, + "nauc_precision_at_20_max": 0.1038328835070601, + "nauc_precision_at_20_std": 0.34287649427771827, + "nauc_precision_at_3_diff1": -0.028163306554911186, + "nauc_precision_at_3_max": 0.05191838517493083, + "nauc_precision_at_3_std": 0.11909793165775594, + "nauc_precision_at_5_diff1": -0.025125849433284355, + "nauc_precision_at_5_max": 0.08704424208702659, + "nauc_precision_at_5_std": 0.1689135260194415, + "nauc_recall_at_1000_diff1": -0.0992627026545825, + "nauc_recall_at_1000_max": -0.030161291935819016, + "nauc_recall_at_1000_std": 0.36126900741417817, + "nauc_recall_at_100_diff1": -0.07028954738998634, + "nauc_recall_at_100_max": 0.0691158223175706, + "nauc_recall_at_100_std": 0.39194430123097806, + "nauc_recall_at_10_diff1": -0.02564226048522745, + "nauc_recall_at_10_max": 0.1143290408604361, + "nauc_recall_at_10_std": 0.27855844074025177, + "nauc_recall_at_1_diff1": -0.14961383675407514, + "nauc_recall_at_1_max": -0.052581448998465743, + "nauc_recall_at_1_std": 0.04057950375661227, + "nauc_recall_at_20_diff1": -0.04468435309276102, + "nauc_recall_at_20_max": 0.10383288350705988, + "nauc_recall_at_20_std": 0.34287649427771855, + "nauc_recall_at_3_diff1": -0.028163306554911286, + "nauc_recall_at_3_max": 0.05191838517493074, + "nauc_recall_at_3_std": 0.11909793165775612, + "nauc_recall_at_5_diff1": -0.02512584943328452, + "nauc_recall_at_5_max": 0.08704424208702641, + "nauc_recall_at_5_std": 0.16891352601944154, + "ndcg_at_1": 0.03818, + "ndcg_at_10": 0.17588, + "ndcg_at_100": 0.23608, + "ndcg_at_1000": 0.26493, + "ndcg_at_20": 0.20056, + "ndcg_at_3": 0.11481, + "ndcg_at_5": 0.14324, + "precision_at_1": 0.03818, + "precision_at_10": 0.03412, + "precision_at_100": 0.0063, + "precision_at_1000": 0.00087, + "precision_at_20": 0.02194, + "precision_at_3": 0.05709, + "precision_at_5": 0.04812, + "recall_at_1": 0.03818, + "recall_at_10": 0.34117, + "recall_at_100": 0.63014, + "recall_at_1000": 0.86624, + "recall_at_20": 0.43877, + "recall_at_3": 0.17126, + "recall_at_5": 0.24062 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL3Pure.json b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL3Pure.json new file mode 100644 index 000000000..d0097507d --- /dev/null +++ b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL3Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 20.179905891418457, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.05986, + "map_at_1": 0.00249, + "map_at_10": 0.03651, + "map_at_100": 0.0449, + "map_at_1000": 0.04607, + "map_at_20": 0.04076, + "map_at_3": 0.02248, + "map_at_5": 0.02947, + "mrr_at_1": 0.0024853140533212833, + "mrr_at_10": 0.03651376426455502, + "mrr_at_100": 0.04489781811703551, + "mrr_at_1000": 0.04607319612976032, + "mrr_at_20": 0.04076473129024089, + "mrr_at_3": 0.02248079530049703, + "mrr_at_5": 0.029473565295978294, + "nauc_map_at_1000_diff1": 0.08829730330412715, + "nauc_map_at_1000_max": 0.38132631196554456, + "nauc_map_at_1000_std": 0.4629614295548509, + "nauc_map_at_100_diff1": 0.08849975791640632, + "nauc_map_at_100_max": 0.3826699863694051, + "nauc_map_at_100_std": 0.464599013180751, + "nauc_map_at_10_diff1": 0.09262180467340206, + "nauc_map_at_10_max": 0.374853625637525, + "nauc_map_at_10_std": 0.4351778892626273, + "nauc_map_at_1_diff1": -0.40726544549893623, + "nauc_map_at_1_max": -0.15167958484944533, + "nauc_map_at_1_std": 0.34853139570984415, + "nauc_map_at_20_diff1": 0.08572771425955591, + "nauc_map_at_20_max": 0.3763794585832061, + "nauc_map_at_20_std": 0.45352913762113745, + "nauc_map_at_3_diff1": 0.07530848812579491, + "nauc_map_at_3_max": 0.35562286514264335, + "nauc_map_at_3_std": 0.396802921482718, + "nauc_map_at_5_diff1": 0.08302152990222149, + "nauc_map_at_5_max": 0.3576968262143065, + "nauc_map_at_5_std": 0.41338731042914795, + "nauc_mrr_at_1000_diff1": 0.08829730330412715, + "nauc_mrr_at_1000_max": 0.38132631196554456, + "nauc_mrr_at_1000_std": 0.4629614295548509, + "nauc_mrr_at_100_diff1": 0.08849975791640632, + "nauc_mrr_at_100_max": 0.3826699863694051, + "nauc_mrr_at_100_std": 0.464599013180751, + "nauc_mrr_at_10_diff1": 0.09262180467340206, + "nauc_mrr_at_10_max": 0.374853625637525, + "nauc_mrr_at_10_std": 0.4351778892626273, + "nauc_mrr_at_1_diff1": -0.40726544549893623, + "nauc_mrr_at_1_max": -0.15167958484944533, + "nauc_mrr_at_1_std": 0.34853139570984415, + "nauc_mrr_at_20_diff1": 0.08572771425955591, + "nauc_mrr_at_20_max": 0.3763794585832061, + "nauc_mrr_at_20_std": 0.45352913762113745, + "nauc_mrr_at_3_diff1": 0.07530848812579491, + "nauc_mrr_at_3_max": 0.35562286514264335, + "nauc_mrr_at_3_std": 0.396802921482718, + "nauc_mrr_at_5_diff1": 0.08302152990222149, + "nauc_mrr_at_5_max": 0.3576968262143065, + "nauc_mrr_at_5_std": 0.41338731042914795, + "nauc_ndcg_at_1000_diff1": 0.09558404978342788, + "nauc_ndcg_at_1000_max": 0.3936290107279401, + "nauc_ndcg_at_1000_std": 0.4971188181699906, + "nauc_ndcg_at_100_diff1": 0.0948498177846759, + "nauc_ndcg_at_100_max": 0.40854086934729583, + "nauc_ndcg_at_100_std": 0.5213271933921025, + "nauc_ndcg_at_10_diff1": 0.10409768757327305, + "nauc_ndcg_at_10_max": 0.3932140933902953, + "nauc_ndcg_at_10_std": 0.4543940154238287, + "nauc_ndcg_at_1_diff1": -0.40726544549893623, + "nauc_ndcg_at_1_max": -0.15167958484944533, + "nauc_ndcg_at_1_std": 0.34853139570984415, + "nauc_ndcg_at_20_diff1": 0.08632838253673568, + "nauc_ndcg_at_20_max": 0.39162753425196184, + "nauc_ndcg_at_20_std": 0.48872104671656186, + "nauc_ndcg_at_3_diff1": 0.08860897943324894, + "nauc_ndcg_at_3_max": 0.3714382687439485, + "nauc_ndcg_at_3_std": 0.4013325209861603, + "nauc_ndcg_at_5_diff1": 0.09492739549108596, + "nauc_ndcg_at_5_max": 0.3688587206540852, + "nauc_ndcg_at_5_std": 0.4202447328033024, + "nauc_precision_at_1000_diff1": 0.10476589452719959, + "nauc_precision_at_1000_max": 0.38974263683844934, + "nauc_precision_at_1000_std": 0.5100084611182429, + "nauc_precision_at_100_diff1": 0.09803735200171552, + "nauc_precision_at_100_max": 0.429959614816513, + "nauc_precision_at_100_std": 0.5769103150196081, + "nauc_precision_at_10_diff1": 0.11379087470382454, + "nauc_precision_at_10_max": 0.41145241283701867, + "nauc_precision_at_10_std": 0.47605794839894633, + "nauc_precision_at_1_diff1": -0.40726544549893623, + "nauc_precision_at_1_max": -0.15167958484944533, + "nauc_precision_at_1_std": 0.34853139570984415, + "nauc_precision_at_20_diff1": 0.08171596036715958, + "nauc_precision_at_20_max": 0.40285759170381147, + "nauc_precision_at_20_std": 0.5247020659856515, + "nauc_precision_at_3_diff1": 0.1052278787522769, + "nauc_precision_at_3_max": 0.3915164014962417, + "nauc_precision_at_3_std": 0.4075451512745097, + "nauc_precision_at_5_diff1": 0.10767607876127211, + "nauc_precision_at_5_max": 0.38022062571895754, + "nauc_precision_at_5_std": 0.42837146905487467, + "nauc_recall_at_1000_diff1": 0.1047658945271991, + "nauc_recall_at_1000_max": 0.38974263683844906, + "nauc_recall_at_1000_std": 0.5100084611182432, + "nauc_recall_at_100_diff1": 0.09803735200171537, + "nauc_recall_at_100_max": 0.42995961481651257, + "nauc_recall_at_100_std": 0.5769103150196074, + "nauc_recall_at_10_diff1": 0.11379087470382458, + "nauc_recall_at_10_max": 0.41145241283701867, + "nauc_recall_at_10_std": 0.4760579483989468, + "nauc_recall_at_1_diff1": -0.40726544549893623, + "nauc_recall_at_1_max": -0.15167958484944533, + "nauc_recall_at_1_std": 0.34853139570984415, + "nauc_recall_at_20_diff1": 0.0817159603671592, + "nauc_recall_at_20_max": 0.40285759170381125, + "nauc_recall_at_20_std": 0.5247020659856513, + "nauc_recall_at_3_diff1": 0.10522787875227695, + "nauc_recall_at_3_max": 0.3915164014962417, + "nauc_recall_at_3_std": 0.40754515127450974, + "nauc_recall_at_5_diff1": 0.10767607876127201, + "nauc_recall_at_5_max": 0.3802206257189575, + "nauc_recall_at_5_std": 0.42837146905487455, + "ndcg_at_1": 0.00249, + "ndcg_at_10": 0.05986, + "ndcg_at_100": 0.10624, + "ndcg_at_1000": 0.14527, + "ndcg_at_20": 0.07531, + "ndcg_at_3": 0.02998, + "ndcg_at_5": 0.04265, + "precision_at_1": 0.00249, + "precision_at_10": 0.01365, + "precision_at_100": 0.00366, + "precision_at_1000": 0.00069, + "precision_at_20": 0.00987, + "precision_at_3": 0.01732, + "precision_at_5": 0.01658, + "recall_at_1": 0.00249, + "recall_at_10": 0.13647, + "recall_at_100": 0.36624, + "recall_at_1000": 0.69047, + "recall_at_20": 0.19747, + "recall_at_3": 0.05197, + "recall_at_5": 0.08292 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/WinoGrande.json b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/WinoGrande.json new file mode 100644 index 000000000..dcd551a23 --- /dev/null +++ b/results/bge-large-en-v1.5-instruct/d4aa6901d3a41ba39fb536a557fa166f842b0e09/WinoGrande.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 5.548569679260254, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.10314, + "map_at_1": 0.03236, + "map_at_10": 0.07127, + "map_at_100": 0.08953, + "map_at_1000": 0.09073, + "map_at_20": 0.08052, + "map_at_3": 0.05025, + "map_at_5": 0.05901, + "mrr_at_1": 0.03235990528808208, + "mrr_at_10": 0.07144767667656388, + "mrr_at_100": 0.08971870593764837, + "mrr_at_1000": 0.09092331548279743, + "mrr_at_20": 0.08070689471954268, + "mrr_at_3": 0.05064456721915288, + "mrr_at_5": 0.059050249934227854, + "nauc_map_at_1000_diff1": 0.14596675972507892, + "nauc_map_at_1000_max": 0.24252505926696344, + "nauc_map_at_1000_std": 0.09512900278057052, + "nauc_map_at_100_diff1": 0.14525210912195685, + "nauc_map_at_100_max": 0.24105215736980723, + "nauc_map_at_100_std": 0.09429498637776018, + "nauc_map_at_10_diff1": 0.150272516752702, + "nauc_map_at_10_max": 0.25998183726738655, + "nauc_map_at_10_std": 0.09138795137895159, + "nauc_map_at_1_diff1": 0.30501361288623796, + "nauc_map_at_1_max": 0.41860005270359646, + "nauc_map_at_1_std": 0.07117916690824193, + "nauc_map_at_20_diff1": 0.14837393719029976, + "nauc_map_at_20_max": 0.2449921048798103, + "nauc_map_at_20_std": 0.09471143204153386, + "nauc_map_at_3_diff1": 0.19965448225565877, + "nauc_map_at_3_max": 0.36700259650869693, + "nauc_map_at_3_std": 0.1244321461679318, + "nauc_map_at_5_diff1": 0.17456518219918832, + "nauc_map_at_5_max": 0.3096400638105496, + "nauc_map_at_5_std": 0.10591223365875652, + "nauc_mrr_at_1000_diff1": 0.14654097259478763, + "nauc_mrr_at_1000_max": 0.24369563113365614, + "nauc_mrr_at_1000_std": 0.09410974332689973, + "nauc_mrr_at_100_diff1": 0.14582523476274759, + "nauc_mrr_at_100_max": 0.24221721886733555, + "nauc_mrr_at_100_std": 0.09328763230845573, + "nauc_mrr_at_10_diff1": 0.1508573175164638, + "nauc_mrr_at_10_max": 0.2611665468467997, + "nauc_mrr_at_10_std": 0.09041900195876698, + "nauc_mrr_at_1_diff1": 0.30501361288623796, + "nauc_mrr_at_1_max": 0.41860005270359646, + "nauc_mrr_at_1_std": 0.07117916690824193, + "nauc_mrr_at_20_diff1": 0.14894548815730077, + "nauc_mrr_at_20_max": 0.2461475725728332, + "nauc_mrr_at_20_std": 0.09375555812918493, + "nauc_mrr_at_3_diff1": 0.2015031222256622, + "nauc_mrr_at_3_max": 0.36842340365838416, + "nauc_mrr_at_3_std": 0.11994187894484581, + "nauc_mrr_at_5_diff1": 0.17343772565829382, + "nauc_mrr_at_5_max": 0.3099761730181975, + "nauc_mrr_at_5_std": 0.10518626847262165, + "nauc_ndcg_at_1000_diff1": 0.11371778286192895, + "nauc_ndcg_at_1000_max": 0.1714110286886414, + "nauc_ndcg_at_1000_std": 0.09981460669282435, + "nauc_ndcg_at_100_diff1": 0.10008850305101025, + "nauc_ndcg_at_100_max": 0.14266667627505938, + "nauc_ndcg_at_100_std": 0.09010746308347013, + "nauc_ndcg_at_10_diff1": 0.10856900303388632, + "nauc_ndcg_at_10_max": 0.18982016065459478, + "nauc_ndcg_at_10_std": 0.08217389858247809, + "nauc_ndcg_at_1_diff1": 0.30501361288623796, + "nauc_ndcg_at_1_max": 0.41860005270359646, + "nauc_ndcg_at_1_std": 0.07117916690824193, + "nauc_ndcg_at_20_diff1": 0.10831706786397509, + "nauc_ndcg_at_20_max": 0.1593869709254141, + "nauc_ndcg_at_20_std": 0.09175649884657201, + "nauc_ndcg_at_3_diff1": 0.17748465265725483, + "nauc_ndcg_at_3_max": 0.3561168750450347, + "nauc_ndcg_at_3_std": 0.13726727651041362, + "nauc_ndcg_at_5_diff1": 0.14483799614277812, + "nauc_ndcg_at_5_max": 0.2729496499084801, + "nauc_ndcg_at_5_std": 0.10700651342120027, + "nauc_precision_at_1000_diff1": 0.011567775526479787, + "nauc_precision_at_1000_max": -0.24663300504122668, + "nauc_precision_at_1000_std": 0.23141259690296725, + "nauc_precision_at_100_diff1": 0.03011526474674965, + "nauc_precision_at_100_max": -0.03737816642625653, + "nauc_precision_at_100_std": 0.08161490433087787, + "nauc_precision_at_10_diff1": 0.055076436197700814, + "nauc_precision_at_10_max": 0.09327549892702514, + "nauc_precision_at_10_std": 0.06763769092287382, + "nauc_precision_at_1_diff1": 0.30501361288623796, + "nauc_precision_at_1_max": 0.41860005270359646, + "nauc_precision_at_1_std": 0.07117916690824193, + "nauc_precision_at_20_diff1": 0.06403315436269384, + "nauc_precision_at_20_max": 0.05164755161385906, + "nauc_precision_at_20_std": 0.08873843895410212, + "nauc_precision_at_3_diff1": 0.13395402909787232, + "nauc_precision_at_3_max": 0.33473685759439975, + "nauc_precision_at_3_std": 0.16280204110922103, + "nauc_precision_at_5_diff1": 0.09666274895112628, + "nauc_precision_at_5_max": 0.21050222317156744, + "nauc_precision_at_5_std": 0.10685827988274411, + "nauc_recall_at_1000_diff1": 0.01156777552647221, + "nauc_recall_at_1000_max": -0.24663300504123742, + "nauc_recall_at_1000_std": 0.23141259690296018, + "nauc_recall_at_100_diff1": 0.03011526474674954, + "nauc_recall_at_100_max": -0.03737816642625687, + "nauc_recall_at_100_std": 0.0816149043308782, + "nauc_recall_at_10_diff1": 0.05507643619770065, + "nauc_recall_at_10_max": 0.09327549892702494, + "nauc_recall_at_10_std": 0.06763769092287365, + "nauc_recall_at_1_diff1": 0.30501361288623796, + "nauc_recall_at_1_max": 0.41860005270359646, + "nauc_recall_at_1_std": 0.07117916690824193, + "nauc_recall_at_20_diff1": 0.06403315436269381, + "nauc_recall_at_20_max": 0.051647551613858804, + "nauc_recall_at_20_std": 0.08873843895410162, + "nauc_recall_at_3_diff1": 0.1339540290978725, + "nauc_recall_at_3_max": 0.33473685759439975, + "nauc_recall_at_3_std": 0.16280204110922106, + "nauc_recall_at_5_diff1": 0.09666274895112592, + "nauc_recall_at_5_max": 0.2105022231715673, + "nauc_recall_at_5_std": 0.10685827988274396, + "ndcg_at_1": 0.03236, + "ndcg_at_10": 0.10314, + "ndcg_at_100": 0.20434, + "ndcg_at_1000": 0.23645, + "ndcg_at_20": 0.13634, + "ndcg_at_3": 0.05656, + "ndcg_at_5": 0.07259, + "precision_at_1": 0.03236, + "precision_at_10": 0.02107, + "precision_at_100": 0.00713, + "precision_at_1000": 0.00097, + "precision_at_20": 0.01705, + "precision_at_3": 0.02499, + "precision_at_5": 0.02289, + "recall_at_1": 0.03236, + "recall_at_10": 0.21073, + "recall_at_100": 0.7135, + "recall_at_1000": 0.96606, + "recall_at_20": 0.34096, + "recall_at_3": 0.07498, + "recall_at_5": 0.11444 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/ARCChallenge.json b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/ARCChallenge.json new file mode 100644 index 000000000..bf0e684cc --- /dev/null +++ b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/ARCChallenge.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 10.827816486358643, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.09988, + "map_at_1": 0.03498, + "map_at_10": 0.07578, + "map_at_100": 0.08521, + "map_at_1000": 0.08649, + "map_at_20": 0.08113, + "map_at_3": 0.06243, + "map_at_5": 0.07007, + "mrr_at_1": 0.03498293515358362, + "mrr_at_10": 0.07577841432363619, + "mrr_at_100": 0.08520636461086317, + "mrr_at_1000": 0.0864939101626472, + "mrr_at_20": 0.08112575108630513, + "mrr_at_3": 0.062428896473265105, + "mrr_at_5": 0.07006541524459614, + "nauc_map_at_1000_diff1": -0.048134193574135335, + "nauc_map_at_1000_max": 8.20749784831938e-05, + "nauc_map_at_1000_std": -0.06497604903585069, + "nauc_map_at_100_diff1": -0.04806122625717239, + "nauc_map_at_100_max": 0.00010119561112278345, + "nauc_map_at_100_std": -0.06578994690432823, + "nauc_map_at_10_diff1": -0.05275149863839832, + "nauc_map_at_10_max": 0.0019796593913104206, + "nauc_map_at_10_std": -0.07267504878460783, + "nauc_map_at_1_diff1": -0.08083641476985393, + "nauc_map_at_1_max": 0.039948671109782015, + "nauc_map_at_1_std": -0.027851853101006834, + "nauc_map_at_20_diff1": -0.04881667452254169, + "nauc_map_at_20_max": 0.0019922805604535, + "nauc_map_at_20_std": -0.06710445918620392, + "nauc_map_at_3_diff1": -0.0630944632731631, + "nauc_map_at_3_max": 0.00986333613618043, + "nauc_map_at_3_std": -0.06125156398225587, + "nauc_map_at_5_diff1": -0.06080699141700033, + "nauc_map_at_5_max": 0.0022877495440284776, + "nauc_map_at_5_std": -0.06695678383278246, + "nauc_mrr_at_1000_diff1": -0.04813431079954059, + "nauc_mrr_at_1000_max": 8.206533930886343e-05, + "nauc_mrr_at_1000_std": -0.06497609073842477, + "nauc_mrr_at_100_diff1": -0.04806122625717239, + "nauc_mrr_at_100_max": 0.00010119561112278345, + "nauc_mrr_at_100_std": -0.06578994690432823, + "nauc_mrr_at_10_diff1": -0.05275149863839832, + "nauc_mrr_at_10_max": 0.0019796593913104206, + "nauc_mrr_at_10_std": -0.07267504878460783, + "nauc_mrr_at_1_diff1": -0.08083641476985393, + "nauc_mrr_at_1_max": 0.039948671109782015, + "nauc_mrr_at_1_std": -0.027851853101006834, + "nauc_mrr_at_20_diff1": -0.04881667452254169, + "nauc_mrr_at_20_max": 0.0019922805604535, + "nauc_mrr_at_20_std": -0.06710445918620392, + "nauc_mrr_at_3_diff1": -0.0630944632731631, + "nauc_mrr_at_3_max": 0.00986333613618043, + "nauc_mrr_at_3_std": -0.06125156398225587, + "nauc_mrr_at_5_diff1": -0.06080699141700033, + "nauc_mrr_at_5_max": 0.0022877495440284776, + "nauc_mrr_at_5_std": -0.06695678383278246, + "nauc_ndcg_at_1000_diff1": -0.04211928162119795, + "nauc_ndcg_at_1000_max": -0.01931151998036835, + "nauc_ndcg_at_1000_std": -0.044710726130894586, + "nauc_ndcg_at_100_diff1": -0.03236536990798992, + "nauc_ndcg_at_100_max": -0.0164069657427625, + "nauc_ndcg_at_100_std": -0.05834470663757984, + "nauc_ndcg_at_10_diff1": -0.041012501996532814, + "nauc_ndcg_at_10_max": -0.0059059022309719544, + "nauc_ndcg_at_10_std": -0.08358199714659408, + "nauc_ndcg_at_1_diff1": -0.08083641476985393, + "nauc_ndcg_at_1_max": 0.039948671109782015, + "nauc_ndcg_at_1_std": -0.027851853101006834, + "nauc_ndcg_at_20_diff1": -0.03234472298782201, + "nauc_ndcg_at_20_max": -0.005151385264338716, + "nauc_ndcg_at_20_std": -0.06884651064707135, + "nauc_ndcg_at_3_diff1": -0.05765041587071118, + "nauc_ndcg_at_3_max": 0.006720520498187055, + "nauc_ndcg_at_3_std": -0.0654858021986373, + "nauc_ndcg_at_5_diff1": -0.05436496426400295, + "nauc_ndcg_at_5_max": -0.005149675743637855, + "nauc_ndcg_at_5_std": -0.07361609267409916, + "nauc_precision_at_1000_diff1": -0.07621650368784313, + "nauc_precision_at_1000_max": -0.08295721321326024, + "nauc_precision_at_1000_std": 0.047482238821146515, + "nauc_precision_at_100_diff1": -0.014492451084535134, + "nauc_precision_at_100_max": -0.04538634253815513, + "nauc_precision_at_100_std": -0.036315840955638085, + "nauc_precision_at_10_diff1": -0.022335371581757777, + "nauc_precision_at_10_max": -0.01813798232559735, + "nauc_precision_at_10_std": -0.10065714007520765, + "nauc_precision_at_1_diff1": -0.08083641476985393, + "nauc_precision_at_1_max": 0.039948671109782015, + "nauc_precision_at_1_std": -0.027851853101006834, + "nauc_precision_at_20_diff1": -0.008355397338225884, + "nauc_precision_at_20_max": -0.014250263741189427, + "nauc_precision_at_20_std": -0.06781628201161967, + "nauc_precision_at_3_diff1": -0.04730482125473772, + "nauc_precision_at_3_max": 0.0014367552880570316, + "nauc_precision_at_3_std": -0.07285206954259184, + "nauc_precision_at_5_diff1": -0.04310673681307753, + "nauc_precision_at_5_max": -0.018120702128355894, + "nauc_precision_at_5_std": -0.08476220011204066, + "nauc_recall_at_1000_diff1": -0.07621650368784262, + "nauc_recall_at_1000_max": -0.0829572132132597, + "nauc_recall_at_1000_std": 0.047482238821147126, + "nauc_recall_at_100_diff1": -0.014492451084535186, + "nauc_recall_at_100_max": -0.045386342538155273, + "nauc_recall_at_100_std": -0.036315840955637904, + "nauc_recall_at_10_diff1": -0.022335371581757902, + "nauc_recall_at_10_max": -0.018137982325597633, + "nauc_recall_at_10_std": -0.10065714007520786, + "nauc_recall_at_1_diff1": -0.08083641476985393, + "nauc_recall_at_1_max": 0.039948671109782015, + "nauc_recall_at_1_std": -0.027851853101006834, + "nauc_recall_at_20_diff1": -0.00835539733822604, + "nauc_recall_at_20_max": -0.014250263741189508, + "nauc_recall_at_20_std": -0.0678162820116197, + "nauc_recall_at_3_diff1": -0.04730482125473788, + "nauc_recall_at_3_max": 0.0014367552880570082, + "nauc_recall_at_3_std": -0.07285206954259187, + "nauc_recall_at_5_diff1": -0.043106736813077744, + "nauc_recall_at_5_max": -0.01812070212835619, + "nauc_recall_at_5_std": -0.08476220011204083, + "ndcg_at_1": 0.03498, + "ndcg_at_10": 0.09988, + "ndcg_at_100": 0.15082, + "ndcg_at_1000": 0.19012, + "ndcg_at_20": 0.11947, + "ndcg_at_3": 0.07219, + "ndcg_at_5": 0.08574, + "precision_at_1": 0.03498, + "precision_at_10": 0.01775, + "precision_at_100": 0.00427, + "precision_at_1000": 0.00075, + "precision_at_20": 0.01276, + "precision_at_3": 0.03356, + "precision_at_5": 0.02662, + "recall_at_1": 0.03498, + "recall_at_10": 0.17747, + "recall_at_100": 0.42747, + "recall_at_1000": 0.74829, + "recall_at_20": 0.25512, + "recall_at_3": 0.10068, + "recall_at_5": 0.13311 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/AlphaNLI.json b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/AlphaNLI.json new file mode 100644 index 000000000..e9459991e --- /dev/null +++ b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/AlphaNLI.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 163.3919985294342, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.13133, + "map_at_1": 0.07572, + "map_at_10": 0.11143, + "map_at_100": 0.1181, + "map_at_1000": 0.11905, + "map_at_20": 0.11484, + "map_at_3": 0.10128, + "map_at_5": 0.10615, + "mrr_at_1": 0.07571801566579635, + "mrr_at_10": 0.11143463259977623, + "mrr_at_100": 0.11810343929956475, + "mrr_at_1000": 0.11904887685140626, + "mrr_at_20": 0.11484435247401674, + "mrr_at_3": 0.10128372497824199, + "mrr_at_5": 0.10614664926022632, + "nauc_map_at_1000_diff1": 0.23418058782938284, + "nauc_map_at_1000_max": 0.22011413468462204, + "nauc_map_at_1000_std": 0.06436410265360974, + "nauc_map_at_100_diff1": 0.23424858441819923, + "nauc_map_at_100_max": 0.220034040818543, + "nauc_map_at_100_std": 0.06396819380423682, + "nauc_map_at_10_diff1": 0.2411012560225268, + "nauc_map_at_10_max": 0.22485624772203183, + "nauc_map_at_10_std": 0.06361448266335185, + "nauc_map_at_1_diff1": 0.3164745836766633, + "nauc_map_at_1_max": 0.27275168179682746, + "nauc_map_at_1_std": 0.06134868768904477, + "nauc_map_at_20_diff1": 0.23640249786216372, + "nauc_map_at_20_max": 0.22271765374224067, + "nauc_map_at_20_std": 0.06411904899822894, + "nauc_map_at_3_diff1": 0.25825689220797077, + "nauc_map_at_3_max": 0.2499915476930295, + "nauc_map_at_3_std": 0.07323769551966346, + "nauc_map_at_5_diff1": 0.253536981856925, + "nauc_map_at_5_max": 0.24020733756507742, + "nauc_map_at_5_std": 0.06350301196393421, + "nauc_mrr_at_1000_diff1": 0.23418058782938284, + "nauc_mrr_at_1000_max": 0.22011413468462204, + "nauc_mrr_at_1000_std": 0.06436410265360974, + "nauc_mrr_at_100_diff1": 0.23424858441819923, + "nauc_mrr_at_100_max": 0.220034040818543, + "nauc_mrr_at_100_std": 0.06396819380423682, + "nauc_mrr_at_10_diff1": 0.2411012560225268, + "nauc_mrr_at_10_max": 0.22485624772203183, + "nauc_mrr_at_10_std": 0.06361448266335185, + "nauc_mrr_at_1_diff1": 0.3164745836766633, + "nauc_mrr_at_1_max": 0.27275168179682746, + "nauc_mrr_at_1_std": 0.06134868768904477, + "nauc_mrr_at_20_diff1": 0.23640249786216372, + "nauc_mrr_at_20_max": 0.22271765374224067, + "nauc_mrr_at_20_std": 0.06411904899822894, + "nauc_mrr_at_3_diff1": 0.25825689220797077, + "nauc_mrr_at_3_max": 0.2499915476930295, + "nauc_mrr_at_3_std": 0.07323769551966346, + "nauc_mrr_at_5_diff1": 0.253536981856925, + "nauc_mrr_at_5_max": 0.24020733756507742, + "nauc_mrr_at_5_std": 0.06350301196393421, + "nauc_ndcg_at_1000_diff1": 0.1830537675236158, + "nauc_ndcg_at_1000_max": 0.1766389015388427, + "nauc_ndcg_at_1000_std": 0.07154637271458869, + "nauc_ndcg_at_100_diff1": 0.18607586485821043, + "nauc_ndcg_at_100_max": 0.17624583743954994, + "nauc_ndcg_at_100_std": 0.06550959315820701, + "nauc_ndcg_at_10_diff1": 0.21124082182627832, + "nauc_ndcg_at_10_max": 0.19519050644914587, + "nauc_ndcg_at_10_std": 0.061257432187420115, + "nauc_ndcg_at_1_diff1": 0.3164745836766633, + "nauc_ndcg_at_1_max": 0.27275168179682746, + "nauc_ndcg_at_1_std": 0.06134868768904477, + "nauc_ndcg_at_20_diff1": 0.19831918675201138, + "nauc_ndcg_at_20_max": 0.18947362462439543, + "nauc_ndcg_at_20_std": 0.06350724954879526, + "nauc_ndcg_at_3_diff1": 0.24360127365224832, + "nauc_ndcg_at_3_max": 0.24413523904472242, + "nauc_ndcg_at_3_std": 0.0777272984865741, + "nauc_ndcg_at_5_diff1": 0.2363925286285705, + "nauc_ndcg_at_5_max": 0.22768427240895958, + "nauc_ndcg_at_5_std": 0.0612216659726091, + "nauc_precision_at_1000_diff1": 0.051879518144797875, + "nauc_precision_at_1000_max": 0.07217433042816335, + "nauc_precision_at_1000_std": 0.10497195230146754, + "nauc_precision_at_100_diff1": 0.08885246244970961, + "nauc_precision_at_100_max": 0.08743151730199814, + "nauc_precision_at_100_std": 0.07351777771060096, + "nauc_precision_at_10_diff1": 0.149092507798683, + "nauc_precision_at_10_max": 0.129977412017621, + "nauc_precision_at_10_std": 0.05543273696790138, + "nauc_precision_at_1_diff1": 0.3164745836766633, + "nauc_precision_at_1_max": 0.27275168179682746, + "nauc_precision_at_1_std": 0.06134868768904477, + "nauc_precision_at_20_diff1": 0.12115449693740217, + "nauc_precision_at_20_max": 0.12054609597240071, + "nauc_precision_at_20_std": 0.06278016358692898, + "nauc_precision_at_3_diff1": 0.20998767625173193, + "nauc_precision_at_3_max": 0.2306724987147689, + "nauc_precision_at_3_std": 0.08838973292332045, + "nauc_precision_at_5_diff1": 0.19903253448680414, + "nauc_precision_at_5_max": 0.1989724923409961, + "nauc_precision_at_5_std": 0.05490153836232773, + "nauc_recall_at_1000_diff1": 0.05187951814479827, + "nauc_recall_at_1000_max": 0.07217433042816422, + "nauc_recall_at_1000_std": 0.10497195230146891, + "nauc_recall_at_100_diff1": 0.08885246244970953, + "nauc_recall_at_100_max": 0.08743151730199795, + "nauc_recall_at_100_std": 0.0735177777106005, + "nauc_recall_at_10_diff1": 0.14909250779868294, + "nauc_recall_at_10_max": 0.12997741201762072, + "nauc_recall_at_10_std": 0.05543273696790109, + "nauc_recall_at_1_diff1": 0.3164745836766633, + "nauc_recall_at_1_max": 0.27275168179682746, + "nauc_recall_at_1_std": 0.06134868768904477, + "nauc_recall_at_20_diff1": 0.12115449693740207, + "nauc_recall_at_20_max": 0.12054609597240067, + "nauc_recall_at_20_std": 0.06278016358692898, + "nauc_recall_at_3_diff1": 0.209987676251732, + "nauc_recall_at_3_max": 0.23067249871476894, + "nauc_recall_at_3_std": 0.08838973292332052, + "nauc_recall_at_5_diff1": 0.19903253448680402, + "nauc_recall_at_5_max": 0.19897249234099576, + "nauc_recall_at_5_std": 0.05490153836232759, + "ndcg_at_1": 0.07572, + "ndcg_at_10": 0.13133, + "ndcg_at_100": 0.16824, + "ndcg_at_1000": 0.19841, + "ndcg_at_20": 0.1435, + "ndcg_at_3": 0.10979, + "ndcg_at_5": 0.11847, + "precision_at_1": 0.07572, + "precision_at_10": 0.01952, + "precision_at_100": 0.00379, + "precision_at_1000": 0.00063, + "precision_at_20": 0.01214, + "precision_at_3": 0.04482, + "precision_at_5": 0.03107, + "recall_at_1": 0.07572, + "recall_at_10": 0.19517, + "recall_at_100": 0.37859, + "recall_at_1000": 0.62728, + "recall_at_20": 0.24282, + "recall_at_3": 0.13446, + "recall_at_5": 0.15535 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/HellaSwag.json b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/HellaSwag.json new file mode 100644 index 000000000..ab9a3609f --- /dev/null +++ b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/HellaSwag.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 391.05748653411865, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.28496, + "map_at_1": 0.15515, + "map_at_10": 0.23984, + "map_at_100": 0.2487, + "map_at_1000": 0.24952, + "map_at_20": 0.24474, + "map_at_3": 0.21672, + "map_at_5": 0.23026, + "mrr_at_1": 0.15514837681736707, + "mrr_at_10": 0.23983807690240627, + "mrr_at_100": 0.2487030741552552, + "mrr_at_1000": 0.24952385512873546, + "mrr_at_20": 0.24473752194486398, + "mrr_at_3": 0.21672309632875145, + "mrr_at_5": 0.23026123614153837, + "nauc_map_at_1000_diff1": 0.19017056639966762, + "nauc_map_at_1000_max": 0.053080914234016986, + "nauc_map_at_1000_std": -0.25339995152644684, + "nauc_map_at_100_diff1": 0.19007524862068573, + "nauc_map_at_100_max": 0.052947576705505345, + "nauc_map_at_100_std": -0.2535654247868339, + "nauc_map_at_10_diff1": 0.19192365859531418, + "nauc_map_at_10_max": 0.054645635770228684, + "nauc_map_at_10_std": -0.2540085576029278, + "nauc_map_at_1_diff1": 0.2244803124009814, + "nauc_map_at_1_max": 0.05374767460804662, + "nauc_map_at_1_std": -0.22348654559940015, + "nauc_map_at_20_diff1": 0.19087417153001382, + "nauc_map_at_20_max": 0.053369804075262775, + "nauc_map_at_20_std": -0.25430387612723865, + "nauc_map_at_3_diff1": 0.19438574458170085, + "nauc_map_at_3_max": 0.05681217567430416, + "nauc_map_at_3_std": -0.24406853191459021, + "nauc_map_at_5_diff1": 0.19498229696358776, + "nauc_map_at_5_max": 0.057334272725585264, + "nauc_map_at_5_std": -0.25057992294034476, + "nauc_mrr_at_1000_diff1": 0.19017056572666055, + "nauc_mrr_at_1000_max": 0.053080914160753334, + "nauc_mrr_at_1000_std": -0.25339995007344013, + "nauc_mrr_at_100_diff1": 0.19007524862068573, + "nauc_mrr_at_100_max": 0.052947576705505345, + "nauc_mrr_at_100_std": -0.2535654247868339, + "nauc_mrr_at_10_diff1": 0.19192365859531418, + "nauc_mrr_at_10_max": 0.054645635770228684, + "nauc_mrr_at_10_std": -0.2540085576029278, + "nauc_mrr_at_1_diff1": 0.2244803124009814, + "nauc_mrr_at_1_max": 0.05374767460804662, + "nauc_mrr_at_1_std": -0.22348654559940015, + "nauc_mrr_at_20_diff1": 0.19087417153001382, + "nauc_mrr_at_20_max": 0.053369804075262775, + "nauc_mrr_at_20_std": -0.25430387612723865, + "nauc_mrr_at_3_diff1": 0.19438574458170085, + "nauc_mrr_at_3_max": 0.05681217567430416, + "nauc_mrr_at_3_std": -0.24406853191459021, + "nauc_mrr_at_5_diff1": 0.19498229696358776, + "nauc_mrr_at_5_max": 0.057334272725585264, + "nauc_mrr_at_5_std": -0.25057992294034476, + "nauc_ndcg_at_1000_diff1": 0.17358193415285786, + "nauc_ndcg_at_1000_max": 0.04930645018806221, + "nauc_ndcg_at_1000_std": -0.2607033987009959, + "nauc_ndcg_at_100_diff1": 0.17088441979734173, + "nauc_ndcg_at_100_max": 0.04570540104737144, + "nauc_ndcg_at_100_std": -0.2645619735755347, + "nauc_ndcg_at_10_diff1": 0.18064042321992388, + "nauc_ndcg_at_10_max": 0.05295201157779419, + "nauc_ndcg_at_10_std": -0.2688149209168702, + "nauc_ndcg_at_1_diff1": 0.2244803124009814, + "nauc_ndcg_at_1_max": 0.05374767460804662, + "nauc_ndcg_at_1_std": -0.22348654559940015, + "nauc_ndcg_at_20_diff1": 0.17680171723731894, + "nauc_ndcg_at_20_max": 0.04828091511359528, + "nauc_ndcg_at_20_std": -0.2700952750347036, + "nauc_ndcg_at_3_diff1": 0.18641334036037419, + "nauc_ndcg_at_3_max": 0.05811411370403474, + "nauc_ndcg_at_3_std": -0.2503414707500411, + "nauc_ndcg_at_5_diff1": 0.18767064914609616, + "nauc_ndcg_at_5_max": 0.05905581279822183, + "nauc_ndcg_at_5_std": -0.2612958195919563, + "nauc_precision_at_1000_diff1": 0.06350650436108815, + "nauc_precision_at_1000_max": 0.0359848725791245, + "nauc_precision_at_1000_std": -0.25831323997990896, + "nauc_precision_at_100_diff1": 0.09544051068071834, + "nauc_precision_at_100_max": 0.013186912659260154, + "nauc_precision_at_100_std": -0.29027702130189287, + "nauc_precision_at_10_diff1": 0.15214593467007106, + "nauc_precision_at_10_max": 0.04730665539481526, + "nauc_precision_at_10_std": -0.30706437366707096, + "nauc_precision_at_1_diff1": 0.2244803124009814, + "nauc_precision_at_1_max": 0.05374767460804662, + "nauc_precision_at_1_std": -0.22348654559940015, + "nauc_precision_at_20_diff1": 0.13801115478571505, + "nauc_precision_at_20_max": 0.030684589597114294, + "nauc_precision_at_20_std": -0.3126790540439078, + "nauc_precision_at_3_diff1": 0.16720948133445968, + "nauc_precision_at_3_max": 0.06137746316886774, + "nauc_precision_at_3_std": -0.2656647120012467, + "nauc_precision_at_5_diff1": 0.1706778297276104, + "nauc_precision_at_5_max": 0.06338358153902575, + "nauc_precision_at_5_std": -0.28797777485521053, + "nauc_recall_at_1000_diff1": 0.0635065043610904, + "nauc_recall_at_1000_max": 0.03598487257912636, + "nauc_recall_at_1000_std": -0.25831323997990574, + "nauc_recall_at_100_diff1": 0.09544051068071878, + "nauc_recall_at_100_max": 0.013186912659260478, + "nauc_recall_at_100_std": -0.29027702130189176, + "nauc_recall_at_10_diff1": 0.15214593467007137, + "nauc_recall_at_10_max": 0.04730665539481596, + "nauc_recall_at_10_std": -0.3070643736670706, + "nauc_recall_at_1_diff1": 0.2244803124009814, + "nauc_recall_at_1_max": 0.05374767460804662, + "nauc_recall_at_1_std": -0.22348654559940015, + "nauc_recall_at_20_diff1": 0.13801115478571505, + "nauc_recall_at_20_max": 0.030684589597114443, + "nauc_recall_at_20_std": -0.31267905404390794, + "nauc_recall_at_3_diff1": 0.16720948133445948, + "nauc_recall_at_3_max": 0.06137746316886731, + "nauc_recall_at_3_std": -0.265664712001247, + "nauc_recall_at_5_diff1": 0.17067782972761047, + "nauc_recall_at_5_max": 0.06338358153902592, + "nauc_recall_at_5_std": -0.2879777748552102, + "ndcg_at_1": 0.15515, + "ndcg_at_10": 0.28496, + "ndcg_at_100": 0.33264, + "ndcg_at_1000": 0.35671, + "ndcg_at_20": 0.30284, + "ndcg_at_3": 0.23736, + "ndcg_at_5": 0.26176, + "precision_at_1": 0.15515, + "precision_at_10": 0.04282, + "precision_at_100": 0.00662, + "precision_at_1000": 0.00086, + "precision_at_20": 0.02495, + "precision_at_3": 0.09908, + "precision_at_5": 0.0713, + "recall_at_1": 0.15515, + "recall_at_10": 0.4282, + "recall_at_100": 0.66202, + "recall_at_1000": 0.8564, + "recall_at_20": 0.499, + "recall_at_3": 0.29725, + "recall_at_5": 0.3565 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/PIQA.json b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/PIQA.json new file mode 100644 index 000000000..a158c7691 --- /dev/null +++ b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/PIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 51.09566307067871, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.2799, + "map_at_1": 0.15071, + "map_at_10": 0.23614, + "map_at_100": 0.24479, + "map_at_1000": 0.24554, + "map_at_20": 0.24098, + "map_at_3": 0.214, + "map_at_5": 0.2266, + "mrr_at_1": 0.15070729053318824, + "mrr_at_10": 0.23614133720227276, + "mrr_at_100": 0.24479036144844413, + "mrr_at_1000": 0.24553714835099666, + "mrr_at_20": 0.24097835712366536, + "mrr_at_3": 0.21400072542618762, + "mrr_at_5": 0.2265959376133474, + "nauc_map_at_1000_diff1": -0.0031540907245369955, + "nauc_map_at_1000_max": 0.0779950733490778, + "nauc_map_at_1000_std": 0.0030060543643981386, + "nauc_map_at_100_diff1": -0.003248058634235043, + "nauc_map_at_100_max": 0.07803034464254782, + "nauc_map_at_100_std": 0.002984586807228381, + "nauc_map_at_10_diff1": -0.0023768197339022927, + "nauc_map_at_10_max": 0.07930057524090228, + "nauc_map_at_10_std": 0.0004282599294061933, + "nauc_map_at_1_diff1": 0.039792558206875224, + "nauc_map_at_1_max": 0.054359985198533405, + "nauc_map_at_1_std": -0.023204977339959243, + "nauc_map_at_20_diff1": -0.003528813972189541, + "nauc_map_at_20_max": 0.07857830102296597, + "nauc_map_at_20_std": 0.0018277261870817832, + "nauc_map_at_3_diff1": 0.00519993986570553, + "nauc_map_at_3_max": 0.08696216786157374, + "nauc_map_at_3_std": -0.003524202133073559, + "nauc_map_at_5_diff1": 0.0019119039244668763, + "nauc_map_at_5_max": 0.08404663361711173, + "nauc_map_at_5_std": -0.001222660804834324, + "nauc_mrr_at_1000_diff1": -0.00315414668752006, + "nauc_mrr_at_1000_max": 0.07799505406253962, + "nauc_mrr_at_1000_std": 0.0030060316921360027, + "nauc_mrr_at_100_diff1": -0.003248058634235043, + "nauc_mrr_at_100_max": 0.07803034464254782, + "nauc_mrr_at_100_std": 0.002984586807228381, + "nauc_mrr_at_10_diff1": -0.0023768197339022927, + "nauc_mrr_at_10_max": 0.07930057524090228, + "nauc_mrr_at_10_std": 0.0004282599294061933, + "nauc_mrr_at_1_diff1": 0.039792558206875224, + "nauc_mrr_at_1_max": 0.054359985198533405, + "nauc_mrr_at_1_std": -0.023204977339959243, + "nauc_mrr_at_20_diff1": -0.003528813972189541, + "nauc_mrr_at_20_max": 0.07857830102296597, + "nauc_mrr_at_20_std": 0.0018277261870817832, + "nauc_mrr_at_3_diff1": 0.00519993986570553, + "nauc_mrr_at_3_max": 0.08696216786157374, + "nauc_mrr_at_3_std": -0.003524202133073559, + "nauc_mrr_at_5_diff1": 0.0019119039244668763, + "nauc_mrr_at_5_max": 0.08404663361711173, + "nauc_mrr_at_5_std": -0.001222660804834324, + "nauc_ndcg_at_1000_diff1": -0.022085609548583705, + "nauc_ndcg_at_1000_max": 0.06320537761531404, + "nauc_ndcg_at_1000_std": 0.01681520336619718, + "nauc_ndcg_at_100_diff1": -0.021461504693749762, + "nauc_ndcg_at_100_max": 0.06566051653170055, + "nauc_ndcg_at_100_std": 0.021797593641621524, + "nauc_ndcg_at_10_diff1": -0.01754888700929439, + "nauc_ndcg_at_10_max": 0.07609129079842644, + "nauc_ndcg_at_10_std": 0.008113506167752372, + "nauc_ndcg_at_1_diff1": 0.039792558206875224, + "nauc_ndcg_at_1_max": 0.054359985198533405, + "nauc_ndcg_at_1_std": -0.023204977339959243, + "nauc_ndcg_at_20_diff1": -0.02187580300461333, + "nauc_ndcg_at_20_max": 0.07260593717369697, + "nauc_ndcg_at_20_std": 0.012995401502492343, + "nauc_ndcg_at_3_diff1": -0.002589272782085806, + "nauc_ndcg_at_3_max": 0.0919673336701326, + "nauc_ndcg_at_3_std": 0.0004968169703350518, + "nauc_ndcg_at_5_diff1": -0.00816952698787415, + "nauc_ndcg_at_5_max": 0.08704290792281509, + "nauc_ndcg_at_5_std": 0.004321498981526007, + "nauc_precision_at_1000_diff1": -0.14436515874026892, + "nauc_precision_at_1000_max": -0.08408822043945148, + "nauc_precision_at_1000_std": 0.07104993524269501, + "nauc_precision_at_100_diff1": -0.08181113888557262, + "nauc_precision_at_100_max": 0.0016452734161283265, + "nauc_precision_at_100_std": 0.09954127562796772, + "nauc_precision_at_10_diff1": -0.055737078965879226, + "nauc_precision_at_10_max": 0.06370073072134415, + "nauc_precision_at_10_std": 0.02724210417873484, + "nauc_precision_at_1_diff1": 0.039792558206875224, + "nauc_precision_at_1_max": 0.054359985198533405, + "nauc_precision_at_1_std": -0.023204977339959243, + "nauc_precision_at_20_diff1": -0.07187495063076786, + "nauc_precision_at_20_max": 0.049779754446981975, + "nauc_precision_at_20_std": 0.04433606211599685, + "nauc_precision_at_3_diff1": -0.02096237538853685, + "nauc_precision_at_3_max": 0.1030711077165347, + "nauc_precision_at_3_std": 0.009858120110805552, + "nauc_precision_at_5_diff1": -0.0321939530393517, + "nauc_precision_at_5_max": 0.0926775327516652, + "nauc_precision_at_5_std": 0.017461356237876084, + "nauc_recall_at_1000_diff1": -0.14436515874026754, + "nauc_recall_at_1000_max": -0.08408822043944994, + "nauc_recall_at_1000_std": 0.07104993524269596, + "nauc_recall_at_100_diff1": -0.08181113888557326, + "nauc_recall_at_100_max": 0.0016452734161272005, + "nauc_recall_at_100_std": 0.09954127562796712, + "nauc_recall_at_10_diff1": -0.05573707896587908, + "nauc_recall_at_10_max": 0.0637007307213445, + "nauc_recall_at_10_std": 0.027242104178735377, + "nauc_recall_at_1_diff1": 0.039792558206875224, + "nauc_recall_at_1_max": 0.054359985198533405, + "nauc_recall_at_1_std": -0.023204977339959243, + "nauc_recall_at_20_diff1": -0.07187495063076778, + "nauc_recall_at_20_max": 0.04977975444698218, + "nauc_recall_at_20_std": 0.0443360621159971, + "nauc_recall_at_3_diff1": -0.02096237538853695, + "nauc_recall_at_3_max": 0.10307110771653477, + "nauc_recall_at_3_std": 0.009858120110805507, + "nauc_recall_at_5_diff1": -0.0321939530393519, + "nauc_recall_at_5_max": 0.09267753275166525, + "nauc_recall_at_5_std": 0.01746135623787608, + "ndcg_at_1": 0.15071, + "ndcg_at_10": 0.2799, + "ndcg_at_100": 0.32613, + "ndcg_at_1000": 0.34864, + "ndcg_at_20": 0.2977, + "ndcg_at_3": 0.23438, + "ndcg_at_5": 0.25692, + "precision_at_1": 0.15071, + "precision_at_10": 0.04184, + "precision_at_100": 0.00644, + "precision_at_1000": 0.00083, + "precision_at_20": 0.02446, + "precision_at_3": 0.09775, + "precision_at_5": 0.06953, + "recall_at_1": 0.15071, + "recall_at_10": 0.41839, + "recall_at_100": 0.64418, + "recall_at_1000": 0.82753, + "recall_at_20": 0.48912, + "recall_at_3": 0.29325, + "recall_at_5": 0.34766 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/Quail.json b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/Quail.json new file mode 100644 index 000000000..dbf1ab30f --- /dev/null +++ b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/Quail.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 76.75059175491333, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01832, + "map_at_1": 0.00588, + "map_at_10": 0.01327, + "map_at_100": 0.0164, + "map_at_1000": 0.01711, + "map_at_20": 0.01471, + "map_at_3": 0.00962, + "map_at_5": 0.01188, + "mrr_at_1": 0.0058823529411764705, + "mrr_at_10": 0.013266514939309063, + "mrr_at_100": 0.01640002258701535, + "mrr_at_1000": 0.01711460755463407, + "mrr_at_20": 0.014706429624448895, + "mrr_at_3": 0.009620098039215687, + "mrr_at_5": 0.01188112745098039, + "nauc_map_at_1000_diff1": 0.012207894289332286, + "nauc_map_at_1000_max": -0.023576222877912906, + "nauc_map_at_1000_std": 0.12832658613807243, + "nauc_map_at_100_diff1": 0.012503494933501912, + "nauc_map_at_100_max": -0.024975796348310885, + "nauc_map_at_100_std": 0.12877025460326125, + "nauc_map_at_10_diff1": 0.015076477920037292, + "nauc_map_at_10_max": -0.05031657236082681, + "nauc_map_at_10_std": 0.117063499053053, + "nauc_map_at_1_diff1": 0.08124832304802804, + "nauc_map_at_1_max": -0.13375368929433853, + "nauc_map_at_1_std": 0.031057150523209072, + "nauc_map_at_20_diff1": 0.014745118988094353, + "nauc_map_at_20_max": -0.034204572523950295, + "nauc_map_at_20_std": 0.12474305003040954, + "nauc_map_at_3_diff1": 0.07709962931884565, + "nauc_map_at_3_max": -0.08652474027538752, + "nauc_map_at_3_std": 0.08171049955651576, + "nauc_map_at_5_diff1": 0.019109676360550346, + "nauc_map_at_5_max": -0.06641968280475061, + "nauc_map_at_5_std": 0.10329525992184767, + "nauc_mrr_at_1000_diff1": 0.012362007735520463, + "nauc_mrr_at_1000_max": -0.02394603602160005, + "nauc_mrr_at_1000_std": 0.12792159200237632, + "nauc_mrr_at_100_diff1": 0.01280637138880983, + "nauc_mrr_at_100_max": -0.025127406976301787, + "nauc_mrr_at_100_std": 0.12824469403934421, + "nauc_mrr_at_10_diff1": 0.01528356921107826, + "nauc_mrr_at_10_max": -0.05091645323847212, + "nauc_mrr_at_10_std": 0.11663170242520707, + "nauc_mrr_at_1_diff1": 0.08124832304802804, + "nauc_mrr_at_1_max": -0.13375368929433853, + "nauc_mrr_at_1_std": 0.031057150523209072, + "nauc_mrr_at_20_diff1": 0.014904396378280126, + "nauc_mrr_at_20_max": -0.03471185142529781, + "nauc_mrr_at_20_std": 0.12429179683302356, + "nauc_mrr_at_3_diff1": 0.07709962931884565, + "nauc_mrr_at_3_max": -0.08652474027538752, + "nauc_mrr_at_3_std": 0.08171049955651576, + "nauc_mrr_at_5_diff1": 0.019109676360550346, + "nauc_mrr_at_5_max": -0.06641968280475061, + "nauc_mrr_at_5_std": 0.10329525992184767, + "nauc_ndcg_at_1000_diff1": 0.004390062376518119, + "nauc_ndcg_at_1000_max": 0.029741424294425178, + "nauc_ndcg_at_1000_std": 0.14880196059217995, + "nauc_ndcg_at_100_diff1": -0.007899019123369214, + "nauc_ndcg_at_100_max": 0.025098070775657132, + "nauc_ndcg_at_100_std": 0.1616394250852923, + "nauc_ndcg_at_10_diff1": -0.013649428095643235, + "nauc_ndcg_at_10_max": -0.026811348845499756, + "nauc_ndcg_at_10_std": 0.13981434118264438, + "nauc_ndcg_at_1_diff1": 0.08124832304802804, + "nauc_ndcg_at_1_max": -0.13375368929433853, + "nauc_ndcg_at_1_std": 0.031057150523209072, + "nauc_ndcg_at_20_diff1": -0.007014529132597082, + "nauc_ndcg_at_20_max": 0.0020659828336233857, + "nauc_ndcg_at_20_std": 0.14988660140142135, + "nauc_ndcg_at_3_diff1": 0.07282679552459181, + "nauc_ndcg_at_3_max": -0.07970412987846956, + "nauc_ndcg_at_3_std": 0.08978639695772411, + "nauc_ndcg_at_5_diff1": -0.008884661309752994, + "nauc_ndcg_at_5_max": -0.050910932041759345, + "nauc_ndcg_at_5_std": 0.11911481760383105, + "nauc_precision_at_1000_diff1": 0.014189676756434517, + "nauc_precision_at_1000_max": 0.054313232464791514, + "nauc_precision_at_1000_std": 0.15205597592207895, + "nauc_precision_at_100_diff1": -0.01686031455267367, + "nauc_precision_at_100_max": 0.057941300820676674, + "nauc_precision_at_100_std": 0.18299042640594348, + "nauc_precision_at_10_diff1": -0.0511911654639683, + "nauc_precision_at_10_max": 0.003623628429808214, + "nauc_precision_at_10_std": 0.16905652916837324, + "nauc_precision_at_1_diff1": 0.08124832304802804, + "nauc_precision_at_1_max": -0.13375368929433853, + "nauc_precision_at_1_std": 0.031057150523209072, + "nauc_precision_at_20_diff1": -0.025157810006637117, + "nauc_precision_at_20_max": 0.03831746995608164, + "nauc_precision_at_20_std": 0.17303673054382693, + "nauc_precision_at_3_diff1": 0.06371385523518593, + "nauc_precision_at_3_max": -0.06681664637124805, + "nauc_precision_at_3_std": 0.1052609853253803, + "nauc_precision_at_5_diff1": -0.05396736346561939, + "nauc_precision_at_5_max": -0.026587311266677894, + "nauc_precision_at_5_std": 0.1434698473872074, + "nauc_recall_at_1000_diff1": 0.014189676756434365, + "nauc_recall_at_1000_max": 0.05431323246479159, + "nauc_recall_at_1000_std": 0.1520559759220788, + "nauc_recall_at_100_diff1": -0.01686031455267385, + "nauc_recall_at_100_max": 0.057941300820676465, + "nauc_recall_at_100_std": 0.18299042640594307, + "nauc_recall_at_10_diff1": -0.051191165463968506, + "nauc_recall_at_10_max": 0.003623628429808181, + "nauc_recall_at_10_std": 0.16905652916837302, + "nauc_recall_at_1_diff1": 0.08124832304802804, + "nauc_recall_at_1_max": -0.13375368929433853, + "nauc_recall_at_1_std": 0.031057150523209072, + "nauc_recall_at_20_diff1": -0.025157810006637294, + "nauc_recall_at_20_max": 0.03831746995608156, + "nauc_recall_at_20_std": 0.17303673054382665, + "nauc_recall_at_3_diff1": 0.06371385523518604, + "nauc_recall_at_3_max": -0.06681664637124785, + "nauc_recall_at_3_std": 0.10526098532538032, + "nauc_recall_at_5_diff1": -0.05396736346561943, + "nauc_recall_at_5_max": -0.026587311266678047, + "nauc_recall_at_5_std": 0.14346984738720725, + "ndcg_at_1": 0.00588, + "ndcg_at_10": 0.01832, + "ndcg_at_100": 0.0368, + "ndcg_at_1000": 0.06249, + "ndcg_at_20": 0.0236, + "ndcg_at_3": 0.01083, + "ndcg_at_5": 0.01491, + "precision_at_1": 0.00588, + "precision_at_10": 0.00349, + "precision_at_100": 0.00129, + "precision_at_1000": 0.00035, + "precision_at_20": 0.00279, + "precision_at_3": 0.00478, + "precision_at_5": 0.00485, + "recall_at_1": 0.00588, + "recall_at_10": 0.03493, + "recall_at_100": 0.12904, + "recall_at_1000": 0.34632, + "recall_at_20": 0.05588, + "recall_at_3": 0.01434, + "recall_at_5": 0.02426 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/RARbCode.json b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/RARbCode.json new file mode 100644 index 000000000..5b3133c88 --- /dev/null +++ b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/RARbCode.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 3013.7035784721375, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.48121, + "map_at_1": 0.3403, + "map_at_10": 0.43225, + "map_at_100": 0.44073, + "map_at_1000": 0.44125, + "map_at_20": 0.43704, + "map_at_3": 0.40645, + "map_at_5": 0.42043, + "mrr_at_1": 0.34097035040431267, + "mrr_at_10": 0.43258407136439464, + "mrr_at_100": 0.4410663241546416, + "mrr_at_1000": 0.4415897680636633, + "mrr_at_20": 0.4373766143523586, + "mrr_at_3": 0.4067834681042228, + "mrr_at_5": 0.42076594788858923, + "nauc_map_at_1000_diff1": 0.4890085130586334, + "nauc_map_at_1000_max": 0.4366282707693178, + "nauc_map_at_1000_std": 0.38181062746599315, + "nauc_map_at_100_diff1": 0.4888687734613964, + "nauc_map_at_100_max": 0.4366713599955114, + "nauc_map_at_100_std": 0.3819204897536032, + "nauc_map_at_10_diff1": 0.4885360007969855, + "nauc_map_at_10_max": 0.4377684576257529, + "nauc_map_at_10_std": 0.3815655097928787, + "nauc_map_at_1_diff1": 0.5486386282502613, + "nauc_map_at_1_max": 0.41421666342685426, + "nauc_map_at_1_std": 0.34987179628832693, + "nauc_map_at_20_diff1": 0.4879479348270673, + "nauc_map_at_20_max": 0.4370046995431948, + "nauc_map_at_20_std": 0.3818783494845684, + "nauc_map_at_3_diff1": 0.4956989779341562, + "nauc_map_at_3_max": 0.43056586738536, + "nauc_map_at_3_std": 0.3774538928587859, + "nauc_map_at_5_diff1": 0.4911892234598353, + "nauc_map_at_5_max": 0.4369440615207409, + "nauc_map_at_5_std": 0.38030427952005963, + "nauc_mrr_at_1000_diff1": 0.48792771219823405, + "nauc_mrr_at_1000_max": 0.4361964321207346, + "nauc_mrr_at_1000_std": 0.3834830369858005, + "nauc_mrr_at_100_diff1": 0.4877894737473183, + "nauc_mrr_at_100_max": 0.43624016687926287, + "nauc_mrr_at_100_std": 0.38359053073866406, + "nauc_mrr_at_10_diff1": 0.4874735389371901, + "nauc_mrr_at_10_max": 0.4373439425582461, + "nauc_mrr_at_10_std": 0.3832086376009776, + "nauc_mrr_at_1_diff1": 0.5465473598786021, + "nauc_mrr_at_1_max": 0.4133966464674671, + "nauc_mrr_at_1_std": 0.3530859568699407, + "nauc_mrr_at_20_diff1": 0.4868771365367993, + "nauc_mrr_at_20_max": 0.43657694304323774, + "nauc_mrr_at_20_std": 0.3835344707511141, + "nauc_mrr_at_3_diff1": 0.49466387542806506, + "nauc_mrr_at_3_max": 0.43015392780252965, + "nauc_mrr_at_3_std": 0.37905357087225416, + "nauc_mrr_at_5_diff1": 0.4901417714096345, + "nauc_mrr_at_5_max": 0.4365258554302311, + "nauc_mrr_at_5_std": 0.381923724165157, + "nauc_ndcg_at_1000_diff1": 0.47186688888020983, + "nauc_ndcg_at_1000_max": 0.4462436819342442, + "nauc_ndcg_at_1000_std": 0.39461997411516614, + "nauc_ndcg_at_100_diff1": 0.46851243096210543, + "nauc_ndcg_at_100_max": 0.44879104055441793, + "nauc_ndcg_at_100_std": 0.39780305232734714, + "nauc_ndcg_at_10_diff1": 0.46461588377269786, + "nauc_ndcg_at_10_max": 0.4499304578186058, + "nauc_ndcg_at_10_std": 0.39381175633725235, + "nauc_ndcg_at_1_diff1": 0.5486386282502613, + "nauc_ndcg_at_1_max": 0.41421666342685426, + "nauc_ndcg_at_1_std": 0.34987179628832693, + "nauc_ndcg_at_20_diff1": 0.46084601504855677, + "nauc_ndcg_at_20_max": 0.4473223391083095, + "nauc_ndcg_at_20_std": 0.395210160512333, + "nauc_ndcg_at_3_diff1": 0.48014708446234255, + "nauc_ndcg_at_3_max": 0.43574371397095446, + "nauc_ndcg_at_3_std": 0.3857774012329781, + "nauc_ndcg_at_5_diff1": 0.4717274248788221, + "nauc_ndcg_at_5_max": 0.44756996367918733, + "nauc_ndcg_at_5_std": 0.39140779356887295, + "nauc_precision_at_1000_diff1": 0.23786056465031374, + "nauc_precision_at_1000_max": 0.6448722004837082, + "nauc_precision_at_1000_std": 0.676514412090789, + "nauc_precision_at_100_diff1": 0.35353588504520506, + "nauc_precision_at_100_max": 0.5497613802061622, + "nauc_precision_at_100_std": 0.5250575398714596, + "nauc_precision_at_10_diff1": 0.3801200996054861, + "nauc_precision_at_10_max": 0.4940520581298417, + "nauc_precision_at_10_std": 0.43598869734045526, + "nauc_precision_at_1_diff1": 0.5486386282502613, + "nauc_precision_at_1_max": 0.41421666342685426, + "nauc_precision_at_1_std": 0.34987179628832693, + "nauc_precision_at_20_diff1": 0.3460876196634242, + "nauc_precision_at_20_max": 0.48778672400956563, + "nauc_precision_at_20_std": 0.4490933754581778, + "nauc_precision_at_3_diff1": 0.4354720956228493, + "nauc_precision_at_3_max": 0.45074521049400473, + "nauc_precision_at_3_std": 0.40976286577775617, + "nauc_precision_at_5_diff1": 0.4119074054516075, + "nauc_precision_at_5_max": 0.481683414097725, + "nauc_precision_at_5_std": 0.42599961889331783, + "nauc_recall_at_1000_diff1": 0.23786056465031616, + "nauc_recall_at_1000_max": 0.6448722004837101, + "nauc_recall_at_1000_std": 0.6765144120907935, + "nauc_recall_at_100_diff1": 0.3535358850452028, + "nauc_recall_at_100_max": 0.5497613802061606, + "nauc_recall_at_100_std": 0.5250575398714572, + "nauc_recall_at_10_diff1": 0.38012009960548576, + "nauc_recall_at_10_max": 0.49405205812984193, + "nauc_recall_at_10_std": 0.4359886973404557, + "nauc_recall_at_1_diff1": 0.5486386282502613, + "nauc_recall_at_1_max": 0.41421666342685426, + "nauc_recall_at_1_std": 0.34987179628832693, + "nauc_recall_at_20_diff1": 0.34608761966342494, + "nauc_recall_at_20_max": 0.487786724009565, + "nauc_recall_at_20_std": 0.44909337545817835, + "nauc_recall_at_3_diff1": 0.4354720956228491, + "nauc_recall_at_3_max": 0.45074521049400423, + "nauc_recall_at_3_std": 0.4097628657777563, + "nauc_recall_at_5_diff1": 0.41190740545160787, + "nauc_recall_at_5_max": 0.48168341409772497, + "nauc_recall_at_5_std": 0.42599961889331794, + "ndcg_at_1": 0.3403, + "ndcg_at_10": 0.48121, + "ndcg_at_100": 0.52529, + "ndcg_at_1000": 0.53938, + "ndcg_at_20": 0.49873, + "ndcg_at_3": 0.42789, + "ndcg_at_5": 0.4534, + "precision_at_1": 0.3403, + "precision_at_10": 0.06368, + "precision_at_100": 0.00849, + "precision_at_1000": 0.00096, + "precision_at_20": 0.03531, + "precision_at_3": 0.1633, + "precision_at_5": 0.11051, + "recall_at_1": 0.3403, + "recall_at_10": 0.63679, + "recall_at_100": 0.84906, + "recall_at_1000": 0.96092, + "recall_at_20": 0.7062, + "recall_at_3": 0.48989, + "recall_at_5": 0.55256 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/RARbMath.json b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/RARbMath.json new file mode 100644 index 000000000..680076b59 --- /dev/null +++ b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/RARbMath.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 4603.088869571686, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.57359, + "map_at_1": 0.49058, + "map_at_10": 0.54457, + "map_at_100": 0.55145, + "map_at_1000": 0.55195, + "map_at_20": 0.54839, + "map_at_3": 0.52917, + "map_at_5": 0.5379, + "mrr_at_1": 0.4905839531571451, + "mrr_at_10": 0.5445693511882781, + "mrr_at_100": 0.5514537112287441, + "mrr_at_1000": 0.5519538768631277, + "mrr_at_20": 0.5483901389552961, + "mrr_at_3": 0.5291712823759035, + "mrr_at_5": 0.537898929155457, + "nauc_map_at_1000_diff1": 0.7788616860407561, + "nauc_map_at_1000_max": 0.43006060447341893, + "nauc_map_at_1000_std": -0.2392504166866928, + "nauc_map_at_100_diff1": 0.7786626796978537, + "nauc_map_at_100_max": 0.42990855991540605, + "nauc_map_at_100_std": -0.23933671604564805, + "nauc_map_at_10_diff1": 0.7797759590926934, + "nauc_map_at_10_max": 0.4284471383745825, + "nauc_map_at_10_std": -0.2419617905187608, + "nauc_map_at_1_diff1": 0.818672879168993, + "nauc_map_at_1_max": 0.4590367940836591, + "nauc_map_at_1_std": -0.2327201351630689, + "nauc_map_at_20_diff1": 0.7785895603267625, + "nauc_map_at_20_max": 0.42909409770272805, + "nauc_map_at_20_std": -0.2403028879633341, + "nauc_map_at_3_diff1": 0.7882552647857282, + "nauc_map_at_3_max": 0.4333657701499395, + "nauc_map_at_3_std": -0.24375433202268185, + "nauc_map_at_5_diff1": 0.7816952798486545, + "nauc_map_at_5_max": 0.4291983820240859, + "nauc_map_at_5_std": -0.24343146077624592, + "nauc_mrr_at_1000_diff1": 0.7788617091276826, + "nauc_mrr_at_1000_max": 0.4300605874345076, + "nauc_mrr_at_1000_std": -0.23925039100882034, + "nauc_mrr_at_100_diff1": 0.7786626796978537, + "nauc_mrr_at_100_max": 0.42990855991540605, + "nauc_mrr_at_100_std": -0.23933671604564805, + "nauc_mrr_at_10_diff1": 0.7797759590926934, + "nauc_mrr_at_10_max": 0.4284471383745825, + "nauc_mrr_at_10_std": -0.2419617905187608, + "nauc_mrr_at_1_diff1": 0.818672879168993, + "nauc_mrr_at_1_max": 0.4590367940836591, + "nauc_mrr_at_1_std": -0.2327201351630689, + "nauc_mrr_at_20_diff1": 0.7785895603267625, + "nauc_mrr_at_20_max": 0.42909409770272805, + "nauc_mrr_at_20_std": -0.2403028879633341, + "nauc_mrr_at_3_diff1": 0.7882552647857282, + "nauc_mrr_at_3_max": 0.4333657701499395, + "nauc_mrr_at_3_std": -0.24375433202268185, + "nauc_mrr_at_5_diff1": 0.7816952798486545, + "nauc_mrr_at_5_max": 0.4291983820240859, + "nauc_mrr_at_5_std": -0.24343146077624592, + "nauc_ndcg_at_1000_diff1": 0.7625245744464318, + "nauc_ndcg_at_1000_max": 0.4263528831512472, + "nauc_ndcg_at_1000_std": -0.22700488707029412, + "nauc_ndcg_at_100_diff1": 0.7557639992349352, + "nauc_ndcg_at_100_max": 0.42268965993237406, + "nauc_ndcg_at_100_std": -0.22822321947553778, + "nauc_ndcg_at_10_diff1": 0.7600657363073214, + "nauc_ndcg_at_10_max": 0.4143049005209262, + "nauc_ndcg_at_10_std": -0.24334240114728958, + "nauc_ndcg_at_1_diff1": 0.818672879168993, + "nauc_ndcg_at_1_max": 0.4590367940836591, + "nauc_ndcg_at_1_std": -0.2327201351630689, + "nauc_ndcg_at_20_diff1": 0.7551160562150742, + "nauc_ndcg_at_20_max": 0.4164700613158976, + "nauc_ndcg_at_20_std": -0.23647346615325499, + "nauc_ndcg_at_3_diff1": 0.7776584012088205, + "nauc_ndcg_at_3_max": 0.4244662884705782, + "nauc_ndcg_at_3_std": -0.24713208481821725, + "nauc_ndcg_at_5_diff1": 0.7655775098890775, + "nauc_ndcg_at_5_max": 0.4165845147800867, + "nauc_ndcg_at_5_std": -0.24682523351995392, + "nauc_precision_at_1000_diff1": 0.5844586077387123, + "nauc_precision_at_1000_max": 0.529728183220264, + "nauc_precision_at_1000_std": 0.2246889794676157, + "nauc_precision_at_100_diff1": 0.6013747141242026, + "nauc_precision_at_100_max": 0.4027538684824536, + "nauc_precision_at_100_std": -0.1082059079148881, + "nauc_precision_at_10_diff1": 0.6873092560929639, + "nauc_precision_at_10_max": 0.3630181248590965, + "nauc_precision_at_10_std": -0.2465949242625704, + "nauc_precision_at_1_diff1": 0.818672879168993, + "nauc_precision_at_1_max": 0.4590367940836591, + "nauc_precision_at_1_std": -0.2327201351630689, + "nauc_precision_at_20_diff1": 0.652445925647192, + "nauc_precision_at_20_max": 0.3667577754259474, + "nauc_precision_at_20_std": -0.2111310744044319, + "nauc_precision_at_3_diff1": 0.7453755828701419, + "nauc_precision_at_3_max": 0.39736810384403404, + "nauc_precision_at_3_std": -0.2572768700755282, + "nauc_precision_at_5_diff1": 0.7127015921872023, + "nauc_precision_at_5_max": 0.37531062389896436, + "nauc_precision_at_5_std": -0.25757180363491405, + "nauc_recall_at_1000_diff1": 0.5844586077387159, + "nauc_recall_at_1000_max": 0.5297281832202694, + "nauc_recall_at_1000_std": 0.22468897946762142, + "nauc_recall_at_100_diff1": 0.6013747141242042, + "nauc_recall_at_100_max": 0.4027538684824529, + "nauc_recall_at_100_std": -0.10820590791488881, + "nauc_recall_at_10_diff1": 0.6873092560929639, + "nauc_recall_at_10_max": 0.3630181248590973, + "nauc_recall_at_10_std": -0.24659492426256988, + "nauc_recall_at_1_diff1": 0.818672879168993, + "nauc_recall_at_1_max": 0.4590367940836591, + "nauc_recall_at_1_std": -0.2327201351630689, + "nauc_recall_at_20_diff1": 0.6524459256471917, + "nauc_recall_at_20_max": 0.3667577754259465, + "nauc_recall_at_20_std": -0.21113107440443135, + "nauc_recall_at_3_diff1": 0.7453755828701422, + "nauc_recall_at_3_max": 0.3973681038440342, + "nauc_recall_at_3_std": -0.2572768700755287, + "nauc_recall_at_5_diff1": 0.7127015921872026, + "nauc_recall_at_5_max": 0.37531062389896497, + "nauc_recall_at_5_std": -0.25757180363491317, + "ndcg_at_1": 0.49058, + "ndcg_at_10": 0.57359, + "ndcg_at_100": 0.60995, + "ndcg_at_1000": 0.62419, + "ndcg_at_20": 0.58767, + "ndcg_at_3": 0.54174, + "ndcg_at_5": 0.55742, + "precision_at_1": 0.49058, + "precision_at_10": 0.06661, + "precision_at_100": 0.00842, + "precision_at_1000": 0.00096, + "precision_at_20": 0.03611, + "precision_at_3": 0.1927, + "precision_at_5": 0.12322, + "recall_at_1": 0.49058, + "recall_at_10": 0.66609, + "recall_at_100": 0.84238, + "recall_at_1000": 0.95648, + "recall_at_20": 0.72211, + "recall_at_3": 0.5781, + "recall_at_5": 0.61608 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/SIQA.json b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/SIQA.json new file mode 100644 index 000000000..9288a30e2 --- /dev/null +++ b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/SIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 33.66920804977417, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01036, + "map_at_1": 0.00051, + "map_at_10": 0.00628, + "map_at_100": 0.00897, + "map_at_1000": 0.00962, + "map_at_20": 0.00725, + "map_at_3": 0.00409, + "map_at_5": 0.00468, + "mrr_at_1": 0.0005117707267144319, + "mrr_at_10": 0.0062787363324722555, + "mrr_at_100": 0.008972601335853593, + "mrr_at_1000": 0.009618233327546234, + "mrr_at_20": 0.007254091475589965, + "mrr_at_3": 0.0040941658137154556, + "mrr_at_5": 0.004682702149437052, + "nauc_map_at_1000_diff1": -0.15661968120769668, + "nauc_map_at_1000_max": -0.11013403612802085, + "nauc_map_at_1000_std": 0.07148428939717427, + "nauc_map_at_100_diff1": -0.16133519907153868, + "nauc_map_at_100_max": -0.1140070909901328, + "nauc_map_at_100_std": 0.07160032897422564, + "nauc_map_at_10_diff1": -0.21955114554131705, + "nauc_map_at_10_max": -0.1443501004070283, + "nauc_map_at_10_std": 0.07486626603873861, + "nauc_map_at_1_diff1": -0.41486592194481703, + "nauc_map_at_1_max": -0.20566865955458707, + "nauc_map_at_1_std": -0.31833868118838016, + "nauc_map_at_20_diff1": -0.1936801718657762, + "nauc_map_at_20_max": -0.12951131727733758, + "nauc_map_at_20_std": 0.06436979563042788, + "nauc_map_at_3_diff1": -0.30438863987109493, + "nauc_map_at_3_max": -0.16046943973365582, + "nauc_map_at_3_std": 0.047037853016540655, + "nauc_map_at_5_diff1": -0.2537217943000065, + "nauc_map_at_5_max": -0.16804142656886592, + "nauc_map_at_5_std": 0.004197798988317119, + "nauc_mrr_at_1000_diff1": -0.15656277575159408, + "nauc_mrr_at_1000_max": -0.11009698275412202, + "nauc_mrr_at_1000_std": 0.07148619545209256, + "nauc_mrr_at_100_diff1": -0.1612759552156447, + "nauc_mrr_at_100_max": -0.11396753408595753, + "nauc_mrr_at_100_std": 0.0716016935801952, + "nauc_mrr_at_10_diff1": -0.21955114554131705, + "nauc_mrr_at_10_max": -0.1443501004070283, + "nauc_mrr_at_10_std": 0.07486626603873861, + "nauc_mrr_at_1_diff1": -0.41486592194481703, + "nauc_mrr_at_1_max": -0.20566865955458707, + "nauc_mrr_at_1_std": -0.31833868118838016, + "nauc_mrr_at_20_diff1": -0.1936801718657762, + "nauc_mrr_at_20_max": -0.12951131727733758, + "nauc_mrr_at_20_std": 0.06436979563042788, + "nauc_mrr_at_3_diff1": -0.30438863987109493, + "nauc_mrr_at_3_max": -0.16046943973365582, + "nauc_mrr_at_3_std": 0.047037853016540655, + "nauc_mrr_at_5_diff1": -0.2537217943000065, + "nauc_mrr_at_5_max": -0.16804142656886592, + "nauc_mrr_at_5_std": 0.004197798988317119, + "nauc_ndcg_at_1000_diff1": -0.07841191921420682, + "nauc_ndcg_at_1000_max": -0.05655261831142639, + "nauc_ndcg_at_1000_std": 0.08009652886192146, + "nauc_ndcg_at_100_diff1": -0.10421996655375987, + "nauc_ndcg_at_100_max": -0.09520316588123551, + "nauc_ndcg_at_100_std": 0.08089387258425296, + "nauc_ndcg_at_10_diff1": -0.19113289183226337, + "nauc_ndcg_at_10_max": -0.1384640519436539, + "nauc_ndcg_at_10_std": 0.10154317687208515, + "nauc_ndcg_at_1_diff1": -0.41486592194481703, + "nauc_ndcg_at_1_max": -0.20566865955458707, + "nauc_ndcg_at_1_std": -0.31833868118838016, + "nauc_ndcg_at_20_diff1": -0.15085405100003438, + "nauc_ndcg_at_20_max": -0.11225461505100737, + "nauc_ndcg_at_20_std": 0.07884722821582046, + "nauc_ndcg_at_3_diff1": -0.3065724836825383, + "nauc_ndcg_at_3_max": -0.1638718288635044, + "nauc_ndcg_at_3_std": 0.05051902413988816, + "nauc_ndcg_at_5_diff1": -0.24300397363764117, + "nauc_ndcg_at_5_max": -0.17552274854863587, + "nauc_ndcg_at_5_std": -0.006611029566835075, + "nauc_precision_at_1000_diff1": -0.049671467356044746, + "nauc_precision_at_1000_max": -0.026429051146521113, + "nauc_precision_at_1000_std": 0.08102036155651876, + "nauc_precision_at_100_diff1": -0.08241036685543668, + "nauc_precision_at_100_max": -0.09075717463642334, + "nauc_precision_at_100_std": 0.0807452953183318, + "nauc_precision_at_10_diff1": -0.16162912988309044, + "nauc_precision_at_10_max": -0.13206629892305333, + "nauc_precision_at_10_std": 0.1293485169330936, + "nauc_precision_at_1_diff1": -0.41486592194481703, + "nauc_precision_at_1_max": -0.20566865955458707, + "nauc_precision_at_1_std": -0.31833868118838016, + "nauc_precision_at_20_diff1": -0.11519037636755725, + "nauc_precision_at_20_max": -0.09661964951334077, + "nauc_precision_at_20_std": 0.08943293415122965, + "nauc_precision_at_3_diff1": -0.31059711235572873, + "nauc_precision_at_3_max": -0.16939850469290665, + "nauc_precision_at_3_std": 0.05376202449003592, + "nauc_precision_at_5_diff1": -0.22843964873845524, + "nauc_precision_at_5_max": -0.18681013711396735, + "nauc_precision_at_5_std": -0.024304217005866963, + "nauc_recall_at_1000_diff1": -0.04967146735604448, + "nauc_recall_at_1000_max": -0.02642905114652088, + "nauc_recall_at_1000_std": 0.08102036155651912, + "nauc_recall_at_100_diff1": -0.08241036685543661, + "nauc_recall_at_100_max": -0.09075717463642337, + "nauc_recall_at_100_std": 0.08074529531833172, + "nauc_recall_at_10_diff1": -0.1616291298830907, + "nauc_recall_at_10_max": -0.13206629892305366, + "nauc_recall_at_10_std": 0.12934851693309335, + "nauc_recall_at_1_diff1": -0.41486592194481703, + "nauc_recall_at_1_max": -0.20566865955458707, + "nauc_recall_at_1_std": -0.31833868118838016, + "nauc_recall_at_20_diff1": -0.11519037636755734, + "nauc_recall_at_20_max": -0.09661964951334083, + "nauc_recall_at_20_std": 0.08943293415122948, + "nauc_recall_at_3_diff1": -0.3105971123557287, + "nauc_recall_at_3_max": -0.16939850469290654, + "nauc_recall_at_3_std": 0.05376202449003598, + "nauc_recall_at_5_diff1": -0.22843964873845526, + "nauc_recall_at_5_max": -0.18681013711396738, + "nauc_recall_at_5_std": -0.02430421700586699, + "ndcg_at_1": 0.00051, + "ndcg_at_10": 0.01036, + "ndcg_at_100": 0.02677, + "ndcg_at_1000": 0.05022, + "ndcg_at_20": 0.01387, + "ndcg_at_3": 0.00528, + "ndcg_at_5": 0.00633, + "precision_at_1": 0.00051, + "precision_at_10": 0.00241, + "precision_at_100": 0.00108, + "precision_at_1000": 0.00031, + "precision_at_20": 0.00189, + "precision_at_3": 0.0029, + "precision_at_5": 0.00225, + "recall_at_1": 0.00051, + "recall_at_10": 0.02405, + "recall_at_100": 0.1085, + "recall_at_1000": 0.30757, + "recall_at_20": 0.03787, + "recall_at_3": 0.0087, + "recall_at_5": 0.01126 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/SpartQA.json b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/SpartQA.json new file mode 100644 index 000000000..206098095 --- /dev/null +++ b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/SpartQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 27.371941804885864, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02993, + "map_at_1": 0.00612, + "map_at_10": 0.01649, + "map_at_100": 0.02415, + "map_at_1000": 0.02549, + "map_at_20": 0.02019, + "map_at_3": 0.00946, + "map_at_5": 0.01156, + "mrr_at_1": 0.01001669449081803, + "mrr_at_10": 0.0272321152538181, + "mrr_at_100": 0.037676037700268374, + "mrr_at_1000": 0.03910136868390102, + "mrr_at_20": 0.03260659694677047, + "mrr_at_3": 0.01613800779076239, + "mrr_at_5": 0.019880356149137468, + "nauc_map_at_1000_diff1": -0.09462437242668087, + "nauc_map_at_1000_max": -0.2304412085702106, + "nauc_map_at_1000_std": 0.3601162342931986, + "nauc_map_at_100_diff1": -0.09505014793504563, + "nauc_map_at_100_max": -0.22385770994268522, + "nauc_map_at_100_std": 0.3528851272142255, + "nauc_map_at_10_diff1": -0.12122362604128861, + "nauc_map_at_10_max": -0.21682230560932114, + "nauc_map_at_10_std": 0.35674372745613186, + "nauc_map_at_1_diff1": -0.33324816120893697, + "nauc_map_at_1_max": -0.3893730323836286, + "nauc_map_at_1_std": 0.4543851962126474, + "nauc_map_at_20_diff1": -0.10312156739887829, + "nauc_map_at_20_max": -0.2149989545278317, + "nauc_map_at_20_std": 0.3496685149429283, + "nauc_map_at_3_diff1": -0.2068526532068033, + "nauc_map_at_3_max": -0.31481425079328496, + "nauc_map_at_3_std": 0.4123120200328107, + "nauc_map_at_5_diff1": -0.17436833985080913, + "nauc_map_at_5_max": -0.2801424204360635, + "nauc_map_at_5_std": 0.37605604935609666, + "nauc_mrr_at_1000_diff1": -0.07176272769829174, + "nauc_mrr_at_1000_max": -0.1958919483304485, + "nauc_mrr_at_1000_std": 0.35299899620569003, + "nauc_mrr_at_100_diff1": -0.07145886247408981, + "nauc_mrr_at_100_max": -0.19340593641661669, + "nauc_mrr_at_100_std": 0.3497072064164153, + "nauc_mrr_at_10_diff1": -0.09932365178428318, + "nauc_mrr_at_10_max": -0.18562217315795734, + "nauc_mrr_at_10_std": 0.3543346493135588, + "nauc_mrr_at_1_diff1": -0.3598408328147733, + "nauc_mrr_at_1_max": -0.3542631465290275, + "nauc_mrr_at_1_std": 0.4605502859231905, + "nauc_mrr_at_20_diff1": -0.07596508976112826, + "nauc_mrr_at_20_max": -0.18638943137350927, + "nauc_mrr_at_20_std": 0.35081480065099924, + "nauc_mrr_at_3_diff1": -0.20904129594713078, + "nauc_mrr_at_3_max": -0.27392068359637206, + "nauc_mrr_at_3_std": 0.42313646038853886, + "nauc_mrr_at_5_diff1": -0.1641662048112181, + "nauc_mrr_at_5_max": -0.23882532161082543, + "nauc_mrr_at_5_std": 0.384662715939034, + "nauc_ndcg_at_1000_diff1": -0.019396923415809092, + "nauc_ndcg_at_1000_max": -0.2727141297282907, + "nauc_ndcg_at_1000_std": 0.42200957176013376, + "nauc_ndcg_at_100_diff1": -0.03211373921922155, + "nauc_ndcg_at_100_max": -0.20225508439522955, + "nauc_ndcg_at_100_std": 0.34591033428033796, + "nauc_ndcg_at_10_diff1": -0.0660180400582697, + "nauc_ndcg_at_10_max": -0.1609428620213725, + "nauc_ndcg_at_10_std": 0.33207591466757536, + "nauc_ndcg_at_1_diff1": -0.3598408328147733, + "nauc_ndcg_at_1_max": -0.3542631465290275, + "nauc_ndcg_at_1_std": 0.4605502859231905, + "nauc_ndcg_at_20_diff1": -0.03946255031673463, + "nauc_ndcg_at_20_max": -0.16877527104761503, + "nauc_ndcg_at_20_std": 0.3248491832821944, + "nauc_ndcg_at_3_diff1": -0.1818394456277844, + "nauc_ndcg_at_3_max": -0.28623400319828984, + "nauc_ndcg_at_3_std": 0.41040925725451954, + "nauc_ndcg_at_5_diff1": -0.13638221474341738, + "nauc_ndcg_at_5_max": -0.24033419711885934, + "nauc_ndcg_at_5_std": 0.35690353119437024, + "nauc_precision_at_1000_diff1": 0.07976084781659203, + "nauc_precision_at_1000_max": -0.2802586966315839, + "nauc_precision_at_1000_std": 0.36769827729315274, + "nauc_precision_at_100_diff1": 0.028853760604852917, + "nauc_precision_at_100_max": -0.20436209646001638, + "nauc_precision_at_100_std": 0.35013853453021043, + "nauc_precision_at_10_diff1": 0.010368015459489552, + "nauc_precision_at_10_max": -0.10060849368032515, + "nauc_precision_at_10_std": 0.29858743091065454, + "nauc_precision_at_1_diff1": -0.3598408328147733, + "nauc_precision_at_1_max": -0.3542631465290275, + "nauc_precision_at_1_std": 0.4605502859231905, + "nauc_precision_at_20_diff1": 0.04023731420900398, + "nauc_precision_at_20_max": -0.1292266462514616, + "nauc_precision_at_20_std": 0.3091919927621368, + "nauc_precision_at_3_diff1": -0.133069263322492, + "nauc_precision_at_3_max": -0.22882155508095162, + "nauc_precision_at_3_std": 0.41181259403087495, + "nauc_precision_at_5_diff1": -0.06858970618461473, + "nauc_precision_at_5_max": -0.17352727108072952, + "nauc_precision_at_5_std": 0.328618089127195, + "nauc_recall_at_1000_diff1": 0.012057313129576424, + "nauc_recall_at_1000_max": -0.2860355697771198, + "nauc_recall_at_1000_std": 0.4110937568652643, + "nauc_recall_at_100_diff1": -0.01366732021666734, + "nauc_recall_at_100_max": -0.1820803695811365, + "nauc_recall_at_100_std": 0.3140434255395357, + "nauc_recall_at_10_diff1": -0.03380668701287019, + "nauc_recall_at_10_max": -0.12278457941196877, + "nauc_recall_at_10_std": 0.31431765502760345, + "nauc_recall_at_1_diff1": -0.33324816120893697, + "nauc_recall_at_1_max": -0.3893730323836286, + "nauc_recall_at_1_std": 0.4543851962126474, + "nauc_recall_at_20_diff1": -0.01421257823481198, + "nauc_recall_at_20_max": -0.1457709059269407, + "nauc_recall_at_20_std": 0.30055666582819723, + "nauc_recall_at_3_diff1": -0.131047941351508, + "nauc_recall_at_3_max": -0.26568827493901764, + "nauc_recall_at_3_std": 0.3959848366746737, + "nauc_recall_at_5_diff1": -0.09046020003874802, + "nauc_recall_at_5_max": -0.2096197342169733, + "nauc_recall_at_5_std": 0.3192244765286294, + "ndcg_at_1": 0.01002, + "ndcg_at_10": 0.02993, + "ndcg_at_100": 0.07647, + "ndcg_at_1000": 0.1189, + "ndcg_at_20": 0.04463, + "ndcg_at_3": 0.01217, + "ndcg_at_5": 0.01659, + "precision_at_1": 0.01002, + "precision_at_10": 0.00988, + "precision_at_100": 0.00435, + "precision_at_1000": 0.00097, + "precision_at_20": 0.00907, + "precision_at_3": 0.00807, + "precision_at_5": 0.00812, + "recall_at_1": 0.00612, + "recall_at_10": 0.06093, + "recall_at_100": 0.26869, + "recall_at_1000": 0.57169, + "recall_at_20": 0.11297, + "recall_at_3": 0.014, + "recall_at_5": 0.02337 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL1.json b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL1.json new file mode 100644 index 000000000..af09bc532 --- /dev/null +++ b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL1.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 10.789602994918823, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01459, + "map_at_1": 0.0025, + "map_at_10": 0.009, + "map_at_100": 0.01372, + "map_at_1000": 0.01496, + "map_at_20": 0.01114, + "map_at_3": 0.00525, + "map_at_5": 0.00685, + "mrr_at_1": 0.0025, + "mrr_at_10": 0.009000793650793655, + "mrr_at_100": 0.01371714232055184, + "mrr_at_1000": 0.0149586444323938, + "mrr_at_20": 0.011143978032416528, + "mrr_at_3": 0.0052499999999999995, + "mrr_at_5": 0.006849999999999997, + "nauc_map_at_1000_diff1": -0.001680722219430552, + "nauc_map_at_1000_max": 0.15808452577536672, + "nauc_map_at_1000_std": 0.18157658032873444, + "nauc_map_at_100_diff1": 0.0021475185298890863, + "nauc_map_at_100_max": 0.15854690486955747, + "nauc_map_at_100_std": 0.18402236958079896, + "nauc_map_at_10_diff1": 0.0062901062264567155, + "nauc_map_at_10_max": 0.17503983873627801, + "nauc_map_at_10_std": 0.23838333182667398, + "nauc_map_at_1_diff1": -0.1317413469278239, + "nauc_map_at_1_max": 0.3478132546283873, + "nauc_map_at_1_std": 0.5063321706466328, + "nauc_map_at_20_diff1": 0.010068607888858577, + "nauc_map_at_20_max": 0.1643333232978275, + "nauc_map_at_20_std": 0.20162524515687935, + "nauc_map_at_3_diff1": 0.01206340688497909, + "nauc_map_at_3_max": 0.18995234262205013, + "nauc_map_at_3_std": 0.30424700065161575, + "nauc_map_at_5_diff1": 0.007351822728468679, + "nauc_map_at_5_max": 0.1891778088088697, + "nauc_map_at_5_std": 0.28767095117695113, + "nauc_mrr_at_1000_diff1": -0.001680722219430552, + "nauc_mrr_at_1000_max": 0.15808452577536672, + "nauc_mrr_at_1000_std": 0.18157658032873444, + "nauc_mrr_at_100_diff1": 0.0021475185298890863, + "nauc_mrr_at_100_max": 0.15854690486955747, + "nauc_mrr_at_100_std": 0.18402236958079896, + "nauc_mrr_at_10_diff1": 0.0062901062264567155, + "nauc_mrr_at_10_max": 0.17503983873627801, + "nauc_mrr_at_10_std": 0.23838333182667398, + "nauc_mrr_at_1_diff1": -0.1317413469278239, + "nauc_mrr_at_1_max": 0.3478132546283873, + "nauc_mrr_at_1_std": 0.5063321706466328, + "nauc_mrr_at_20_diff1": 0.010068607888858577, + "nauc_mrr_at_20_max": 0.1643333232978275, + "nauc_mrr_at_20_std": 0.20162524515687935, + "nauc_mrr_at_3_diff1": 0.01206340688497909, + "nauc_mrr_at_3_max": 0.18995234262205013, + "nauc_mrr_at_3_std": 0.30424700065161575, + "nauc_mrr_at_5_diff1": 0.007351822728468679, + "nauc_mrr_at_5_max": 0.1891778088088697, + "nauc_mrr_at_5_std": 0.28767095117695113, + "nauc_ndcg_at_1000_diff1": -0.03584802021173371, + "nauc_ndcg_at_1000_max": 0.14262521999138394, + "nauc_ndcg_at_1000_std": 0.1225405949868495, + "nauc_ndcg_at_100_diff1": -0.003726117823991231, + "nauc_ndcg_at_100_max": 0.1296560426116582, + "nauc_ndcg_at_100_std": 0.1199658517933518, + "nauc_ndcg_at_10_diff1": 0.024699673849455848, + "nauc_ndcg_at_10_max": 0.1600303707975624, + "nauc_ndcg_at_10_std": 0.1980346849310171, + "nauc_ndcg_at_1_diff1": -0.1317413469278239, + "nauc_ndcg_at_1_max": 0.3478132546283873, + "nauc_ndcg_at_1_std": 0.5063321706466328, + "nauc_ndcg_at_20_diff1": 0.022242078480579477, + "nauc_ndcg_at_20_max": 0.14413629542840703, + "nauc_ndcg_at_20_std": 0.14512777440069746, + "nauc_ndcg_at_3_diff1": 0.04654784404377604, + "nauc_ndcg_at_3_max": 0.16652351053472536, + "nauc_ndcg_at_3_std": 0.2734077876903067, + "nauc_ndcg_at_5_diff1": 0.03279741750705075, + "nauc_ndcg_at_5_max": 0.17222854364639872, + "nauc_ndcg_at_5_std": 0.2613699688528739, + "nauc_precision_at_1000_diff1": -0.0689610238460924, + "nauc_precision_at_1000_max": 0.14736923277946806, + "nauc_precision_at_1000_std": 0.10795145813385354, + "nauc_precision_at_100_diff1": -0.011773760656772986, + "nauc_precision_at_100_max": 0.11479098691365834, + "nauc_precision_at_100_std": 0.0923753639967724, + "nauc_precision_at_10_diff1": 0.040599257535771566, + "nauc_precision_at_10_max": 0.1484227640974093, + "nauc_precision_at_10_std": 0.16095935669118844, + "nauc_precision_at_1_diff1": -0.1317413469278239, + "nauc_precision_at_1_max": 0.3478132546283873, + "nauc_precision_at_1_std": 0.5063321706466328, + "nauc_precision_at_20_diff1": 0.027430254397513915, + "nauc_precision_at_20_max": 0.13090313093433004, + "nauc_precision_at_20_std": 0.1058065696998437, + "nauc_precision_at_3_diff1": 0.10474065496448388, + "nauc_precision_at_3_max": 0.12856396424385344, + "nauc_precision_at_3_std": 0.22329233332862605, + "nauc_precision_at_5_diff1": 0.06572838662991613, + "nauc_precision_at_5_max": 0.15164117699669086, + "nauc_precision_at_5_std": 0.22891105853273835, + "nauc_recall_at_1000_diff1": -0.06896102384609201, + "nauc_recall_at_1000_max": 0.14736923277946873, + "nauc_recall_at_1000_std": 0.10795145813385425, + "nauc_recall_at_100_diff1": -0.011773760656773033, + "nauc_recall_at_100_max": 0.11479098691365809, + "nauc_recall_at_100_std": 0.09237536399677222, + "nauc_recall_at_10_diff1": 0.04059925753577164, + "nauc_recall_at_10_max": 0.1484227640974093, + "nauc_recall_at_10_std": 0.16095935669118838, + "nauc_recall_at_1_diff1": -0.1317413469278239, + "nauc_recall_at_1_max": 0.3478132546283873, + "nauc_recall_at_1_std": 0.5063321706466328, + "nauc_recall_at_20_diff1": 0.027430254397514096, + "nauc_recall_at_20_max": 0.13090313093432995, + "nauc_recall_at_20_std": 0.10580656969984388, + "nauc_recall_at_3_diff1": 0.10474065496448398, + "nauc_recall_at_3_max": 0.1285639642438535, + "nauc_recall_at_3_std": 0.22329233332862616, + "nauc_recall_at_5_diff1": 0.06572838662991608, + "nauc_recall_at_5_max": 0.15164117699669089, + "nauc_recall_at_5_std": 0.22891105853273816, + "ndcg_at_1": 0.0025, + "ndcg_at_10": 0.01459, + "ndcg_at_100": 0.04304, + "ndcg_at_1000": 0.08854, + "ndcg_at_20": 0.02242, + "ndcg_at_3": 0.00633, + "ndcg_at_5": 0.00921, + "precision_at_1": 0.0025, + "precision_at_10": 0.00335, + "precision_at_100": 0.0018, + "precision_at_1000": 0.00057, + "precision_at_20": 0.00323, + "precision_at_3": 0.00317, + "precision_at_5": 0.0033, + "recall_at_1": 0.0025, + "recall_at_10": 0.0335, + "recall_at_100": 0.18, + "recall_at_1000": 0.5655, + "recall_at_20": 0.0645, + "recall_at_3": 0.0095, + "recall_at_5": 0.0165 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL2Fact.json b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL2Fact.json new file mode 100644 index 000000000..039e7cad3 --- /dev/null +++ b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL2Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 63.72642636299133, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.24248, + "map_at_1": 0.10543, + "map_at_10": 0.19243, + "map_at_100": 0.20396, + "map_at_1000": 0.20476, + "map_at_20": 0.19904, + "map_at_3": 0.16346, + "map_at_5": 0.1799, + "mrr_at_1": 0.10542894200481749, + "mrr_at_10": 0.1924335536203248, + "mrr_at_100": 0.2039597063693534, + "mrr_at_1000": 0.20476169479526368, + "mrr_at_20": 0.19903642377118422, + "mrr_at_3": 0.1634550058674579, + "mrr_at_5": 0.17989932678648768, + "nauc_map_at_1000_diff1": 0.009080672537790454, + "nauc_map_at_1000_max": -0.020069526416928753, + "nauc_map_at_1000_std": 0.05848629017195087, + "nauc_map_at_100_diff1": 0.009033962920823644, + "nauc_map_at_100_max": -0.01982622673266152, + "nauc_map_at_100_std": 0.05905427858748045, + "nauc_map_at_10_diff1": 0.010588372188036405, + "nauc_map_at_10_max": -0.01829669812007949, + "nauc_map_at_10_std": 0.05111762352661315, + "nauc_map_at_1_diff1": 0.047784112391869665, + "nauc_map_at_1_max": -0.03347905728864299, + "nauc_map_at_1_std": 0.01228651610574734, + "nauc_map_at_20_diff1": 0.010707475145431635, + "nauc_map_at_20_max": -0.017214785538610396, + "nauc_map_at_20_std": 0.05744547923305885, + "nauc_map_at_3_diff1": 0.01951387224579398, + "nauc_map_at_3_max": -0.013517823043352225, + "nauc_map_at_3_std": 0.033315278086476975, + "nauc_map_at_5_diff1": 0.013808405460564372, + "nauc_map_at_5_max": -0.01725279459885914, + "nauc_map_at_5_std": 0.040794572390721845, + "nauc_mrr_at_1000_diff1": 0.00908066801315866, + "nauc_mrr_at_1000_max": -0.02006952783047357, + "nauc_mrr_at_1000_std": 0.058486289596937545, + "nauc_mrr_at_100_diff1": 0.009033962920823644, + "nauc_mrr_at_100_max": -0.01982622673266152, + "nauc_mrr_at_100_std": 0.05905427858748045, + "nauc_mrr_at_10_diff1": 0.010588372188036405, + "nauc_mrr_at_10_max": -0.01829669812007949, + "nauc_mrr_at_10_std": 0.05111762352661315, + "nauc_mrr_at_1_diff1": 0.047784112391869665, + "nauc_mrr_at_1_max": -0.03347905728864299, + "nauc_mrr_at_1_std": 0.01228651610574734, + "nauc_mrr_at_20_diff1": 0.010707475145431635, + "nauc_mrr_at_20_max": -0.017214785538610396, + "nauc_mrr_at_20_std": 0.05744547923305885, + "nauc_mrr_at_3_diff1": 0.01951387224579398, + "nauc_mrr_at_3_max": -0.013517823043352225, + "nauc_mrr_at_3_std": 0.033315278086476975, + "nauc_mrr_at_5_diff1": 0.013808405460564372, + "nauc_mrr_at_5_max": -0.01725279459885914, + "nauc_mrr_at_5_std": 0.040794572390721845, + "nauc_ndcg_at_1000_diff1": -0.015035410932808434, + "nauc_ndcg_at_1000_max": -0.03848035167564171, + "nauc_ndcg_at_1000_std": 0.08895645675170119, + "nauc_ndcg_at_100_diff1": -0.016550195954754814, + "nauc_ndcg_at_100_max": -0.03383074716003292, + "nauc_ndcg_at_100_std": 0.10301882562520609, + "nauc_ndcg_at_10_diff1": -0.004348372673127467, + "nauc_ndcg_at_10_max": -0.017731461304350618, + "nauc_ndcg_at_10_std": 0.07431280850033226, + "nauc_ndcg_at_1_diff1": 0.047784112391869665, + "nauc_ndcg_at_1_max": -0.03347905728864299, + "nauc_ndcg_at_1_std": 0.01228651610574734, + "nauc_ndcg_at_20_diff1": -0.00487953343959437, + "nauc_ndcg_at_20_max": -0.015436084678449816, + "nauc_ndcg_at_20_std": 0.09394660854179639, + "nauc_ndcg_at_3_diff1": 0.011622934884397947, + "nauc_ndcg_at_3_max": -0.009628060790555558, + "nauc_ndcg_at_3_std": 0.0391288401056918, + "nauc_ndcg_at_5_diff1": 0.00293057597542126, + "nauc_ndcg_at_5_max": -0.015719011890967378, + "nauc_ndcg_at_5_std": 0.0513907166560198, + "nauc_precision_at_1000_diff1": -0.22723798315231597, + "nauc_precision_at_1000_max": -0.29816935693601265, + "nauc_precision_at_1000_std": 0.24204511589844727, + "nauc_precision_at_100_diff1": -0.11403104347325514, + "nauc_precision_at_100_max": -0.11009166354918486, + "nauc_precision_at_100_std": 0.26142920442673834, + "nauc_precision_at_10_diff1": -0.03782456031654786, + "nauc_precision_at_10_max": -0.017592023696242475, + "nauc_precision_at_10_std": 0.12948064557341302, + "nauc_precision_at_1_diff1": 0.047784112391869665, + "nauc_precision_at_1_max": -0.03347905728864299, + "nauc_precision_at_1_std": 0.01228651610574734, + "nauc_precision_at_20_diff1": -0.0418253622324627, + "nauc_precision_at_20_max": -0.012487475828037614, + "nauc_precision_at_20_std": 0.18978692768660552, + "nauc_precision_at_3_diff1": -0.006376391446560311, + "nauc_precision_at_3_max": -0.0011038796413114758, + "nauc_precision_at_3_std": 0.05237802696541294, + "nauc_precision_at_5_diff1": -0.02071417312907715, + "nauc_precision_at_5_max": -0.013199644435332914, + "nauc_precision_at_5_std": 0.07502836909749075, + "nauc_recall_at_1000_diff1": -0.22723798315231525, + "nauc_recall_at_1000_max": -0.2981693569360115, + "nauc_recall_at_1000_std": 0.24204511589844807, + "nauc_recall_at_100_diff1": -0.11403104347325556, + "nauc_recall_at_100_max": -0.11009166354918543, + "nauc_recall_at_100_std": 0.2614292044267381, + "nauc_recall_at_10_diff1": -0.03782456031654778, + "nauc_recall_at_10_max": -0.017592023696242753, + "nauc_recall_at_10_std": 0.12948064557341304, + "nauc_recall_at_1_diff1": 0.047784112391869665, + "nauc_recall_at_1_max": -0.03347905728864299, + "nauc_recall_at_1_std": 0.01228651610574734, + "nauc_recall_at_20_diff1": -0.04182536223246254, + "nauc_recall_at_20_max": -0.0124874758280377, + "nauc_recall_at_20_std": 0.1897869276866057, + "nauc_recall_at_3_diff1": -0.006376391446560309, + "nauc_recall_at_3_max": -0.0011038796413115808, + "nauc_recall_at_3_std": 0.052378026965413035, + "nauc_recall_at_5_diff1": -0.02071417312907718, + "nauc_recall_at_5_max": -0.013199644435332916, + "nauc_recall_at_5_std": 0.07502836909749083, + "ndcg_at_1": 0.10543, + "ndcg_at_10": 0.24248, + "ndcg_at_100": 0.30248, + "ndcg_at_1000": 0.32727, + "ndcg_at_20": 0.26637, + "ndcg_at_3": 0.18256, + "ndcg_at_5": 0.21211, + "precision_at_1": 0.10543, + "precision_at_10": 0.04034, + "precision_at_100": 0.00693, + "precision_at_1000": 0.0009, + "precision_at_20": 0.02487, + "precision_at_3": 0.0793, + "precision_at_5": 0.06189, + "recall_at_1": 0.10543, + "recall_at_10": 0.40337, + "recall_at_100": 0.69316, + "recall_at_1000": 0.89605, + "recall_at_20": 0.4975, + "recall_at_3": 0.23791, + "recall_at_5": 0.30943 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL2Pure.json b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL2Pure.json new file mode 100644 index 000000000..b1aceeb22 --- /dev/null +++ b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL2Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 19.12759280204773, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02352, + "map_at_1": 0.00797, + "map_at_10": 0.01689, + "map_at_100": 0.02103, + "map_at_1000": 0.02231, + "map_at_20": 0.0186, + "map_at_3": 0.01266, + "map_at_5": 0.01472, + "mrr_at_1": 0.007967389290346488, + "mrr_at_10": 0.016888938887271315, + "mrr_at_100": 0.021034783941191293, + "mrr_at_1000": 0.022312128279968393, + "mrr_at_20": 0.018598184087676044, + "mrr_at_3": 0.01266135507380644, + "mrr_at_5": 0.014718053239454026, + "nauc_map_at_1000_diff1": -0.030831489941766068, + "nauc_map_at_1000_max": 0.041312227667893234, + "nauc_map_at_1000_std": 0.23930154850699303, + "nauc_map_at_100_diff1": -0.028664734733955515, + "nauc_map_at_100_max": 0.042414375059808516, + "nauc_map_at_100_std": 0.24025498631109132, + "nauc_map_at_10_diff1": -0.03570630960426734, + "nauc_map_at_10_max": 0.0434314253624944, + "nauc_map_at_10_std": 0.24686315769756217, + "nauc_map_at_1_diff1": -0.06928049592958904, + "nauc_map_at_1_max": -0.03758067155990016, + "nauc_map_at_1_std": 0.2529528962318883, + "nauc_map_at_20_diff1": -0.03183574109663094, + "nauc_map_at_20_max": 0.0418379146040191, + "nauc_map_at_20_std": 0.24399641662168867, + "nauc_map_at_3_diff1": -0.02666452894601386, + "nauc_map_at_3_max": 0.034392447716492955, + "nauc_map_at_3_std": 0.2741727032867167, + "nauc_map_at_5_diff1": -0.03244859646815297, + "nauc_map_at_5_max": 0.03595063624002333, + "nauc_map_at_5_std": 0.2594840959374127, + "nauc_mrr_at_1000_diff1": -0.030831489941766068, + "nauc_mrr_at_1000_max": 0.041312227667893234, + "nauc_mrr_at_1000_std": 0.23930154850699303, + "nauc_mrr_at_100_diff1": -0.028664734733955515, + "nauc_mrr_at_100_max": 0.042414375059808516, + "nauc_mrr_at_100_std": 0.24025498631109132, + "nauc_mrr_at_10_diff1": -0.03570630960426734, + "nauc_mrr_at_10_max": 0.0434314253624944, + "nauc_mrr_at_10_std": 0.24686315769756217, + "nauc_mrr_at_1_diff1": -0.06928049592958904, + "nauc_mrr_at_1_max": -0.03758067155990016, + "nauc_mrr_at_1_std": 0.2529528962318883, + "nauc_mrr_at_20_diff1": -0.03183574109663094, + "nauc_mrr_at_20_max": 0.0418379146040191, + "nauc_mrr_at_20_std": 0.24399641662168867, + "nauc_mrr_at_3_diff1": -0.02666452894601386, + "nauc_mrr_at_3_max": 0.034392447716492955, + "nauc_mrr_at_3_std": 0.2741727032867167, + "nauc_mrr_at_5_diff1": -0.03244859646815297, + "nauc_mrr_at_5_max": 0.03595063624002333, + "nauc_mrr_at_5_std": 0.2594840959374127, + "nauc_ndcg_at_1000_diff1": -0.05043006251424324, + "nauc_ndcg_at_1000_max": 0.028905747676432392, + "nauc_ndcg_at_1000_std": 0.21841451399111153, + "nauc_ndcg_at_100_diff1": -0.015833336875018606, + "nauc_ndcg_at_100_max": 0.05013502061370964, + "nauc_ndcg_at_100_std": 0.22868319375230034, + "nauc_ndcg_at_10_diff1": -0.03296167632397119, + "nauc_ndcg_at_10_max": 0.060359439113299496, + "nauc_ndcg_at_10_std": 0.23287057096862882, + "nauc_ndcg_at_1_diff1": -0.06928049592958904, + "nauc_ndcg_at_1_max": -0.03758067155990016, + "nauc_ndcg_at_1_std": 0.2529528962318883, + "nauc_ndcg_at_20_diff1": -0.025663232367533897, + "nauc_ndcg_at_20_max": 0.05201677441805444, + "nauc_ndcg_at_20_std": 0.2291895183530877, + "nauc_ndcg_at_3_diff1": -0.015822098631959887, + "nauc_ndcg_at_3_max": 0.05232914166746337, + "nauc_ndcg_at_3_std": 0.2805800572127523, + "nauc_ndcg_at_5_diff1": -0.025896002674802614, + "nauc_ndcg_at_5_max": 0.05135152984758543, + "nauc_ndcg_at_5_std": 0.25700824252671023, + "nauc_precision_at_1000_diff1": -0.08707902197969807, + "nauc_precision_at_1000_max": 0.0021777307983812627, + "nauc_precision_at_1000_std": 0.2037674853613723, + "nauc_precision_at_100_diff1": -0.006909559471859661, + "nauc_precision_at_100_max": 0.051478218824302674, + "nauc_precision_at_100_std": 0.22544066629862358, + "nauc_precision_at_10_diff1": -0.030966512036138823, + "nauc_precision_at_10_max": 0.07995628654584412, + "nauc_precision_at_10_std": 0.21212377407099275, + "nauc_precision_at_1_diff1": -0.06928049592958904, + "nauc_precision_at_1_max": -0.03758067155990016, + "nauc_precision_at_1_std": 0.2529528962318883, + "nauc_precision_at_20_diff1": -0.020314733576082274, + "nauc_precision_at_20_max": 0.058016516135737516, + "nauc_precision_at_20_std": 0.2134300045417171, + "nauc_precision_at_3_diff1": 0.005477201964025044, + "nauc_precision_at_3_max": 0.0875040239107717, + "nauc_precision_at_3_std": 0.29333016700946346, + "nauc_precision_at_5_diff1": -0.01606037350049715, + "nauc_precision_at_5_max": 0.07517734632340844, + "nauc_precision_at_5_std": 0.25178075671852224, + "nauc_recall_at_1000_diff1": -0.08707902197969777, + "nauc_recall_at_1000_max": 0.0021777307983818447, + "nauc_recall_at_1000_std": 0.20376748536137282, + "nauc_recall_at_100_diff1": -0.006909559471859689, + "nauc_recall_at_100_max": 0.05147821882430269, + "nauc_recall_at_100_std": 0.22544066629862336, + "nauc_recall_at_10_diff1": -0.030966512036139114, + "nauc_recall_at_10_max": 0.07995628654584398, + "nauc_recall_at_10_std": 0.2121237740709927, + "nauc_recall_at_1_diff1": -0.06928049592958904, + "nauc_recall_at_1_max": -0.03758067155990016, + "nauc_recall_at_1_std": 0.2529528962318883, + "nauc_recall_at_20_diff1": -0.020314733576082347, + "nauc_recall_at_20_max": 0.058016516135737425, + "nauc_recall_at_20_std": 0.2134300045417169, + "nauc_recall_at_3_diff1": 0.005477201964025133, + "nauc_recall_at_3_max": 0.08750402391077176, + "nauc_recall_at_3_std": 0.29333016700946346, + "nauc_recall_at_5_diff1": -0.01606037350049733, + "nauc_recall_at_5_max": 0.07517734632340836, + "nauc_recall_at_5_std": 0.2517807567185221, + "ndcg_at_1": 0.00797, + "ndcg_at_10": 0.02352, + "ndcg_at_100": 0.04969, + "ndcg_at_1000": 0.09543, + "ndcg_at_20": 0.0299, + "ndcg_at_3": 0.01435, + "ndcg_at_5": 0.01811, + "precision_at_1": 0.00797, + "precision_at_10": 0.00456, + "precision_at_100": 0.00182, + "precision_at_1000": 0.00057, + "precision_at_20": 0.00356, + "precision_at_3": 0.00642, + "precision_at_5": 0.00571, + "recall_at_1": 0.00797, + "recall_at_10": 0.04558, + "recall_at_100": 0.18232, + "recall_at_1000": 0.56883, + "recall_at_20": 0.07115, + "recall_at_3": 0.01927, + "recall_at_5": 0.02853 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL3Fact.json b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL3Fact.json new file mode 100644 index 000000000..d63c3d687 --- /dev/null +++ b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL3Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 56.531965017318726, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.20644, + "map_at_1": 0.05829, + "map_at_10": 0.15187, + "map_at_100": 0.1634, + "map_at_1000": 0.16425, + "map_at_20": 0.15891, + "map_at_3": 0.12065, + "map_at_5": 0.13892, + "mrr_at_1": 0.058291911432444644, + "mrr_at_10": 0.15186864774528594, + "mrr_at_100": 0.1634013750043632, + "mrr_at_1000": 0.16424571885127215, + "mrr_at_20": 0.1589088461198841, + "mrr_at_3": 0.12065070040668739, + "mrr_at_5": 0.13891775869859926, + "nauc_map_at_1000_diff1": -0.042725252436270504, + "nauc_map_at_1000_max": 0.019654649217147935, + "nauc_map_at_1000_std": 0.13372234451112483, + "nauc_map_at_100_diff1": -0.042680642432071876, + "nauc_map_at_100_max": 0.020100225106689056, + "nauc_map_at_100_std": 0.13448404911024062, + "nauc_map_at_10_diff1": -0.03932146299718776, + "nauc_map_at_10_max": 0.02269232615902216, + "nauc_map_at_10_std": 0.12362234201927344, + "nauc_map_at_1_diff1": -0.07970645568305326, + "nauc_map_at_1_max": -0.06284013654652752, + "nauc_map_at_1_std": 0.03540638795595751, + "nauc_map_at_20_diff1": -0.04112514104213493, + "nauc_map_at_20_max": 0.021233454971583153, + "nauc_map_at_20_std": 0.13206278274698197, + "nauc_map_at_3_diff1": -0.03942193810481521, + "nauc_map_at_3_max": 0.004889859207095552, + "nauc_map_at_3_std": 0.07655017477122203, + "nauc_map_at_5_diff1": -0.040901086010797685, + "nauc_map_at_5_max": 0.018036442187975312, + "nauc_map_at_5_std": 0.10369506572594354, + "nauc_mrr_at_1000_diff1": -0.042725252436270504, + "nauc_mrr_at_1000_max": 0.019654649217147935, + "nauc_mrr_at_1000_std": 0.13372234451112483, + "nauc_mrr_at_100_diff1": -0.042680642432071876, + "nauc_mrr_at_100_max": 0.020100225106689056, + "nauc_mrr_at_100_std": 0.13448404911024062, + "nauc_mrr_at_10_diff1": -0.03932146299718776, + "nauc_mrr_at_10_max": 0.02269232615902216, + "nauc_mrr_at_10_std": 0.12362234201927344, + "nauc_mrr_at_1_diff1": -0.07970645568305326, + "nauc_mrr_at_1_max": -0.06284013654652752, + "nauc_mrr_at_1_std": 0.03540638795595751, + "nauc_mrr_at_20_diff1": -0.04112514104213493, + "nauc_mrr_at_20_max": 0.021233454971583153, + "nauc_mrr_at_20_std": 0.13206278274698197, + "nauc_mrr_at_3_diff1": -0.03942193810481521, + "nauc_mrr_at_3_max": 0.004889859207095552, + "nauc_mrr_at_3_std": 0.07655017477122203, + "nauc_mrr_at_5_diff1": -0.040901086010797685, + "nauc_mrr_at_5_max": 0.018036442187975312, + "nauc_mrr_at_5_std": 0.10369506572594354, + "nauc_ndcg_at_1000_diff1": -0.04879147780119499, + "nauc_ndcg_at_1000_max": 0.01950248458090517, + "nauc_ndcg_at_1000_std": 0.18519507862985946, + "nauc_ndcg_at_100_diff1": -0.048614663526684955, + "nauc_ndcg_at_100_max": 0.029718111141624155, + "nauc_ndcg_at_100_std": 0.20240625728002096, + "nauc_ndcg_at_10_diff1": -0.03488277514522448, + "nauc_ndcg_at_10_max": 0.042669221461817244, + "nauc_ndcg_at_10_std": 0.16508879212099742, + "nauc_ndcg_at_1_diff1": -0.07970645568305326, + "nauc_ndcg_at_1_max": -0.06284013654652752, + "nauc_ndcg_at_1_std": 0.03540638795595751, + "nauc_ndcg_at_20_diff1": -0.040388863286446766, + "nauc_ndcg_at_20_max": 0.03808253996915903, + "nauc_ndcg_at_20_std": 0.1905534340710386, + "nauc_ndcg_at_3_diff1": -0.034840798771029476, + "nauc_ndcg_at_3_max": 0.01516782798791774, + "nauc_ndcg_at_3_std": 0.08482701119567602, + "nauc_ndcg_at_5_diff1": -0.037864066339165274, + "nauc_ndcg_at_5_max": 0.03411872100451472, + "nauc_ndcg_at_5_std": 0.12543423524020839, + "nauc_precision_at_1000_diff1": -0.10847465701678263, + "nauc_precision_at_1000_max": -0.09590275830048813, + "nauc_precision_at_1000_std": 0.38501362249402044, + "nauc_precision_at_100_diff1": -0.07586430047395595, + "nauc_precision_at_100_max": 0.03343941887579493, + "nauc_precision_at_100_std": 0.3843616722017996, + "nauc_precision_at_10_diff1": -0.027851050504051365, + "nauc_precision_at_10_max": 0.07778691342695437, + "nauc_precision_at_10_std": 0.24468112468531433, + "nauc_precision_at_1_diff1": -0.07970645568305326, + "nauc_precision_at_1_max": -0.06284013654652752, + "nauc_precision_at_1_std": 0.03540638795595751, + "nauc_precision_at_20_diff1": -0.042328005656775955, + "nauc_precision_at_20_max": 0.0659048690005881, + "nauc_precision_at_20_std": 0.31316583755308175, + "nauc_precision_at_3_diff1": -0.026811434003769483, + "nauc_precision_at_3_max": 0.03396731269723995, + "nauc_precision_at_3_std": 0.10043076834848129, + "nauc_precision_at_5_diff1": -0.033554220169585466, + "nauc_precision_at_5_max": 0.0625850578329826, + "nauc_precision_at_5_std": 0.1657860498381563, + "nauc_recall_at_1000_diff1": -0.10847465701678242, + "nauc_recall_at_1000_max": -0.09590275830048922, + "nauc_recall_at_1000_std": 0.38501362249402116, + "nauc_recall_at_100_diff1": -0.07586430047395526, + "nauc_recall_at_100_max": 0.03343941887579526, + "nauc_recall_at_100_std": 0.38436167220179923, + "nauc_recall_at_10_diff1": -0.027851050504051508, + "nauc_recall_at_10_max": 0.07778691342695418, + "nauc_recall_at_10_std": 0.24468112468531442, + "nauc_recall_at_1_diff1": -0.07970645568305326, + "nauc_recall_at_1_max": -0.06284013654652752, + "nauc_recall_at_1_std": 0.03540638795595751, + "nauc_recall_at_20_diff1": -0.042328005656776524, + "nauc_recall_at_20_max": 0.06590486900058774, + "nauc_recall_at_20_std": 0.3131658375530816, + "nauc_recall_at_3_diff1": -0.026811434003769428, + "nauc_recall_at_3_max": 0.03396731269723987, + "nauc_recall_at_3_std": 0.10043076834848116, + "nauc_recall_at_5_diff1": -0.033554220169585564, + "nauc_recall_at_5_max": 0.06258505783298245, + "nauc_recall_at_5_std": 0.16578604983815623, + "ndcg_at_1": 0.05829, + "ndcg_at_10": 0.20644, + "ndcg_at_100": 0.26473, + "ndcg_at_1000": 0.291, + "ndcg_at_20": 0.2319, + "ndcg_at_3": 0.14193, + "ndcg_at_5": 0.17491, + "precision_at_1": 0.05829, + "precision_at_10": 0.03818, + "precision_at_100": 0.0066, + "precision_at_1000": 0.00088, + "precision_at_20": 0.02411, + "precision_at_3": 0.06793, + "precision_at_5": 0.0568, + "recall_at_1": 0.05829, + "recall_at_10": 0.38183, + "recall_at_100": 0.65996, + "recall_at_1000": 0.87506, + "recall_at_20": 0.48215, + "recall_at_3": 0.2038, + "recall_at_5": 0.284 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL3Pure.json b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL3Pure.json new file mode 100644 index 000000000..12f24917b --- /dev/null +++ b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/TempReasonL3Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 17.984113454818726, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.06674, + "map_at_1": 0.00113, + "map_at_10": 0.04043, + "map_at_100": 0.04919, + "map_at_1000": 0.05046, + "map_at_20": 0.04518, + "map_at_3": 0.02323, + "map_at_5": 0.03277, + "mrr_at_1": 0.0011296882060551287, + "mrr_at_10": 0.040434409944125234, + "mrr_at_100": 0.04918678504422484, + "mrr_at_1000": 0.05045601020915698, + "mrr_at_20": 0.04517689895053848, + "mrr_at_3": 0.023233920771200445, + "mrr_at_5": 0.032768489230305765, + "nauc_map_at_1000_diff1": 0.01157693895371157, + "nauc_map_at_1000_max": 0.3574086348360916, + "nauc_map_at_1000_std": 0.4872049822008692, + "nauc_map_at_100_diff1": 0.012029125662044648, + "nauc_map_at_100_max": 0.3598446150693288, + "nauc_map_at_100_std": 0.48876573100936055, + "nauc_map_at_10_diff1": 0.020321246176315894, + "nauc_map_at_10_max": 0.3569287490476008, + "nauc_map_at_10_std": 0.4664646770060542, + "nauc_map_at_1_diff1": -0.5235972965540956, + "nauc_map_at_1_max": -0.15468692645598692, + "nauc_map_at_1_std": -0.02489541279393542, + "nauc_map_at_20_diff1": 0.01660870152878239, + "nauc_map_at_20_max": 0.363555575711099, + "nauc_map_at_20_std": 0.48446954400563724, + "nauc_map_at_3_diff1": 0.01237724261573366, + "nauc_map_at_3_max": 0.31811076912904085, + "nauc_map_at_3_std": 0.4274992175375288, + "nauc_map_at_5_diff1": 0.02082797026193164, + "nauc_map_at_5_max": 0.33381487421227446, + "nauc_map_at_5_std": 0.438421660146671, + "nauc_mrr_at_1000_diff1": 0.01157693895371157, + "nauc_mrr_at_1000_max": 0.3574086348360916, + "nauc_mrr_at_1000_std": 0.4872049822008692, + "nauc_mrr_at_100_diff1": 0.012029125662044648, + "nauc_mrr_at_100_max": 0.3598446150693288, + "nauc_mrr_at_100_std": 0.48876573100936055, + "nauc_mrr_at_10_diff1": 0.020321246176315894, + "nauc_mrr_at_10_max": 0.3569287490476008, + "nauc_mrr_at_10_std": 0.4664646770060542, + "nauc_mrr_at_1_diff1": -0.5235972965540956, + "nauc_mrr_at_1_max": -0.15468692645598692, + "nauc_mrr_at_1_std": -0.02489541279393542, + "nauc_mrr_at_20_diff1": 0.01660870152878239, + "nauc_mrr_at_20_max": 0.363555575711099, + "nauc_mrr_at_20_std": 0.48446954400563724, + "nauc_mrr_at_3_diff1": 0.01237724261573366, + "nauc_mrr_at_3_max": 0.31811076912904085, + "nauc_mrr_at_3_std": 0.4274992175375288, + "nauc_mrr_at_5_diff1": 0.02082797026193164, + "nauc_mrr_at_5_max": 0.33381487421227446, + "nauc_mrr_at_5_std": 0.438421660146671, + "nauc_ndcg_at_1000_diff1": -0.013494996921678453, + "nauc_ndcg_at_1000_max": 0.32950798889981514, + "nauc_ndcg_at_1000_std": 0.5079702885962211, + "nauc_ndcg_at_100_diff1": -0.00454640385345279, + "nauc_ndcg_at_100_max": 0.3643718203086939, + "nauc_ndcg_at_100_std": 0.5285294822891394, + "nauc_ndcg_at_10_diff1": 0.02146306267300232, + "nauc_ndcg_at_10_max": 0.37575556997117404, + "nauc_ndcg_at_10_std": 0.48692539746058905, + "nauc_ndcg_at_1_diff1": -0.5235972965540956, + "nauc_ndcg_at_1_max": -0.15468692645598692, + "nauc_ndcg_at_1_std": -0.02489541279393542, + "nauc_ndcg_at_20_diff1": 0.013400463049347831, + "nauc_ndcg_at_20_max": 0.38772984004100336, + "nauc_ndcg_at_20_std": 0.521531556832064, + "nauc_ndcg_at_3_diff1": 0.017752634850667193, + "nauc_ndcg_at_3_max": 0.32317059723347463, + "nauc_ndcg_at_3_std": 0.42950714235359444, + "nauc_ndcg_at_5_diff1": 0.02600682959865051, + "nauc_ndcg_at_5_max": 0.34093421922783795, + "nauc_ndcg_at_5_std": 0.44234757762846444, + "nauc_precision_at_1000_diff1": -0.07653105724376366, + "nauc_precision_at_1000_max": 0.21623593264299265, + "nauc_precision_at_1000_std": 0.5023872622928964, + "nauc_precision_at_100_diff1": -0.027741964341465017, + "nauc_precision_at_100_max": 0.3559569372003831, + "nauc_precision_at_100_std": 0.5638481984801192, + "nauc_precision_at_10_diff1": 0.020828358102685914, + "nauc_precision_at_10_max": 0.39648399336183276, + "nauc_precision_at_10_std": 0.5104659750621583, + "nauc_precision_at_1_diff1": -0.5235972965540956, + "nauc_precision_at_1_max": -0.15468692645598692, + "nauc_precision_at_1_std": -0.02489541279393542, + "nauc_precision_at_20_diff1": 0.007910726835360137, + "nauc_precision_at_20_max": 0.4119826663289845, + "nauc_precision_at_20_std": 0.561054690315529, + "nauc_precision_at_3_diff1": 0.02442165970833555, + "nauc_precision_at_3_max": 0.3295158953805034, + "nauc_precision_at_3_std": 0.4314592775508264, + "nauc_precision_at_5_diff1": 0.03137180737645975, + "nauc_precision_at_5_max": 0.3488717763840216, + "nauc_precision_at_5_std": 0.44654748915006154, + "nauc_recall_at_1000_diff1": -0.07653105724376427, + "nauc_recall_at_1000_max": 0.21623593264299298, + "nauc_recall_at_1000_std": 0.5023872622928968, + "nauc_recall_at_100_diff1": -0.02774196434146519, + "nauc_recall_at_100_max": 0.35595693720038285, + "nauc_recall_at_100_std": 0.5638481984801191, + "nauc_recall_at_10_diff1": 0.020828358102685716, + "nauc_recall_at_10_max": 0.3964839933618329, + "nauc_recall_at_10_std": 0.5104659750621584, + "nauc_recall_at_1_diff1": -0.5235972965540956, + "nauc_recall_at_1_max": -0.15468692645598692, + "nauc_recall_at_1_std": -0.02489541279393542, + "nauc_recall_at_20_diff1": 0.007910726835360218, + "nauc_recall_at_20_max": 0.41198266632898434, + "nauc_recall_at_20_std": 0.5610546903155288, + "nauc_recall_at_3_diff1": 0.02442165970833546, + "nauc_recall_at_3_max": 0.3295158953805035, + "nauc_recall_at_3_std": 0.43145927755082675, + "nauc_recall_at_5_diff1": 0.03137180737645957, + "nauc_recall_at_5_max": 0.34887177638402134, + "nauc_recall_at_5_std": 0.4465474891500615, + "ndcg_at_1": 0.00113, + "ndcg_at_10": 0.06674, + "ndcg_at_100": 0.11421, + "ndcg_at_1000": 0.15526, + "ndcg_at_20": 0.08412, + "ndcg_at_3": 0.03076, + "ndcg_at_5": 0.04801, + "precision_at_1": 0.00113, + "precision_at_10": 0.0153, + "precision_at_100": 0.00387, + "precision_at_1000": 0.00073, + "precision_at_20": 0.01109, + "precision_at_3": 0.01755, + "precision_at_5": 0.01893, + "recall_at_1": 0.00113, + "recall_at_10": 0.15296, + "recall_at_100": 0.38658, + "recall_at_1000": 0.72549, + "recall_at_20": 0.22187, + "recall_at_3": 0.05264, + "recall_at_5": 0.09467 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/WinoGrande.json b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/WinoGrande.json new file mode 100644 index 000000000..3928c2e10 --- /dev/null +++ b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/WinoGrande.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 4.3535566329956055, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.19183, + "map_at_1": 0.03157, + "map_at_10": 0.12315, + "map_at_100": 0.14126, + "map_at_1000": 0.14197, + "map_at_20": 0.13357, + "map_at_3": 0.07643, + "map_at_5": 0.1005, + "mrr_at_1": 0.03235990528808208, + "mrr_at_10": 0.12379542977411967, + "mrr_at_100": 0.14177286758344088, + "mrr_at_1000": 0.14248956105590216, + "mrr_at_20": 0.13408745535194258, + "mrr_at_3": 0.07682188897658504, + "mrr_at_5": 0.10097342804525122, + "nauc_map_at_1000_diff1": -0.08197200374129568, + "nauc_map_at_1000_max": 0.11509728324002434, + "nauc_map_at_1000_std": 0.17606765886318462, + "nauc_map_at_100_diff1": -0.08182782612902792, + "nauc_map_at_100_max": 0.11400519428225839, + "nauc_map_at_100_std": 0.17560172500849888, + "nauc_map_at_10_diff1": -0.08502078670139157, + "nauc_map_at_10_max": 0.10611164742663869, + "nauc_map_at_10_std": 0.16893139357636724, + "nauc_map_at_1_diff1": -0.10507193255438411, + "nauc_map_at_1_max": 0.4536348872124285, + "nauc_map_at_1_std": 0.3411713905243081, + "nauc_map_at_20_diff1": -0.08188405648515008, + "nauc_map_at_20_max": 0.10932527604210626, + "nauc_map_at_20_std": 0.173584351669537, + "nauc_map_at_3_diff1": -0.10953615443184042, + "nauc_map_at_3_max": 0.16826403764144984, + "nauc_map_at_3_std": 0.19419677960118312, + "nauc_map_at_5_diff1": -0.0870978571165143, + "nauc_map_at_5_max": 0.12536154144618736, + "nauc_map_at_5_std": 0.17342421951212206, + "nauc_mrr_at_1000_diff1": -0.0838846859496081, + "nauc_mrr_at_1000_max": 0.11558810037350156, + "nauc_mrr_at_1000_std": 0.17675266562872852, + "nauc_mrr_at_100_diff1": -0.083732551610732, + "nauc_mrr_at_100_max": 0.11449959475321762, + "nauc_mrr_at_100_std": 0.17628603266374657, + "nauc_mrr_at_10_diff1": -0.0872847388403873, + "nauc_mrr_at_10_max": 0.10576741275108936, + "nauc_mrr_at_10_std": 0.17031384823273396, + "nauc_mrr_at_1_diff1": -0.11652912045227262, + "nauc_mrr_at_1_max": 0.4449738329317315, + "nauc_mrr_at_1_std": 0.3490128515618255, + "nauc_mrr_at_20_diff1": -0.08389016701938092, + "nauc_mrr_at_20_max": 0.10968343975863482, + "nauc_mrr_at_20_std": 0.17436302005757934, + "nauc_mrr_at_3_diff1": -0.11170301701681205, + "nauc_mrr_at_3_max": 0.16843781992366758, + "nauc_mrr_at_3_std": 0.19497145943257654, + "nauc_mrr_at_5_diff1": -0.08873659682675812, + "nauc_mrr_at_5_max": 0.12717042531143818, + "nauc_mrr_at_5_std": 0.17630496627046463, + "nauc_ndcg_at_1000_diff1": -0.06983210256481306, + "nauc_ndcg_at_1000_max": 0.0834965057861013, + "nauc_ndcg_at_1000_std": 0.16582709189838035, + "nauc_ndcg_at_100_diff1": -0.06494970809400966, + "nauc_ndcg_at_100_max": 0.06692952585796237, + "nauc_ndcg_at_100_std": 0.15666908761258147, + "nauc_ndcg_at_10_diff1": -0.0746075796454769, + "nauc_ndcg_at_10_max": 0.04605562102053437, + "nauc_ndcg_at_10_std": 0.1406707696334551, + "nauc_ndcg_at_1_diff1": -0.10507193255438411, + "nauc_ndcg_at_1_max": 0.4536348872124285, + "nauc_ndcg_at_1_std": 0.3411713905243081, + "nauc_ndcg_at_20_diff1": -0.06542856827811648, + "nauc_ndcg_at_20_max": 0.05205260005346201, + "nauc_ndcg_at_20_std": 0.15078629034069638, + "nauc_ndcg_at_3_diff1": -0.10526049094104875, + "nauc_ndcg_at_3_max": 0.13160936387695435, + "nauc_ndcg_at_3_std": 0.17126535812406443, + "nauc_ndcg_at_5_diff1": -0.07418062392008268, + "nauc_ndcg_at_5_max": 0.0798357023596558, + "nauc_ndcg_at_5_std": 0.14606263558057372, + "nauc_precision_at_1000_diff1": 0.09165795842286677, + "nauc_precision_at_1000_max": -0.07241693031330573, + "nauc_precision_at_1000_std": 0.4582409674600277, + "nauc_precision_at_100_diff1": -0.006031753129515924, + "nauc_precision_at_100_max": -0.06986666882283397, + "nauc_precision_at_100_std": 0.10757351340596569, + "nauc_precision_at_10_diff1": -0.06107217891737454, + "nauc_precision_at_10_max": -0.03842728858653006, + "nauc_precision_at_10_std": 0.10290815234539871, + "nauc_precision_at_1_diff1": -0.10507193255438411, + "nauc_precision_at_1_max": 0.4536348872124285, + "nauc_precision_at_1_std": 0.3411713905243081, + "nauc_precision_at_20_diff1": -0.03806080882004369, + "nauc_precision_at_20_max": -0.03373335189298987, + "nauc_precision_at_20_std": 0.12075172503168374, + "nauc_precision_at_3_diff1": -0.09739178105828683, + "nauc_precision_at_3_max": 0.07207292335190058, + "nauc_precision_at_3_std": 0.13324664502201558, + "nauc_precision_at_5_diff1": -0.05396521253039873, + "nauc_precision_at_5_max": 0.015557341802773324, + "nauc_precision_at_5_std": 0.10673215443082074, + "nauc_recall_at_1000_diff1": 0.0916579584228631, + "nauc_recall_at_1000_max": -0.07241693031330818, + "nauc_recall_at_1000_std": 0.4582409674600307, + "nauc_recall_at_100_diff1": -0.006031753129515074, + "nauc_recall_at_100_max": -0.06986666882283242, + "nauc_recall_at_100_std": 0.10757351340596648, + "nauc_recall_at_10_diff1": -0.06107217891737481, + "nauc_recall_at_10_max": -0.038427288586530106, + "nauc_recall_at_10_std": 0.10290815234539866, + "nauc_recall_at_1_diff1": -0.10507193255438411, + "nauc_recall_at_1_max": 0.4536348872124285, + "nauc_recall_at_1_std": 0.3411713905243081, + "nauc_recall_at_20_diff1": -0.0380608088200444, + "nauc_recall_at_20_max": -0.033733351892990086, + "nauc_recall_at_20_std": 0.12075172503168344, + "nauc_recall_at_3_diff1": -0.09739178105828673, + "nauc_recall_at_3_max": 0.07207292335190064, + "nauc_recall_at_3_std": 0.13324664502201577, + "nauc_recall_at_5_diff1": -0.05396521253039912, + "nauc_recall_at_5_max": 0.015557341802773086, + "nauc_recall_at_5_std": 0.1067321544308207, + "ndcg_at_1": 0.03157, + "ndcg_at_10": 0.19183, + "ndcg_at_100": 0.28385, + "ndcg_at_1000": 0.30092, + "ndcg_at_20": 0.22951, + "ndcg_at_3": 0.09331, + "ndcg_at_5": 0.13695, + "precision_at_1": 0.03157, + "precision_at_10": 0.04191, + "precision_at_100": 0.00858, + "precision_at_1000": 0.00099, + "precision_at_20": 0.02837, + "precision_at_3": 0.04762, + "precision_at_5": 0.04988, + "recall_at_1": 0.03157, + "recall_at_10": 0.4191, + "recall_at_100": 0.85793, + "recall_at_1000": 0.98816, + "recall_at_20": 0.56748, + "recall_at_3": 0.14286, + "recall_at_5": 0.24941 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/model_metaInstruct.json b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/model_metaInstruct.json new file mode 100644 index 000000000..588e0ca6f --- /dev/null +++ b/results/bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa166f842b0e09/model_metaInstruct.json @@ -0,0 +1 @@ +{"name": "BAAI/bge-large-en-v1.5", "revision": "d4aa6901d3a41ba39fb536a557fa166f842b0e09", "release_date": null, "languages": [], "n_parameters": null, "memory_usage": null, "max_tokens": null, "embed_dim": null, "license": null, "open_source": null, "similarity_fn_name": null, "framework": ["Sentence Transformers"], "loader": null} \ No newline at end of file diff --git a/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/ARCChallengeInstruct.json b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/ARCChallengeInstruct.json new file mode 100644 index 000000000..926609c7a --- /dev/null +++ b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/ARCChallengeInstruct.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 11.226194143295288, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.09028, + "map_at_1": 0.03413, + "map_at_10": 0.06932, + "map_at_100": 0.07715, + "map_at_1000": 0.07836, + "map_at_20": 0.07302, + "map_at_3": 0.05617, + "map_at_5": 0.06406, + "mrr_at_1": 0.034129692832764506, + "mrr_at_10": 0.06932221409610491, + "mrr_at_100": 0.07715312103686371, + "mrr_at_1000": 0.07835848422564771, + "mrr_at_20": 0.07302323495479204, + "mrr_at_3": 0.0561717861205916, + "mrr_at_5": 0.0640642775881684, + "nauc_map_at_1000_diff1": 0.042565464794658475, + "nauc_map_at_1000_max": 0.09940837843597702, + "nauc_map_at_1000_std": -0.012029971804557409, + "nauc_map_at_100_diff1": 0.04192339631193171, + "nauc_map_at_100_max": 0.09971431243886326, + "nauc_map_at_100_std": -0.012419406984865381, + "nauc_map_at_10_diff1": 0.04481623922828964, + "nauc_map_at_10_max": 0.11421190164898988, + "nauc_map_at_10_std": -0.010694540041963553, + "nauc_map_at_1_diff1": 0.023770396082955614, + "nauc_map_at_1_max": 0.09198662145751842, + "nauc_map_at_1_std": -0.017147282182822285, + "nauc_map_at_20_diff1": 0.04597467302226207, + "nauc_map_at_20_max": 0.1047410226116558, + "nauc_map_at_20_std": -0.013305618370929199, + "nauc_map_at_3_diff1": 0.044511903576639894, + "nauc_map_at_3_max": 0.13047713820881002, + "nauc_map_at_3_std": 0.004280145204012681, + "nauc_map_at_5_diff1": 0.042654227887482236, + "nauc_map_at_5_max": 0.11837247357071101, + "nauc_map_at_5_std": -0.010815870909235694, + "nauc_mrr_at_1000_diff1": 0.042565464794658475, + "nauc_mrr_at_1000_max": 0.09940837843597702, + "nauc_mrr_at_1000_std": -0.012029971804557409, + "nauc_mrr_at_100_diff1": 0.04192339631193171, + "nauc_mrr_at_100_max": 0.09971431243886326, + "nauc_mrr_at_100_std": -0.012419406984865381, + "nauc_mrr_at_10_diff1": 0.04481623922828964, + "nauc_mrr_at_10_max": 0.11421190164898988, + "nauc_mrr_at_10_std": -0.010694540041963553, + "nauc_mrr_at_1_diff1": 0.023770396082955614, + "nauc_mrr_at_1_max": 0.09198662145751842, + "nauc_mrr_at_1_std": -0.017147282182822285, + "nauc_mrr_at_20_diff1": 0.04597467302226207, + "nauc_mrr_at_20_max": 0.1047410226116558, + "nauc_mrr_at_20_std": -0.013305618370929199, + "nauc_mrr_at_3_diff1": 0.044511903576639894, + "nauc_mrr_at_3_max": 0.13047713820881002, + "nauc_mrr_at_3_std": 0.004280145204012681, + "nauc_mrr_at_5_diff1": 0.042654227887482236, + "nauc_mrr_at_5_max": 0.11837247357071101, + "nauc_mrr_at_5_std": -0.010815870909235694, + "nauc_ndcg_at_1000_diff1": 0.037399226947955916, + "nauc_ndcg_at_1000_max": 0.0650911915068853, + "nauc_ndcg_at_1000_std": -0.003615285447013631, + "nauc_ndcg_at_100_diff1": 0.02899261952470698, + "nauc_ndcg_at_100_max": 0.06749291200065488, + "nauc_ndcg_at_100_std": -0.014233770924440132, + "nauc_ndcg_at_10_diff1": 0.047769359847463395, + "nauc_ndcg_at_10_max": 0.11414945781832156, + "nauc_ndcg_at_10_std": -0.013153999911736932, + "nauc_ndcg_at_1_diff1": 0.023770396082955614, + "nauc_ndcg_at_1_max": 0.09198662145751842, + "nauc_ndcg_at_1_std": -0.017147282182822285, + "nauc_ndcg_at_20_diff1": 0.050909936751779426, + "nauc_ndcg_at_20_max": 0.08935585455917816, + "nauc_ndcg_at_20_std": -0.019942757498308816, + "nauc_ndcg_at_3_diff1": 0.045161977930373715, + "nauc_ndcg_at_3_max": 0.1391583049581629, + "nauc_ndcg_at_3_std": 0.0074203300625072235, + "nauc_ndcg_at_5_diff1": 0.0419017617563517, + "nauc_ndcg_at_5_max": 0.11968526622604249, + "nauc_ndcg_at_5_std": -0.01643310719347986, + "nauc_precision_at_1000_diff1": 0.026571299235637055, + "nauc_precision_at_1000_max": -0.013064105402917262, + "nauc_precision_at_1000_std": 0.04542836515284075, + "nauc_precision_at_100_diff1": 0.0006279750065658321, + "nauc_precision_at_100_max": 0.013203414550460472, + "nauc_precision_at_100_std": -0.013131439483084264, + "nauc_precision_at_10_diff1": 0.05328823752574305, + "nauc_precision_at_10_max": 0.11369623701994798, + "nauc_precision_at_10_std": -0.016197298818370624, + "nauc_precision_at_1_diff1": 0.023770396082955614, + "nauc_precision_at_1_max": 0.09198662145751842, + "nauc_precision_at_1_std": -0.017147282182822285, + "nauc_precision_at_20_diff1": 0.05919624976305172, + "nauc_precision_at_20_max": 0.06203188737807272, + "nauc_precision_at_20_std": -0.029950049267669556, + "nauc_precision_at_3_diff1": 0.04572715530274857, + "nauc_precision_at_3_max": 0.15630341119030072, + "nauc_precision_at_3_std": 0.013320121799812035, + "nauc_precision_at_5_diff1": 0.03974202275616404, + "nauc_precision_at_5_max": 0.12063654601634473, + "nauc_precision_at_5_std": -0.02781509446426783, + "nauc_recall_at_1000_diff1": 0.02657129923563623, + "nauc_recall_at_1000_max": -0.013064105402917886, + "nauc_recall_at_1000_std": 0.04542836515284017, + "nauc_recall_at_100_diff1": 0.0006279750065656288, + "nauc_recall_at_100_max": 0.013203414550460273, + "nauc_recall_at_100_std": -0.013131439483084758, + "nauc_recall_at_10_diff1": 0.053288237525742944, + "nauc_recall_at_10_max": 0.11369623701994772, + "nauc_recall_at_10_std": -0.016197298818370655, + "nauc_recall_at_1_diff1": 0.023770396082955614, + "nauc_recall_at_1_max": 0.09198662145751842, + "nauc_recall_at_1_std": -0.017147282182822285, + "nauc_recall_at_20_diff1": 0.05919624976305146, + "nauc_recall_at_20_max": 0.06203188737807235, + "nauc_recall_at_20_std": -0.029950049267669858, + "nauc_recall_at_3_diff1": 0.04572715530274846, + "nauc_recall_at_3_max": 0.15630341119030064, + "nauc_recall_at_3_std": 0.013320121799812035, + "nauc_recall_at_5_diff1": 0.039742022756163946, + "nauc_recall_at_5_max": 0.12063654601634474, + "nauc_recall_at_5_std": -0.027815094464267838, + "ndcg_at_1": 0.03413, + "ndcg_at_10": 0.09028, + "ndcg_at_100": 0.13653, + "ndcg_at_1000": 0.17501, + "ndcg_at_20": 0.10384, + "ndcg_at_3": 0.06343, + "ndcg_at_5": 0.07757, + "precision_at_1": 0.03413, + "precision_at_10": 0.01578, + "precision_at_100": 0.00393, + "precision_at_1000": 0.00071, + "precision_at_20": 0.01058, + "precision_at_3": 0.02816, + "precision_at_5": 0.02372, + "recall_at_1": 0.03413, + "recall_at_10": 0.15785, + "recall_at_100": 0.39334, + "recall_at_1000": 0.7116, + "recall_at_20": 0.2116, + "recall_at_3": 0.08447, + "recall_at_5": 0.1186 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/AlphaNLIInstruct.json b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/AlphaNLIInstruct.json new file mode 100644 index 000000000..714dcbf73 --- /dev/null +++ b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/AlphaNLIInstruct.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 178.3533718585968, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.24686, + "map_at_1": 0.15535, + "map_at_10": 0.21421, + "map_at_100": 0.2213, + "map_at_1000": 0.22211, + "map_at_20": 0.21814, + "map_at_3": 0.19691, + "map_at_5": 0.20572, + "mrr_at_1": 0.15535248041775457, + "mrr_at_10": 0.21420800696257625, + "mrr_at_100": 0.2213042233146552, + "mrr_at_1000": 0.22210749499479313, + "mrr_at_20": 0.2181397319725472, + "mrr_at_3": 0.19691035683202793, + "mrr_at_5": 0.20572236727589205, + "nauc_map_at_1000_diff1": 0.3686425373038789, + "nauc_map_at_1000_max": 0.23245547796001995, + "nauc_map_at_1000_std": -0.07909462941104609, + "nauc_map_at_100_diff1": 0.368615660439539, + "nauc_map_at_100_max": 0.2322561251921514, + "nauc_map_at_100_std": -0.079380096315514, + "nauc_map_at_10_diff1": 0.3741349460035734, + "nauc_map_at_10_max": 0.23550017412500104, + "nauc_map_at_10_std": -0.07983081586147664, + "nauc_map_at_1_diff1": 0.4138187145914196, + "nauc_map_at_1_max": 0.25687148376056373, + "nauc_map_at_1_std": -0.07658656963673584, + "nauc_map_at_20_diff1": 0.36989484923678173, + "nauc_map_at_20_max": 0.2329295710333112, + "nauc_map_at_20_std": -0.08014289864203608, + "nauc_map_at_3_diff1": 0.38831554990044426, + "nauc_map_at_3_max": 0.2498184166640843, + "nauc_map_at_3_std": -0.08342444526455162, + "nauc_map_at_5_diff1": 0.38229360201998763, + "nauc_map_at_5_max": 0.24293463069530571, + "nauc_map_at_5_std": -0.07815329870453086, + "nauc_mrr_at_1000_diff1": 0.3686425373038789, + "nauc_mrr_at_1000_max": 0.23245547796001995, + "nauc_mrr_at_1000_std": -0.07909462941104609, + "nauc_mrr_at_100_diff1": 0.368615660439539, + "nauc_mrr_at_100_max": 0.2322561251921514, + "nauc_mrr_at_100_std": -0.079380096315514, + "nauc_mrr_at_10_diff1": 0.3741349460035734, + "nauc_mrr_at_10_max": 0.23550017412500104, + "nauc_mrr_at_10_std": -0.07983081586147664, + "nauc_mrr_at_1_diff1": 0.4138187145914196, + "nauc_mrr_at_1_max": 0.25687148376056373, + "nauc_mrr_at_1_std": -0.07658656963673584, + "nauc_mrr_at_20_diff1": 0.36989484923678173, + "nauc_mrr_at_20_max": 0.2329295710333112, + "nauc_mrr_at_20_std": -0.08014289864203608, + "nauc_mrr_at_3_diff1": 0.38831554990044426, + "nauc_mrr_at_3_max": 0.2498184166640843, + "nauc_mrr_at_3_std": -0.08342444526455162, + "nauc_mrr_at_5_diff1": 0.38229360201998763, + "nauc_mrr_at_5_max": 0.24293463069530571, + "nauc_mrr_at_5_std": -0.07815329870453086, + "nauc_ndcg_at_1000_diff1": 0.32837097610133187, + "nauc_ndcg_at_1000_max": 0.20927653569304108, + "nauc_ndcg_at_1000_std": -0.06778795604558678, + "nauc_ndcg_at_100_diff1": 0.3301040961305206, + "nauc_ndcg_at_100_max": 0.20444291550921387, + "nauc_ndcg_at_100_std": -0.0736666437682108, + "nauc_ndcg_at_10_diff1": 0.35324614045174957, + "nauc_ndcg_at_10_max": 0.21858878902444742, + "nauc_ndcg_at_10_std": -0.07933420458469044, + "nauc_ndcg_at_1_diff1": 0.4138187145914196, + "nauc_ndcg_at_1_max": 0.25687148376056373, + "nauc_ndcg_at_1_std": -0.07658656963673584, + "nauc_ndcg_at_20_diff1": 0.33850026146448786, + "nauc_ndcg_at_20_max": 0.2094688039950592, + "nauc_ndcg_at_20_std": -0.08039082072813827, + "nauc_ndcg_at_3_diff1": 0.3805999967112052, + "nauc_ndcg_at_3_max": 0.2465921105327637, + "nauc_ndcg_at_3_std": -0.08480463236750498, + "nauc_ndcg_at_5_diff1": 0.3702341287289666, + "nauc_ndcg_at_5_max": 0.23505793108628914, + "nauc_ndcg_at_5_std": -0.07531921724636587, + "nauc_precision_at_1000_diff1": 0.12561658373785048, + "nauc_precision_at_1000_max": 0.1190319156717462, + "nauc_precision_at_1000_std": 0.018937237807480353, + "nauc_precision_at_100_diff1": 0.2051691211950828, + "nauc_precision_at_100_max": 0.11355926393492728, + "nauc_precision_at_100_std": -0.047314761169831555, + "nauc_precision_at_10_diff1": 0.2993544790907214, + "nauc_precision_at_10_max": 0.17308956163060865, + "nauc_precision_at_10_std": -0.07815369747956655, + "nauc_precision_at_1_diff1": 0.4138187145914196, + "nauc_precision_at_1_max": 0.25687148376056373, + "nauc_precision_at_1_std": -0.07658656963673584, + "nauc_precision_at_20_diff1": 0.2510972307752734, + "nauc_precision_at_20_max": 0.14311143557843856, + "nauc_precision_at_20_std": -0.08170634160848313, + "nauc_precision_at_3_diff1": 0.3610298202866828, + "nauc_precision_at_3_max": 0.23813847774165384, + "nauc_precision_at_3_std": -0.08813511403711423, + "nauc_precision_at_5_diff1": 0.3398006096625753, + "nauc_precision_at_5_max": 0.21461446962193173, + "nauc_precision_at_5_std": -0.06704164464375566, + "nauc_recall_at_1000_diff1": 0.1256165837378508, + "nauc_recall_at_1000_max": 0.11903191567174613, + "nauc_recall_at_1000_std": 0.018937237807480516, + "nauc_recall_at_100_diff1": 0.20516912119508254, + "nauc_recall_at_100_max": 0.11355926393492712, + "nauc_recall_at_100_std": -0.047314761169831465, + "nauc_recall_at_10_diff1": 0.2993544790907214, + "nauc_recall_at_10_max": 0.1730895616306087, + "nauc_recall_at_10_std": -0.07815369747956669, + "nauc_recall_at_1_diff1": 0.4138187145914196, + "nauc_recall_at_1_max": 0.25687148376056373, + "nauc_recall_at_1_std": -0.07658656963673584, + "nauc_recall_at_20_diff1": 0.2510972307752736, + "nauc_recall_at_20_max": 0.14311143557843845, + "nauc_recall_at_20_std": -0.08170634160848338, + "nauc_recall_at_3_diff1": 0.36102982028668296, + "nauc_recall_at_3_max": 0.23813847774165428, + "nauc_recall_at_3_std": -0.08813511403711413, + "nauc_recall_at_5_diff1": 0.3398006096625752, + "nauc_recall_at_5_max": 0.2146144696219315, + "nauc_recall_at_5_std": -0.06704164464375563, + "ndcg_at_1": 0.15535, + "ndcg_at_10": 0.24686, + "ndcg_at_100": 0.28597, + "ndcg_at_1000": 0.31061, + "ndcg_at_20": 0.26142, + "ndcg_at_3": 0.21023, + "ndcg_at_5": 0.2261, + "precision_at_1": 0.15535, + "precision_at_10": 0.03518, + "precision_at_100": 0.00546, + "precision_at_1000": 0.00075, + "precision_at_20": 0.0205, + "precision_at_3": 0.0829, + "precision_at_5": 0.05744, + "recall_at_1": 0.15535, + "recall_at_10": 0.35183, + "recall_at_100": 0.54569, + "recall_at_1000": 0.74674, + "recall_at_20": 0.40992, + "recall_at_3": 0.24869, + "recall_at_5": 0.28721 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/HellaSwagInstruct.json b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/HellaSwagInstruct.json new file mode 100644 index 000000000..8865a960b --- /dev/null +++ b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/HellaSwagInstruct.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 423.18965435028076, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.25549, + "map_at_1": 0.13344, + "map_at_10": 0.21296, + "map_at_100": 0.22147, + "map_at_1000": 0.2223, + "map_at_20": 0.21769, + "map_at_3": 0.19065, + "map_at_5": 0.20398, + "mrr_at_1": 0.13343955387373033, + "mrr_at_10": 0.21296111885635774, + "mrr_at_100": 0.22147263706884177, + "mrr_at_1000": 0.2222992543786751, + "mrr_at_20": 0.21768760421169756, + "mrr_at_3": 0.19064927305317544, + "mrr_at_5": 0.20398327026488675, + "nauc_map_at_1000_diff1": 0.20387089052860427, + "nauc_map_at_1000_max": 0.09628150061405313, + "nauc_map_at_1000_std": -0.06461417805126693, + "nauc_map_at_100_diff1": 0.20379572166725457, + "nauc_map_at_100_max": 0.09615934622272736, + "nauc_map_at_100_std": -0.06486335995855402, + "nauc_map_at_10_diff1": 0.20516394389267872, + "nauc_map_at_10_max": 0.09722252424413709, + "nauc_map_at_10_std": -0.06788900377064369, + "nauc_map_at_1_diff1": 0.2385834153798901, + "nauc_map_at_1_max": 0.08652282268755562, + "nauc_map_at_1_std": -0.06138844294271157, + "nauc_map_at_20_diff1": 0.2044482718232994, + "nauc_map_at_20_max": 0.09626198577371879, + "nauc_map_at_20_std": -0.06685089024908536, + "nauc_map_at_3_diff1": 0.2084746970537495, + "nauc_map_at_3_max": 0.09848912502328151, + "nauc_map_at_3_std": -0.06859849962192137, + "nauc_map_at_5_diff1": 0.20540883771728619, + "nauc_map_at_5_max": 0.09756006083033048, + "nauc_map_at_5_std": -0.06816003319872734, + "nauc_mrr_at_1000_diff1": 0.20387090281545353, + "nauc_mrr_at_1000_max": 0.09628154855913341, + "nauc_mrr_at_1000_std": -0.06461412649462946, + "nauc_mrr_at_100_diff1": 0.20379573269624107, + "nauc_mrr_at_100_max": 0.09615938881653423, + "nauc_mrr_at_100_std": -0.06486331335010247, + "nauc_mrr_at_10_diff1": 0.20516394389267872, + "nauc_mrr_at_10_max": 0.09722252424413709, + "nauc_mrr_at_10_std": -0.06788900377064369, + "nauc_mrr_at_1_diff1": 0.2385834153798901, + "nauc_mrr_at_1_max": 0.08652282268755562, + "nauc_mrr_at_1_std": -0.06138844294271157, + "nauc_mrr_at_20_diff1": 0.2044482718232994, + "nauc_mrr_at_20_max": 0.09626198577371879, + "nauc_mrr_at_20_std": -0.06685089024908536, + "nauc_mrr_at_3_diff1": 0.2084746970537495, + "nauc_mrr_at_3_max": 0.09848912502328151, + "nauc_mrr_at_3_std": -0.06859849962192137, + "nauc_mrr_at_5_diff1": 0.20540883771728619, + "nauc_mrr_at_5_max": 0.09756006083033048, + "nauc_mrr_at_5_std": -0.06816003319872734, + "nauc_ndcg_at_1000_diff1": 0.19124512124107626, + "nauc_ndcg_at_1000_max": 0.09710237686183626, + "nauc_ndcg_at_1000_std": -0.047651491317007286, + "nauc_ndcg_at_100_diff1": 0.1892783561200762, + "nauc_ndcg_at_100_max": 0.09478805035424746, + "nauc_ndcg_at_100_std": -0.05252259848754084, + "nauc_ndcg_at_10_diff1": 0.19604192019351266, + "nauc_ndcg_at_10_max": 0.09910259197141988, + "nauc_ndcg_at_10_std": -0.06862849162114151, + "nauc_ndcg_at_1_diff1": 0.2385834153798901, + "nauc_ndcg_at_1_max": 0.08652282268755562, + "nauc_ndcg_at_1_std": -0.06138844294271157, + "nauc_ndcg_at_20_diff1": 0.1934619352447989, + "nauc_ndcg_at_20_max": 0.09602368632392005, + "nauc_ndcg_at_20_std": -0.06520333004782994, + "nauc_ndcg_at_3_diff1": 0.20149170367322528, + "nauc_ndcg_at_3_max": 0.10154529402086514, + "nauc_ndcg_at_3_std": -0.0702381018576458, + "nauc_ndcg_at_5_diff1": 0.19658902641998, + "nauc_ndcg_at_5_max": 0.09995584685702935, + "nauc_ndcg_at_5_std": -0.0693586926564439, + "nauc_precision_at_1000_diff1": 0.13121551086226588, + "nauc_precision_at_1000_max": 0.10344425521563563, + "nauc_precision_at_1000_std": 0.10048234896959972, + "nauc_precision_at_100_diff1": 0.14233344805856424, + "nauc_precision_at_100_max": 0.08520317979771214, + "nauc_precision_at_100_std": 0.0035751114194481947, + "nauc_precision_at_10_diff1": 0.17548888545054941, + "nauc_precision_at_10_max": 0.10276089844435306, + "nauc_precision_at_10_std": -0.06975519342323863, + "nauc_precision_at_1_diff1": 0.2385834153798901, + "nauc_precision_at_1_max": 0.08652282268755562, + "nauc_precision_at_1_std": -0.06138844294271157, + "nauc_precision_at_20_diff1": 0.1665661441780543, + "nauc_precision_at_20_max": 0.09308897809918117, + "nauc_precision_at_20_std": -0.05872771741248014, + "nauc_precision_at_3_diff1": 0.18521156799084204, + "nauc_precision_at_3_max": 0.1087491268251242, + "nauc_precision_at_3_std": -0.07405153484189447, + "nauc_precision_at_5_diff1": 0.17640890706304765, + "nauc_precision_at_5_max": 0.10520392928610714, + "nauc_precision_at_5_std": -0.07185627370275346, + "nauc_recall_at_1000_diff1": 0.13121551086226646, + "nauc_recall_at_1000_max": 0.10344425521563681, + "nauc_recall_at_1000_std": 0.10048234896960145, + "nauc_recall_at_100_diff1": 0.14233344805856396, + "nauc_recall_at_100_max": 0.08520317979771176, + "nauc_recall_at_100_std": 0.003575111419448286, + "nauc_recall_at_10_diff1": 0.17548888545054955, + "nauc_recall_at_10_max": 0.10276089844435311, + "nauc_recall_at_10_std": -0.06975519342323871, + "nauc_recall_at_1_diff1": 0.2385834153798901, + "nauc_recall_at_1_max": 0.08652282268755562, + "nauc_recall_at_1_std": -0.06138844294271157, + "nauc_recall_at_20_diff1": 0.16656614417805476, + "nauc_recall_at_20_max": 0.09308897809918172, + "nauc_recall_at_20_std": -0.058727717412479605, + "nauc_recall_at_3_diff1": 0.18521156799084185, + "nauc_recall_at_3_max": 0.10874912682512401, + "nauc_recall_at_3_std": -0.07405153484189476, + "nauc_recall_at_5_diff1": 0.1764089070630478, + "nauc_recall_at_5_max": 0.10520392928610718, + "nauc_recall_at_5_std": -0.0718562737027536, + "ndcg_at_1": 0.13344, + "ndcg_at_10": 0.25549, + "ndcg_at_100": 0.30124, + "ndcg_at_1000": 0.32644, + "ndcg_at_20": 0.2726, + "ndcg_at_3": 0.20971, + "ndcg_at_5": 0.23362, + "precision_at_1": 0.13344, + "precision_at_10": 0.03907, + "precision_at_100": 0.00615, + "precision_at_1000": 0.00082, + "precision_at_20": 0.0229, + "precision_at_3": 0.08833, + "precision_at_5": 0.06455, + "recall_at_1": 0.13344, + "recall_at_10": 0.39066, + "recall_at_100": 0.61512, + "recall_at_1000": 0.82055, + "recall_at_20": 0.45808, + "recall_at_3": 0.26499, + "recall_at_5": 0.32274 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/PIQAInstruct.json b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/PIQAInstruct.json new file mode 100644 index 000000000..5e1357c5e --- /dev/null +++ b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/PIQAInstruct.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 55.074302196502686, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.19027, + "map_at_1": 0.08814, + "map_at_10": 0.15643, + "map_at_100": 0.16525, + "map_at_1000": 0.16601, + "map_at_20": 0.16117, + "map_at_3": 0.14182, + "map_at_5": 0.14957, + "mrr_at_1": 0.088139281828074, + "mrr_at_10": 0.15643016909338997, + "mrr_at_100": 0.16524852822794867, + "mrr_at_1000": 0.16601376033350612, + "mrr_at_20": 0.16117490320017716, + "mrr_at_3": 0.14182081973159244, + "mrr_at_5": 0.14957381211461737, + "nauc_map_at_1000_diff1": -0.015477184961386956, + "nauc_map_at_1000_max": 0.14793307136167896, + "nauc_map_at_1000_std": 0.08146594371921635, + "nauc_map_at_100_diff1": -0.015428145714597722, + "nauc_map_at_100_max": 0.14812600818248298, + "nauc_map_at_100_std": 0.08145147901153778, + "nauc_map_at_10_diff1": -0.015661066459281673, + "nauc_map_at_10_max": 0.14832872000429126, + "nauc_map_at_10_std": 0.07175412826360622, + "nauc_map_at_1_diff1": 0.04829854018437726, + "nauc_map_at_1_max": 0.15431791487872937, + "nauc_map_at_1_std": 0.039905594979485724, + "nauc_map_at_20_diff1": -0.016572404009532728, + "nauc_map_at_20_max": 0.14856268540152637, + "nauc_map_at_20_std": 0.0791925137205779, + "nauc_map_at_3_diff1": -0.00767132642974905, + "nauc_map_at_3_max": 0.16069551004107563, + "nauc_map_at_3_std": 0.06786156564879801, + "nauc_map_at_5_diff1": -0.011834118996431038, + "nauc_map_at_5_max": 0.15691663278805779, + "nauc_map_at_5_std": 0.06859826824835594, + "nauc_mrr_at_1000_diff1": -0.015477134338727218, + "nauc_mrr_at_1000_max": 0.14793316333952697, + "nauc_mrr_at_1000_std": 0.08146594285335429, + "nauc_mrr_at_100_diff1": -0.015428145714597722, + "nauc_mrr_at_100_max": 0.14812600818248298, + "nauc_mrr_at_100_std": 0.08145147901153778, + "nauc_mrr_at_10_diff1": -0.015661066459281673, + "nauc_mrr_at_10_max": 0.14832872000429126, + "nauc_mrr_at_10_std": 0.07175412826360622, + "nauc_mrr_at_1_diff1": 0.04829854018437726, + "nauc_mrr_at_1_max": 0.15431791487872937, + "nauc_mrr_at_1_std": 0.039905594979485724, + "nauc_mrr_at_20_diff1": -0.016572404009532728, + "nauc_mrr_at_20_max": 0.14856268540152637, + "nauc_mrr_at_20_std": 0.0791925137205779, + "nauc_mrr_at_3_diff1": -0.00767132642974905, + "nauc_mrr_at_3_max": 0.16069551004107563, + "nauc_mrr_at_3_std": 0.06786156564879801, + "nauc_mrr_at_5_diff1": -0.011834118996431038, + "nauc_mrr_at_5_max": 0.15691663278805779, + "nauc_mrr_at_5_std": 0.06859826824835594, + "nauc_ndcg_at_1000_diff1": -0.03142607049024857, + "nauc_ndcg_at_1000_max": 0.12583003703736514, + "nauc_ndcg_at_1000_std": 0.11986320461735325, + "nauc_ndcg_at_100_diff1": -0.02803943987226383, + "nauc_ndcg_at_100_max": 0.1320236598922112, + "nauc_ndcg_at_100_std": 0.1187437899374198, + "nauc_ndcg_at_10_diff1": -0.03208702827570455, + "nauc_ndcg_at_10_max": 0.13318865045401093, + "nauc_ndcg_at_10_std": 0.07946247815852475, + "nauc_ndcg_at_1_diff1": 0.04829854018437726, + "nauc_ndcg_at_1_max": 0.15431791487872937, + "nauc_ndcg_at_1_std": 0.039905594979485724, + "nauc_ndcg_at_20_diff1": -0.0348732819114721, + "nauc_ndcg_at_20_max": 0.13386980759755138, + "nauc_ndcg_at_20_std": 0.1031227967924423, + "nauc_ndcg_at_3_diff1": -0.01835822227963399, + "nauc_ndcg_at_3_max": 0.1584443302185807, + "nauc_ndcg_at_3_std": 0.07369131660039789, + "nauc_ndcg_at_5_diff1": -0.025195447542108933, + "nauc_ndcg_at_5_max": 0.152121616756152, + "nauc_ndcg_at_5_std": 0.07421175707395235, + "nauc_precision_at_1000_diff1": -0.08401357162435262, + "nauc_precision_at_1000_max": 0.02449381466190679, + "nauc_precision_at_1000_std": 0.28148860760242994, + "nauc_precision_at_100_diff1": -0.046598456782854146, + "nauc_precision_at_100_max": 0.09244762990007184, + "nauc_precision_at_100_std": 0.22967007872514023, + "nauc_precision_at_10_diff1": -0.06511435377508734, + "nauc_precision_at_10_max": 0.09734468875543743, + "nauc_precision_at_10_std": 0.09434818909520114, + "nauc_precision_at_1_diff1": 0.04829854018437726, + "nauc_precision_at_1_max": 0.15431791487872937, + "nauc_precision_at_1_std": 0.039905594979485724, + "nauc_precision_at_20_diff1": -0.07206837139426062, + "nauc_precision_at_20_max": 0.10016764875483765, + "nauc_precision_at_20_std": 0.1614552602556027, + "nauc_precision_at_3_diff1": -0.04081267292075056, + "nauc_precision_at_3_max": 0.15277376747394367, + "nauc_precision_at_3_std": 0.08607367873771987, + "nauc_precision_at_5_diff1": -0.0530592556364417, + "nauc_precision_at_5_max": 0.1407402323110919, + "nauc_precision_at_5_std": 0.08540596054890336, + "nauc_recall_at_1000_diff1": -0.08401357162435094, + "nauc_recall_at_1000_max": 0.02449381466190786, + "nauc_recall_at_1000_std": 0.28148860760243133, + "nauc_recall_at_100_diff1": -0.04659845678285415, + "nauc_recall_at_100_max": 0.09244762990007152, + "nauc_recall_at_100_std": 0.22967007872514028, + "nauc_recall_at_10_diff1": -0.06511435377508745, + "nauc_recall_at_10_max": 0.09734468875543736, + "nauc_recall_at_10_std": 0.09434818909520107, + "nauc_recall_at_1_diff1": 0.04829854018437726, + "nauc_recall_at_1_max": 0.15431791487872937, + "nauc_recall_at_1_std": 0.039905594979485724, + "nauc_recall_at_20_diff1": -0.07206837139426066, + "nauc_recall_at_20_max": 0.10016764875483775, + "nauc_recall_at_20_std": 0.16145526025560292, + "nauc_recall_at_3_diff1": -0.04081267292075031, + "nauc_recall_at_3_max": 0.15277376747394397, + "nauc_recall_at_3_std": 0.08607367873772002, + "nauc_recall_at_5_diff1": -0.05305925563644175, + "nauc_recall_at_5_max": 0.14074023231109184, + "nauc_recall_at_5_std": 0.08540596054890336, + "ndcg_at_1": 0.08814, + "ndcg_at_10": 0.19027, + "ndcg_at_100": 0.2384, + "ndcg_at_1000": 0.262, + "ndcg_at_20": 0.20731, + "ndcg_at_3": 0.15933, + "ndcg_at_5": 0.17349, + "precision_at_1": 0.08814, + "precision_at_10": 0.02971, + "precision_at_100": 0.00535, + "precision_at_1000": 0.00073, + "precision_at_20": 0.0182, + "precision_at_3": 0.07, + "precision_at_5": 0.04897, + "recall_at_1": 0.08814, + "recall_at_10": 0.29706, + "recall_at_100": 0.53482, + "recall_at_1000": 0.72742, + "recall_at_20": 0.36398, + "recall_at_3": 0.21001, + "recall_at_5": 0.24483 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/QuailInstruct.json b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/QuailInstruct.json new file mode 100644 index 000000000..13f36b05b --- /dev/null +++ b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/QuailInstruct.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 92.38344383239746, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07076, + "map_at_1": 0.02574, + "map_at_10": 0.05336, + "map_at_100": 0.06001, + "map_at_1000": 0.06103, + "map_at_20": 0.05675, + "map_at_3": 0.04277, + "map_at_5": 0.0477, + "mrr_at_1": 0.025735294117647058, + "mrr_at_10": 0.0533565301120448, + "mrr_at_100": 0.06001128054620309, + "mrr_at_1000": 0.06103119536184295, + "mrr_at_20": 0.056752117503745175, + "mrr_at_3": 0.042769607843137235, + "mrr_at_5": 0.04769607843137253, + "nauc_map_at_1000_diff1": 0.18103464002464317, + "nauc_map_at_1000_max": 0.13529619417063862, + "nauc_map_at_1000_std": 0.07993165602896918, + "nauc_map_at_100_diff1": 0.18135695389209958, + "nauc_map_at_100_max": 0.136233551465129, + "nauc_map_at_100_std": 0.0793201885603607, + "nauc_map_at_10_diff1": 0.19347409908463464, + "nauc_map_at_10_max": 0.13646282305830712, + "nauc_map_at_10_std": 0.07457956682616576, + "nauc_map_at_1_diff1": 0.34535628042470023, + "nauc_map_at_1_max": 0.19313120472229678, + "nauc_map_at_1_std": 0.05892905055770628, + "nauc_map_at_20_diff1": 0.18713839110900596, + "nauc_map_at_20_max": 0.1394425770738342, + "nauc_map_at_20_std": 0.07733101152626362, + "nauc_map_at_3_diff1": 0.22911027174886572, + "nauc_map_at_3_max": 0.13604049440195948, + "nauc_map_at_3_std": 0.07136108149083223, + "nauc_map_at_5_diff1": 0.2016964411528772, + "nauc_map_at_5_max": 0.12991493424142206, + "nauc_map_at_5_std": 0.07243446685405337, + "nauc_mrr_at_1000_diff1": 0.18103464002464317, + "nauc_mrr_at_1000_max": 0.13529619417063862, + "nauc_mrr_at_1000_std": 0.07993165602896918, + "nauc_mrr_at_100_diff1": 0.18135695389209958, + "nauc_mrr_at_100_max": 0.136233551465129, + "nauc_mrr_at_100_std": 0.0793201885603607, + "nauc_mrr_at_10_diff1": 0.19347409908463464, + "nauc_mrr_at_10_max": 0.13646282305830712, + "nauc_mrr_at_10_std": 0.07457956682616576, + "nauc_mrr_at_1_diff1": 0.34535628042470023, + "nauc_mrr_at_1_max": 0.19313120472229678, + "nauc_mrr_at_1_std": 0.05892905055770628, + "nauc_mrr_at_20_diff1": 0.18713839110900596, + "nauc_mrr_at_20_max": 0.1394425770738342, + "nauc_mrr_at_20_std": 0.07733101152626362, + "nauc_mrr_at_3_diff1": 0.22911027174886572, + "nauc_mrr_at_3_max": 0.13604049440195948, + "nauc_mrr_at_3_std": 0.07136108149083223, + "nauc_mrr_at_5_diff1": 0.2016964411528772, + "nauc_mrr_at_5_max": 0.12991493424142206, + "nauc_mrr_at_5_std": 0.07243446685405337, + "nauc_ndcg_at_1000_diff1": 0.12195840395880321, + "nauc_ndcg_at_1000_max": 0.11172498535598953, + "nauc_ndcg_at_1000_std": 0.10379571245411649, + "nauc_ndcg_at_100_diff1": 0.12643102240493012, + "nauc_ndcg_at_100_max": 0.12289830425460839, + "nauc_ndcg_at_100_std": 0.09290212023930731, + "nauc_ndcg_at_10_diff1": 0.15943766168212056, + "nauc_ndcg_at_10_max": 0.13103476510166165, + "nauc_ndcg_at_10_std": 0.07627032323501705, + "nauc_ndcg_at_1_diff1": 0.34535628042470023, + "nauc_ndcg_at_1_max": 0.19313120472229678, + "nauc_ndcg_at_1_std": 0.05892905055770628, + "nauc_ndcg_at_20_diff1": 0.14604408415941758, + "nauc_ndcg_at_20_max": 0.13940200255769397, + "nauc_ndcg_at_20_std": 0.08437251016953842, + "nauc_ndcg_at_3_diff1": 0.20772251643014736, + "nauc_ndcg_at_3_max": 0.1256710736333287, + "nauc_ndcg_at_3_std": 0.07226563521757766, + "nauc_ndcg_at_5_diff1": 0.17076488169931012, + "nauc_ndcg_at_5_max": 0.11848471577935935, + "nauc_ndcg_at_5_std": 0.0738818680415232, + "nauc_precision_at_1000_diff1": 0.04097215483552182, + "nauc_precision_at_1000_max": 0.0650064176642347, + "nauc_precision_at_1000_std": 0.15517129208973213, + "nauc_precision_at_100_diff1": 0.06468711021828528, + "nauc_precision_at_100_max": 0.10363910164794261, + "nauc_precision_at_100_std": 0.11267011505950646, + "nauc_precision_at_10_diff1": 0.1113008427812199, + "nauc_precision_at_10_max": 0.12521595069608943, + "nauc_precision_at_10_std": 0.07812514337624721, + "nauc_precision_at_1_diff1": 0.34535628042470023, + "nauc_precision_at_1_max": 0.19313120472229678, + "nauc_precision_at_1_std": 0.05892905055770628, + "nauc_precision_at_20_diff1": 0.09442461390384277, + "nauc_precision_at_20_max": 0.14319967934026762, + "nauc_precision_at_20_std": 0.0950719490083025, + "nauc_precision_at_3_diff1": 0.16653962485059884, + "nauc_precision_at_3_max": 0.10573334634241516, + "nauc_precision_at_3_std": 0.07370966168256206, + "nauc_precision_at_5_diff1": 0.11821057565083024, + "nauc_precision_at_5_max": 0.09960835614371874, + "nauc_precision_at_5_std": 0.07619263672700442, + "nauc_recall_at_1000_diff1": 0.04097215483552268, + "nauc_recall_at_1000_max": 0.065006417664235, + "nauc_recall_at_1000_std": 0.1551712920897331, + "nauc_recall_at_100_diff1": 0.06468711021828516, + "nauc_recall_at_100_max": 0.1036391016479424, + "nauc_recall_at_100_std": 0.11267011505950605, + "nauc_recall_at_10_diff1": 0.11130084278121978, + "nauc_recall_at_10_max": 0.12521595069608904, + "nauc_recall_at_10_std": 0.07812514337624694, + "nauc_recall_at_1_diff1": 0.34535628042470023, + "nauc_recall_at_1_max": 0.19313120472229678, + "nauc_recall_at_1_std": 0.05892905055770628, + "nauc_recall_at_20_diff1": 0.09442461390384257, + "nauc_recall_at_20_max": 0.1431996793402673, + "nauc_recall_at_20_std": 0.09507194900830218, + "nauc_recall_at_3_diff1": 0.16653962485059876, + "nauc_recall_at_3_max": 0.10573334634241519, + "nauc_recall_at_3_std": 0.07370966168256202, + "nauc_recall_at_5_diff1": 0.11821057565083008, + "nauc_recall_at_5_max": 0.09960835614371859, + "nauc_recall_at_5_std": 0.07619263672700428, + "ndcg_at_1": 0.02574, + "ndcg_at_10": 0.07076, + "ndcg_at_100": 0.10905, + "ndcg_at_1000": 0.14321, + "ndcg_at_20": 0.08319, + "ndcg_at_3": 0.0484, + "ndcg_at_5": 0.05715, + "precision_at_1": 0.02574, + "precision_at_10": 0.01276, + "precision_at_100": 0.00321, + "precision_at_1000": 0.00061, + "precision_at_20": 0.00884, + "precision_at_3": 0.02157, + "precision_at_5": 0.01713, + "recall_at_1": 0.02574, + "recall_at_10": 0.12757, + "recall_at_100": 0.32096, + "recall_at_1000": 0.60588, + "recall_at_20": 0.17684, + "recall_at_3": 0.06471, + "recall_at_5": 0.08566 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/RARbCodeInstruct.json b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/RARbCodeInstruct.json new file mode 100644 index 000000000..576a9462e --- /dev/null +++ b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/RARbCodeInstruct.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 3950.9801058769226, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.39575, + "map_at_1": 0.2628, + "map_at_10": 0.3448, + "map_at_100": 0.35294, + "map_at_1000": 0.35358, + "map_at_20": 0.34955, + "map_at_3": 0.31345, + "map_at_5": 0.33108, + "mrr_at_1": 0.26212938005390835, + "mrr_at_10": 0.34446155820818875, + "mrr_at_100": 0.35260904630013984, + "mrr_at_1000": 0.3532481042222237, + "mrr_at_20": 0.3492112557790156, + "mrr_at_3": 0.3131176999101526, + "mrr_at_5": 0.33073899371069154, + "nauc_map_at_1000_diff1": 0.4111451484821214, + "nauc_map_at_1000_max": 0.19989007434231018, + "nauc_map_at_1000_std": 0.18227118352186988, + "nauc_map_at_100_diff1": 0.4109419508177575, + "nauc_map_at_100_max": 0.19980382180631875, + "nauc_map_at_100_std": 0.18244334984344326, + "nauc_map_at_10_diff1": 0.4112195449397908, + "nauc_map_at_10_max": 0.2014359578007846, + "nauc_map_at_10_std": 0.18282123685645582, + "nauc_map_at_1_diff1": 0.473830785740485, + "nauc_map_at_1_max": 0.18147016978705804, + "nauc_map_at_1_std": 0.15626333641709, + "nauc_map_at_20_diff1": 0.41046126811041533, + "nauc_map_at_20_max": 0.20002001513259066, + "nauc_map_at_20_std": 0.18257247558157935, + "nauc_map_at_3_diff1": 0.42013118874756433, + "nauc_map_at_3_max": 0.20176209602178352, + "nauc_map_at_3_std": 0.17320889735449035, + "nauc_map_at_5_diff1": 0.4154639001142559, + "nauc_map_at_5_max": 0.20349093524756517, + "nauc_map_at_5_std": 0.1757735556979957, + "nauc_mrr_at_1000_diff1": 0.41239823563497396, + "nauc_mrr_at_1000_max": 0.19982530439381074, + "nauc_mrr_at_1000_std": 0.18060017805809006, + "nauc_mrr_at_100_diff1": 0.41219298830858336, + "nauc_mrr_at_100_max": 0.19973914613934052, + "nauc_mrr_at_100_std": 0.18077506304041457, + "nauc_mrr_at_10_diff1": 0.4124551836372662, + "nauc_mrr_at_10_max": 0.2013781076201602, + "nauc_mrr_at_10_std": 0.1811778803870234, + "nauc_mrr_at_1_diff1": 0.4764644164775741, + "nauc_mrr_at_1_max": 0.18132691545202756, + "nauc_mrr_at_1_std": 0.152827128481755, + "nauc_mrr_at_20_diff1": 0.41170455413818874, + "nauc_mrr_at_20_max": 0.19995576269658782, + "nauc_mrr_at_20_std": 0.18091452203015795, + "nauc_mrr_at_3_diff1": 0.42135562893870365, + "nauc_mrr_at_3_max": 0.20170518485849198, + "nauc_mrr_at_3_std": 0.17158168412120625, + "nauc_mrr_at_5_diff1": 0.4166894240507472, + "nauc_mrr_at_5_max": 0.20343481975616035, + "nauc_mrr_at_5_std": 0.17414286649938387, + "nauc_ndcg_at_1000_diff1": 0.3908434067658865, + "nauc_ndcg_at_1000_max": 0.20597185814245916, + "nauc_ndcg_at_1000_std": 0.19708725498546767, + "nauc_ndcg_at_100_diff1": 0.3835906743886766, + "nauc_ndcg_at_100_max": 0.20137370798352291, + "nauc_ndcg_at_100_std": 0.20223392294399523, + "nauc_ndcg_at_10_diff1": 0.3850602935011896, + "nauc_ndcg_at_10_max": 0.2067438306120317, + "nauc_ndcg_at_10_std": 0.20128765086797382, + "nauc_ndcg_at_1_diff1": 0.473830785740485, + "nauc_ndcg_at_1_max": 0.18147016978705804, + "nauc_ndcg_at_1_std": 0.15626333641709, + "nauc_ndcg_at_20_diff1": 0.3813577076866735, + "nauc_ndcg_at_20_max": 0.20145127666088186, + "nauc_ndcg_at_20_std": 0.20105088556480633, + "nauc_ndcg_at_3_diff1": 0.40326441072640407, + "nauc_ndcg_at_3_max": 0.20871476016684154, + "nauc_ndcg_at_3_std": 0.17943859486391875, + "nauc_ndcg_at_5_diff1": 0.3950856078262072, + "nauc_ndcg_at_5_max": 0.2118184850364788, + "nauc_ndcg_at_5_std": 0.18437795127792822, + "nauc_precision_at_1000_diff1": 0.2779225680434838, + "nauc_precision_at_1000_max": 0.35350731487632653, + "nauc_precision_at_1000_std": 0.3343179210586312, + "nauc_precision_at_100_diff1": 0.2536788197972267, + "nauc_precision_at_100_max": 0.20275359148301447, + "nauc_precision_at_100_std": 0.31298624425653543, + "nauc_precision_at_10_diff1": 0.3032250796901123, + "nauc_precision_at_10_max": 0.22077745360337558, + "nauc_precision_at_10_std": 0.26363938775104423, + "nauc_precision_at_1_diff1": 0.473830785740485, + "nauc_precision_at_1_max": 0.18147016978705804, + "nauc_precision_at_1_std": 0.15626333641709, + "nauc_precision_at_20_diff1": 0.2780939907177748, + "nauc_precision_at_20_max": 0.19882993058588402, + "nauc_precision_at_20_std": 0.26963423663117836, + "nauc_precision_at_3_diff1": 0.35697178929115175, + "nauc_precision_at_3_max": 0.22796262664585074, + "nauc_precision_at_3_std": 0.19679601254087797, + "nauc_precision_at_5_diff1": 0.3376172238706129, + "nauc_precision_at_5_max": 0.2354914661725942, + "nauc_precision_at_5_std": 0.20939252273067058, + "nauc_recall_at_1000_diff1": 0.27792256804348126, + "nauc_recall_at_1000_max": 0.3535073148763273, + "nauc_recall_at_1000_std": 0.33431792105863023, + "nauc_recall_at_100_diff1": 0.2536788197972266, + "nauc_recall_at_100_max": 0.20275359148301467, + "nauc_recall_at_100_std": 0.3129862442565355, + "nauc_recall_at_10_diff1": 0.30322507969011214, + "nauc_recall_at_10_max": 0.22077745360337575, + "nauc_recall_at_10_std": 0.2636393877510443, + "nauc_recall_at_1_diff1": 0.473830785740485, + "nauc_recall_at_1_max": 0.18147016978705804, + "nauc_recall_at_1_std": 0.15626333641709, + "nauc_recall_at_20_diff1": 0.2780939907177751, + "nauc_recall_at_20_max": 0.1988299305858839, + "nauc_recall_at_20_std": 0.26963423663117875, + "nauc_recall_at_3_diff1": 0.35697178929115203, + "nauc_recall_at_3_max": 0.22796262664585096, + "nauc_recall_at_3_std": 0.19679601254087803, + "nauc_recall_at_5_diff1": 0.33761722387061294, + "nauc_recall_at_5_max": 0.23549146617259387, + "nauc_recall_at_5_std": 0.20939252273067077, + "ndcg_at_1": 0.2628, + "ndcg_at_10": 0.39575, + "ndcg_at_100": 0.43826, + "ndcg_at_1000": 0.45716, + "ndcg_at_20": 0.41309, + "ndcg_at_3": 0.33164, + "ndcg_at_5": 0.36334, + "precision_at_1": 0.2628, + "precision_at_10": 0.056, + "precision_at_100": 0.00765, + "precision_at_1000": 0.00092, + "precision_at_20": 0.03144, + "precision_at_3": 0.12826, + "precision_at_5": 0.09232, + "recall_at_1": 0.2628, + "recall_at_10": 0.55997, + "recall_at_100": 0.7655, + "recall_at_1000": 0.91846, + "recall_at_20": 0.62871, + "recall_at_3": 0.38477, + "recall_at_5": 0.46159 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/RARbMathInstruct.json b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/RARbMathInstruct.json new file mode 100644 index 000000000..5ccd910da --- /dev/null +++ b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/RARbMathInstruct.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 5020.938431501389, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.64509, + "map_at_1": 0.57683, + "map_at_10": 0.62114, + "map_at_100": 0.62691, + "map_at_1000": 0.62734, + "map_at_20": 0.62422, + "map_at_3": 0.60875, + "map_at_5": 0.61551, + "mrr_at_1": 0.5768317771799335, + "mrr_at_10": 0.6211363687744446, + "mrr_at_100": 0.6269073307417888, + "mrr_at_1000": 0.6273373664779892, + "mrr_at_20": 0.6242185787753797, + "mrr_at_3": 0.6087461096165011, + "mrr_at_5": 0.6155114205834259, + "nauc_map_at_1000_diff1": 0.8545730317865433, + "nauc_map_at_1000_max": 0.37839300300271955, + "nauc_map_at_1000_std": -0.3246619751938657, + "nauc_map_at_100_diff1": 0.8544236208976506, + "nauc_map_at_100_max": 0.37838106719036607, + "nauc_map_at_100_std": -0.3246507164540515, + "nauc_map_at_10_diff1": 0.8549660691375637, + "nauc_map_at_10_max": 0.3762377834859537, + "nauc_map_at_10_std": -0.3278550868898928, + "nauc_map_at_1_diff1": 0.8849172046529393, + "nauc_map_at_1_max": 0.3982741826682749, + "nauc_map_at_1_std": -0.31753638814816376, + "nauc_map_at_20_diff1": 0.8542498897144643, + "nauc_map_at_20_max": 0.37742887016142523, + "nauc_map_at_20_std": -0.3264492649990765, + "nauc_map_at_3_diff1": 0.861290211538951, + "nauc_map_at_3_max": 0.3803224232217883, + "nauc_map_at_3_std": -0.3272992131082136, + "nauc_map_at_5_diff1": 0.8573435461889151, + "nauc_map_at_5_max": 0.3763360424182241, + "nauc_map_at_5_std": -0.32970309513229457, + "nauc_mrr_at_1000_diff1": 0.8545730317865433, + "nauc_mrr_at_1000_max": 0.37839300300271955, + "nauc_mrr_at_1000_std": -0.3246619751938657, + "nauc_mrr_at_100_diff1": 0.8544236208976506, + "nauc_mrr_at_100_max": 0.37838106719036607, + "nauc_mrr_at_100_std": -0.3246507164540515, + "nauc_mrr_at_10_diff1": 0.8549660691375637, + "nauc_mrr_at_10_max": 0.3762377834859537, + "nauc_mrr_at_10_std": -0.3278550868898928, + "nauc_mrr_at_1_diff1": 0.8849172046529393, + "nauc_mrr_at_1_max": 0.3982741826682749, + "nauc_mrr_at_1_std": -0.31753638814816376, + "nauc_mrr_at_20_diff1": 0.8542498897144643, + "nauc_mrr_at_20_max": 0.37742887016142523, + "nauc_mrr_at_20_std": -0.3264492649990765, + "nauc_mrr_at_3_diff1": 0.861290211538951, + "nauc_mrr_at_3_max": 0.3803224232217883, + "nauc_mrr_at_3_std": -0.3272992131082136, + "nauc_mrr_at_5_diff1": 0.8573435461889151, + "nauc_mrr_at_5_max": 0.3763360424182241, + "nauc_mrr_at_5_std": -0.32970309513229457, + "nauc_ndcg_at_1000_diff1": 0.8425513181870316, + "nauc_ndcg_at_1000_max": 0.37844885696502856, + "nauc_ndcg_at_1000_std": -0.3126053453492018, + "nauc_ndcg_at_100_diff1": 0.8372768972650982, + "nauc_ndcg_at_100_max": 0.37777936978228527, + "nauc_ndcg_at_100_std": -0.31178669149359, + "nauc_ndcg_at_10_diff1": 0.8394982548952292, + "nauc_ndcg_at_10_max": 0.36623232250139576, + "nauc_ndcg_at_10_std": -0.3306673858422091, + "nauc_ndcg_at_1_diff1": 0.8849172046529393, + "nauc_ndcg_at_1_max": 0.3982741826682749, + "nauc_ndcg_at_1_std": -0.31753638814816376, + "nauc_ndcg_at_20_diff1": 0.8362032372911271, + "nauc_ndcg_at_20_max": 0.37023152475777465, + "nauc_ndcg_at_20_std": -0.3254052858161765, + "nauc_ndcg_at_3_diff1": 0.8533093321918598, + "nauc_ndcg_at_3_max": 0.3742305887221768, + "nauc_ndcg_at_3_std": -0.33090548904659445, + "nauc_ndcg_at_5_diff1": 0.8458274494073954, + "nauc_ndcg_at_5_max": 0.36657781860051314, + "nauc_ndcg_at_5_std": -0.33563532832490783, + "nauc_precision_at_1000_diff1": 0.6950764043644625, + "nauc_precision_at_1000_max": 0.5501924010107552, + "nauc_precision_at_1000_std": 0.22236600036653686, + "nauc_precision_at_100_diff1": 0.7090836759744418, + "nauc_precision_at_100_max": 0.41178200680775334, + "nauc_precision_at_100_std": -0.1516669850169436, + "nauc_precision_at_10_diff1": 0.7801193211579912, + "nauc_precision_at_10_max": 0.3292194188917609, + "nauc_precision_at_10_std": -0.3388003807236741, + "nauc_precision_at_1_diff1": 0.8849172046529393, + "nauc_precision_at_1_max": 0.3982741826682749, + "nauc_precision_at_1_std": -0.31753638814816376, + "nauc_precision_at_20_diff1": 0.7537241029573506, + "nauc_precision_at_20_max": 0.34350298479072666, + "nauc_precision_at_20_std": -0.31292152856772487, + "nauc_precision_at_3_diff1": 0.8286755990858974, + "nauc_precision_at_3_max": 0.35541830144080166, + "nauc_precision_at_3_std": -0.34213882479986685, + "nauc_precision_at_5_diff1": 0.807380425484518, + "nauc_precision_at_5_max": 0.3336722898328749, + "nauc_precision_at_5_std": -0.35584260140552376, + "nauc_recall_at_1000_diff1": 0.695076404364474, + "nauc_recall_at_1000_max": 0.5501924010107683, + "nauc_recall_at_1000_std": 0.2223660003665412, + "nauc_recall_at_100_diff1": 0.7090836759744402, + "nauc_recall_at_100_max": 0.4117820068077513, + "nauc_recall_at_100_std": -0.15166698501694634, + "nauc_recall_at_10_diff1": 0.7801193211579912, + "nauc_recall_at_10_max": 0.3292194188917622, + "nauc_recall_at_10_std": -0.3388003807236725, + "nauc_recall_at_1_diff1": 0.8849172046529393, + "nauc_recall_at_1_max": 0.3982741826682749, + "nauc_recall_at_1_std": -0.31753638814816376, + "nauc_recall_at_20_diff1": 0.7537241029573503, + "nauc_recall_at_20_max": 0.34350298479072733, + "nauc_recall_at_20_std": -0.3129215285677236, + "nauc_recall_at_3_diff1": 0.8286755990858976, + "nauc_recall_at_3_max": 0.3554183014408015, + "nauc_recall_at_3_std": -0.34213882479986724, + "nauc_recall_at_5_diff1": 0.8073804254845174, + "nauc_recall_at_5_max": 0.33367228983287506, + "nauc_recall_at_5_std": -0.35584260140552326, + "ndcg_at_1": 0.57683, + "ndcg_at_10": 0.64509, + "ndcg_at_100": 0.67624, + "ndcg_at_1000": 0.68801, + "ndcg_at_20": 0.65635, + "ndcg_at_3": 0.61913, + "ndcg_at_5": 0.63135, + "precision_at_1": 0.57683, + "precision_at_10": 0.07216, + "precision_at_100": 0.00874, + "precision_at_1000": 0.00097, + "precision_at_20": 0.03831, + "precision_at_3": 0.21638, + "precision_at_5": 0.13578, + "recall_at_1": 0.57683, + "recall_at_10": 0.72163, + "recall_at_100": 0.87435, + "recall_at_1000": 0.96756, + "recall_at_20": 0.76626, + "recall_at_3": 0.64915, + "recall_at_5": 0.6789 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/SIQAInstruct.json b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/SIQAInstruct.json new file mode 100644 index 000000000..da2579df3 --- /dev/null +++ b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/SIQAInstruct.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 44.792665243148804, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.04769, + "map_at_1": 0.02405, + "map_at_10": 0.03898, + "map_at_100": 0.04253, + "map_at_1000": 0.04342, + "map_at_20": 0.04056, + "map_at_3": 0.03412, + "map_at_5": 0.03652, + "mrr_at_1": 0.024053224155578302, + "mrr_at_10": 0.03898230735487647, + "mrr_at_100": 0.04253228559089224, + "mrr_at_1000": 0.04341542727929972, + "mrr_at_20": 0.0405578036080166, + "mrr_at_3": 0.03411804844762881, + "mrr_at_5": 0.03652337086318665, + "nauc_map_at_1000_diff1": 0.16852806670558992, + "nauc_map_at_1000_max": 0.06929844364888887, + "nauc_map_at_1000_std": -0.015176246681721994, + "nauc_map_at_100_diff1": 0.17044700693514786, + "nauc_map_at_100_max": 0.06892427200055323, + "nauc_map_at_100_std": -0.016056999012383322, + "nauc_map_at_10_diff1": 0.1788845687382626, + "nauc_map_at_10_max": 0.0636648224843595, + "nauc_map_at_10_std": -0.021952498468159585, + "nauc_map_at_1_diff1": 0.31501997480107374, + "nauc_map_at_1_max": 0.09627316380324026, + "nauc_map_at_1_std": -0.06409715408446262, + "nauc_map_at_20_diff1": 0.17431185365870377, + "nauc_map_at_20_max": 0.06962181006995087, + "nauc_map_at_20_std": -0.019452014093450248, + "nauc_map_at_3_diff1": 0.22206107015908805, + "nauc_map_at_3_max": 0.07911281943745216, + "nauc_map_at_3_std": -0.024382561492411844, + "nauc_map_at_5_diff1": 0.19867150703732564, + "nauc_map_at_5_max": 0.07147520435711652, + "nauc_map_at_5_std": -0.026227119587301926, + "nauc_mrr_at_1000_diff1": 0.1685280395784018, + "nauc_mrr_at_1000_max": 0.0692984242933688, + "nauc_mrr_at_1000_std": -0.015176242098857423, + "nauc_mrr_at_100_diff1": 0.17044700693514786, + "nauc_mrr_at_100_max": 0.06892427200055323, + "nauc_mrr_at_100_std": -0.016056999012383322, + "nauc_mrr_at_10_diff1": 0.1788845687382626, + "nauc_mrr_at_10_max": 0.0636648224843595, + "nauc_mrr_at_10_std": -0.021952498468159585, + "nauc_mrr_at_1_diff1": 0.31501997480107374, + "nauc_mrr_at_1_max": 0.09627316380324026, + "nauc_mrr_at_1_std": -0.06409715408446262, + "nauc_mrr_at_20_diff1": 0.17431185365870377, + "nauc_mrr_at_20_max": 0.06962181006995087, + "nauc_mrr_at_20_std": -0.019452014093450248, + "nauc_mrr_at_3_diff1": 0.22206107015908805, + "nauc_mrr_at_3_max": 0.07911281943745216, + "nauc_mrr_at_3_std": -0.024382561492411844, + "nauc_mrr_at_5_diff1": 0.19867150703732564, + "nauc_mrr_at_5_max": 0.07147520435711652, + "nauc_mrr_at_5_std": -0.026227119587301926, + "nauc_ndcg_at_1000_diff1": 0.0858961604702629, + "nauc_ndcg_at_1000_max": 0.0709258770812647, + "nauc_ndcg_at_1000_std": 0.029370133376191918, + "nauc_ndcg_at_100_diff1": 0.10965209145024711, + "nauc_ndcg_at_100_max": 0.06701653962875134, + "nauc_ndcg_at_100_std": 0.011610941951980694, + "nauc_ndcg_at_10_diff1": 0.13208363541065596, + "nauc_ndcg_at_10_max": 0.05179470295761284, + "nauc_ndcg_at_10_std": -0.010970103991568515, + "nauc_ndcg_at_1_diff1": 0.31501997480107374, + "nauc_ndcg_at_1_max": 0.09627316380324026, + "nauc_ndcg_at_1_std": -0.06409715408446262, + "nauc_ndcg_at_20_diff1": 0.12546466579865115, + "nauc_ndcg_at_20_max": 0.06965194954700141, + "nauc_ndcg_at_20_std": -0.003917179319886021, + "nauc_ndcg_at_3_diff1": 0.20331016953056155, + "nauc_ndcg_at_3_max": 0.0780624562923775, + "nauc_ndcg_at_3_std": -0.014603432007666709, + "nauc_ndcg_at_5_diff1": 0.1680678014259147, + "nauc_ndcg_at_5_max": 0.06615088426020567, + "nauc_ndcg_at_5_std": -0.019024227039225593, + "nauc_precision_at_1000_diff1": -0.0038027895408111996, + "nauc_precision_at_1000_max": 0.07593403319479965, + "nauc_precision_at_1000_std": 0.08994716460680498, + "nauc_precision_at_100_diff1": 0.04451968281456622, + "nauc_precision_at_100_max": 0.06749180125106173, + "nauc_precision_at_100_std": 0.04576857247798274, + "nauc_precision_at_10_diff1": 0.052059845040417656, + "nauc_precision_at_10_max": 0.030976518407509014, + "nauc_precision_at_10_std": 0.007120037458244442, + "nauc_precision_at_1_diff1": 0.31501997480107374, + "nauc_precision_at_1_max": 0.09627316380324026, + "nauc_precision_at_1_std": -0.06409715408446262, + "nauc_precision_at_20_diff1": 0.05834476711289891, + "nauc_precision_at_20_max": 0.07417402494356819, + "nauc_precision_at_20_std": 0.01918762464215351, + "nauc_precision_at_3_diff1": 0.16417146591808893, + "nauc_precision_at_3_max": 0.07647824652081293, + "nauc_precision_at_3_std": 0.006254565823549571, + "nauc_precision_at_5_diff1": 0.1089296467693165, + "nauc_precision_at_5_max": 0.05585338568193698, + "nauc_precision_at_5_std": -0.006223709347632574, + "nauc_recall_at_1000_diff1": -0.0038027895408108783, + "nauc_recall_at_1000_max": 0.07593403319480013, + "nauc_recall_at_1000_std": 0.08994716460680537, + "nauc_recall_at_100_diff1": 0.04451968281456611, + "nauc_recall_at_100_max": 0.06749180125106172, + "nauc_recall_at_100_std": 0.04576857247798268, + "nauc_recall_at_10_diff1": 0.05205984504041761, + "nauc_recall_at_10_max": 0.030976518407508927, + "nauc_recall_at_10_std": 0.007120037458244393, + "nauc_recall_at_1_diff1": 0.31501997480107374, + "nauc_recall_at_1_max": 0.09627316380324026, + "nauc_recall_at_1_std": -0.06409715408446262, + "nauc_recall_at_20_diff1": 0.05834476711289885, + "nauc_recall_at_20_max": 0.0741740249435682, + "nauc_recall_at_20_std": 0.01918762464215341, + "nauc_recall_at_3_diff1": 0.16417146591808887, + "nauc_recall_at_3_max": 0.07647824652081306, + "nauc_recall_at_3_std": 0.006254565823549643, + "nauc_recall_at_5_diff1": 0.10892964676931624, + "nauc_recall_at_5_max": 0.05585338568193677, + "nauc_recall_at_5_std": -0.006223709347632776, + "ndcg_at_1": 0.02405, + "ndcg_at_10": 0.04769, + "ndcg_at_100": 0.06955, + "ndcg_at_1000": 0.09933, + "ndcg_at_20": 0.05365, + "ndcg_at_3": 0.03744, + "ndcg_at_5": 0.04183, + "precision_at_1": 0.02405, + "precision_at_10": 0.00757, + "precision_at_100": 0.00189, + "precision_at_1000": 0.00044, + "precision_at_20": 0.00499, + "precision_at_3": 0.01569, + "precision_at_5": 0.01157, + "recall_at_1": 0.02405, + "recall_at_10": 0.07574, + "recall_at_100": 0.18884, + "recall_at_1000": 0.43705, + "recall_at_20": 0.0998, + "recall_at_3": 0.04708, + "recall_at_5": 0.05783 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/SpartQAInstruct.json b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/SpartQAInstruct.json new file mode 100644 index 000000000..e44c16809 --- /dev/null +++ b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/SpartQAInstruct.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 33.35317063331604, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07002, + "map_at_1": 0.01493, + "map_at_10": 0.04236, + "map_at_100": 0.05359, + "map_at_1000": 0.05491, + "map_at_20": 0.04877, + "map_at_3": 0.02739, + "map_at_5": 0.03446, + "mrr_at_1": 0.020868113522537562, + "mrr_at_10": 0.059926597238784136, + "mrr_at_100": 0.0728541738511466, + "mrr_at_1000": 0.07411910229386767, + "mrr_at_20": 0.06746897760500153, + "mrr_at_3": 0.038582823223891616, + "mrr_at_5": 0.04911426451493224, + "nauc_map_at_1000_diff1": -0.07571413278253834, + "nauc_map_at_1000_max": -0.057806573004504584, + "nauc_map_at_1000_std": 0.5965839095516873, + "nauc_map_at_100_diff1": -0.07613667710419034, + "nauc_map_at_100_max": -0.05597764182189667, + "nauc_map_at_100_std": 0.5933891618300428, + "nauc_map_at_10_diff1": -0.0965356367891366, + "nauc_map_at_10_max": -0.07358820307982668, + "nauc_map_at_10_std": 0.5878258478906763, + "nauc_map_at_1_diff1": -0.12039049625758898, + "nauc_map_at_1_max": -0.12890685649761913, + "nauc_map_at_1_std": 0.6439838714917643, + "nauc_map_at_20_diff1": -0.08898388203614704, + "nauc_map_at_20_max": -0.06484077179512043, + "nauc_map_at_20_std": 0.5931693898399234, + "nauc_map_at_3_diff1": -0.0782454773231606, + "nauc_map_at_3_max": -0.07524510939868727, + "nauc_map_at_3_std": 0.6227095837392824, + "nauc_map_at_5_diff1": -0.10261800391872314, + "nauc_map_at_5_max": -0.08012787100018975, + "nauc_map_at_5_std": 0.599438655585099, + "nauc_mrr_at_1000_diff1": -0.07042666964425377, + "nauc_mrr_at_1000_max": -0.06076887982045704, + "nauc_mrr_at_1000_std": 0.5571936998622518, + "nauc_mrr_at_100_diff1": -0.06999870151109583, + "nauc_mrr_at_100_max": -0.06020373470772566, + "nauc_mrr_at_100_std": 0.5553576289619075, + "nauc_mrr_at_10_diff1": -0.0948444724948587, + "nauc_mrr_at_10_max": -0.0843845013399704, + "nauc_mrr_at_10_std": 0.5618509721683385, + "nauc_mrr_at_1_diff1": -0.14552670672800674, + "nauc_mrr_at_1_max": -0.13778777533380046, + "nauc_mrr_at_1_std": 0.6295180280275989, + "nauc_mrr_at_20_diff1": -0.08279162409431519, + "nauc_mrr_at_20_max": -0.07193026709187246, + "nauc_mrr_at_20_std": 0.5589365960411181, + "nauc_mrr_at_3_diff1": -0.08855152724528602, + "nauc_mrr_at_3_max": -0.09259264783186423, + "nauc_mrr_at_3_std": 0.5892289127856827, + "nauc_mrr_at_5_diff1": -0.10925548897062733, + "nauc_mrr_at_5_max": -0.09657067471216468, + "nauc_mrr_at_5_std": 0.5729067658007578, + "nauc_ndcg_at_1000_diff1": -0.017022935239967188, + "nauc_ndcg_at_1000_max": -0.028280697484173455, + "nauc_ndcg_at_1000_std": 0.5900719186414247, + "nauc_ndcg_at_100_diff1": -0.02643173152570448, + "nauc_ndcg_at_100_max": -0.0042171048511313565, + "nauc_ndcg_at_100_std": 0.5662790895038647, + "nauc_ndcg_at_10_diff1": -0.09154802516019334, + "nauc_ndcg_at_10_max": -0.06399149230517791, + "nauc_ndcg_at_10_std": 0.5636659379873394, + "nauc_ndcg_at_1_diff1": -0.14552670672800674, + "nauc_ndcg_at_1_max": -0.13778777533380046, + "nauc_ndcg_at_1_std": 0.6295180280275989, + "nauc_ndcg_at_20_diff1": -0.07173950063155225, + "nauc_ndcg_at_20_max": -0.04084631786612581, + "nauc_ndcg_at_20_std": 0.5687735667150783, + "nauc_ndcg_at_3_diff1": -0.07375321238468104, + "nauc_ndcg_at_3_max": -0.06647637377500004, + "nauc_ndcg_at_3_std": 0.6118963897204542, + "nauc_ndcg_at_5_diff1": -0.10849011823683047, + "nauc_ndcg_at_5_max": -0.07614991056018874, + "nauc_ndcg_at_5_std": 0.5836870374305989, + "nauc_precision_at_1000_diff1": 0.08953940558242199, + "nauc_precision_at_1000_max": -0.0488480696762022, + "nauc_precision_at_1000_std": 0.17966529662924433, + "nauc_precision_at_100_diff1": 0.04472884948772196, + "nauc_precision_at_100_max": 0.009331376771144434, + "nauc_precision_at_100_std": 0.4191996794152265, + "nauc_precision_at_10_diff1": -0.07843854232010643, + "nauc_precision_at_10_max": -0.05959158527269603, + "nauc_precision_at_10_std": 0.521457629391506, + "nauc_precision_at_1_diff1": -0.14552670672800674, + "nauc_precision_at_1_max": -0.13778777533380046, + "nauc_precision_at_1_std": 0.6295180280275989, + "nauc_precision_at_20_diff1": -0.03774637465704378, + "nauc_precision_at_20_max": -0.028901284689887074, + "nauc_precision_at_20_std": 0.5207953572091886, + "nauc_precision_at_3_diff1": -0.06810721970976537, + "nauc_precision_at_3_max": -0.06256104536378346, + "nauc_precision_at_3_std": 0.5822397493386754, + "nauc_precision_at_5_diff1": -0.11797785219825865, + "nauc_precision_at_5_max": -0.08582752841000384, + "nauc_precision_at_5_std": 0.5550439508013425, + "nauc_recall_at_1000_diff1": 0.08716671128607187, + "nauc_recall_at_1000_max": 0.011102508213453984, + "nauc_recall_at_1000_std": 0.4427048573702621, + "nauc_recall_at_100_diff1": 0.026928250833784757, + "nauc_recall_at_100_max": 0.06950901565034709, + "nauc_recall_at_100_std": 0.496234584787019, + "nauc_recall_at_10_diff1": -0.08502006178680872, + "nauc_recall_at_10_max": -0.045085778454751826, + "nauc_recall_at_10_std": 0.5290306982610012, + "nauc_recall_at_1_diff1": -0.12039049625758898, + "nauc_recall_at_1_max": -0.12890685649761913, + "nauc_recall_at_1_std": 0.6439838714917643, + "nauc_recall_at_20_diff1": -0.05495795504530423, + "nauc_recall_at_20_max": -0.005976004711836337, + "nauc_recall_at_20_std": 0.5260771934243214, + "nauc_recall_at_3_diff1": -0.05989384664134088, + "nauc_recall_at_3_max": -0.03656799604924897, + "nauc_recall_at_3_std": 0.6191810620274676, + "nauc_recall_at_5_diff1": -0.11518141872861343, + "nauc_recall_at_5_max": -0.05819214858650267, + "nauc_recall_at_5_std": 0.5773215415972311, + "ndcg_at_1": 0.02087, + "ndcg_at_10": 0.07002, + "ndcg_at_100": 0.1285, + "ndcg_at_1000": 0.17133, + "ndcg_at_20": 0.09403, + "ndcg_at_3": 0.03536, + "ndcg_at_5": 0.04947, + "precision_at_1": 0.02087, + "precision_at_10": 0.02067, + "precision_at_100": 0.00632, + "precision_at_1000": 0.00118, + "precision_at_20": 0.01717, + "precision_at_3": 0.02272, + "precision_at_5": 0.02326, + "recall_at_1": 0.01493, + "recall_at_10": 0.13625, + "recall_at_100": 0.3798, + "recall_at_1000": 0.68985, + "recall_at_20": 0.22111, + "recall_at_3": 0.04814, + "recall_at_5": 0.07921 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL1Instruct.json b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL1Instruct.json new file mode 100644 index 000000000..c06b45a29 --- /dev/null +++ b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL1Instruct.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 14.804904222488403, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.00795, + "map_at_1": 0.0, + "map_at_10": 0.00412, + "map_at_100": 0.0076, + "map_at_1000": 0.00905, + "map_at_20": 0.00565, + "map_at_3": 0.00137, + "map_at_5": 0.00251, + "mrr_at_1": 0.0, + "mrr_at_10": 0.004121428571428569, + "mrr_at_100": 0.007600007418572877, + "mrr_at_1000": 0.009047256913788517, + "mrr_at_20": 0.0056545232169361425, + "mrr_at_3": 0.001375, + "mrr_at_5": 0.0025124999999999995, + "nauc_map_at_1000_diff1": 0.23523704713292073, + "nauc_map_at_1000_max": 0.46530692273647367, + "nauc_map_at_1000_std": 0.10881633250516534, + "nauc_map_at_100_diff1": 0.2519285671973511, + "nauc_map_at_100_max": 0.48414343072688115, + "nauc_map_at_100_std": 0.10683594593270962, + "nauc_map_at_10_diff1": 0.32848137166959873, + "nauc_map_at_10_max": 0.6058911112878159, + "nauc_map_at_10_std": 0.15421909749202645, + "nauc_map_at_1_diff1": NaN, + "nauc_map_at_1_max": NaN, + "nauc_map_at_1_std": NaN, + "nauc_map_at_20_diff1": 0.3138583755126235, + "nauc_map_at_20_max": 0.5726788731724103, + "nauc_map_at_20_std": 0.15748966000532072, + "nauc_map_at_3_diff1": 0.3207063931507184, + "nauc_map_at_3_max": 0.7128082542625069, + "nauc_map_at_3_std": 0.13461960631265693, + "nauc_map_at_5_diff1": 0.31647370873029523, + "nauc_map_at_5_max": 0.685743538812511, + "nauc_map_at_5_std": 0.15274045655810028, + "nauc_mrr_at_1000_diff1": 0.23523704713292073, + "nauc_mrr_at_1000_max": 0.46530692273647367, + "nauc_mrr_at_1000_std": 0.10881633250516534, + "nauc_mrr_at_100_diff1": 0.2519285671973511, + "nauc_mrr_at_100_max": 0.48414343072688115, + "nauc_mrr_at_100_std": 0.10683594593270962, + "nauc_mrr_at_10_diff1": 0.32848137166959873, + "nauc_mrr_at_10_max": 0.6058911112878159, + "nauc_mrr_at_10_std": 0.15421909749202645, + "nauc_mrr_at_1_diff1": NaN, + "nauc_mrr_at_1_max": NaN, + "nauc_mrr_at_1_std": NaN, + "nauc_mrr_at_20_diff1": 0.3138583755126235, + "nauc_mrr_at_20_max": 0.5726788731724103, + "nauc_mrr_at_20_std": 0.15748966000532072, + "nauc_mrr_at_3_diff1": 0.3207063931507184, + "nauc_mrr_at_3_max": 0.7128082542625069, + "nauc_mrr_at_3_std": 0.13461960631265693, + "nauc_mrr_at_5_diff1": 0.31647370873029523, + "nauc_mrr_at_5_max": 0.685743538812511, + "nauc_mrr_at_5_std": 0.15274045655810028, + "nauc_ndcg_at_1000_diff1": 0.11688744140554634, + "nauc_ndcg_at_1000_max": 0.3162005830756752, + "nauc_ndcg_at_1000_std": 0.09798852454636749, + "nauc_ndcg_at_100_diff1": 0.17326768121219416, + "nauc_ndcg_at_100_max": 0.35917595550682085, + "nauc_ndcg_at_100_std": 0.053904540086633035, + "nauc_ndcg_at_10_diff1": 0.32395736827688526, + "nauc_ndcg_at_10_max": 0.5745121272829092, + "nauc_ndcg_at_10_std": 0.15233336371155573, + "nauc_ndcg_at_1_diff1": NaN, + "nauc_ndcg_at_1_max": NaN, + "nauc_ndcg_at_1_std": NaN, + "nauc_ndcg_at_20_diff1": 0.30179178919836763, + "nauc_ndcg_at_20_max": 0.5321804421072197, + "nauc_ndcg_at_20_std": 0.15771271890074254, + "nauc_ndcg_at_3_diff1": 0.3330369457719168, + "nauc_ndcg_at_3_max": 0.7162397736761974, + "nauc_ndcg_at_3_std": 0.1325229039375958, + "nauc_ndcg_at_5_diff1": 0.3177795258633667, + "nauc_ndcg_at_5_max": 0.6788873362695379, + "nauc_ndcg_at_5_std": 0.15163285624979617, + "nauc_precision_at_1000_diff1": 0.06608141551966146, + "nauc_precision_at_1000_max": 0.26363371396659774, + "nauc_precision_at_1000_std": 0.11119561662366344, + "nauc_precision_at_100_diff1": 0.1345261711261173, + "nauc_precision_at_100_max": 0.30111809116350535, + "nauc_precision_at_100_std": 0.02765532775101824, + "nauc_precision_at_10_diff1": 0.31812896878633407, + "nauc_precision_at_10_max": 0.5470983939591398, + "nauc_precision_at_10_std": 0.15041460641138674, + "nauc_precision_at_1_diff1": NaN, + "nauc_precision_at_1_max": NaN, + "nauc_precision_at_1_std": NaN, + "nauc_precision_at_20_diff1": 0.2925472764749034, + "nauc_precision_at_20_max": 0.5054507724447906, + "nauc_precision_at_20_std": 0.15775833590530594, + "nauc_precision_at_3_diff1": 0.34901682701521713, + "nauc_precision_at_3_max": 0.7206868795277704, + "nauc_precision_at_3_std": 0.1298056652228909, + "nauc_precision_at_5_diff1": 0.3179658769866948, + "nauc_precision_at_5_max": 0.6706860903739011, + "nauc_precision_at_5_std": 0.15022333054498974, + "nauc_recall_at_1000_diff1": 0.06608141551966172, + "nauc_recall_at_1000_max": 0.26363371396659757, + "nauc_recall_at_1000_std": 0.11119561662366365, + "nauc_recall_at_100_diff1": 0.13452617112611706, + "nauc_recall_at_100_max": 0.3011180911635052, + "nauc_recall_at_100_std": 0.027655327751018206, + "nauc_recall_at_10_diff1": 0.318128968786334, + "nauc_recall_at_10_max": 0.54709839395914, + "nauc_recall_at_10_std": 0.15041460641138665, + "nauc_recall_at_1_diff1": NaN, + "nauc_recall_at_1_max": NaN, + "nauc_recall_at_1_std": NaN, + "nauc_recall_at_20_diff1": 0.2925472764749034, + "nauc_recall_at_20_max": 0.5054507724447904, + "nauc_recall_at_20_std": 0.1577583359053059, + "nauc_recall_at_3_diff1": 0.34901682701521697, + "nauc_recall_at_3_max": 0.7206868795277703, + "nauc_recall_at_3_std": 0.12980566522289091, + "nauc_recall_at_5_diff1": 0.3179658769866949, + "nauc_recall_at_5_max": 0.6706860903739013, + "nauc_recall_at_5_std": 0.15022333054498963, + "ndcg_at_1": 0.0, + "ndcg_at_10": 0.00795, + "ndcg_at_100": 0.02928, + "ndcg_at_1000": 0.08409, + "ndcg_at_20": 0.01356, + "ndcg_at_3": 0.00191, + "ndcg_at_5": 0.00397, + "precision_at_1": 0.0, + "precision_at_10": 0.0021, + "precision_at_100": 0.00131, + "precision_at_1000": 0.0006, + "precision_at_20": 0.00216, + "precision_at_3": 0.00117, + "precision_at_5": 0.0017, + "recall_at_1": 0.0, + "recall_at_10": 0.021, + "recall_at_100": 0.1315, + "recall_at_1000": 0.5995, + "recall_at_20": 0.04325, + "recall_at_3": 0.0035, + "recall_at_5": 0.0085 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL2FactInstruct.json b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL2FactInstruct.json new file mode 100644 index 000000000..ef782c7a9 --- /dev/null +++ b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL2FactInstruct.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 78.79260015487671, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.34992, + "map_at_1": 0.16713, + "map_at_10": 0.28378, + "map_at_100": 0.29439, + "map_at_1000": 0.29503, + "map_at_20": 0.29047, + "map_at_3": 0.24767, + "map_at_5": 0.26788, + "mrr_at_1": 0.16712988697424494, + "mrr_at_10": 0.28377765719344294, + "mrr_at_100": 0.2943911832210203, + "mrr_at_1000": 0.2950336046717147, + "mrr_at_20": 0.2904747333239796, + "mrr_at_3": 0.2476684577851888, + "mrr_at_5": 0.26788339200790573, + "nauc_map_at_1000_diff1": 0.05754261102583493, + "nauc_map_at_1000_max": 0.1379066943249642, + "nauc_map_at_1000_std": 0.061061124205636516, + "nauc_map_at_100_diff1": 0.057458294935249246, + "nauc_map_at_100_max": 0.13829711433753156, + "nauc_map_at_100_std": 0.061562535726683944, + "nauc_map_at_10_diff1": 0.05813960499692064, + "nauc_map_at_10_max": 0.13586058561264522, + "nauc_map_at_10_std": 0.055778451476223435, + "nauc_map_at_1_diff1": 0.07987224135681306, + "nauc_map_at_1_max": 0.07875532580507903, + "nauc_map_at_1_std": 0.013217851603506107, + "nauc_map_at_20_diff1": 0.05701074379643972, + "nauc_map_at_20_max": 0.1378383228617681, + "nauc_map_at_20_std": 0.06119318490530621, + "nauc_map_at_3_diff1": 0.06474569008716792, + "nauc_map_at_3_max": 0.11784987780835815, + "nauc_map_at_3_std": 0.03228718004741795, + "nauc_map_at_5_diff1": 0.05911019733188959, + "nauc_map_at_5_max": 0.1283537862447425, + "nauc_map_at_5_std": 0.04630876421253011, + "nauc_mrr_at_1000_diff1": 0.05754261102583493, + "nauc_mrr_at_1000_max": 0.1379066943249642, + "nauc_mrr_at_1000_std": 0.061061124205636516, + "nauc_mrr_at_100_diff1": 0.057458294935249246, + "nauc_mrr_at_100_max": 0.13829711433753156, + "nauc_mrr_at_100_std": 0.061562535726683944, + "nauc_mrr_at_10_diff1": 0.05813960499692064, + "nauc_mrr_at_10_max": 0.13586058561264522, + "nauc_mrr_at_10_std": 0.055778451476223435, + "nauc_mrr_at_1_diff1": 0.07987224135681306, + "nauc_mrr_at_1_max": 0.07875532580507903, + "nauc_mrr_at_1_std": 0.013217851603506107, + "nauc_mrr_at_20_diff1": 0.05701074379643972, + "nauc_mrr_at_20_max": 0.1378383228617681, + "nauc_mrr_at_20_std": 0.06119318490530621, + "nauc_mrr_at_3_diff1": 0.06474569008716792, + "nauc_mrr_at_3_max": 0.11784987780835815, + "nauc_mrr_at_3_std": 0.03228718004741795, + "nauc_mrr_at_5_diff1": 0.05911019733188959, + "nauc_mrr_at_5_max": 0.1283537862447425, + "nauc_mrr_at_5_std": 0.04630876421253011, + "nauc_ndcg_at_1000_diff1": 0.04938345246161239, + "nauc_ndcg_at_1000_max": 0.16734561860546798, + "nauc_ndcg_at_1000_std": 0.09418001285834739, + "nauc_ndcg_at_100_diff1": 0.04735771922671735, + "nauc_ndcg_at_100_max": 0.18012749274103598, + "nauc_ndcg_at_100_std": 0.10994736559222255, + "nauc_ndcg_at_10_diff1": 0.04940536366677268, + "nauc_ndcg_at_10_max": 0.1665392880825192, + "nauc_ndcg_at_10_std": 0.08505714429614859, + "nauc_ndcg_at_1_diff1": 0.07987224135681306, + "nauc_ndcg_at_1_max": 0.07875532580507903, + "nauc_ndcg_at_1_std": 0.013217851603506107, + "nauc_ndcg_at_20_diff1": 0.044659095031744075, + "nauc_ndcg_at_20_max": 0.17489529087517874, + "nauc_ndcg_at_20_std": 0.10558275356218719, + "nauc_ndcg_at_3_diff1": 0.06139029923982226, + "nauc_ndcg_at_3_max": 0.12952251663577533, + "nauc_ndcg_at_3_std": 0.037920393747902244, + "nauc_ndcg_at_5_diff1": 0.05205239271572126, + "nauc_ndcg_at_5_max": 0.14785274496946887, + "nauc_ndcg_at_5_std": 0.06201348560089073, + "nauc_precision_at_1000_diff1": -0.06485746214289448, + "nauc_precision_at_1000_max": 0.5365319218009642, + "nauc_precision_at_1000_std": 0.5237979806568346, + "nauc_precision_at_100_diff1": -0.0030507914972667948, + "nauc_precision_at_100_max": 0.4256025431190576, + "nauc_precision_at_100_std": 0.4032589353956031, + "nauc_precision_at_10_diff1": 0.024505600052074448, + "nauc_precision_at_10_max": 0.25736836531371926, + "nauc_precision_at_10_std": 0.17411838655112172, + "nauc_precision_at_1_diff1": 0.07987224135681306, + "nauc_precision_at_1_max": 0.07875532580507903, + "nauc_precision_at_1_std": 0.013217851603506107, + "nauc_precision_at_20_diff1": 0.00039711531239638564, + "nauc_precision_at_20_max": 0.3061136525644728, + "nauc_precision_at_20_std": 0.2719865427718515, + "nauc_precision_at_3_diff1": 0.05336065109387158, + "nauc_precision_at_3_max": 0.15841012789140727, + "nauc_precision_at_3_std": 0.05184727872121028, + "nauc_precision_at_5_diff1": 0.03409564198773103, + "nauc_precision_at_5_max": 0.1981289856446135, + "nauc_precision_at_5_std": 0.10337589006603906, + "nauc_recall_at_1000_diff1": -0.06485746214289274, + "nauc_recall_at_1000_max": 0.5365319218009621, + "nauc_recall_at_1000_std": 0.5237979806568335, + "nauc_recall_at_100_diff1": -0.0030507914972663776, + "nauc_recall_at_100_max": 0.4256025431190564, + "nauc_recall_at_100_std": 0.40325893539560265, + "nauc_recall_at_10_diff1": 0.024505600052074597, + "nauc_recall_at_10_max": 0.2573683653137194, + "nauc_recall_at_10_std": 0.17411838655112147, + "nauc_recall_at_1_diff1": 0.07987224135681306, + "nauc_recall_at_1_max": 0.07875532580507903, + "nauc_recall_at_1_std": 0.013217851603506107, + "nauc_recall_at_20_diff1": 0.00039711531239609773, + "nauc_recall_at_20_max": 0.30611365256447204, + "nauc_recall_at_20_std": 0.2719865427718518, + "nauc_recall_at_3_diff1": 0.05336065109387145, + "nauc_recall_at_3_max": 0.15841012789140743, + "nauc_recall_at_3_std": 0.05184727872121034, + "nauc_recall_at_5_diff1": 0.03409564198773111, + "nauc_recall_at_5_max": 0.1981289856446134, + "nauc_recall_at_5_std": 0.10337589006603894, + "ndcg_at_1": 0.16713, + "ndcg_at_10": 0.34992, + "ndcg_at_100": 0.40258, + "ndcg_at_1000": 0.42072, + "ndcg_at_20": 0.37399, + "ndcg_at_3": 0.27505, + "ndcg_at_5": 0.31147, + "precision_at_1": 0.16713, + "precision_at_10": 0.05618, + "precision_at_100": 0.00811, + "precision_at_1000": 0.00096, + "precision_at_20": 0.03281, + "precision_at_3": 0.11821, + "precision_at_5": 0.0886, + "recall_at_1": 0.16713, + "recall_at_10": 0.56179, + "recall_at_100": 0.81101, + "recall_at_1000": 0.95627, + "recall_at_20": 0.65629, + "recall_at_3": 0.35464, + "recall_at_5": 0.44302 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL2PureInstruct.json b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL2PureInstruct.json new file mode 100644 index 000000000..8efed64f2 --- /dev/null +++ b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL2PureInstruct.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 23.489399909973145, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.00623, + "map_at_1": 0.0013, + "map_at_10": 0.00405, + "map_at_100": 0.00616, + "map_at_1000": 0.00722, + "map_at_20": 0.00479, + "map_at_3": 0.00259, + "map_at_5": 0.00329, + "mrr_at_1": 0.0012970168612191958, + "mrr_at_10": 0.004047810217904713, + "mrr_at_100": 0.00615697585853246, + "mrr_at_1000": 0.007216557601289494, + "mrr_at_20": 0.004789436045577657, + "mrr_at_3": 0.002594033722438391, + "mrr_at_5": 0.003288864183805817, + "nauc_map_at_1000_diff1": 0.032119274538086, + "nauc_map_at_1000_max": 0.051406586601622645, + "nauc_map_at_1000_std": 0.18023579872342094, + "nauc_map_at_100_diff1": 0.041153871155147626, + "nauc_map_at_100_max": 0.06005382731465371, + "nauc_map_at_100_std": 0.18418658976479216, + "nauc_map_at_10_diff1": 0.06377065220630145, + "nauc_map_at_10_max": 0.07755904491831926, + "nauc_map_at_10_std": 0.23103966021616892, + "nauc_map_at_1_diff1": -0.05550403397771144, + "nauc_map_at_1_max": 0.0057651144163855085, + "nauc_map_at_1_std": 0.27945489619456015, + "nauc_map_at_20_diff1": 0.06312738982726745, + "nauc_map_at_20_max": 0.08961704934380994, + "nauc_map_at_20_std": 0.20738384770245447, + "nauc_map_at_3_diff1": 0.09978851758136983, + "nauc_map_at_3_max": 0.11459295911030822, + "nauc_map_at_3_std": 0.23307404011031044, + "nauc_map_at_5_diff1": 0.09556638613168444, + "nauc_map_at_5_max": 0.09699213514786982, + "nauc_map_at_5_std": 0.21372754653819315, + "nauc_mrr_at_1000_diff1": 0.03211927819724293, + "nauc_mrr_at_1000_max": 0.051406590310253124, + "nauc_mrr_at_1000_std": 0.18023582324230236, + "nauc_mrr_at_100_diff1": 0.041153871155147626, + "nauc_mrr_at_100_max": 0.06005382731465371, + "nauc_mrr_at_100_std": 0.18418658976479216, + "nauc_mrr_at_10_diff1": 0.06377065220630145, + "nauc_mrr_at_10_max": 0.07755904491831926, + "nauc_mrr_at_10_std": 0.23103966021616892, + "nauc_mrr_at_1_diff1": -0.05550403397771144, + "nauc_mrr_at_1_max": 0.0057651144163855085, + "nauc_mrr_at_1_std": 0.27945489619456015, + "nauc_mrr_at_20_diff1": 0.06312738982726745, + "nauc_mrr_at_20_max": 0.08961704934380994, + "nauc_mrr_at_20_std": 0.20738384770245447, + "nauc_mrr_at_3_diff1": 0.09978851758136983, + "nauc_mrr_at_3_max": 0.11459295911030822, + "nauc_mrr_at_3_std": 0.23307404011031044, + "nauc_mrr_at_5_diff1": 0.09556638613168444, + "nauc_mrr_at_5_max": 0.09699213514786982, + "nauc_mrr_at_5_std": 0.21372754653819315, + "nauc_ndcg_at_1000_diff1": -0.04306158746340035, + "nauc_ndcg_at_1000_max": -0.02635336495216523, + "nauc_ndcg_at_1000_std": 0.14207125616410837, + "nauc_ndcg_at_100_diff1": 0.00378459016773017, + "nauc_ndcg_at_100_max": 0.014384917964949475, + "nauc_ndcg_at_100_std": 0.13712946464662992, + "nauc_ndcg_at_10_diff1": 0.052448821685661236, + "nauc_ndcg_at_10_max": 0.07291944137475664, + "nauc_ndcg_at_10_std": 0.2367339839739525, + "nauc_ndcg_at_1_diff1": -0.05550403397771144, + "nauc_ndcg_at_1_max": 0.0057651144163855085, + "nauc_ndcg_at_1_std": 0.27945489619456015, + "nauc_ndcg_at_20_diff1": 0.051907675948530956, + "nauc_ndcg_at_20_max": 0.09612357360826118, + "nauc_ndcg_at_20_std": 0.18866912160701643, + "nauc_ndcg_at_3_diff1": 0.11081260247645235, + "nauc_ndcg_at_3_max": 0.1288132202229761, + "nauc_ndcg_at_3_std": 0.22832110941083503, + "nauc_ndcg_at_5_diff1": 0.10613028565774416, + "nauc_ndcg_at_5_max": 0.10375811381521799, + "nauc_ndcg_at_5_std": 0.20619247293579776, + "nauc_precision_at_1000_diff1": -0.07185741412080332, + "nauc_precision_at_1000_max": -0.05680944899076427, + "nauc_precision_at_1000_std": 0.13754394082387747, + "nauc_precision_at_100_diff1": -0.01254826274928649, + "nauc_precision_at_100_max": -0.00931700645396415, + "nauc_precision_at_100_std": 0.11594489745376155, + "nauc_precision_at_10_diff1": 0.03674464598077104, + "nauc_precision_at_10_max": 0.06630368722054343, + "nauc_precision_at_10_std": 0.24542610248359756, + "nauc_precision_at_1_diff1": -0.05550403397771144, + "nauc_precision_at_1_max": 0.0057651144163855085, + "nauc_precision_at_1_std": 0.27945489619456015, + "nauc_precision_at_20_diff1": 0.040738131406999056, + "nauc_precision_at_20_max": 0.10176279669837035, + "nauc_precision_at_20_std": 0.17146583363061824, + "nauc_precision_at_3_diff1": 0.12719472361291928, + "nauc_precision_at_3_max": 0.15260271098771022, + "nauc_precision_at_3_std": 0.22066048749897405, + "nauc_precision_at_5_diff1": 0.11950395722400198, + "nauc_precision_at_5_max": 0.11201474709572974, + "nauc_precision_at_5_std": 0.19695961482065794, + "nauc_recall_at_1000_diff1": -0.07185741412080254, + "nauc_recall_at_1000_max": -0.05680944899076335, + "nauc_recall_at_1000_std": 0.13754394082387783, + "nauc_recall_at_100_diff1": -0.012548262749286734, + "nauc_recall_at_100_max": -0.009317006453964402, + "nauc_recall_at_100_std": 0.11594489745376141, + "nauc_recall_at_10_diff1": 0.036744645980770804, + "nauc_recall_at_10_max": 0.06630368722054314, + "nauc_recall_at_10_std": 0.245426102483597, + "nauc_recall_at_1_diff1": -0.05550403397771144, + "nauc_recall_at_1_max": 0.0057651144163855085, + "nauc_recall_at_1_std": 0.27945489619456015, + "nauc_recall_at_20_diff1": 0.04073813140699871, + "nauc_recall_at_20_max": 0.10176279669836999, + "nauc_recall_at_20_std": 0.17146583363061807, + "nauc_recall_at_3_diff1": 0.1271947236129192, + "nauc_recall_at_3_max": 0.1526027109877103, + "nauc_recall_at_3_std": 0.22066048749897393, + "nauc_recall_at_5_diff1": 0.11950395722400174, + "nauc_recall_at_5_max": 0.11201474709572976, + "nauc_recall_at_5_std": 0.196959614820658, + "ndcg_at_1": 0.0013, + "ndcg_at_10": 0.00623, + "ndcg_at_100": 0.02057, + "ndcg_at_1000": 0.06179, + "ndcg_at_20": 0.00894, + "ndcg_at_3": 0.00307, + "ndcg_at_5": 0.00434, + "precision_at_1": 0.0013, + "precision_at_10": 0.00135, + "precision_at_100": 0.00091, + "precision_at_1000": 0.00044, + "precision_at_20": 0.00121, + "precision_at_3": 0.00148, + "precision_at_5": 0.00152, + "recall_at_1": 0.0013, + "recall_at_10": 0.01353, + "recall_at_100": 0.09061, + "recall_at_1000": 0.44432, + "recall_at_20": 0.02427, + "recall_at_3": 0.00445, + "recall_at_5": 0.0076 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL3FactInstruct.json b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL3FactInstruct.json new file mode 100644 index 000000000..a6a6d48ad --- /dev/null +++ b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL3FactInstruct.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 72.0484368801117, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.32467, + "map_at_1": 0.12811, + "map_at_10": 0.25385, + "map_at_100": 0.26415, + "map_at_1000": 0.26475, + "map_at_20": 0.2602, + "map_at_3": 0.21393, + "map_at_5": 0.23829, + "mrr_at_1": 0.1281066425666516, + "mrr_at_10": 0.2538534023339724, + "mrr_at_100": 0.26414683054604854, + "mrr_at_1000": 0.26475085503212975, + "mrr_at_20": 0.2601992871015358, + "mrr_at_3": 0.21392528995330742, + "mrr_at_5": 0.23829266455791748, + "nauc_map_at_1000_diff1": 0.05827494847668488, + "nauc_map_at_1000_max": 0.151581743718594, + "nauc_map_at_1000_std": 0.06863880078484748, + "nauc_map_at_100_diff1": 0.05801399433154969, + "nauc_map_at_100_max": 0.1519501799978567, + "nauc_map_at_100_std": 0.06917641899575612, + "nauc_map_at_10_diff1": 0.05770772103906597, + "nauc_map_at_10_max": 0.14829338699475822, + "nauc_map_at_10_std": 0.06491399624332157, + "nauc_map_at_1_diff1": 0.096483925298403, + "nauc_map_at_1_max": 0.06098161431830515, + "nauc_map_at_1_std": -0.037034379878766566, + "nauc_map_at_20_diff1": 0.05753071943790574, + "nauc_map_at_20_max": 0.15192398825424244, + "nauc_map_at_20_std": 0.07011306234983397, + "nauc_map_at_3_diff1": 0.07556139796416698, + "nauc_map_at_3_max": 0.12354638050961639, + "nauc_map_at_3_std": 0.022558096176447266, + "nauc_map_at_5_diff1": 0.06144327551675631, + "nauc_map_at_5_max": 0.14009280888496267, + "nauc_map_at_5_std": 0.0465708669362906, + "nauc_mrr_at_1000_diff1": 0.058274946778575344, + "nauc_mrr_at_1000_max": 0.1515817442825963, + "nauc_mrr_at_1000_std": 0.06863880256985665, + "nauc_mrr_at_100_diff1": 0.05801399433154969, + "nauc_mrr_at_100_max": 0.1519501799978567, + "nauc_mrr_at_100_std": 0.06917641899575612, + "nauc_mrr_at_10_diff1": 0.05770772103906597, + "nauc_mrr_at_10_max": 0.14829338699475822, + "nauc_mrr_at_10_std": 0.06491399624332157, + "nauc_mrr_at_1_diff1": 0.096483925298403, + "nauc_mrr_at_1_max": 0.06098161431830515, + "nauc_mrr_at_1_std": -0.037034379878766566, + "nauc_mrr_at_20_diff1": 0.05753071943790574, + "nauc_mrr_at_20_max": 0.15192398825424244, + "nauc_mrr_at_20_std": 0.07011306234983397, + "nauc_mrr_at_3_diff1": 0.07556139796416698, + "nauc_mrr_at_3_max": 0.12354638050961639, + "nauc_mrr_at_3_std": 0.022558096176447266, + "nauc_mrr_at_5_diff1": 0.06144327551675631, + "nauc_mrr_at_5_max": 0.14009280888496267, + "nauc_mrr_at_5_std": 0.0465708669362906, + "nauc_ndcg_at_1000_diff1": 0.04462782938898856, + "nauc_ndcg_at_1000_max": 0.19067172776189523, + "nauc_ndcg_at_1000_std": 0.11854655181150194, + "nauc_ndcg_at_100_diff1": 0.03819656819771063, + "nauc_ndcg_at_100_max": 0.20228384654614595, + "nauc_ndcg_at_100_std": 0.13505113564342677, + "nauc_ndcg_at_10_diff1": 0.03841801277989221, + "nauc_ndcg_at_10_max": 0.1872014132917956, + "nauc_ndcg_at_10_std": 0.11991514674175344, + "nauc_ndcg_at_1_diff1": 0.096483925298403, + "nauc_ndcg_at_1_max": 0.06098161431830515, + "nauc_ndcg_at_1_std": -0.037034379878766566, + "nauc_ndcg_at_20_diff1": 0.03736408859128836, + "nauc_ndcg_at_20_max": 0.2015517726002749, + "nauc_ndcg_at_20_std": 0.13941861038614667, + "nauc_ndcg_at_3_diff1": 0.06950148761378382, + "nauc_ndcg_at_3_max": 0.139903093845982, + "nauc_ndcg_at_3_std": 0.03841086385519972, + "nauc_ndcg_at_5_diff1": 0.046048169155940115, + "nauc_ndcg_at_5_max": 0.16765685954475157, + "nauc_ndcg_at_5_std": 0.07869720723340304, + "nauc_precision_at_1000_diff1": -0.043451362467466954, + "nauc_precision_at_1000_max": 0.5521422600062844, + "nauc_precision_at_1000_std": 0.5395174696772156, + "nauc_precision_at_100_diff1": -0.052610445048008055, + "nauc_precision_at_100_max": 0.44001331438687497, + "nauc_precision_at_100_std": 0.4418571938439194, + "nauc_precision_at_10_diff1": -0.011886036147818439, + "nauc_precision_at_10_max": 0.29025287959117746, + "nauc_precision_at_10_std": 0.26876432667330125, + "nauc_precision_at_1_diff1": 0.096483925298403, + "nauc_precision_at_1_max": 0.06098161431830515, + "nauc_precision_at_1_std": -0.037034379878766566, + "nauc_precision_at_20_diff1": -0.022270170929447344, + "nauc_precision_at_20_max": 0.3588891298806521, + "nauc_precision_at_20_std": 0.36127301332102885, + "nauc_precision_at_3_diff1": 0.05556178938906479, + "nauc_precision_at_3_max": 0.17717138966701557, + "nauc_precision_at_3_std": 0.07459220969769871, + "nauc_precision_at_5_diff1": 0.008952905690535501, + "nauc_precision_at_5_max": 0.23260267566578244, + "nauc_precision_at_5_std": 0.15527274557797002, + "nauc_recall_at_1000_diff1": -0.043451362467472436, + "nauc_recall_at_1000_max": 0.552142260006282, + "nauc_recall_at_1000_std": 0.53951746967721, + "nauc_recall_at_100_diff1": -0.05261044504800674, + "nauc_recall_at_100_max": 0.4400133143868747, + "nauc_recall_at_100_std": 0.44185719384392047, + "nauc_recall_at_10_diff1": -0.011886036147818939, + "nauc_recall_at_10_max": 0.29025287959117735, + "nauc_recall_at_10_std": 0.26876432667330136, + "nauc_recall_at_1_diff1": 0.096483925298403, + "nauc_recall_at_1_max": 0.06098161431830515, + "nauc_recall_at_1_std": -0.037034379878766566, + "nauc_recall_at_20_diff1": -0.02227017092944802, + "nauc_recall_at_20_max": 0.3588891298806519, + "nauc_recall_at_20_std": 0.3612730133210281, + "nauc_recall_at_3_diff1": 0.055561789389064836, + "nauc_recall_at_3_max": 0.1771713896670159, + "nauc_recall_at_3_std": 0.07459220969769899, + "nauc_recall_at_5_diff1": 0.008952905690535279, + "nauc_recall_at_5_max": 0.23260267566578208, + "nauc_recall_at_5_std": 0.1552727455779698, + "ndcg_at_1": 0.12811, + "ndcg_at_10": 0.32467, + "ndcg_at_100": 0.37629, + "ndcg_at_1000": 0.39411, + "ndcg_at_20": 0.34765, + "ndcg_at_3": 0.2433, + "ndcg_at_5": 0.28727, + "precision_at_1": 0.12811, + "precision_at_10": 0.05506, + "precision_at_100": 0.00796, + "precision_at_1000": 0.00094, + "precision_at_20": 0.03206, + "precision_at_3": 0.10958, + "precision_at_5": 0.08712, + "recall_at_1": 0.12811, + "recall_at_10": 0.55061, + "recall_at_100": 0.79575, + "recall_at_1000": 0.93945, + "recall_at_20": 0.64121, + "recall_at_3": 0.32874, + "recall_at_5": 0.43561 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL3PureInstruct.json b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL3PureInstruct.json new file mode 100644 index 000000000..04ad777b9 --- /dev/null +++ b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL3PureInstruct.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 21.688836574554443, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07014, + "map_at_1": 0.00113, + "map_at_10": 0.04419, + "map_at_100": 0.04979, + "map_at_1000": 0.05095, + "map_at_20": 0.04701, + "map_at_3": 0.02881, + "map_at_5": 0.03778, + "mrr_at_1": 0.0011296882060551287, + "mrr_at_10": 0.04418676794411086, + "mrr_at_100": 0.0497932575129137, + "mrr_at_1000": 0.050948666854623105, + "mrr_at_20": 0.04701146575127057, + "mrr_at_3": 0.028807049254405723, + "mrr_at_5": 0.037776773610483504, + "nauc_map_at_1000_diff1": -0.07298362580528965, + "nauc_map_at_1000_max": 0.382280220408855, + "nauc_map_at_1000_std": 0.649667212169248, + "nauc_map_at_100_diff1": -0.07242850024032427, + "nauc_map_at_100_max": 0.3837877460609165, + "nauc_map_at_100_std": 0.6518624214229349, + "nauc_map_at_10_diff1": -0.07419896439057112, + "nauc_map_at_10_max": 0.3905848459660377, + "nauc_map_at_10_std": 0.658749693252962, + "nauc_map_at_1_diff1": -0.3462469008459133, + "nauc_map_at_1_max": -0.03902115875453853, + "nauc_map_at_1_std": 0.46601217638978787, + "nauc_map_at_20_diff1": -0.07347465188227344, + "nauc_map_at_20_max": 0.387624491988462, + "nauc_map_at_20_std": 0.6591982174793058, + "nauc_map_at_3_diff1": -0.05039986608018414, + "nauc_map_at_3_max": 0.35162060512750615, + "nauc_map_at_3_std": 0.6033672116248089, + "nauc_map_at_5_diff1": -0.0645617274452381, + "nauc_map_at_5_max": 0.37916977053963424, + "nauc_map_at_5_std": 0.6373740544245619, + "nauc_mrr_at_1000_diff1": -0.07298362580528965, + "nauc_mrr_at_1000_max": 0.382280220408855, + "nauc_mrr_at_1000_std": 0.649667212169248, + "nauc_mrr_at_100_diff1": -0.07242850024032427, + "nauc_mrr_at_100_max": 0.3837877460609165, + "nauc_mrr_at_100_std": 0.6518624214229349, + "nauc_mrr_at_10_diff1": -0.07419896439057112, + "nauc_mrr_at_10_max": 0.3905848459660377, + "nauc_mrr_at_10_std": 0.658749693252962, + "nauc_mrr_at_1_diff1": -0.3462469008459133, + "nauc_mrr_at_1_max": -0.03902115875453853, + "nauc_mrr_at_1_std": 0.46601217638978787, + "nauc_mrr_at_20_diff1": -0.07347465188227344, + "nauc_mrr_at_20_max": 0.387624491988462, + "nauc_mrr_at_20_std": 0.6591982174793058, + "nauc_mrr_at_3_diff1": -0.05039986608018414, + "nauc_mrr_at_3_max": 0.35162060512750615, + "nauc_mrr_at_3_std": 0.6033672116248089, + "nauc_mrr_at_5_diff1": -0.0645617274452381, + "nauc_mrr_at_5_max": 0.37916977053963424, + "nauc_mrr_at_5_std": 0.6373740544245619, + "nauc_ndcg_at_1000_diff1": -0.08454248126597252, + "nauc_ndcg_at_1000_max": 0.35297133649850904, + "nauc_ndcg_at_1000_std": 0.603900285047838, + "nauc_ndcg_at_100_diff1": -0.07314115699856477, + "nauc_ndcg_at_100_max": 0.3738576383708661, + "nauc_ndcg_at_100_std": 0.6362748050902535, + "nauc_ndcg_at_10_diff1": -0.08021160572836324, + "nauc_ndcg_at_10_max": 0.4059073203658881, + "nauc_ndcg_at_10_std": 0.6792492440453695, + "nauc_ndcg_at_1_diff1": -0.3462469008459133, + "nauc_ndcg_at_1_max": -0.03902115875453853, + "nauc_ndcg_at_1_std": 0.46601217638978787, + "nauc_ndcg_at_20_diff1": -0.07725567050126181, + "nauc_ndcg_at_20_max": 0.3977133803842578, + "nauc_ndcg_at_20_std": 0.6776127448895999, + "nauc_ndcg_at_3_diff1": -0.04970165848713881, + "nauc_ndcg_at_3_max": 0.35719794298372654, + "nauc_ndcg_at_3_std": 0.6085058214012575, + "nauc_ndcg_at_5_diff1": -0.06774677139602117, + "nauc_ndcg_at_5_max": 0.3906293479333123, + "nauc_ndcg_at_5_std": 0.6504792184755727, + "nauc_precision_at_1000_diff1": -0.11364966792165691, + "nauc_precision_at_1000_max": 0.2740690674964775, + "nauc_precision_at_1000_std": 0.4797716020727521, + "nauc_precision_at_100_diff1": -0.07127154208749836, + "nauc_precision_at_100_max": 0.3488489329512223, + "nauc_precision_at_100_std": 0.597997620053613, + "nauc_precision_at_10_diff1": -0.08719199398788134, + "nauc_precision_at_10_max": 0.42286624940147943, + "nauc_precision_at_10_std": 0.7024033578303032, + "nauc_precision_at_1_diff1": -0.3462469008459133, + "nauc_precision_at_1_max": -0.03902115875453853, + "nauc_precision_at_1_std": 0.46601217638978787, + "nauc_precision_at_20_diff1": -0.08024396359400346, + "nauc_precision_at_20_max": 0.4057313595988548, + "nauc_precision_at_20_std": 0.6950380804344024, + "nauc_precision_at_3_diff1": -0.04921013202536246, + "nauc_precision_at_3_max": 0.3644319315327231, + "nauc_precision_at_3_std": 0.6155439466026964, + "nauc_precision_at_5_diff1": -0.07225110245386675, + "nauc_precision_at_5_max": 0.40460023043466714, + "nauc_precision_at_5_std": 0.666934457297114, + "nauc_recall_at_1000_diff1": -0.11364966792165758, + "nauc_recall_at_1000_max": 0.2740690674964765, + "nauc_recall_at_1000_std": 0.4797716020727518, + "nauc_recall_at_100_diff1": -0.07127154208749828, + "nauc_recall_at_100_max": 0.34884893295122216, + "nauc_recall_at_100_std": 0.5979976200536128, + "nauc_recall_at_10_diff1": -0.08719199398788162, + "nauc_recall_at_10_max": 0.4228662494014793, + "nauc_recall_at_10_std": 0.7024033578303033, + "nauc_recall_at_1_diff1": -0.3462469008459133, + "nauc_recall_at_1_max": -0.03902115875453853, + "nauc_recall_at_1_std": 0.46601217638978787, + "nauc_recall_at_20_diff1": -0.08024396359400358, + "nauc_recall_at_20_max": 0.40573135959885465, + "nauc_recall_at_20_std": 0.6950380804344022, + "nauc_recall_at_3_diff1": -0.04921013202536223, + "nauc_recall_at_3_max": 0.364431931532723, + "nauc_recall_at_3_std": 0.6155439466026962, + "nauc_recall_at_5_diff1": -0.07225110245386669, + "nauc_recall_at_5_max": 0.4046002304346667, + "nauc_recall_at_5_std": 0.6669344572971139, + "ndcg_at_1": 0.00113, + "ndcg_at_10": 0.07014, + "ndcg_at_100": 0.10213, + "ndcg_at_1000": 0.14139, + "ndcg_at_20": 0.08061, + "ndcg_at_3": 0.03858, + "ndcg_at_5": 0.05476, + "precision_at_1": 0.00113, + "precision_at_10": 0.01536, + "precision_at_100": 0.00315, + "precision_at_1000": 0.00064, + "precision_at_20": 0.00977, + "precision_at_3": 0.02237, + "precision_at_5": 0.02128, + "recall_at_1": 0.00113, + "recall_at_10": 0.15364, + "recall_at_100": 0.31451, + "recall_at_1000": 0.64234, + "recall_at_20": 0.19544, + "recall_at_3": 0.0671, + "recall_at_5": 0.10642 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/WinoGrandeInstruct.json b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/WinoGrandeInstruct.json new file mode 100644 index 000000000..7bd11546a --- /dev/null +++ b/results/bge-m3-instruct/5617a9f61b028005a4858fdac845db406aefb181/WinoGrandeInstruct.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 6.34290885925293, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.35331, + "map_at_1": 0.1468, + "map_at_10": 0.27493, + "map_at_100": 0.29055, + "map_at_1000": 0.29093, + "map_at_20": 0.28559, + "map_at_3": 0.22836, + "map_at_5": 0.25259, + "mrr_at_1": 0.1468034727703236, + "mrr_at_10": 0.2749339146339935, + "mrr_at_100": 0.2905472256374475, + "mrr_at_1000": 0.29092667692823254, + "mrr_at_20": 0.28558725100661814, + "mrr_at_3": 0.22836095764272576, + "mrr_at_5": 0.25259142330965506, + "nauc_map_at_1000_diff1": 0.13445215938392557, + "nauc_map_at_1000_max": 0.026625961987701653, + "nauc_map_at_1000_std": -0.04475140345099324, + "nauc_map_at_100_diff1": 0.13440256557487867, + "nauc_map_at_100_max": 0.026429931479190028, + "nauc_map_at_100_std": -0.044838064866869164, + "nauc_map_at_10_diff1": 0.13076439295279574, + "nauc_map_at_10_max": 0.024945749439268534, + "nauc_map_at_10_std": -0.047301694638962236, + "nauc_map_at_1_diff1": 0.18640954787216782, + "nauc_map_at_1_max": 0.041213744493062865, + "nauc_map_at_1_std": -0.04047659161524531, + "nauc_map_at_20_diff1": 0.1349820453331751, + "nauc_map_at_20_max": 0.026767349215579096, + "nauc_map_at_20_std": -0.046386464725917655, + "nauc_map_at_3_diff1": 0.14021009240158797, + "nauc_map_at_3_max": 0.03956977778650356, + "nauc_map_at_3_std": -0.038080498419861414, + "nauc_map_at_5_diff1": 0.12582079466911375, + "nauc_map_at_5_max": 0.02306275462941085, + "nauc_map_at_5_std": -0.049009584203765784, + "nauc_mrr_at_1000_diff1": 0.13445215938392557, + "nauc_mrr_at_1000_max": 0.026625961987701653, + "nauc_mrr_at_1000_std": -0.04475140345099324, + "nauc_mrr_at_100_diff1": 0.13440256557487867, + "nauc_mrr_at_100_max": 0.026429931479190028, + "nauc_mrr_at_100_std": -0.044838064866869164, + "nauc_mrr_at_10_diff1": 0.13076439295279574, + "nauc_mrr_at_10_max": 0.024945749439268534, + "nauc_mrr_at_10_std": -0.047301694638962236, + "nauc_mrr_at_1_diff1": 0.18640954787216782, + "nauc_mrr_at_1_max": 0.041213744493062865, + "nauc_mrr_at_1_std": -0.04047659161524531, + "nauc_mrr_at_20_diff1": 0.1349820453331751, + "nauc_mrr_at_20_max": 0.026767349215579096, + "nauc_mrr_at_20_std": -0.046386464725917655, + "nauc_mrr_at_3_diff1": 0.14021009240158797, + "nauc_mrr_at_3_max": 0.03956977778650356, + "nauc_mrr_at_3_std": -0.038080498419861414, + "nauc_mrr_at_5_diff1": 0.12582079466911375, + "nauc_mrr_at_5_max": 0.02306275462941085, + "nauc_mrr_at_5_std": -0.049009584203765784, + "nauc_ndcg_at_1000_diff1": 0.12750925546854402, + "nauc_ndcg_at_1000_max": 0.02164131545083465, + "nauc_ndcg_at_1000_std": -0.044984206202755735, + "nauc_ndcg_at_100_diff1": 0.12513241265369277, + "nauc_ndcg_at_100_max": 0.016133258293475592, + "nauc_ndcg_at_100_std": -0.04580424046652768, + "nauc_ndcg_at_10_diff1": 0.11436877610837674, + "nauc_ndcg_at_10_max": 0.014618029130867929, + "nauc_ndcg_at_10_std": -0.05361577865266892, + "nauc_ndcg_at_1_diff1": 0.18640954787216782, + "nauc_ndcg_at_1_max": 0.041213744493062865, + "nauc_ndcg_at_1_std": -0.04047659161524531, + "nauc_ndcg_at_20_diff1": 0.1290578914692648, + "nauc_ndcg_at_20_max": 0.02082993481231252, + "nauc_ndcg_at_20_std": -0.05010624086119338, + "nauc_ndcg_at_3_diff1": 0.12810097209207194, + "nauc_ndcg_at_3_max": 0.03698784312753865, + "nauc_ndcg_at_3_std": -0.0393866179239746, + "nauc_ndcg_at_5_diff1": 0.10419282119243839, + "nauc_ndcg_at_5_max": 0.009685644703470591, + "nauc_ndcg_at_5_std": -0.05778700146341584, + "nauc_precision_at_1000_diff1": 0.122587549864487, + "nauc_precision_at_1000_max": 0.3580675238444718, + "nauc_precision_at_1000_std": 0.3580675238444718, + "nauc_precision_at_100_diff1": 0.048175295993667086, + "nauc_precision_at_100_max": -0.13820804733456732, + "nauc_precision_at_100_std": -0.05381583079108475, + "nauc_precision_at_10_diff1": 0.07189998150747738, + "nauc_precision_at_10_max": -0.01332437457350223, + "nauc_precision_at_10_std": -0.07095975090836182, + "nauc_precision_at_1_diff1": 0.18640954787216782, + "nauc_precision_at_1_max": 0.041213744493062865, + "nauc_precision_at_1_std": -0.04047659161524531, + "nauc_precision_at_20_diff1": 0.12589497895356644, + "nauc_precision_at_20_max": 0.005403026564419423, + "nauc_precision_at_20_std": -0.060037263137292435, + "nauc_precision_at_3_diff1": 0.09953910767898456, + "nauc_precision_at_3_max": 0.030368042123013292, + "nauc_precision_at_3_std": -0.04294372678448787, + "nauc_precision_at_5_diff1": 0.05118708964072995, + "nauc_precision_at_5_max": -0.02479163023557208, + "nauc_precision_at_5_std": -0.08077472084749951, + "nauc_recall_at_1000_diff1": 0.12258754986412868, + "nauc_recall_at_1000_max": 0.35806752384437546, + "nauc_recall_at_1000_std": 0.35806752384437546, + "nauc_recall_at_100_diff1": 0.04817529599366618, + "nauc_recall_at_100_max": -0.1382080473345659, + "nauc_recall_at_100_std": -0.05381583079108228, + "nauc_recall_at_10_diff1": 0.07189998150747734, + "nauc_recall_at_10_max": -0.013324374573502547, + "nauc_recall_at_10_std": -0.07095975090836178, + "nauc_recall_at_1_diff1": 0.18640954787216782, + "nauc_recall_at_1_max": 0.041213744493062865, + "nauc_recall_at_1_std": -0.04047659161524531, + "nauc_recall_at_20_diff1": 0.12589497895356702, + "nauc_recall_at_20_max": 0.005403026564419723, + "nauc_recall_at_20_std": -0.06003726313729287, + "nauc_recall_at_3_diff1": 0.09953910767898444, + "nauc_recall_at_3_max": 0.030368042123013157, + "nauc_recall_at_3_std": -0.04294372678448769, + "nauc_recall_at_5_diff1": 0.051187089640729995, + "nauc_recall_at_5_max": -0.0247916302355724, + "nauc_recall_at_5_std": -0.08077472084749965, + "ndcg_at_1": 0.1468, + "ndcg_at_10": 0.35331, + "ndcg_at_100": 0.42565, + "ndcg_at_1000": 0.43401, + "ndcg_at_20": 0.39192, + "ndcg_at_3": 0.25617, + "ndcg_at_5": 0.29978, + "precision_at_1": 0.1468, + "precision_at_10": 0.06069, + "precision_at_100": 0.00937, + "precision_at_1000": 0.001, + "precision_at_20": 0.03796, + "precision_at_3": 0.11234, + "precision_at_5": 0.08856, + "recall_at_1": 0.1468, + "recall_at_10": 0.60695, + "recall_at_100": 0.93686, + "recall_at_1000": 0.99921, + "recall_at_20": 0.75927, + "recall_at_3": 0.33702, + "recall_at_5": 0.44278 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/ARCChallenge.json b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/ARCChallenge.json new file mode 100644 index 000000000..1c6f4098b --- /dev/null +++ b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/ARCChallenge.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 10.955883264541626, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.09019, + "map_at_1": 0.03413, + "map_at_10": 0.06918, + "map_at_100": 0.076, + "map_at_1000": 0.07716, + "map_at_20": 0.07191, + "map_at_3": 0.05646, + "map_at_5": 0.06414, + "mrr_at_1": 0.034129692832764506, + "mrr_at_10": 0.06917865268974488, + "mrr_at_100": 0.07599788374674538, + "mrr_at_1000": 0.07715522284512971, + "mrr_at_20": 0.07190712237099038, + "mrr_at_3": 0.056456200227531304, + "mrr_at_5": 0.06413538111490333, + "nauc_map_at_1000_diff1": -0.008258030866491281, + "nauc_map_at_1000_max": 0.12505085665029336, + "nauc_map_at_1000_std": -0.09365818361331088, + "nauc_map_at_100_diff1": -0.0076375490318172385, + "nauc_map_at_100_max": 0.12551240926643953, + "nauc_map_at_100_std": -0.09369808840986074, + "nauc_map_at_10_diff1": -0.011646137593318954, + "nauc_map_at_10_max": 0.13628373500689986, + "nauc_map_at_10_std": -0.09512669427944971, + "nauc_map_at_1_diff1": -0.025098020320789827, + "nauc_map_at_1_max": 0.13071712879086667, + "nauc_map_at_1_std": -0.06639998332825695, + "nauc_map_at_20_diff1": -0.0070559401062504756, + "nauc_map_at_20_max": 0.12999636792594954, + "nauc_map_at_20_std": -0.09489748399808293, + "nauc_map_at_3_diff1": 0.0006965395831685174, + "nauc_map_at_3_max": 0.1417774305363711, + "nauc_map_at_3_std": -0.09307556340721633, + "nauc_map_at_5_diff1": -0.013292418025841588, + "nauc_map_at_5_max": 0.14462792358607707, + "nauc_map_at_5_std": -0.0868474003399526, + "nauc_mrr_at_1000_diff1": -0.008258030866491281, + "nauc_mrr_at_1000_max": 0.12505085665029336, + "nauc_mrr_at_1000_std": -0.09365818361331088, + "nauc_mrr_at_100_diff1": -0.0076375490318172385, + "nauc_mrr_at_100_max": 0.12551240926643953, + "nauc_mrr_at_100_std": -0.09369808840986074, + "nauc_mrr_at_10_diff1": -0.011646137593318954, + "nauc_mrr_at_10_max": 0.13628373500689986, + "nauc_mrr_at_10_std": -0.09512669427944971, + "nauc_mrr_at_1_diff1": -0.025098020320789827, + "nauc_mrr_at_1_max": 0.13071712879086667, + "nauc_mrr_at_1_std": -0.06639998332825695, + "nauc_mrr_at_20_diff1": -0.0070559401062504756, + "nauc_mrr_at_20_max": 0.12999636792594954, + "nauc_mrr_at_20_std": -0.09489748399808293, + "nauc_mrr_at_3_diff1": 0.0006965395831685174, + "nauc_mrr_at_3_max": 0.1417774305363711, + "nauc_mrr_at_3_std": -0.09307556340721633, + "nauc_mrr_at_5_diff1": -0.013292418025841588, + "nauc_mrr_at_5_max": 0.14462792358607707, + "nauc_mrr_at_5_std": -0.0868474003399526, + "nauc_ndcg_at_1000_diff1": -0.014089412127870666, + "nauc_ndcg_at_1000_max": 0.08397988566939876, + "nauc_ndcg_at_1000_std": -0.09773973322451011, + "nauc_ndcg_at_100_diff1": -0.0037840087364904864, + "nauc_ndcg_at_100_max": 0.09283527467451888, + "nauc_ndcg_at_100_std": -0.0943587350375537, + "nauc_ndcg_at_10_diff1": -0.010560182659211657, + "nauc_ndcg_at_10_max": 0.13212555477199558, + "nauc_ndcg_at_10_std": -0.10497202163100296, + "nauc_ndcg_at_1_diff1": -0.025098020320789827, + "nauc_ndcg_at_1_max": 0.13071712879086667, + "nauc_ndcg_at_1_std": -0.06639998332825695, + "nauc_ndcg_at_20_diff1": 0.0031190529916548925, + "nauc_ndcg_at_20_max": 0.11607984250479564, + "nauc_ndcg_at_20_std": -0.10247816106789316, + "nauc_ndcg_at_3_diff1": 0.005114158734598399, + "nauc_ndcg_at_3_max": 0.14401220019594113, + "nauc_ndcg_at_3_std": -0.10025375370384529, + "nauc_ndcg_at_5_diff1": -0.015970614182944213, + "nauc_ndcg_at_5_max": 0.1470817377969051, + "nauc_ndcg_at_5_std": -0.09026150509646323, + "nauc_precision_at_1000_diff1": -0.04974184796248972, + "nauc_precision_at_1000_max": -0.024793619192371226, + "nauc_precision_at_1000_std": -0.1051917391556684, + "nauc_precision_at_100_diff1": -0.0027381626383449036, + "nauc_precision_at_100_max": 0.03505328239477593, + "nauc_precision_at_100_std": -0.0872922191471653, + "nauc_precision_at_10_diff1": -0.007896987711299016, + "nauc_precision_at_10_max": 0.12407511530858102, + "nauc_precision_at_10_std": -0.12084340582360063, + "nauc_precision_at_1_diff1": -0.025098020320789827, + "nauc_precision_at_1_max": 0.13071712879086667, + "nauc_precision_at_1_std": -0.06639998332825695, + "nauc_precision_at_20_diff1": 0.022459901497801835, + "nauc_precision_at_20_max": 0.09171743075156978, + "nauc_precision_at_20_std": -0.11166292941391204, + "nauc_precision_at_3_diff1": 0.013469314708851973, + "nauc_precision_at_3_max": 0.1483173177014115, + "nauc_precision_at_3_std": -0.11443112546098784, + "nauc_precision_at_5_diff1": -0.02165981362461835, + "nauc_precision_at_5_max": 0.1508978644896243, + "nauc_precision_at_5_std": -0.09557099078808354, + "nauc_recall_at_1000_diff1": -0.049741847962489594, + "nauc_recall_at_1000_max": -0.02479361919237092, + "nauc_recall_at_1000_std": -0.10519173915566764, + "nauc_recall_at_100_diff1": -0.0027381626383451837, + "nauc_recall_at_100_max": 0.03505328239477559, + "nauc_recall_at_100_std": -0.08729221914716553, + "nauc_recall_at_10_diff1": -0.007896987711299066, + "nauc_recall_at_10_max": 0.12407511530858104, + "nauc_recall_at_10_std": -0.12084340582360076, + "nauc_recall_at_1_diff1": -0.025098020320789827, + "nauc_recall_at_1_max": 0.13071712879086667, + "nauc_recall_at_1_std": -0.06639998332825695, + "nauc_recall_at_20_diff1": 0.022459901497801842, + "nauc_recall_at_20_max": 0.09171743075156964, + "nauc_recall_at_20_std": -0.11166292941391226, + "nauc_recall_at_3_diff1": 0.013469314708851873, + "nauc_recall_at_3_max": 0.1483173177014116, + "nauc_recall_at_3_std": -0.11443112546098791, + "nauc_recall_at_5_diff1": -0.02165981362461843, + "nauc_recall_at_5_max": 0.15089786448962414, + "nauc_recall_at_5_std": -0.09557099078808369, + "ndcg_at_1": 0.03413, + "ndcg_at_10": 0.09019, + "ndcg_at_100": 0.13159, + "ndcg_at_1000": 0.16936, + "ndcg_at_20": 0.10026, + "ndcg_at_3": 0.06406, + "ndcg_at_5": 0.07801, + "precision_at_1": 0.03413, + "precision_at_10": 0.01578, + "precision_at_100": 0.0037, + "precision_at_1000": 0.00068, + "precision_at_20": 0.0099, + "precision_at_3": 0.02873, + "precision_at_5": 0.02406, + "recall_at_1": 0.03413, + "recall_at_10": 0.15785, + "recall_at_100": 0.37031, + "recall_at_1000": 0.68345, + "recall_at_20": 0.19795, + "recall_at_3": 0.08618, + "recall_at_5": 0.12031 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/AlphaNLI.json b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/AlphaNLI.json new file mode 100644 index 000000000..5fbc71781 --- /dev/null +++ b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/AlphaNLI.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 177.5106143951416, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.24727, + "map_at_1": 0.15666, + "map_at_10": 0.21519, + "map_at_100": 0.22242, + "map_at_1000": 0.22323, + "map_at_20": 0.21912, + "map_at_3": 0.19811, + "map_at_5": 0.20718, + "mrr_at_1": 0.1566579634464752, + "mrr_at_10": 0.21518504703883276, + "mrr_at_100": 0.22241983810295682, + "mrr_at_1000": 0.22322836899237092, + "mrr_at_20": 0.2191168587276841, + "mrr_at_3": 0.1981070496083551, + "mrr_at_5": 0.20718015665796333, + "nauc_map_at_1000_diff1": 0.3977585720867937, + "nauc_map_at_1000_max": 0.18671307103174203, + "nauc_map_at_1000_std": -0.08347290588455553, + "nauc_map_at_100_diff1": 0.39766366325299285, + "nauc_map_at_100_max": 0.18661257688271182, + "nauc_map_at_100_std": -0.08346170292430116, + "nauc_map_at_10_diff1": 0.4002116566370461, + "nauc_map_at_10_max": 0.18757670282787353, + "nauc_map_at_10_std": -0.08592886579317223, + "nauc_map_at_1_diff1": 0.4472256809997404, + "nauc_map_at_1_max": 0.20364207476017862, + "nauc_map_at_1_std": -0.09292361029135697, + "nauc_map_at_20_diff1": 0.39947562257943187, + "nauc_map_at_20_max": 0.18747966347854397, + "nauc_map_at_20_std": -0.0853076464701389, + "nauc_map_at_3_diff1": 0.414472717140021, + "nauc_map_at_3_max": 0.20108312804814454, + "nauc_map_at_3_std": -0.08870700126891143, + "nauc_map_at_5_diff1": 0.4066667451997476, + "nauc_map_at_5_max": 0.19166225522545796, + "nauc_map_at_5_std": -0.08923455270236809, + "nauc_mrr_at_1000_diff1": 0.3977585720867937, + "nauc_mrr_at_1000_max": 0.18671307103174203, + "nauc_mrr_at_1000_std": -0.08347290588455553, + "nauc_mrr_at_100_diff1": 0.39766366325299285, + "nauc_mrr_at_100_max": 0.18661257688271182, + "nauc_mrr_at_100_std": -0.08346170292430116, + "nauc_mrr_at_10_diff1": 0.4002116566370461, + "nauc_mrr_at_10_max": 0.18757670282787353, + "nauc_mrr_at_10_std": -0.08592886579317223, + "nauc_mrr_at_1_diff1": 0.4472256809997404, + "nauc_mrr_at_1_max": 0.20364207476017862, + "nauc_mrr_at_1_std": -0.09292361029135697, + "nauc_mrr_at_20_diff1": 0.39947562257943187, + "nauc_mrr_at_20_max": 0.18747966347854397, + "nauc_mrr_at_20_std": -0.0853076464701389, + "nauc_mrr_at_3_diff1": 0.414472717140021, + "nauc_mrr_at_3_max": 0.20108312804814454, + "nauc_mrr_at_3_std": -0.08870700126891143, + "nauc_mrr_at_5_diff1": 0.4066667451997476, + "nauc_mrr_at_5_max": 0.19166225522545796, + "nauc_mrr_at_5_std": -0.08923455270236809, + "nauc_ndcg_at_1000_diff1": 0.3655939837663988, + "nauc_ndcg_at_1000_max": 0.17543420673764654, + "nauc_ndcg_at_1000_std": -0.06340809065002308, + "nauc_ndcg_at_100_diff1": 0.3628212845075164, + "nauc_ndcg_at_100_max": 0.1718089281238929, + "nauc_ndcg_at_100_std": -0.0631324795777629, + "nauc_ndcg_at_10_diff1": 0.3786675354636969, + "nauc_ndcg_at_10_max": 0.1742307830613818, + "nauc_ndcg_at_10_std": -0.08128269757400217, + "nauc_ndcg_at_1_diff1": 0.4472256809997404, + "nauc_ndcg_at_1_max": 0.20364207476017862, + "nauc_ndcg_at_1_std": -0.09292361029135697, + "nauc_ndcg_at_20_diff1": 0.3766807178569935, + "nauc_ndcg_at_20_max": 0.17497978492035215, + "nauc_ndcg_at_20_std": -0.07854800600466973, + "nauc_ndcg_at_3_diff1": 0.40574847281133763, + "nauc_ndcg_at_3_max": 0.19982166313674002, + "nauc_ndcg_at_3_std": -0.08727508179213732, + "nauc_ndcg_at_5_diff1": 0.392947463018066, + "nauc_ndcg_at_5_max": 0.18394882041908162, + "nauc_ndcg_at_5_std": -0.08816133495244483, + "nauc_precision_at_1000_diff1": 0.2096463937993861, + "nauc_precision_at_1000_max": 0.1502064004696453, + "nauc_precision_at_1000_std": 0.06827715545262211, + "nauc_precision_at_100_diff1": 0.2446740256377969, + "nauc_precision_at_100_max": 0.13085331853907517, + "nauc_precision_at_100_std": 0.02253603849361198, + "nauc_precision_at_10_diff1": 0.3231222240028476, + "nauc_precision_at_10_max": 0.13794656896153576, + "nauc_precision_at_10_std": -0.068812799702163, + "nauc_precision_at_1_diff1": 0.4472256809997404, + "nauc_precision_at_1_max": 0.20364207476017862, + "nauc_precision_at_1_std": -0.09292361029135697, + "nauc_precision_at_20_diff1": 0.3183898406671603, + "nauc_precision_at_20_max": 0.14288183088063672, + "nauc_precision_at_20_std": -0.05885376848039759, + "nauc_precision_at_3_diff1": 0.3839122907326991, + "nauc_precision_at_3_max": 0.19650093617440834, + "nauc_precision_at_3_std": -0.08360409535781911, + "nauc_precision_at_5_diff1": 0.35890145381497685, + "nauc_precision_at_5_max": 0.16363425400522355, + "nauc_precision_at_5_std": -0.08559468778793246, + "nauc_recall_at_1000_diff1": 0.20964639379938554, + "nauc_recall_at_1000_max": 0.1502064004696449, + "nauc_recall_at_1000_std": 0.06827715545262149, + "nauc_recall_at_100_diff1": 0.2446740256377965, + "nauc_recall_at_100_max": 0.13085331853907492, + "nauc_recall_at_100_std": 0.022536038493611594, + "nauc_recall_at_10_diff1": 0.32312222400284774, + "nauc_recall_at_10_max": 0.1379465689615358, + "nauc_recall_at_10_std": -0.06881279970216293, + "nauc_recall_at_1_diff1": 0.4472256809997404, + "nauc_recall_at_1_max": 0.20364207476017862, + "nauc_recall_at_1_std": -0.09292361029135697, + "nauc_recall_at_20_diff1": 0.3183898406671603, + "nauc_recall_at_20_max": 0.14288183088063675, + "nauc_recall_at_20_std": -0.05885376848039743, + "nauc_recall_at_3_diff1": 0.38391229073269956, + "nauc_recall_at_3_max": 0.1965009361744083, + "nauc_recall_at_3_std": -0.08360409535781896, + "nauc_recall_at_5_diff1": 0.3589014538149771, + "nauc_recall_at_5_max": 0.16363425400522363, + "nauc_recall_at_5_std": -0.08559468778793239, + "ndcg_at_1": 0.15666, + "ndcg_at_10": 0.24727, + "ndcg_at_100": 0.28773, + "ndcg_at_1000": 0.31403, + "ndcg_at_20": 0.2615, + "ndcg_at_3": 0.2116, + "ndcg_at_5": 0.22798, + "precision_at_1": 0.15666, + "precision_at_10": 0.03499, + "precision_at_100": 0.00552, + "precision_at_1000": 0.00077, + "precision_at_20": 0.0203, + "precision_at_3": 0.08355, + "precision_at_5": 0.05809, + "recall_at_1": 0.15666, + "recall_at_10": 0.34987, + "recall_at_100": 0.55222, + "recall_at_1000": 0.76958, + "recall_at_20": 0.40601, + "recall_at_3": 0.25065, + "recall_at_5": 0.29047 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/HellaSwag.json b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/HellaSwag.json new file mode 100644 index 000000000..d4196e8fd --- /dev/null +++ b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/HellaSwag.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 414.61306524276733, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.25671, + "map_at_1": 0.13553, + "map_at_10": 0.21431, + "map_at_100": 0.22308, + "map_at_1000": 0.22392, + "map_at_20": 0.21919, + "map_at_3": 0.19211, + "map_at_5": 0.2049, + "mrr_at_1": 0.13553077076279627, + "mrr_at_10": 0.214308357280374, + "mrr_at_100": 0.22307809179074214, + "mrr_at_1000": 0.22391920249498745, + "mrr_at_20": 0.21918785652892922, + "mrr_at_3": 0.19210980548363413, + "mrr_at_5": 0.20490108212175454, + "nauc_map_at_1000_diff1": 0.2002583819004535, + "nauc_map_at_1000_max": 0.12170965664811922, + "nauc_map_at_1000_std": -0.07093910309989154, + "nauc_map_at_100_diff1": 0.20015078749655799, + "nauc_map_at_100_max": 0.12163129389377648, + "nauc_map_at_100_std": -0.07112105844396893, + "nauc_map_at_10_diff1": 0.20222981081147978, + "nauc_map_at_10_max": 0.12278715531638519, + "nauc_map_at_10_std": -0.07445772115638305, + "nauc_map_at_1_diff1": 0.2309190431589508, + "nauc_map_at_1_max": 0.10756370451704937, + "nauc_map_at_1_std": -0.06734756782053894, + "nauc_map_at_20_diff1": 0.20090761073343288, + "nauc_map_at_20_max": 0.12187135888531767, + "nauc_map_at_20_std": -0.07323417936999717, + "nauc_map_at_3_diff1": 0.20910892420799687, + "nauc_map_at_3_max": 0.1230567774117033, + "nauc_map_at_3_std": -0.07694847519540557, + "nauc_map_at_5_diff1": 0.2040983833868241, + "nauc_map_at_5_max": 0.1231544250352372, + "nauc_map_at_5_std": -0.07619147304251703, + "nauc_mrr_at_1000_diff1": 0.2002583819004535, + "nauc_mrr_at_1000_max": 0.12170965664811922, + "nauc_mrr_at_1000_std": -0.07093910309989154, + "nauc_mrr_at_100_diff1": 0.20015078749655799, + "nauc_mrr_at_100_max": 0.12163129389377648, + "nauc_mrr_at_100_std": -0.07112105844396893, + "nauc_mrr_at_10_diff1": 0.20222981081147978, + "nauc_mrr_at_10_max": 0.12278715531638519, + "nauc_mrr_at_10_std": -0.07445772115638305, + "nauc_mrr_at_1_diff1": 0.2309190431589508, + "nauc_mrr_at_1_max": 0.10756370451704937, + "nauc_mrr_at_1_std": -0.06734756782053894, + "nauc_mrr_at_20_diff1": 0.20090761073343288, + "nauc_mrr_at_20_max": 0.12187135888531767, + "nauc_mrr_at_20_std": -0.07323417936999717, + "nauc_mrr_at_3_diff1": 0.20910892420799687, + "nauc_mrr_at_3_max": 0.1230567774117033, + "nauc_mrr_at_3_std": -0.07694847519540557, + "nauc_mrr_at_5_diff1": 0.2040983833868241, + "nauc_mrr_at_5_max": 0.1231544250352372, + "nauc_mrr_at_5_std": -0.07619147304251703, + "nauc_ndcg_at_1000_diff1": 0.18350355984573152, + "nauc_ndcg_at_1000_max": 0.12445415390421918, + "nauc_ndcg_at_1000_std": -0.04977477893230322, + "nauc_ndcg_at_100_diff1": 0.18149288101659516, + "nauc_ndcg_at_100_max": 0.12289841040232441, + "nauc_ndcg_at_100_std": -0.05289381936113572, + "nauc_ndcg_at_10_diff1": 0.1916121762066358, + "nauc_ndcg_at_10_max": 0.12594414968189757, + "nauc_ndcg_at_10_std": -0.0740162688290502, + "nauc_ndcg_at_1_diff1": 0.2309190431589508, + "nauc_ndcg_at_1_max": 0.10756370451704937, + "nauc_ndcg_at_1_std": -0.06734756782053894, + "nauc_ndcg_at_20_diff1": 0.1872998455562462, + "nauc_ndcg_at_20_max": 0.12330993330959045, + "nauc_ndcg_at_20_std": -0.06947560861884744, + "nauc_ndcg_at_3_diff1": 0.2040969069876222, + "nauc_ndcg_at_3_max": 0.12717823820455584, + "nauc_ndcg_at_3_std": -0.07951982199606906, + "nauc_ndcg_at_5_diff1": 0.19619161238872682, + "nauc_ndcg_at_5_max": 0.12730797385461426, + "nauc_ndcg_at_5_std": -0.07796773919792778, + "nauc_precision_at_1000_diff1": 0.08689592205863962, + "nauc_precision_at_1000_max": 0.1436568820551219, + "nauc_precision_at_1000_std": 0.13569934418893848, + "nauc_precision_at_100_diff1": 0.11550187145517318, + "nauc_precision_at_100_max": 0.12465848839046696, + "nauc_precision_at_100_std": 0.03420074096984425, + "nauc_precision_at_10_diff1": 0.16594814820762072, + "nauc_precision_at_10_max": 0.13218789658812533, + "nauc_precision_at_10_std": -0.07151795026759672, + "nauc_precision_at_1_diff1": 0.2309190431589508, + "nauc_precision_at_1_max": 0.10756370451704937, + "nauc_precision_at_1_std": -0.06734756782053894, + "nauc_precision_at_20_diff1": 0.15177195623032888, + "nauc_precision_at_20_max": 0.12443844428160963, + "nauc_precision_at_20_std": -0.0559092684863215, + "nauc_precision_at_3_diff1": 0.19238374592074442, + "nauc_precision_at_3_max": 0.1369704379161881, + "nauc_precision_at_3_std": -0.08563337121968437, + "nauc_precision_at_5_diff1": 0.17780306992787684, + "nauc_precision_at_5_max": 0.13679375017744996, + "nauc_precision_at_5_std": -0.08172062810556924, + "nauc_recall_at_1000_diff1": 0.08689592205864033, + "nauc_recall_at_1000_max": 0.14365688205512256, + "nauc_recall_at_1000_std": 0.13569934418893864, + "nauc_recall_at_100_diff1": 0.11550187145517407, + "nauc_recall_at_100_max": 0.12465848839046756, + "nauc_recall_at_100_std": 0.03420074096984516, + "nauc_recall_at_10_diff1": 0.16594814820762085, + "nauc_recall_at_10_max": 0.13218789658812563, + "nauc_recall_at_10_std": -0.07151795026759658, + "nauc_recall_at_1_diff1": 0.2309190431589508, + "nauc_recall_at_1_max": 0.10756370451704937, + "nauc_recall_at_1_std": -0.06734756782053894, + "nauc_recall_at_20_diff1": 0.15177195623032924, + "nauc_recall_at_20_max": 0.12443844428160994, + "nauc_recall_at_20_std": -0.05590926848632095, + "nauc_recall_at_3_diff1": 0.19238374592074428, + "nauc_recall_at_3_max": 0.1369704379161879, + "nauc_recall_at_3_std": -0.08563337121968446, + "nauc_recall_at_5_diff1": 0.17780306992787703, + "nauc_recall_at_5_max": 0.13679375017745007, + "nauc_recall_at_5_std": -0.08172062810556907, + "ndcg_at_1": 0.13553, + "ndcg_at_10": 0.25671, + "ndcg_at_100": 0.30396, + "ndcg_at_1000": 0.32892, + "ndcg_at_20": 0.27447, + "ndcg_at_3": 0.21095, + "ndcg_at_5": 0.23389, + "precision_at_1": 0.13553, + "precision_at_10": 0.03917, + "precision_at_100": 0.00624, + "precision_at_1000": 0.00083, + "precision_at_20": 0.02309, + "precision_at_3": 0.08853, + "precision_at_5": 0.06421, + "recall_at_1": 0.13553, + "recall_at_10": 0.39166, + "recall_at_100": 0.62358, + "recall_at_1000": 0.82583, + "recall_at_20": 0.46186, + "recall_at_3": 0.26558, + "recall_at_5": 0.32105 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/PIQA.json b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/PIQA.json new file mode 100644 index 000000000..a8c57d546 --- /dev/null +++ b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/PIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 54.15647554397583, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.22935, + "map_at_1": 0.11153, + "map_at_10": 0.1899, + "map_at_100": 0.19926, + "map_at_1000": 0.20003, + "map_at_20": 0.19518, + "map_at_3": 0.17165, + "map_at_5": 0.18158, + "mrr_at_1": 0.11153427638737759, + "mrr_at_10": 0.18989930393630053, + "mrr_at_100": 0.1992609381699616, + "mrr_at_1000": 0.20003280152165565, + "mrr_at_20": 0.19517897407073515, + "mrr_at_3": 0.17165397170837868, + "mrr_at_5": 0.18158324265505965, + "nauc_map_at_1000_diff1": -0.1202083775999386, + "nauc_map_at_1000_max": -0.02933378334163804, + "nauc_map_at_1000_std": -0.04581529903595277, + "nauc_map_at_100_diff1": -0.12014511915334827, + "nauc_map_at_100_max": -0.02907220374989626, + "nauc_map_at_100_std": -0.04561104034162173, + "nauc_map_at_10_diff1": -0.11743141388844373, + "nauc_map_at_10_max": -0.02388798033912426, + "nauc_map_at_10_std": -0.04714228404493196, + "nauc_map_at_1_diff1": -0.08190043587552145, + "nauc_map_at_1_max": -0.025293093762147365, + "nauc_map_at_1_std": -0.043209248229367114, + "nauc_map_at_20_diff1": -0.11883222089010803, + "nauc_map_at_20_max": -0.028296199838762, + "nauc_map_at_20_std": -0.04523830381173142, + "nauc_map_at_3_diff1": -0.11738885706608293, + "nauc_map_at_3_max": -0.01426346557587223, + "nauc_map_at_3_std": -0.046678998921360584, + "nauc_map_at_5_diff1": -0.12361339359806227, + "nauc_map_at_5_max": -0.022899301197922894, + "nauc_map_at_5_std": -0.04997925932370262, + "nauc_mrr_at_1000_diff1": -0.1202083775999386, + "nauc_mrr_at_1000_max": -0.02933378334163804, + "nauc_mrr_at_1000_std": -0.04581529903595277, + "nauc_mrr_at_100_diff1": -0.12014511915334827, + "nauc_mrr_at_100_max": -0.02907220374989626, + "nauc_mrr_at_100_std": -0.04561104034162173, + "nauc_mrr_at_10_diff1": -0.11743141388844373, + "nauc_mrr_at_10_max": -0.02388798033912426, + "nauc_mrr_at_10_std": -0.04714228404493196, + "nauc_mrr_at_1_diff1": -0.08190043587552145, + "nauc_mrr_at_1_max": -0.025293093762147365, + "nauc_mrr_at_1_std": -0.043209248229367114, + "nauc_mrr_at_20_diff1": -0.11883222089010803, + "nauc_mrr_at_20_max": -0.028296199838762, + "nauc_mrr_at_20_std": -0.04523830381173142, + "nauc_mrr_at_3_diff1": -0.11738885706608293, + "nauc_mrr_at_3_max": -0.01426346557587223, + "nauc_mrr_at_3_std": -0.046678998921360584, + "nauc_mrr_at_5_diff1": -0.12361339359806227, + "nauc_mrr_at_5_max": -0.022899301197922894, + "nauc_mrr_at_5_std": -0.04997925932370262, + "nauc_ndcg_at_1000_diff1": -0.1335422655622764, + "nauc_ndcg_at_1000_max": -0.054879721913823155, + "nauc_ndcg_at_1000_std": -0.047898246687391, + "nauc_ndcg_at_100_diff1": -0.13271804957355576, + "nauc_ndcg_at_100_max": -0.04929392109350335, + "nauc_ndcg_at_100_std": -0.043128357815960465, + "nauc_ndcg_at_10_diff1": -0.12001493743448409, + "nauc_ndcg_at_10_max": -0.03058322187237474, + "nauc_ndcg_at_10_std": -0.04858754409763881, + "nauc_ndcg_at_1_diff1": -0.08190043587552145, + "nauc_ndcg_at_1_max": -0.025293093762147365, + "nauc_ndcg_at_1_std": -0.043209248229367114, + "nauc_ndcg_at_20_diff1": -0.12541839595271262, + "nauc_ndcg_at_20_max": -0.04513618718300163, + "nauc_ndcg_at_20_std": -0.04189304001984062, + "nauc_ndcg_at_3_diff1": -0.12343247718961835, + "nauc_ndcg_at_3_max": -0.014011284404777181, + "nauc_ndcg_at_3_std": -0.04815600509357237, + "nauc_ndcg_at_5_diff1": -0.13361670085076469, + "nauc_ndcg_at_5_max": -0.028228337838708775, + "nauc_ndcg_at_5_std": -0.05401626314980824, + "nauc_precision_at_1000_diff1": -0.20136736978118094, + "nauc_precision_at_1000_max": -0.20426829652228273, + "nauc_precision_at_1000_std": -0.07146754688998991, + "nauc_precision_at_100_diff1": -0.1730019374446837, + "nauc_precision_at_100_max": -0.11458695251282508, + "nauc_precision_at_100_std": -0.032001566381841665, + "nauc_precision_at_10_diff1": -0.12209743353915246, + "nauc_precision_at_10_max": -0.04735759958521929, + "nauc_precision_at_10_std": -0.051663794235937636, + "nauc_precision_at_1_diff1": -0.08190043587552145, + "nauc_precision_at_1_max": -0.025293093762147365, + "nauc_precision_at_1_std": -0.043209248229367114, + "nauc_precision_at_20_diff1": -0.14012205158705923, + "nauc_precision_at_20_max": -0.09221288723830921, + "nauc_precision_at_20_std": -0.03025418514112973, + "nauc_precision_at_3_diff1": -0.13658810667953333, + "nauc_precision_at_3_max": -0.014026364787827383, + "nauc_precision_at_3_std": -0.05167846742539682, + "nauc_precision_at_5_diff1": -0.15578310094892917, + "nauc_precision_at_5_max": -0.041734001549383344, + "nauc_precision_at_5_std": -0.0637484123281095, + "nauc_recall_at_1000_diff1": -0.20136736978118, + "nauc_recall_at_1000_max": -0.20426829652228112, + "nauc_recall_at_1000_std": -0.07146754688998795, + "nauc_recall_at_100_diff1": -0.17300193744468395, + "nauc_recall_at_100_max": -0.11458695251282626, + "nauc_recall_at_100_std": -0.032001566381842206, + "nauc_recall_at_10_diff1": -0.1220974335391522, + "nauc_recall_at_10_max": -0.047357599585219234, + "nauc_recall_at_10_std": -0.05166379423593761, + "nauc_recall_at_1_diff1": -0.08190043587552145, + "nauc_recall_at_1_max": -0.025293093762147365, + "nauc_recall_at_1_std": -0.043209248229367114, + "nauc_recall_at_20_diff1": -0.1401220515870591, + "nauc_recall_at_20_max": -0.09221288723830914, + "nauc_recall_at_20_std": -0.03025418514112981, + "nauc_recall_at_3_diff1": -0.1365881066795331, + "nauc_recall_at_3_max": -0.014026364787827227, + "nauc_recall_at_3_std": -0.05167846742539666, + "nauc_recall_at_5_diff1": -0.1557831009489293, + "nauc_recall_at_5_max": -0.041734001549383365, + "nauc_recall_at_5_std": -0.06374841232810959, + "ndcg_at_1": 0.11153, + "ndcg_at_10": 0.22935, + "ndcg_at_100": 0.27782, + "ndcg_at_1000": 0.30166, + "ndcg_at_20": 0.24851, + "ndcg_at_3": 0.19102, + "ndcg_at_5": 0.20905, + "precision_at_1": 0.11153, + "precision_at_10": 0.03542, + "precision_at_100": 0.00588, + "precision_at_1000": 0.00078, + "precision_at_20": 0.02149, + "precision_at_3": 0.08234, + "precision_at_5": 0.05822, + "recall_at_1": 0.11153, + "recall_at_10": 0.35419, + "recall_at_100": 0.5876, + "recall_at_1000": 0.78237, + "recall_at_20": 0.42982, + "recall_at_3": 0.24701, + "recall_at_5": 0.29108 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/Quail.json b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/Quail.json new file mode 100644 index 000000000..6e33b50e0 --- /dev/null +++ b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/Quail.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 86.74064326286316, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07508, + "map_at_1": 0.03015, + "map_at_10": 0.05673, + "map_at_100": 0.06339, + "map_at_1000": 0.06447, + "map_at_20": 0.06027, + "map_at_3": 0.04547, + "map_at_5": 0.05089, + "mrr_at_1": 0.030147058823529412, + "mrr_at_10": 0.056727357609710524, + "mrr_at_100": 0.06338951459017533, + "mrr_at_1000": 0.06447265763997032, + "mrr_at_20": 0.060273154264529345, + "mrr_at_3": 0.04546568627450979, + "mrr_at_5": 0.05088848039215686, + "nauc_map_at_1000_diff1": 0.1525305827813089, + "nauc_map_at_1000_max": 0.11849191891092513, + "nauc_map_at_1000_std": 0.07501365776159237, + "nauc_map_at_100_diff1": 0.1527642024415799, + "nauc_map_at_100_max": 0.11946725077960395, + "nauc_map_at_100_std": 0.07489151090665053, + "nauc_map_at_10_diff1": 0.1643602740069935, + "nauc_map_at_10_max": 0.12056785804762576, + "nauc_map_at_10_std": 0.07366545139281472, + "nauc_map_at_1_diff1": 0.25291707840609395, + "nauc_map_at_1_max": 0.14269634244504512, + "nauc_map_at_1_std": 0.06226808981263949, + "nauc_map_at_20_diff1": 0.1556046778556637, + "nauc_map_at_20_max": 0.11903938203550996, + "nauc_map_at_20_std": 0.07455757952102222, + "nauc_map_at_3_diff1": 0.18203435699423667, + "nauc_map_at_3_max": 0.12510730684586938, + "nauc_map_at_3_std": 0.06660039617651345, + "nauc_map_at_5_diff1": 0.16996123282805234, + "nauc_map_at_5_max": 0.11848219551519446, + "nauc_map_at_5_std": 0.06644582457737593, + "nauc_mrr_at_1000_diff1": 0.1525305827813089, + "nauc_mrr_at_1000_max": 0.11849191891092513, + "nauc_mrr_at_1000_std": 0.07501365776159237, + "nauc_mrr_at_100_diff1": 0.1527642024415799, + "nauc_mrr_at_100_max": 0.11946725077960395, + "nauc_mrr_at_100_std": 0.07489151090665053, + "nauc_mrr_at_10_diff1": 0.1643602740069935, + "nauc_mrr_at_10_max": 0.12056785804762576, + "nauc_mrr_at_10_std": 0.07366545139281472, + "nauc_mrr_at_1_diff1": 0.25291707840609395, + "nauc_mrr_at_1_max": 0.14269634244504512, + "nauc_mrr_at_1_std": 0.06226808981263949, + "nauc_mrr_at_20_diff1": 0.1556046778556637, + "nauc_mrr_at_20_max": 0.11903938203550996, + "nauc_mrr_at_20_std": 0.07455757952102222, + "nauc_mrr_at_3_diff1": 0.18203435699423667, + "nauc_mrr_at_3_max": 0.12510730684586938, + "nauc_mrr_at_3_std": 0.06660039617651345, + "nauc_mrr_at_5_diff1": 0.16996123282805234, + "nauc_mrr_at_5_max": 0.11848219551519446, + "nauc_mrr_at_5_std": 0.06644582457737593, + "nauc_ndcg_at_1000_diff1": 0.10511074028959022, + "nauc_ndcg_at_1000_max": 0.09814067715768526, + "nauc_ndcg_at_1000_std": 0.09160087081791904, + "nauc_ndcg_at_100_diff1": 0.11155738184767085, + "nauc_ndcg_at_100_max": 0.11341818791123565, + "nauc_ndcg_at_100_std": 0.08372112906687838, + "nauc_ndcg_at_10_diff1": 0.14446730680251182, + "nauc_ndcg_at_10_max": 0.11731956107828223, + "nauc_ndcg_at_10_std": 0.08079647172800729, + "nauc_ndcg_at_1_diff1": 0.25291707840609395, + "nauc_ndcg_at_1_max": 0.14269634244504512, + "nauc_ndcg_at_1_std": 0.06226808981263949, + "nauc_ndcg_at_20_diff1": 0.12285831712907087, + "nauc_ndcg_at_20_max": 0.11371825360447073, + "nauc_ndcg_at_20_std": 0.08485888608097215, + "nauc_ndcg_at_3_diff1": 0.1675691738226628, + "nauc_ndcg_at_3_max": 0.11971042692491582, + "nauc_ndcg_at_3_std": 0.06706980760798174, + "nauc_ndcg_at_5_diff1": 0.15253687009755426, + "nauc_ndcg_at_5_max": 0.11060948476805064, + "nauc_ndcg_at_5_std": 0.06684601334602042, + "nauc_precision_at_1000_diff1": 0.02654296470746097, + "nauc_precision_at_1000_max": 0.05058485257016225, + "nauc_precision_at_1000_std": 0.13052980762238192, + "nauc_precision_at_100_diff1": 0.060402186050401215, + "nauc_precision_at_100_max": 0.10586652499643386, + "nauc_precision_at_100_std": 0.09358893004540354, + "nauc_precision_at_10_diff1": 0.11660014859825263, + "nauc_precision_at_10_max": 0.1145698910572105, + "nauc_precision_at_10_std": 0.09278771758032264, + "nauc_precision_at_1_diff1": 0.25291707840609395, + "nauc_precision_at_1_max": 0.14269634244504512, + "nauc_precision_at_1_std": 0.06226808981263949, + "nauc_precision_at_20_diff1": 0.07857431981396688, + "nauc_precision_at_20_max": 0.10806838990680222, + "nauc_precision_at_20_std": 0.10098203041372669, + "nauc_precision_at_3_diff1": 0.13865784217273328, + "nauc_precision_at_3_max": 0.10852189726619553, + "nauc_precision_at_3_std": 0.06791580955788075, + "nauc_precision_at_5_diff1": 0.12343561427769133, + "nauc_precision_at_5_max": 0.09683576136063701, + "nauc_precision_at_5_std": 0.06745393338250612, + "nauc_recall_at_1000_diff1": 0.02654296470746186, + "nauc_recall_at_1000_max": 0.05058485257016248, + "nauc_recall_at_1000_std": 0.1305298076223827, + "nauc_recall_at_100_diff1": 0.06040218605040139, + "nauc_recall_at_100_max": 0.10586652499643387, + "nauc_recall_at_100_std": 0.09358893004540322, + "nauc_recall_at_10_diff1": 0.11660014859825245, + "nauc_recall_at_10_max": 0.11456989105721044, + "nauc_recall_at_10_std": 0.0927877175803224, + "nauc_recall_at_1_diff1": 0.25291707840609395, + "nauc_recall_at_1_max": 0.14269634244504512, + "nauc_recall_at_1_std": 0.06226808981263949, + "nauc_recall_at_20_diff1": 0.07857431981396668, + "nauc_recall_at_20_max": 0.1080683899068019, + "nauc_recall_at_20_std": 0.10098203041372651, + "nauc_recall_at_3_diff1": 0.13865784217273344, + "nauc_recall_at_3_max": 0.10852189726619556, + "nauc_recall_at_3_std": 0.06791580955788101, + "nauc_recall_at_5_diff1": 0.12343561427769138, + "nauc_recall_at_5_max": 0.09683576136063675, + "nauc_recall_at_5_std": 0.06745393338250588, + "ndcg_at_1": 0.03015, + "ndcg_at_10": 0.07508, + "ndcg_at_100": 0.11212, + "ndcg_at_1000": 0.1476, + "ndcg_at_20": 0.08806, + "ndcg_at_3": 0.05076, + "ndcg_at_5": 0.06073, + "precision_at_1": 0.03015, + "precision_at_10": 0.01357, + "precision_at_100": 0.0032, + "precision_at_1000": 0.00061, + "precision_at_20": 0.00936, + "precision_at_3": 0.02206, + "precision_at_5": 0.01816, + "recall_at_1": 0.03015, + "recall_at_10": 0.13566, + "recall_at_100": 0.31985, + "recall_at_1000": 0.61397, + "recall_at_20": 0.18713, + "recall_at_3": 0.06618, + "recall_at_5": 0.09081 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/RARbCode.json b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/RARbCode.json new file mode 100644 index 000000000..72f8a2dd4 --- /dev/null +++ b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/RARbCode.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 3950.5699920654297, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.38799, + "map_at_1": 0.25404, + "map_at_10": 0.33882, + "map_at_100": 0.34706, + "map_at_1000": 0.34767, + "map_at_20": 0.34363, + "map_at_3": 0.31098, + "map_at_5": 0.32729, + "mrr_at_1": 0.25404312668463613, + "mrr_at_10": 0.3388190968211182, + "mrr_at_100": 0.347060740704687, + "mrr_at_1000": 0.34767471300234665, + "mrr_at_20": 0.34363430347995816, + "mrr_at_3": 0.31098382749326137, + "mrr_at_5": 0.3272911051212937, + "nauc_map_at_1000_diff1": 0.4319314213781107, + "nauc_map_at_1000_max": 0.10096202688517208, + "nauc_map_at_1000_std": 0.2587210310847483, + "nauc_map_at_100_diff1": 0.43170115462888403, + "nauc_map_at_100_max": 0.10079578832071552, + "nauc_map_at_100_std": 0.2588284761803217, + "nauc_map_at_10_diff1": 0.4321965331949236, + "nauc_map_at_10_max": 0.10278649808500598, + "nauc_map_at_10_std": 0.2576692885163314, + "nauc_map_at_1_diff1": 0.4990676208526851, + "nauc_map_at_1_max": 0.08531399420472693, + "nauc_map_at_1_std": 0.23535533142977524, + "nauc_map_at_20_diff1": 0.43132810138129196, + "nauc_map_at_20_max": 0.10148631732276808, + "nauc_map_at_20_std": 0.258529345854879, + "nauc_map_at_3_diff1": 0.44121433626841167, + "nauc_map_at_3_max": 0.1005819744328791, + "nauc_map_at_3_std": 0.2523909913026496, + "nauc_map_at_5_diff1": 0.4352877630863773, + "nauc_map_at_5_max": 0.09921397442159408, + "nauc_map_at_5_std": 0.2531634035787249, + "nauc_mrr_at_1000_diff1": 0.4319309231792763, + "nauc_mrr_at_1000_max": 0.10058757918006098, + "nauc_mrr_at_1000_std": 0.25681716940210275, + "nauc_mrr_at_100_diff1": 0.4317007162734585, + "nauc_mrr_at_100_max": 0.1004218382660686, + "nauc_mrr_at_100_std": 0.2569273520358395, + "nauc_mrr_at_10_diff1": 0.4321965331949236, + "nauc_mrr_at_10_max": 0.10241984989520163, + "nauc_mrr_at_10_std": 0.2557928494547785, + "nauc_mrr_at_1_diff1": 0.4990676208526851, + "nauc_mrr_at_1_max": 0.08454616524728445, + "nauc_mrr_at_1_std": 0.23142572182470852, + "nauc_mrr_at_20_diff1": 0.43132810138129196, + "nauc_mrr_at_20_max": 0.10111760903819433, + "nauc_mrr_at_20_std": 0.2566423636012347, + "nauc_mrr_at_3_diff1": 0.44121433626841167, + "nauc_mrr_at_3_max": 0.10021931803782737, + "nauc_mrr_at_3_std": 0.250534981524012, + "nauc_mrr_at_5_diff1": 0.4352877630863773, + "nauc_mrr_at_5_max": 0.09885017749647472, + "nauc_mrr_at_5_std": 0.2513015567736698, + "nauc_ndcg_at_1000_diff1": 0.4094555178198218, + "nauc_ndcg_at_1000_max": 0.10747989011840707, + "nauc_ndcg_at_1000_std": 0.27404013274986233, + "nauc_ndcg_at_100_diff1": 0.40412767009096356, + "nauc_ndcg_at_100_max": 0.10236075382236297, + "nauc_ndcg_at_100_std": 0.2761587251302958, + "nauc_ndcg_at_10_diff1": 0.40665902152513317, + "nauc_ndcg_at_10_max": 0.11178952134593233, + "nauc_ndcg_at_10_std": 0.26914690298551774, + "nauc_ndcg_at_1_diff1": 0.4990676208526851, + "nauc_ndcg_at_1_max": 0.08531399420472693, + "nauc_ndcg_at_1_std": 0.23535533142977524, + "nauc_ndcg_at_20_diff1": 0.4027372932005213, + "nauc_ndcg_at_20_max": 0.10697569552827535, + "nauc_ndcg_at_20_std": 0.2727051384606981, + "nauc_ndcg_at_3_diff1": 0.4247745253634616, + "nauc_ndcg_at_3_max": 0.10678955420209003, + "nauc_ndcg_at_3_std": 0.25657507816256026, + "nauc_ndcg_at_5_diff1": 0.4143614649494247, + "nauc_ndcg_at_5_max": 0.10440586249473052, + "nauc_ndcg_at_5_std": 0.25830312048803794, + "nauc_precision_at_1000_diff1": 0.2545503695927704, + "nauc_precision_at_1000_max": 0.20099997719168886, + "nauc_precision_at_1000_std": 0.4367031469024004, + "nauc_precision_at_100_diff1": 0.27931550723270976, + "nauc_precision_at_100_max": 0.09400737552597889, + "nauc_precision_at_100_std": 0.3729195755629746, + "nauc_precision_at_10_diff1": 0.328652409711537, + "nauc_precision_at_10_max": 0.13967600744269115, + "nauc_precision_at_10_std": 0.3068716500774234, + "nauc_precision_at_1_diff1": 0.4990676208526851, + "nauc_precision_at_1_max": 0.08531399420472693, + "nauc_precision_at_1_std": 0.23535533142977524, + "nauc_precision_at_20_diff1": 0.30478103952392643, + "nauc_precision_at_20_max": 0.12130025220198902, + "nauc_precision_at_20_std": 0.32560600182856403, + "nauc_precision_at_3_diff1": 0.38042680960661, + "nauc_precision_at_3_max": 0.12411590393060698, + "nauc_precision_at_3_std": 0.2676578374846156, + "nauc_precision_at_5_diff1": 0.3559358769963611, + "nauc_precision_at_5_max": 0.1188176954703965, + "nauc_precision_at_5_std": 0.2725864613888732, + "nauc_recall_at_1000_diff1": 0.25455036959277316, + "nauc_recall_at_1000_max": 0.20099997719168927, + "nauc_recall_at_1000_std": 0.4367031469024013, + "nauc_recall_at_100_diff1": 0.2793155072327089, + "nauc_recall_at_100_max": 0.09400737552597828, + "nauc_recall_at_100_std": 0.3729195755629739, + "nauc_recall_at_10_diff1": 0.32865240971153675, + "nauc_recall_at_10_max": 0.13967600744269112, + "nauc_recall_at_10_std": 0.3068716500774237, + "nauc_recall_at_1_diff1": 0.4990676208526851, + "nauc_recall_at_1_max": 0.08531399420472693, + "nauc_recall_at_1_std": 0.23535533142977524, + "nauc_recall_at_20_diff1": 0.30478103952392616, + "nauc_recall_at_20_max": 0.12130025220198902, + "nauc_recall_at_20_std": 0.3256060018285646, + "nauc_recall_at_3_diff1": 0.38042680960661013, + "nauc_recall_at_3_max": 0.12411590393060704, + "nauc_recall_at_3_std": 0.26765783748461586, + "nauc_recall_at_5_diff1": 0.35593587699636103, + "nauc_recall_at_5_max": 0.11881769547039636, + "nauc_recall_at_5_std": 0.2725864613888732, + "ndcg_at_1": 0.25404, + "ndcg_at_10": 0.38799, + "ndcg_at_100": 0.43022, + "ndcg_at_1000": 0.44821, + "ndcg_at_20": 0.4053, + "ndcg_at_3": 0.33055, + "ndcg_at_5": 0.35995, + "precision_at_1": 0.25404, + "precision_at_10": 0.05458, + "precision_at_100": 0.00749, + "precision_at_1000": 0.00089, + "precision_at_20": 0.03069, + "precision_at_3": 0.12916, + "precision_at_5": 0.09178, + "recall_at_1": 0.25404, + "recall_at_10": 0.54582, + "recall_at_100": 0.74865, + "recall_at_1000": 0.89353, + "recall_at_20": 0.61388, + "recall_at_3": 0.38747, + "recall_at_5": 0.45889 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/RARbMath.json b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/RARbMath.json new file mode 100644 index 000000000..62176ffb1 --- /dev/null +++ b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/RARbMath.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 4320.397106170654, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.69191, + "map_at_1": 0.62573, + "map_at_10": 0.66932, + "map_at_100": 0.67466, + "map_at_1000": 0.67501, + "map_at_20": 0.67236, + "map_at_3": 0.65788, + "map_at_5": 0.66428, + "mrr_at_1": 0.6257319196075328, + "mrr_at_10": 0.6693193493043156, + "mrr_at_100": 0.6746603727610746, + "mrr_at_1000": 0.6750051530923139, + "mrr_at_20": 0.6723554088137629, + "mrr_at_3": 0.6578836313762734, + "mrr_at_5": 0.6642770480561272, + "nauc_map_at_1000_diff1": 0.8669056122181757, + "nauc_map_at_1000_max": 0.46775571722587067, + "nauc_map_at_1000_std": -0.2934441965642985, + "nauc_map_at_100_diff1": 0.8667263274647016, + "nauc_map_at_100_max": 0.4677089936241976, + "nauc_map_at_100_std": -0.29342301747218263, + "nauc_map_at_10_diff1": 0.8671556722151866, + "nauc_map_at_10_max": 0.46616474696499965, + "nauc_map_at_10_std": -0.2972396010537064, + "nauc_map_at_1_diff1": 0.8935494505093846, + "nauc_map_at_1_max": 0.48248610590918717, + "nauc_map_at_1_std": -0.28710702690239936, + "nauc_map_at_20_diff1": 0.8663005225625965, + "nauc_map_at_20_max": 0.4667691618012897, + "nauc_map_at_20_std": -0.2951034955148164, + "nauc_map_at_3_diff1": 0.8707143342911945, + "nauc_map_at_3_max": 0.46721150483851404, + "nauc_map_at_3_std": -0.29556142539767205, + "nauc_map_at_5_diff1": 0.8687716034086219, + "nauc_map_at_5_max": 0.4663517029073937, + "nauc_map_at_5_std": -0.29791914881230047, + "nauc_mrr_at_1000_diff1": 0.8669056122181757, + "nauc_mrr_at_1000_max": 0.46775571722587067, + "nauc_mrr_at_1000_std": -0.2934441965642985, + "nauc_mrr_at_100_diff1": 0.8667263274647016, + "nauc_mrr_at_100_max": 0.4677089936241976, + "nauc_mrr_at_100_std": -0.29342301747218263, + "nauc_mrr_at_10_diff1": 0.8671556722151866, + "nauc_mrr_at_10_max": 0.46616474696499965, + "nauc_mrr_at_10_std": -0.2972396010537064, + "nauc_mrr_at_1_diff1": 0.8935494505093846, + "nauc_mrr_at_1_max": 0.48248610590918717, + "nauc_mrr_at_1_std": -0.28710702690239936, + "nauc_mrr_at_20_diff1": 0.8663005225625965, + "nauc_mrr_at_20_max": 0.4667691618012897, + "nauc_mrr_at_20_std": -0.2951034955148164, + "nauc_mrr_at_3_diff1": 0.8707143342911945, + "nauc_mrr_at_3_max": 0.46721150483851404, + "nauc_mrr_at_3_std": -0.29556142539767205, + "nauc_mrr_at_5_diff1": 0.8687716034086219, + "nauc_mrr_at_5_max": 0.4663517029073937, + "nauc_mrr_at_5_std": -0.29791914881230047, + "nauc_ndcg_at_1000_diff1": 0.8581763230796313, + "nauc_ndcg_at_1000_max": 0.46935320006905523, + "nauc_ndcg_at_1000_std": -0.28196607191825257, + "nauc_ndcg_at_100_diff1": 0.8536061558980497, + "nauc_ndcg_at_100_max": 0.4684217017178792, + "nauc_ndcg_at_100_std": -0.28003353051058966, + "nauc_ndcg_at_10_diff1": 0.8546607435822683, + "nauc_ndcg_at_10_max": 0.4594099404078137, + "nauc_ndcg_at_10_std": -0.30043470794421423, + "nauc_ndcg_at_1_diff1": 0.8935494505093846, + "nauc_ndcg_at_1_max": 0.48248610590918717, + "nauc_ndcg_at_1_std": -0.28710702690239936, + "nauc_ndcg_at_20_diff1": 0.8510717001986216, + "nauc_ndcg_at_20_max": 0.46164808202580193, + "nauc_ndcg_at_20_std": -0.2925159381107523, + "nauc_ndcg_at_3_diff1": 0.8628557569540497, + "nauc_ndcg_at_3_max": 0.46180313795909617, + "nauc_ndcg_at_3_std": -0.29803236398181415, + "nauc_ndcg_at_5_diff1": 0.8590555412345475, + "nauc_ndcg_at_5_max": 0.459984325009171, + "nauc_ndcg_at_5_std": -0.3023692503382712, + "nauc_precision_at_1000_diff1": 0.7627503669784113, + "nauc_precision_at_1000_max": 0.6707210150379928, + "nauc_precision_at_1000_std": 0.22601238365489354, + "nauc_precision_at_100_diff1": 0.7495953888065984, + "nauc_precision_at_100_max": 0.5084057420982254, + "nauc_precision_at_100_std": -0.101111773376916, + "nauc_precision_at_10_diff1": 0.805449243687206, + "nauc_precision_at_10_max": 0.4337150920433679, + "nauc_precision_at_10_std": -0.31142492753700746, + "nauc_precision_at_1_diff1": 0.8935494505093846, + "nauc_precision_at_1_max": 0.48248610590918717, + "nauc_precision_at_1_std": -0.28710702690239936, + "nauc_precision_at_20_diff1": 0.7775530773673117, + "nauc_precision_at_20_max": 0.44164953536954954, + "nauc_precision_at_20_std": -0.2710407472178616, + "nauc_precision_at_3_diff1": 0.8382755217368822, + "nauc_precision_at_3_max": 0.44483612944627376, + "nauc_precision_at_3_std": -0.3056147344445131, + "nauc_precision_at_5_diff1": 0.826093773156859, + "nauc_precision_at_5_max": 0.43836818348870016, + "nauc_precision_at_5_std": -0.31765430436932707, + "nauc_recall_at_1000_diff1": 0.7627503669784147, + "nauc_recall_at_1000_max": 0.6707210150379928, + "nauc_recall_at_1000_std": 0.22601238365489992, + "nauc_recall_at_100_diff1": 0.7495953888065978, + "nauc_recall_at_100_max": 0.5084057420982234, + "nauc_recall_at_100_std": -0.10111177337691815, + "nauc_recall_at_10_diff1": 0.805449243687206, + "nauc_recall_at_10_max": 0.43371509204336894, + "nauc_recall_at_10_std": -0.3114249275370044, + "nauc_recall_at_1_diff1": 0.8935494505093846, + "nauc_recall_at_1_max": 0.48248610590918717, + "nauc_recall_at_1_std": -0.28710702690239936, + "nauc_recall_at_20_diff1": 0.7775530773673109, + "nauc_recall_at_20_max": 0.4416495353695492, + "nauc_recall_at_20_std": -0.2710407472178585, + "nauc_recall_at_3_diff1": 0.8382755217368825, + "nauc_recall_at_3_max": 0.44483612944627365, + "nauc_recall_at_3_std": -0.30561473444451365, + "nauc_recall_at_5_diff1": 0.8260937731568581, + "nauc_recall_at_5_max": 0.43836818348870016, + "nauc_recall_at_5_std": -0.31765430436932635, + "ndcg_at_1": 0.62573, + "ndcg_at_10": 0.69191, + "ndcg_at_100": 0.72007, + "ndcg_at_1000": 0.72931, + "ndcg_at_20": 0.70286, + "ndcg_at_3": 0.66806, + "ndcg_at_5": 0.67962, + "precision_at_1": 0.62573, + "precision_at_10": 0.07637, + "precision_at_100": 0.00901, + "precision_at_1000": 0.00097, + "precision_at_20": 0.04034, + "precision_at_3": 0.23247, + "precision_at_5": 0.14512, + "recall_at_1": 0.62573, + "recall_at_10": 0.76373, + "recall_at_100": 0.90062, + "recall_at_1000": 0.97357, + "recall_at_20": 0.80677, + "recall_at_3": 0.69742, + "recall_at_5": 0.72559 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/SIQA.json b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/SIQA.json new file mode 100644 index 000000000..8f3c3e34d --- /dev/null +++ b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/SIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 36.51301836967468, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.04888, + "map_at_1": 0.0261, + "map_at_10": 0.03963, + "map_at_100": 0.04343, + "map_at_1000": 0.04433, + "map_at_20": 0.04149, + "map_at_3": 0.03386, + "map_at_5": 0.03606, + "mrr_at_1": 0.026100307062436028, + "mrr_at_10": 0.03963339344608537, + "mrr_at_100": 0.04342763458669466, + "mrr_at_1000": 0.04433258322655591, + "mrr_at_20": 0.04148585693552994, + "mrr_at_3": 0.03386216308427159, + "mrr_at_5": 0.03606277720914365, + "nauc_map_at_1000_diff1": 0.19404015764164617, + "nauc_map_at_1000_max": 0.03840324299268857, + "nauc_map_at_1000_std": -0.040201750137555566, + "nauc_map_at_100_diff1": 0.19620440264836822, + "nauc_map_at_100_max": 0.03814718670528615, + "nauc_map_at_100_std": -0.042038709871048525, + "nauc_map_at_10_diff1": 0.20376397932732, + "nauc_map_at_10_max": 0.03613159202644634, + "nauc_map_at_10_std": -0.04232230726754121, + "nauc_map_at_1_diff1": 0.33854664527668243, + "nauc_map_at_1_max": 0.05572712060672099, + "nauc_map_at_1_std": -0.08211447750666306, + "nauc_map_at_20_diff1": 0.19928578877616496, + "nauc_map_at_20_max": 0.0350660560259541, + "nauc_map_at_20_std": -0.04530074585030131, + "nauc_map_at_3_diff1": 0.23971294332359785, + "nauc_map_at_3_max": 0.05118204742461026, + "nauc_map_at_3_std": -0.04731356315831868, + "nauc_map_at_5_diff1": 0.22510234611047295, + "nauc_map_at_5_max": 0.042720101532300214, + "nauc_map_at_5_std": -0.04616640290919424, + "nauc_mrr_at_1000_diff1": 0.19404015764164617, + "nauc_mrr_at_1000_max": 0.03840324299268857, + "nauc_mrr_at_1000_std": -0.040201750137555566, + "nauc_mrr_at_100_diff1": 0.19620440264836822, + "nauc_mrr_at_100_max": 0.03814718670528615, + "nauc_mrr_at_100_std": -0.042038709871048525, + "nauc_mrr_at_10_diff1": 0.20376397932732, + "nauc_mrr_at_10_max": 0.03613159202644634, + "nauc_mrr_at_10_std": -0.04232230726754121, + "nauc_mrr_at_1_diff1": 0.33854664527668243, + "nauc_mrr_at_1_max": 0.05572712060672099, + "nauc_mrr_at_1_std": -0.08211447750666306, + "nauc_mrr_at_20_diff1": 0.19928578877616496, + "nauc_mrr_at_20_max": 0.0350660560259541, + "nauc_mrr_at_20_std": -0.04530074585030131, + "nauc_mrr_at_3_diff1": 0.23971294332359785, + "nauc_mrr_at_3_max": 0.05118204742461026, + "nauc_mrr_at_3_std": -0.04731356315831868, + "nauc_mrr_at_5_diff1": 0.22510234611047295, + "nauc_mrr_at_5_max": 0.042720101532300214, + "nauc_mrr_at_5_std": -0.04616640290919424, + "nauc_ndcg_at_1000_diff1": 0.10430688131078128, + "nauc_ndcg_at_1000_max": 0.038541139762939665, + "nauc_ndcg_at_1000_std": 0.0056682247159925165, + "nauc_ndcg_at_100_diff1": 0.13874965601168673, + "nauc_ndcg_at_100_max": 0.041693681305731485, + "nauc_ndcg_at_100_std": -0.019937067533454558, + "nauc_ndcg_at_10_diff1": 0.15886336813675897, + "nauc_ndcg_at_10_max": 0.024606895125900446, + "nauc_ndcg_at_10_std": -0.031183717158746533, + "nauc_ndcg_at_1_diff1": 0.33854664527668243, + "nauc_ndcg_at_1_max": 0.05572712060672099, + "nauc_ndcg_at_1_std": -0.08211447750666306, + "nauc_ndcg_at_20_diff1": 0.15101216468190526, + "nauc_ndcg_at_20_max": 0.023361953582333318, + "nauc_ndcg_at_20_std": -0.03969972244450772, + "nauc_ndcg_at_3_diff1": 0.21722805746698923, + "nauc_ndcg_at_3_max": 0.048703872168810614, + "nauc_ndcg_at_3_std": -0.03943352263043316, + "nauc_ndcg_at_5_diff1": 0.195110820801632, + "nauc_ndcg_at_5_max": 0.03638110761618801, + "nauc_ndcg_at_5_std": -0.037545773522186694, + "nauc_precision_at_1000_diff1": -0.00559366540575826, + "nauc_precision_at_1000_max": 0.03886540084267212, + "nauc_precision_at_1000_std": 0.07329224375373032, + "nauc_precision_at_100_diff1": 0.07792160376824021, + "nauc_precision_at_100_max": 0.05460502256269195, + "nauc_precision_at_100_std": 0.0116946969292063, + "nauc_precision_at_10_diff1": 0.08537150349983526, + "nauc_precision_at_10_max": 0.004906667234255891, + "nauc_precision_at_10_std": -0.01345766558030241, + "nauc_precision_at_1_diff1": 0.33854664527668243, + "nauc_precision_at_1_max": 0.05572712060672099, + "nauc_precision_at_1_std": -0.08211447750666306, + "nauc_precision_at_20_diff1": 0.08588921360419488, + "nauc_precision_at_20_max": 0.00736544748442157, + "nauc_precision_at_20_std": -0.034555531428382566, + "nauc_precision_at_3_diff1": 0.16732645250331082, + "nauc_precision_at_3_max": 0.042829015989267485, + "nauc_precision_at_3_std": -0.0219547037153523, + "nauc_precision_at_5_diff1": 0.13446927060587274, + "nauc_precision_at_5_max": 0.02315354136020454, + "nauc_precision_at_5_std": -0.02025333703779539, + "nauc_recall_at_1000_diff1": -0.005593665405757973, + "nauc_recall_at_1000_max": 0.03886540084267253, + "nauc_recall_at_1000_std": 0.07329224375373092, + "nauc_recall_at_100_diff1": 0.07792160376824024, + "nauc_recall_at_100_max": 0.05460502256269204, + "nauc_recall_at_100_std": 0.011694696929206314, + "nauc_recall_at_10_diff1": 0.0853715034998351, + "nauc_recall_at_10_max": 0.004906667234255801, + "nauc_recall_at_10_std": -0.013457665580302395, + "nauc_recall_at_1_diff1": 0.33854664527668243, + "nauc_recall_at_1_max": 0.05572712060672099, + "nauc_recall_at_1_std": -0.08211447750666306, + "nauc_recall_at_20_diff1": 0.08588921360419467, + "nauc_recall_at_20_max": 0.007365447484421394, + "nauc_recall_at_20_std": -0.03455553142838276, + "nauc_recall_at_3_diff1": 0.1673264525033109, + "nauc_recall_at_3_max": 0.04282901598926764, + "nauc_recall_at_3_std": -0.021954703715352217, + "nauc_recall_at_5_diff1": 0.13446927060587263, + "nauc_recall_at_5_max": 0.023153541360204463, + "nauc_recall_at_5_std": -0.020253337037795468, + "ndcg_at_1": 0.0261, + "ndcg_at_10": 0.04888, + "ndcg_at_100": 0.07126, + "ndcg_at_1000": 0.10151, + "ndcg_at_20": 0.05579, + "ndcg_at_3": 0.03646, + "ndcg_at_5": 0.04045, + "precision_at_1": 0.0261, + "precision_at_10": 0.00793, + "precision_at_100": 0.00193, + "precision_at_1000": 0.00045, + "precision_at_20": 0.00535, + "precision_at_3": 0.01467, + "precision_at_5": 0.01075, + "recall_at_1": 0.0261, + "recall_at_10": 0.07932, + "recall_at_100": 0.19345, + "recall_at_1000": 0.44524, + "recall_at_20": 0.10696, + "recall_at_3": 0.04401, + "recall_at_5": 0.05374 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/SpartQA.json b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/SpartQA.json new file mode 100644 index 000000000..ec9cf10ff --- /dev/null +++ b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/SpartQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 30.37383723258972, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07492, + "map_at_1": 0.01076, + "map_at_10": 0.04432, + "map_at_100": 0.05398, + "map_at_1000": 0.05511, + "map_at_20": 0.05009, + "map_at_3": 0.02762, + "map_at_5": 0.03576, + "mrr_at_1": 0.014468558708959377, + "mrr_at_10": 0.06286867000556468, + "mrr_at_100": 0.07417167731424383, + "mrr_at_1000": 0.07526573253035114, + "mrr_at_20": 0.06969359743710819, + "mrr_at_3": 0.03927842700797625, + "mrr_at_5": 0.05099239473196065, + "nauc_map_at_1000_diff1": 0.05111079321515993, + "nauc_map_at_1000_max": -0.09715353252680807, + "nauc_map_at_1000_std": 0.5730378310495571, + "nauc_map_at_100_diff1": 0.050080186695561746, + "nauc_map_at_100_max": -0.09629467087941822, + "nauc_map_at_100_std": 0.5700754796573002, + "nauc_map_at_10_diff1": 0.0347055850575149, + "nauc_map_at_10_max": -0.1122296774020076, + "nauc_map_at_10_std": 0.5687839619329802, + "nauc_map_at_1_diff1": 0.05312016153249039, + "nauc_map_at_1_max": -0.2204621280084663, + "nauc_map_at_1_std": 0.5963529752318756, + "nauc_map_at_20_diff1": 0.04042292623932624, + "nauc_map_at_20_max": -0.10508864015538658, + "nauc_map_at_20_std": 0.5683535081428635, + "nauc_map_at_3_diff1": 0.044335917694470706, + "nauc_map_at_3_max": -0.14537704007077143, + "nauc_map_at_3_std": 0.6158544642672931, + "nauc_map_at_5_diff1": 0.024754500283944558, + "nauc_map_at_5_max": -0.1421553053850475, + "nauc_map_at_5_std": 0.5943944549308551, + "nauc_mrr_at_1000_diff1": 0.08165887539332636, + "nauc_mrr_at_1000_max": -0.08222563459187253, + "nauc_mrr_at_1000_std": 0.5443514449273331, + "nauc_mrr_at_100_diff1": 0.08144514390100936, + "nauc_mrr_at_100_max": -0.08253959737682291, + "nauc_mrr_at_100_std": 0.5426796604071773, + "nauc_mrr_at_10_diff1": 0.06420174282371996, + "nauc_mrr_at_10_max": -0.1047593130990519, + "nauc_mrr_at_10_std": 0.548277506070713, + "nauc_mrr_at_1_diff1": 0.05773881839452445, + "nauc_mrr_at_1_max": -0.21507745800842099, + "nauc_mrr_at_1_std": 0.5859750479068336, + "nauc_mrr_at_20_diff1": 0.07341636959117513, + "nauc_mrr_at_20_max": -0.09212012206215545, + "nauc_mrr_at_20_std": 0.544032838846391, + "nauc_mrr_at_3_diff1": 0.06328279411687682, + "nauc_mrr_at_3_max": -0.1449079013512444, + "nauc_mrr_at_3_std": 0.6093922374388724, + "nauc_mrr_at_5_diff1": 0.047571184871256667, + "nauc_mrr_at_5_max": -0.1372762174076084, + "nauc_mrr_at_5_std": 0.5812895146154639, + "nauc_ndcg_at_1000_diff1": 0.11166214798986297, + "nauc_ndcg_at_1000_max": -0.03322860782135785, + "nauc_ndcg_at_1000_std": 0.5785239235947183, + "nauc_ndcg_at_100_diff1": 0.08975060986408612, + "nauc_ndcg_at_100_max": -0.029172579460574815, + "nauc_ndcg_at_100_std": 0.5386891995947048, + "nauc_ndcg_at_10_diff1": 0.03774242796627812, + "nauc_ndcg_at_10_max": -0.08585539393304259, + "nauc_ndcg_at_10_std": 0.537178495291056, + "nauc_ndcg_at_1_diff1": 0.05773881839452445, + "nauc_ndcg_at_1_max": -0.21507745800842099, + "nauc_ndcg_at_1_std": 0.5859750479068336, + "nauc_ndcg_at_20_diff1": 0.05369351654325242, + "nauc_ndcg_at_20_max": -0.06823305276541078, + "nauc_ndcg_at_20_std": 0.5330924873018242, + "nauc_ndcg_at_3_diff1": 0.03991192866830476, + "nauc_ndcg_at_3_max": -0.1389354813341555, + "nauc_ndcg_at_3_std": 0.6137779245360964, + "nauc_ndcg_at_5_diff1": 0.01899883126033539, + "nauc_ndcg_at_5_max": -0.13438827738324394, + "nauc_ndcg_at_5_std": 0.5829050416336644, + "nauc_precision_at_1000_diff1": 0.16567493243627165, + "nauc_precision_at_1000_max": 0.00790857203749484, + "nauc_precision_at_1000_std": 0.32693791985335985, + "nauc_precision_at_100_diff1": 0.12932470063223317, + "nauc_precision_at_100_max": 0.012289678964534584, + "nauc_precision_at_100_std": 0.42346460193579527, + "nauc_precision_at_10_diff1": 0.056089881538414606, + "nauc_precision_at_10_max": -0.059420887078218514, + "nauc_precision_at_10_std": 0.4999143243110502, + "nauc_precision_at_1_diff1": 0.05773881839452445, + "nauc_precision_at_1_max": -0.21507745800842099, + "nauc_precision_at_1_std": 0.5859750479068336, + "nauc_precision_at_20_diff1": 0.08389752929508223, + "nauc_precision_at_20_max": -0.034663211035064756, + "nauc_precision_at_20_std": 0.484286488086085, + "nauc_precision_at_3_diff1": 0.03772689951420597, + "nauc_precision_at_3_max": -0.12907052241669306, + "nauc_precision_at_3_std": 0.6037678444817082, + "nauc_precision_at_5_diff1": 0.011536878322082033, + "nauc_precision_at_5_max": -0.12682026969574167, + "nauc_precision_at_5_std": 0.5643249224864385, + "nauc_recall_at_1000_diff1": 0.1828492592679612, + "nauc_recall_at_1000_max": 0.06888290120007207, + "nauc_recall_at_1000_std": 0.5025091117759001, + "nauc_recall_at_100_diff1": 0.11591211410660388, + "nauc_recall_at_100_max": 0.05734096469195574, + "nauc_recall_at_100_std": 0.45736803941890436, + "nauc_recall_at_10_diff1": 0.023307880621019975, + "nauc_recall_at_10_max": -0.054243896401166274, + "nauc_recall_at_10_std": 0.48868428446588785, + "nauc_recall_at_1_diff1": 0.05312016153249039, + "nauc_recall_at_1_max": -0.2204621280084663, + "nauc_recall_at_1_std": 0.5963529752318756, + "nauc_recall_at_20_diff1": 0.04906750845914843, + "nauc_recall_at_20_max": -0.0296151040622392, + "nauc_recall_at_20_std": 0.47218032309838137, + "nauc_recall_at_3_diff1": 0.0175519563151169, + "nauc_recall_at_3_max": -0.129243441911071, + "nauc_recall_at_3_std": 0.6157247079475138, + "nauc_recall_at_5_diff1": -0.0014238164424170393, + "nauc_recall_at_5_max": -0.12610989951474316, + "nauc_recall_at_5_std": 0.5727532955286546, + "ndcg_at_1": 0.01447, + "ndcg_at_10": 0.07492, + "ndcg_at_100": 0.12505, + "ndcg_at_1000": 0.16182, + "ndcg_at_20": 0.09662, + "ndcg_at_3": 0.03645, + "ndcg_at_5": 0.05242, + "precision_at_1": 0.01447, + "precision_at_10": 0.0227, + "precision_at_100": 0.00587, + "precision_at_1000": 0.00106, + "precision_at_20": 0.01754, + "precision_at_3": 0.02449, + "precision_at_5": 0.02577, + "recall_at_1": 0.01076, + "recall_at_10": 0.1484, + "recall_at_100": 0.35754, + "recall_at_1000": 0.62168, + "recall_at_20": 0.2251, + "recall_at_3": 0.05064, + "recall_at_5": 0.08542 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL1.json b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL1.json new file mode 100644 index 000000000..b4b1c1b5e --- /dev/null +++ b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL1.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 10.734277725219727, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.00989, + "map_at_1": 0.0, + "map_at_10": 0.00518, + "map_at_100": 0.00896, + "map_at_1000": 0.01043, + "map_at_20": 0.00667, + "map_at_3": 0.00187, + "map_at_5": 0.00339, + "mrr_at_1": 0.0, + "mrr_at_10": 0.005184722222222221, + "mrr_at_100": 0.008958839677002055, + "mrr_at_1000": 0.010426533146251549, + "mrr_at_20": 0.006666239493435701, + "mrr_at_3": 0.0018749999999999997, + "mrr_at_5": 0.003387499999999999, + "nauc_map_at_1000_diff1": 0.25819798473671124, + "nauc_map_at_1000_max": 0.5084400019984511, + "nauc_map_at_1000_std": 0.24253841718577998, + "nauc_map_at_100_diff1": 0.27156906527297847, + "nauc_map_at_100_max": 0.5189904766087506, + "nauc_map_at_100_std": 0.24697418584133274, + "nauc_map_at_10_diff1": 0.33478544158384194, + "nauc_map_at_10_max": 0.649811243400096, + "nauc_map_at_10_std": 0.3290940651474132, + "nauc_map_at_1_diff1": NaN, + "nauc_map_at_1_max": NaN, + "nauc_map_at_1_std": NaN, + "nauc_map_at_20_diff1": 0.33350412173804445, + "nauc_map_at_20_max": 0.6163482554526557, + "nauc_map_at_20_std": 0.3071226922978085, + "nauc_map_at_3_diff1": 0.34211608979518826, + "nauc_map_at_3_max": 0.8044182094624811, + "nauc_map_at_3_std": 0.32886146140774536, + "nauc_map_at_5_diff1": 0.3724323451981501, + "nauc_map_at_5_max": 0.6888488015548254, + "nauc_map_at_5_std": 0.3322062895971057, + "nauc_mrr_at_1000_diff1": 0.25819798473671124, + "nauc_mrr_at_1000_max": 0.5084400019984511, + "nauc_mrr_at_1000_std": 0.24253841718577998, + "nauc_mrr_at_100_diff1": 0.27156906527297847, + "nauc_mrr_at_100_max": 0.5189904766087506, + "nauc_mrr_at_100_std": 0.24697418584133274, + "nauc_mrr_at_10_diff1": 0.33478544158384194, + "nauc_mrr_at_10_max": 0.649811243400096, + "nauc_mrr_at_10_std": 0.3290940651474132, + "nauc_mrr_at_1_diff1": NaN, + "nauc_mrr_at_1_max": NaN, + "nauc_mrr_at_1_std": NaN, + "nauc_mrr_at_20_diff1": 0.33350412173804445, + "nauc_mrr_at_20_max": 0.6163482554526557, + "nauc_mrr_at_20_std": 0.3071226922978085, + "nauc_mrr_at_3_diff1": 0.34211608979518826, + "nauc_mrr_at_3_max": 0.8044182094624811, + "nauc_mrr_at_3_std": 0.32886146140774536, + "nauc_mrr_at_5_diff1": 0.3724323451981501, + "nauc_mrr_at_5_max": 0.6888488015548254, + "nauc_mrr_at_5_std": 0.3322062895971057, + "nauc_ndcg_at_1000_diff1": 0.16217359996155606, + "nauc_ndcg_at_1000_max": 0.38289480331912956, + "nauc_ndcg_at_1000_std": 0.18799377982267065, + "nauc_ndcg_at_100_diff1": 0.19497988007810202, + "nauc_ndcg_at_100_max": 0.3785421823783113, + "nauc_ndcg_at_100_std": 0.16849961492447774, + "nauc_ndcg_at_10_diff1": 0.32550741395057414, + "nauc_ndcg_at_10_max": 0.6272381559064458, + "nauc_ndcg_at_10_std": 0.327536713116621, + "nauc_ndcg_at_1_diff1": NaN, + "nauc_ndcg_at_1_max": NaN, + "nauc_ndcg_at_1_std": NaN, + "nauc_ndcg_at_20_diff1": 0.32837578447518456, + "nauc_ndcg_at_20_max": 0.5804975436819747, + "nauc_ndcg_at_20_std": 0.29240140183092844, + "nauc_ndcg_at_3_diff1": 0.34847407347122683, + "nauc_ndcg_at_3_max": 0.8097968828566656, + "nauc_ndcg_at_3_std": 0.325961196342254, + "nauc_ndcg_at_5_diff1": 0.3758802832251958, + "nauc_ndcg_at_5_max": 0.6719631067332522, + "nauc_ndcg_at_5_std": 0.33309805318488095, + "nauc_precision_at_1000_diff1": 0.12667810758903822, + "nauc_precision_at_1000_max": 0.34906579005748867, + "nauc_precision_at_1000_std": 0.18232940031818995, + "nauc_precision_at_100_diff1": 0.156664184884148, + "nauc_precision_at_100_max": 0.30972096913274694, + "nauc_precision_at_100_std": 0.12958896890918672, + "nauc_precision_at_10_diff1": 0.3168020267899527, + "nauc_precision_at_10_max": 0.6089657592206561, + "nauc_precision_at_10_std": 0.32608718086314004, + "nauc_precision_at_1_diff1": NaN, + "nauc_precision_at_1_max": NaN, + "nauc_precision_at_1_std": NaN, + "nauc_precision_at_20_diff1": 0.325428767339151, + "nauc_precision_at_20_max": 0.5563860460560217, + "nauc_precision_at_20_std": 0.2812395745049354, + "nauc_precision_at_3_diff1": 0.35721312941597344, + "nauc_precision_at_3_max": 0.8171898756819604, + "nauc_precision_at_3_std": 0.32197477864233964, + "nauc_precision_at_5_diff1": 0.3787019646423993, + "nauc_precision_at_5_max": 0.653084101004681, + "nauc_precision_at_5_std": 0.33446620755448236, + "nauc_recall_at_1000_diff1": 0.12667810758903933, + "nauc_recall_at_1000_max": 0.3490657900574894, + "nauc_recall_at_1000_std": 0.18232940031819028, + "nauc_recall_at_100_diff1": 0.1566641848841479, + "nauc_recall_at_100_max": 0.3097209691327468, + "nauc_recall_at_100_std": 0.12958896890918684, + "nauc_recall_at_10_diff1": 0.3168020267899529, + "nauc_recall_at_10_max": 0.608965759220656, + "nauc_recall_at_10_std": 0.3260871808631402, + "nauc_recall_at_1_diff1": NaN, + "nauc_recall_at_1_max": NaN, + "nauc_recall_at_1_std": NaN, + "nauc_recall_at_20_diff1": 0.3254287673391512, + "nauc_recall_at_20_max": 0.5563860460560222, + "nauc_recall_at_20_std": 0.2812395745049354, + "nauc_recall_at_3_diff1": 0.35721312941597355, + "nauc_recall_at_3_max": 0.8171898756819608, + "nauc_recall_at_3_std": 0.3219747786423398, + "nauc_recall_at_5_diff1": 0.3787019646423992, + "nauc_recall_at_5_max": 0.6530841010046803, + "nauc_recall_at_5_std": 0.33446620755448236, + "ndcg_at_1": 0.0, + "ndcg_at_10": 0.00989, + "ndcg_at_100": 0.03391, + "ndcg_at_1000": 0.09041, + "ndcg_at_20": 0.01528, + "ndcg_at_3": 0.00254, + "ndcg_at_5": 0.0053, + "precision_at_1": 0.0, + "precision_at_10": 0.0026, + "precision_at_100": 0.00152, + "precision_at_1000": 0.00064, + "precision_at_20": 0.00236, + "precision_at_3": 0.0015, + "precision_at_5": 0.00225, + "recall_at_1": 0.0, + "recall_at_10": 0.026, + "recall_at_100": 0.152, + "recall_at_1000": 0.636, + "recall_at_20": 0.04725, + "recall_at_3": 0.0045, + "recall_at_5": 0.01125 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL2Fact.json b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL2Fact.json new file mode 100644 index 000000000..2cb087817 --- /dev/null +++ b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL2Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 75.41699862480164, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.33234, + "map_at_1": 0.14879, + "map_at_10": 0.26604, + "map_at_100": 0.27734, + "map_at_1000": 0.27801, + "map_at_20": 0.27304, + "map_at_3": 0.22966, + "map_at_5": 0.25051, + "mrr_at_1": 0.1487863627941449, + "mrr_at_10": 0.2660431574272588, + "mrr_at_100": 0.27733654906425104, + "mrr_at_1000": 0.2780129322656861, + "mrr_at_20": 0.2730449461561239, + "mrr_at_3": 0.22966462849731345, + "mrr_at_5": 0.25050954233833667, + "nauc_map_at_1000_diff1": 0.042313908880934795, + "nauc_map_at_1000_max": 0.08441750141171367, + "nauc_map_at_1000_std": 0.03585224630856188, + "nauc_map_at_100_diff1": 0.042150026007992565, + "nauc_map_at_100_max": 0.08466598961408495, + "nauc_map_at_100_std": 0.03632858780793204, + "nauc_map_at_10_diff1": 0.04205365478095683, + "nauc_map_at_10_max": 0.08327082840706831, + "nauc_map_at_10_std": 0.031691768726596355, + "nauc_map_at_1_diff1": 0.06579248381003683, + "nauc_map_at_1_max": 0.0312959728510955, + "nauc_map_at_1_std": -0.0011216625899934328, + "nauc_map_at_20_diff1": 0.042207378241339334, + "nauc_map_at_20_max": 0.08507563891514201, + "nauc_map_at_20_std": 0.036190091789959314, + "nauc_map_at_3_diff1": 0.0496597106763098, + "nauc_map_at_3_max": 0.07240436633314715, + "nauc_map_at_3_std": 0.012180384633863459, + "nauc_map_at_5_diff1": 0.04404700275779296, + "nauc_map_at_5_max": 0.07647675376313016, + "nauc_map_at_5_std": 0.018882051264746243, + "nauc_mrr_at_1000_diff1": 0.042313908670483416, + "nauc_mrr_at_1000_max": 0.08441750077334044, + "nauc_mrr_at_1000_std": 0.03585224698488132, + "nauc_mrr_at_100_diff1": 0.042150026007992565, + "nauc_mrr_at_100_max": 0.08466598961408495, + "nauc_mrr_at_100_std": 0.03632858780793204, + "nauc_mrr_at_10_diff1": 0.04205365478095683, + "nauc_mrr_at_10_max": 0.08327082840706831, + "nauc_mrr_at_10_std": 0.031691768726596355, + "nauc_mrr_at_1_diff1": 0.06579248381003683, + "nauc_mrr_at_1_max": 0.0312959728510955, + "nauc_mrr_at_1_std": -0.0011216625899934328, + "nauc_mrr_at_20_diff1": 0.042207378241339334, + "nauc_mrr_at_20_max": 0.08507563891514201, + "nauc_mrr_at_20_std": 0.036190091789959314, + "nauc_mrr_at_3_diff1": 0.0496597106763098, + "nauc_mrr_at_3_max": 0.07240436633314715, + "nauc_mrr_at_3_std": 0.012180384633863459, + "nauc_mrr_at_5_diff1": 0.04404700275779296, + "nauc_mrr_at_5_max": 0.07647675376313016, + "nauc_mrr_at_5_std": 0.018882051264746243, + "nauc_ndcg_at_1000_diff1": 0.037169288314676904, + "nauc_ndcg_at_1000_max": 0.10623068365929167, + "nauc_ndcg_at_1000_std": 0.06240748728244834, + "nauc_ndcg_at_100_diff1": 0.03270101203686195, + "nauc_ndcg_at_100_max": 0.11400452917554414, + "nauc_ndcg_at_100_std": 0.0766801817333811, + "nauc_ndcg_at_10_diff1": 0.0318526587904726, + "nauc_ndcg_at_10_max": 0.10778588380572396, + "nauc_ndcg_at_10_std": 0.05811146736748382, + "nauc_ndcg_at_1_diff1": 0.06579248381003683, + "nauc_ndcg_at_1_max": 0.0312959728510955, + "nauc_ndcg_at_1_std": -0.0011216625899934328, + "nauc_ndcg_at_20_diff1": 0.03147364372172023, + "nauc_ndcg_at_20_max": 0.11503871638835818, + "nauc_ndcg_at_20_std": 0.07551854576494763, + "nauc_ndcg_at_3_diff1": 0.04649797727018203, + "nauc_ndcg_at_3_max": 0.08409572462183527, + "nauc_ndcg_at_3_std": 0.016510484454294642, + "nauc_ndcg_at_5_diff1": 0.03694088592824708, + "nauc_ndcg_at_5_max": 0.09104461912424056, + "nauc_ndcg_at_5_std": 0.027976162464419054, + "nauc_precision_at_1000_diff1": 0.0688842879996053, + "nauc_precision_at_1000_max": 0.38252845820381043, + "nauc_precision_at_1000_std": 0.3600716244168305, + "nauc_precision_at_100_diff1": -0.008075432098776099, + "nauc_precision_at_100_max": 0.26923453249968154, + "nauc_precision_at_100_std": 0.30763567573896733, + "nauc_precision_at_10_diff1": 0.0035349661106700105, + "nauc_precision_at_10_max": 0.17638813786318788, + "nauc_precision_at_10_std": 0.1363321878530331, + "nauc_precision_at_1_diff1": 0.06579248381003683, + "nauc_precision_at_1_max": 0.0312959728510955, + "nauc_precision_at_1_std": -0.0011216625899934328, + "nauc_precision_at_20_diff1": -0.0033988911343350342, + "nauc_precision_at_20_max": 0.21502983304656656, + "nauc_precision_at_20_std": 0.21726377373000716, + "nauc_precision_at_3_diff1": 0.03927361578307819, + "nauc_precision_at_3_max": 0.11201875235944136, + "nauc_precision_at_3_std": 0.026977633252415752, + "nauc_precision_at_5_diff1": 0.01947654442157814, + "nauc_precision_at_5_max": 0.1261787312793756, + "nauc_precision_at_5_std": 0.0508086322501904, + "nauc_recall_at_1000_diff1": 0.06888428799960472, + "nauc_recall_at_1000_max": 0.3825284582038123, + "nauc_recall_at_1000_std": 0.3600716244168345, + "nauc_recall_at_100_diff1": -0.008075432098775953, + "nauc_recall_at_100_max": 0.26923453249968105, + "nauc_recall_at_100_std": 0.3076356757389669, + "nauc_recall_at_10_diff1": 0.0035349661106699117, + "nauc_recall_at_10_max": 0.1763881378631877, + "nauc_recall_at_10_std": 0.1363321878530331, + "nauc_recall_at_1_diff1": 0.06579248381003683, + "nauc_recall_at_1_max": 0.0312959728510955, + "nauc_recall_at_1_std": -0.0011216625899934328, + "nauc_recall_at_20_diff1": -0.003398891134335033, + "nauc_recall_at_20_max": 0.21502983304656637, + "nauc_recall_at_20_std": 0.21726377373000708, + "nauc_recall_at_3_diff1": 0.039273615783078156, + "nauc_recall_at_3_max": 0.1120187523594411, + "nauc_recall_at_3_std": 0.026977633252415846, + "nauc_recall_at_5_diff1": 0.01947654442157791, + "nauc_recall_at_5_max": 0.1261787312793755, + "nauc_recall_at_5_std": 0.050808632250190486, + "ndcg_at_1": 0.14879, + "ndcg_at_10": 0.33234, + "ndcg_at_100": 0.3886, + "ndcg_at_1000": 0.40725, + "ndcg_at_20": 0.35767, + "ndcg_at_3": 0.25702, + "ndcg_at_5": 0.29446, + "precision_at_1": 0.14879, + "precision_at_10": 0.05447, + "precision_at_100": 0.00811, + "precision_at_1000": 0.00096, + "precision_at_20": 0.03223, + "precision_at_3": 0.11216, + "precision_at_5": 0.08542, + "recall_at_1": 0.14879, + "recall_at_10": 0.54475, + "recall_at_100": 0.81101, + "recall_at_1000": 0.95942, + "recall_at_20": 0.64462, + "recall_at_3": 0.33648, + "recall_at_5": 0.42709 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL2Pure.json b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL2Pure.json new file mode 100644 index 000000000..ec332d1e5 --- /dev/null +++ b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL2Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 19.242865562438965, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.00677, + "map_at_1": 0.00111, + "map_at_10": 0.00434, + "map_at_100": 0.006, + "map_at_1000": 0.00682, + "map_at_20": 0.00498, + "map_at_3": 0.00275, + "map_at_5": 0.00365, + "mrr_at_1": 0.0011117287381878821, + "mrr_at_10": 0.004338389052118901, + "mrr_at_100": 0.005996673147605992, + "mrr_at_1000": 0.006818649575270293, + "mrr_at_20": 0.004983746246285461, + "mrr_at_3": 0.0027484404916311538, + "mrr_at_5": 0.0036470878883330237, + "nauc_map_at_1000_diff1": 0.022703693804016333, + "nauc_map_at_1000_max": 0.0024347178226237273, + "nauc_map_at_1000_std": -0.14117510964682048, + "nauc_map_at_100_diff1": 0.028417662349410074, + "nauc_map_at_100_max": 0.001689445770161767, + "nauc_map_at_100_std": -0.15253770492953958, + "nauc_map_at_10_diff1": 0.058503235927609414, + "nauc_map_at_10_max": -0.0023914619597652006, + "nauc_map_at_10_std": -0.1823942848724004, + "nauc_map_at_1_diff1": 0.11541057523175788, + "nauc_map_at_1_max": -0.0567400415386506, + "nauc_map_at_1_std": -0.25130725744350596, + "nauc_map_at_20_diff1": 0.04043821555739006, + "nauc_map_at_20_max": 0.0035503700925812788, + "nauc_map_at_20_std": -0.16208282560749054, + "nauc_map_at_3_diff1": 0.09132256944505764, + "nauc_map_at_3_max": -0.008505707704070333, + "nauc_map_at_3_std": -0.16159626239181865, + "nauc_map_at_5_diff1": 0.06207274087679263, + "nauc_map_at_5_max": -0.0009686835313007612, + "nauc_map_at_5_std": -0.1871570642673465, + "nauc_mrr_at_1000_diff1": 0.022703693804016333, + "nauc_mrr_at_1000_max": 0.0024347178226237273, + "nauc_mrr_at_1000_std": -0.14117510964682048, + "nauc_mrr_at_100_diff1": 0.028417662349410074, + "nauc_mrr_at_100_max": 0.001689445770161767, + "nauc_mrr_at_100_std": -0.15253770492953958, + "nauc_mrr_at_10_diff1": 0.058503235927609414, + "nauc_mrr_at_10_max": -0.0023914619597652006, + "nauc_mrr_at_10_std": -0.1823942848724004, + "nauc_mrr_at_1_diff1": 0.11541057523175788, + "nauc_mrr_at_1_max": -0.0567400415386506, + "nauc_mrr_at_1_std": -0.25130725744350596, + "nauc_mrr_at_20_diff1": 0.04043821555739006, + "nauc_mrr_at_20_max": 0.0035503700925812788, + "nauc_mrr_at_20_std": -0.16208282560749054, + "nauc_mrr_at_3_diff1": 0.09132256944505764, + "nauc_mrr_at_3_max": -0.008505707704070333, + "nauc_mrr_at_3_std": -0.16159626239181865, + "nauc_mrr_at_5_diff1": 0.06207274087679263, + "nauc_mrr_at_5_max": -0.0009686835313007612, + "nauc_mrr_at_5_std": -0.1871570642673465, + "nauc_ndcg_at_1000_diff1": -0.030479708448302143, + "nauc_ndcg_at_1000_max": 0.018626188289555846, + "nauc_ndcg_at_1000_std": -0.05361203795906396, + "nauc_ndcg_at_100_diff1": -0.0026885368628520967, + "nauc_ndcg_at_100_max": 0.006050679606384858, + "nauc_ndcg_at_100_std": -0.12008453530857284, + "nauc_ndcg_at_10_diff1": 0.048722418861036086, + "nauc_ndcg_at_10_max": 0.005358288173036365, + "nauc_ndcg_at_10_std": -0.18336234377200591, + "nauc_ndcg_at_1_diff1": 0.11541057523175788, + "nauc_ndcg_at_1_max": -0.0567400415386506, + "nauc_ndcg_at_1_std": -0.25130725744350596, + "nauc_ndcg_at_20_diff1": 0.01566571428681214, + "nauc_ndcg_at_20_max": 0.01499936299238303, + "nauc_ndcg_at_20_std": -0.1409775746215031, + "nauc_ndcg_at_3_diff1": 0.08777814884739443, + "nauc_ndcg_at_3_max": 0.004723520109740435, + "nauc_ndcg_at_3_std": -0.15019463399338664, + "nauc_ndcg_at_5_diff1": 0.050178441592798224, + "nauc_ndcg_at_5_max": 0.011260894542533307, + "nauc_ndcg_at_5_std": -0.1890627151271941, + "nauc_precision_at_1000_diff1": -0.047176835147961754, + "nauc_precision_at_1000_max": 0.026748906955269856, + "nauc_precision_at_1000_std": -0.019256844723236605, + "nauc_precision_at_100_diff1": -0.015423606219065722, + "nauc_precision_at_100_max": 0.005711163391022172, + "nauc_precision_at_100_std": -0.10445421358356273, + "nauc_precision_at_10_diff1": 0.03966900675949178, + "nauc_precision_at_10_max": 0.011952930872556132, + "nauc_precision_at_10_std": -0.18599022049986913, + "nauc_precision_at_1_diff1": 0.11541057523175788, + "nauc_precision_at_1_max": -0.0567400415386506, + "nauc_precision_at_1_std": -0.25130725744350596, + "nauc_precision_at_20_diff1": -0.005702156557512661, + "nauc_precision_at_20_max": 0.02363645079483618, + "nauc_precision_at_20_std": -0.1204701382395429, + "nauc_precision_at_3_diff1": 0.08217375055925755, + "nauc_precision_at_3_max": 0.026530834433394997, + "nauc_precision_at_3_std": -0.13242742809674654, + "nauc_precision_at_5_diff1": 0.03465016016180569, + "nauc_precision_at_5_max": 0.02669777789403918, + "nauc_precision_at_5_std": -0.1934923333159723, + "nauc_recall_at_1000_diff1": -0.04717683514796139, + "nauc_recall_at_1000_max": 0.02674890695527004, + "nauc_recall_at_1000_std": -0.01925684472323646, + "nauc_recall_at_100_diff1": -0.015423606219065739, + "nauc_recall_at_100_max": 0.005711163391022, + "nauc_recall_at_100_std": -0.10445421358356291, + "nauc_recall_at_10_diff1": 0.039669006759491685, + "nauc_recall_at_10_max": 0.011952930872555834, + "nauc_recall_at_10_std": -0.18599022049986938, + "nauc_recall_at_1_diff1": 0.11541057523175788, + "nauc_recall_at_1_max": -0.0567400415386506, + "nauc_recall_at_1_std": -0.25130725744350596, + "nauc_recall_at_20_diff1": -0.0057021565575129, + "nauc_recall_at_20_max": 0.023636450794835978, + "nauc_recall_at_20_std": -0.12047013823954306, + "nauc_recall_at_3_diff1": 0.08217375055925749, + "nauc_recall_at_3_max": 0.026530834433395052, + "nauc_recall_at_3_std": -0.13242742809674646, + "nauc_recall_at_5_diff1": 0.03465016016180543, + "nauc_recall_at_5_max": 0.026697777894038967, + "nauc_recall_at_5_std": -0.19349233331597251, + "ndcg_at_1": 0.00111, + "ndcg_at_10": 0.00677, + "ndcg_at_100": 0.01779, + "ndcg_at_1000": 0.04997, + "ndcg_at_20": 0.00914, + "ndcg_at_3": 0.00337, + "ndcg_at_5": 0.00502, + "precision_at_1": 0.00111, + "precision_at_10": 0.00148, + "precision_at_100": 0.00074, + "precision_at_1000": 0.00035, + "precision_at_20": 0.00121, + "precision_at_3": 0.00173, + "precision_at_5": 0.00185, + "recall_at_1": 0.00111, + "recall_at_10": 0.01482, + "recall_at_100": 0.07374, + "recall_at_1000": 0.35038, + "recall_at_20": 0.02427, + "recall_at_3": 0.00519, + "recall_at_5": 0.00926 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL3Fact.json b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL3Fact.json new file mode 100644 index 000000000..9b5112e42 --- /dev/null +++ b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL3Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 68.57438063621521, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.30051, + "map_at_1": 0.11432, + "map_at_10": 0.23184, + "map_at_100": 0.24276, + "map_at_1000": 0.24346, + "map_at_20": 0.23874, + "map_at_3": 0.19272, + "map_at_5": 0.21492, + "mrr_at_1": 0.11432444645277903, + "mrr_at_10": 0.23183712406487034, + "mrr_at_100": 0.2427572530018055, + "mrr_at_1000": 0.2434569367238391, + "mrr_at_20": 0.2387368519809959, + "mrr_at_3": 0.19272480795300587, + "mrr_at_5": 0.21492318120199014, + "nauc_map_at_1000_diff1": 0.013134937094442724, + "nauc_map_at_1000_max": 0.0962933645697882, + "nauc_map_at_1000_std": 0.07336888381621556, + "nauc_map_at_100_diff1": 0.012823767527517073, + "nauc_map_at_100_max": 0.09667334028849157, + "nauc_map_at_100_std": 0.07401452012534562, + "nauc_map_at_10_diff1": 0.013154607308724638, + "nauc_map_at_10_max": 0.09457822413222601, + "nauc_map_at_10_std": 0.06970108747894982, + "nauc_map_at_1_diff1": 0.038644501526563506, + "nauc_map_at_1_max": 0.03406766330980977, + "nauc_map_at_1_std": 0.010790996092590491, + "nauc_map_at_20_diff1": 0.012847249421188589, + "nauc_map_at_20_max": 0.09685668499488599, + "nauc_map_at_20_std": 0.0742771623660682, + "nauc_map_at_3_diff1": 0.019370963496954996, + "nauc_map_at_3_max": 0.07003314822588419, + "nauc_map_at_3_std": 0.032165131885122905, + "nauc_map_at_5_diff1": 0.016326031738962497, + "nauc_map_at_5_max": 0.08471229494768483, + "nauc_map_at_5_std": 0.05333455117026215, + "nauc_mrr_at_1000_diff1": 0.013134937094442724, + "nauc_mrr_at_1000_max": 0.0962933645697882, + "nauc_mrr_at_1000_std": 0.07336888381621556, + "nauc_mrr_at_100_diff1": 0.012823767527517073, + "nauc_mrr_at_100_max": 0.09667334028849157, + "nauc_mrr_at_100_std": 0.07401452012534562, + "nauc_mrr_at_10_diff1": 0.013154607308724638, + "nauc_mrr_at_10_max": 0.09457822413222601, + "nauc_mrr_at_10_std": 0.06970108747894982, + "nauc_mrr_at_1_diff1": 0.038644501526563506, + "nauc_mrr_at_1_max": 0.03406766330980977, + "nauc_mrr_at_1_std": 0.010790996092590491, + "nauc_mrr_at_20_diff1": 0.012847249421188589, + "nauc_mrr_at_20_max": 0.09685668499488599, + "nauc_mrr_at_20_std": 0.0742771623660682, + "nauc_mrr_at_3_diff1": 0.019370963496954996, + "nauc_mrr_at_3_max": 0.07003314822588419, + "nauc_mrr_at_3_std": 0.032165131885122905, + "nauc_mrr_at_5_diff1": 0.016326031738962497, + "nauc_mrr_at_5_max": 0.08471229494768483, + "nauc_mrr_at_5_std": 0.05333455117026215, + "nauc_ndcg_at_1000_diff1": 0.007287896657875496, + "nauc_ndcg_at_1000_max": 0.12415606594963452, + "nauc_ndcg_at_1000_std": 0.10850116578139887, + "nauc_ndcg_at_100_diff1": -0.0008231054278060389, + "nauc_ndcg_at_100_max": 0.1332515861100407, + "nauc_ndcg_at_100_std": 0.12579315721657533, + "nauc_ndcg_at_10_diff1": 0.002018165465489979, + "nauc_ndcg_at_10_max": 0.12538561653457625, + "nauc_ndcg_at_10_std": 0.11015857539261714, + "nauc_ndcg_at_1_diff1": 0.038644501526563506, + "nauc_ndcg_at_1_max": 0.03406766330980977, + "nauc_ndcg_at_1_std": 0.010790996092590491, + "nauc_ndcg_at_20_diff1": 0.00098165083391897, + "nauc_ndcg_at_20_max": 0.13472208908663064, + "nauc_ndcg_at_20_std": 0.12696210886847556, + "nauc_ndcg_at_3_diff1": 0.01438990009944873, + "nauc_ndcg_at_3_max": 0.0799723996183634, + "nauc_ndcg_at_3_std": 0.03861979077546565, + "nauc_ndcg_at_5_diff1": 0.01000318336931375, + "nauc_ndcg_at_5_max": 0.10383931310497652, + "nauc_ndcg_at_5_std": 0.07341185573621907, + "nauc_precision_at_1000_diff1": 0.03826116653305184, + "nauc_precision_at_1000_max": 0.362601597774564, + "nauc_precision_at_1000_std": 0.34396294575617925, + "nauc_precision_at_100_diff1": -0.06411842197104656, + "nauc_precision_at_100_max": 0.28609888351972257, + "nauc_precision_at_100_std": 0.35413838655304547, + "nauc_precision_at_10_diff1": -0.02614710878862861, + "nauc_precision_at_10_max": 0.20292929422529946, + "nauc_precision_at_10_std": 0.21578667184495312, + "nauc_precision_at_1_diff1": 0.038644501526563506, + "nauc_precision_at_1_max": 0.03406766330980977, + "nauc_precision_at_1_std": 0.010790996092590491, + "nauc_precision_at_20_diff1": -0.03268957862286433, + "nauc_precision_at_20_max": 0.24671194908785984, + "nauc_precision_at_20_std": 0.28811741923058143, + "nauc_precision_at_3_diff1": 0.0033353511409591405, + "nauc_precision_at_3_max": 0.10216798690934813, + "nauc_precision_at_3_std": 0.053142981684902973, + "nauc_precision_at_5_diff1": -0.0037132169145803295, + "nauc_precision_at_5_max": 0.14725426038268102, + "nauc_precision_at_5_std": 0.12004830080994579, + "nauc_recall_at_1000_diff1": 0.03826116653304679, + "nauc_recall_at_1000_max": 0.3626015977745635, + "nauc_recall_at_1000_std": 0.3439629457561741, + "nauc_recall_at_100_diff1": -0.06411842197104592, + "nauc_recall_at_100_max": 0.28609888351972185, + "nauc_recall_at_100_std": 0.35413838655304614, + "nauc_recall_at_10_diff1": -0.026147108788628564, + "nauc_recall_at_10_max": 0.20292929422529893, + "nauc_recall_at_10_std": 0.21578667184495304, + "nauc_recall_at_1_diff1": 0.038644501526563506, + "nauc_recall_at_1_max": 0.03406766330980977, + "nauc_recall_at_1_std": 0.010790996092590491, + "nauc_recall_at_20_diff1": -0.03268957862286486, + "nauc_recall_at_20_max": 0.24671194908785968, + "nauc_recall_at_20_std": 0.28811741923058115, + "nauc_recall_at_3_diff1": 0.00333535114095895, + "nauc_recall_at_3_max": 0.10216798690934792, + "nauc_recall_at_3_std": 0.053142981684902814, + "nauc_recall_at_5_diff1": -0.0037132169145805555, + "nauc_recall_at_5_max": 0.147254260382681, + "nauc_recall_at_5_std": 0.1200483008099457, + "ndcg_at_1": 0.11432, + "ndcg_at_10": 0.30051, + "ndcg_at_100": 0.355, + "ndcg_at_1000": 0.37519, + "ndcg_at_20": 0.32542, + "ndcg_at_3": 0.21977, + "ndcg_at_5": 0.25982, + "precision_at_1": 0.11432, + "precision_at_10": 0.0521, + "precision_at_100": 0.0078, + "precision_at_1000": 0.00094, + "precision_at_20": 0.03095, + "precision_at_3": 0.09949, + "precision_at_5": 0.07917, + "recall_at_1": 0.11432, + "recall_at_10": 0.52101, + "recall_at_100": 0.77971, + "recall_at_1000": 0.94193, + "recall_at_20": 0.61907, + "recall_at_3": 0.29846, + "recall_at_5": 0.39584 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL3Pure.json b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL3Pure.json new file mode 100644 index 000000000..94172e4ea --- /dev/null +++ b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TempReasonL3Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 17.65882444381714, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.05276, + "map_at_1": 0.00158, + "map_at_10": 0.03112, + "map_at_100": 0.03698, + "map_at_1000": 0.03801, + "map_at_20": 0.03429, + "map_at_3": 0.01619, + "map_at_5": 0.02394, + "mrr_at_1": 0.0015815634884771804, + "mrr_at_10": 0.0311151098487294, + "mrr_at_100": 0.03697665428815571, + "mrr_at_1000": 0.03801018890358903, + "mrr_at_20": 0.03429240930451061, + "mrr_at_3": 0.016192197620123524, + "mrr_at_5": 0.02394185871366171, + "nauc_map_at_1000_diff1": -0.1378369684146819, + "nauc_map_at_1000_max": -0.10810937286628022, + "nauc_map_at_1000_std": 0.3172630739719468, + "nauc_map_at_100_diff1": -0.13919859025811768, + "nauc_map_at_100_max": -0.10921456055067215, + "nauc_map_at_100_std": 0.318842075082212, + "nauc_map_at_10_diff1": -0.13689477059925856, + "nauc_map_at_10_max": -0.1071143152437047, + "nauc_map_at_10_std": 0.31063290840062946, + "nauc_map_at_1_diff1": -0.3830096687898963, + "nauc_map_at_1_max": -0.30425436549872814, + "nauc_map_at_1_std": -0.11186418917553566, + "nauc_map_at_20_diff1": -0.1418525467331912, + "nauc_map_at_20_max": -0.10950994374714397, + "nauc_map_at_20_std": 0.31973968849591283, + "nauc_map_at_3_diff1": -0.11240653551821737, + "nauc_map_at_3_max": -0.08607342202753115, + "nauc_map_at_3_std": 0.2306829182404542, + "nauc_map_at_5_diff1": -0.11743267089798926, + "nauc_map_at_5_max": -0.08349807288332894, + "nauc_map_at_5_std": 0.28152558145376344, + "nauc_mrr_at_1000_diff1": -0.1378369684146819, + "nauc_mrr_at_1000_max": -0.10810937286628022, + "nauc_mrr_at_1000_std": 0.3172630739719468, + "nauc_mrr_at_100_diff1": -0.13919859025811768, + "nauc_mrr_at_100_max": -0.10921456055067215, + "nauc_mrr_at_100_std": 0.318842075082212, + "nauc_mrr_at_10_diff1": -0.13689477059925856, + "nauc_mrr_at_10_max": -0.1071143152437047, + "nauc_mrr_at_10_std": 0.31063290840062946, + "nauc_mrr_at_1_diff1": -0.3830096687898963, + "nauc_mrr_at_1_max": -0.30425436549872814, + "nauc_mrr_at_1_std": -0.11186418917553566, + "nauc_mrr_at_20_diff1": -0.1418525467331912, + "nauc_mrr_at_20_max": -0.10950994374714397, + "nauc_mrr_at_20_std": 0.31973968849591283, + "nauc_mrr_at_3_diff1": -0.11240653551821737, + "nauc_mrr_at_3_max": -0.08607342202753115, + "nauc_mrr_at_3_std": 0.2306829182404542, + "nauc_mrr_at_5_diff1": -0.11743267089798926, + "nauc_mrr_at_5_max": -0.08349807288332894, + "nauc_mrr_at_5_std": 0.28152558145376344, + "nauc_ndcg_at_1000_diff1": -0.12689248579504456, + "nauc_ndcg_at_1000_max": -0.09830510507811402, + "nauc_ndcg_at_1000_std": 0.3165080288109831, + "nauc_ndcg_at_100_diff1": -0.1414704259308614, + "nauc_ndcg_at_100_max": -0.11774849241224465, + "nauc_ndcg_at_100_std": 0.33802042863663334, + "nauc_ndcg_at_10_diff1": -0.14777165585672034, + "nauc_ndcg_at_10_max": -0.11823213664378047, + "nauc_ndcg_at_10_std": 0.33891171345670545, + "nauc_ndcg_at_1_diff1": -0.3830096687898963, + "nauc_ndcg_at_1_max": -0.30425436549872814, + "nauc_ndcg_at_1_std": -0.11186418917553566, + "nauc_ndcg_at_20_diff1": -0.15630524692420616, + "nauc_ndcg_at_20_max": -0.12301419860158318, + "nauc_ndcg_at_20_std": 0.3524618990623191, + "nauc_ndcg_at_3_diff1": -0.11348879157387518, + "nauc_ndcg_at_3_max": -0.08535923455394812, + "nauc_ndcg_at_3_std": 0.24177575707339533, + "nauc_ndcg_at_5_diff1": -0.11919647063907728, + "nauc_ndcg_at_5_max": -0.0823957531876704, + "nauc_ndcg_at_5_std": 0.2991365085453318, + "nauc_precision_at_1000_diff1": -0.09796193909111542, + "nauc_precision_at_1000_max": -0.06262599578487324, + "nauc_precision_at_1000_std": 0.28211159882247605, + "nauc_precision_at_100_diff1": -0.13709846713513565, + "nauc_precision_at_100_max": -0.12206844973083031, + "nauc_precision_at_100_std": 0.3423799999069633, + "nauc_precision_at_10_diff1": -0.1598132735296753, + "nauc_precision_at_10_max": -0.13097388618003125, + "nauc_precision_at_10_std": 0.36698426859693245, + "nauc_precision_at_1_diff1": -0.3830096687898963, + "nauc_precision_at_1_max": -0.30425436549872814, + "nauc_precision_at_1_std": -0.11186418917553566, + "nauc_precision_at_20_diff1": -0.17058204207440014, + "nauc_precision_at_20_max": -0.1369178232264215, + "nauc_precision_at_20_std": 0.3813836613464555, + "nauc_precision_at_3_diff1": -0.1162281274212962, + "nauc_precision_at_3_max": -0.08525905584121808, + "nauc_precision_at_3_std": 0.2564420814267733, + "nauc_precision_at_5_diff1": -0.1218484678964452, + "nauc_precision_at_5_max": -0.08158409615509583, + "nauc_precision_at_5_std": 0.3187867391196734, + "nauc_recall_at_1000_diff1": -0.09796193909111546, + "nauc_recall_at_1000_max": -0.06262599578487353, + "nauc_recall_at_1000_std": 0.2821115988224764, + "nauc_recall_at_100_diff1": -0.13709846713513588, + "nauc_recall_at_100_max": -0.12206844973083045, + "nauc_recall_at_100_std": 0.3423799999069632, + "nauc_recall_at_10_diff1": -0.1598132735296755, + "nauc_recall_at_10_max": -0.13097388618003147, + "nauc_recall_at_10_std": 0.3669842685969321, + "nauc_recall_at_1_diff1": -0.3830096687898963, + "nauc_recall_at_1_max": -0.30425436549872814, + "nauc_recall_at_1_std": -0.11186418917553566, + "nauc_recall_at_20_diff1": -0.17058204207440028, + "nauc_recall_at_20_max": -0.13691782322642168, + "nauc_recall_at_20_std": 0.3813836613464554, + "nauc_recall_at_3_diff1": -0.11622812742129625, + "nauc_recall_at_3_max": -0.08525905584121808, + "nauc_recall_at_3_std": 0.25644208142677344, + "nauc_recall_at_5_diff1": -0.12184846789644525, + "nauc_recall_at_5_max": -0.08158409615509582, + "nauc_recall_at_5_std": 0.3187867391196735, + "ndcg_at_1": 0.00158, + "ndcg_at_10": 0.05276, + "ndcg_at_100": 0.08417, + "ndcg_at_1000": 0.12154, + "ndcg_at_20": 0.06435, + "ndcg_at_3": 0.0214, + "ndcg_at_5": 0.03546, + "precision_at_1": 0.00158, + "precision_at_10": 0.01243, + "precision_at_100": 0.00278, + "precision_at_1000": 0.00059, + "precision_at_20": 0.00851, + "precision_at_3": 0.0122, + "precision_at_5": 0.01419, + "recall_at_1": 0.00158, + "recall_at_10": 0.12427, + "recall_at_100": 0.2779, + "recall_at_1000": 0.59444, + "recall_at_20": 0.17013, + "recall_at_3": 0.0366, + "recall_at_5": 0.07094 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/WinoGrande.json b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/WinoGrande.json new file mode 100644 index 000000000..5ca352807 --- /dev/null +++ b/results/bge-m3/5617a9f61b028005a4858fdac845db406aefb181/WinoGrande.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 4.738288402557373, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.41723, + "map_at_1": 0.191, + "map_at_10": 0.33232, + "map_at_100": 0.34514, + "map_at_1000": 0.34537, + "map_at_20": 0.34101, + "map_at_3": 0.28243, + "map_at_5": 0.308, + "mrr_at_1": 0.1910023677979479, + "mrr_at_10": 0.3323185627842295, + "mrr_at_100": 0.34514246247092956, + "mrr_at_1000": 0.34536773261805204, + "mrr_at_20": 0.3410068076084549, + "mrr_at_3": 0.2824256774533015, + "mrr_at_5": 0.30799789529071225, + "nauc_map_at_1000_diff1": 0.10916632240654867, + "nauc_map_at_1000_max": -0.02386918997973203, + "nauc_map_at_1000_std": -0.14810635772798342, + "nauc_map_at_100_diff1": 0.10916429118455738, + "nauc_map_at_100_max": -0.02393557614749841, + "nauc_map_at_100_std": -0.1479984831956555, + "nauc_map_at_10_diff1": 0.10701202804788863, + "nauc_map_at_10_max": -0.02542896286766606, + "nauc_map_at_10_std": -0.15184491248705534, + "nauc_map_at_1_diff1": 0.13333508529448998, + "nauc_map_at_1_max": 0.0028144939788324872, + "nauc_map_at_1_std": -0.12204233743782984, + "nauc_map_at_20_diff1": 0.10856021579241194, + "nauc_map_at_20_max": -0.024428207894663947, + "nauc_map_at_20_std": -0.1492151815416021, + "nauc_map_at_3_diff1": 0.12163346137577287, + "nauc_map_at_3_max": -0.014203074150091541, + "nauc_map_at_3_std": -0.1389510154357969, + "nauc_map_at_5_diff1": 0.10779270685174705, + "nauc_map_at_5_max": -0.026210548988846158, + "nauc_map_at_5_std": -0.15158590032024333, + "nauc_mrr_at_1000_diff1": 0.10916632240654867, + "nauc_mrr_at_1000_max": -0.02386918997973203, + "nauc_mrr_at_1000_std": -0.14810635772798342, + "nauc_mrr_at_100_diff1": 0.10916429118455738, + "nauc_mrr_at_100_max": -0.02393557614749841, + "nauc_mrr_at_100_std": -0.1479984831956555, + "nauc_mrr_at_10_diff1": 0.10701202804788863, + "nauc_mrr_at_10_max": -0.02542896286766606, + "nauc_mrr_at_10_std": -0.15184491248705534, + "nauc_mrr_at_1_diff1": 0.13333508529448998, + "nauc_mrr_at_1_max": 0.0028144939788324872, + "nauc_mrr_at_1_std": -0.12204233743782984, + "nauc_mrr_at_20_diff1": 0.10856021579241194, + "nauc_mrr_at_20_max": -0.024428207894663947, + "nauc_mrr_at_20_std": -0.1492151815416021, + "nauc_mrr_at_3_diff1": 0.12163346137577287, + "nauc_mrr_at_3_max": -0.014203074150091541, + "nauc_mrr_at_3_std": -0.1389510154357969, + "nauc_mrr_at_5_diff1": 0.10779270685174705, + "nauc_mrr_at_5_max": -0.026210548988846158, + "nauc_mrr_at_5_std": -0.15158590032024333, + "nauc_ndcg_at_1000_diff1": 0.10330394048804838, + "nauc_ndcg_at_1000_max": -0.03010600915015423, + "nauc_ndcg_at_1000_std": -0.15098566195701646, + "nauc_ndcg_at_100_diff1": 0.10170073590399521, + "nauc_ndcg_at_100_max": -0.033452464341435145, + "nauc_ndcg_at_100_std": -0.1482306578362068, + "nauc_ndcg_at_10_diff1": 0.0935357315949425, + "nauc_ndcg_at_10_max": -0.03783427625200473, + "nauc_ndcg_at_10_std": -0.1652227005726498, + "nauc_ndcg_at_1_diff1": 0.13333508529448998, + "nauc_ndcg_at_1_max": 0.0028144939788324872, + "nauc_ndcg_at_1_std": -0.12204233743782984, + "nauc_ndcg_at_20_diff1": 0.0982495593575223, + "nauc_ndcg_at_20_max": -0.03551025369076682, + "nauc_ndcg_at_20_std": -0.15499416930219714, + "nauc_ndcg_at_3_diff1": 0.12045940134549928, + "nauc_ndcg_at_3_max": -0.01879344934130561, + "nauc_ndcg_at_3_std": -0.14418000483341734, + "nauc_ndcg_at_5_diff1": 0.09615120439119341, + "nauc_ndcg_at_5_max": -0.039702162522318035, + "nauc_ndcg_at_5_std": -0.1660999346008315, + "nauc_precision_at_1000_diff1": -1.1528394467661298, + "nauc_precision_at_1000_max": -0.5636741363731029, + "nauc_precision_at_1000_std": 0.3580675238444718, + "nauc_precision_at_100_diff1": -0.016802507195330392, + "nauc_precision_at_100_max": -0.22221811198005062, + "nauc_precision_at_100_std": -0.009208907731537755, + "nauc_precision_at_10_diff1": 0.04397011446975025, + "nauc_precision_at_10_max": -0.08067055300599703, + "nauc_precision_at_10_std": -0.21016007528080607, + "nauc_precision_at_1_diff1": 0.13333508529448998, + "nauc_precision_at_1_max": 0.0028144939788324872, + "nauc_precision_at_1_std": -0.12204233743782984, + "nauc_precision_at_20_diff1": 0.04662533460082883, + "nauc_precision_at_20_max": -0.0905070980719148, + "nauc_precision_at_20_std": -0.16659554498984333, + "nauc_precision_at_3_diff1": 0.11804383524512585, + "nauc_precision_at_3_max": -0.030439457370097914, + "nauc_precision_at_3_std": -0.15763594628166266, + "nauc_precision_at_5_diff1": 0.06284063571659496, + "nauc_precision_at_5_max": -0.07783275783350095, + "nauc_precision_at_5_std": -0.20718619021047754, + "nauc_recall_at_1000_diff1": -1.152839446766421, + "nauc_recall_at_1000_max": -0.5636741363736752, + "nauc_recall_at_1000_std": 0.35806752384437546, + "nauc_recall_at_100_diff1": -0.01680250719532816, + "nauc_recall_at_100_max": -0.2222181119800518, + "nauc_recall_at_100_std": -0.009208907731540433, + "nauc_recall_at_10_diff1": 0.04397011446974916, + "nauc_recall_at_10_max": -0.08067055300599775, + "nauc_recall_at_10_std": -0.2101600752808071, + "nauc_recall_at_1_diff1": 0.13333508529448998, + "nauc_recall_at_1_max": 0.0028144939788324872, + "nauc_recall_at_1_std": -0.12204233743782984, + "nauc_recall_at_20_diff1": 0.046625334600829786, + "nauc_recall_at_20_max": -0.09050709807191597, + "nauc_recall_at_20_std": -0.16659554498984203, + "nauc_recall_at_3_diff1": 0.11804383524512563, + "nauc_recall_at_3_max": -0.03043945737009796, + "nauc_recall_at_3_std": -0.15763594628166264, + "nauc_recall_at_5_diff1": 0.06284063571659523, + "nauc_recall_at_5_max": -0.07783275783350099, + "nauc_recall_at_5_std": -0.20718619021047763, + "ndcg_at_1": 0.191, + "ndcg_at_10": 0.41723, + "ndcg_at_100": 0.47647, + "ndcg_at_1000": 0.48152, + "ndcg_at_20": 0.44881, + "ndcg_at_3": 0.31263, + "ndcg_at_5": 0.35859, + "precision_at_1": 0.191, + "precision_at_10": 0.06922, + "precision_at_100": 0.00961, + "precision_at_1000": 0.001, + "precision_at_20": 0.04084, + "precision_at_3": 0.13339, + "precision_at_5": 0.10229, + "recall_at_1": 0.191, + "recall_at_10": 0.69219, + "recall_at_100": 0.96133, + "recall_at_1000": 0.99921, + "recall_at_20": 0.81689, + "recall_at_3": 0.40016, + "recall_at_5": 0.51144 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/ARCChallenge.json b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/ARCChallenge.json new file mode 100644 index 000000000..777955187 --- /dev/null +++ b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/ARCChallenge.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 2.7134382724761963, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07715, + "map_at_1": 0.02389, + "map_at_10": 0.05697, + "map_at_100": 0.06374, + "map_at_1000": 0.06515, + "map_at_20": 0.06025, + "map_at_3": 0.04465, + "map_at_5": 0.05148, + "mrr_at_1": 0.023890784982935155, + "mrr_at_10": 0.056967468443577716, + "mrr_at_100": 0.0637427346666799, + "mrr_at_1000": 0.0651489854876816, + "mrr_at_20": 0.06025176147288207, + "mrr_at_3": 0.044653014789533575, + "mrr_at_5": 0.051478953356086515, + "nauc_map_at_1000_diff1": 0.0894852091778207, + "nauc_map_at_1000_max": 0.10172328165986272, + "nauc_map_at_1000_std": -0.025131559145247367, + "nauc_map_at_100_diff1": 0.0900789500343102, + "nauc_map_at_100_max": 0.10264775493761884, + "nauc_map_at_100_std": -0.02505335330209713, + "nauc_map_at_10_diff1": 0.09284413078105919, + "nauc_map_at_10_max": 0.10074277447385774, + "nauc_map_at_10_std": -0.04007301713775738, + "nauc_map_at_1_diff1": 0.16923831532112849, + "nauc_map_at_1_max": 0.09650854101833761, + "nauc_map_at_1_std": -0.05979532629167708, + "nauc_map_at_20_diff1": 0.09392108896331487, + "nauc_map_at_20_max": 0.10587863164504453, + "nauc_map_at_20_std": -0.030367422864793263, + "nauc_map_at_3_diff1": 0.10563393174243375, + "nauc_map_at_3_max": 0.11893419851902372, + "nauc_map_at_3_std": -0.03553189135447554, + "nauc_map_at_5_diff1": 0.08938285872148892, + "nauc_map_at_5_max": 0.11040904011964525, + "nauc_map_at_5_std": -0.03842243218601317, + "nauc_mrr_at_1000_diff1": 0.08949355175335057, + "nauc_mrr_at_1000_max": 0.10173152978635552, + "nauc_mrr_at_1000_std": -0.02513572523065766, + "nauc_mrr_at_100_diff1": 0.09008719600631543, + "nauc_mrr_at_100_max": 0.10265596639962254, + "nauc_mrr_at_100_std": -0.02505752423508231, + "nauc_mrr_at_10_diff1": 0.09284413078105919, + "nauc_mrr_at_10_max": 0.10074277447385774, + "nauc_mrr_at_10_std": -0.04007301713775738, + "nauc_mrr_at_1_diff1": 0.16923831532112849, + "nauc_mrr_at_1_max": 0.09650854101833761, + "nauc_mrr_at_1_std": -0.05979532629167708, + "nauc_mrr_at_20_diff1": 0.09392108896331487, + "nauc_mrr_at_20_max": 0.10587863164504453, + "nauc_mrr_at_20_std": -0.030367422864793263, + "nauc_mrr_at_3_diff1": 0.10563393174243375, + "nauc_mrr_at_3_max": 0.11893419851902372, + "nauc_mrr_at_3_std": -0.03553189135447554, + "nauc_mrr_at_5_diff1": 0.08938285872148892, + "nauc_mrr_at_5_max": 0.11040904011964525, + "nauc_mrr_at_5_std": -0.03842243218601317, + "nauc_ndcg_at_1000_diff1": 0.06126313528683786, + "nauc_ndcg_at_1000_max": 0.08540705126535471, + "nauc_ndcg_at_1000_std": 0.013663309174494551, + "nauc_ndcg_at_100_diff1": 0.06980183518374118, + "nauc_ndcg_at_100_max": 0.0935383359018508, + "nauc_ndcg_at_100_std": 0.011655948034436054, + "nauc_ndcg_at_10_diff1": 0.08527190268886085, + "nauc_ndcg_at_10_max": 0.09437006397991156, + "nauc_ndcg_at_10_std": -0.03958575653947941, + "nauc_ndcg_at_1_diff1": 0.16923831532112849, + "nauc_ndcg_at_1_max": 0.09650854101833761, + "nauc_ndcg_at_1_std": -0.05979532629167708, + "nauc_ndcg_at_20_diff1": 0.08867392299632793, + "nauc_ndcg_at_20_max": 0.10799269687395867, + "nauc_ndcg_at_20_std": -0.012697571573072317, + "nauc_ndcg_at_3_diff1": 0.10036171330777166, + "nauc_ndcg_at_3_max": 0.1241674152970108, + "nauc_ndcg_at_3_std": -0.03130641255484136, + "nauc_ndcg_at_5_diff1": 0.07708991445767557, + "nauc_ndcg_at_5_max": 0.11109288417024689, + "nauc_ndcg_at_5_std": -0.03605854672588748, + "nauc_precision_at_1000_diff1": -0.0004100557380247895, + "nauc_precision_at_1000_max": 0.050245749273256535, + "nauc_precision_at_1000_std": 0.09780881107185921, + "nauc_precision_at_100_diff1": 0.03996944739906475, + "nauc_precision_at_100_max": 0.07865059513301972, + "nauc_precision_at_100_std": 0.06822584573149115, + "nauc_precision_at_10_diff1": 0.07656997899805043, + "nauc_precision_at_10_max": 0.08357134047046377, + "nauc_precision_at_10_std": -0.0399241832139346, + "nauc_precision_at_1_diff1": 0.16923831532112849, + "nauc_precision_at_1_max": 0.09650854101833761, + "nauc_precision_at_1_std": -0.05979532629167708, + "nauc_precision_at_20_diff1": 0.08482131063108395, + "nauc_precision_at_20_max": 0.11236425290391677, + "nauc_precision_at_20_std": 0.015479086516195858, + "nauc_precision_at_3_diff1": 0.09181294023435216, + "nauc_precision_at_3_max": 0.13400447323471468, + "nauc_precision_at_3_std": -0.023568021825508555, + "nauc_precision_at_5_diff1": 0.05773500514657997, + "nauc_precision_at_5_max": 0.11159364724277286, + "nauc_precision_at_5_std": -0.03271990344873595, + "nauc_recall_at_1000_diff1": -0.000410055738024271, + "nauc_recall_at_1000_max": 0.050245749273256646, + "nauc_recall_at_1000_std": 0.09780881107185953, + "nauc_recall_at_100_diff1": 0.03996944739906468, + "nauc_recall_at_100_max": 0.07865059513301956, + "nauc_recall_at_100_std": 0.06822584573149107, + "nauc_recall_at_10_diff1": 0.07656997899805025, + "nauc_recall_at_10_max": 0.0835713404704637, + "nauc_recall_at_10_std": -0.03992418321393473, + "nauc_recall_at_1_diff1": 0.16923831532112849, + "nauc_recall_at_1_max": 0.09650854101833761, + "nauc_recall_at_1_std": -0.05979532629167708, + "nauc_recall_at_20_diff1": 0.08482131063108368, + "nauc_recall_at_20_max": 0.11236425290391659, + "nauc_recall_at_20_std": 0.015479086516195534, + "nauc_recall_at_3_diff1": 0.09181294023435223, + "nauc_recall_at_3_max": 0.13400447323471476, + "nauc_recall_at_3_std": -0.023568021825508587, + "nauc_recall_at_5_diff1": 0.05773500514657975, + "nauc_recall_at_5_max": 0.1115936472427729, + "nauc_recall_at_5_std": -0.032719903448736015, + "ndcg_at_1": 0.02389, + "ndcg_at_10": 0.07715, + "ndcg_at_100": 0.11545, + "ndcg_at_1000": 0.15885, + "ndcg_at_20": 0.08933, + "ndcg_at_3": 0.05158, + "ndcg_at_5": 0.06388, + "precision_at_1": 0.02389, + "precision_at_10": 0.01425, + "precision_at_100": 0.00334, + "precision_at_1000": 0.00069, + "precision_at_20": 0.00956, + "precision_at_3": 0.02389, + "precision_at_5": 0.02031, + "recall_at_1": 0.02389, + "recall_at_10": 0.14249, + "recall_at_100": 0.33362, + "recall_at_1000": 0.68857, + "recall_at_20": 0.19113, + "recall_at_3": 0.07167, + "recall_at_5": 0.10154 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/AlphaNLI.json b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/AlphaNLI.json new file mode 100644 index 000000000..34f9ec371 --- /dev/null +++ b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/AlphaNLI.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 25.20677876472473, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01259, + "map_at_1": 0.00522, + "map_at_10": 0.00934, + "map_at_100": 0.0117, + "map_at_1000": 0.01236, + "map_at_20": 0.01033, + "map_at_3": 0.0074, + "map_at_5": 0.00795, + "mrr_at_1": 0.005221932114882507, + "mrr_at_10": 0.009338866094740765, + "mrr_at_100": 0.011703186768015208, + "mrr_at_1000": 0.01236133748907418, + "mrr_at_20": 0.010333942688020603, + "mrr_at_3": 0.007397737162750217, + "mrr_at_5": 0.007952567449956484, + "nauc_map_at_1000_diff1": -0.1654338851362356, + "nauc_map_at_1000_max": -0.10042954340203969, + "nauc_map_at_1000_std": 0.07371986084018137, + "nauc_map_at_100_diff1": -0.17127396878348755, + "nauc_map_at_100_max": -0.10212440678180983, + "nauc_map_at_100_std": 0.07291083916795472, + "nauc_map_at_10_diff1": -0.21753751283100384, + "nauc_map_at_10_max": -0.12677350752658106, + "nauc_map_at_10_std": 0.0834166584026742, + "nauc_map_at_1_diff1": -0.25476030988656967, + "nauc_map_at_1_max": -0.05292467974554457, + "nauc_map_at_1_std": 0.06749510130271344, + "nauc_map_at_20_diff1": -0.19914182021513535, + "nauc_map_at_20_max": -0.11538928576596985, + "nauc_map_at_20_std": 0.0780952805412548, + "nauc_map_at_3_diff1": -0.20138741558858733, + "nauc_map_at_3_max": -0.07910908583969532, + "nauc_map_at_3_std": 0.11795300346488251, + "nauc_map_at_5_diff1": -0.22355730811291177, + "nauc_map_at_5_max": -0.10822482227119436, + "nauc_map_at_5_std": 0.10054951378329507, + "nauc_mrr_at_1000_diff1": -0.1654338851362356, + "nauc_mrr_at_1000_max": -0.10042954340203969, + "nauc_mrr_at_1000_std": 0.07371986084018137, + "nauc_mrr_at_100_diff1": -0.17127396878348755, + "nauc_mrr_at_100_max": -0.10212440678180983, + "nauc_mrr_at_100_std": 0.07291083916795472, + "nauc_mrr_at_10_diff1": -0.21753751283100384, + "nauc_mrr_at_10_max": -0.12677350752658106, + "nauc_mrr_at_10_std": 0.0834166584026742, + "nauc_mrr_at_1_diff1": -0.25476030988656967, + "nauc_mrr_at_1_max": -0.05292467974554457, + "nauc_mrr_at_1_std": 0.06749510130271344, + "nauc_mrr_at_20_diff1": -0.19914182021513535, + "nauc_mrr_at_20_max": -0.11538928576596985, + "nauc_mrr_at_20_std": 0.0780952805412548, + "nauc_mrr_at_3_diff1": -0.20138741558858733, + "nauc_mrr_at_3_max": -0.07910908583969532, + "nauc_mrr_at_3_std": 0.11795300346488251, + "nauc_mrr_at_5_diff1": -0.22355730811291177, + "nauc_mrr_at_5_max": -0.10822482227119436, + "nauc_mrr_at_5_std": 0.10054951378329507, + "nauc_ndcg_at_1000_diff1": -0.0847741392940737, + "nauc_ndcg_at_1000_max": -0.07081092518037109, + "nauc_ndcg_at_1000_std": 0.041953725927482394, + "nauc_ndcg_at_100_diff1": -0.10221960663436985, + "nauc_ndcg_at_100_max": -0.07566904769707256, + "nauc_ndcg_at_100_std": 0.042285173094502006, + "nauc_ndcg_at_10_diff1": -0.21398763820145172, + "nauc_ndcg_at_10_max": -0.15771963373267298, + "nauc_ndcg_at_10_std": 0.058469967404929477, + "nauc_ndcg_at_1_diff1": -0.25476030988656967, + "nauc_ndcg_at_1_max": -0.05292467974554457, + "nauc_ndcg_at_1_std": 0.06749510130271344, + "nauc_ndcg_at_20_diff1": -0.17547479291474052, + "nauc_ndcg_at_20_max": -0.12479544363684651, + "nauc_ndcg_at_20_std": 0.048355454503285676, + "nauc_ndcg_at_3_diff1": -0.18577049056737835, + "nauc_ndcg_at_3_max": -0.085894103060205, + "nauc_ndcg_at_3_std": 0.12088011230168003, + "nauc_ndcg_at_5_diff1": -0.2231475417173146, + "nauc_ndcg_at_5_max": -0.13188402436244318, + "nauc_ndcg_at_5_std": 0.09072406576044639, + "nauc_precision_at_1000_diff1": -0.057332244286840216, + "nauc_precision_at_1000_max": -0.05539244998980885, + "nauc_precision_at_1000_std": 0.026257881168528157, + "nauc_precision_at_100_diff1": -0.06102309492045376, + "nauc_precision_at_100_max": -0.05148959075866856, + "nauc_precision_at_100_std": 0.026303147506593128, + "nauc_precision_at_10_diff1": -0.21097886832005217, + "nauc_precision_at_10_max": -0.1991529400694617, + "nauc_precision_at_10_std": 0.02007936680986054, + "nauc_precision_at_1_diff1": -0.25476030988656967, + "nauc_precision_at_1_max": -0.05292467974554457, + "nauc_precision_at_1_std": 0.06749510130271344, + "nauc_precision_at_20_diff1": -0.14944286556537217, + "nauc_precision_at_20_max": -0.12812163872514284, + "nauc_precision_at_20_std": 0.013848252423820592, + "nauc_precision_at_3_diff1": -0.15271489693448098, + "nauc_precision_at_3_max": -0.10010643434791922, + "nauc_precision_at_3_std": 0.12506114860160675, + "nauc_precision_at_5_diff1": -0.22531317989383393, + "nauc_precision_at_5_max": -0.17839814765354775, + "nauc_precision_at_5_std": 0.06806315124565918, + "nauc_recall_at_1000_diff1": -0.057332244286840195, + "nauc_recall_at_1000_max": -0.05539244998980871, + "nauc_recall_at_1000_std": 0.02625788116852816, + "nauc_recall_at_100_diff1": -0.06102309492045372, + "nauc_recall_at_100_max": -0.05148959075866864, + "nauc_recall_at_100_std": 0.02630314750659303, + "nauc_recall_at_10_diff1": -0.2109788683200521, + "nauc_recall_at_10_max": -0.1991529400694617, + "nauc_recall_at_10_std": 0.02007936680986057, + "nauc_recall_at_1_diff1": -0.25476030988656967, + "nauc_recall_at_1_max": -0.05292467974554457, + "nauc_recall_at_1_std": 0.06749510130271344, + "nauc_recall_at_20_diff1": -0.1494428655653723, + "nauc_recall_at_20_max": -0.12812163872514298, + "nauc_recall_at_20_std": 0.013848252423820368, + "nauc_recall_at_3_diff1": -0.1527148969344811, + "nauc_recall_at_3_max": -0.10010643434791934, + "nauc_recall_at_3_std": 0.12506114860160666, + "nauc_recall_at_5_diff1": -0.2253131798938337, + "nauc_recall_at_5_max": -0.17839814765354745, + "nauc_recall_at_5_std": 0.06806315124565938, + "ndcg_at_1": 0.00522, + "ndcg_at_10": 0.01259, + "ndcg_at_100": 0.0275, + "ndcg_at_1000": 0.05034, + "ndcg_at_20": 0.0161, + "ndcg_at_3": 0.00817, + "ndcg_at_5": 0.00921, + "precision_at_1": 0.00522, + "precision_at_10": 0.00235, + "precision_at_100": 0.00102, + "precision_at_1000": 0.00029, + "precision_at_20": 0.00186, + "precision_at_3": 0.00348, + "precision_at_5": 0.00261, + "recall_at_1": 0.00522, + "recall_at_10": 0.0235, + "recall_at_100": 0.10183, + "recall_at_1000": 0.29373, + "recall_at_20": 0.03721, + "recall_at_3": 0.01044, + "recall_at_5": 0.01305 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/HellaSwag.json b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/HellaSwag.json new file mode 100644 index 000000000..2117a13e1 --- /dev/null +++ b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/HellaSwag.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 72.29276847839355, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.23408, + "map_at_1": 0.12428, + "map_at_10": 0.19555, + "map_at_100": 0.20317, + "map_at_1000": 0.20399, + "map_at_20": 0.19975, + "map_at_3": 0.17551, + "map_at_5": 0.18704, + "mrr_at_1": 0.12427803226448915, + "mrr_at_10": 0.19554952532695935, + "mrr_at_100": 0.20317473048361978, + "mrr_at_1000": 0.20398523355012213, + "mrr_at_20": 0.19975228292008593, + "mrr_at_3": 0.1755128460466032, + "mrr_at_5": 0.18704441346345294, + "nauc_map_at_1000_diff1": 0.29871593117826495, + "nauc_map_at_1000_max": 0.32937136231698727, + "nauc_map_at_1000_std": 0.012217047389456389, + "nauc_map_at_100_diff1": 0.2986819888770715, + "nauc_map_at_100_max": 0.32929854374260314, + "nauc_map_at_100_std": 0.012136628494158004, + "nauc_map_at_10_diff1": 0.29917362538799164, + "nauc_map_at_10_max": 0.3244324335550969, + "nauc_map_at_10_std": 0.009425664231323563, + "nauc_map_at_1_diff1": 0.33080877746915216, + "nauc_map_at_1_max": 0.28864119522996234, + "nauc_map_at_1_std": 0.000780579396599158, + "nauc_map_at_20_diff1": 0.29870342668821187, + "nauc_map_at_20_max": 0.32733761638527575, + "nauc_map_at_20_std": 0.010399796184128203, + "nauc_map_at_3_diff1": 0.30095148509516223, + "nauc_map_at_3_max": 0.31075187938141524, + "nauc_map_at_3_std": 0.0035412280251755986, + "nauc_map_at_5_diff1": 0.29928715031977243, + "nauc_map_at_5_max": 0.3177170562070303, + "nauc_map_at_5_std": 0.005684507790330314, + "nauc_mrr_at_1000_diff1": 0.29871593232328525, + "nauc_mrr_at_1000_max": 0.32937136640119474, + "nauc_mrr_at_1000_std": 0.012217046330305703, + "nauc_mrr_at_100_diff1": 0.2986819888770715, + "nauc_mrr_at_100_max": 0.32929854374260314, + "nauc_mrr_at_100_std": 0.012136628494158004, + "nauc_mrr_at_10_diff1": 0.29917362538799164, + "nauc_mrr_at_10_max": 0.3244324335550969, + "nauc_mrr_at_10_std": 0.009425664231323563, + "nauc_mrr_at_1_diff1": 0.33080877746915216, + "nauc_mrr_at_1_max": 0.28864119522996234, + "nauc_mrr_at_1_std": 0.000780579396599158, + "nauc_mrr_at_20_diff1": 0.29870342668821187, + "nauc_mrr_at_20_max": 0.32733761638527575, + "nauc_mrr_at_20_std": 0.010399796184128203, + "nauc_mrr_at_3_diff1": 0.30095148509516223, + "nauc_mrr_at_3_max": 0.31075187938141524, + "nauc_mrr_at_3_std": 0.0035412280251755986, + "nauc_mrr_at_5_diff1": 0.29928715031977243, + "nauc_mrr_at_5_max": 0.3177170562070303, + "nauc_mrr_at_5_std": 0.005684507790330314, + "nauc_ndcg_at_1000_diff1": 0.2930762967928209, + "nauc_ndcg_at_1000_max": 0.3698544060811429, + "nauc_ndcg_at_1000_std": 0.0320684628527925, + "nauc_ndcg_at_100_diff1": 0.29236564519021774, + "nauc_ndcg_at_100_max": 0.36750581157423556, + "nauc_ndcg_at_100_std": 0.03245814043302183, + "nauc_ndcg_at_10_diff1": 0.29303818389760805, + "nauc_ndcg_at_10_max": 0.34412567154432144, + "nauc_ndcg_at_10_std": 0.016727867046527817, + "nauc_ndcg_at_1_diff1": 0.33080877746915216, + "nauc_ndcg_at_1_max": 0.28864119522996234, + "nauc_ndcg_at_1_std": 0.000780579396599158, + "nauc_ndcg_at_20_diff1": 0.2920567426860574, + "nauc_ndcg_at_20_max": 0.3534766232307963, + "nauc_ndcg_at_20_std": 0.01982152679538546, + "nauc_ndcg_at_3_diff1": 0.2952486911454889, + "nauc_ndcg_at_3_max": 0.31833712633474515, + "nauc_ndcg_at_3_std": 0.004755151079939548, + "nauc_ndcg_at_5_diff1": 0.29273111086047443, + "nauc_ndcg_at_5_max": 0.3294761139100085, + "nauc_ndcg_at_5_std": 0.008499475196406234, + "nauc_precision_at_1000_diff1": 0.28072903185173137, + "nauc_precision_at_1000_max": 0.580321448416243, + "nauc_precision_at_1000_std": 0.13378476156052818, + "nauc_precision_at_100_diff1": 0.2798862706052911, + "nauc_precision_at_100_max": 0.4917949809457509, + "nauc_precision_at_100_std": 0.10608289079172625, + "nauc_precision_at_10_diff1": 0.28052724923562716, + "nauc_precision_at_10_max": 0.391993929537533, + "nauc_precision_at_10_std": 0.03538354554187286, + "nauc_precision_at_1_diff1": 0.33080877746915216, + "nauc_precision_at_1_max": 0.28864119522996234, + "nauc_precision_at_1_std": 0.000780579396599158, + "nauc_precision_at_20_diff1": 0.2785520974742837, + "nauc_precision_at_20_max": 0.4202844405589697, + "nauc_precision_at_20_std": 0.04460625448318676, + "nauc_precision_at_3_diff1": 0.2823430354093899, + "nauc_precision_at_3_max": 0.3366343899833294, + "nauc_precision_at_3_std": 0.007733402671147311, + "nauc_precision_at_5_diff1": 0.27844493495191175, + "nauc_precision_at_5_max": 0.3569774773356502, + "nauc_precision_at_5_std": 0.015353608103077437, + "nauc_recall_at_1000_diff1": 0.2807290318517321, + "nauc_recall_at_1000_max": 0.5803214484162431, + "nauc_recall_at_1000_std": 0.1337847615605289, + "nauc_recall_at_100_diff1": 0.2798862706052909, + "nauc_recall_at_100_max": 0.49179498094575097, + "nauc_recall_at_100_std": 0.10608289079172657, + "nauc_recall_at_10_diff1": 0.28052724923562744, + "nauc_recall_at_10_max": 0.3919939295375333, + "nauc_recall_at_10_std": 0.03538354554187291, + "nauc_recall_at_1_diff1": 0.33080877746915216, + "nauc_recall_at_1_max": 0.28864119522996234, + "nauc_recall_at_1_std": 0.000780579396599158, + "nauc_recall_at_20_diff1": 0.278552097474284, + "nauc_recall_at_20_max": 0.4202844405589698, + "nauc_recall_at_20_std": 0.04460625448318737, + "nauc_recall_at_3_diff1": 0.28234303540938976, + "nauc_recall_at_3_max": 0.33663438998332934, + "nauc_recall_at_3_std": 0.007733402671146946, + "nauc_recall_at_5_diff1": 0.2784449349519115, + "nauc_recall_at_5_max": 0.3569774773356501, + "nauc_recall_at_5_std": 0.015353608103077431, + "ndcg_at_1": 0.12428, + "ndcg_at_10": 0.23408, + "ndcg_at_100": 0.27521, + "ndcg_at_1000": 0.3003, + "ndcg_at_20": 0.24929, + "ndcg_at_3": 0.1926, + "ndcg_at_5": 0.21339, + "precision_at_1": 0.12428, + "precision_at_10": 0.03568, + "precision_at_100": 0.00559, + "precision_at_1000": 0.00076, + "precision_at_20": 0.02084, + "precision_at_3": 0.08073, + "precision_at_5": 0.05853, + "recall_at_1": 0.12428, + "recall_at_10": 0.3568, + "recall_at_100": 0.55895, + "recall_at_1000": 0.76399, + "recall_at_20": 0.41675, + "recall_at_3": 0.24218, + "recall_at_5": 0.29267 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/PIQA.json b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/PIQA.json new file mode 100644 index 000000000..e22876266 --- /dev/null +++ b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/PIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 8.25755262374878, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.20789, + "map_at_1": 0.10392, + "map_at_10": 0.1726, + "map_at_100": 0.18021, + "map_at_1000": 0.18096, + "map_at_20": 0.17671, + "map_at_3": 0.1537, + "map_at_5": 0.16491, + "mrr_at_1": 0.10391730141458107, + "mrr_at_10": 0.17260458227542005, + "mrr_at_100": 0.1802063032668654, + "mrr_at_1000": 0.18096082314311038, + "mrr_at_20": 0.17670570352789458, + "mrr_at_3": 0.15369967355821557, + "mrr_at_5": 0.16490750816104463, + "nauc_map_at_1000_diff1": -0.056793587239229275, + "nauc_map_at_1000_max": 0.24692017479769393, + "nauc_map_at_1000_std": 0.1674929529277241, + "nauc_map_at_100_diff1": -0.0563251284387581, + "nauc_map_at_100_max": 0.24720005135556547, + "nauc_map_at_100_std": 0.16720718163034257, + "nauc_map_at_10_diff1": -0.0501591064614069, + "nauc_map_at_10_max": 0.250622471700301, + "nauc_map_at_10_std": 0.1629930494430865, + "nauc_map_at_1_diff1": 0.002816775649447694, + "nauc_map_at_1_max": 0.2620714396160667, + "nauc_map_at_1_std": 0.14038510674546484, + "nauc_map_at_20_diff1": -0.05478397735033253, + "nauc_map_at_20_max": 0.24769968058172737, + "nauc_map_at_20_std": 0.1644650168558283, + "nauc_map_at_3_diff1": -0.03807829060397246, + "nauc_map_at_3_max": 0.26309237206315705, + "nauc_map_at_3_std": 0.15372382948965455, + "nauc_map_at_5_diff1": -0.044967332837981974, + "nauc_map_at_5_max": 0.25649607923444634, + "nauc_map_at_5_std": 0.15981535027578275, + "nauc_mrr_at_1000_diff1": -0.05679407077785212, + "nauc_mrr_at_1000_max": 0.24691946245210117, + "nauc_mrr_at_1000_std": 0.16749286350882947, + "nauc_mrr_at_100_diff1": -0.05632561129690453, + "nauc_mrr_at_100_max": 0.24719933996971935, + "nauc_mrr_at_100_std": 0.1672070922985018, + "nauc_mrr_at_10_diff1": -0.0501591064614069, + "nauc_mrr_at_10_max": 0.250622471700301, + "nauc_mrr_at_10_std": 0.1629930494430865, + "nauc_mrr_at_1_diff1": 0.002816775649447694, + "nauc_mrr_at_1_max": 0.2620714396160667, + "nauc_mrr_at_1_std": 0.14038510674546484, + "nauc_mrr_at_20_diff1": -0.05478397735033253, + "nauc_mrr_at_20_max": 0.24769968058172737, + "nauc_mrr_at_20_std": 0.1644650168558283, + "nauc_mrr_at_3_diff1": -0.03807829060397246, + "nauc_mrr_at_3_max": 0.26309237206315705, + "nauc_mrr_at_3_std": 0.15372382948965455, + "nauc_mrr_at_5_diff1": -0.044967332837981974, + "nauc_mrr_at_5_max": 0.25649607923444634, + "nauc_mrr_at_5_std": 0.15981535027578275, + "nauc_ndcg_at_1000_diff1": -0.10767592440203741, + "nauc_ndcg_at_1000_max": 0.21615888872018757, + "nauc_ndcg_at_1000_std": 0.20234828127047294, + "nauc_ndcg_at_100_diff1": -0.09527501470796423, + "nauc_ndcg_at_100_max": 0.22584801317695086, + "nauc_ndcg_at_100_std": 0.19821008677051302, + "nauc_ndcg_at_10_diff1": -0.069652074172003, + "nauc_ndcg_at_10_max": 0.23816897578454002, + "nauc_ndcg_at_10_std": 0.1720616038543109, + "nauc_ndcg_at_1_diff1": 0.002816775649447694, + "nauc_ndcg_at_1_max": 0.2620714396160667, + "nauc_ndcg_at_1_std": 0.14038510674546484, + "nauc_ndcg_at_20_diff1": -0.08481655619076496, + "nauc_ndcg_at_20_max": 0.22862590227739915, + "nauc_ndcg_at_20_std": 0.1776415341013595, + "nauc_ndcg_at_3_diff1": -0.04752797905728647, + "nauc_ndcg_at_3_max": 0.2623529367071397, + "nauc_ndcg_at_3_std": 0.15593264119745082, + "nauc_ndcg_at_5_diff1": -0.05790217171415268, + "nauc_ndcg_at_5_max": 0.2519485918738827, + "nauc_ndcg_at_5_std": 0.1653340810398282, + "nauc_precision_at_1000_diff1": -0.339325057249443, + "nauc_precision_at_1000_max": 0.06456103848012733, + "nauc_precision_at_1000_std": 0.3614510242060348, + "nauc_precision_at_100_diff1": -0.20552129890710427, + "nauc_precision_at_100_max": 0.16598339950954463, + "nauc_precision_at_100_std": 0.3021379562752926, + "nauc_precision_at_10_diff1": -0.1137132696406204, + "nauc_precision_at_10_max": 0.20713146416763584, + "nauc_precision_at_10_std": 0.19268854649650544, + "nauc_precision_at_1_diff1": 0.002816775649447694, + "nauc_precision_at_1_max": 0.2620714396160667, + "nauc_precision_at_1_std": 0.14038510674546484, + "nauc_precision_at_20_diff1": -0.15825713631811553, + "nauc_precision_at_20_max": 0.17926671491613969, + "nauc_precision_at_20_std": 0.2101713360156665, + "nauc_precision_at_3_diff1": -0.06901530955491124, + "nauc_precision_at_3_max": 0.26041868374110017, + "nauc_precision_at_3_std": 0.16072874244310245, + "nauc_precision_at_5_diff1": -0.08636211158513593, + "nauc_precision_at_5_max": 0.24111665883255926, + "nauc_precision_at_5_std": 0.17763637783246108, + "nauc_recall_at_1000_diff1": -0.3393250572494427, + "nauc_recall_at_1000_max": 0.06456103848012812, + "nauc_recall_at_1000_std": 0.36145102420603537, + "nauc_recall_at_100_diff1": -0.2055212989071044, + "nauc_recall_at_100_max": 0.16598339950954422, + "nauc_recall_at_100_std": 0.3021379562752921, + "nauc_recall_at_10_diff1": -0.11371326964062044, + "nauc_recall_at_10_max": 0.20713146416763603, + "nauc_recall_at_10_std": 0.19268854649650544, + "nauc_recall_at_1_diff1": 0.002816775649447694, + "nauc_recall_at_1_max": 0.2620714396160667, + "nauc_recall_at_1_std": 0.14038510674546484, + "nauc_recall_at_20_diff1": -0.15825713631811542, + "nauc_recall_at_20_max": 0.17926671491613994, + "nauc_recall_at_20_std": 0.21017133601566662, + "nauc_recall_at_3_diff1": -0.06901530955491082, + "nauc_recall_at_3_max": 0.26041868374110044, + "nauc_recall_at_3_std": 0.1607287424431028, + "nauc_recall_at_5_diff1": -0.08636211158513593, + "nauc_recall_at_5_max": 0.24111665883255917, + "nauc_recall_at_5_std": 0.17763637783246078, + "ndcg_at_1": 0.10392, + "ndcg_at_10": 0.20789, + "ndcg_at_100": 0.24852, + "ndcg_at_1000": 0.27144, + "ndcg_at_20": 0.22268, + "ndcg_at_3": 0.16907, + "ndcg_at_5": 0.18914, + "precision_at_1": 0.10392, + "precision_at_10": 0.03199, + "precision_at_100": 0.00518, + "precision_at_1000": 0.0007, + "precision_at_20": 0.01891, + "precision_at_3": 0.07109, + "precision_at_5": 0.05234, + "recall_at_1": 0.10392, + "recall_at_10": 0.31991, + "recall_at_100": 0.5185, + "recall_at_1000": 0.70457, + "recall_at_20": 0.37813, + "recall_at_3": 0.21328, + "recall_at_5": 0.2617 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/Quail.json b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/Quail.json new file mode 100644 index 000000000..1cfd416f0 --- /dev/null +++ b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/Quail.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 14.206177949905396, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02005, + "map_at_1": 0.00625, + "map_at_10": 0.01433, + "map_at_100": 0.01713, + "map_at_1000": 0.01784, + "map_at_20": 0.01558, + "map_at_3": 0.01078, + "map_at_5": 0.0124, + "mrr_at_1": 0.00625, + "mrr_at_10": 0.014321895424836605, + "mrr_at_100": 0.017122450088100857, + "mrr_at_1000": 0.01783155951432448, + "mrr_at_20": 0.015577369444407565, + "mrr_at_3": 0.010784313725490192, + "mrr_at_5": 0.012328431372549017, + "nauc_map_at_1000_diff1": 0.19418168025915902, + "nauc_map_at_1000_max": 0.2614236645747492, + "nauc_map_at_1000_std": 0.28513827147937226, + "nauc_map_at_100_diff1": 0.1981794665379785, + "nauc_map_at_100_max": 0.26491672060948873, + "nauc_map_at_100_std": 0.28727038128480076, + "nauc_map_at_10_diff1": 0.23930640374400253, + "nauc_map_at_10_max": 0.3016977694199745, + "nauc_map_at_10_std": 0.2970612614633832, + "nauc_map_at_1_diff1": 0.41015483198914127, + "nauc_map_at_1_max": 0.24185987783898102, + "nauc_map_at_1_std": 0.17688094824728928, + "nauc_map_at_20_diff1": 0.21424218395852881, + "nauc_map_at_20_max": 0.2846657294398872, + "nauc_map_at_20_std": 0.297051792613521, + "nauc_map_at_3_diff1": 0.28538063760762994, + "nauc_map_at_3_max": 0.35348165719442887, + "nauc_map_at_3_std": 0.29091457911554525, + "nauc_map_at_5_diff1": 0.26629480311921017, + "nauc_map_at_5_max": 0.3218884785843288, + "nauc_map_at_5_std": 0.2884353415043094, + "nauc_mrr_at_1000_diff1": 0.19414153102361392, + "nauc_mrr_at_1000_max": 0.26188163626773137, + "nauc_mrr_at_1000_std": 0.2853493030661739, + "nauc_mrr_at_100_diff1": 0.19813835270711722, + "nauc_mrr_at_100_max": 0.2653850016549682, + "nauc_mrr_at_100_std": 0.28748666506225407, + "nauc_mrr_at_10_diff1": 0.23929347820026386, + "nauc_mrr_at_10_max": 0.30229714732908763, + "nauc_mrr_at_10_std": 0.2973230243475005, + "nauc_mrr_at_1_diff1": 0.41015483198914127, + "nauc_mrr_at_1_max": 0.24185987783898102, + "nauc_mrr_at_1_std": 0.17688094824728928, + "nauc_mrr_at_20_diff1": 0.21422114522789767, + "nauc_mrr_at_20_max": 0.28521057876594225, + "nauc_mrr_at_20_std": 0.2972924549917342, + "nauc_mrr_at_3_diff1": 0.28538063760762994, + "nauc_mrr_at_3_max": 0.35348165719442887, + "nauc_mrr_at_3_std": 0.29091457911554525, + "nauc_mrr_at_5_diff1": 0.26393517083706514, + "nauc_mrr_at_5_max": 0.32503569940699245, + "nauc_mrr_at_5_std": 0.29138304063464665, + "nauc_ndcg_at_1000_diff1": 0.09875589286088866, + "nauc_ndcg_at_1000_max": 0.17341165292910896, + "nauc_ndcg_at_1000_std": 0.25649137997290944, + "nauc_ndcg_at_100_diff1": 0.11873647450248587, + "nauc_ndcg_at_100_max": 0.19297165410683342, + "nauc_ndcg_at_100_std": 0.27571269785551683, + "nauc_ndcg_at_10_diff1": 0.2044920457225081, + "nauc_ndcg_at_10_max": 0.29146323323415824, + "nauc_ndcg_at_10_std": 0.3160432634013452, + "nauc_ndcg_at_1_diff1": 0.41015483198914127, + "nauc_ndcg_at_1_max": 0.24185987783898102, + "nauc_ndcg_at_1_std": 0.17688094824728928, + "nauc_ndcg_at_20_diff1": 0.1546122748498037, + "nauc_ndcg_at_20_max": 0.2552836614077521, + "nauc_ndcg_at_20_std": 0.3134382743789195, + "nauc_ndcg_at_3_diff1": 0.2681545301255103, + "nauc_ndcg_at_3_max": 0.3759469055513397, + "nauc_ndcg_at_3_std": 0.31119859076631357, + "nauc_ndcg_at_5_diff1": 0.2429312507999789, + "nauc_ndcg_at_5_max": 0.32648065336971155, + "nauc_ndcg_at_5_std": 0.303346852327321, + "nauc_precision_at_1000_diff1": 0.05481114341931888, + "nauc_precision_at_1000_max": 0.12451535654089897, + "nauc_precision_at_1000_std": 0.23163260474717495, + "nauc_precision_at_100_diff1": 0.06674566229369451, + "nauc_precision_at_100_max": 0.13398391874735516, + "nauc_precision_at_100_std": 0.2590461278036397, + "nauc_precision_at_10_diff1": 0.16249348203573113, + "nauc_precision_at_10_max": 0.2745822174747255, + "nauc_precision_at_10_std": 0.33830386116609545, + "nauc_precision_at_1_diff1": 0.41015483198914127, + "nauc_precision_at_1_max": 0.24185987783898102, + "nauc_precision_at_1_std": 0.17688094824728928, + "nauc_precision_at_20_diff1": 0.0924026335885742, + "nauc_precision_at_20_max": 0.21937627706342516, + "nauc_precision_at_20_std": 0.3273823037708202, + "nauc_precision_at_3_diff1": 0.23780463438165436, + "nauc_precision_at_3_max": 0.41736836997413945, + "nauc_precision_at_3_std": 0.3481209574753525, + "nauc_precision_at_5_diff1": 0.20685253392524675, + "nauc_precision_at_5_max": 0.33078436633574826, + "nauc_precision_at_5_std": 0.3248896260702005, + "nauc_recall_at_1000_diff1": 0.05481114341931925, + "nauc_recall_at_1000_max": 0.12451535654089899, + "nauc_recall_at_1000_std": 0.23163260474717526, + "nauc_recall_at_100_diff1": 0.06674566229369454, + "nauc_recall_at_100_max": 0.13398391874735496, + "nauc_recall_at_100_std": 0.25904612780363934, + "nauc_recall_at_10_diff1": 0.16249348203573116, + "nauc_recall_at_10_max": 0.27458221747472555, + "nauc_recall_at_10_std": 0.33830386116609545, + "nauc_recall_at_1_diff1": 0.41015483198914127, + "nauc_recall_at_1_max": 0.24185987783898102, + "nauc_recall_at_1_std": 0.17688094824728928, + "nauc_recall_at_20_diff1": 0.09240263358857406, + "nauc_recall_at_20_max": 0.21937627706342494, + "nauc_recall_at_20_std": 0.32738230377081995, + "nauc_recall_at_3_diff1": 0.23780463438165422, + "nauc_recall_at_3_max": 0.4173683699741393, + "nauc_recall_at_3_std": 0.3481209574753525, + "nauc_recall_at_5_diff1": 0.2068525339252464, + "nauc_recall_at_5_max": 0.33078436633574804, + "nauc_recall_at_5_std": 0.32488962607020033, + "ndcg_at_1": 0.00625, + "ndcg_at_10": 0.02005, + "ndcg_at_100": 0.03683, + "ndcg_at_1000": 0.06182, + "ndcg_at_20": 0.02468, + "ndcg_at_3": 0.01244, + "ndcg_at_5": 0.01533, + "precision_at_1": 0.00625, + "precision_at_10": 0.0039, + "precision_at_100": 0.00125, + "precision_at_1000": 0.00034, + "precision_at_20": 0.00287, + "precision_at_3": 0.00576, + "precision_at_5": 0.00485, + "recall_at_1": 0.00625, + "recall_at_10": 0.03897, + "recall_at_100": 0.125, + "recall_at_1000": 0.33566, + "recall_at_20": 0.05735, + "recall_at_3": 0.01728, + "recall_at_5": 0.02426 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/RARbCode.json b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/RARbCode.json new file mode 100644 index 000000000..5e7a88d25 --- /dev/null +++ b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/RARbCode.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 414.69705605506897, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.41524, + "map_at_1": 0.28032, + "map_at_10": 0.36765, + "map_at_100": 0.37635, + "map_at_1000": 0.37699, + "map_at_20": 0.37264, + "map_at_3": 0.34232, + "map_at_5": 0.35674, + "mrr_at_1": 0.2803234501347709, + "mrr_at_10": 0.36764616223847996, + "mrr_at_100": 0.37635324096894374, + "mrr_at_1000": 0.37698732378221633, + "mrr_at_20": 0.3726356516801341, + "mrr_at_3": 0.34231805929919124, + "mrr_at_5": 0.3567385444743933, + "nauc_map_at_1000_diff1": 0.4432207492123247, + "nauc_map_at_1000_max": 0.2678789439795066, + "nauc_map_at_1000_std": 0.11396219754479885, + "nauc_map_at_100_diff1": 0.4429246003235531, + "nauc_map_at_100_max": 0.2678097288416373, + "nauc_map_at_100_std": 0.11406353787620592, + "nauc_map_at_10_diff1": 0.4423177782233741, + "nauc_map_at_10_max": 0.266589603235675, + "nauc_map_at_10_std": 0.11006350168532078, + "nauc_map_at_1_diff1": 0.5315818452035748, + "nauc_map_at_1_max": 0.25738718972063684, + "nauc_map_at_1_std": 0.08808757851933524, + "nauc_map_at_20_diff1": 0.4416165089436131, + "nauc_map_at_20_max": 0.2676532031683357, + "nauc_map_at_20_std": 0.11313241690559629, + "nauc_map_at_3_diff1": 0.45724384214616864, + "nauc_map_at_3_max": 0.26558587382521387, + "nauc_map_at_3_std": 0.10415333887444318, + "nauc_map_at_5_diff1": 0.4461269387684228, + "nauc_map_at_5_max": 0.2612211344587996, + "nauc_map_at_5_std": 0.10485510925520782, + "nauc_mrr_at_1000_diff1": 0.443221700136747, + "nauc_mrr_at_1000_max": 0.2678777716916454, + "nauc_mrr_at_1000_std": 0.11396132739590698, + "nauc_mrr_at_100_diff1": 0.4429255474284813, + "nauc_mrr_at_100_max": 0.2678085655583522, + "nauc_mrr_at_100_std": 0.11406265874459591, + "nauc_mrr_at_10_diff1": 0.4423177782233741, + "nauc_mrr_at_10_max": 0.266589603235675, + "nauc_mrr_at_10_std": 0.11006350168532078, + "nauc_mrr_at_1_diff1": 0.5315818452035748, + "nauc_mrr_at_1_max": 0.25738718972063684, + "nauc_mrr_at_1_std": 0.08808757851933524, + "nauc_mrr_at_20_diff1": 0.4416165089436131, + "nauc_mrr_at_20_max": 0.2676532031683357, + "nauc_mrr_at_20_std": 0.11313241690559629, + "nauc_mrr_at_3_diff1": 0.45724384214616864, + "nauc_mrr_at_3_max": 0.26558587382521387, + "nauc_mrr_at_3_std": 0.10415333887444318, + "nauc_mrr_at_5_diff1": 0.4461269387684228, + "nauc_mrr_at_5_max": 0.2612211344587996, + "nauc_mrr_at_5_std": 0.10485510925520782, + "nauc_ndcg_at_1000_diff1": 0.42084666962803907, + "nauc_ndcg_at_1000_max": 0.2805634823232343, + "nauc_ndcg_at_1000_std": 0.13738285275881237, + "nauc_ndcg_at_100_diff1": 0.41351606954528364, + "nauc_ndcg_at_100_max": 0.28069491183060435, + "nauc_ndcg_at_100_std": 0.14128075504470777, + "nauc_ndcg_at_10_diff1": 0.40540548407219335, + "nauc_ndcg_at_10_max": 0.271943726980855, + "nauc_ndcg_at_10_std": 0.1220041553779375, + "nauc_ndcg_at_1_diff1": 0.5315818452035748, + "nauc_ndcg_at_1_max": 0.25738718972063684, + "nauc_ndcg_at_1_std": 0.08808757851933524, + "nauc_ndcg_at_20_diff1": 0.402573874345797, + "nauc_ndcg_at_20_max": 0.2764682031558545, + "nauc_ndcg_at_20_std": 0.13377691151094645, + "nauc_ndcg_at_3_diff1": 0.4350483234026452, + "nauc_ndcg_at_3_max": 0.267198894572138, + "nauc_ndcg_at_3_std": 0.10868152087333308, + "nauc_ndcg_at_5_diff1": 0.41491763771843776, + "nauc_ndcg_at_5_max": 0.2593090563972338, + "nauc_ndcg_at_5_std": 0.10999357919972876, + "nauc_precision_at_1000_diff1": 0.32835340895342324, + "nauc_precision_at_1000_max": 0.5448138520773129, + "nauc_precision_at_1000_std": 0.5206203906425675, + "nauc_precision_at_100_diff1": 0.29868208679310915, + "nauc_precision_at_100_max": 0.37861596983354456, + "nauc_precision_at_100_std": 0.3222641489031205, + "nauc_precision_at_10_diff1": 0.2873037825874559, + "nauc_precision_at_10_max": 0.2915157040855642, + "nauc_precision_at_10_std": 0.16254524861568517, + "nauc_precision_at_1_diff1": 0.5315818452035748, + "nauc_precision_at_1_max": 0.25738718972063684, + "nauc_precision_at_1_std": 0.08808757851933524, + "nauc_precision_at_20_diff1": 0.2630745669961495, + "nauc_precision_at_20_max": 0.3148031739726345, + "nauc_precision_at_20_std": 0.2195192131746571, + "nauc_precision_at_3_diff1": 0.37345148458070143, + "nauc_precision_at_3_max": 0.27141665246302216, + "nauc_precision_at_3_std": 0.12116485607742007, + "nauc_precision_at_5_diff1": 0.32391864739292286, + "nauc_precision_at_5_max": 0.2524455814170421, + "nauc_precision_at_5_std": 0.12460851470488332, + "nauc_recall_at_1000_diff1": 0.3283534089534244, + "nauc_recall_at_1000_max": 0.5448138520773169, + "nauc_recall_at_1000_std": 0.5206203906425709, + "nauc_recall_at_100_diff1": 0.2986820867931085, + "nauc_recall_at_100_max": 0.378615969833544, + "nauc_recall_at_100_std": 0.3222641489031199, + "nauc_recall_at_10_diff1": 0.28730378258745604, + "nauc_recall_at_10_max": 0.29151570408556426, + "nauc_recall_at_10_std": 0.16254524861568545, + "nauc_recall_at_1_diff1": 0.5315818452035748, + "nauc_recall_at_1_max": 0.25738718972063684, + "nauc_recall_at_1_std": 0.08808757851933524, + "nauc_recall_at_20_diff1": 0.26307456699614995, + "nauc_recall_at_20_max": 0.314803173972635, + "nauc_recall_at_20_std": 0.2195192131746579, + "nauc_recall_at_3_diff1": 0.37345148458070165, + "nauc_recall_at_3_max": 0.2714166524630225, + "nauc_recall_at_3_std": 0.12116485607742007, + "nauc_recall_at_5_diff1": 0.3239186473929233, + "nauc_recall_at_5_max": 0.2524455814170427, + "nauc_recall_at_5_std": 0.12460851470488377, + "ndcg_at_1": 0.28032, + "ndcg_at_10": 0.41524, + "ndcg_at_100": 0.46033, + "ndcg_at_1000": 0.47888, + "ndcg_at_20": 0.43323, + "ndcg_at_3": 0.36256, + "ndcg_at_5": 0.3886, + "precision_at_1": 0.28032, + "precision_at_10": 0.05674, + "precision_at_100": 0.00785, + "precision_at_1000": 0.00093, + "precision_at_20": 0.03191, + "precision_at_3": 0.14039, + "precision_at_5": 0.0969, + "recall_at_1": 0.28032, + "recall_at_10": 0.56739, + "recall_at_100": 0.78504, + "recall_at_1000": 0.93464, + "recall_at_20": 0.63814, + "recall_at_3": 0.42116, + "recall_at_5": 0.4845 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/RARbMath.json b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/RARbMath.json new file mode 100644 index 000000000..6c315e1b1 --- /dev/null +++ b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/RARbMath.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 641.1556694507599, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.46499, + "map_at_1": 0.39642, + "map_at_10": 0.43948, + "map_at_100": 0.44715, + "map_at_1000": 0.44789, + "map_at_20": 0.44376, + "map_at_3": 0.42504, + "map_at_5": 0.43273, + "mrr_at_1": 0.3964234847285963, + "mrr_at_10": 0.43948453517610003, + "mrr_at_100": 0.44715093907266484, + "mrr_at_1000": 0.44788568041115234, + "mrr_at_20": 0.44376115727865423, + "mrr_at_3": 0.42504088199609624, + "mrr_at_5": 0.43273197235849564, + "nauc_map_at_1000_diff1": 0.7604502375160113, + "nauc_map_at_1000_max": 0.3136535224751929, + "nauc_map_at_1000_std": -0.08562034353995605, + "nauc_map_at_100_diff1": 0.7601700636310588, + "nauc_map_at_100_max": 0.31344214042920243, + "nauc_map_at_100_std": -0.08575293411342455, + "nauc_map_at_10_diff1": 0.7629852295254623, + "nauc_map_at_10_max": 0.3132522484628133, + "nauc_map_at_10_std": -0.08878424247576594, + "nauc_map_at_1_diff1": 0.8060055320912798, + "nauc_map_at_1_max": 0.34033342690829327, + "nauc_map_at_1_std": -0.07802677391008361, + "nauc_map_at_20_diff1": 0.7604624986631677, + "nauc_map_at_20_max": 0.3125510652958948, + "nauc_map_at_20_std": -0.0873664980209971, + "nauc_map_at_3_diff1": 0.775028889292432, + "nauc_map_at_3_max": 0.3198752110444364, + "nauc_map_at_3_std": -0.08611526076111055, + "nauc_map_at_5_diff1": 0.7673992934538139, + "nauc_map_at_5_max": 0.31498772777456924, + "nauc_map_at_5_std": -0.08874615927636101, + "nauc_mrr_at_1000_diff1": 0.7604502375160113, + "nauc_mrr_at_1000_max": 0.3136535224751929, + "nauc_mrr_at_1000_std": -0.08562034353995605, + "nauc_mrr_at_100_diff1": 0.7601700636310588, + "nauc_mrr_at_100_max": 0.31344214042920243, + "nauc_mrr_at_100_std": -0.08575293411342455, + "nauc_mrr_at_10_diff1": 0.7629852295254623, + "nauc_mrr_at_10_max": 0.3132522484628133, + "nauc_mrr_at_10_std": -0.08878424247576594, + "nauc_mrr_at_1_diff1": 0.8060055320912798, + "nauc_mrr_at_1_max": 0.34033342690829327, + "nauc_mrr_at_1_std": -0.07802677391008361, + "nauc_mrr_at_20_diff1": 0.7604624986631677, + "nauc_mrr_at_20_max": 0.3125510652958948, + "nauc_mrr_at_20_std": -0.0873664980209971, + "nauc_mrr_at_3_diff1": 0.775028889292432, + "nauc_mrr_at_3_max": 0.3198752110444364, + "nauc_mrr_at_3_std": -0.08611526076111055, + "nauc_mrr_at_5_diff1": 0.7673992934538139, + "nauc_mrr_at_5_max": 0.31498772777456924, + "nauc_mrr_at_5_std": -0.08874615927636101, + "nauc_ndcg_at_1000_diff1": 0.7351284127714339, + "nauc_ndcg_at_1000_max": 0.3093618249435201, + "nauc_ndcg_at_1000_std": -0.07121627861888048, + "nauc_ndcg_at_100_diff1": 0.7268782074015258, + "nauc_ndcg_at_100_max": 0.3039281309211191, + "nauc_ndcg_at_100_std": -0.07387103624377098, + "nauc_ndcg_at_10_diff1": 0.7396431840817339, + "nauc_ndcg_at_10_max": 0.29950882546863183, + "nauc_ndcg_at_10_std": -0.0929396020626785, + "nauc_ndcg_at_1_diff1": 0.8060055320912798, + "nauc_ndcg_at_1_max": 0.34033342690829327, + "nauc_ndcg_at_1_std": -0.07802677391008361, + "nauc_ndcg_at_20_diff1": 0.7301317986232748, + "nauc_ndcg_at_20_max": 0.2968036934197857, + "nauc_ndcg_at_20_std": -0.08779386537454927, + "nauc_ndcg_at_3_diff1": 0.7647940579847343, + "nauc_ndcg_at_3_max": 0.3131374944411467, + "nauc_ndcg_at_3_std": -0.08820248862002544, + "nauc_ndcg_at_5_diff1": 0.7508953288033724, + "nauc_ndcg_at_5_max": 0.3042323163719015, + "nauc_ndcg_at_5_std": -0.09292505838460233, + "nauc_precision_at_1000_diff1": 0.48678579909631514, + "nauc_precision_at_1000_max": 0.38559405167585475, + "nauc_precision_at_1000_std": 0.2763021898895817, + "nauc_precision_at_100_diff1": 0.543288259071437, + "nauc_precision_at_100_max": 0.2748373892478634, + "nauc_precision_at_100_std": 0.03155605710402436, + "nauc_precision_at_10_diff1": 0.6605299691365243, + "nauc_precision_at_10_max": 0.2534165367058916, + "nauc_precision_at_10_std": -0.10608359533034598, + "nauc_precision_at_1_diff1": 0.8060055320912798, + "nauc_precision_at_1_max": 0.34033342690829327, + "nauc_precision_at_1_std": -0.07802677391008361, + "nauc_precision_at_20_diff1": 0.6131529517210937, + "nauc_precision_at_20_max": 0.23821906258948078, + "nauc_precision_at_20_std": -0.08461864008142721, + "nauc_precision_at_3_diff1": 0.7348370003857593, + "nauc_precision_at_3_max": 0.2934230844877828, + "nauc_precision_at_3_std": -0.094131858770072, + "nauc_precision_at_5_diff1": 0.7001452792272154, + "nauc_precision_at_5_max": 0.27118733164888265, + "nauc_precision_at_5_std": -0.10572227477637407, + "nauc_recall_at_1000_diff1": 0.48678579909631664, + "nauc_recall_at_1000_max": 0.3855940516758572, + "nauc_recall_at_1000_std": 0.2763021898895846, + "nauc_recall_at_100_diff1": 0.5432882590714365, + "nauc_recall_at_100_max": 0.27483738924786255, + "nauc_recall_at_100_std": 0.03155605710402365, + "nauc_recall_at_10_diff1": 0.6605299691365246, + "nauc_recall_at_10_max": 0.25341653670589187, + "nauc_recall_at_10_std": -0.10608359533034563, + "nauc_recall_at_1_diff1": 0.8060055320912798, + "nauc_recall_at_1_max": 0.34033342690829327, + "nauc_recall_at_1_std": -0.07802677391008361, + "nauc_recall_at_20_diff1": 0.6131529517210943, + "nauc_recall_at_20_max": 0.23821906258948122, + "nauc_recall_at_20_std": -0.08461864008142653, + "nauc_recall_at_3_diff1": 0.7348370003857588, + "nauc_recall_at_3_max": 0.293423084487783, + "nauc_recall_at_3_std": -0.0941318587700714, + "nauc_recall_at_5_diff1": 0.700145279227215, + "nauc_recall_at_5_max": 0.27118733164888287, + "nauc_recall_at_5_std": -0.10572227477637336, + "ndcg_at_1": 0.39642, + "ndcg_at_10": 0.46499, + "ndcg_at_100": 0.50634, + "ndcg_at_1000": 0.52727, + "ndcg_at_20": 0.48069, + "ndcg_at_3": 0.43451, + "ndcg_at_5": 0.44838, + "precision_at_1": 0.39642, + "precision_at_10": 0.05476, + "precision_at_100": 0.0075, + "precision_at_1000": 0.00092, + "precision_at_20": 0.0305, + "precision_at_3": 0.15398, + "precision_at_5": 0.09913, + "recall_at_1": 0.39642, + "recall_at_10": 0.54755, + "recall_at_100": 0.75044, + "recall_at_1000": 0.91834, + "recall_at_20": 0.60991, + "recall_at_3": 0.46194, + "recall_at_5": 0.49565 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/SIQA.json b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/SIQA.json new file mode 100644 index 000000000..1c3c17498 --- /dev/null +++ b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/SIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 8.069786071777344, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.00981, + "map_at_1": 0.00409, + "map_at_10": 0.0074, + "map_at_100": 0.00921, + "map_at_1000": 0.00972, + "map_at_20": 0.00831, + "map_at_3": 0.00597, + "map_at_5": 0.00628, + "mrr_at_1": 0.0040941658137154556, + "mrr_at_10": 0.007401382593296613, + "mrr_at_100": 0.009210796165553857, + "mrr_at_1000": 0.009724179315163789, + "mrr_at_20": 0.008314215988519075, + "mrr_at_3": 0.005970658478335039, + "mrr_at_5": 0.006277720914363698, + "nauc_map_at_1000_diff1": 0.07447989299777821, + "nauc_map_at_1000_max": -0.012085018367037362, + "nauc_map_at_1000_std": -0.08717812778929826, + "nauc_map_at_100_diff1": 0.07915022502424725, + "nauc_map_at_100_max": -0.01286479509817553, + "nauc_map_at_100_std": -0.09269988998541398, + "nauc_map_at_10_diff1": 0.08762468386955542, + "nauc_map_at_10_max": -0.033923097219994806, + "nauc_map_at_10_std": -0.1284988113044257, + "nauc_map_at_1_diff1": 0.15439789712620836, + "nauc_map_at_1_max": -0.0010381058856798716, + "nauc_map_at_1_std": -0.1280017206025579, + "nauc_map_at_20_diff1": 0.08343939881551417, + "nauc_map_at_20_max": -0.01465341197177314, + "nauc_map_at_20_std": -0.10394071141472284, + "nauc_map_at_3_diff1": 0.055425389305253266, + "nauc_map_at_3_max": -0.08557365060297219, + "nauc_map_at_3_std": -0.19489549845972695, + "nauc_map_at_5_diff1": 0.059410255781059976, + "nauc_map_at_5_max": -0.09709348028998573, + "nauc_map_at_5_std": -0.19709091822015212, + "nauc_mrr_at_1000_diff1": 0.0744797945198824, + "nauc_mrr_at_1000_max": -0.012086258394608642, + "nauc_mrr_at_1000_std": -0.08717748850166752, + "nauc_mrr_at_100_diff1": 0.07915022502424725, + "nauc_mrr_at_100_max": -0.01286479509817553, + "nauc_mrr_at_100_std": -0.09269988998541398, + "nauc_mrr_at_10_diff1": 0.08762468386955542, + "nauc_mrr_at_10_max": -0.033923097219994806, + "nauc_mrr_at_10_std": -0.1284988113044257, + "nauc_mrr_at_1_diff1": 0.15439789712620836, + "nauc_mrr_at_1_max": -0.0010381058856798716, + "nauc_mrr_at_1_std": -0.1280017206025579, + "nauc_mrr_at_20_diff1": 0.08343939881551417, + "nauc_mrr_at_20_max": -0.01465341197177314, + "nauc_mrr_at_20_std": -0.10394071141472284, + "nauc_mrr_at_3_diff1": 0.055425389305253266, + "nauc_mrr_at_3_max": -0.08557365060297219, + "nauc_mrr_at_3_std": -0.19489549845972695, + "nauc_mrr_at_5_diff1": 0.059410255781059976, + "nauc_mrr_at_5_max": -0.09709348028998573, + "nauc_mrr_at_5_std": -0.19709091822015212, + "nauc_ndcg_at_1000_diff1": 0.033427390884758684, + "nauc_ndcg_at_1000_max": 0.02456695673631008, + "nauc_ndcg_at_1000_std": 0.0010781932616807186, + "nauc_ndcg_at_100_diff1": 0.06232050331161282, + "nauc_ndcg_at_100_max": 0.012377977208042174, + "nauc_ndcg_at_100_std": -0.026437333303116473, + "nauc_ndcg_at_10_diff1": 0.08612624770586527, + "nauc_ndcg_at_10_max": -0.01024109957284893, + "nauc_ndcg_at_10_std": -0.09155555128425921, + "nauc_ndcg_at_1_diff1": 0.15439789712620836, + "nauc_ndcg_at_1_max": -0.0010381058856798716, + "nauc_ndcg_at_1_std": -0.1280017206025579, + "nauc_ndcg_at_20_diff1": 0.07228150556490781, + "nauc_ndcg_at_20_max": 0.02555686060108657, + "nauc_ndcg_at_20_std": -0.04529018257692364, + "nauc_ndcg_at_3_diff1": 0.032978074576183895, + "nauc_ndcg_at_3_max": -0.1039047102748613, + "nauc_ndcg_at_3_std": -0.2078129452577576, + "nauc_ndcg_at_5_diff1": 0.0416256474951902, + "nauc_ndcg_at_5_max": -0.12197827529254217, + "nauc_ndcg_at_5_std": -0.21047312363227605, + "nauc_precision_at_1000_diff1": 0.016614306807587118, + "nauc_precision_at_1000_max": 0.03961828183732736, + "nauc_precision_at_1000_std": 0.03168647194946584, + "nauc_precision_at_100_diff1": 0.05187126789937876, + "nauc_precision_at_100_max": 0.020168118929940856, + "nauc_precision_at_100_std": 0.01007431539605394, + "nauc_precision_at_10_diff1": 0.08514610237754221, + "nauc_precision_at_10_max": 0.028407365611598047, + "nauc_precision_at_10_std": -0.03435132692131302, + "nauc_precision_at_1_diff1": 0.15439789712620836, + "nauc_precision_at_1_max": -0.0010381058856798716, + "nauc_precision_at_1_std": -0.1280017206025579, + "nauc_precision_at_20_diff1": 0.05827701542615609, + "nauc_precision_at_20_max": 0.07016359714603448, + "nauc_precision_at_20_std": 0.01857311836987206, + "nauc_precision_at_3_diff1": -0.014969417146622937, + "nauc_precision_at_3_max": -0.14287501550684076, + "nauc_precision_at_3_std": -0.23490963904182594, + "nauc_precision_at_5_diff1": 0.00900898091680353, + "nauc_precision_at_5_max": -0.1710142502134319, + "nauc_precision_at_5_std": -0.23567858589584925, + "nauc_recall_at_1000_diff1": 0.01661430680758714, + "nauc_recall_at_1000_max": 0.03961828183732763, + "nauc_recall_at_1000_std": 0.031686471949465986, + "nauc_recall_at_100_diff1": 0.05187126789937898, + "nauc_recall_at_100_max": 0.020168118929940918, + "nauc_recall_at_100_std": 0.010074315396054051, + "nauc_recall_at_10_diff1": 0.08514610237754229, + "nauc_recall_at_10_max": 0.028407365611597932, + "nauc_recall_at_10_std": -0.03435132692131308, + "nauc_recall_at_1_diff1": 0.15439789712620836, + "nauc_recall_at_1_max": -0.0010381058856798716, + "nauc_recall_at_1_std": -0.1280017206025579, + "nauc_recall_at_20_diff1": 0.058277015426155834, + "nauc_recall_at_20_max": 0.07016359714603419, + "nauc_recall_at_20_std": 0.018573118369871956, + "nauc_recall_at_3_diff1": -0.014969417146623077, + "nauc_recall_at_3_max": -0.1428750155068408, + "nauc_recall_at_3_std": -0.23490963904182605, + "nauc_recall_at_5_diff1": 0.009008980916803657, + "nauc_recall_at_5_max": -0.17101425021343178, + "nauc_recall_at_5_std": -0.23567858589584925, + "ndcg_at_1": 0.00409, + "ndcg_at_10": 0.00981, + "ndcg_at_100": 0.02056, + "ndcg_at_1000": 0.03964, + "ndcg_at_20": 0.01308, + "ndcg_at_3": 0.00654, + "ndcg_at_5": 0.00714, + "precision_at_1": 0.00409, + "precision_at_10": 0.00179, + "precision_at_100": 0.00073, + "precision_at_1000": 0.00024, + "precision_at_20": 0.00154, + "precision_at_3": 0.00273, + "precision_at_5": 0.00194, + "recall_at_1": 0.00409, + "recall_at_10": 0.01791, + "recall_at_100": 0.07318, + "recall_at_1000": 0.23541, + "recall_at_20": 0.03071, + "recall_at_3": 0.00819, + "recall_at_5": 0.00972 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/SpartQA.json b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/SpartQA.json new file mode 100644 index 000000000..6e0ca6a0a --- /dev/null +++ b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/SpartQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 7.533648252487183, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02857, + "map_at_1": 0.00306, + "map_at_10": 0.01561, + "map_at_100": 0.02067, + "map_at_1000": 0.02193, + "map_at_20": 0.01784, + "map_at_3": 0.00852, + "map_at_5": 0.01192, + "mrr_at_1": 0.004173622704507512, + "mrr_at_10": 0.024652087694658677, + "mrr_at_100": 0.03239484184915531, + "mrr_at_1000": 0.03374834895284076, + "mrr_at_20": 0.028307010707696627, + "mrr_at_3": 0.013030977555184571, + "mrr_at_5": 0.01869319235763311, + "nauc_map_at_1000_diff1": -0.023247541505640148, + "nauc_map_at_1000_max": -0.0414544768329071, + "nauc_map_at_1000_std": 0.19794771052063106, + "nauc_map_at_100_diff1": -0.02679970045258727, + "nauc_map_at_100_max": -0.038472598709711266, + "nauc_map_at_100_std": 0.19123079562086945, + "nauc_map_at_10_diff1": -0.033456193632482346, + "nauc_map_at_10_max": -0.00536117002763197, + "nauc_map_at_10_std": 0.19514351682319345, + "nauc_map_at_1_diff1": -0.3760908158653634, + "nauc_map_at_1_max": -0.15921684298778002, + "nauc_map_at_1_std": 0.27762648609064355, + "nauc_map_at_20_diff1": -0.02992212592244966, + "nauc_map_at_20_max": -0.01781253252041509, + "nauc_map_at_20_std": 0.19626717900294743, + "nauc_map_at_3_diff1": -0.15161724834962115, + "nauc_map_at_3_max": -0.022776410625008525, + "nauc_map_at_3_std": 0.24745410869517048, + "nauc_map_at_5_diff1": -0.08723392406273205, + "nauc_map_at_5_max": -0.018463890648043428, + "nauc_map_at_5_std": 0.19475975614706284, + "nauc_mrr_at_1000_diff1": 0.007978410398552158, + "nauc_mrr_at_1000_max": 0.036473687123347476, + "nauc_mrr_at_1000_std": 0.20055356904642052, + "nauc_mrr_at_100_diff1": 0.006310993445210062, + "nauc_mrr_at_100_max": 0.0365192394737216, + "nauc_mrr_at_100_std": 0.1971221473503456, + "nauc_mrr_at_10_diff1": -0.007507078816603962, + "nauc_mrr_at_10_max": 0.06121999407523352, + "nauc_mrr_at_10_std": 0.20339795754086343, + "nauc_mrr_at_1_diff1": -0.40147904740159013, + "nauc_mrr_at_1_max": -0.08077862338899514, + "nauc_mrr_at_1_std": 0.33751634147733606, + "nauc_mrr_at_20_diff1": 0.0027944056496741134, + "nauc_mrr_at_20_max": 0.051562754539992324, + "nauc_mrr_at_20_std": 0.20165231381946247, + "nauc_mrr_at_3_diff1": -0.12432429349728993, + "nauc_mrr_at_3_max": 0.05612985604838371, + "nauc_mrr_at_3_std": 0.28150160505729094, + "nauc_mrr_at_5_diff1": -0.05332164940797338, + "nauc_mrr_at_5_max": 0.058509519846370275, + "nauc_mrr_at_5_std": 0.21136612333834756, + "nauc_ndcg_at_1000_diff1": 0.06129447035852173, + "nauc_ndcg_at_1000_max": -0.09810515187609785, + "nauc_ndcg_at_1000_std": 0.253730927638004, + "nauc_ndcg_at_100_diff1": 0.02108787564678142, + "nauc_ndcg_at_100_max": -0.07091195141926947, + "nauc_ndcg_at_100_std": 0.16873764908191932, + "nauc_ndcg_at_10_diff1": 0.017263948909974576, + "nauc_ndcg_at_10_max": 0.023073277848953466, + "nauc_ndcg_at_10_std": 0.17899210422979736, + "nauc_ndcg_at_1_diff1": -0.40147904740159013, + "nauc_ndcg_at_1_max": -0.08077862338899514, + "nauc_ndcg_at_1_std": 0.33751634147733606, + "nauc_ndcg_at_20_diff1": 0.019065997684719095, + "nauc_ndcg_at_20_max": -0.002746631327086614, + "nauc_ndcg_at_20_std": 0.18430929477326727, + "nauc_ndcg_at_3_diff1": -0.12198238235378096, + "nauc_ndcg_at_3_max": 0.01343235503752329, + "nauc_ndcg_at_3_std": 0.24961447892103122, + "nauc_ndcg_at_5_diff1": -0.043194906085679816, + "nauc_ndcg_at_5_max": 0.015449825799040057, + "nauc_ndcg_at_5_std": 0.17731391579477893, + "nauc_precision_at_1000_diff1": 0.1133752788063319, + "nauc_precision_at_1000_max": -0.0778432379720834, + "nauc_precision_at_1000_std": 0.28823354690858455, + "nauc_precision_at_100_diff1": 0.06078453420734899, + "nauc_precision_at_100_max": -0.07906222145104003, + "nauc_precision_at_100_std": 0.16160152248896628, + "nauc_precision_at_10_diff1": 0.06292045788165064, + "nauc_precision_at_10_max": 0.0590704657941352, + "nauc_precision_at_10_std": 0.15627682828234096, + "nauc_precision_at_1_diff1": -0.40147904740159013, + "nauc_precision_at_1_max": -0.08077862338899514, + "nauc_precision_at_1_std": 0.33751634147733606, + "nauc_precision_at_20_diff1": 0.06745408739332585, + "nauc_precision_at_20_max": 0.02741498504060653, + "nauc_precision_at_20_std": 0.17055339739740094, + "nauc_precision_at_3_diff1": -0.07077747911652375, + "nauc_precision_at_3_max": 0.08900081335619826, + "nauc_precision_at_3_std": 0.26802742949202424, + "nauc_precision_at_5_diff1": 0.023354957155256477, + "nauc_precision_at_5_max": 0.07827450342288142, + "nauc_precision_at_5_std": 0.1538803088528427, + "nauc_recall_at_1000_diff1": 0.09792754928335262, + "nauc_recall_at_1000_max": -0.16576329460493303, + "nauc_recall_at_1000_std": 0.25581872607515616, + "nauc_recall_at_100_diff1": 0.027614668728395447, + "nauc_recall_at_100_max": -0.1272416962448981, + "nauc_recall_at_100_std": 0.13453642989208667, + "nauc_recall_at_10_diff1": 0.05346608604903748, + "nauc_recall_at_10_max": 0.01731604126017363, + "nauc_recall_at_10_std": 0.16406241468484487, + "nauc_recall_at_1_diff1": -0.3760908158653634, + "nauc_recall_at_1_max": -0.15921684298778002, + "nauc_recall_at_1_std": 0.27762648609064355, + "nauc_recall_at_20_diff1": 0.0376805771629268, + "nauc_recall_at_20_max": -0.027258234456886583, + "nauc_recall_at_20_std": 0.17695931975670287, + "nauc_recall_at_3_diff1": -0.0951225182975633, + "nauc_recall_at_3_max": 0.014477393981773641, + "nauc_recall_at_3_std": 0.22619544821806675, + "nauc_recall_at_5_diff1": -0.011394847305691546, + "nauc_recall_at_5_max": 0.009179029290685812, + "nauc_recall_at_5_std": 0.14700207851011307, + "ndcg_at_1": 0.00417, + "ndcg_at_10": 0.02857, + "ndcg_at_100": 0.06288, + "ndcg_at_1000": 0.10508, + "ndcg_at_20": 0.03794, + "ndcg_at_3": 0.01147, + "ndcg_at_5": 0.01846, + "precision_at_1": 0.00417, + "precision_at_10": 0.0096, + "precision_at_100": 0.00354, + "precision_at_1000": 0.00088, + "precision_at_20": 0.00757, + "precision_at_3": 0.00825, + "precision_at_5": 0.01002, + "recall_at_1": 0.00306, + "recall_at_10": 0.05815, + "recall_at_100": 0.21517, + "recall_at_1000": 0.52319, + "recall_at_20": 0.09108, + "recall_at_3": 0.01549, + "recall_at_5": 0.03042 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL1.json b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL1.json new file mode 100644 index 000000000..694371392 --- /dev/null +++ b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL1.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 6.4837119579315186, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01266, + "map_at_1": 0.00075, + "map_at_10": 0.00745, + "map_at_100": 0.01058, + "map_at_1000": 0.01138, + "map_at_20": 0.00878, + "map_at_3": 0.00375, + "map_at_5": 0.00545, + "mrr_at_1": 0.00075, + "mrr_at_10": 0.007454464285714283, + "mrr_at_100": 0.010578761486227163, + "mrr_at_1000": 0.011377937807513535, + "mrr_at_20": 0.008778479194094524, + "mrr_at_3": 0.0037500000000000007, + "mrr_at_5": 0.005449999999999997, + "nauc_map_at_1000_diff1": 0.058051646896854006, + "nauc_map_at_1000_max": 0.3133493752408613, + "nauc_map_at_1000_std": 0.20398210361678645, + "nauc_map_at_100_diff1": 0.060872371921145814, + "nauc_map_at_100_max": 0.31566094177077564, + "nauc_map_at_100_std": 0.20616703932788993, + "nauc_map_at_10_diff1": 0.07831101694809639, + "nauc_map_at_10_max": 0.3331556796645972, + "nauc_map_at_10_std": 0.2306674774204212, + "nauc_map_at_1_diff1": 0.04936946605849211, + "nauc_map_at_1_max": 0.06189070745013867, + "nauc_map_at_1_std": 0.1996243627582506, + "nauc_map_at_20_diff1": 0.0699416895025675, + "nauc_map_at_20_max": 0.3275199077921782, + "nauc_map_at_20_std": 0.2147433100184691, + "nauc_map_at_3_diff1": 0.09260352383507746, + "nauc_map_at_3_max": 0.33404883284142733, + "nauc_map_at_3_std": 0.2958769340846078, + "nauc_map_at_5_diff1": 0.10041465329864153, + "nauc_map_at_5_max": 0.33847167828122576, + "nauc_map_at_5_std": 0.26826369931297284, + "nauc_mrr_at_1000_diff1": 0.058051646896854006, + "nauc_mrr_at_1000_max": 0.3133493752408613, + "nauc_mrr_at_1000_std": 0.20398210361678645, + "nauc_mrr_at_100_diff1": 0.060872371921145814, + "nauc_mrr_at_100_max": 0.31566094177077564, + "nauc_mrr_at_100_std": 0.20616703932788993, + "nauc_mrr_at_10_diff1": 0.07831101694809639, + "nauc_mrr_at_10_max": 0.3331556796645972, + "nauc_mrr_at_10_std": 0.2306674774204212, + "nauc_mrr_at_1_diff1": 0.04936946605849211, + "nauc_mrr_at_1_max": 0.06189070745013867, + "nauc_mrr_at_1_std": 0.1996243627582506, + "nauc_mrr_at_20_diff1": 0.0699416895025675, + "nauc_mrr_at_20_max": 0.3275199077921782, + "nauc_mrr_at_20_std": 0.2147433100184691, + "nauc_mrr_at_3_diff1": 0.09260352383507746, + "nauc_mrr_at_3_max": 0.33404883284142733, + "nauc_mrr_at_3_std": 0.2958769340846078, + "nauc_mrr_at_5_diff1": 0.10041465329864153, + "nauc_mrr_at_5_max": 0.33847167828122576, + "nauc_mrr_at_5_std": 0.26826369931297284, + "nauc_ndcg_at_1000_diff1": 0.015611676241269065, + "nauc_ndcg_at_1000_max": 0.2951535932113366, + "nauc_ndcg_at_1000_std": 0.18804737209395364, + "nauc_ndcg_at_100_diff1": 0.03409928919682608, + "nauc_ndcg_at_100_max": 0.30079521268654874, + "nauc_ndcg_at_100_std": 0.18190953968549714, + "nauc_ndcg_at_10_diff1": 0.06711010032629668, + "nauc_ndcg_at_10_max": 0.33821403939460326, + "nauc_ndcg_at_10_std": 0.2100139153153549, + "nauc_ndcg_at_1_diff1": 0.04936946605849211, + "nauc_ndcg_at_1_max": 0.06189070745013867, + "nauc_ndcg_at_1_std": 0.1996243627582506, + "nauc_ndcg_at_20_diff1": 0.05563758307886325, + "nauc_ndcg_at_20_max": 0.3288672587560291, + "nauc_ndcg_at_20_std": 0.18487862004989336, + "nauc_ndcg_at_3_diff1": 0.08704881242080709, + "nauc_ndcg_at_3_max": 0.35222923815945834, + "nauc_ndcg_at_3_std": 0.2987194212105018, + "nauc_ndcg_at_5_diff1": 0.09836297945605711, + "nauc_ndcg_at_5_max": 0.34840174982139027, + "nauc_ndcg_at_5_std": 0.2602126649548603, + "nauc_precision_at_1000_diff1": -0.004759006356632049, + "nauc_precision_at_1000_max": 0.2899061907402261, + "nauc_precision_at_1000_std": 0.19417932944910116, + "nauc_precision_at_100_diff1": 0.018908672483377263, + "nauc_precision_at_100_max": 0.2916449469507796, + "nauc_precision_at_100_std": 0.17464301892289946, + "nauc_precision_at_10_diff1": 0.05573964761649219, + "nauc_precision_at_10_max": 0.3411702888829263, + "nauc_precision_at_10_std": 0.18918030587603968, + "nauc_precision_at_1_diff1": 0.04936946605849211, + "nauc_precision_at_1_max": 0.06189070745013867, + "nauc_precision_at_1_std": 0.1996243627582506, + "nauc_precision_at_20_diff1": 0.04457372219647506, + "nauc_precision_at_20_max": 0.32856333661270604, + "nauc_precision_at_20_std": 0.16082748602201244, + "nauc_precision_at_3_diff1": 0.07781922674121709, + "nauc_precision_at_3_max": 0.37845019344452435, + "nauc_precision_at_3_std": 0.302301427248414, + "nauc_precision_at_5_diff1": 0.09580047950007375, + "nauc_precision_at_5_max": 0.3579329565420603, + "nauc_precision_at_5_std": 0.24921886495235324, + "nauc_recall_at_1000_diff1": -0.00475900635663118, + "nauc_recall_at_1000_max": 0.28990619074022644, + "nauc_recall_at_1000_std": 0.19417932944910166, + "nauc_recall_at_100_diff1": 0.018908672483377416, + "nauc_recall_at_100_max": 0.2916449469507796, + "nauc_recall_at_100_std": 0.1746430189228995, + "nauc_recall_at_10_diff1": 0.055739647616492326, + "nauc_recall_at_10_max": 0.34117028888292633, + "nauc_recall_at_10_std": 0.1891803058760398, + "nauc_recall_at_1_diff1": 0.04936946605849211, + "nauc_recall_at_1_max": 0.06189070745013867, + "nauc_recall_at_1_std": 0.1996243627582506, + "nauc_recall_at_20_diff1": 0.044573722196474985, + "nauc_recall_at_20_max": 0.3285633366127061, + "nauc_recall_at_20_std": 0.1608274860220125, + "nauc_recall_at_3_diff1": 0.07781922674121712, + "nauc_recall_at_3_max": 0.37845019344452435, + "nauc_recall_at_3_std": 0.30230142724841397, + "nauc_recall_at_5_diff1": 0.0958004795000736, + "nauc_recall_at_5_max": 0.3579329565420602, + "nauc_recall_at_5_std": 0.24921886495235288, + "ndcg_at_1": 0.00075, + "ndcg_at_10": 0.01266, + "ndcg_at_100": 0.03156, + "ndcg_at_1000": 0.06281, + "ndcg_at_20": 0.01756, + "ndcg_at_3": 0.00477, + "ndcg_at_5": 0.0079, + "precision_at_1": 0.00075, + "precision_at_10": 0.003, + "precision_at_100": 0.00127, + "precision_at_1000": 0.0004, + "precision_at_20": 0.00248, + "precision_at_3": 0.00258, + "precision_at_5": 0.0031, + "recall_at_1": 0.00075, + "recall_at_10": 0.03, + "recall_at_100": 0.127, + "recall_at_1000": 0.39525, + "recall_at_20": 0.0495, + "recall_at_3": 0.00775, + "recall_at_5": 0.0155 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL2Fact.json b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL2Fact.json new file mode 100644 index 000000000..a17d48fab --- /dev/null +++ b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL2Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 14.65330195426941, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.16722, + "map_at_1": 0.06967, + "map_at_10": 0.13073, + "map_at_100": 0.14063, + "map_at_1000": 0.14153, + "map_at_20": 0.13572, + "map_at_3": 0.11003, + "map_at_5": 0.12059, + "mrr_at_1": 0.06966833425977395, + "mrr_at_10": 0.1307349615159512, + "mrr_at_100": 0.14063173994272213, + "mrr_at_1000": 0.14153145850897425, + "mrr_at_20": 0.1357229161903503, + "mrr_at_3": 0.11003026372676175, + "mrr_at_5": 0.12059168673954689, + "nauc_map_at_1000_diff1": 0.004099960738405665, + "nauc_map_at_1000_max": -0.05042464232732731, + "nauc_map_at_1000_std": 0.11007632819603767, + "nauc_map_at_100_diff1": 0.0044158916197503135, + "nauc_map_at_100_max": -0.05025951650103021, + "nauc_map_at_100_std": 0.11012484264318705, + "nauc_map_at_10_diff1": 0.012801890701608778, + "nauc_map_at_10_max": -0.04076155903094085, + "nauc_map_at_10_std": 0.09841828883045728, + "nauc_map_at_1_diff1": 0.05249140003740938, + "nauc_map_at_1_max": -0.05675447589815147, + "nauc_map_at_1_std": 0.05826590543045682, + "nauc_map_at_20_diff1": 0.007490190753345988, + "nauc_map_at_20_max": -0.04637479026055593, + "nauc_map_at_20_std": 0.10275702419320101, + "nauc_map_at_3_diff1": 0.026806069240343185, + "nauc_map_at_3_max": -0.030424935313501718, + "nauc_map_at_3_std": 0.07676126420843074, + "nauc_map_at_5_diff1": 0.019553017096872464, + "nauc_map_at_5_max": -0.034531729196599435, + "nauc_map_at_5_std": 0.09043867529692334, + "nauc_mrr_at_1000_diff1": 0.004099960738405665, + "nauc_mrr_at_1000_max": -0.05042464232732731, + "nauc_mrr_at_1000_std": 0.11007632819603767, + "nauc_mrr_at_100_diff1": 0.0044158916197503135, + "nauc_mrr_at_100_max": -0.05025951650103021, + "nauc_mrr_at_100_std": 0.11012484264318705, + "nauc_mrr_at_10_diff1": 0.012801890701608778, + "nauc_mrr_at_10_max": -0.04076155903094085, + "nauc_mrr_at_10_std": 0.09841828883045728, + "nauc_mrr_at_1_diff1": 0.05249140003740938, + "nauc_mrr_at_1_max": -0.05675447589815147, + "nauc_mrr_at_1_std": 0.05826590543045682, + "nauc_mrr_at_20_diff1": 0.007490190753345988, + "nauc_mrr_at_20_max": -0.04637479026055593, + "nauc_mrr_at_20_std": 0.10275702419320101, + "nauc_mrr_at_3_diff1": 0.026806069240343185, + "nauc_mrr_at_3_max": -0.030424935313501718, + "nauc_mrr_at_3_std": 0.07676126420843074, + "nauc_mrr_at_5_diff1": 0.019553017096872464, + "nauc_mrr_at_5_max": -0.034531729196599435, + "nauc_mrr_at_5_std": 0.09043867529692334, + "nauc_ndcg_at_1000_diff1": -0.04405285121377426, + "nauc_ndcg_at_1000_max": -0.09083078625737907, + "nauc_ndcg_at_1000_std": 0.17205780117085867, + "nauc_ndcg_at_100_diff1": -0.0388296923637338, + "nauc_ndcg_at_100_max": -0.08819965978128536, + "nauc_ndcg_at_100_std": 0.17641230449987408, + "nauc_ndcg_at_10_diff1": -0.0033220397734913753, + "nauc_ndcg_at_10_max": -0.04542692088849132, + "nauc_ndcg_at_10_std": 0.118123176259705, + "nauc_ndcg_at_1_diff1": 0.05249140003740938, + "nauc_ndcg_at_1_max": -0.05675447589815147, + "nauc_ndcg_at_1_std": 0.05826590543045682, + "nauc_ndcg_at_20_diff1": -0.019232071501018928, + "nauc_ndcg_at_20_max": -0.062072942599869174, + "nauc_ndcg_at_20_std": 0.13173437862044932, + "nauc_ndcg_at_3_diff1": 0.022038656846622817, + "nauc_ndcg_at_3_max": -0.025203041495316346, + "nauc_ndcg_at_3_std": 0.08154455335531258, + "nauc_ndcg_at_5_diff1": 0.010457560173135335, + "nauc_ndcg_at_5_max": -0.03226878449996761, + "nauc_ndcg_at_5_std": 0.10271304242657642, + "nauc_precision_at_1000_diff1": -0.256418143102918, + "nauc_precision_at_1000_max": -0.2865757577193985, + "nauc_precision_at_1000_std": 0.42678347836365377, + "nauc_precision_at_100_diff1": -0.15231398971409643, + "nauc_precision_at_100_max": -0.2023409464739884, + "nauc_precision_at_100_std": 0.3606022520318554, + "nauc_precision_at_10_diff1": -0.034836350519293464, + "nauc_precision_at_10_max": -0.0571337724515079, + "nauc_precision_at_10_std": 0.1563037677309709, + "nauc_precision_at_1_diff1": 0.05249140003740938, + "nauc_precision_at_1_max": -0.05675447589815147, + "nauc_precision_at_1_std": 0.05826590543045682, + "nauc_precision_at_20_diff1": -0.07464783769634727, + "nauc_precision_at_20_max": -0.09929761181534297, + "nauc_precision_at_20_std": 0.19077471001882637, + "nauc_precision_at_3_diff1": 0.012283392353854292, + "nauc_precision_at_3_max": -0.014429631947530549, + "nauc_precision_at_3_std": 0.09168780628289194, + "nauc_precision_at_5_diff1": -0.007591917878106942, + "nauc_precision_at_5_max": -0.028830303438963523, + "nauc_precision_at_5_std": 0.12753759911868462, + "nauc_recall_at_1000_diff1": -0.2564181431029171, + "nauc_recall_at_1000_max": -0.28657575771939875, + "nauc_recall_at_1000_std": 0.4267834783636542, + "nauc_recall_at_100_diff1": -0.15231398971409685, + "nauc_recall_at_100_max": -0.20234094647398881, + "nauc_recall_at_100_std": 0.3606022520318543, + "nauc_recall_at_10_diff1": -0.034836350519293624, + "nauc_recall_at_10_max": -0.05713377245150803, + "nauc_recall_at_10_std": 0.15630376773097054, + "nauc_recall_at_1_diff1": 0.05249140003740938, + "nauc_recall_at_1_max": -0.05675447589815147, + "nauc_recall_at_1_std": 0.05826590543045682, + "nauc_recall_at_20_diff1": -0.07464783769634734, + "nauc_recall_at_20_max": -0.09929761181534325, + "nauc_recall_at_20_std": 0.19077471001882623, + "nauc_recall_at_3_diff1": 0.012283392353854257, + "nauc_recall_at_3_max": -0.01442963194753048, + "nauc_recall_at_3_std": 0.0916878062828919, + "nauc_recall_at_5_diff1": -0.007591917878107139, + "nauc_recall_at_5_max": -0.028830303438963697, + "nauc_recall_at_5_std": 0.12753759911868454, + "ndcg_at_1": 0.06967, + "ndcg_at_10": 0.16722, + "ndcg_at_100": 0.22188, + "ndcg_at_1000": 0.24921, + "ndcg_at_20": 0.18528, + "ndcg_at_3": 0.1237, + "ndcg_at_5": 0.14272, + "precision_at_1": 0.06967, + "precision_at_10": 0.02852, + "precision_at_100": 0.00556, + "precision_at_1000": 0.00078, + "precision_at_20": 0.01782, + "precision_at_3": 0.05447, + "precision_at_5": 0.04191, + "recall_at_1": 0.06967, + "recall_at_10": 0.28516, + "recall_at_100": 0.55568, + "recall_at_1000": 0.77858, + "recall_at_20": 0.35631, + "recall_at_3": 0.16342, + "recall_at_5": 0.20956 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL2Pure.json b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL2Pure.json new file mode 100644 index 000000000..3c2e5bba4 --- /dev/null +++ b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL2Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 8.4010488986969, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01101, + "map_at_1": 0.00389, + "map_at_10": 0.00788, + "map_at_100": 0.01039, + "map_at_1000": 0.01148, + "map_at_20": 0.00879, + "map_at_3": 0.00571, + "map_at_5": 0.00671, + "mrr_at_1": 0.0038910505836575876, + "mrr_at_10": 0.007883274364652911, + "mrr_at_100": 0.01038554868344234, + "mrr_at_1000": 0.01147626192062602, + "mrr_at_20": 0.008793579786903401, + "mrr_at_3": 0.005713050460132171, + "mrr_at_5": 0.006713606324501265, + "nauc_map_at_1000_diff1": -0.028810479442770726, + "nauc_map_at_1000_max": -0.09820067563472686, + "nauc_map_at_1000_std": 0.30946719474062157, + "nauc_map_at_100_diff1": -0.023127173867327457, + "nauc_map_at_100_max": -0.0958562111513254, + "nauc_map_at_100_std": 0.3157868816184268, + "nauc_map_at_10_diff1": -0.022414398031078416, + "nauc_map_at_10_max": -0.10686504821352079, + "nauc_map_at_10_std": 0.3406795609469651, + "nauc_map_at_1_diff1": 0.004825977125735202, + "nauc_map_at_1_max": -0.17911679546379342, + "nauc_map_at_1_std": 0.3935503223206968, + "nauc_map_at_20_diff1": -0.02046307627201428, + "nauc_map_at_20_max": -0.10085912351728968, + "nauc_map_at_20_std": 0.3322877420229669, + "nauc_map_at_3_diff1": -0.01963375860312318, + "nauc_map_at_3_max": -0.13510207041537123, + "nauc_map_at_3_std": 0.35719571063861655, + "nauc_map_at_5_diff1": -0.03503295595772687, + "nauc_map_at_5_max": -0.12848155589630525, + "nauc_map_at_5_std": 0.3469106845810941, + "nauc_mrr_at_1000_diff1": -0.02881049872350125, + "nauc_mrr_at_1000_max": -0.09820066371027932, + "nauc_mrr_at_1000_std": 0.30946713046753066, + "nauc_mrr_at_100_diff1": -0.023127173867327457, + "nauc_mrr_at_100_max": -0.0958562111513254, + "nauc_mrr_at_100_std": 0.3157868816184268, + "nauc_mrr_at_10_diff1": -0.022414398031078416, + "nauc_mrr_at_10_max": -0.10686504821352079, + "nauc_mrr_at_10_std": 0.3406795609469651, + "nauc_mrr_at_1_diff1": 0.004825977125735202, + "nauc_mrr_at_1_max": -0.17911679546379342, + "nauc_mrr_at_1_std": 0.3935503223206968, + "nauc_mrr_at_20_diff1": -0.02046307627201428, + "nauc_mrr_at_20_max": -0.10085912351728968, + "nauc_mrr_at_20_std": 0.3322877420229669, + "nauc_mrr_at_3_diff1": -0.01963375860312318, + "nauc_mrr_at_3_max": -0.13510207041537123, + "nauc_mrr_at_3_std": 0.35719571063861655, + "nauc_mrr_at_5_diff1": -0.03503295595772687, + "nauc_mrr_at_5_max": -0.12848155589630525, + "nauc_mrr_at_5_std": 0.3469106845810941, + "nauc_ndcg_at_1000_diff1": -0.07811744423996074, + "nauc_ndcg_at_1000_max": -0.09738436254573139, + "nauc_ndcg_at_1000_std": 0.22593409205808782, + "nauc_ndcg_at_100_diff1": -0.029843588490075196, + "nauc_ndcg_at_100_max": -0.07146526802386048, + "nauc_ndcg_at_100_std": 0.2771188995631173, + "nauc_ndcg_at_10_diff1": -0.018627631545629075, + "nauc_ndcg_at_10_max": -0.07872674083974605, + "nauc_ndcg_at_10_std": 0.3288582129790009, + "nauc_ndcg_at_1_diff1": 0.004825977125735202, + "nauc_ndcg_at_1_max": -0.17911679546379342, + "nauc_ndcg_at_1_std": 0.3935503223206968, + "nauc_ndcg_at_20_diff1": -0.016873184637039972, + "nauc_ndcg_at_20_max": -0.07478390399909685, + "nauc_ndcg_at_20_std": 0.31195130526159026, + "nauc_ndcg_at_3_diff1": -0.024688009822301477, + "nauc_ndcg_at_3_max": -0.12600807564520403, + "nauc_ndcg_at_3_std": 0.3455968175330955, + "nauc_ndcg_at_5_diff1": -0.0463818979549875, + "nauc_ndcg_at_5_max": -0.11755140076570712, + "nauc_ndcg_at_5_std": 0.3305814502605601, + "nauc_precision_at_1000_diff1": -0.11065717993196837, + "nauc_precision_at_1000_max": -0.10696935041119454, + "nauc_precision_at_1000_std": 0.18189295673216566, + "nauc_precision_at_100_diff1": -0.03549679530837609, + "nauc_precision_at_100_max": -0.062459561612957445, + "nauc_precision_at_100_std": 0.25877965401618813, + "nauc_precision_at_10_diff1": -0.010115174710713064, + "nauc_precision_at_10_max": -0.04094905092554761, + "nauc_precision_at_10_std": 0.3170175828701519, + "nauc_precision_at_1_diff1": 0.004825977125735202, + "nauc_precision_at_1_max": -0.17911679546379342, + "nauc_precision_at_1_std": 0.3935503223206968, + "nauc_precision_at_20_diff1": -0.011988488638693054, + "nauc_precision_at_20_max": -0.05193037752246059, + "nauc_precision_at_20_std": 0.29362140334757064, + "nauc_precision_at_3_diff1": -0.034968724770355356, + "nauc_precision_at_3_max": -0.1075104611657106, + "nauc_precision_at_3_std": 0.3210636646918373, + "nauc_precision_at_5_diff1": -0.06537910552978424, + "nauc_precision_at_5_max": -0.09978978109093775, + "nauc_precision_at_5_std": 0.3026729243568893, + "nauc_recall_at_1000_diff1": -0.11065717993196794, + "nauc_recall_at_1000_max": -0.10696935041119401, + "nauc_recall_at_1000_std": 0.1818929567321658, + "nauc_recall_at_100_diff1": -0.03549679530837626, + "nauc_recall_at_100_max": -0.062459561612957536, + "nauc_recall_at_100_std": 0.25877965401618824, + "nauc_recall_at_10_diff1": -0.010115174710713076, + "nauc_recall_at_10_max": -0.04094905092554777, + "nauc_recall_at_10_std": 0.31701758287015175, + "nauc_recall_at_1_diff1": 0.004825977125735202, + "nauc_recall_at_1_max": -0.17911679546379342, + "nauc_recall_at_1_std": 0.3935503223206968, + "nauc_recall_at_20_diff1": -0.011988488638693229, + "nauc_recall_at_20_max": -0.05193037752246057, + "nauc_recall_at_20_std": 0.2936214033475704, + "nauc_recall_at_3_diff1": -0.03496872477035522, + "nauc_recall_at_3_max": -0.10751046116571036, + "nauc_recall_at_3_std": 0.32106366469183767, + "nauc_recall_at_5_diff1": -0.06537910552978454, + "nauc_recall_at_5_max": -0.09978978109093795, + "nauc_recall_at_5_std": 0.302672924356889, + "ndcg_at_1": 0.00389, + "ndcg_at_10": 0.01101, + "ndcg_at_100": 0.02766, + "ndcg_at_1000": 0.06643, + "ndcg_at_20": 0.01449, + "ndcg_at_3": 0.00634, + "ndcg_at_5": 0.00815, + "precision_at_1": 0.00389, + "precision_at_10": 0.00215, + "precision_at_100": 0.0011, + "precision_at_1000": 0.00044, + "precision_at_20": 0.00178, + "precision_at_3": 0.00272, + "precision_at_5": 0.00252, + "recall_at_1": 0.00389, + "recall_at_10": 0.02149, + "recall_at_100": 0.11006, + "recall_at_1000": 0.43709, + "recall_at_20": 0.03558, + "recall_at_3": 0.00815, + "recall_at_5": 0.0126 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL3Fact.json b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL3Fact.json new file mode 100644 index 000000000..73844103e --- /dev/null +++ b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL3Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 12.536754608154297, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.12814, + "map_at_1": 0.02892, + "map_at_10": 0.09076, + "map_at_100": 0.10122, + "map_at_1000": 0.10213, + "map_at_20": 0.09633, + "map_at_3": 0.06925, + "map_at_5": 0.0805, + "mrr_at_1": 0.028920018075011298, + "mrr_at_10": 0.09076219883946943, + "mrr_at_100": 0.10121915673565332, + "mrr_at_1000": 0.10212718576457647, + "mrr_at_20": 0.09632668051373838, + "mrr_at_3": 0.06924988703117939, + "mrr_at_5": 0.08050158156348827, + "nauc_map_at_1000_diff1": -0.04568766319559932, + "nauc_map_at_1000_max": 0.06909638502514297, + "nauc_map_at_1000_std": 0.21713415628541263, + "nauc_map_at_100_diff1": -0.04520045008404081, + "nauc_map_at_100_max": 0.0695652751720877, + "nauc_map_at_100_std": 0.21755830168725732, + "nauc_map_at_10_diff1": -0.04191161158058715, + "nauc_map_at_10_max": 0.07482031922142397, + "nauc_map_at_10_std": 0.19217047548540697, + "nauc_map_at_1_diff1": -0.21647050599904238, + "nauc_map_at_1_max": 0.0018736245693242533, + "nauc_map_at_1_std": 0.14920734763861399, + "nauc_map_at_20_diff1": -0.04240618973210107, + "nauc_map_at_20_max": 0.07369492786826777, + "nauc_map_at_20_std": 0.2058558986925295, + "nauc_map_at_3_diff1": -0.05301424273765744, + "nauc_map_at_3_max": 0.07330888524106406, + "nauc_map_at_3_std": 0.15741424888885844, + "nauc_map_at_5_diff1": -0.042756542077091085, + "nauc_map_at_5_max": 0.07507636838502467, + "nauc_map_at_5_std": 0.17467577129750309, + "nauc_mrr_at_1000_diff1": -0.04568766319559932, + "nauc_mrr_at_1000_max": 0.06909638502514297, + "nauc_mrr_at_1000_std": 0.21713415628541263, + "nauc_mrr_at_100_diff1": -0.04520045008404081, + "nauc_mrr_at_100_max": 0.0695652751720877, + "nauc_mrr_at_100_std": 0.21755830168725732, + "nauc_mrr_at_10_diff1": -0.04191161158058715, + "nauc_mrr_at_10_max": 0.07482031922142397, + "nauc_mrr_at_10_std": 0.19217047548540697, + "nauc_mrr_at_1_diff1": -0.21647050599904238, + "nauc_mrr_at_1_max": 0.0018736245693242533, + "nauc_mrr_at_1_std": 0.14920734763861399, + "nauc_mrr_at_20_diff1": -0.04240618973210107, + "nauc_mrr_at_20_max": 0.07369492786826777, + "nauc_mrr_at_20_std": 0.2058558986925295, + "nauc_mrr_at_3_diff1": -0.05301424273765744, + "nauc_mrr_at_3_max": 0.07330888524106406, + "nauc_mrr_at_3_std": 0.15741424888885844, + "nauc_mrr_at_5_diff1": -0.042756542077091085, + "nauc_mrr_at_5_max": 0.07507636838502467, + "nauc_mrr_at_5_std": 0.17467577129750309, + "nauc_ndcg_at_1000_diff1": -0.04847351745835046, + "nauc_ndcg_at_1000_max": 0.05031076480447946, + "nauc_ndcg_at_1000_std": 0.3066677050400783, + "nauc_ndcg_at_100_diff1": -0.0420321478608393, + "nauc_ndcg_at_100_max": 0.05740012163834685, + "nauc_ndcg_at_100_std": 0.31487522592675604, + "nauc_ndcg_at_10_diff1": -0.022408704343513497, + "nauc_ndcg_at_10_max": 0.08144756304104127, + "nauc_ndcg_at_10_std": 0.21753387475171784, + "nauc_ndcg_at_1_diff1": -0.21647050599904238, + "nauc_ndcg_at_1_max": 0.0018736245693242533, + "nauc_ndcg_at_1_std": 0.14920734763861399, + "nauc_ndcg_at_20_diff1": -0.024784310923259407, + "nauc_ndcg_at_20_max": 0.07772998735846719, + "nauc_ndcg_at_20_std": 0.25319789876798604, + "nauc_ndcg_at_3_diff1": -0.033701882995112564, + "nauc_ndcg_at_3_max": 0.08282366593245344, + "nauc_ndcg_at_3_std": 0.1606138708174599, + "nauc_ndcg_at_5_diff1": -0.021706665032681823, + "nauc_ndcg_at_5_max": 0.08293046834697426, + "nauc_ndcg_at_5_std": 0.18442983195349447, + "nauc_precision_at_1000_diff1": -0.10162049430651895, + "nauc_precision_at_1000_max": -0.0372279154944061, + "nauc_precision_at_1000_std": 0.5680520692764486, + "nauc_precision_at_100_diff1": -0.05846498498783109, + "nauc_precision_at_100_max": 0.02166704085218074, + "nauc_precision_at_100_std": 0.5151292487597681, + "nauc_precision_at_10_diff1": 0.002633732083922679, + "nauc_precision_at_10_max": 0.08915704632609085, + "nauc_precision_at_10_std": 0.25829790373379485, + "nauc_precision_at_1_diff1": -0.21647050599904238, + "nauc_precision_at_1_max": 0.0018736245693242533, + "nauc_precision_at_1_std": 0.14920734763861399, + "nauc_precision_at_20_diff1": -0.004977806690539815, + "nauc_precision_at_20_max": 0.08005459518120583, + "nauc_precision_at_20_std": 0.33064755938655827, + "nauc_precision_at_3_diff1": -0.001508477426829554, + "nauc_precision_at_3_max": 0.0989115069902709, + "nauc_precision_at_3_std": 0.1664182947598158, + "nauc_precision_at_5_diff1": 0.009585575594776073, + "nauc_precision_at_5_max": 0.09399388501851103, + "nauc_precision_at_5_std": 0.20039741732460223, + "nauc_recall_at_1000_diff1": -0.10162049430651852, + "nauc_recall_at_1000_max": -0.03722791549440625, + "nauc_recall_at_1000_std": 0.5680520692764479, + "nauc_recall_at_100_diff1": -0.05846498498783118, + "nauc_recall_at_100_max": 0.021667040852180797, + "nauc_recall_at_100_std": 0.5151292487597683, + "nauc_recall_at_10_diff1": 0.002633732083922731, + "nauc_recall_at_10_max": 0.08915704632609088, + "nauc_recall_at_10_std": 0.25829790373379474, + "nauc_recall_at_1_diff1": -0.21647050599904238, + "nauc_recall_at_1_max": 0.0018736245693242533, + "nauc_recall_at_1_std": 0.14920734763861399, + "nauc_recall_at_20_diff1": -0.004977806690540095, + "nauc_recall_at_20_max": 0.08005459518120553, + "nauc_recall_at_20_std": 0.3306475593865584, + "nauc_recall_at_3_diff1": -0.001508477426829635, + "nauc_recall_at_3_max": 0.09891150699027096, + "nauc_recall_at_3_std": 0.1664182947598159, + "nauc_recall_at_5_diff1": 0.009585575594775849, + "nauc_recall_at_5_max": 0.09399388501851065, + "nauc_recall_at_5_std": 0.200397417324602, + "ndcg_at_1": 0.02892, + "ndcg_at_10": 0.12814, + "ndcg_at_100": 0.18448, + "ndcg_at_1000": 0.21284, + "ndcg_at_20": 0.1485, + "ndcg_at_3": 0.08309, + "ndcg_at_5": 0.10342, + "precision_at_1": 0.02892, + "precision_at_10": 0.0249, + "precision_at_100": 0.00525, + "precision_at_1000": 0.00076, + "precision_at_20": 0.01648, + "precision_at_3": 0.04112, + "precision_at_5": 0.03457, + "recall_at_1": 0.02892, + "recall_at_10": 0.24898, + "recall_at_100": 0.52485, + "recall_at_1000": 0.75757, + "recall_at_20": 0.32964, + "recall_at_3": 0.12336, + "recall_at_5": 0.17284 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL3Pure.json b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL3Pure.json new file mode 100644 index 000000000..99c425ef2 --- /dev/null +++ b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL3Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 7.056488037109375, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.04626, + "map_at_1": 0.00136, + "map_at_10": 0.02836, + "map_at_100": 0.03611, + "map_at_1000": 0.03715, + "map_at_20": 0.03209, + "map_at_3": 0.01777, + "map_at_5": 0.0227, + "mrr_at_1": 0.0013556258472661546, + "mrr_at_10": 0.028363332831249678, + "mrr_at_100": 0.036111022214722864, + "mrr_at_1000": 0.03715469964234754, + "mrr_at_20": 0.03208904553313091, + "mrr_at_3": 0.017773761108600687, + "mrr_at_5": 0.02269920168700105, + "nauc_map_at_1000_diff1": -0.06515356499909437, + "nauc_map_at_1000_max": 0.11161908558113329, + "nauc_map_at_1000_std": 0.3778509786333467, + "nauc_map_at_100_diff1": -0.065594213498428, + "nauc_map_at_100_max": 0.11066951932683462, + "nauc_map_at_100_std": 0.3779511339176355, + "nauc_map_at_10_diff1": -0.06511869049442168, + "nauc_map_at_10_max": 0.12385293313304041, + "nauc_map_at_10_std": 0.3236806198830003, + "nauc_map_at_1_diff1": -0.47828856808576137, + "nauc_map_at_1_max": -0.08761628422696081, + "nauc_map_at_1_std": 0.11555320426665448, + "nauc_map_at_20_diff1": -0.06522377366075253, + "nauc_map_at_20_max": 0.11795021721659313, + "nauc_map_at_20_std": 0.35199099279728185, + "nauc_map_at_3_diff1": -0.07089966150497336, + "nauc_map_at_3_max": 0.12017300503067348, + "nauc_map_at_3_std": 0.2692487553784929, + "nauc_map_at_5_diff1": -0.07640971677297119, + "nauc_map_at_5_max": 0.13058929681233467, + "nauc_map_at_5_std": 0.29473427770799754, + "nauc_mrr_at_1000_diff1": -0.06515356499909437, + "nauc_mrr_at_1000_max": 0.11161908558113329, + "nauc_mrr_at_1000_std": 0.3778509786333467, + "nauc_mrr_at_100_diff1": -0.065594213498428, + "nauc_mrr_at_100_max": 0.11066951932683462, + "nauc_mrr_at_100_std": 0.3779511339176355, + "nauc_mrr_at_10_diff1": -0.06511869049442168, + "nauc_mrr_at_10_max": 0.12385293313304041, + "nauc_mrr_at_10_std": 0.3236806198830003, + "nauc_mrr_at_1_diff1": -0.47828856808576137, + "nauc_mrr_at_1_max": -0.08761628422696081, + "nauc_mrr_at_1_std": 0.11555320426665448, + "nauc_mrr_at_20_diff1": -0.06522377366075253, + "nauc_mrr_at_20_max": 0.11795021721659313, + "nauc_mrr_at_20_std": 0.35199099279728185, + "nauc_mrr_at_3_diff1": -0.07089966150497336, + "nauc_mrr_at_3_max": 0.12017300503067348, + "nauc_mrr_at_3_std": 0.2692487553784929, + "nauc_mrr_at_5_diff1": -0.07640971677297119, + "nauc_mrr_at_5_max": 0.13058929681233467, + "nauc_mrr_at_5_std": 0.29473427770799754, + "nauc_ndcg_at_1000_diff1": -0.05235578149829765, + "nauc_ndcg_at_1000_max": 0.1094871389279945, + "nauc_ndcg_at_1000_std": 0.4834862244487283, + "nauc_ndcg_at_100_diff1": -0.06125234878929293, + "nauc_ndcg_at_100_max": 0.09098178073276825, + "nauc_ndcg_at_100_std": 0.4877815961197076, + "nauc_ndcg_at_10_diff1": -0.0572034043903275, + "nauc_ndcg_at_10_max": 0.12501556257918345, + "nauc_ndcg_at_10_std": 0.3494018329744066, + "nauc_ndcg_at_1_diff1": -0.47828856808576137, + "nauc_ndcg_at_1_max": -0.08761628422696081, + "nauc_ndcg_at_1_std": 0.11555320426665448, + "nauc_ndcg_at_20_diff1": -0.05966646205565801, + "nauc_ndcg_at_20_max": 0.11286656150716269, + "nauc_ndcg_at_20_std": 0.40301029655940085, + "nauc_ndcg_at_3_diff1": -0.062042149399002725, + "nauc_ndcg_at_3_max": 0.1263996218963238, + "nauc_ndcg_at_3_std": 0.27934624146229453, + "nauc_ndcg_at_5_diff1": -0.07143935216147394, + "nauc_ndcg_at_5_max": 0.13786101100696865, + "nauc_ndcg_at_5_std": 0.30960387550210067, + "nauc_precision_at_1000_diff1": -0.0321636675798244, + "nauc_precision_at_1000_max": 0.12545806285727498, + "nauc_precision_at_1000_std": 0.5906746699027895, + "nauc_precision_at_100_diff1": -0.05974389327350332, + "nauc_precision_at_100_max": 0.0709036867566476, + "nauc_precision_at_100_std": 0.5901993733302335, + "nauc_precision_at_10_diff1": -0.05009615125288167, + "nauc_precision_at_10_max": 0.1247210623715924, + "nauc_precision_at_10_std": 0.37619396432880764, + "nauc_precision_at_1_diff1": -0.47828856808576137, + "nauc_precision_at_1_max": -0.08761628422696081, + "nauc_precision_at_1_std": 0.11555320426665448, + "nauc_precision_at_20_diff1": -0.056552859501466435, + "nauc_precision_at_20_max": 0.1059463432712056, + "nauc_precision_at_20_std": 0.4528029751620227, + "nauc_precision_at_3_diff1": -0.050654234090007695, + "nauc_precision_at_3_max": 0.13466598974292257, + "nauc_precision_at_3_std": 0.2933599790526501, + "nauc_precision_at_5_diff1": -0.06659003450574166, + "nauc_precision_at_5_max": 0.14634274724685434, + "nauc_precision_at_5_std": 0.3278783842017949, + "nauc_recall_at_1000_diff1": -0.03216366757982496, + "nauc_recall_at_1000_max": 0.12545806285727487, + "nauc_recall_at_1000_std": 0.5906746699027893, + "nauc_recall_at_100_diff1": -0.059743893273503615, + "nauc_recall_at_100_max": 0.07090368675664725, + "nauc_recall_at_100_std": 0.5901993733302335, + "nauc_recall_at_10_diff1": -0.05009615125288182, + "nauc_recall_at_10_max": 0.12472106237159239, + "nauc_recall_at_10_std": 0.3761939643288077, + "nauc_recall_at_1_diff1": -0.47828856808576137, + "nauc_recall_at_1_max": -0.08761628422696081, + "nauc_recall_at_1_std": 0.11555320426665448, + "nauc_recall_at_20_diff1": -0.0565528595014666, + "nauc_recall_at_20_max": 0.10594634327120546, + "nauc_recall_at_20_std": 0.45280297516202256, + "nauc_recall_at_3_diff1": -0.05065423409000769, + "nauc_recall_at_3_max": 0.13466598974292243, + "nauc_recall_at_3_std": 0.29335997905265015, + "nauc_recall_at_5_diff1": -0.06659003450574187, + "nauc_recall_at_5_max": 0.1463427472468541, + "nauc_recall_at_5_std": 0.32787838420179494, + "ndcg_at_1": 0.00136, + "ndcg_at_10": 0.04626, + "ndcg_at_100": 0.09072, + "ndcg_at_1000": 0.12558, + "ndcg_at_20": 0.06003, + "ndcg_at_3": 0.02362, + "ndcg_at_5": 0.03257, + "precision_at_1": 0.00136, + "precision_at_10": 0.01048, + "precision_at_100": 0.00328, + "precision_at_1000": 0.00062, + "precision_at_20": 0.00799, + "precision_at_3": 0.01356, + "precision_at_5": 0.01252, + "recall_at_1": 0.00136, + "recall_at_10": 0.10484, + "recall_at_100": 0.32829, + "recall_at_1000": 0.61839, + "recall_at_20": 0.15974, + "recall_at_3": 0.04067, + "recall_at_5": 0.06258 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/WinoGrande.json b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/WinoGrande.json new file mode 100644 index 000000000..5106cc768 --- /dev/null +++ b/results/bge-small-en-v1.5-instruct/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/WinoGrande.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 2.0574240684509277, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.05346, + "map_at_1": 0.00552, + "map_at_10": 0.03293, + "map_at_100": 0.04342, + "map_at_1000": 0.04536, + "map_at_20": 0.03748, + "map_at_3": 0.01881, + "map_at_5": 0.02591, + "mrr_at_1": 0.0055248618784530384, + "mrr_at_10": 0.033106575963718854, + "mrr_at_100": 0.043520930512428134, + "mrr_at_1000": 0.045461821196136815, + "mrr_at_20": 0.03758641774144872, + "mrr_at_3": 0.019073927913706913, + "mrr_at_5": 0.025980005261773204, + "nauc_map_at_1000_diff1": -0.19956370641739596, + "nauc_map_at_1000_max": 0.005513170769771311, + "nauc_map_at_1000_std": -0.1413983857015843, + "nauc_map_at_100_diff1": -0.19744867450178513, + "nauc_map_at_100_max": 0.0060623123020502245, + "nauc_map_at_100_std": -0.14249414013579315, + "nauc_map_at_10_diff1": -0.22805770140527606, + "nauc_map_at_10_max": 0.012000383576417906, + "nauc_map_at_10_std": -0.15161238296947174, + "nauc_map_at_1_diff1": -0.2335103461642707, + "nauc_map_at_1_max": 0.023281960178675763, + "nauc_map_at_1_std": -0.37130021863437823, + "nauc_map_at_20_diff1": -0.2141479648276059, + "nauc_map_at_20_max": 0.004685284915928075, + "nauc_map_at_20_std": -0.14260732568178877, + "nauc_map_at_3_diff1": -0.2812324492004562, + "nauc_map_at_3_max": -0.04552723046037303, + "nauc_map_at_3_std": -0.15794997204944805, + "nauc_map_at_5_diff1": -0.26121852675772056, + "nauc_map_at_5_max": 0.0076996675831766505, + "nauc_map_at_5_std": -0.16211221248945343, + "nauc_mrr_at_1000_diff1": -0.1996643700809418, + "nauc_mrr_at_1000_max": 0.00542468306010573, + "nauc_mrr_at_1000_std": -0.1413758992763313, + "nauc_mrr_at_100_diff1": -0.1975547568411178, + "nauc_mrr_at_100_max": 0.0059735226108934975, + "nauc_mrr_at_100_std": -0.14246735806952546, + "nauc_mrr_at_10_diff1": -0.2290815760990376, + "nauc_mrr_at_10_max": 0.011205722952053018, + "nauc_mrr_at_10_std": -0.1497655121419894, + "nauc_mrr_at_1_diff1": -0.2335103461642707, + "nauc_mrr_at_1_max": 0.023281960178675763, + "nauc_mrr_at_1_std": -0.37130021863437823, + "nauc_mrr_at_20_diff1": -0.21421945552977859, + "nauc_mrr_at_20_max": 0.004574632977491483, + "nauc_mrr_at_20_std": -0.14256925552248312, + "nauc_mrr_at_3_diff1": -0.27832531697801544, + "nauc_mrr_at_3_max": -0.0435402112581078, + "nauc_mrr_at_3_std": -0.15674328778771088, + "nauc_mrr_at_5_diff1": -0.26073560735598844, + "nauc_mrr_at_5_max": 0.007929621998672023, + "nauc_mrr_at_5_std": -0.16188019514915997, + "nauc_ndcg_at_1000_diff1": -0.1483809336939553, + "nauc_ndcg_at_1000_max": 0.012133758863273317, + "nauc_ndcg_at_1000_std": -0.10045867133819596, + "nauc_ndcg_at_100_diff1": -0.13005699268019283, + "nauc_ndcg_at_100_max": 0.01601705572501616, + "nauc_ndcg_at_100_std": -0.12352895535838225, + "nauc_ndcg_at_10_diff1": -0.20940681515255782, + "nauc_ndcg_at_10_max": 0.02274710095248597, + "nauc_ndcg_at_10_std": -0.1392255354402627, + "nauc_ndcg_at_1_diff1": -0.2335103461642707, + "nauc_ndcg_at_1_max": 0.023281960178675763, + "nauc_ndcg_at_1_std": -0.37130021863437823, + "nauc_ndcg_at_20_diff1": -0.18458325795994704, + "nauc_ndcg_at_20_max": 0.004402214477302281, + "nauc_ndcg_at_20_std": -0.12460301938666966, + "nauc_ndcg_at_3_diff1": -0.28636045370921437, + "nauc_ndcg_at_3_max": -0.05392296192576933, + "nauc_ndcg_at_3_std": -0.14192808372126367, + "nauc_ndcg_at_5_diff1": -0.25912605762447916, + "nauc_ndcg_at_5_max": 0.01823280343124151, + "nauc_ndcg_at_5_std": -0.15227497187586844, + "nauc_precision_at_1000_diff1": 0.02820722999026055, + "nauc_precision_at_1000_max": 0.049894538285731475, + "nauc_precision_at_1000_std": 0.17473406551103887, + "nauc_precision_at_100_diff1": -0.061458566973878435, + "nauc_precision_at_100_max": 0.02893788359967453, + "nauc_precision_at_100_std": -0.1086840658567768, + "nauc_precision_at_10_diff1": -0.18803327194090988, + "nauc_precision_at_10_max": 0.03457857822179372, + "nauc_precision_at_10_std": -0.12785747293724078, + "nauc_precision_at_1_diff1": -0.2335103461642707, + "nauc_precision_at_1_max": 0.023281960178675763, + "nauc_precision_at_1_std": -0.37130021863437823, + "nauc_precision_at_20_diff1": -0.15562076316134962, + "nauc_precision_at_20_max": 0.0015325673405364158, + "nauc_precision_at_20_std": -0.10957334381413311, + "nauc_precision_at_3_diff1": -0.2939921994517307, + "nauc_precision_at_3_max": -0.06655331496209609, + "nauc_precision_at_3_std": -0.11901673765386542, + "nauc_precision_at_5_diff1": -0.2558082034400187, + "nauc_precision_at_5_max": 0.03312036929159322, + "nauc_precision_at_5_std": -0.1418435362166448, + "nauc_recall_at_1000_diff1": 0.02820722999026004, + "nauc_recall_at_1000_max": 0.049894538285730476, + "nauc_recall_at_1000_std": 0.1747340655110385, + "nauc_recall_at_100_diff1": -0.061458566973879136, + "nauc_recall_at_100_max": 0.028937883599673878, + "nauc_recall_at_100_std": -0.10868406585677723, + "nauc_recall_at_10_diff1": -0.1880332719409099, + "nauc_recall_at_10_max": 0.03457857822179362, + "nauc_recall_at_10_std": -0.12785747293724092, + "nauc_recall_at_1_diff1": -0.2335103461642707, + "nauc_recall_at_1_max": 0.023281960178675763, + "nauc_recall_at_1_std": -0.37130021863437823, + "nauc_recall_at_20_diff1": -0.1556207631613498, + "nauc_recall_at_20_max": 0.0015325673405362072, + "nauc_recall_at_20_std": -0.10957334381413329, + "nauc_recall_at_3_diff1": -0.29399219945173066, + "nauc_recall_at_3_max": -0.06655331496209607, + "nauc_recall_at_3_std": -0.11901673765386546, + "nauc_recall_at_5_diff1": -0.25580820344001887, + "nauc_recall_at_5_max": 0.03312036929159304, + "nauc_recall_at_5_std": -0.14184353621664494, + "ndcg_at_1": 0.00552, + "ndcg_at_10": 0.05346, + "ndcg_at_100": 0.11721, + "ndcg_at_1000": 0.17628, + "ndcg_at_20": 0.07004, + "ndcg_at_3": 0.02367, + "ndcg_at_5": 0.03641, + "precision_at_1": 0.00552, + "precision_at_10": 0.01215, + "precision_at_100": 0.0045, + "precision_at_1000": 0.00093, + "precision_at_20": 0.00935, + "precision_at_3": 0.01263, + "precision_at_5": 0.01373, + "recall_at_1": 0.00552, + "recall_at_10": 0.12155, + "recall_at_100": 0.44988, + "recall_at_1000": 0.92976, + "recall_at_20": 0.18706, + "recall_at_3": 0.03788, + "recall_at_5": 0.06867 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/ARCChallenge.json b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/ARCChallenge.json new file mode 100644 index 000000000..9d8604620 --- /dev/null +++ b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/ARCChallenge.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 2.6208300590515137, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.08952, + "map_at_1": 0.02901, + "map_at_10": 0.0663, + "map_at_100": 0.07337, + "map_at_1000": 0.0746, + "map_at_20": 0.06985, + "map_at_3": 0.05191, + "map_at_5": 0.05993, + "mrr_at_1": 0.02901023890784983, + "mrr_at_10": 0.06630268432742836, + "mrr_at_100": 0.0733654897218601, + "mrr_at_1000": 0.07460287554423754, + "mrr_at_20": 0.06984751911004572, + "mrr_at_3": 0.05190557451649605, + "mrr_at_5": 0.05992605233219569, + "nauc_map_at_1000_diff1": -0.06503053774942563, + "nauc_map_at_1000_max": -0.014102939504188868, + "nauc_map_at_1000_std": -0.08799269051631438, + "nauc_map_at_100_diff1": -0.06511061392882153, + "nauc_map_at_100_max": -0.014151661626723905, + "nauc_map_at_100_std": -0.08854440074454631, + "nauc_map_at_10_diff1": -0.06795476265375595, + "nauc_map_at_10_max": -0.014123757032830076, + "nauc_map_at_10_std": -0.09929290547923486, + "nauc_map_at_1_diff1": -0.11368232124882452, + "nauc_map_at_1_max": -0.002031275888372802, + "nauc_map_at_1_std": -0.029165883501388455, + "nauc_map_at_20_diff1": -0.06632111660871812, + "nauc_map_at_20_max": -0.011198834214146332, + "nauc_map_at_20_std": -0.091728144305986, + "nauc_map_at_3_diff1": -0.0820452879107508, + "nauc_map_at_3_max": 0.00018005649426598372, + "nauc_map_at_3_std": -0.09710954140868844, + "nauc_map_at_5_diff1": -0.07777660749243681, + "nauc_map_at_5_max": -0.018022503007171477, + "nauc_map_at_5_std": -0.10086393928265128, + "nauc_mrr_at_1000_diff1": -0.06502944924154873, + "nauc_mrr_at_1000_max": -0.014101096034597065, + "nauc_mrr_at_1000_std": -0.08799306422363294, + "nauc_mrr_at_100_diff1": -0.06510955666408359, + "nauc_mrr_at_100_max": -0.014150076790991827, + "nauc_mrr_at_100_std": -0.08854489058468588, + "nauc_mrr_at_10_diff1": -0.06795476265375595, + "nauc_mrr_at_10_max": -0.014123757032830076, + "nauc_mrr_at_10_std": -0.09929290547923486, + "nauc_mrr_at_1_diff1": -0.11368232124882452, + "nauc_mrr_at_1_max": -0.002031275888372802, + "nauc_mrr_at_1_std": -0.029165883501388455, + "nauc_mrr_at_20_diff1": -0.06632111660871812, + "nauc_mrr_at_20_max": -0.011198834214146332, + "nauc_mrr_at_20_std": -0.091728144305986, + "nauc_mrr_at_3_diff1": -0.0820452879107508, + "nauc_mrr_at_3_max": 0.00018005649426598372, + "nauc_mrr_at_3_std": -0.09710954140868844, + "nauc_mrr_at_5_diff1": -0.07777660749243681, + "nauc_mrr_at_5_max": -0.018022503007171477, + "nauc_mrr_at_5_std": -0.10086393928265128, + "nauc_ndcg_at_1000_diff1": -0.040836895576635515, + "nauc_ndcg_at_1000_max": -0.017682798705369412, + "nauc_ndcg_at_1000_std": -0.053153431801339746, + "nauc_ndcg_at_100_diff1": -0.04395391173053841, + "nauc_ndcg_at_100_max": -0.020797735452195674, + "nauc_ndcg_at_100_std": -0.06958695127328453, + "nauc_ndcg_at_10_diff1": -0.051499792587319404, + "nauc_ndcg_at_10_max": -0.016558365324646242, + "nauc_ndcg_at_10_std": -0.10778985309406151, + "nauc_ndcg_at_1_diff1": -0.11368232124882452, + "nauc_ndcg_at_1_max": -0.002031275888372802, + "nauc_ndcg_at_1_std": -0.029165883501388455, + "nauc_ndcg_at_20_diff1": -0.04903043434001842, + "nauc_ndcg_at_20_max": -0.00880071641240972, + "nauc_ndcg_at_20_std": -0.0881459975441001, + "nauc_ndcg_at_3_diff1": -0.07337057838367071, + "nauc_ndcg_at_3_max": 0.003092340539053967, + "nauc_ndcg_at_3_std": -0.10647474443001477, + "nauc_ndcg_at_5_diff1": -0.06940979225458557, + "nauc_ndcg_at_5_max": -0.024301177343036297, + "nauc_ndcg_at_5_std": -0.11073717074437997, + "nauc_precision_at_1000_diff1": 0.008040953722439856, + "nauc_precision_at_1000_max": -0.01669301092867407, + "nauc_precision_at_1000_std": 0.07033821401010996, + "nauc_precision_at_100_diff1": -0.017155402488586276, + "nauc_precision_at_100_max": -0.03176202837791754, + "nauc_precision_at_100_std": -0.03024275395628948, + "nauc_precision_at_10_diff1": -0.026383755787465393, + "nauc_precision_at_10_max": -0.019750580805585467, + "nauc_precision_at_10_std": -0.11892193698445241, + "nauc_precision_at_1_diff1": -0.11368232124882452, + "nauc_precision_at_1_max": -0.002031275888372802, + "nauc_precision_at_1_std": -0.029165883501388455, + "nauc_precision_at_20_diff1": -0.02604366472051104, + "nauc_precision_at_20_max": -0.003474577354524507, + "nauc_precision_at_20_std": -0.07781507762246076, + "nauc_precision_at_3_diff1": -0.056831370186340546, + "nauc_precision_at_3_max": 0.00893850695611105, + "nauc_precision_at_3_std": -0.12315083995702913, + "nauc_precision_at_5_diff1": -0.05618855129971433, + "nauc_precision_at_5_max": -0.035520699882177, + "nauc_precision_at_5_std": -0.12596714235221598, + "nauc_recall_at_1000_diff1": 0.00804095372243947, + "nauc_recall_at_1000_max": -0.0166930109286745, + "nauc_recall_at_1000_std": 0.07033821401010991, + "nauc_recall_at_100_diff1": -0.017155402488586678, + "nauc_recall_at_100_max": -0.03176202837791784, + "nauc_recall_at_100_std": -0.030242753956289843, + "nauc_recall_at_10_diff1": -0.0263837557874656, + "nauc_recall_at_10_max": -0.019750580805585657, + "nauc_recall_at_10_std": -0.11892193698445265, + "nauc_recall_at_1_diff1": -0.11368232124882452, + "nauc_recall_at_1_max": -0.002031275888372802, + "nauc_recall_at_1_std": -0.029165883501388455, + "nauc_recall_at_20_diff1": -0.02604366472051123, + "nauc_recall_at_20_max": -0.0034745773545247806, + "nauc_recall_at_20_std": -0.0778150776224609, + "nauc_recall_at_3_diff1": -0.05683137018634059, + "nauc_recall_at_3_max": 0.008938506956111049, + "nauc_recall_at_3_std": -0.12315083995702915, + "nauc_recall_at_5_diff1": -0.05618855129971457, + "nauc_recall_at_5_max": -0.03552069988217719, + "nauc_recall_at_5_std": -0.12596714235221615, + "ndcg_at_1": 0.02901, + "ndcg_at_10": 0.08952, + "ndcg_at_100": 0.13036, + "ndcg_at_1000": 0.17037, + "ndcg_at_20": 0.10258, + "ndcg_at_3": 0.0598, + "ndcg_at_5": 0.07423, + "precision_at_1": 0.02901, + "precision_at_10": 0.01647, + "precision_at_100": 0.00371, + "precision_at_1000": 0.0007, + "precision_at_20": 0.01084, + "precision_at_3": 0.02759, + "precision_at_5": 0.02355, + "recall_at_1": 0.02901, + "recall_at_10": 0.16468, + "recall_at_100": 0.37116, + "recall_at_1000": 0.70051, + "recall_at_20": 0.21672, + "recall_at_3": 0.08276, + "recall_at_5": 0.11775 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/AlphaNLI.json b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/AlphaNLI.json new file mode 100644 index 000000000..6310b5961 --- /dev/null +++ b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/AlphaNLI.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 25.156047105789185, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.11635, + "map_at_1": 0.06854, + "map_at_10": 0.0983, + "map_at_100": 0.10432, + "map_at_1000": 0.10527, + "map_at_20": 0.10159, + "map_at_3": 0.08736, + "map_at_5": 0.09343, + "mrr_at_1": 0.0685378590078329, + "mrr_at_10": 0.09830287206266311, + "mrr_at_100": 0.10432334539722314, + "mrr_at_1000": 0.10527129104622361, + "mrr_at_20": 0.10158940266619872, + "mrr_at_3": 0.08735857267188858, + "mrr_at_5": 0.0934290687554395, + "nauc_map_at_1000_diff1": 0.24683142017331275, + "nauc_map_at_1000_max": 0.09368735719674443, + "nauc_map_at_1000_std": -0.0380172317860986, + "nauc_map_at_100_diff1": 0.2469142870009923, + "nauc_map_at_100_max": 0.0935159769207791, + "nauc_map_at_100_std": -0.03820038810566689, + "nauc_map_at_10_diff1": 0.25014057728875705, + "nauc_map_at_10_max": 0.0971872186922582, + "nauc_map_at_10_std": -0.04308741250938237, + "nauc_map_at_1_diff1": 0.3391083471658043, + "nauc_map_at_1_max": 0.1253047660426719, + "nauc_map_at_1_std": -0.07017753885705297, + "nauc_map_at_20_diff1": 0.24789372622343114, + "nauc_map_at_20_max": 0.09374910117556036, + "nauc_map_at_20_std": -0.04174537174121096, + "nauc_map_at_3_diff1": 0.2713285988509424, + "nauc_map_at_3_max": 0.11802370902953137, + "nauc_map_at_3_std": -0.046327475344058844, + "nauc_map_at_5_diff1": 0.25136560930638147, + "nauc_map_at_5_max": 0.10744562205204944, + "nauc_map_at_5_std": -0.043050460204879924, + "nauc_mrr_at_1000_diff1": 0.24683142017331275, + "nauc_mrr_at_1000_max": 0.09368735719674443, + "nauc_mrr_at_1000_std": -0.0380172317860986, + "nauc_mrr_at_100_diff1": 0.2469142870009923, + "nauc_mrr_at_100_max": 0.0935159769207791, + "nauc_mrr_at_100_std": -0.03820038810566689, + "nauc_mrr_at_10_diff1": 0.25014057728875705, + "nauc_mrr_at_10_max": 0.0971872186922582, + "nauc_mrr_at_10_std": -0.04308741250938237, + "nauc_mrr_at_1_diff1": 0.3391083471658043, + "nauc_mrr_at_1_max": 0.1253047660426719, + "nauc_mrr_at_1_std": -0.07017753885705297, + "nauc_mrr_at_20_diff1": 0.24789372622343114, + "nauc_mrr_at_20_max": 0.09374910117556036, + "nauc_mrr_at_20_std": -0.04174537174121096, + "nauc_mrr_at_3_diff1": 0.2713285988509424, + "nauc_mrr_at_3_max": 0.11802370902953137, + "nauc_mrr_at_3_std": -0.046327475344058844, + "nauc_mrr_at_5_diff1": 0.25136560930638147, + "nauc_mrr_at_5_max": 0.10744562205204944, + "nauc_mrr_at_5_std": -0.043050460204879924, + "nauc_ndcg_at_1000_diff1": 0.20772308307151405, + "nauc_ndcg_at_1000_max": 0.07482681674547899, + "nauc_ndcg_at_1000_std": -0.005553170980714802, + "nauc_ndcg_at_100_diff1": 0.21139296739157065, + "nauc_ndcg_at_100_max": 0.06603507154637482, + "nauc_ndcg_at_100_std": -0.015757630583936342, + "nauc_ndcg_at_10_diff1": 0.22295344185712793, + "nauc_ndcg_at_10_max": 0.07757819951209477, + "nauc_ndcg_at_10_std": -0.03645428355181664, + "nauc_ndcg_at_1_diff1": 0.3391083471658043, + "nauc_ndcg_at_1_max": 0.1253047660426719, + "nauc_ndcg_at_1_std": -0.07017753885705297, + "nauc_ndcg_at_20_diff1": 0.2180067137190887, + "nauc_ndcg_at_20_max": 0.06697416903175916, + "nauc_ndcg_at_20_std": -0.03413456631587837, + "nauc_ndcg_at_3_diff1": 0.2558488309115895, + "nauc_ndcg_at_3_max": 0.11563673470516861, + "nauc_ndcg_at_3_std": -0.04022366472132845, + "nauc_ndcg_at_5_diff1": 0.22363977319243364, + "nauc_ndcg_at_5_max": 0.09886400990091682, + "nauc_ndcg_at_5_std": -0.035308396276166124, + "nauc_precision_at_1000_diff1": 0.12169973047241457, + "nauc_precision_at_1000_max": 0.06104247193372876, + "nauc_precision_at_1000_std": 0.0962261415173858, + "nauc_precision_at_100_diff1": 0.14984040861513492, + "nauc_precision_at_100_max": 0.01620091223683802, + "nauc_precision_at_100_std": 0.031233491794505443, + "nauc_precision_at_10_diff1": 0.1706885662336254, + "nauc_precision_at_10_max": 0.03525638693525411, + "nauc_precision_at_10_std": -0.024636818034059527, + "nauc_precision_at_1_diff1": 0.3391083471658043, + "nauc_precision_at_1_max": 0.1253047660426719, + "nauc_precision_at_1_std": -0.07017753885705297, + "nauc_precision_at_20_diff1": 0.16569780765022127, + "nauc_precision_at_20_max": 0.012287019871269757, + "nauc_precision_at_20_std": -0.022133708456538084, + "nauc_precision_at_3_diff1": 0.22013761198747892, + "nauc_precision_at_3_max": 0.10992820212554107, + "nauc_precision_at_3_std": -0.02595928505261012, + "nauc_precision_at_5_diff1": 0.16237290550439204, + "nauc_precision_at_5_max": 0.07932170193252526, + "nauc_precision_at_5_std": -0.018584351541722107, + "nauc_recall_at_1000_diff1": 0.12169973047241489, + "nauc_recall_at_1000_max": 0.06104247193372925, + "nauc_recall_at_1000_std": 0.09622614151738659, + "nauc_recall_at_100_diff1": 0.14984040861513476, + "nauc_recall_at_100_max": 0.01620091223683782, + "nauc_recall_at_100_std": 0.031233491794505193, + "nauc_recall_at_10_diff1": 0.1706885662336253, + "nauc_recall_at_10_max": 0.035256386935253896, + "nauc_recall_at_10_std": -0.024636818034059472, + "nauc_recall_at_1_diff1": 0.3391083471658043, + "nauc_recall_at_1_max": 0.1253047660426719, + "nauc_recall_at_1_std": -0.07017753885705297, + "nauc_recall_at_20_diff1": 0.1656978076502213, + "nauc_recall_at_20_max": 0.012287019871269783, + "nauc_recall_at_20_std": -0.022133708456538323, + "nauc_recall_at_3_diff1": 0.22013761198747897, + "nauc_recall_at_3_max": 0.10992820212554105, + "nauc_recall_at_3_std": -0.025959285052610036, + "nauc_recall_at_5_diff1": 0.16237290550439204, + "nauc_recall_at_5_max": 0.07932170193252534, + "nauc_recall_at_5_std": -0.018584351541722218, + "ndcg_at_1": 0.06854, + "ndcg_at_10": 0.11635, + "ndcg_at_100": 0.14969, + "ndcg_at_1000": 0.1808, + "ndcg_at_20": 0.12837, + "ndcg_at_3": 0.09343, + "ndcg_at_5": 0.10441, + "precision_at_1": 0.06854, + "precision_at_10": 0.01749, + "precision_at_100": 0.00341, + "precision_at_1000": 0.0006, + "precision_at_20": 0.01113, + "precision_at_3": 0.03699, + "precision_at_5": 0.02755, + "recall_at_1": 0.06854, + "recall_at_10": 0.17493, + "recall_at_100": 0.34073, + "recall_at_1000": 0.59856, + "recall_at_20": 0.22258, + "recall_at_3": 0.11097, + "recall_at_5": 0.13773 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/HellaSwag.json b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/HellaSwag.json new file mode 100644 index 000000000..7b60a1c8a --- /dev/null +++ b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/HellaSwag.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 72.53871369361877, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.25445, + "map_at_1": 0.13414, + "map_at_10": 0.21205, + "map_at_100": 0.22036, + "map_at_1000": 0.22122, + "map_at_20": 0.2164, + "map_at_3": 0.19002, + "map_at_5": 0.20278, + "mrr_at_1": 0.13413662617008565, + "mrr_at_10": 0.2120474167227796, + "mrr_at_100": 0.2203630291015804, + "mrr_at_1000": 0.22121637183938705, + "mrr_at_20": 0.2164016760503186, + "mrr_at_3": 0.1900185885945681, + "mrr_at_5": 0.20277501161787084, + "nauc_map_at_1000_diff1": 0.16920408511742122, + "nauc_map_at_1000_max": 0.11942090794018957, + "nauc_map_at_1000_std": -0.22228210232795945, + "nauc_map_at_100_diff1": 0.16918329096267173, + "nauc_map_at_100_max": 0.11940451708891518, + "nauc_map_at_100_std": -0.222458448866135, + "nauc_map_at_10_diff1": 0.17049711218442903, + "nauc_map_at_10_max": 0.11961521112326622, + "nauc_map_at_10_std": -0.22239308337772526, + "nauc_map_at_1_diff1": 0.20731200684899442, + "nauc_map_at_1_max": 0.11056825825023103, + "nauc_map_at_1_std": -0.1993969795992301, + "nauc_map_at_20_diff1": 0.16988589452107616, + "nauc_map_at_20_max": 0.11967685596319587, + "nauc_map_at_20_std": -0.2229002661234134, + "nauc_map_at_3_diff1": 0.1771045843690053, + "nauc_map_at_3_max": 0.11694365398820145, + "nauc_map_at_3_std": -0.21647331785727414, + "nauc_map_at_5_diff1": 0.17358566885563328, + "nauc_map_at_5_max": 0.11758564894829045, + "nauc_map_at_5_std": -0.220689970387812, + "nauc_mrr_at_1000_diff1": 0.16920408511742122, + "nauc_mrr_at_1000_max": 0.11942090794018957, + "nauc_mrr_at_1000_std": -0.22228210232795945, + "nauc_mrr_at_100_diff1": 0.16918329096267173, + "nauc_mrr_at_100_max": 0.11940451708891518, + "nauc_mrr_at_100_std": -0.222458448866135, + "nauc_mrr_at_10_diff1": 0.17049711218442903, + "nauc_mrr_at_10_max": 0.11961521112326622, + "nauc_mrr_at_10_std": -0.22239308337772526, + "nauc_mrr_at_1_diff1": 0.20731200684899442, + "nauc_mrr_at_1_max": 0.11056825825023103, + "nauc_mrr_at_1_std": -0.1993969795992301, + "nauc_mrr_at_20_diff1": 0.16988589452107616, + "nauc_mrr_at_20_max": 0.11967685596319587, + "nauc_mrr_at_20_std": -0.2229002661234134, + "nauc_mrr_at_3_diff1": 0.1771045843690053, + "nauc_mrr_at_3_max": 0.11694365398820145, + "nauc_mrr_at_3_std": -0.21647331785727414, + "nauc_mrr_at_5_diff1": 0.17358566885563328, + "nauc_mrr_at_5_max": 0.11758564894829045, + "nauc_mrr_at_5_std": -0.220689970387812, + "nauc_ndcg_at_1000_diff1": 0.15002710073172612, + "nauc_ndcg_at_1000_max": 0.12302340764181141, + "nauc_ndcg_at_1000_std": -0.2275505421813381, + "nauc_ndcg_at_100_diff1": 0.1496523363371206, + "nauc_ndcg_at_100_max": 0.12286971890023622, + "nauc_ndcg_at_100_std": -0.23061765853904154, + "nauc_ndcg_at_10_diff1": 0.15742162456172687, + "nauc_ndcg_at_10_max": 0.12430894693735832, + "nauc_ndcg_at_10_std": -0.23257909717724837, + "nauc_ndcg_at_1_diff1": 0.20731200684899442, + "nauc_ndcg_at_1_max": 0.11056825825023103, + "nauc_ndcg_at_1_std": -0.1993969795992301, + "nauc_ndcg_at_20_diff1": 0.15564686229588046, + "nauc_ndcg_at_20_max": 0.12455909768668483, + "nauc_ndcg_at_20_std": -0.23431146083013984, + "nauc_ndcg_at_3_diff1": 0.1700294904702389, + "nauc_ndcg_at_3_max": 0.1193455575696362, + "nauc_ndcg_at_3_std": -0.2218783177472549, + "nauc_ndcg_at_5_diff1": 0.1642310396328197, + "nauc_ndcg_at_5_max": 0.12018835244931579, + "nauc_ndcg_at_5_std": -0.22894823111670287, + "nauc_precision_at_1000_diff1": 0.037987543829532906, + "nauc_precision_at_1000_max": 0.13731567515219448, + "nauc_precision_at_1000_std": -0.2271576159121804, + "nauc_precision_at_100_diff1": 0.08365570852320388, + "nauc_precision_at_100_max": 0.13029793860974825, + "nauc_precision_at_100_std": -0.24729714456114213, + "nauc_precision_at_10_diff1": 0.12619928322231352, + "nauc_precision_at_10_max": 0.13569162726259376, + "nauc_precision_at_10_std": -0.2569947617615736, + "nauc_precision_at_1_diff1": 0.20731200684899442, + "nauc_precision_at_1_max": 0.11056825825023103, + "nauc_precision_at_1_std": -0.1993969795992301, + "nauc_precision_at_20_diff1": 0.1205934946473436, + "nauc_precision_at_20_max": 0.13667048558028624, + "nauc_precision_at_20_std": -0.2629344320438703, + "nauc_precision_at_3_diff1": 0.1534895831665981, + "nauc_precision_at_3_max": 0.1252143726143716, + "nauc_precision_at_3_std": -0.23490637411673096, + "nauc_precision_at_5_diff1": 0.14265831002418106, + "nauc_precision_at_5_max": 0.12622391566536648, + "nauc_precision_at_5_std": -0.2486251629686647, + "nauc_recall_at_1000_diff1": 0.037987543829533676, + "nauc_recall_at_1000_max": 0.1373156751521956, + "nauc_recall_at_1000_std": -0.22715761591217942, + "nauc_recall_at_100_diff1": 0.0836557085232039, + "nauc_recall_at_100_max": 0.13029793860974812, + "nauc_recall_at_100_std": -0.247297144561142, + "nauc_recall_at_10_diff1": 0.1261992832223136, + "nauc_recall_at_10_max": 0.13569162726259407, + "nauc_recall_at_10_std": -0.25699476176157326, + "nauc_recall_at_1_diff1": 0.20731200684899442, + "nauc_recall_at_1_max": 0.11056825825023103, + "nauc_recall_at_1_std": -0.1993969795992301, + "nauc_recall_at_20_diff1": 0.1205934946473439, + "nauc_recall_at_20_max": 0.13667048558028635, + "nauc_recall_at_20_std": -0.2629344320438698, + "nauc_recall_at_3_diff1": 0.15348958316659803, + "nauc_recall_at_3_max": 0.12521437261437163, + "nauc_recall_at_3_std": -0.2349063741167311, + "nauc_recall_at_5_diff1": 0.1426583100241812, + "nauc_recall_at_5_max": 0.12622391566536645, + "nauc_recall_at_5_std": -0.24862516296866452, + "ndcg_at_1": 0.13414, + "ndcg_at_10": 0.25445, + "ndcg_at_100": 0.29986, + "ndcg_at_1000": 0.32538, + "ndcg_at_20": 0.27036, + "ndcg_at_3": 0.20882, + "ndcg_at_5": 0.23192, + "precision_at_1": 0.13414, + "precision_at_10": 0.03896, + "precision_at_100": 0.00613, + "precision_at_1000": 0.00082, + "precision_at_20": 0.02263, + "precision_at_3": 0.0878, + "precision_at_5": 0.06395, + "recall_at_1": 0.13414, + "recall_at_10": 0.38956, + "recall_at_100": 0.61342, + "recall_at_1000": 0.82045, + "recall_at_20": 0.4526, + "recall_at_3": 0.26339, + "recall_at_5": 0.31976 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/PIQA.json b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/PIQA.json new file mode 100644 index 000000000..baf03061b --- /dev/null +++ b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/PIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 8.162226915359497, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.2392, + "map_at_1": 0.13003, + "map_at_10": 0.20132, + "map_at_100": 0.20941, + "map_at_1000": 0.21023, + "map_at_20": 0.20593, + "map_at_3": 0.18063, + "map_at_5": 0.19241, + "mrr_at_1": 0.13003264417845484, + "mrr_at_10": 0.20132174378637913, + "mrr_at_100": 0.2094141490621967, + "mrr_at_1000": 0.21023405749769658, + "mrr_at_20": 0.20593227294480826, + "mrr_at_3": 0.18063112078346022, + "mrr_at_5": 0.19241022850924902, + "nauc_map_at_1000_diff1": 0.0029169806803219004, + "nauc_map_at_1000_max": 0.1483770230948205, + "nauc_map_at_1000_std": -0.008187236391101721, + "nauc_map_at_100_diff1": 0.0029685697238530724, + "nauc_map_at_100_max": 0.14863837926556142, + "nauc_map_at_100_std": -0.008256664254698625, + "nauc_map_at_10_diff1": 0.004715043234417298, + "nauc_map_at_10_max": 0.15052540932077252, + "nauc_map_at_10_std": -0.008761817363222414, + "nauc_map_at_1_diff1": 0.05864639162341699, + "nauc_map_at_1_max": 0.15659474011469066, + "nauc_map_at_1_std": -0.010500241680339745, + "nauc_map_at_20_diff1": 0.003474751844909473, + "nauc_map_at_20_max": 0.1492798668322656, + "nauc_map_at_20_std": -0.008765489294084848, + "nauc_map_at_3_diff1": 0.019124851328028297, + "nauc_map_at_3_max": 0.1631783488017669, + "nauc_map_at_3_std": -0.006077575729019004, + "nauc_map_at_5_diff1": 0.00863702620166129, + "nauc_map_at_5_max": 0.1562634865241866, + "nauc_map_at_5_std": -0.007363215274688428, + "nauc_mrr_at_1000_diff1": 0.0029169219004663376, + "nauc_mrr_at_1000_max": 0.14837697089058277, + "nauc_mrr_at_1000_std": -0.008187307672721564, + "nauc_mrr_at_100_diff1": 0.0029685697238530724, + "nauc_mrr_at_100_max": 0.14863837926556142, + "nauc_mrr_at_100_std": -0.008256664254698625, + "nauc_mrr_at_10_diff1": 0.004715043234417298, + "nauc_mrr_at_10_max": 0.15052540932077252, + "nauc_mrr_at_10_std": -0.008761817363222414, + "nauc_mrr_at_1_diff1": 0.05864639162341699, + "nauc_mrr_at_1_max": 0.15659474011469066, + "nauc_mrr_at_1_std": -0.010500241680339745, + "nauc_mrr_at_20_diff1": 0.003474751844909473, + "nauc_mrr_at_20_max": 0.1492798668322656, + "nauc_mrr_at_20_std": -0.008765489294084848, + "nauc_mrr_at_3_diff1": 0.019124851328028297, + "nauc_mrr_at_3_max": 0.1631783488017669, + "nauc_mrr_at_3_std": -0.006077575729019004, + "nauc_mrr_at_5_diff1": 0.00863702620166129, + "nauc_mrr_at_5_max": 0.1562634865241866, + "nauc_mrr_at_5_std": -0.007363215274688428, + "nauc_ndcg_at_1000_diff1": -0.029125249061922202, + "nauc_ndcg_at_1000_max": 0.1226077317259181, + "nauc_ndcg_at_1000_std": -0.008360826825029482, + "nauc_ndcg_at_100_diff1": -0.026648317121868575, + "nauc_ndcg_at_100_max": 0.12957501770538107, + "nauc_ndcg_at_100_std": -0.007141771707810686, + "nauc_ndcg_at_10_diff1": -0.016424090232807075, + "nauc_ndcg_at_10_max": 0.14011601963783551, + "nauc_ndcg_at_10_std": -0.00807726394254869, + "nauc_ndcg_at_1_diff1": 0.05864639162341699, + "nauc_ndcg_at_1_max": 0.15659474011469066, + "nauc_ndcg_at_1_std": -0.010500241680339745, + "nauc_ndcg_at_20_diff1": -0.020187084783902746, + "nauc_ndcg_at_20_max": 0.1365166238594867, + "nauc_ndcg_at_20_std": -0.0075145349822168354, + "nauc_ndcg_at_3_diff1": 0.00823697151265602, + "nauc_ndcg_at_3_max": 0.163171077963184, + "nauc_ndcg_at_3_std": -0.0034155148513863955, + "nauc_ndcg_at_5_diff1": -0.007848001433699436, + "nauc_ndcg_at_5_max": 0.1520383937943663, + "nauc_ndcg_at_5_std": -0.005402240758016838, + "nauc_precision_at_1000_diff1": -0.19290904366340747, + "nauc_precision_at_1000_max": -0.04221083414862571, + "nauc_precision_at_1000_std": -0.027821699300845878, + "nauc_precision_at_100_diff1": -0.11815861885256766, + "nauc_precision_at_100_max": 0.06247355295616381, + "nauc_precision_at_100_std": -0.007157237376787209, + "nauc_precision_at_10_diff1": -0.06634252525019324, + "nauc_precision_at_10_max": 0.11320721848674635, + "nauc_precision_at_10_std": -0.006753714581039177, + "nauc_precision_at_1_diff1": 0.05864639162341699, + "nauc_precision_at_1_max": 0.15659474011469066, + "nauc_precision_at_1_std": -0.010500241680339745, + "nauc_precision_at_20_diff1": -0.07727650429372479, + "nauc_precision_at_20_max": 0.10286843131951263, + "nauc_precision_at_20_std": -0.004034886814124244, + "nauc_precision_at_3_diff1": -0.01791328277069697, + "nauc_precision_at_3_max": 0.1627162174603348, + "nauc_precision_at_3_std": 0.0033249192802869915, + "nauc_precision_at_5_diff1": -0.04614851794350641, + "nauc_precision_at_5_max": 0.14120909505652626, + "nauc_precision_at_5_std": -0.0007024463416768167, + "nauc_recall_at_1000_diff1": -0.19290904366340733, + "nauc_recall_at_1000_max": -0.04221083414862456, + "nauc_recall_at_1000_std": -0.027821699300845586, + "nauc_recall_at_100_diff1": -0.11815861885256818, + "nauc_recall_at_100_max": 0.062473552956163116, + "nauc_recall_at_100_std": -0.0071572373767879, + "nauc_recall_at_10_diff1": -0.0663425252501934, + "nauc_recall_at_10_max": 0.11320721848674611, + "nauc_recall_at_10_std": -0.006753714581039406, + "nauc_recall_at_1_diff1": 0.05864639162341699, + "nauc_recall_at_1_max": 0.15659474011469066, + "nauc_recall_at_1_std": -0.010500241680339745, + "nauc_recall_at_20_diff1": -0.07727650429372437, + "nauc_recall_at_20_max": 0.10286843131951326, + "nauc_recall_at_20_std": -0.004034886814124017, + "nauc_recall_at_3_diff1": -0.017913282770696856, + "nauc_recall_at_3_max": 0.16271621746033507, + "nauc_recall_at_3_std": 0.0033249192802871975, + "nauc_recall_at_5_diff1": -0.04614851794350621, + "nauc_recall_at_5_max": 0.14120909505652612, + "nauc_recall_at_5_std": -0.0007024463416766974, + "ndcg_at_1": 0.13003, + "ndcg_at_10": 0.2392, + "ndcg_at_100": 0.28229, + "ndcg_at_1000": 0.30664, + "ndcg_at_20": 0.25608, + "ndcg_at_3": 0.19686, + "ndcg_at_5": 0.21789, + "precision_at_1": 0.13003, + "precision_at_10": 0.03596, + "precision_at_100": 0.0057, + "precision_at_1000": 0.00077, + "precision_at_20": 0.02133, + "precision_at_3": 0.08125, + "precision_at_5": 0.05887, + "recall_at_1": 0.13003, + "recall_at_10": 0.35963, + "recall_at_100": 0.57018, + "recall_at_1000": 0.76768, + "recall_at_20": 0.42655, + "recall_at_3": 0.24374, + "recall_at_5": 0.29434 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/Quail.json b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/Quail.json new file mode 100644 index 000000000..877d2134f --- /dev/null +++ b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/Quail.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 14.173505306243896, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01749, + "map_at_1": 0.00625, + "map_at_10": 0.01287, + "map_at_100": 0.01564, + "map_at_1000": 0.01636, + "map_at_20": 0.0142, + "map_at_3": 0.00993, + "map_at_5": 0.01132, + "mrr_at_1": 0.00625, + "mrr_at_10": 0.012883549253034546, + "mrr_at_100": 0.015661545199695627, + "mrr_at_1000": 0.016382330901641873, + "mrr_at_20": 0.014217690948378102, + "mrr_at_3": 0.00992647058823529, + "mrr_at_5": 0.011341911764705876, + "nauc_map_at_1000_diff1": -0.01089050288535258, + "nauc_map_at_1000_max": 0.029070101251190413, + "nauc_map_at_1000_std": 0.1961294319722858, + "nauc_map_at_100_diff1": -0.00966481905384864, + "nauc_map_at_100_max": 0.02654229042380809, + "nauc_map_at_100_std": 0.19640318792780773, + "nauc_map_at_10_diff1": 0.0008791143497383057, + "nauc_map_at_10_max": 0.01968559168768355, + "nauc_map_at_10_std": 0.18778163410278467, + "nauc_map_at_1_diff1": 0.07171830363484259, + "nauc_map_at_1_max": -0.06030713868590104, + "nauc_map_at_1_std": 0.14184251645385815, + "nauc_map_at_20_diff1": -0.005751783537443177, + "nauc_map_at_20_max": 0.02264060500021267, + "nauc_map_at_20_std": 0.19854364592553575, + "nauc_map_at_3_diff1": -0.002712935634856884, + "nauc_map_at_3_max": -0.0026897481507980507, + "nauc_map_at_3_std": 0.1796649077303759, + "nauc_map_at_5_diff1": -0.0007051909721617528, + "nauc_map_at_5_max": 0.013377140255326495, + "nauc_map_at_5_std": 0.18562987187215801, + "nauc_mrr_at_1000_diff1": -0.011100610575689542, + "nauc_mrr_at_1000_max": 0.028466450489151456, + "nauc_mrr_at_1000_std": 0.19568462767591854, + "nauc_mrr_at_100_diff1": -0.00988282248487714, + "nauc_mrr_at_100_max": 0.025926675334769667, + "nauc_mrr_at_100_std": 0.19594728325495364, + "nauc_mrr_at_10_diff1": 0.0005842292620798778, + "nauc_mrr_at_10_max": 0.018944674300724038, + "nauc_mrr_at_10_std": 0.18722007497863064, + "nauc_mrr_at_1_diff1": 0.07171830363484259, + "nauc_mrr_at_1_max": -0.06030713868590104, + "nauc_mrr_at_1_std": 0.14184251645385815, + "nauc_mrr_at_20_diff1": -0.006010424343387268, + "nauc_mrr_at_20_max": 0.02196539228249113, + "nauc_mrr_at_20_std": 0.1980208672435966, + "nauc_mrr_at_3_diff1": -0.002712935634856884, + "nauc_mrr_at_3_max": -0.0026897481507980507, + "nauc_mrr_at_3_std": 0.1796649077303759, + "nauc_mrr_at_5_diff1": -0.0010375902510004335, + "nauc_mrr_at_5_max": 0.012545738842389624, + "nauc_mrr_at_5_std": 0.18499547087071913, + "nauc_ndcg_at_1000_diff1": -0.034268385591887496, + "nauc_ndcg_at_1000_max": 0.07579068246257431, + "nauc_ndcg_at_1000_std": 0.20269981810993506, + "nauc_ndcg_at_100_diff1": -0.031609829835831466, + "nauc_ndcg_at_100_max": 0.04594114704131282, + "nauc_ndcg_at_100_std": 0.2027956281860088, + "nauc_ndcg_at_10_diff1": -0.00660713299934946, + "nauc_ndcg_at_10_max": 0.03852690437399444, + "nauc_ndcg_at_10_std": 0.19645133055669292, + "nauc_ndcg_at_1_diff1": 0.07171830363484259, + "nauc_ndcg_at_1_max": -0.06030713868590104, + "nauc_ndcg_at_1_std": 0.14184251645385815, + "nauc_ndcg_at_20_diff1": -0.022380732461093105, + "nauc_ndcg_at_20_max": 0.03959617885223457, + "nauc_ndcg_at_20_std": 0.21805148953865922, + "nauc_ndcg_at_3_diff1": -0.01505723802675598, + "nauc_ndcg_at_3_max": 0.006507866474920912, + "nauc_ndcg_at_3_std": 0.18405955696585147, + "nauc_ndcg_at_5_diff1": -0.009755801608263358, + "nauc_ndcg_at_5_max": 0.030749367929577706, + "nauc_ndcg_at_5_std": 0.19335576354365286, + "nauc_precision_at_1000_diff1": -0.043148262239710286, + "nauc_precision_at_1000_max": 0.10829139101525644, + "nauc_precision_at_1000_std": 0.20515501762659927, + "nauc_precision_at_100_diff1": -0.04694038743374215, + "nauc_precision_at_100_max": 0.0562367883998156, + "nauc_precision_at_100_std": 0.20274573005647634, + "nauc_precision_at_10_diff1": -0.015070710846751328, + "nauc_precision_at_10_max": 0.06294787807164867, + "nauc_precision_at_10_std": 0.2079330003044897, + "nauc_precision_at_1_diff1": 0.07171830363484259, + "nauc_precision_at_1_max": -0.06030713868590104, + "nauc_precision_at_1_std": 0.14184251645385815, + "nauc_precision_at_20_diff1": -0.040741308597493156, + "nauc_precision_at_20_max": 0.054501897351374326, + "nauc_precision_at_20_std": 0.23955306834298004, + "nauc_precision_at_3_diff1": -0.03829013068773017, + "nauc_precision_at_3_max": 0.02372927941782786, + "nauc_precision_at_3_std": 0.19186293821618125, + "nauc_precision_at_5_diff1": -0.02304710268959968, + "nauc_precision_at_5_max": 0.05991228962926639, + "nauc_precision_at_5_std": 0.20605460618228577, + "nauc_recall_at_1000_diff1": -0.04314826223970975, + "nauc_recall_at_1000_max": 0.10829139101525682, + "nauc_recall_at_1000_std": 0.20515501762659966, + "nauc_recall_at_100_diff1": -0.04694038743374224, + "nauc_recall_at_100_max": 0.05623678839981548, + "nauc_recall_at_100_std": 0.20274573005647606, + "nauc_recall_at_10_diff1": -0.015070710846751465, + "nauc_recall_at_10_max": 0.06294787807164835, + "nauc_recall_at_10_std": 0.20793300030448927, + "nauc_recall_at_1_diff1": 0.07171830363484259, + "nauc_recall_at_1_max": -0.06030713868590104, + "nauc_recall_at_1_std": 0.14184251645385815, + "nauc_recall_at_20_diff1": -0.040741308597493225, + "nauc_recall_at_20_max": 0.054501897351374125, + "nauc_recall_at_20_std": 0.2395530683429798, + "nauc_recall_at_3_diff1": -0.038290130687730246, + "nauc_recall_at_3_max": 0.023729279417827667, + "nauc_recall_at_3_std": 0.19186293821618133, + "nauc_recall_at_5_diff1": -0.023047102689599735, + "nauc_recall_at_5_max": 0.05991228962926632, + "nauc_recall_at_5_std": 0.20605460618228583, + "ndcg_at_1": 0.00625, + "ndcg_at_10": 0.01749, + "ndcg_at_100": 0.0333, + "ndcg_at_1000": 0.05798, + "ndcg_at_20": 0.02227, + "ndcg_at_3": 0.01124, + "ndcg_at_5": 0.01379, + "precision_at_1": 0.00625, + "precision_at_10": 0.00327, + "precision_at_100": 0.00112, + "precision_at_1000": 0.00032, + "precision_at_20": 0.00257, + "precision_at_3": 0.00502, + "precision_at_5": 0.00426, + "recall_at_1": 0.00625, + "recall_at_10": 0.03272, + "recall_at_100": 0.11213, + "recall_at_1000": 0.31912, + "recall_at_20": 0.05147, + "recall_at_3": 0.01507, + "recall_at_5": 0.02132 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/RARbCode.json b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/RARbCode.json new file mode 100644 index 000000000..9e551a60d --- /dev/null +++ b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/RARbCode.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 414.4998710155487, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.42358, + "map_at_1": 0.29111, + "map_at_10": 0.37689, + "map_at_100": 0.38482, + "map_at_1000": 0.38549, + "map_at_20": 0.38146, + "map_at_3": 0.35142, + "map_at_5": 0.36516, + "mrr_at_1": 0.2917789757412399, + "mrr_at_10": 0.3772306721430707, + "mrr_at_100": 0.385153312921134, + "mrr_at_1000": 0.38583044395348126, + "mrr_at_20": 0.38180068752581614, + "mrr_at_3": 0.3517520215633422, + "mrr_at_5": 0.3654986522911049, + "nauc_map_at_1000_diff1": 0.49620984875720014, + "nauc_map_at_1000_max": 0.37888641700239734, + "nauc_map_at_1000_std": 0.2897040914901818, + "nauc_map_at_100_diff1": 0.4959336213229856, + "nauc_map_at_100_max": 0.3787786445540414, + "nauc_map_at_100_std": 0.28991721222997047, + "nauc_map_at_10_diff1": 0.49657690449983843, + "nauc_map_at_10_max": 0.3787029630451453, + "nauc_map_at_10_std": 0.2880166523116251, + "nauc_map_at_1_diff1": 0.5814171948923675, + "nauc_map_at_1_max": 0.3757939010348388, + "nauc_map_at_1_std": 0.24831501407993395, + "nauc_map_at_20_diff1": 0.4946696401468986, + "nauc_map_at_20_max": 0.37846370842441807, + "nauc_map_at_20_std": 0.2890654672047795, + "nauc_map_at_3_diff1": 0.5042683127139559, + "nauc_map_at_3_max": 0.3773742349508392, + "nauc_map_at_3_std": 0.2786320382658328, + "nauc_map_at_5_diff1": 0.5002634011685545, + "nauc_map_at_5_max": 0.3737169470224663, + "nauc_map_at_5_std": 0.28447816532492687, + "nauc_mrr_at_1000_diff1": 0.4949437628662878, + "nauc_mrr_at_1000_max": 0.380401063723026, + "nauc_mrr_at_1000_std": 0.2897120378604137, + "nauc_mrr_at_100_diff1": 0.494673594893828, + "nauc_mrr_at_100_max": 0.38030511098625447, + "nauc_mrr_at_100_std": 0.28992793566056196, + "nauc_mrr_at_10_diff1": 0.4953264311017586, + "nauc_mrr_at_10_max": 0.38019569523100877, + "nauc_mrr_at_10_std": 0.2880253265060112, + "nauc_mrr_at_1_diff1": 0.578792802252991, + "nauc_mrr_at_1_max": 0.3788171534495151, + "nauc_mrr_at_1_std": 0.24837678756070422, + "nauc_mrr_at_20_diff1": 0.4934125941908545, + "nauc_mrr_at_20_max": 0.3799656802341993, + "nauc_mrr_at_20_std": 0.28907361333284187, + "nauc_mrr_at_3_diff1": 0.5030327127910004, + "nauc_mrr_at_3_max": 0.37884495438239074, + "nauc_mrr_at_3_std": 0.2786456687172082, + "nauc_mrr_at_5_diff1": 0.499024000715356, + "nauc_mrr_at_5_max": 0.37519677996017997, + "nauc_mrr_at_5_std": 0.28448867664165534, + "nauc_ndcg_at_1000_diff1": 0.47530006537505703, + "nauc_ndcg_at_1000_max": 0.38915411248648846, + "nauc_ndcg_at_1000_std": 0.31718594726603266, + "nauc_ndcg_at_100_diff1": 0.46715121184639546, + "nauc_ndcg_at_100_max": 0.38692294693897594, + "nauc_ndcg_at_100_std": 0.3212041988477853, + "nauc_ndcg_at_10_diff1": 0.4640997375017232, + "nauc_ndcg_at_10_max": 0.38218758713459167, + "nauc_ndcg_at_10_std": 0.308306523085033, + "nauc_ndcg_at_1_diff1": 0.5814171948923675, + "nauc_ndcg_at_1_max": 0.3757939010348388, + "nauc_ndcg_at_1_std": 0.24831501407993395, + "nauc_ndcg_at_20_diff1": 0.45731330375887436, + "nauc_ndcg_at_20_max": 0.3827605357214266, + "nauc_ndcg_at_20_std": 0.3131275777117845, + "nauc_ndcg_at_3_diff1": 0.4808122043110997, + "nauc_ndcg_at_3_max": 0.3768320859649572, + "nauc_ndcg_at_3_std": 0.2876410578912413, + "nauc_ndcg_at_5_diff1": 0.4735662324698512, + "nauc_ndcg_at_5_max": 0.37004248942024115, + "nauc_ndcg_at_5_std": 0.29850393559482374, + "nauc_precision_at_1000_diff1": 0.4211912784607442, + "nauc_precision_at_1000_max": 0.6070406552810179, + "nauc_precision_at_1000_std": 0.7073834416173209, + "nauc_precision_at_100_diff1": 0.3515277333488929, + "nauc_precision_at_100_max": 0.45105556470925445, + "nauc_precision_at_100_std": 0.5136074748412546, + "nauc_precision_at_10_diff1": 0.3597773131185713, + "nauc_precision_at_10_max": 0.39663212204172077, + "nauc_precision_at_10_std": 0.37739860713159623, + "nauc_precision_at_1_diff1": 0.5814171948923675, + "nauc_precision_at_1_max": 0.3757939010348388, + "nauc_precision_at_1_std": 0.24831501407993395, + "nauc_precision_at_20_diff1": 0.320805775980422, + "nauc_precision_at_20_max": 0.4039472151226507, + "nauc_precision_at_20_std": 0.4072929824654305, + "nauc_precision_at_3_diff1": 0.4149588657605751, + "nauc_precision_at_3_max": 0.3749926022570703, + "nauc_precision_at_3_std": 0.31286929681937187, + "nauc_precision_at_5_diff1": 0.39648670640157746, + "nauc_precision_at_5_max": 0.35810489783547, + "nauc_precision_at_5_std": 0.3402090666364838, + "nauc_recall_at_1000_diff1": 0.42119127846074705, + "nauc_recall_at_1000_max": 0.6070406552810189, + "nauc_recall_at_1000_std": 0.707383441617324, + "nauc_recall_at_100_diff1": 0.3515277333488927, + "nauc_recall_at_100_max": 0.4510555647092542, + "nauc_recall_at_100_std": 0.5136074748412547, + "nauc_recall_at_10_diff1": 0.3597773131185714, + "nauc_recall_at_10_max": 0.39663212204172116, + "nauc_recall_at_10_std": 0.377398607131597, + "nauc_recall_at_1_diff1": 0.5814171948923675, + "nauc_recall_at_1_max": 0.3757939010348388, + "nauc_recall_at_1_std": 0.24831501407993395, + "nauc_recall_at_20_diff1": 0.3208057759804223, + "nauc_recall_at_20_max": 0.4039472151226509, + "nauc_recall_at_20_std": 0.40729298246543083, + "nauc_recall_at_3_diff1": 0.414958865760575, + "nauc_recall_at_3_max": 0.3749926022570704, + "nauc_recall_at_3_std": 0.3128692968193719, + "nauc_recall_at_5_diff1": 0.3964867064015776, + "nauc_recall_at_5_max": 0.35810489783547, + "nauc_recall_at_5_std": 0.3402090666364839, + "ndcg_at_1": 0.29111, + "ndcg_at_10": 0.42358, + "ndcg_at_100": 0.46466, + "ndcg_at_1000": 0.48335, + "ndcg_at_20": 0.44026, + "ndcg_at_3": 0.37074, + "ndcg_at_5": 0.39533, + "precision_at_1": 0.29111, + "precision_at_10": 0.05728, + "precision_at_100": 0.00771, + "precision_at_1000": 0.00092, + "precision_at_20": 0.03194, + "precision_at_3": 0.14218, + "precision_at_5": 0.09717, + "recall_at_1": 0.29111, + "recall_at_10": 0.57278, + "recall_at_100": 0.77089, + "recall_at_1000": 0.91981, + "recall_at_20": 0.63881, + "recall_at_3": 0.42655, + "recall_at_5": 0.48585 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/RARbMath.json b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/RARbMath.json new file mode 100644 index 000000000..05c09963f --- /dev/null +++ b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/RARbMath.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 640.5954542160034, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.44983, + "map_at_1": 0.37015, + "map_at_10": 0.42074, + "map_at_100": 0.42879, + "map_at_1000": 0.42952, + "map_at_20": 0.42509, + "map_at_3": 0.40478, + "map_at_5": 0.41349, + "mrr_at_1": 0.37015350530147173, + "mrr_at_10": 0.4207377850121954, + "mrr_at_100": 0.4287861537503735, + "mrr_at_1000": 0.42952101556931677, + "mrr_at_20": 0.42508901491852297, + "mrr_at_3": 0.4047845123173497, + "mrr_at_5": 0.4134884211636866, + "nauc_map_at_1000_diff1": 0.7227975478835476, + "nauc_map_at_1000_max": 0.23003571333269981, + "nauc_map_at_1000_std": -0.07016562086257944, + "nauc_map_at_100_diff1": 0.7225101783776512, + "nauc_map_at_100_max": 0.2297397538549774, + "nauc_map_at_100_std": -0.07033785371239681, + "nauc_map_at_10_diff1": 0.7251028761818618, + "nauc_map_at_10_max": 0.22945530031382666, + "nauc_map_at_10_std": -0.07295175922556386, + "nauc_map_at_1_diff1": 0.7776349226624967, + "nauc_map_at_1_max": 0.2548343269210406, + "nauc_map_at_1_std": -0.0633326934275761, + "nauc_map_at_20_diff1": 0.7229251471284226, + "nauc_map_at_20_max": 0.2291407692891053, + "nauc_map_at_20_std": -0.07161299902437442, + "nauc_map_at_3_diff1": 0.7369223396051537, + "nauc_map_at_3_max": 0.23441384896786563, + "nauc_map_at_3_std": -0.07364839971213387, + "nauc_map_at_5_diff1": 0.7294588007040945, + "nauc_map_at_5_max": 0.23144733809923154, + "nauc_map_at_5_std": -0.07266974461849861, + "nauc_mrr_at_1000_diff1": 0.7227975853214645, + "nauc_mrr_at_1000_max": 0.23003568330815172, + "nauc_mrr_at_1000_std": -0.07016565351827617, + "nauc_mrr_at_100_diff1": 0.7225102157413289, + "nauc_mrr_at_100_max": 0.22973972386947494, + "nauc_mrr_at_100_std": -0.07033788631980002, + "nauc_mrr_at_10_diff1": 0.7251028761818618, + "nauc_mrr_at_10_max": 0.22945530031382666, + "nauc_mrr_at_10_std": -0.07295175922556386, + "nauc_mrr_at_1_diff1": 0.7776349226624967, + "nauc_mrr_at_1_max": 0.2548343269210406, + "nauc_mrr_at_1_std": -0.0633326934275761, + "nauc_mrr_at_20_diff1": 0.7229251471284226, + "nauc_mrr_at_20_max": 0.2291407692891053, + "nauc_mrr_at_20_std": -0.07161299902437442, + "nauc_mrr_at_3_diff1": 0.7369223396051537, + "nauc_mrr_at_3_max": 0.23441384896786563, + "nauc_mrr_at_3_std": -0.07364839971213387, + "nauc_mrr_at_5_diff1": 0.7294588007040945, + "nauc_mrr_at_5_max": 0.23144733809923154, + "nauc_mrr_at_5_std": -0.07266974461849861, + "nauc_ndcg_at_1000_diff1": 0.6974117860442425, + "nauc_ndcg_at_1000_max": 0.22673944404575236, + "nauc_ndcg_at_1000_std": -0.05695441206867443, + "nauc_ndcg_at_100_diff1": 0.6889548074055989, + "nauc_ndcg_at_100_max": 0.220288552298754, + "nauc_ndcg_at_100_std": -0.06038658121926321, + "nauc_ndcg_at_10_diff1": 0.7000296537702575, + "nauc_ndcg_at_10_max": 0.21713182868290223, + "nauc_ndcg_at_10_std": -0.07575460665119871, + "nauc_ndcg_at_1_diff1": 0.7776349226624967, + "nauc_ndcg_at_1_max": 0.2548343269210406, + "nauc_ndcg_at_1_std": -0.0633326934275761, + "nauc_ndcg_at_20_diff1": 0.6916627063670486, + "nauc_ndcg_at_20_max": 0.21550824433603372, + "nauc_ndcg_at_20_std": -0.07096676213637498, + "nauc_ndcg_at_3_diff1": 0.7242931392969104, + "nauc_ndcg_at_3_max": 0.22748958769082667, + "nauc_ndcg_at_3_std": -0.07727684565255645, + "nauc_ndcg_at_5_diff1": 0.7106835275272843, + "nauc_ndcg_at_5_max": 0.22203297945549136, + "nauc_ndcg_at_5_std": -0.07546178126911636, + "nauc_precision_at_1000_diff1": 0.4579297266640136, + "nauc_precision_at_1000_max": 0.31180004066343386, + "nauc_precision_at_1000_std": 0.2814709079720996, + "nauc_precision_at_100_diff1": 0.5098735467100989, + "nauc_precision_at_100_max": 0.18569365641353483, + "nauc_precision_at_100_std": 0.026363487143647037, + "nauc_precision_at_10_diff1": 0.617187564870094, + "nauc_precision_at_10_max": 0.1765134231590779, + "nauc_precision_at_10_std": -0.08376803160988956, + "nauc_precision_at_1_diff1": 0.7776349226624967, + "nauc_precision_at_1_max": 0.2548343269210406, + "nauc_precision_at_1_std": -0.0633326934275761, + "nauc_precision_at_20_diff1": 0.5746529917140661, + "nauc_precision_at_20_max": 0.1657206282431249, + "nauc_precision_at_20_std": -0.06381506938922449, + "nauc_precision_at_3_diff1": 0.6878224236678768, + "nauc_precision_at_3_max": 0.20730373971205468, + "nauc_precision_at_3_std": -0.08789307661193776, + "nauc_precision_at_5_diff1": 0.6538395091220743, + "nauc_precision_at_5_max": 0.19351932434302277, + "nauc_precision_at_5_std": -0.08342973382945297, + "nauc_recall_at_1000_diff1": 0.4579297266640137, + "nauc_recall_at_1000_max": 0.3118000406634332, + "nauc_recall_at_1000_std": 0.2814709079720994, + "nauc_recall_at_100_diff1": 0.5098735467100987, + "nauc_recall_at_100_max": 0.18569365641353433, + "nauc_recall_at_100_std": 0.026363487143645854, + "nauc_recall_at_10_diff1": 0.6171875648700937, + "nauc_recall_at_10_max": 0.1765134231590783, + "nauc_recall_at_10_std": -0.08376803160988912, + "nauc_recall_at_1_diff1": 0.7776349226624967, + "nauc_recall_at_1_max": 0.2548343269210406, + "nauc_recall_at_1_std": -0.0633326934275761, + "nauc_recall_at_20_diff1": 0.5746529917140663, + "nauc_recall_at_20_max": 0.16572062824312542, + "nauc_recall_at_20_std": -0.06381506938922434, + "nauc_recall_at_3_diff1": 0.6878224236678772, + "nauc_recall_at_3_max": 0.2073037397120549, + "nauc_recall_at_3_std": -0.08789307661193793, + "nauc_recall_at_5_diff1": 0.6538395091220737, + "nauc_recall_at_5_max": 0.19351932434302305, + "nauc_recall_at_5_std": -0.08342973382945268, + "ndcg_at_1": 0.37015, + "ndcg_at_10": 0.44983, + "ndcg_at_100": 0.49321, + "ndcg_at_1000": 0.51417, + "ndcg_at_20": 0.46579, + "ndcg_at_3": 0.41643, + "ndcg_at_5": 0.43213, + "precision_at_1": 0.37015, + "precision_at_10": 0.05434, + "precision_at_100": 0.00756, + "precision_at_1000": 0.00092, + "precision_at_20": 0.03034, + "precision_at_3": 0.15008, + "precision_at_5": 0.09767, + "recall_at_1": 0.37015, + "recall_at_10": 0.54344, + "recall_at_100": 0.75597, + "recall_at_1000": 0.9242, + "recall_at_20": 0.60674, + "recall_at_3": 0.45023, + "recall_at_5": 0.48837 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/SIQA.json b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/SIQA.json new file mode 100644 index 000000000..528008a5a --- /dev/null +++ b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/SIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 7.938632249832153, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.00772, + "map_at_1": 0.00256, + "map_at_10": 0.00532, + "map_at_100": 0.00699, + "map_at_1000": 0.0075, + "map_at_20": 0.00601, + "map_at_3": 0.00375, + "map_at_5": 0.00452, + "mrr_at_1": 0.00255885363357216, + "mrr_at_10": 0.005321400139721532, + "mrr_at_100": 0.006990124930930149, + "mrr_at_1000": 0.007499925217557, + "mrr_at_20": 0.006006741982639639, + "mrr_at_3": 0.0037529853292391675, + "mrr_at_5": 0.004520641419310815, + "nauc_map_at_1000_diff1": -0.08358083286030964, + "nauc_map_at_1000_max": -0.07789341106081035, + "nauc_map_at_1000_std": -0.11011358537637518, + "nauc_map_at_100_diff1": -0.0867517031401266, + "nauc_map_at_100_max": -0.07985974774687116, + "nauc_map_at_100_std": -0.11344634811153781, + "nauc_map_at_10_diff1": -0.1387943671419254, + "nauc_map_at_10_max": -0.1042687241338244, + "nauc_map_at_10_std": -0.1225901580909283, + "nauc_map_at_1_diff1": -0.21221588943007685, + "nauc_map_at_1_max": -0.27976027068573195, + "nauc_map_at_1_std": -0.247508112032633, + "nauc_map_at_20_diff1": -0.12492044476134875, + "nauc_map_at_20_max": -0.08937098464394926, + "nauc_map_at_20_std": -0.12566438322677562, + "nauc_map_at_3_diff1": -0.16382289841494455, + "nauc_map_at_3_max": -0.23894939630350454, + "nauc_map_at_3_std": -0.20538597785256854, + "nauc_map_at_5_diff1": -0.15984675295234127, + "nauc_map_at_5_max": -0.1661587830390632, + "nauc_map_at_5_std": -0.14139216276733368, + "nauc_mrr_at_1000_diff1": -0.08350732181066912, + "nauc_mrr_at_1000_max": -0.07786940464958375, + "nauc_mrr_at_1000_std": -0.11006710808665691, + "nauc_mrr_at_100_diff1": -0.08666897267473937, + "nauc_mrr_at_100_max": -0.0798320623878201, + "nauc_mrr_at_100_std": -0.11339836198252755, + "nauc_mrr_at_10_diff1": -0.1387943671419254, + "nauc_mrr_at_10_max": -0.1042687241338244, + "nauc_mrr_at_10_std": -0.1225901580909283, + "nauc_mrr_at_1_diff1": -0.21221588943007685, + "nauc_mrr_at_1_max": -0.27976027068573195, + "nauc_mrr_at_1_std": -0.247508112032633, + "nauc_mrr_at_20_diff1": -0.12492044476134875, + "nauc_mrr_at_20_max": -0.08937098464394926, + "nauc_mrr_at_20_std": -0.12566438322677562, + "nauc_mrr_at_3_diff1": -0.16382289841494455, + "nauc_mrr_at_3_max": -0.23894939630350454, + "nauc_mrr_at_3_std": -0.20538597785256854, + "nauc_mrr_at_5_diff1": -0.15984675295234127, + "nauc_mrr_at_5_max": -0.1661587830390632, + "nauc_mrr_at_5_std": -0.14139216276733368, + "nauc_ndcg_at_1000_diff1": 0.0013571690657341214, + "nauc_ndcg_at_1000_max": -0.01701976584697287, + "nauc_ndcg_at_1000_std": -0.053465679961292305, + "nauc_ndcg_at_100_diff1": 0.017163203786297865, + "nauc_ndcg_at_100_max": -0.01588275182873795, + "nauc_ndcg_at_100_std": -0.06348044121133228, + "nauc_ndcg_at_10_diff1": -0.10664869947889777, + "nauc_ndcg_at_10_max": -0.025085628905444367, + "nauc_ndcg_at_10_std": -0.08222585562162876, + "nauc_ndcg_at_1_diff1": -0.21221588943007685, + "nauc_ndcg_at_1_max": -0.27976027068573195, + "nauc_ndcg_at_1_std": -0.247508112032633, + "nauc_ndcg_at_20_diff1": -0.08481696302680221, + "nauc_ndcg_at_20_max": -0.009598483702408352, + "nauc_ndcg_at_20_std": -0.09740759261446046, + "nauc_ndcg_at_3_diff1": -0.1463494355902815, + "nauc_ndcg_at_3_max": -0.22950740437235786, + "nauc_ndcg_at_3_std": -0.1927808478433289, + "nauc_ndcg_at_5_diff1": -0.14314510463076466, + "nauc_ndcg_at_5_max": -0.1280317305155644, + "nauc_ndcg_at_5_std": -0.10861564763367293, + "nauc_precision_at_1000_diff1": 0.01810141600970039, + "nauc_precision_at_1000_max": -0.005130925954438545, + "nauc_precision_at_1000_std": -0.03690298245303272, + "nauc_precision_at_100_diff1": 0.07687770985860955, + "nauc_precision_at_100_max": 0.006566300567948056, + "nauc_precision_at_100_std": -0.037941806100489604, + "nauc_precision_at_10_diff1": -0.06731875369369669, + "nauc_precision_at_10_max": 0.07137196306338064, + "nauc_precision_at_10_std": -0.03646779939138254, + "nauc_precision_at_1_diff1": -0.21221588943007685, + "nauc_precision_at_1_max": -0.27976027068573195, + "nauc_precision_at_1_std": -0.247508112032633, + "nauc_precision_at_20_diff1": -0.04810291112046227, + "nauc_precision_at_20_max": 0.06130593330486304, + "nauc_precision_at_20_std": -0.07672884714000452, + "nauc_precision_at_3_diff1": -0.11090374549604792, + "nauc_precision_at_3_max": -0.21101766370526637, + "nauc_precision_at_3_std": -0.1675372981225829, + "nauc_precision_at_5_diff1": -0.11743502815052503, + "nauc_precision_at_5_max": -0.06828344947662973, + "nauc_precision_at_5_std": -0.05871731186915574, + "nauc_recall_at_1000_diff1": 0.01810141600970052, + "nauc_recall_at_1000_max": -0.0051309259544383805, + "nauc_recall_at_1000_std": -0.0369029824530325, + "nauc_recall_at_100_diff1": 0.07687770985860952, + "nauc_recall_at_100_max": 0.006566300567948198, + "nauc_recall_at_100_std": -0.037941806100489486, + "nauc_recall_at_10_diff1": -0.06731875369369655, + "nauc_recall_at_10_max": 0.0713719630633808, + "nauc_recall_at_10_std": -0.036467799391382456, + "nauc_recall_at_1_diff1": -0.21221588943007685, + "nauc_recall_at_1_max": -0.27976027068573195, + "nauc_recall_at_1_std": -0.247508112032633, + "nauc_recall_at_20_diff1": -0.0481029111204623, + "nauc_recall_at_20_max": 0.061305933304862927, + "nauc_recall_at_20_std": -0.07672884714000457, + "nauc_recall_at_3_diff1": -0.11090374549604788, + "nauc_recall_at_3_max": -0.21101766370526637, + "nauc_recall_at_3_std": -0.16753729812258286, + "nauc_recall_at_5_diff1": -0.11743502815052505, + "nauc_recall_at_5_max": -0.06828344947662966, + "nauc_recall_at_5_std": -0.05871731186915582, + "ndcg_at_1": 0.00256, + "ndcg_at_10": 0.00772, + "ndcg_at_100": 0.01819, + "ndcg_at_1000": 0.0372, + "ndcg_at_20": 0.01019, + "ndcg_at_3": 0.00423, + "ndcg_at_5": 0.00566, + "precision_at_1": 0.00256, + "precision_at_10": 0.00159, + "precision_at_100": 0.00071, + "precision_at_1000": 0.00023, + "precision_at_20": 0.00128, + "precision_at_3": 0.00188, + "precision_at_5": 0.00184, + "recall_at_1": 0.00256, + "recall_at_10": 0.01586, + "recall_at_100": 0.07062, + "recall_at_1000": 0.23286, + "recall_at_20": 0.02559, + "recall_at_3": 0.00563, + "recall_at_5": 0.00921 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/SpartQA.json b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/SpartQA.json new file mode 100644 index 000000000..8d39f1612 --- /dev/null +++ b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/SpartQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 7.141481161117554, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.03553, + "map_at_1": 0.00223, + "map_at_10": 0.01839, + "map_at_100": 0.02547, + "map_at_1000": 0.02672, + "map_at_20": 0.02169, + "map_at_3": 0.00812, + "map_at_5": 0.01307, + "mrr_at_1": 0.0027824151363383415, + "mrr_at_10": 0.028058890037187208, + "mrr_at_100": 0.03813320789505707, + "mrr_at_1000": 0.03933549192156555, + "mrr_at_20": 0.03313960742715197, + "mrr_at_3": 0.012474494527916907, + "mrr_at_5": 0.02022352068261919, + "nauc_map_at_1000_diff1": 0.06640614683559147, + "nauc_map_at_1000_max": -0.07757141481645476, + "nauc_map_at_1000_std": 0.17047327337201015, + "nauc_map_at_100_diff1": 0.06425217204376824, + "nauc_map_at_100_max": -0.07451596322497274, + "nauc_map_at_100_std": 0.1641362028150766, + "nauc_map_at_10_diff1": 0.07536976810008054, + "nauc_map_at_10_max": -0.033447891839814156, + "nauc_map_at_10_std": 0.1620514648346186, + "nauc_map_at_1_diff1": -0.1582012861227588, + "nauc_map_at_1_max": -0.17792123036441815, + "nauc_map_at_1_std": 0.2541000750855491, + "nauc_map_at_20_diff1": 0.06928769588926213, + "nauc_map_at_20_max": -0.048816690056603954, + "nauc_map_at_20_std": 0.1664065804070807, + "nauc_map_at_3_diff1": 0.061816395779133594, + "nauc_map_at_3_max": -0.026163647365152053, + "nauc_map_at_3_std": 0.18259220972304838, + "nauc_map_at_5_diff1": 0.08059340979009069, + "nauc_map_at_5_max": -0.030038614824550086, + "nauc_map_at_5_std": 0.15679927281203745, + "nauc_mrr_at_1000_diff1": 0.10120058672272593, + "nauc_mrr_at_1000_max": -0.019119148876136305, + "nauc_mrr_at_1000_std": 0.16133455036824834, + "nauc_mrr_at_100_diff1": 0.09993737252755039, + "nauc_mrr_at_100_max": -0.019202583988421083, + "nauc_mrr_at_100_std": 0.15975885056849234, + "nauc_mrr_at_10_diff1": 0.10417094999848464, + "nauc_mrr_at_10_max": 0.016988158524525888, + "nauc_mrr_at_10_std": 0.15499212392718661, + "nauc_mrr_at_1_diff1": -0.19723165228662198, + "nauc_mrr_at_1_max": -0.13960651741797697, + "nauc_mrr_at_1_std": 0.27180466633868283, + "nauc_mrr_at_20_diff1": 0.10176112507882275, + "nauc_mrr_at_20_max": -1.4641709439268517e-05, + "nauc_mrr_at_20_std": 0.15956193144306416, + "nauc_mrr_at_3_diff1": 0.0936068323744152, + "nauc_mrr_at_3_max": 0.024603587550269597, + "nauc_mrr_at_3_std": 0.19218681931836432, + "nauc_mrr_at_5_diff1": 0.10036259842177943, + "nauc_mrr_at_5_max": 0.017718305616387476, + "nauc_mrr_at_5_std": 0.15531031431694253, + "nauc_ndcg_at_1000_diff1": 0.09649298997571218, + "nauc_ndcg_at_1000_max": -0.14617917660760898, + "nauc_ndcg_at_1000_std": 0.22366511269184694, + "nauc_ndcg_at_100_diff1": 0.06523474392363143, + "nauc_ndcg_at_100_max": -0.12442153846985661, + "nauc_ndcg_at_100_std": 0.16107893065850212, + "nauc_ndcg_at_10_diff1": 0.09277721353548499, + "nauc_ndcg_at_10_max": -0.02028838194494558, + "nauc_ndcg_at_10_std": 0.1552592667657891, + "nauc_ndcg_at_1_diff1": -0.19723165228662198, + "nauc_ndcg_at_1_max": -0.13960651741797697, + "nauc_ndcg_at_1_std": 0.27180466633868283, + "nauc_ndcg_at_20_diff1": 0.07925211801334711, + "nauc_ndcg_at_20_max": -0.05078397030331436, + "nauc_ndcg_at_20_std": 0.1631830617436249, + "nauc_ndcg_at_3_diff1": 0.08982062641663875, + "nauc_ndcg_at_3_max": -0.005147309233396563, + "nauc_ndcg_at_3_std": 0.17351130796545616, + "nauc_ndcg_at_5_diff1": 0.0995788805391717, + "nauc_ndcg_at_5_max": -0.01576233304552963, + "nauc_ndcg_at_5_std": 0.14471322150609164, + "nauc_precision_at_1000_diff1": 0.13388001306101452, + "nauc_precision_at_1000_max": -0.1267644349919296, + "nauc_precision_at_1000_std": 0.24455091564942083, + "nauc_precision_at_100_diff1": 0.0823127809338215, + "nauc_precision_at_100_max": -0.14935808528921068, + "nauc_precision_at_100_std": 0.18430013112998567, + "nauc_precision_at_10_diff1": 0.12327095403979746, + "nauc_precision_at_10_max": 0.010013039665370909, + "nauc_precision_at_10_std": 0.14137704995237418, + "nauc_precision_at_1_diff1": -0.19723165228662198, + "nauc_precision_at_1_max": -0.13960651741797697, + "nauc_precision_at_1_std": 0.27180466633868283, + "nauc_precision_at_20_diff1": 0.10089556397209767, + "nauc_precision_at_20_max": -0.0417577828609778, + "nauc_precision_at_20_std": 0.15969643714386575, + "nauc_precision_at_3_diff1": 0.14005948957801642, + "nauc_precision_at_3_max": 0.04466663922564199, + "nauc_precision_at_3_std": 0.16976424627200393, + "nauc_precision_at_5_diff1": 0.12077785708999017, + "nauc_precision_at_5_max": 0.015718753051032323, + "nauc_precision_at_5_std": 0.12839444199366498, + "nauc_recall_at_1000_diff1": 0.08896278716145872, + "nauc_recall_at_1000_max": -0.20098846441495852, + "nauc_recall_at_1000_std": 0.23934390533663166, + "nauc_recall_at_100_diff1": 0.03813099047987098, + "nauc_recall_at_100_max": -0.17188787940318567, + "nauc_recall_at_100_std": 0.1344828199915965, + "nauc_recall_at_10_diff1": 0.09067683612066126, + "nauc_recall_at_10_max": -0.034562324014977, + "nauc_recall_at_10_std": 0.15671143797766063, + "nauc_recall_at_1_diff1": -0.1582012861227588, + "nauc_recall_at_1_max": -0.17792123036441815, + "nauc_recall_at_1_std": 0.2541000750855491, + "nauc_recall_at_20_diff1": 0.06489047176883958, + "nauc_recall_at_20_max": -0.07329295788184277, + "nauc_recall_at_20_std": 0.1602553594862745, + "nauc_recall_at_3_diff1": 0.10675830562586613, + "nauc_recall_at_3_max": -0.012356031449478099, + "nauc_recall_at_3_std": 0.15186360596114135, + "nauc_recall_at_5_diff1": 0.10991371719444867, + "nauc_recall_at_5_max": -0.029224990392006087, + "nauc_recall_at_5_std": 0.13377392606741928, + "ndcg_at_1": 0.00278, + "ndcg_at_10": 0.03553, + "ndcg_at_100": 0.07973, + "ndcg_at_1000": 0.11802, + "ndcg_at_20": 0.04899, + "ndcg_at_3": 0.01157, + "ndcg_at_5": 0.02147, + "precision_at_1": 0.00278, + "precision_at_10": 0.01213, + "precision_at_100": 0.00447, + "precision_at_1000": 0.00093, + "precision_at_20": 0.00995, + "precision_at_3": 0.00909, + "precision_at_5": 0.01224, + "recall_at_1": 0.00223, + "recall_at_10": 0.07754, + "recall_at_100": 0.27472, + "recall_at_1000": 0.5473, + "recall_at_20": 0.12493, + "recall_at_3": 0.01707, + "recall_at_5": 0.0384 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL1.json b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL1.json new file mode 100644 index 000000000..7c1b45894 --- /dev/null +++ b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL1.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 5.966301441192627, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01415, + "map_at_1": 0.001, + "map_at_10": 0.00824, + "map_at_100": 0.01161, + "map_at_1000": 0.01254, + "map_at_20": 0.00983, + "map_at_3": 0.00383, + "map_at_5": 0.00598, + "mrr_at_1": 0.001, + "mrr_at_10": 0.008236210317460316, + "mrr_at_100": 0.011608409244658275, + "mrr_at_1000": 0.012539208321845803, + "mrr_at_20": 0.009834321762688648, + "mrr_at_3": 0.003833333333333334, + "mrr_at_5": 0.00598333333333333, + "nauc_map_at_1000_diff1": 0.031118899806473223, + "nauc_map_at_1000_max": 0.3476713689436928, + "nauc_map_at_1000_std": 0.23963327429325723, + "nauc_map_at_100_diff1": 0.03675467208516807, + "nauc_map_at_100_max": 0.35207430089924746, + "nauc_map_at_100_std": 0.24016974853173792, + "nauc_map_at_10_diff1": 0.03478312809783765, + "nauc_map_at_10_max": 0.37738538757510537, + "nauc_map_at_10_std": 0.2709637276724595, + "nauc_map_at_1_diff1": -0.4066943922726054, + "nauc_map_at_1_max": -0.24047491279849748, + "nauc_map_at_1_std": 0.34478132546283863, + "nauc_map_at_20_diff1": 0.05071653017513199, + "nauc_map_at_20_max": 0.36880943642873415, + "nauc_map_at_20_std": 0.2507288577811392, + "nauc_map_at_3_diff1": 0.04324494581257793, + "nauc_map_at_3_max": 0.3876704658135113, + "nauc_map_at_3_std": 0.32960418100582123, + "nauc_map_at_5_diff1": 0.060210329949409294, + "nauc_map_at_5_max": 0.37894630240965377, + "nauc_map_at_5_std": 0.2701477137772769, + "nauc_mrr_at_1000_diff1": 0.031119757500064817, + "nauc_mrr_at_1000_max": 0.34767108726581497, + "nauc_mrr_at_1000_std": 0.2396330586292886, + "nauc_mrr_at_100_diff1": 0.03675467208516807, + "nauc_mrr_at_100_max": 0.35207430089924746, + "nauc_mrr_at_100_std": 0.24016974853173792, + "nauc_mrr_at_10_diff1": 0.03478312809783765, + "nauc_mrr_at_10_max": 0.37738538757510537, + "nauc_mrr_at_10_std": 0.2709637276724595, + "nauc_mrr_at_1_diff1": -0.4066943922726054, + "nauc_mrr_at_1_max": -0.24047491279849748, + "nauc_mrr_at_1_std": 0.34478132546283863, + "nauc_mrr_at_20_diff1": 0.05071653017513199, + "nauc_mrr_at_20_max": 0.36880943642873415, + "nauc_mrr_at_20_std": 0.2507288577811392, + "nauc_mrr_at_3_diff1": 0.04324494581257793, + "nauc_mrr_at_3_max": 0.3876704658135113, + "nauc_mrr_at_3_std": 0.32960418100582123, + "nauc_mrr_at_5_diff1": 0.060210329949409294, + "nauc_mrr_at_5_max": 0.37894630240965377, + "nauc_mrr_at_5_std": 0.2701477137772769, + "nauc_ndcg_at_1000_diff1": -0.03863041012702467, + "nauc_ndcg_at_1000_max": 0.3006744917360344, + "nauc_ndcg_at_1000_std": 0.22777521344704296, + "nauc_ndcg_at_100_diff1": 0.017536937625195887, + "nauc_ndcg_at_100_max": 0.32676810785682764, + "nauc_ndcg_at_100_std": 0.21472310100645234, + "nauc_ndcg_at_10_diff1": 0.038423365606597884, + "nauc_ndcg_at_10_max": 0.39432159051211974, + "nauc_ndcg_at_10_std": 0.26168151155431557, + "nauc_ndcg_at_1_diff1": -0.4066943922726054, + "nauc_ndcg_at_1_max": -0.24047491279849748, + "nauc_ndcg_at_1_std": 0.34478132546283863, + "nauc_ndcg_at_20_diff1": 0.06632728970700592, + "nauc_ndcg_at_20_max": 0.37764335526928977, + "nauc_ndcg_at_20_std": 0.2303371771323737, + "nauc_ndcg_at_3_diff1": 0.07710177911718614, + "nauc_ndcg_at_3_max": 0.4297536672257638, + "nauc_ndcg_at_3_std": 0.3212801451784558, + "nauc_ndcg_at_5_diff1": 0.08066108449368213, + "nauc_ndcg_at_5_max": 0.3996844636433791, + "nauc_ndcg_at_5_std": 0.2503212709641342, + "nauc_precision_at_1000_diff1": -0.09322191995042577, + "nauc_precision_at_1000_max": 0.27176949044761584, + "nauc_precision_at_1000_std": 0.23411312968108916, + "nauc_precision_at_100_diff1": -0.001078658136030066, + "nauc_precision_at_100_max": 0.30531159088274434, + "nauc_precision_at_100_std": 0.20373390155174428, + "nauc_precision_at_10_diff1": 0.037847819567859306, + "nauc_precision_at_10_max": 0.4070830505531968, + "nauc_precision_at_10_std": 0.25548461939108885, + "nauc_precision_at_1_diff1": -0.4066943922726054, + "nauc_precision_at_1_max": -0.24047491279849748, + "nauc_precision_at_1_std": 0.34478132546283863, + "nauc_precision_at_20_diff1": 0.07689383776048642, + "nauc_precision_at_20_max": 0.38142125504262386, + "nauc_precision_at_20_std": 0.2162679639802483, + "nauc_precision_at_3_diff1": 0.12776138091405057, + "nauc_precision_at_3_max": 0.49180753063232263, + "nauc_precision_at_3_std": 0.3075574635542436, + "nauc_precision_at_5_diff1": 0.10103142410707261, + "nauc_precision_at_5_max": 0.41943133572183944, + "nauc_precision_at_5_std": 0.22654240123739353, + "nauc_recall_at_1000_diff1": -0.09322191995042539, + "nauc_recall_at_1000_max": 0.2717694904476164, + "nauc_recall_at_1000_std": 0.23411312968108963, + "nauc_recall_at_100_diff1": -0.0010786581360301914, + "nauc_recall_at_100_max": 0.30531159088274423, + "nauc_recall_at_100_std": 0.20373390155174415, + "nauc_recall_at_10_diff1": 0.037847819567859306, + "nauc_recall_at_10_max": 0.4070830505531967, + "nauc_recall_at_10_std": 0.2554846193910889, + "nauc_recall_at_1_diff1": -0.4066943922726054, + "nauc_recall_at_1_max": -0.24047491279849748, + "nauc_recall_at_1_std": 0.34478132546283863, + "nauc_recall_at_20_diff1": 0.07689383776048639, + "nauc_recall_at_20_max": 0.38142125504262403, + "nauc_recall_at_20_std": 0.21626796398024836, + "nauc_recall_at_3_diff1": 0.1277613809140506, + "nauc_recall_at_3_max": 0.49180753063232285, + "nauc_recall_at_3_std": 0.3075574635542438, + "nauc_recall_at_5_diff1": 0.10103142410707243, + "nauc_recall_at_5_max": 0.41943133572183916, + "nauc_recall_at_5_std": 0.22654240123739333, + "ndcg_at_1": 0.001, + "ndcg_at_10": 0.01415, + "ndcg_at_100": 0.03363, + "ndcg_at_1000": 0.06792, + "ndcg_at_20": 0.01996, + "ndcg_at_3": 0.00477, + "ndcg_at_5": 0.00867, + "precision_at_1": 0.001, + "precision_at_10": 0.0034, + "precision_at_100": 0.00132, + "precision_at_1000": 0.00042, + "precision_at_20": 0.00285, + "precision_at_3": 0.0025, + "precision_at_5": 0.0034, + "recall_at_1": 0.001, + "recall_at_10": 0.034, + "recall_at_100": 0.1325, + "recall_at_1000": 0.42375, + "recall_at_20": 0.057, + "recall_at_3": 0.0075, + "recall_at_5": 0.017 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL2Fact.json b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL2Fact.json new file mode 100644 index 000000000..fe7e35651 --- /dev/null +++ b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL2Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 14.261869430541992, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.17559, + "map_at_1": 0.07541, + "map_at_10": 0.13878, + "map_at_100": 0.14841, + "map_at_1000": 0.14932, + "map_at_20": 0.14375, + "map_at_3": 0.11775, + "map_at_5": 0.12929, + "mrr_at_1": 0.07541226607374467, + "mrr_at_10": 0.13877609842034552, + "mrr_at_100": 0.1484113040881823, + "mrr_at_1000": 0.14931802748008352, + "mrr_at_20": 0.1437471659176359, + "mrr_at_3": 0.11775060218639985, + "mrr_at_5": 0.129294052251251, + "nauc_map_at_1000_diff1": 0.02190411754596993, + "nauc_map_at_1000_max": -0.031245361595851666, + "nauc_map_at_1000_std": 0.08713404682099639, + "nauc_map_at_100_diff1": 0.022036736619286335, + "nauc_map_at_100_max": -0.03114870061056912, + "nauc_map_at_100_std": 0.08721483266449084, + "nauc_map_at_10_diff1": 0.028258559597879748, + "nauc_map_at_10_max": -0.023613155592649322, + "nauc_map_at_10_std": 0.07586978111548523, + "nauc_map_at_1_diff1": 0.08000020808861073, + "nauc_map_at_1_max": -0.038091619403375375, + "nauc_map_at_1_std": 0.03407927351019806, + "nauc_map_at_20_diff1": 0.025215891196104227, + "nauc_map_at_20_max": -0.026702104063827514, + "nauc_map_at_20_std": 0.0806287996848228, + "nauc_map_at_3_diff1": 0.04412755550823211, + "nauc_map_at_3_max": -0.011949428811530083, + "nauc_map_at_3_std": 0.06030055580631621, + "nauc_map_at_5_diff1": 0.03739380719165283, + "nauc_map_at_5_max": -0.0195091895064273, + "nauc_map_at_5_std": 0.06734240759463726, + "nauc_mrr_at_1000_diff1": 0.02190411754596993, + "nauc_mrr_at_1000_max": -0.031245361595851666, + "nauc_mrr_at_1000_std": 0.08713404682099639, + "nauc_mrr_at_100_diff1": 0.022036736619286335, + "nauc_mrr_at_100_max": -0.03114870061056912, + "nauc_mrr_at_100_std": 0.08721483266449084, + "nauc_mrr_at_10_diff1": 0.028258559597879748, + "nauc_mrr_at_10_max": -0.023613155592649322, + "nauc_mrr_at_10_std": 0.07586978111548523, + "nauc_mrr_at_1_diff1": 0.08000020808861073, + "nauc_mrr_at_1_max": -0.038091619403375375, + "nauc_mrr_at_1_std": 0.03407927351019806, + "nauc_mrr_at_20_diff1": 0.025215891196104227, + "nauc_mrr_at_20_max": -0.026702104063827514, + "nauc_mrr_at_20_std": 0.0806287996848228, + "nauc_mrr_at_3_diff1": 0.04412755550823211, + "nauc_mrr_at_3_max": -0.011949428811530083, + "nauc_mrr_at_3_std": 0.06030055580631621, + "nauc_mrr_at_5_diff1": 0.03739380719165283, + "nauc_mrr_at_5_max": -0.0195091895064273, + "nauc_mrr_at_5_std": 0.06734240759463726, + "nauc_ndcg_at_1000_diff1": -0.022565056004900698, + "nauc_ndcg_at_1000_max": -0.0661203158059184, + "nauc_ndcg_at_1000_std": 0.1438035882069785, + "nauc_ndcg_at_100_diff1": -0.021139619326663424, + "nauc_ndcg_at_100_max": -0.06407759711911386, + "nauc_ndcg_at_100_std": 0.15063914672255352, + "nauc_ndcg_at_10_diff1": 0.008445454679262393, + "nauc_ndcg_at_10_max": -0.028729048091956012, + "nauc_ndcg_at_10_std": 0.09319473213954049, + "nauc_ndcg_at_1_diff1": 0.08000020808861073, + "nauc_ndcg_at_1_max": -0.038091619403375375, + "nauc_ndcg_at_1_std": 0.03407927351019806, + "nauc_ndcg_at_20_diff1": -0.0008837453819206079, + "nauc_ndcg_at_20_max": -0.038088273635786776, + "nauc_ndcg_at_20_std": 0.1082429657423473, + "nauc_ndcg_at_3_diff1": 0.03666946619975272, + "nauc_ndcg_at_3_max": -0.00720186188562223, + "nauc_ndcg_at_3_std": 0.06524977829725997, + "nauc_ndcg_at_5_diff1": 0.02643662576207325, + "nauc_ndcg_at_5_max": -0.01998956636235934, + "nauc_ndcg_at_5_std": 0.07628582937297583, + "nauc_precision_at_1000_diff1": -0.2086466913666868, + "nauc_precision_at_1000_max": -0.23712533626937002, + "nauc_precision_at_1000_std": 0.3737554555819623, + "nauc_precision_at_100_diff1": -0.1361034216830546, + "nauc_precision_at_100_max": -0.16443564775760328, + "nauc_precision_at_100_std": 0.3360435425995156, + "nauc_precision_at_10_diff1": -0.030746065556361862, + "nauc_precision_at_10_max": -0.04125041785214541, + "nauc_precision_at_10_std": 0.12796553082711423, + "nauc_precision_at_1_diff1": 0.08000020808861073, + "nauc_precision_at_1_max": -0.038091619403375375, + "nauc_precision_at_1_std": 0.03407927351019806, + "nauc_precision_at_20_diff1": -0.05437037151133793, + "nauc_precision_at_20_max": -0.06556325919936747, + "nauc_precision_at_20_std": 0.16752906598468953, + "nauc_precision_at_3_diff1": 0.02099574498527454, + "nauc_precision_at_3_max": 0.0026078350006097863, + "nauc_precision_at_3_std": 0.0755284364457462, + "nauc_precision_at_5_diff1": 0.004646879675478431, + "nauc_precision_at_5_max": -0.02245304670247497, + "nauc_precision_at_5_std": 0.0942901457981883, + "nauc_recall_at_1000_diff1": -0.20864669136668798, + "nauc_recall_at_1000_max": -0.2371253362693698, + "nauc_recall_at_1000_std": 0.3737554555819621, + "nauc_recall_at_100_diff1": -0.1361034216830551, + "nauc_recall_at_100_max": -0.16443564775760383, + "nauc_recall_at_100_std": 0.3360435425995152, + "nauc_recall_at_10_diff1": -0.03074606555636176, + "nauc_recall_at_10_max": -0.041250417852145185, + "nauc_recall_at_10_std": 0.12796553082711423, + "nauc_recall_at_1_diff1": 0.08000020808861073, + "nauc_recall_at_1_max": -0.038091619403375375, + "nauc_recall_at_1_std": 0.03407927351019806, + "nauc_recall_at_20_diff1": -0.05437037151133804, + "nauc_recall_at_20_max": -0.06556325919936738, + "nauc_recall_at_20_std": 0.16752906598468933, + "nauc_recall_at_3_diff1": 0.020995744985274456, + "nauc_recall_at_3_max": 0.002607835000609756, + "nauc_recall_at_3_std": 0.07552843644574611, + "nauc_recall_at_5_diff1": 0.004646879675478214, + "nauc_recall_at_5_max": -0.022453046702475346, + "nauc_recall_at_5_std": 0.09429014579818823, + "ndcg_at_1": 0.07541, + "ndcg_at_10": 0.17559, + "ndcg_at_100": 0.22803, + "ndcg_at_1000": 0.25531, + "ndcg_at_20": 0.19368, + "ndcg_at_3": 0.13184, + "ndcg_at_5": 0.1527, + "precision_at_1": 0.07541, + "precision_at_10": 0.02941, + "precision_at_100": 0.00552, + "precision_at_1000": 0.00077, + "precision_at_20": 0.01828, + "precision_at_3": 0.05756, + "precision_at_5": 0.04469, + "recall_at_1": 0.07541, + "recall_at_10": 0.29405, + "recall_at_100": 0.55179, + "recall_at_1000": 0.77413, + "recall_at_20": 0.36557, + "recall_at_3": 0.17269, + "recall_at_5": 0.22346 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL2Pure.json b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL2Pure.json new file mode 100644 index 000000000..58ed7bd48 --- /dev/null +++ b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL2Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 8.146118402481079, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01049, + "map_at_1": 0.00278, + "map_at_10": 0.00697, + "map_at_100": 0.00969, + "map_at_1000": 0.01084, + "map_at_20": 0.008, + "map_at_3": 0.00457, + "map_at_5": 0.00569, + "mrr_at_1": 0.0027793218454697055, + "mrr_at_10": 0.006970583304657793, + "mrr_at_100": 0.009694588057569915, + "mrr_at_1000": 0.010836648452612969, + "mrr_at_20": 0.007996220169778934, + "mrr_at_3": 0.004570440368105736, + "mrr_at_5": 0.005691433512445184, + "nauc_map_at_1000_diff1": -0.10292018232480911, + "nauc_map_at_1000_max": -0.12699981468965044, + "nauc_map_at_1000_std": 0.23378761878436863, + "nauc_map_at_100_diff1": -0.10043486030446072, + "nauc_map_at_100_max": -0.12355648034809966, + "nauc_map_at_100_std": 0.24134294050835006, + "nauc_map_at_10_diff1": -0.11895447482303148, + "nauc_map_at_10_max": -0.1347760334175005, + "nauc_map_at_10_std": 0.27411051359729943, + "nauc_map_at_1_diff1": -0.14558748639644287, + "nauc_map_at_1_max": -0.22080360177812436, + "nauc_map_at_1_std": 0.3055515041065293, + "nauc_map_at_20_diff1": -0.1136026841605639, + "nauc_map_at_20_max": -0.1258300686378737, + "nauc_map_at_20_std": 0.25916861946675246, + "nauc_map_at_3_diff1": -0.14558113681534804, + "nauc_map_at_3_max": -0.15616002907479148, + "nauc_map_at_3_std": 0.29844898932406566, + "nauc_map_at_5_diff1": -0.11896779964062704, + "nauc_map_at_5_max": -0.14381141059860755, + "nauc_map_at_5_std": 0.2921505193261156, + "nauc_mrr_at_1000_diff1": -0.10292017951437252, + "nauc_mrr_at_1000_max": -0.1269998119893909, + "nauc_mrr_at_1000_std": 0.2337876152785341, + "nauc_mrr_at_100_diff1": -0.10043486030446072, + "nauc_mrr_at_100_max": -0.12355648034809966, + "nauc_mrr_at_100_std": 0.24134294050835006, + "nauc_mrr_at_10_diff1": -0.11895447482303148, + "nauc_mrr_at_10_max": -0.1347760334175005, + "nauc_mrr_at_10_std": 0.27411051359729943, + "nauc_mrr_at_1_diff1": -0.14558748639644287, + "nauc_mrr_at_1_max": -0.22080360177812436, + "nauc_mrr_at_1_std": 0.3055515041065293, + "nauc_mrr_at_20_diff1": -0.1136026841605639, + "nauc_mrr_at_20_max": -0.1258300686378737, + "nauc_mrr_at_20_std": 0.25916861946675246, + "nauc_mrr_at_3_diff1": -0.14558113681534804, + "nauc_mrr_at_3_max": -0.15616002907479148, + "nauc_mrr_at_3_std": 0.29844898932406566, + "nauc_mrr_at_5_diff1": -0.11896779964062704, + "nauc_mrr_at_5_max": -0.14381141059860755, + "nauc_mrr_at_5_std": 0.2921505193261156, + "nauc_ndcg_at_1000_diff1": -0.11633059151346081, + "nauc_ndcg_at_1000_max": -0.15275258274364018, + "nauc_ndcg_at_1000_std": 0.13574141553421595, + "nauc_ndcg_at_100_diff1": -0.07760258986199307, + "nauc_ndcg_at_100_max": -0.1141434183777079, + "nauc_ndcg_at_100_std": 0.1935768057189142, + "nauc_ndcg_at_10_diff1": -0.11146003691737694, + "nauc_ndcg_at_10_max": -0.11819524911075921, + "nauc_ndcg_at_10_std": 0.2588217895994924, + "nauc_ndcg_at_1_diff1": -0.14558748639644287, + "nauc_ndcg_at_1_max": -0.22080360177812436, + "nauc_ndcg_at_1_std": 0.3055515041065293, + "nauc_ndcg_at_20_diff1": -0.10086917495310244, + "nauc_ndcg_at_20_max": -0.10359789516987489, + "nauc_ndcg_at_20_std": 0.2295715959705141, + "nauc_ndcg_at_3_diff1": -0.14517596561732646, + "nauc_ndcg_at_3_max": -0.14249119983180192, + "nauc_ndcg_at_3_std": 0.296844037793489, + "nauc_ndcg_at_5_diff1": -0.10792074619682855, + "nauc_ndcg_at_5_max": -0.1282831179056432, + "nauc_ndcg_at_5_std": 0.29049551563055864, + "nauc_precision_at_1000_diff1": -0.13803577749618803, + "nauc_precision_at_1000_max": -0.1784410949780009, + "nauc_precision_at_1000_std": 0.08398927892931035, + "nauc_precision_at_100_diff1": -0.06856582537835403, + "nauc_precision_at_100_max": -0.11509327468832507, + "nauc_precision_at_100_std": 0.17093163205984926, + "nauc_precision_at_10_diff1": -0.10410903153720731, + "nauc_precision_at_10_max": -0.10142261982083745, + "nauc_precision_at_10_std": 0.24033446684273227, + "nauc_precision_at_1_diff1": -0.14558748639644287, + "nauc_precision_at_1_max": -0.22080360177812436, + "nauc_precision_at_1_std": 0.3055515041065293, + "nauc_precision_at_20_diff1": -0.08998231224794097, + "nauc_precision_at_20_max": -0.08585776768799622, + "nauc_precision_at_20_std": 0.2015954747358713, + "nauc_precision_at_3_diff1": -0.144324540550923, + "nauc_precision_at_3_max": -0.11630069396485111, + "nauc_precision_at_3_std": 0.2937496540474576, + "nauc_precision_at_5_diff1": -0.09073352077093137, + "nauc_precision_at_5_max": -0.10570087772653054, + "nauc_precision_at_5_std": 0.28870262431360066, + "nauc_recall_at_1000_diff1": -0.13803577749618753, + "nauc_recall_at_1000_max": -0.1784410949780004, + "nauc_recall_at_1000_std": 0.08398927892931063, + "nauc_recall_at_100_diff1": -0.06856582537835426, + "nauc_recall_at_100_max": -0.11509327468832528, + "nauc_recall_at_100_std": 0.17093163205984901, + "nauc_recall_at_10_diff1": -0.1041090315372075, + "nauc_recall_at_10_max": -0.1014226198208376, + "nauc_recall_at_10_std": 0.24033446684273205, + "nauc_recall_at_1_diff1": -0.14558748639644287, + "nauc_recall_at_1_max": -0.22080360177812436, + "nauc_recall_at_1_std": 0.3055515041065293, + "nauc_recall_at_20_diff1": -0.0899823122479412, + "nauc_recall_at_20_max": -0.08585776768799643, + "nauc_recall_at_20_std": 0.2015954747358711, + "nauc_recall_at_3_diff1": -0.14432454055092295, + "nauc_recall_at_3_max": -0.11630069396485103, + "nauc_recall_at_3_std": 0.29374965404745795, + "nauc_recall_at_5_diff1": -0.09073352077093166, + "nauc_recall_at_5_max": -0.10570087772653086, + "nauc_recall_at_5_std": 0.28870262431360033, + "ndcg_at_1": 0.00278, + "ndcg_at_10": 0.01049, + "ndcg_at_100": 0.02824, + "ndcg_at_1000": 0.06896, + "ndcg_at_20": 0.0143, + "ndcg_at_3": 0.0052, + "ndcg_at_5": 0.00724, + "precision_at_1": 0.00278, + "precision_at_10": 0.00224, + "precision_at_100": 0.00116, + "precision_at_1000": 0.00046, + "precision_at_20": 0.00188, + "precision_at_3": 0.00235, + "precision_at_5": 0.00241, + "recall_at_1": 0.00278, + "recall_at_10": 0.02242, + "recall_at_100": 0.11618, + "recall_at_1000": 0.45951, + "recall_at_20": 0.03761, + "recall_at_3": 0.00704, + "recall_at_5": 0.01204 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL3Fact.json b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL3Fact.json new file mode 100644 index 000000000..8d2ae1826 --- /dev/null +++ b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL3Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 12.274138450622559, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.13883, + "map_at_1": 0.03864, + "map_at_10": 0.1009, + "map_at_100": 0.11068, + "map_at_1000": 0.11154, + "map_at_20": 0.106, + "map_at_3": 0.07878, + "map_at_5": 0.09066, + "mrr_at_1": 0.038635336647085405, + "mrr_at_10": 0.10089971596410796, + "mrr_at_100": 0.1106776503716446, + "mrr_at_1000": 0.11154382721446959, + "mrr_at_20": 0.10600089029325734, + "mrr_at_3": 0.0787769242355775, + "mrr_at_5": 0.09066124416327724, + "nauc_map_at_1000_diff1": -0.030817143729081998, + "nauc_map_at_1000_max": 0.042454633883770486, + "nauc_map_at_1000_std": 0.16160127189959783, + "nauc_map_at_100_diff1": -0.030481476816353152, + "nauc_map_at_100_max": 0.04299475373759486, + "nauc_map_at_100_std": 0.16189961547369672, + "nauc_map_at_10_diff1": -0.02564265761838756, + "nauc_map_at_10_max": 0.04762781990636439, + "nauc_map_at_10_std": 0.13877967820876944, + "nauc_map_at_1_diff1": -0.11989845182459109, + "nauc_map_at_1_max": 0.011545869041154544, + "nauc_map_at_1_std": 0.09726522805083375, + "nauc_map_at_20_diff1": -0.027829195876103767, + "nauc_map_at_20_max": 0.04544211792827223, + "nauc_map_at_20_std": 0.15010986628654274, + "nauc_map_at_3_diff1": -0.021886765375722622, + "nauc_map_at_3_max": 0.05649247294746982, + "nauc_map_at_3_std": 0.11772748521102311, + "nauc_map_at_5_diff1": -0.022567599500540988, + "nauc_map_at_5_max": 0.05265207596184244, + "nauc_map_at_5_std": 0.1232091640568664, + "nauc_mrr_at_1000_diff1": -0.030817143729081998, + "nauc_mrr_at_1000_max": 0.042454633883770486, + "nauc_mrr_at_1000_std": 0.16160127189959783, + "nauc_mrr_at_100_diff1": -0.030481476816353152, + "nauc_mrr_at_100_max": 0.04299475373759486, + "nauc_mrr_at_100_std": 0.16189961547369672, + "nauc_mrr_at_10_diff1": -0.02564265761838756, + "nauc_mrr_at_10_max": 0.04762781990636439, + "nauc_mrr_at_10_std": 0.13877967820876944, + "nauc_mrr_at_1_diff1": -0.11989845182459109, + "nauc_mrr_at_1_max": 0.011545869041154544, + "nauc_mrr_at_1_std": 0.09726522805083375, + "nauc_mrr_at_20_diff1": -0.027829195876103767, + "nauc_mrr_at_20_max": 0.04544211792827223, + "nauc_mrr_at_20_std": 0.15010986628654274, + "nauc_mrr_at_3_diff1": -0.021886765375722622, + "nauc_mrr_at_3_max": 0.05649247294746982, + "nauc_mrr_at_3_std": 0.11772748521102311, + "nauc_mrr_at_5_diff1": -0.022567599500540988, + "nauc_mrr_at_5_max": 0.05265207596184244, + "nauc_mrr_at_5_std": 0.1232091640568664, + "nauc_ndcg_at_1000_diff1": -0.043647884569532766, + "nauc_ndcg_at_1000_max": 0.01747412608593683, + "nauc_ndcg_at_1000_std": 0.24759762164716573, + "nauc_ndcg_at_100_diff1": -0.041112217349272014, + "nauc_ndcg_at_100_max": 0.025668130751039235, + "nauc_ndcg_at_100_std": 0.25523729372428117, + "nauc_ndcg_at_10_diff1": -0.01978993091495972, + "nauc_ndcg_at_10_max": 0.04610826624026404, + "nauc_ndcg_at_10_std": 0.15996254382588973, + "nauc_ndcg_at_1_diff1": -0.11989845182459109, + "nauc_ndcg_at_1_max": 0.011545869041154544, + "nauc_ndcg_at_1_std": 0.09726522805083375, + "nauc_ndcg_at_20_diff1": -0.025998592282752787, + "nauc_ndcg_at_20_max": 0.03902894235025046, + "nauc_ndcg_at_20_std": 0.19000663350279207, + "nauc_ndcg_at_3_diff1": -0.010265966676998544, + "nauc_ndcg_at_3_max": 0.06331833529861558, + "nauc_ndcg_at_3_std": 0.12205083100430547, + "nauc_ndcg_at_5_diff1": -0.012960208005455165, + "nauc_ndcg_at_5_max": 0.055816816781336966, + "nauc_ndcg_at_5_std": 0.12891017122615117, + "nauc_precision_at_1000_diff1": -0.0999175754791264, + "nauc_precision_at_1000_max": -0.08415459259452766, + "nauc_precision_at_1000_std": 0.5174502820215692, + "nauc_precision_at_100_diff1": -0.0762525031721128, + "nauc_precision_at_100_max": -0.01757067327304807, + "nauc_precision_at_100_std": 0.46703321015001686, + "nauc_precision_at_10_diff1": -0.013872926135186502, + "nauc_precision_at_10_max": 0.04136634806611198, + "nauc_precision_at_10_std": 0.19651050266946513, + "nauc_precision_at_1_diff1": -0.11989845182459109, + "nauc_precision_at_1_max": 0.011545869041154544, + "nauc_precision_at_1_std": 0.09726522805083375, + "nauc_precision_at_20_diff1": -0.02818306886567862, + "nauc_precision_at_20_max": 0.02453530535305187, + "nauc_precision_at_20_std": 0.2604919169169616, + "nauc_precision_at_3_diff1": 0.010004531624012084, + "nauc_precision_at_3_max": 0.0756252502743051, + "nauc_precision_at_3_std": 0.1300996576053757, + "nauc_precision_at_5_diff1": 0.0011464581329819336, + "nauc_precision_at_5_max": 0.05976538045141451, + "nauc_precision_at_5_std": 0.1381603926156352, + "nauc_recall_at_1000_diff1": -0.09991757547912723, + "nauc_recall_at_1000_max": -0.08415459259452862, + "nauc_recall_at_1000_std": 0.5174502820215692, + "nauc_recall_at_100_diff1": -0.07625250317211309, + "nauc_recall_at_100_max": -0.01757067327304815, + "nauc_recall_at_100_std": 0.4670332101500164, + "nauc_recall_at_10_diff1": -0.013872926135186932, + "nauc_recall_at_10_max": 0.04136634806611148, + "nauc_recall_at_10_std": 0.19651050266946465, + "nauc_recall_at_1_diff1": -0.11989845182459109, + "nauc_recall_at_1_max": 0.011545869041154544, + "nauc_recall_at_1_std": 0.09726522805083375, + "nauc_recall_at_20_diff1": -0.02818306886567866, + "nauc_recall_at_20_max": 0.024535305353051814, + "nauc_recall_at_20_std": 0.2604919169169613, + "nauc_recall_at_3_diff1": 0.010004531624012046, + "nauc_recall_at_3_max": 0.07562525027430497, + "nauc_recall_at_3_std": 0.13009965760537542, + "nauc_recall_at_5_diff1": 0.0011464581329817833, + "nauc_recall_at_5_max": 0.05976538045141454, + "nauc_recall_at_5_std": 0.13816039261563529, + "ndcg_at_1": 0.03864, + "ndcg_at_10": 0.13883, + "ndcg_at_100": 0.19246, + "ndcg_at_1000": 0.21948, + "ndcg_at_20": 0.15755, + "ndcg_at_3": 0.09244, + "ndcg_at_5": 0.114, + "precision_at_1": 0.03864, + "precision_at_10": 0.02616, + "precision_at_100": 0.00526, + "precision_at_1000": 0.00075, + "precision_at_20": 0.0168, + "precision_at_3": 0.04406, + "precision_at_5": 0.03696, + "recall_at_1": 0.03864, + "recall_at_10": 0.26164, + "recall_at_100": 0.52621, + "recall_at_1000": 0.74808, + "recall_at_20": 0.33597, + "recall_at_3": 0.13217, + "recall_at_5": 0.18482 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL3Pure.json b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL3Pure.json new file mode 100644 index 000000000..becbee01c --- /dev/null +++ b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/TempReasonL3Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 6.968750715255737, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.04756, + "map_at_1": 0.0009, + "map_at_10": 0.02866, + "map_at_100": 0.03634, + "map_at_1000": 0.0374, + "map_at_20": 0.03241, + "map_at_3": 0.01664, + "map_at_5": 0.0227, + "mrr_at_1": 0.0009037505648441031, + "mrr_at_10": 0.028664403703942812, + "mrr_at_100": 0.03633963496225244, + "mrr_at_1000": 0.03739776834393567, + "mrr_at_20": 0.03240920931153606, + "mrr_at_3": 0.016644072902545572, + "mrr_at_5": 0.02269920168700107, + "nauc_map_at_1000_diff1": -0.04761351367032372, + "nauc_map_at_1000_max": 0.23065469886910814, + "nauc_map_at_1000_std": 0.45118893821474765, + "nauc_map_at_100_diff1": -0.04829616327797522, + "nauc_map_at_100_max": 0.23232148385291385, + "nauc_map_at_100_std": 0.4524354655888791, + "nauc_map_at_10_diff1": -0.05466769786337041, + "nauc_map_at_10_max": 0.2261274884834992, + "nauc_map_at_10_std": 0.4086315789135239, + "nauc_map_at_1_diff1": -0.44879163397658794, + "nauc_map_at_1_max": -0.14827276798522823, + "nauc_map_at_1_std": 0.323610603679025, + "nauc_map_at_20_diff1": -0.049167756892001625, + "nauc_map_at_20_max": 0.23404635780049707, + "nauc_map_at_20_std": 0.4316772199557157, + "nauc_map_at_3_diff1": -0.09585632295851854, + "nauc_map_at_3_max": 0.19921814070181837, + "nauc_map_at_3_std": 0.3387241039010992, + "nauc_map_at_5_diff1": -0.05965125188713115, + "nauc_map_at_5_max": 0.22868861771191681, + "nauc_map_at_5_std": 0.3758779990720749, + "nauc_mrr_at_1000_diff1": -0.047613511966263115, + "nauc_mrr_at_1000_max": 0.23065470167336183, + "nauc_mrr_at_1000_std": 0.4511889418909308, + "nauc_mrr_at_100_diff1": -0.04829616327797522, + "nauc_mrr_at_100_max": 0.23232148385291385, + "nauc_mrr_at_100_std": 0.4524354655888791, + "nauc_mrr_at_10_diff1": -0.05466769786337041, + "nauc_mrr_at_10_max": 0.2261274884834992, + "nauc_mrr_at_10_std": 0.4086315789135239, + "nauc_mrr_at_1_diff1": -0.44879163397658794, + "nauc_mrr_at_1_max": -0.14827276798522823, + "nauc_mrr_at_1_std": 0.323610603679025, + "nauc_mrr_at_20_diff1": -0.049167756892001625, + "nauc_mrr_at_20_max": 0.23404635780049707, + "nauc_mrr_at_20_std": 0.4316772199557157, + "nauc_mrr_at_3_diff1": -0.09585632295851854, + "nauc_mrr_at_3_max": 0.19921814070181837, + "nauc_mrr_at_3_std": 0.3387241039010992, + "nauc_mrr_at_5_diff1": -0.05965125188713115, + "nauc_mrr_at_5_max": 0.22868861771191681, + "nauc_mrr_at_5_std": 0.3758779990720749, + "nauc_ndcg_at_1000_diff1": -0.026284994345656298, + "nauc_ndcg_at_1000_max": 0.21557523966897923, + "nauc_ndcg_at_1000_std": 0.5214391660175564, + "nauc_ndcg_at_100_diff1": -0.03324454943353628, + "nauc_ndcg_at_100_max": 0.23422404316401127, + "nauc_ndcg_at_100_std": 0.537027973110257, + "nauc_ndcg_at_10_diff1": -0.040920712622853433, + "nauc_ndcg_at_10_max": 0.23302719660147508, + "nauc_ndcg_at_10_std": 0.43372630986685545, + "nauc_ndcg_at_1_diff1": -0.44879163397658794, + "nauc_ndcg_at_1_max": -0.14827276798522823, + "nauc_ndcg_at_1_std": 0.323610603679025, + "nauc_ndcg_at_20_diff1": -0.03245448090174258, + "nauc_ndcg_at_20_max": 0.24605085386710918, + "nauc_ndcg_at_20_std": 0.4758771129894261, + "nauc_ndcg_at_3_diff1": -0.08808303131848118, + "nauc_ndcg_at_3_max": 0.20809429860048795, + "nauc_ndcg_at_3_std": 0.3438700397581077, + "nauc_ndcg_at_5_diff1": -0.044480975843656435, + "nauc_ndcg_at_5_max": 0.24124207224782285, + "nauc_ndcg_at_5_std": 0.38745270028441686, + "nauc_precision_at_1000_diff1": -0.00534406465033436, + "nauc_precision_at_1000_max": 0.17722598731771033, + "nauc_precision_at_1000_std": 0.5785629225793563, + "nauc_precision_at_100_diff1": -0.02448953936570131, + "nauc_precision_at_100_max": 0.22893790518125137, + "nauc_precision_at_100_std": 0.6124484309950415, + "nauc_precision_at_10_diff1": -0.027972323793120406, + "nauc_precision_at_10_max": 0.23823171109273647, + "nauc_precision_at_10_std": 0.46000713513833885, + "nauc_precision_at_1_diff1": -0.44879163397658794, + "nauc_precision_at_1_max": -0.14827276798522823, + "nauc_precision_at_1_std": 0.323610603679025, + "nauc_precision_at_20_diff1": -0.018508665988160544, + "nauc_precision_at_20_max": 0.25559650196644934, + "nauc_precision_at_20_std": 0.5183207132778898, + "nauc_precision_at_3_diff1": -0.07775584796400778, + "nauc_precision_at_3_max": 0.22001757192295138, + "nauc_precision_at_3_std": 0.35122182512995187, + "nauc_precision_at_5_diff1": -0.026315457532653887, + "nauc_precision_at_5_max": 0.2557752861474183, + "nauc_precision_at_5_std": 0.40144626332029126, + "nauc_recall_at_1000_diff1": -0.005344064650334441, + "nauc_recall_at_1000_max": 0.17722598731771028, + "nauc_recall_at_1000_std": 0.5785629225793565, + "nauc_recall_at_100_diff1": -0.024489539365701377, + "nauc_recall_at_100_max": 0.2289379051812513, + "nauc_recall_at_100_std": 0.6124484309950413, + "nauc_recall_at_10_diff1": -0.02797232379312054, + "nauc_recall_at_10_max": 0.23823171109273647, + "nauc_recall_at_10_std": 0.46000713513833874, + "nauc_recall_at_1_diff1": -0.44879163397658794, + "nauc_recall_at_1_max": -0.14827276798522823, + "nauc_recall_at_1_std": 0.323610603679025, + "nauc_recall_at_20_diff1": -0.01850866598816056, + "nauc_recall_at_20_max": 0.2555965019664491, + "nauc_recall_at_20_std": 0.5183207132778899, + "nauc_recall_at_3_diff1": -0.07775584796400782, + "nauc_recall_at_3_max": 0.22001757192295132, + "nauc_recall_at_3_std": 0.3512218251299518, + "nauc_recall_at_5_diff1": -0.026315457532654015, + "nauc_recall_at_5_max": 0.2557752861474181, + "nauc_recall_at_5_std": 0.40144626332029115, + "ndcg_at_1": 0.0009, + "ndcg_at_10": 0.04756, + "ndcg_at_100": 0.09049, + "ndcg_at_1000": 0.12591, + "ndcg_at_20": 0.06132, + "ndcg_at_3": 0.02215, + "ndcg_at_5": 0.03309, + "precision_at_1": 0.0009, + "precision_at_10": 0.01096, + "precision_at_100": 0.00323, + "precision_at_1000": 0.00062, + "precision_at_20": 0.00821, + "precision_at_3": 0.01273, + "precision_at_5": 0.01297, + "recall_at_1": 0.0009, + "recall_at_10": 0.10958, + "recall_at_100": 0.32309, + "recall_at_1000": 0.61771, + "recall_at_20": 0.16426, + "recall_at_3": 0.03818, + "recall_at_5": 0.06484 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/WinoGrande.json b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/WinoGrande.json new file mode 100644 index 000000000..07ccc1bf6 --- /dev/null +++ b/results/bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/WinoGrande.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 2.067396402359009, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.10283, + "map_at_1": 0.01736, + "map_at_10": 0.06528, + "map_at_100": 0.08083, + "map_at_1000": 0.08211, + "map_at_20": 0.07169, + "map_at_3": 0.0413, + "map_at_5": 0.05235, + "mrr_at_1": 0.017363851617995266, + "mrr_at_10": 0.06547556407461698, + "mrr_at_100": 0.08118235376168162, + "mrr_at_1000": 0.08246431263052251, + "mrr_at_20": 0.0720440311069061, + "mrr_at_3": 0.04156800841883717, + "mrr_at_5": 0.052933438568797724, + "nauc_map_at_1000_diff1": 0.00950330889522517, + "nauc_map_at_1000_max": 0.11553845907621385, + "nauc_map_at_1000_std": -0.09710316292823348, + "nauc_map_at_100_diff1": 0.008882365074668058, + "nauc_map_at_100_max": 0.11441796540610048, + "nauc_map_at_100_std": -0.09729248226766976, + "nauc_map_at_10_diff1": 0.014534250361798569, + "nauc_map_at_10_max": 0.11049927197486412, + "nauc_map_at_10_std": -0.09584301734421237, + "nauc_map_at_1_diff1": 0.14262466879890098, + "nauc_map_at_1_max": 0.20172892339862458, + "nauc_map_at_1_std": -0.16572153261458453, + "nauc_map_at_20_diff1": 0.009614199328996256, + "nauc_map_at_20_max": 0.1204405897387734, + "nauc_map_at_20_std": -0.10436234707253307, + "nauc_map_at_3_diff1": 0.028373806297890335, + "nauc_map_at_3_max": 0.11916470146233964, + "nauc_map_at_3_std": -0.10870362181438083, + "nauc_map_at_5_diff1": 0.02076670885967242, + "nauc_map_at_5_max": 0.12626768062322416, + "nauc_map_at_5_std": -0.09631432924619455, + "nauc_mrr_at_1000_diff1": 0.010593055152053122, + "nauc_mrr_at_1000_max": 0.11686640362986501, + "nauc_mrr_at_1000_std": -0.09790880744759846, + "nauc_mrr_at_100_diff1": 0.00996536659683116, + "nauc_mrr_at_100_max": 0.11573920778241534, + "nauc_mrr_at_100_std": -0.09808943295320273, + "nauc_mrr_at_10_diff1": 0.016126848873298617, + "nauc_mrr_at_10_max": 0.1123032256411604, + "nauc_mrr_at_10_std": -0.09748537530464721, + "nauc_mrr_at_1_diff1": 0.14262466879890098, + "nauc_mrr_at_1_max": 0.20172892339862458, + "nauc_mrr_at_1_std": -0.16572153261458453, + "nauc_mrr_at_20_diff1": 0.010665885961186278, + "nauc_mrr_at_20_max": 0.1216994368172494, + "nauc_mrr_at_20_std": -0.10511968543757606, + "nauc_mrr_at_3_diff1": 0.030350674693676513, + "nauc_mrr_at_3_max": 0.12135205979778839, + "nauc_mrr_at_3_std": -0.11024815776141617, + "nauc_mrr_at_5_diff1": 0.019491281454299195, + "nauc_mrr_at_5_max": 0.12651769590908243, + "nauc_mrr_at_5_std": -0.09568885998732592, + "nauc_ndcg_at_1000_diff1": -0.004093200175385698, + "nauc_ndcg_at_1000_max": 0.10883514978562657, + "nauc_ndcg_at_1000_std": -0.07676212278541178, + "nauc_ndcg_at_100_diff1": -0.015806228874127498, + "nauc_ndcg_at_100_max": 0.08713486084312357, + "nauc_ndcg_at_100_std": -0.07678271736602076, + "nauc_ndcg_at_10_diff1": 0.00013631141264093665, + "nauc_ndcg_at_10_max": 0.09281090479637784, + "nauc_ndcg_at_10_std": -0.08442793805852157, + "nauc_ndcg_at_1_diff1": 0.14262466879890098, + "nauc_ndcg_at_1_max": 0.20172892339862458, + "nauc_ndcg_at_1_std": -0.16572153261458453, + "nauc_ndcg_at_20_diff1": -0.01022041528604856, + "nauc_ndcg_at_20_max": 0.11632628784017104, + "nauc_ndcg_at_20_std": -0.10620655549956806, + "nauc_ndcg_at_3_diff1": 0.011384980453007279, + "nauc_ndcg_at_3_max": 0.10504956876862813, + "nauc_ndcg_at_3_std": -0.0994397673727353, + "nauc_ndcg_at_5_diff1": 0.006918177476502814, + "nauc_ndcg_at_5_max": 0.1171935482359195, + "nauc_ndcg_at_5_std": -0.08387232529326215, + "nauc_precision_at_1000_diff1": 0.005443019193477756, + "nauc_precision_at_1000_max": 0.2763900060594366, + "nauc_precision_at_1000_std": 0.25928225652967163, + "nauc_precision_at_100_diff1": -0.05757196345253522, + "nauc_precision_at_100_max": 0.028864657280275336, + "nauc_precision_at_100_std": -0.03386148186567595, + "nauc_precision_at_10_diff1": -0.014351626561925802, + "nauc_precision_at_10_max": 0.07215284299046247, + "nauc_precision_at_10_std": -0.07183032218472324, + "nauc_precision_at_1_diff1": 0.14262466879890098, + "nauc_precision_at_1_max": 0.20172892339862458, + "nauc_precision_at_1_std": -0.16572153261458453, + "nauc_precision_at_20_diff1": -0.031052083114122303, + "nauc_precision_at_20_max": 0.11635623297570012, + "nauc_precision_at_20_std": -0.11369107649497943, + "nauc_precision_at_3_diff1": -0.014050891813067396, + "nauc_precision_at_3_max": 0.08365578735714556, + "nauc_precision_at_3_std": -0.08545852425244585, + "nauc_precision_at_5_diff1": -0.009797868382856423, + "nauc_precision_at_5_max": 0.10608420539129947, + "nauc_precision_at_5_std": -0.06727818255837076, + "nauc_recall_at_1000_diff1": 0.005443019193475701, + "nauc_recall_at_1000_max": 0.2763900060594386, + "nauc_recall_at_1000_std": 0.25928225652966813, + "nauc_recall_at_100_diff1": -0.05757196345253532, + "nauc_recall_at_100_max": 0.02886465728027499, + "nauc_recall_at_100_std": -0.03386148186567653, + "nauc_recall_at_10_diff1": -0.014351626561925986, + "nauc_recall_at_10_max": 0.07215284299046221, + "nauc_recall_at_10_std": -0.07183032218472338, + "nauc_recall_at_1_diff1": 0.14262466879890098, + "nauc_recall_at_1_max": 0.20172892339862458, + "nauc_recall_at_1_std": -0.16572153261458453, + "nauc_recall_at_20_diff1": -0.03105208311412233, + "nauc_recall_at_20_max": 0.11635623297569975, + "nauc_recall_at_20_std": -0.11369107649497964, + "nauc_recall_at_3_diff1": -0.01405089181306737, + "nauc_recall_at_3_max": 0.08365578735714557, + "nauc_recall_at_3_std": -0.08545852425244588, + "nauc_recall_at_5_diff1": -0.009797868382856458, + "nauc_recall_at_5_max": 0.10608420539129937, + "nauc_recall_at_5_std": -0.0672781825583709, + "ndcg_at_1": 0.01736, + "ndcg_at_10": 0.10283, + "ndcg_at_100": 0.19631, + "ndcg_at_1000": 0.2304, + "ndcg_at_20": 0.12671, + "ndcg_at_3": 0.05158, + "ndcg_at_5": 0.07162, + "precision_at_1": 0.01736, + "precision_at_10": 0.02273, + "precision_at_100": 0.00705, + "precision_at_1000": 0.00097, + "precision_at_20": 0.01614, + "precision_at_3": 0.02736, + "precision_at_5": 0.0262, + "recall_at_1": 0.01736, + "recall_at_10": 0.22731, + "recall_at_100": 0.70481, + "recall_at_1000": 0.97316, + "recall_at_20": 0.32281, + "recall_at_3": 0.08208, + "recall_at_5": 0.13102 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/ARCChallenge.json b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/ARCChallenge.json new file mode 100644 index 000000000..f6b7c0063 --- /dev/null +++ b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/ARCChallenge.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 4.369304656982422, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07632, + "map_at_1": 0.01792, + "map_at_10": 0.05439, + "map_at_100": 0.05965, + "map_at_1000": 0.06074, + "map_at_20": 0.05694, + "map_at_3": 0.04067, + "map_at_5": 0.04903, + "mrr_at_1": 0.017918088737201365, + "mrr_at_10": 0.05438505607020969, + "mrr_at_100": 0.05964798471833107, + "mrr_at_1000": 0.060744121833893695, + "mrr_at_20": 0.05694290119203479, + "mrr_at_3": 0.040671217292377715, + "mrr_at_5": 0.04903299203640502, + "nauc_map_at_1000_diff1": -0.013850973611605382, + "nauc_map_at_1000_max": 0.3134326007087558, + "nauc_map_at_1000_std": 0.04975343812599383, + "nauc_map_at_100_diff1": -0.013868607585728908, + "nauc_map_at_100_max": 0.3149081388158546, + "nauc_map_at_100_std": 0.04982584041892596, + "nauc_map_at_10_diff1": -0.0095390924269391, + "nauc_map_at_10_max": 0.3364665409048257, + "nauc_map_at_10_std": 0.047407458610126366, + "nauc_map_at_1_diff1": -0.01580883633311793, + "nauc_map_at_1_max": 0.4057841263158078, + "nauc_map_at_1_std": 0.12428711624037517, + "nauc_map_at_20_diff1": -0.011497657780061475, + "nauc_map_at_20_max": 0.32201847303650305, + "nauc_map_at_20_std": 0.04904889889619527, + "nauc_map_at_3_diff1": -0.015507495859129323, + "nauc_map_at_3_max": 0.34448582240724407, + "nauc_map_at_3_std": 0.05306648104668278, + "nauc_map_at_5_diff1": -0.0028647590679952355, + "nauc_map_at_5_max": 0.35683575673472995, + "nauc_map_at_5_std": 0.04600036419493422, + "nauc_mrr_at_1000_diff1": -0.013850702903326623, + "nauc_mrr_at_1000_max": 0.31343287421298904, + "nauc_mrr_at_1000_std": 0.04975337846543717, + "nauc_mrr_at_100_diff1": -0.013868607585728908, + "nauc_mrr_at_100_max": 0.3149081388158546, + "nauc_mrr_at_100_std": 0.04982584041892596, + "nauc_mrr_at_10_diff1": -0.0095390924269391, + "nauc_mrr_at_10_max": 0.3364665409048257, + "nauc_mrr_at_10_std": 0.047407458610126366, + "nauc_mrr_at_1_diff1": -0.01580883633311793, + "nauc_mrr_at_1_max": 0.4057841263158078, + "nauc_mrr_at_1_std": 0.12428711624037517, + "nauc_mrr_at_20_diff1": -0.011497657780061475, + "nauc_mrr_at_20_max": 0.32201847303650305, + "nauc_mrr_at_20_std": 0.04904889889619527, + "nauc_mrr_at_3_diff1": -0.015507495859129323, + "nauc_mrr_at_3_max": 0.34448582240724407, + "nauc_mrr_at_3_std": 0.05306648104668278, + "nauc_mrr_at_5_diff1": -0.0028647590679952355, + "nauc_mrr_at_5_max": 0.35683575673472995, + "nauc_mrr_at_5_std": 0.04600036419493422, + "nauc_ndcg_at_1000_diff1": -0.018317843426227828, + "nauc_ndcg_at_1000_max": 0.2295762200766897, + "nauc_ndcg_at_1000_std": 0.04138581321279402, + "nauc_ndcg_at_100_diff1": -0.02162889640523569, + "nauc_ndcg_at_100_max": 0.2535376202005575, + "nauc_ndcg_at_100_std": 0.051511490622892814, + "nauc_ndcg_at_10_diff1": -0.009067044001193536, + "nauc_ndcg_at_10_max": 0.3163914655620504, + "nauc_ndcg_at_10_std": 0.04224272369072503, + "nauc_ndcg_at_1_diff1": -0.01580883633311793, + "nauc_ndcg_at_1_max": 0.4057841263158078, + "nauc_ndcg_at_1_std": 0.12428711624037517, + "nauc_ndcg_at_20_diff1": -0.0146293572923056, + "nauc_ndcg_at_20_max": 0.2799940769682937, + "nauc_ndcg_at_20_std": 0.04741510583186048, + "nauc_ndcg_at_3_diff1": -0.012698565510666943, + "nauc_ndcg_at_3_max": 0.3350083970119941, + "nauc_ndcg_at_3_std": 0.04400844229763976, + "nauc_ndcg_at_5_diff1": 0.00433845382741301, + "nauc_ndcg_at_5_max": 0.3542448581939863, + "nauc_ndcg_at_5_std": 0.03624456012075268, + "nauc_precision_at_1000_diff1": -0.017220583057661602, + "nauc_precision_at_1000_max": 0.0797031999601713, + "nauc_precision_at_1000_std": 0.013734484068318384, + "nauc_precision_at_100_diff1": -0.03277141174119712, + "nauc_precision_at_100_max": 0.17162271299133533, + "nauc_precision_at_100_std": 0.058169474554807435, + "nauc_precision_at_10_diff1": -0.010139621006638719, + "nauc_precision_at_10_max": 0.28619952329720977, + "nauc_precision_at_10_std": 0.03814720912645494, + "nauc_precision_at_1_diff1": -0.01580883633311793, + "nauc_precision_at_1_max": 0.4057841263158078, + "nauc_precision_at_1_std": 0.12428711624037517, + "nauc_precision_at_20_diff1": -0.02147913249634559, + "nauc_precision_at_20_max": 0.21825341270374315, + "nauc_precision_at_20_std": 0.04954271472457075, + "nauc_precision_at_3_diff1": -0.007578813240374332, + "nauc_precision_at_3_max": 0.3192175467904462, + "nauc_precision_at_3_std": 0.02922726420088891, + "nauc_precision_at_5_diff1": 0.015482209792619972, + "nauc_precision_at_5_max": 0.3516851979392782, + "nauc_precision_at_5_std": 0.022651665545322185, + "nauc_recall_at_1000_diff1": -0.01722058305766113, + "nauc_recall_at_1000_max": 0.0797031999601717, + "nauc_recall_at_1000_std": 0.013734484068318767, + "nauc_recall_at_100_diff1": -0.03277141174119689, + "nauc_recall_at_100_max": 0.17162271299133558, + "nauc_recall_at_100_std": 0.058169474554807456, + "nauc_recall_at_10_diff1": -0.010139621006638753, + "nauc_recall_at_10_max": 0.2861995232972096, + "nauc_recall_at_10_std": 0.03814720912645486, + "nauc_recall_at_1_diff1": -0.01580883633311793, + "nauc_recall_at_1_max": 0.4057841263158078, + "nauc_recall_at_1_std": 0.12428711624037517, + "nauc_recall_at_20_diff1": -0.02147913249634568, + "nauc_recall_at_20_max": 0.21825341270374288, + "nauc_recall_at_20_std": 0.049542714724570655, + "nauc_recall_at_3_diff1": -0.007578813240374362, + "nauc_recall_at_3_max": 0.31921754679044617, + "nauc_recall_at_3_std": 0.02922726420088881, + "nauc_recall_at_5_diff1": 0.015482209792619972, + "nauc_recall_at_5_max": 0.351685197939278, + "nauc_recall_at_5_std": 0.022651665545322008, + "ndcg_at_1": 0.01792, + "ndcg_at_10": 0.07632, + "ndcg_at_100": 0.10642, + "ndcg_at_1000": 0.14242, + "ndcg_at_20": 0.08576, + "ndcg_at_3": 0.0488, + "ndcg_at_5": 0.06353, + "precision_at_1": 0.01792, + "precision_at_10": 0.01468, + "precision_at_100": 0.00298, + "precision_at_1000": 0.0006, + "precision_at_20": 0.00922, + "precision_at_3": 0.02418, + "precision_at_5": 0.0215, + "recall_at_1": 0.01792, + "recall_at_10": 0.14676, + "recall_at_100": 0.29778, + "recall_at_1000": 0.59727, + "recall_at_20": 0.1843, + "recall_at_3": 0.07253, + "recall_at_5": 0.10751 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/AlphaNLI.json b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/AlphaNLI.json new file mode 100644 index 000000000..ae017700b --- /dev/null +++ b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/AlphaNLI.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 55.28659772872925, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.27086, + "map_at_1": 0.17298, + "map_at_10": 0.23902, + "map_at_100": 0.24528, + "map_at_1000": 0.24591, + "map_at_20": 0.2423, + "map_at_3": 0.22476, + "map_at_5": 0.23214, + "mrr_at_1": 0.17297650130548303, + "mrr_at_10": 0.23902099133822355, + "mrr_at_100": 0.24528003876952437, + "mrr_at_1000": 0.24590695556198838, + "mrr_at_20": 0.24230026935079704, + "mrr_at_3": 0.22476066144473458, + "mrr_at_5": 0.23213664055700597, + "nauc_map_at_1000_diff1": 0.4050316460740273, + "nauc_map_at_1000_max": 0.35112729692658085, + "nauc_map_at_1000_std": 0.06474535411752938, + "nauc_map_at_100_diff1": 0.405267350380686, + "nauc_map_at_100_max": 0.3511386236348347, + "nauc_map_at_100_std": 0.06445458837849362, + "nauc_map_at_10_diff1": 0.4075783141947772, + "nauc_map_at_10_max": 0.3532271633808377, + "nauc_map_at_10_std": 0.06110690451741604, + "nauc_map_at_1_diff1": 0.44093006803609697, + "nauc_map_at_1_max": 0.3314420998559394, + "nauc_map_at_1_std": 0.04027429310137797, + "nauc_map_at_20_diff1": 0.40587215681687117, + "nauc_map_at_20_max": 0.3520871595476501, + "nauc_map_at_20_std": 0.06264695269897308, + "nauc_map_at_3_diff1": 0.42209785553198387, + "nauc_map_at_3_max": 0.3553718626979501, + "nauc_map_at_3_std": 0.04763697995755128, + "nauc_map_at_5_diff1": 0.412898298882015, + "nauc_map_at_5_max": 0.35352028509345784, + "nauc_map_at_5_std": 0.05245288039189765, + "nauc_mrr_at_1000_diff1": 0.405031631301937, + "nauc_mrr_at_1000_max": 0.35112728680564187, + "nauc_mrr_at_1000_std": 0.06474535256064472, + "nauc_mrr_at_100_diff1": 0.405267350380686, + "nauc_mrr_at_100_max": 0.3511386236348347, + "nauc_mrr_at_100_std": 0.06445458837849362, + "nauc_mrr_at_10_diff1": 0.4075783141947772, + "nauc_mrr_at_10_max": 0.3532271633808377, + "nauc_mrr_at_10_std": 0.06110690451741604, + "nauc_mrr_at_1_diff1": 0.44093006803609697, + "nauc_mrr_at_1_max": 0.3314420998559394, + "nauc_mrr_at_1_std": 0.04027429310137797, + "nauc_mrr_at_20_diff1": 0.40587215681687117, + "nauc_mrr_at_20_max": 0.3520871595476501, + "nauc_mrr_at_20_std": 0.06264695269897308, + "nauc_mrr_at_3_diff1": 0.42209785553198387, + "nauc_mrr_at_3_max": 0.3553718626979501, + "nauc_mrr_at_3_std": 0.04763697995755128, + "nauc_mrr_at_5_diff1": 0.412898298882015, + "nauc_mrr_at_5_max": 0.35352028509345784, + "nauc_mrr_at_5_std": 0.05245288039189765, + "nauc_ndcg_at_1000_diff1": 0.37482522323994266, + "nauc_ndcg_at_1000_max": 0.34840460737406276, + "nauc_ndcg_at_1000_std": 0.10263181564767138, + "nauc_ndcg_at_100_diff1": 0.37941237732591176, + "nauc_ndcg_at_100_max": 0.34722952387779876, + "nauc_ndcg_at_100_std": 0.09740750147377758, + "nauc_ndcg_at_10_diff1": 0.3880756117662661, + "nauc_ndcg_at_10_max": 0.35768166893229547, + "nauc_ndcg_at_10_std": 0.07896583737171556, + "nauc_ndcg_at_1_diff1": 0.44093006803609697, + "nauc_ndcg_at_1_max": 0.3314420998559394, + "nauc_ndcg_at_1_std": 0.04027429310137797, + "nauc_ndcg_at_20_diff1": 0.38227205937003944, + "nauc_ndcg_at_20_max": 0.35363437292691113, + "nauc_ndcg_at_20_std": 0.08390550440052634, + "nauc_ndcg_at_3_diff1": 0.41621896837462935, + "nauc_ndcg_at_3_max": 0.36109660599883836, + "nauc_ndcg_at_3_std": 0.04946300124415147, + "nauc_ndcg_at_5_diff1": 0.4007903152548472, + "nauc_ndcg_at_5_max": 0.3578169727076494, + "nauc_ndcg_at_5_std": 0.058037162508292495, + "nauc_precision_at_1000_diff1": 0.236361390843889, + "nauc_precision_at_1000_max": 0.3289768836242905, + "nauc_precision_at_1000_std": 0.2999983857788411, + "nauc_precision_at_100_diff1": 0.2980846000221865, + "nauc_precision_at_100_max": 0.32217063481058783, + "nauc_precision_at_100_std": 0.22165405931789772, + "nauc_precision_at_10_diff1": 0.33425150001903975, + "nauc_precision_at_10_max": 0.36828314879900304, + "nauc_precision_at_10_std": 0.13129303932128944, + "nauc_precision_at_1_diff1": 0.44093006803609697, + "nauc_precision_at_1_max": 0.3314420998559394, + "nauc_precision_at_1_std": 0.04027429310137797, + "nauc_precision_at_20_diff1": 0.31472363809860937, + "nauc_precision_at_20_max": 0.35405534936231803, + "nauc_precision_at_20_std": 0.1473378464574554, + "nauc_precision_at_3_diff1": 0.40115604241099406, + "nauc_precision_at_3_max": 0.3753390949900163, + "nauc_precision_at_3_std": 0.0540264885872957, + "nauc_precision_at_5_diff1": 0.3689894370114384, + "nauc_precision_at_5_max": 0.36780692344557275, + "nauc_precision_at_5_std": 0.07302550601146121, + "nauc_recall_at_1000_diff1": 0.2363613908438888, + "nauc_recall_at_1000_max": 0.3289768836242918, + "nauc_recall_at_1000_std": 0.2999983857788421, + "nauc_recall_at_100_diff1": 0.2980846000221865, + "nauc_recall_at_100_max": 0.32217063481058744, + "nauc_recall_at_100_std": 0.22165405931789744, + "nauc_recall_at_10_diff1": 0.3342515000190401, + "nauc_recall_at_10_max": 0.3682831487990031, + "nauc_recall_at_10_std": 0.13129303932128938, + "nauc_recall_at_1_diff1": 0.44093006803609697, + "nauc_recall_at_1_max": 0.3314420998559394, + "nauc_recall_at_1_std": 0.04027429310137797, + "nauc_recall_at_20_diff1": 0.31472363809860937, + "nauc_recall_at_20_max": 0.3540553493623181, + "nauc_recall_at_20_std": 0.1473378464574555, + "nauc_recall_at_3_diff1": 0.40115604241099434, + "nauc_recall_at_3_max": 0.3753390949900163, + "nauc_recall_at_3_std": 0.05402648858729579, + "nauc_recall_at_5_diff1": 0.36898943701143866, + "nauc_recall_at_5_max": 0.367806923445573, + "nauc_recall_at_5_std": 0.07302550601146114, + "ndcg_at_1": 0.17298, + "ndcg_at_10": 0.27086, + "ndcg_at_100": 0.3059, + "ndcg_at_1000": 0.32553, + "ndcg_at_20": 0.28287, + "ndcg_at_3": 0.2407, + "ndcg_at_5": 0.25394, + "precision_at_1": 0.17298, + "precision_at_10": 0.03714, + "precision_at_100": 0.00546, + "precision_at_1000": 0.00071, + "precision_at_20": 0.02095, + "precision_at_3": 0.09552, + "precision_at_5": 0.06371, + "recall_at_1": 0.17298, + "recall_at_10": 0.37141, + "recall_at_100": 0.54634, + "recall_at_1000": 0.70692, + "recall_at_20": 0.41906, + "recall_at_3": 0.28655, + "recall_at_5": 0.31854 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/PIQA.json b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/PIQA.json new file mode 100644 index 000000000..4434d1801 --- /dev/null +++ b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/PIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 17.774213790893555, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.2173, + "map_at_1": 0.10501, + "map_at_10": 0.18006, + "map_at_100": 0.1883, + "map_at_1000": 0.18891, + "map_at_20": 0.18512, + "map_at_3": 0.16023, + "map_at_5": 0.17239, + "mrr_at_1": 0.10500544069640914, + "mrr_at_10": 0.18005574554812834, + "mrr_at_100": 0.1883030857408693, + "mrr_at_1000": 0.1889076010443501, + "mrr_at_20": 0.18512493328282353, + "mrr_at_3": 0.1602285092491839, + "mrr_at_5": 0.17238846572361244, + "nauc_map_at_1000_diff1": 0.07591931653439235, + "nauc_map_at_1000_max": 0.2953087857513961, + "nauc_map_at_1000_std": 0.02868850269134595, + "nauc_map_at_100_diff1": 0.07611753925226203, + "nauc_map_at_100_max": 0.29552204562152823, + "nauc_map_at_100_std": 0.028898872701212573, + "nauc_map_at_10_diff1": 0.07899181697057596, + "nauc_map_at_10_max": 0.2962446856330825, + "nauc_map_at_10_std": 0.025444290954972117, + "nauc_map_at_1_diff1": 0.0976433572478846, + "nauc_map_at_1_max": 0.2604937436392378, + "nauc_map_at_1_std": -0.024618410405720638, + "nauc_map_at_20_diff1": 0.07737515000539463, + "nauc_map_at_20_max": 0.2961213236410303, + "nauc_map_at_20_std": 0.027349185680960408, + "nauc_map_at_3_diff1": 0.07998778845148533, + "nauc_map_at_3_max": 0.29785004160128226, + "nauc_map_at_3_std": 0.016620363826652412, + "nauc_map_at_5_diff1": 0.0797889752551689, + "nauc_map_at_5_max": 0.2934852471230759, + "nauc_map_at_5_std": 0.020155894952402525, + "nauc_mrr_at_1000_diff1": 0.07591931653439235, + "nauc_mrr_at_1000_max": 0.2953087857513961, + "nauc_mrr_at_1000_std": 0.02868850269134595, + "nauc_mrr_at_100_diff1": 0.07611753925226203, + "nauc_mrr_at_100_max": 0.29552204562152823, + "nauc_mrr_at_100_std": 0.028898872701212573, + "nauc_mrr_at_10_diff1": 0.07899181697057596, + "nauc_mrr_at_10_max": 0.2962446856330825, + "nauc_mrr_at_10_std": 0.025444290954972117, + "nauc_mrr_at_1_diff1": 0.0976433572478846, + "nauc_mrr_at_1_max": 0.2604937436392378, + "nauc_mrr_at_1_std": -0.024618410405720638, + "nauc_mrr_at_20_diff1": 0.07737515000539463, + "nauc_mrr_at_20_max": 0.2961213236410303, + "nauc_mrr_at_20_std": 0.027349185680960408, + "nauc_mrr_at_3_diff1": 0.07998778845148533, + "nauc_mrr_at_3_max": 0.29785004160128226, + "nauc_mrr_at_3_std": 0.016620363826652412, + "nauc_mrr_at_5_diff1": 0.0797889752551689, + "nauc_mrr_at_5_max": 0.2934852471230759, + "nauc_mrr_at_5_std": 0.020155894952402525, + "nauc_ndcg_at_1000_diff1": 0.05445078564680303, + "nauc_ndcg_at_1000_max": 0.29289397672643286, + "nauc_ndcg_at_1000_std": 0.054047122422559574, + "nauc_ndcg_at_100_diff1": 0.05819169346236468, + "nauc_ndcg_at_100_max": 0.2979444738360693, + "nauc_ndcg_at_100_std": 0.06143030032675404, + "nauc_ndcg_at_10_diff1": 0.07502853799034458, + "nauc_ndcg_at_10_max": 0.304168348832182, + "nauc_ndcg_at_10_std": 0.04484930696615589, + "nauc_ndcg_at_1_diff1": 0.0976433572478846, + "nauc_ndcg_at_1_max": 0.2604937436392378, + "nauc_ndcg_at_1_std": -0.024618410405720638, + "nauc_ndcg_at_20_diff1": 0.06835983130185981, + "nauc_ndcg_at_20_max": 0.30398448902964387, + "nauc_ndcg_at_20_std": 0.05197796554822873, + "nauc_ndcg_at_3_diff1": 0.07703035704808275, + "nauc_ndcg_at_3_max": 0.30542058022654767, + "nauc_ndcg_at_3_std": 0.02685855633377791, + "nauc_ndcg_at_5_diff1": 0.07659898732827841, + "nauc_ndcg_at_5_max": 0.2977064882736323, + "nauc_ndcg_at_5_std": 0.03201489649214358, + "nauc_precision_at_1000_diff1": -0.04746185224321635, + "nauc_precision_at_1000_max": 0.2516206948113974, + "nauc_precision_at_1000_std": 0.11603203442282103, + "nauc_precision_at_100_diff1": -0.003700919726563919, + "nauc_precision_at_100_max": 0.292382862356361, + "nauc_precision_at_100_std": 0.1551927186845684, + "nauc_precision_at_10_diff1": 0.0665829070268933, + "nauc_precision_at_10_max": 0.3215365724657946, + "nauc_precision_at_10_std": 0.09000386044460425, + "nauc_precision_at_1_diff1": 0.0976433572478846, + "nauc_precision_at_1_max": 0.2604937436392378, + "nauc_precision_at_1_std": -0.024618410405720638, + "nauc_precision_at_20_diff1": 0.04449554664919431, + "nauc_precision_at_20_max": 0.32100492203671177, + "nauc_precision_at_20_std": 0.11196417632127974, + "nauc_precision_at_3_diff1": 0.07060162239661805, + "nauc_precision_at_3_max": 0.32233856575546327, + "nauc_precision_at_3_std": 0.050284344020636, + "nauc_precision_at_5_diff1": 0.06989329742403648, + "nauc_precision_at_5_max": 0.3055225530408722, + "nauc_precision_at_5_std": 0.0578510970344075, + "nauc_recall_at_1000_diff1": -0.04746185224321616, + "nauc_recall_at_1000_max": 0.2516206948113973, + "nauc_recall_at_1000_std": 0.11603203442282217, + "nauc_recall_at_100_diff1": -0.0037009197265642185, + "nauc_recall_at_100_max": 0.2923828623563606, + "nauc_recall_at_100_std": 0.15519271868456855, + "nauc_recall_at_10_diff1": 0.06658290702689332, + "nauc_recall_at_10_max": 0.3215365724657945, + "nauc_recall_at_10_std": 0.09000386044460443, + "nauc_recall_at_1_diff1": 0.0976433572478846, + "nauc_recall_at_1_max": 0.2604937436392378, + "nauc_recall_at_1_std": -0.024618410405720638, + "nauc_recall_at_20_diff1": 0.044495546649194306, + "nauc_recall_at_20_max": 0.3210049220367118, + "nauc_recall_at_20_std": 0.11196417632127967, + "nauc_recall_at_3_diff1": 0.07060162239661837, + "nauc_recall_at_3_max": 0.32233856575546355, + "nauc_recall_at_3_std": 0.05028434402063637, + "nauc_recall_at_5_diff1": 0.06989329742403644, + "nauc_recall_at_5_max": 0.30552255304087217, + "nauc_recall_at_5_std": 0.05785109703440752, + "ndcg_at_1": 0.10501, + "ndcg_at_10": 0.2173, + "ndcg_at_100": 0.25917, + "ndcg_at_1000": 0.27811, + "ndcg_at_20": 0.23557, + "ndcg_at_3": 0.17728, + "ndcg_at_5": 0.1991, + "precision_at_1": 0.10501, + "precision_at_10": 0.03346, + "precision_at_100": 0.00535, + "precision_at_1000": 0.00069, + "precision_at_20": 0.02032, + "precision_at_3": 0.07544, + "precision_at_5": 0.05582, + "recall_at_1": 0.10501, + "recall_at_10": 0.3346, + "recall_at_100": 0.53482, + "recall_at_1000": 0.69042, + "recall_at_20": 0.40642, + "recall_at_3": 0.22633, + "recall_at_5": 0.27911 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/Quail.json b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/Quail.json new file mode 100644 index 000000000..14c9e27fe --- /dev/null +++ b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/Quail.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 26.93253993988037, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.04918, + "map_at_1": 0.01544, + "map_at_10": 0.03511, + "map_at_100": 0.04115, + "map_at_1000": 0.04206, + "map_at_20": 0.03828, + "map_at_3": 0.02635, + "map_at_5": 0.02993, + "mrr_at_1": 0.015441176470588236, + "mrr_at_10": 0.03511087768440709, + "mrr_at_100": 0.04115627382970709, + "mrr_at_1000": 0.04206451881378511, + "mrr_at_20": 0.038280467701651236, + "mrr_at_3": 0.02634803921568628, + "mrr_at_5": 0.029932598039215694, + "nauc_map_at_1000_diff1": 0.08889019549820741, + "nauc_map_at_1000_max": 0.1464774350643247, + "nauc_map_at_1000_std": 0.09792667215920507, + "nauc_map_at_100_diff1": 0.08983892765195002, + "nauc_map_at_100_max": 0.14791659623703723, + "nauc_map_at_100_std": 0.0984510225402992, + "nauc_map_at_10_diff1": 0.09459820027839799, + "nauc_map_at_10_max": 0.14936901475366318, + "nauc_map_at_10_std": 0.09502347926750661, + "nauc_map_at_1_diff1": 0.17852351565794003, + "nauc_map_at_1_max": 0.23712420304853893, + "nauc_map_at_1_std": 0.1555955894566037, + "nauc_map_at_20_diff1": 0.09107663958654146, + "nauc_map_at_20_max": 0.14392996902195893, + "nauc_map_at_20_std": 0.09232946967585468, + "nauc_map_at_3_diff1": 0.10381190682698851, + "nauc_map_at_3_max": 0.16464018070522454, + "nauc_map_at_3_std": 0.1048283737153768, + "nauc_map_at_5_diff1": 0.11420196035513888, + "nauc_map_at_5_max": 0.163995782800494, + "nauc_map_at_5_std": 0.10211258187027138, + "nauc_mrr_at_1000_diff1": 0.0889147276835571, + "nauc_mrr_at_1000_max": 0.14648188665920547, + "nauc_mrr_at_1000_std": 0.09793304849705335, + "nauc_mrr_at_100_diff1": 0.08986405660008849, + "nauc_mrr_at_100_max": 0.14792053621722803, + "nauc_mrr_at_100_std": 0.09845740529156807, + "nauc_mrr_at_10_diff1": 0.09459820027839799, + "nauc_mrr_at_10_max": 0.14936901475366318, + "nauc_mrr_at_10_std": 0.09502347926750661, + "nauc_mrr_at_1_diff1": 0.17852351565794003, + "nauc_mrr_at_1_max": 0.23712420304853893, + "nauc_mrr_at_1_std": 0.1555955894566037, + "nauc_mrr_at_20_diff1": 0.09108512172396849, + "nauc_mrr_at_20_max": 0.1439246320325195, + "nauc_mrr_at_20_std": 0.09233792512526329, + "nauc_mrr_at_3_diff1": 0.10381190682698851, + "nauc_mrr_at_3_max": 0.16464018070522454, + "nauc_mrr_at_3_std": 0.1048283737153768, + "nauc_mrr_at_5_diff1": 0.11420196035513888, + "nauc_mrr_at_5_max": 0.163995782800494, + "nauc_mrr_at_5_std": 0.10211258187027138, + "nauc_ndcg_at_1000_diff1": 0.05645176987956921, + "nauc_ndcg_at_1000_max": 0.12284694953424079, + "nauc_ndcg_at_1000_std": 0.1042830850195271, + "nauc_ndcg_at_100_diff1": 0.06670463081384014, + "nauc_ndcg_at_100_max": 0.14437056751109473, + "nauc_ndcg_at_100_std": 0.10989256228121541, + "nauc_ndcg_at_10_diff1": 0.07316561794722444, + "nauc_ndcg_at_10_max": 0.1326915236033066, + "nauc_ndcg_at_10_std": 0.08556294400371348, + "nauc_ndcg_at_1_diff1": 0.17852351565794003, + "nauc_ndcg_at_1_max": 0.23712420304853893, + "nauc_ndcg_at_1_std": 0.1555955894566037, + "nauc_ndcg_at_20_diff1": 0.06944396908829671, + "nauc_ndcg_at_20_max": 0.125288139601863, + "nauc_ndcg_at_20_std": 0.08320566905735483, + "nauc_ndcg_at_3_diff1": 0.08980847274745442, + "nauc_ndcg_at_3_max": 0.15333233526873297, + "nauc_ndcg_at_3_std": 0.09803385850023554, + "nauc_ndcg_at_5_diff1": 0.10745136342483516, + "nauc_ndcg_at_5_max": 0.15417121119247312, + "nauc_ndcg_at_5_std": 0.09530933128803894, + "nauc_precision_at_1000_diff1": 0.023163428410440126, + "nauc_precision_at_1000_max": 0.09006043484130206, + "nauc_precision_at_1000_std": 0.11557258539429355, + "nauc_precision_at_100_diff1": 0.04808889933003799, + "nauc_precision_at_100_max": 0.15037159555926644, + "nauc_precision_at_100_std": 0.1305055456258817, + "nauc_precision_at_10_diff1": 0.045240951655466634, + "nauc_precision_at_10_max": 0.11277238583105378, + "nauc_precision_at_10_std": 0.07463297239672811, + "nauc_precision_at_1_diff1": 0.17852351565794003, + "nauc_precision_at_1_max": 0.23712420304853893, + "nauc_precision_at_1_std": 0.1555955894566037, + "nauc_precision_at_20_diff1": 0.047164362130130075, + "nauc_precision_at_20_max": 0.10762466196441356, + "nauc_precision_at_20_std": 0.07571765476276911, + "nauc_precision_at_3_diff1": 0.06332654092246247, + "nauc_precision_at_3_max": 0.13240608464649253, + "nauc_precision_at_3_std": 0.08573182788369271, + "nauc_precision_at_5_diff1": 0.09804623038733422, + "nauc_precision_at_5_max": 0.13915588594797554, + "nauc_precision_at_5_std": 0.08495504453458355, + "nauc_recall_at_1000_diff1": 0.023163428410440348, + "nauc_recall_at_1000_max": 0.09006043484130243, + "nauc_recall_at_1000_std": 0.11557258539429384, + "nauc_recall_at_100_diff1": 0.048088899330037994, + "nauc_recall_at_100_max": 0.15037159555926632, + "nauc_recall_at_100_std": 0.13050554562588149, + "nauc_recall_at_10_diff1": 0.04524095165546641, + "nauc_recall_at_10_max": 0.11277238583105363, + "nauc_recall_at_10_std": 0.07463297239672799, + "nauc_recall_at_1_diff1": 0.17852351565794003, + "nauc_recall_at_1_max": 0.23712420304853893, + "nauc_recall_at_1_std": 0.1555955894566037, + "nauc_recall_at_20_diff1": 0.04716436213013001, + "nauc_recall_at_20_max": 0.10762466196441328, + "nauc_recall_at_20_std": 0.07571765476276887, + "nauc_recall_at_3_diff1": 0.06332654092246245, + "nauc_recall_at_3_max": 0.13240608464649256, + "nauc_recall_at_3_std": 0.08573182788369274, + "nauc_recall_at_5_diff1": 0.0980462303873343, + "nauc_recall_at_5_max": 0.13915588594797548, + "nauc_recall_at_5_std": 0.08495504453458336, + "ndcg_at_1": 0.01544, + "ndcg_at_10": 0.04918, + "ndcg_at_100": 0.08268, + "ndcg_at_1000": 0.11111, + "ndcg_at_20": 0.06077, + "ndcg_at_3": 0.03005, + "ndcg_at_5": 0.03646, + "precision_at_1": 0.01544, + "precision_at_10": 0.0096, + "precision_at_100": 0.00262, + "precision_at_1000": 0.0005, + "precision_at_20": 0.0071, + "precision_at_3": 0.0136, + "precision_at_5": 0.01125, + "recall_at_1": 0.01544, + "recall_at_10": 0.09596, + "recall_at_100": 0.2625, + "recall_at_1000": 0.49559, + "recall_at_20": 0.14191, + "recall_at_3": 0.04081, + "recall_at_5": 0.05625 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/RARbCode.json b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/RARbCode.json new file mode 100644 index 000000000..9cae04a46 --- /dev/null +++ b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/RARbCode.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 956.2811398506165, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07122, + "map_at_1": 0.03841, + "map_at_10": 0.05919, + "map_at_100": 0.06308, + "map_at_1000": 0.06372, + "map_at_20": 0.06095, + "map_at_3": 0.05245, + "map_at_5": 0.05582, + "mrr_at_1": 0.03840970350404313, + "mrr_at_10": 0.05918821931288243, + "mrr_at_100": 0.06308178071196151, + "mrr_at_1000": 0.06372340492243873, + "mrr_at_20": 0.06094996237673969, + "mrr_at_3": 0.052448337825696315, + "mrr_at_5": 0.0558176100628931, + "nauc_map_at_1000_diff1": 0.2521955343391825, + "nauc_map_at_1000_max": -0.15210657922331686, + "nauc_map_at_1000_std": -0.1415375431364946, + "nauc_map_at_100_diff1": 0.25338028924480943, + "nauc_map_at_100_max": -0.15156265768848956, + "nauc_map_at_100_std": -0.1411912769409258, + "nauc_map_at_10_diff1": 0.265084159005705, + "nauc_map_at_10_max": -0.1497505168395373, + "nauc_map_at_10_std": -0.14296376202995792, + "nauc_map_at_1_diff1": 0.4275875266192091, + "nauc_map_at_1_max": -0.20344309348681208, + "nauc_map_at_1_std": -0.20634464385054033, + "nauc_map_at_20_diff1": 0.2589285283962237, + "nauc_map_at_20_max": -0.1493637645943407, + "nauc_map_at_20_std": -0.14097391374607726, + "nauc_map_at_3_diff1": 0.29808652135597935, + "nauc_map_at_3_max": -0.16308202079998077, + "nauc_map_at_3_std": -0.1607467349198526, + "nauc_map_at_5_diff1": 0.287596947954514, + "nauc_map_at_5_max": -0.14905986266833765, + "nauc_map_at_5_std": -0.1455381325281949, + "nauc_mrr_at_1000_diff1": 0.2521955343391825, + "nauc_mrr_at_1000_max": -0.15210657922331686, + "nauc_mrr_at_1000_std": -0.1415375431364946, + "nauc_mrr_at_100_diff1": 0.25338028924480943, + "nauc_mrr_at_100_max": -0.15156265768848956, + "nauc_mrr_at_100_std": -0.1411912769409258, + "nauc_mrr_at_10_diff1": 0.265084159005705, + "nauc_mrr_at_10_max": -0.1497505168395373, + "nauc_mrr_at_10_std": -0.14296376202995792, + "nauc_mrr_at_1_diff1": 0.4275875266192091, + "nauc_mrr_at_1_max": -0.20344309348681208, + "nauc_mrr_at_1_std": -0.20634464385054033, + "nauc_mrr_at_20_diff1": 0.2589285283962237, + "nauc_mrr_at_20_max": -0.1493637645943407, + "nauc_mrr_at_20_std": -0.14097391374607726, + "nauc_mrr_at_3_diff1": 0.29808652135597935, + "nauc_mrr_at_3_max": -0.16308202079998077, + "nauc_mrr_at_3_std": -0.1607467349198526, + "nauc_mrr_at_5_diff1": 0.287596947954514, + "nauc_mrr_at_5_max": -0.14905986266833765, + "nauc_mrr_at_5_std": -0.1455381325281949, + "nauc_ndcg_at_1000_diff1": 0.1542913790043396, + "nauc_ndcg_at_1000_max": -0.168586312142756, + "nauc_ndcg_at_1000_std": -0.1371641805333142, + "nauc_ndcg_at_100_diff1": 0.17683013957619814, + "nauc_ndcg_at_100_max": -0.15519631906248066, + "nauc_ndcg_at_100_std": -0.12879786160298473, + "nauc_ndcg_at_10_diff1": 0.21218562724076326, + "nauc_ndcg_at_10_max": -0.1366726201691105, + "nauc_ndcg_at_10_std": -0.12423490375804028, + "nauc_ndcg_at_1_diff1": 0.4275875266192091, + "nauc_ndcg_at_1_max": -0.20344309348681208, + "nauc_ndcg_at_1_std": -0.20634464385054033, + "nauc_ndcg_at_20_diff1": 0.19788102977667535, + "nauc_ndcg_at_20_max": -0.1378267137128995, + "nauc_ndcg_at_20_std": -0.1211151091633466, + "nauc_ndcg_at_3_diff1": 0.26978686120439366, + "nauc_ndcg_at_3_max": -0.15225180973727498, + "nauc_ndcg_at_3_std": -0.14827110438197663, + "nauc_ndcg_at_5_diff1": 0.2553940194853697, + "nauc_ndcg_at_5_max": -0.13265770619880274, + "nauc_ndcg_at_5_std": -0.12687666393980904, + "nauc_precision_at_1000_diff1": 0.009794690128572411, + "nauc_precision_at_1000_max": -0.22293791287183604, + "nauc_precision_at_1000_std": -0.1558371325363893, + "nauc_precision_at_100_diff1": 0.07131004358904726, + "nauc_precision_at_100_max": -0.17812356634289786, + "nauc_precision_at_100_std": -0.125274830720807, + "nauc_precision_at_10_diff1": 0.11585910600087215, + "nauc_precision_at_10_max": -0.11614946750228622, + "nauc_precision_at_10_std": -0.09273544818151506, + "nauc_precision_at_1_diff1": 0.4275875266192091, + "nauc_precision_at_1_max": -0.20344309348681208, + "nauc_precision_at_1_std": -0.20634464385054033, + "nauc_precision_at_20_diff1": 0.09578354253849179, + "nauc_precision_at_20_max": -0.12364021064394053, + "nauc_precision_at_20_std": -0.09166444263839721, + "nauc_precision_at_3_diff1": 0.20969010302398775, + "nauc_precision_at_3_max": -0.12876025641396344, + "nauc_precision_at_3_std": -0.12116256652713343, + "nauc_precision_at_5_diff1": 0.19307601210720074, + "nauc_precision_at_5_max": -0.10031827816201219, + "nauc_precision_at_5_std": -0.08996695674993647, + "nauc_recall_at_1000_diff1": 0.009794690128572956, + "nauc_recall_at_1000_max": -0.22293791287183568, + "nauc_recall_at_1000_std": -0.1558371325363887, + "nauc_recall_at_100_diff1": 0.07131004358904718, + "nauc_recall_at_100_max": -0.17812356634289792, + "nauc_recall_at_100_std": -0.12527483072080692, + "nauc_recall_at_10_diff1": 0.11585910600087204, + "nauc_recall_at_10_max": -0.11614946750228634, + "nauc_recall_at_10_std": -0.09273544818151516, + "nauc_recall_at_1_diff1": 0.4275875266192091, + "nauc_recall_at_1_max": -0.20344309348681208, + "nauc_recall_at_1_std": -0.20634464385054033, + "nauc_recall_at_20_diff1": 0.09578354253849168, + "nauc_recall_at_20_max": -0.12364021064394068, + "nauc_recall_at_20_std": -0.0916644426383973, + "nauc_recall_at_3_diff1": 0.20969010302398813, + "nauc_recall_at_3_max": -0.12876025641396308, + "nauc_recall_at_3_std": -0.12116256652713299, + "nauc_recall_at_5_diff1": 0.1930760121072007, + "nauc_recall_at_5_max": -0.10031827816201229, + "nauc_recall_at_5_std": -0.08996695674993647, + "ndcg_at_1": 0.03841, + "ndcg_at_10": 0.07122, + "ndcg_at_100": 0.09357, + "ndcg_at_1000": 0.11499, + "ndcg_at_20": 0.07768, + "ndcg_at_3": 0.0573, + "ndcg_at_5": 0.06325, + "precision_at_1": 0.03841, + "precision_at_10": 0.01098, + "precision_at_100": 0.00222, + "precision_at_1000": 0.0004, + "precision_at_20": 0.00677, + "precision_at_3": 0.02381, + "precision_at_5": 0.01712, + "recall_at_1": 0.03841, + "recall_at_10": 0.10984, + "recall_at_100": 0.22237, + "recall_at_1000": 0.40094, + "recall_at_20": 0.13544, + "recall_at_3": 0.07143, + "recall_at_5": 0.08558 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/RARbMath.json b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/RARbMath.json new file mode 100644 index 000000000..0bb04b774 --- /dev/null +++ b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/RARbMath.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 1472.5339450836182, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.21835, + "map_at_1": 0.18626, + "map_at_10": 0.20604, + "map_at_100": 0.2101, + "map_at_1000": 0.21084, + "map_at_20": 0.20806, + "map_at_3": 0.19887, + "map_at_5": 0.20271, + "mrr_at_1": 0.18626364931159994, + "mrr_at_10": 0.2060374104803604, + "mrr_at_100": 0.21010468303521612, + "mrr_at_1000": 0.2108405607879488, + "mrr_at_20": 0.20806416603755773, + "mrr_at_3": 0.19887112939811155, + "mrr_at_5": 0.20270876193490547, + "nauc_map_at_1000_diff1": 0.7370231241600175, + "nauc_map_at_1000_max": 0.2679148381188134, + "nauc_map_at_1000_std": 0.14780122808153184, + "nauc_map_at_100_diff1": 0.737517066644068, + "nauc_map_at_100_max": 0.26801843961191685, + "nauc_map_at_100_std": 0.14745872983496808, + "nauc_map_at_10_diff1": 0.7457543123937718, + "nauc_map_at_10_max": 0.2710536549886601, + "nauc_map_at_10_std": 0.14620852820863492, + "nauc_map_at_1_diff1": 0.8017395490240417, + "nauc_map_at_1_max": 0.2885247282534555, + "nauc_map_at_1_std": 0.14323807155701498, + "nauc_map_at_20_diff1": 0.7409091309835212, + "nauc_map_at_20_max": 0.2692921780725845, + "nauc_map_at_20_std": 0.14676689095996787, + "nauc_map_at_3_diff1": 0.761247300198119, + "nauc_map_at_3_max": 0.27519394449762247, + "nauc_map_at_3_std": 0.14378083711422124, + "nauc_map_at_5_diff1": 0.7531919724048645, + "nauc_map_at_5_max": 0.27372150055263966, + "nauc_map_at_5_std": 0.14494074078764202, + "nauc_mrr_at_1000_diff1": 0.7370231081039941, + "nauc_mrr_at_1000_max": 0.26791482059990884, + "nauc_mrr_at_1000_std": 0.14780122542400992, + "nauc_mrr_at_100_diff1": 0.737517066644068, + "nauc_mrr_at_100_max": 0.26801843961191685, + "nauc_mrr_at_100_std": 0.14745872983496808, + "nauc_mrr_at_10_diff1": 0.7457543123937718, + "nauc_mrr_at_10_max": 0.2710536549886601, + "nauc_mrr_at_10_std": 0.14620852820863492, + "nauc_mrr_at_1_diff1": 0.8017395490240417, + "nauc_mrr_at_1_max": 0.2885247282534555, + "nauc_mrr_at_1_std": 0.14323807155701498, + "nauc_mrr_at_20_diff1": 0.7409091309835212, + "nauc_mrr_at_20_max": 0.2692921780725845, + "nauc_mrr_at_20_std": 0.14676689095996787, + "nauc_mrr_at_3_diff1": 0.761247300198119, + "nauc_mrr_at_3_max": 0.27519394449762247, + "nauc_mrr_at_3_std": 0.14378083711422124, + "nauc_mrr_at_5_diff1": 0.7531919724048645, + "nauc_mrr_at_5_max": 0.27372150055263966, + "nauc_mrr_at_5_std": 0.14494074078764202, + "nauc_ndcg_at_1000_diff1": 0.6663280275785286, + "nauc_ndcg_at_1000_max": 0.25104045937838465, + "nauc_ndcg_at_1000_std": 0.17089384890025994, + "nauc_ndcg_at_100_diff1": 0.6769032883250671, + "nauc_ndcg_at_100_max": 0.2467326459795287, + "nauc_ndcg_at_100_std": 0.15627577088371422, + "nauc_ndcg_at_10_diff1": 0.7169991271397482, + "nauc_ndcg_at_10_max": 0.26197162938577856, + "nauc_ndcg_at_10_std": 0.148752394621319, + "nauc_ndcg_at_1_diff1": 0.8017395490240417, + "nauc_ndcg_at_1_max": 0.2885247282534555, + "nauc_ndcg_at_1_std": 0.14323807155701498, + "nauc_ndcg_at_20_diff1": 0.700226713675784, + "nauc_ndcg_at_20_max": 0.25601339824156, + "nauc_ndcg_at_20_std": 0.15074466461296046, + "nauc_ndcg_at_3_diff1": 0.7487957626557432, + "nauc_ndcg_at_3_max": 0.27107486872355624, + "nauc_ndcg_at_3_std": 0.14386899298531283, + "nauc_ndcg_at_5_diff1": 0.7344270200930225, + "nauc_ndcg_at_5_max": 0.2683335582563377, + "nauc_ndcg_at_5_std": 0.14578464897305332, + "nauc_precision_at_1000_diff1": 0.3817685616050309, + "nauc_precision_at_1000_max": 0.21344594308075207, + "nauc_precision_at_1000_std": 0.3131056166819925, + "nauc_precision_at_100_diff1": 0.47813170789940257, + "nauc_precision_at_100_max": 0.17474746129195898, + "nauc_precision_at_100_std": 0.1889373758259278, + "nauc_precision_at_10_diff1": 0.6341899584055569, + "nauc_precision_at_10_max": 0.23556537839949435, + "nauc_precision_at_10_std": 0.15651814518819945, + "nauc_precision_at_1_diff1": 0.8017395490240417, + "nauc_precision_at_1_max": 0.2885247282534555, + "nauc_precision_at_1_std": 0.14323807155701498, + "nauc_precision_at_20_diff1": 0.5791499228353385, + "nauc_precision_at_20_max": 0.21615731816871037, + "nauc_precision_at_20_std": 0.16326438032471358, + "nauc_precision_at_3_diff1": 0.7144117236530398, + "nauc_precision_at_3_max": 0.25969444787782664, + "nauc_precision_at_3_std": 0.14408902859100586, + "nauc_precision_at_5_diff1": 0.6818027423989761, + "nauc_precision_at_5_max": 0.25332767910887555, + "nauc_precision_at_5_std": 0.14819811400503838, + "nauc_recall_at_1000_diff1": 0.38176856160503175, + "nauc_recall_at_1000_max": 0.21344594308075307, + "nauc_recall_at_1000_std": 0.313105616681994, + "nauc_recall_at_100_diff1": 0.47813170789940246, + "nauc_recall_at_100_max": 0.17474746129195895, + "nauc_recall_at_100_std": 0.18893737582592748, + "nauc_recall_at_10_diff1": 0.6341899584055569, + "nauc_recall_at_10_max": 0.23556537839949432, + "nauc_recall_at_10_std": 0.1565181451881994, + "nauc_recall_at_1_diff1": 0.8017395490240417, + "nauc_recall_at_1_max": 0.2885247282534555, + "nauc_recall_at_1_std": 0.14323807155701498, + "nauc_recall_at_20_diff1": 0.5791499228353385, + "nauc_recall_at_20_max": 0.21615731816871078, + "nauc_recall_at_20_std": 0.1632643803247139, + "nauc_recall_at_3_diff1": 0.71441172365304, + "nauc_recall_at_3_max": 0.25969444787782675, + "nauc_recall_at_3_std": 0.14408902859100595, + "nauc_recall_at_5_diff1": 0.6818027423989763, + "nauc_recall_at_5_max": 0.2533276791088755, + "nauc_recall_at_5_std": 0.1481981140050384, + "ndcg_at_1": 0.18626, + "ndcg_at_10": 0.21835, + "ndcg_at_100": 0.24193, + "ndcg_at_1000": 0.26655, + "ndcg_at_20": 0.22586, + "ndcg_at_3": 0.20314, + "ndcg_at_5": 0.21019, + "precision_at_1": 0.18626, + "precision_at_10": 0.02584, + "precision_at_100": 0.00378, + "precision_at_1000": 0.00058, + "precision_at_20": 0.01442, + "precision_at_3": 0.07185, + "precision_at_5": 0.04659, + "recall_at_1": 0.18626, + "recall_at_10": 0.25843, + "recall_at_100": 0.37759, + "recall_at_1000": 0.58285, + "recall_at_20": 0.28834, + "recall_at_3": 0.21554, + "recall_at_5": 0.23295 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/SIQA.json b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/SIQA.json new file mode 100644 index 000000000..118ce1940 --- /dev/null +++ b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/SIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 13.141312599182129, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.00876, + "map_at_1": 0.00358, + "map_at_10": 0.00663, + "map_at_100": 0.0073, + "map_at_1000": 0.00772, + "map_at_20": 0.00693, + "map_at_3": 0.00554, + "map_at_5": 0.00585, + "mrr_at_1": 0.0035823950870010235, + "mrr_at_10": 0.006625806241978195, + "mrr_at_100": 0.007304436214573302, + "mrr_at_1000": 0.0077238129262859195, + "mrr_at_20": 0.006934397485830441, + "mrr_at_3": 0.00554418287273968, + "mrr_at_5": 0.005851245308768338, + "nauc_map_at_1000_diff1": -0.06513769312715259, + "nauc_map_at_1000_max": -0.11042336357235977, + "nauc_map_at_1000_std": -0.27850440774965884, + "nauc_map_at_100_diff1": -0.07143944815678854, + "nauc_map_at_100_max": -0.11270528562188886, + "nauc_map_at_100_std": -0.2811666242346653, + "nauc_map_at_10_diff1": -0.0870030454076618, + "nauc_map_at_10_max": -0.12479761846345787, + "nauc_map_at_10_std": -0.2765607233710985, + "nauc_map_at_1_diff1": -0.11138777843383446, + "nauc_map_at_1_max": -0.10064796673482844, + "nauc_map_at_1_std": -0.27643821614514547, + "nauc_map_at_20_diff1": -0.079256031754402, + "nauc_map_at_20_max": -0.11421102624442973, + "nauc_map_at_20_std": -0.2777461946824304, + "nauc_map_at_3_diff1": -0.1925951661244175, + "nauc_map_at_3_max": -0.20146407965817978, + "nauc_map_at_3_std": -0.2983681717694159, + "nauc_map_at_5_diff1": -0.1517051166365022, + "nauc_map_at_5_max": -0.16897011388133373, + "nauc_map_at_5_std": -0.2805029682613254, + "nauc_mrr_at_1000_diff1": -0.06513544581129449, + "nauc_mrr_at_1000_max": -0.11040416891601085, + "nauc_mrr_at_1000_std": -0.2785121028299979, + "nauc_mrr_at_100_diff1": -0.07143687148471245, + "nauc_mrr_at_100_max": -0.11268526214871928, + "nauc_mrr_at_100_std": -0.2811744672148674, + "nauc_mrr_at_10_diff1": -0.0870030454076618, + "nauc_mrr_at_10_max": -0.12479761846345787, + "nauc_mrr_at_10_std": -0.2765607233710985, + "nauc_mrr_at_1_diff1": -0.11138777843383446, + "nauc_mrr_at_1_max": -0.10064796673482844, + "nauc_mrr_at_1_std": -0.27643821614514547, + "nauc_mrr_at_20_diff1": -0.079256031754402, + "nauc_mrr_at_20_max": -0.11421102624442973, + "nauc_mrr_at_20_std": -0.2777461946824304, + "nauc_mrr_at_3_diff1": -0.1925951661244175, + "nauc_mrr_at_3_max": -0.20146407965817978, + "nauc_mrr_at_3_std": -0.2983681717694159, + "nauc_mrr_at_5_diff1": -0.1517051166365022, + "nauc_mrr_at_5_max": -0.16897011388133373, + "nauc_mrr_at_5_std": -0.2805029682613254, + "nauc_ndcg_at_1000_diff1": 0.031780240912167884, + "nauc_ndcg_at_1000_max": -0.04447280524228775, + "nauc_ndcg_at_1000_std": -0.2127838677324453, + "nauc_ndcg_at_100_diff1": 0.01596016813049004, + "nauc_ndcg_at_100_max": -0.06589863913276627, + "nauc_ndcg_at_100_std": -0.2892263279635762, + "nauc_ndcg_at_10_diff1": -0.02084892913112549, + "nauc_ndcg_at_10_max": -0.08272245992096403, + "nauc_ndcg_at_10_std": -0.26397088546144115, + "nauc_ndcg_at_1_diff1": -0.11138777843383446, + "nauc_ndcg_at_1_max": -0.10064796673482844, + "nauc_ndcg_at_1_std": -0.27643821614514547, + "nauc_ndcg_at_20_diff1": -0.012962594047822563, + "nauc_ndcg_at_20_max": -0.06446339068329279, + "nauc_ndcg_at_20_std": -0.27048488699640383, + "nauc_ndcg_at_3_diff1": -0.20729660803016003, + "nauc_ndcg_at_3_max": -0.21887297974370964, + "nauc_ndcg_at_3_std": -0.29624480446403323, + "nauc_ndcg_at_5_diff1": -0.13810137818396034, + "nauc_ndcg_at_5_max": -0.16338673264024234, + "nauc_ndcg_at_5_std": -0.2667577521557138, + "nauc_precision_at_1000_diff1": 0.05394069217838985, + "nauc_precision_at_1000_max": -0.02151546018809854, + "nauc_precision_at_1000_std": -0.17122951550742455, + "nauc_precision_at_100_diff1": 0.09236977754375761, + "nauc_precision_at_100_max": -0.030726352239525176, + "nauc_precision_at_100_std": -0.30449142208578195, + "nauc_precision_at_10_diff1": 0.08331750822897034, + "nauc_precision_at_10_max": -0.014629507888834995, + "nauc_precision_at_10_std": -0.24639553560885197, + "nauc_precision_at_1_diff1": -0.11138777843383446, + "nauc_precision_at_1_max": -0.10064796673482844, + "nauc_precision_at_1_std": -0.27643821614514547, + "nauc_precision_at_20_diff1": 0.07291635841525071, + "nauc_precision_at_20_max": 0.002849383738076465, + "nauc_precision_at_20_std": -0.2645986683407644, + "nauc_precision_at_3_diff1": -0.23595395888002157, + "nauc_precision_at_3_max": -0.2526051760016159, + "nauc_precision_at_3_std": -0.29063904673592966, + "nauc_precision_at_5_diff1": -0.10607900059970758, + "nauc_precision_at_5_max": -0.14676333393459817, + "nauc_precision_at_5_std": -0.23810711206336574, + "nauc_recall_at_1000_diff1": 0.05394069217838991, + "nauc_recall_at_1000_max": -0.021515460188098537, + "nauc_recall_at_1000_std": -0.17122951550742452, + "nauc_recall_at_100_diff1": 0.0923697775437577, + "nauc_recall_at_100_max": -0.030726352239525162, + "nauc_recall_at_100_std": -0.3044914220857821, + "nauc_recall_at_10_diff1": 0.08331750822897056, + "nauc_recall_at_10_max": -0.014629507888834907, + "nauc_recall_at_10_std": -0.24639553560885194, + "nauc_recall_at_1_diff1": -0.11138777843383446, + "nauc_recall_at_1_max": -0.10064796673482844, + "nauc_recall_at_1_std": -0.27643821614514547, + "nauc_recall_at_20_diff1": 0.07291635841525074, + "nauc_recall_at_20_max": 0.002849383738076495, + "nauc_recall_at_20_std": -0.2645986683407644, + "nauc_recall_at_3_diff1": -0.23595395888002169, + "nauc_recall_at_3_max": -0.252605176001616, + "nauc_recall_at_3_std": -0.2906390467359297, + "nauc_recall_at_5_diff1": -0.10607900059970743, + "nauc_recall_at_5_max": -0.1467633339345981, + "nauc_recall_at_5_std": -0.23810711206336563, + "ndcg_at_1": 0.00358, + "ndcg_at_10": 0.00876, + "ndcg_at_100": 0.0131, + "ndcg_at_1000": 0.03243, + "ndcg_at_20": 0.00982, + "ndcg_at_3": 0.00622, + "ndcg_at_5": 0.00681, + "precision_at_1": 0.00358, + "precision_at_10": 0.00159, + "precision_at_100": 0.00039, + "precision_at_1000": 0.00021, + "precision_at_20": 0.001, + "precision_at_3": 0.00273, + "precision_at_5": 0.00194, + "recall_at_1": 0.00358, + "recall_at_10": 0.01586, + "recall_at_100": 0.03889, + "recall_at_1000": 0.21034, + "recall_at_20": 0.01996, + "recall_at_3": 0.00819, + "recall_at_5": 0.00972 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/SpartQA.json b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/SpartQA.json new file mode 100644 index 000000000..87f563f72 --- /dev/null +++ b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/SpartQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 12.070430994033813, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.10557, + "map_at_1": 0.02662, + "map_at_10": 0.0689, + "map_at_100": 0.08151, + "map_at_1000": 0.08204, + "map_at_20": 0.07535, + "map_at_3": 0.04823, + "map_at_5": 0.05894, + "mrr_at_1": 0.046466332776850305, + "mrr_at_10": 0.09864335179443678, + "mrr_at_100": 0.11147722752225088, + "mrr_at_1000": 0.11208284114638586, + "mrr_at_20": 0.10571533782377292, + "mrr_at_3": 0.07327026525690974, + "mrr_at_5": 0.08670933036542372, + "nauc_map_at_1000_diff1": 0.027895202673362908, + "nauc_map_at_1000_max": -0.1526184175889588, + "nauc_map_at_1000_std": 0.561754559801512, + "nauc_map_at_100_diff1": 0.027705315688689627, + "nauc_map_at_100_max": -0.15323209078978972, + "nauc_map_at_100_std": 0.5623636855217733, + "nauc_map_at_10_diff1": 0.004061066801569926, + "nauc_map_at_10_max": -0.18005647405200162, + "nauc_map_at_10_std": 0.5334962173137007, + "nauc_map_at_1_diff1": -0.011487669434501354, + "nauc_map_at_1_max": -0.2615492505845482, + "nauc_map_at_1_std": 0.5338948529306528, + "nauc_map_at_20_diff1": 0.014283886377011534, + "nauc_map_at_20_max": -0.16852193972233337, + "nauc_map_at_20_std": 0.5450908957101908, + "nauc_map_at_3_diff1": 0.013964201915648788, + "nauc_map_at_3_max": -0.20447414177927034, + "nauc_map_at_3_std": 0.5217123632957806, + "nauc_map_at_5_diff1": 0.00783043303921473, + "nauc_map_at_5_max": -0.19024592749450236, + "nauc_map_at_5_std": 0.5239835521206816, + "nauc_mrr_at_1000_diff1": 0.03594233881068425, + "nauc_mrr_at_1000_max": -0.16676550569551454, + "nauc_mrr_at_1000_std": 0.5223130022198074, + "nauc_mrr_at_100_diff1": 0.03605611093707853, + "nauc_mrr_at_100_max": -0.16700878942975594, + "nauc_mrr_at_100_std": 0.5230609561286523, + "nauc_mrr_at_10_diff1": 0.0157460686874011, + "nauc_mrr_at_10_max": -0.1912324323692207, + "nauc_mrr_at_10_std": 0.5037855542566498, + "nauc_mrr_at_1_diff1": 0.022610078297685174, + "nauc_mrr_at_1_max": -0.26885098566430005, + "nauc_mrr_at_1_std": 0.5088863436805715, + "nauc_mrr_at_20_diff1": 0.026900007364022503, + "nauc_mrr_at_20_max": -0.1794727493388359, + "nauc_mrr_at_20_std": 0.5121104629259202, + "nauc_mrr_at_3_diff1": 0.016503476461330716, + "nauc_mrr_at_3_max": -0.21951643273399454, + "nauc_mrr_at_3_std": 0.4900117823870603, + "nauc_mrr_at_5_diff1": 0.013562056590424075, + "nauc_mrr_at_5_max": -0.20226669876245285, + "nauc_mrr_at_5_std": 0.4976652139485048, + "nauc_ndcg_at_1000_diff1": 0.08981536787264395, + "nauc_ndcg_at_1000_max": -0.05070120343656182, + "nauc_ndcg_at_1000_std": 0.6169302256452622, + "nauc_ndcg_at_100_diff1": 0.09103129563204265, + "nauc_ndcg_at_100_max": -0.05436685749829505, + "nauc_ndcg_at_100_std": 0.6390449171126196, + "nauc_ndcg_at_10_diff1": 0.003834716121138158, + "nauc_ndcg_at_10_max": -0.15891124562267867, + "nauc_ndcg_at_10_std": 0.5324815378278537, + "nauc_ndcg_at_1_diff1": 0.022610078297685174, + "nauc_ndcg_at_1_max": -0.26885098566430005, + "nauc_ndcg_at_1_std": 0.5088863436805715, + "nauc_ndcg_at_20_diff1": 0.031135908452294615, + "nauc_ndcg_at_20_max": -0.12952209476480475, + "nauc_ndcg_at_20_std": 0.5611021933068211, + "nauc_ndcg_at_3_diff1": 0.015186638619863926, + "nauc_ndcg_at_3_max": -0.1981452187058653, + "nauc_ndcg_at_3_std": 0.5101614679275697, + "nauc_ndcg_at_5_diff1": 0.007501021977469618, + "nauc_ndcg_at_5_max": -0.17677548403430393, + "nauc_ndcg_at_5_std": 0.5173818023760687, + "nauc_precision_at_1000_diff1": 0.18513035510293638, + "nauc_precision_at_1000_max": 0.09089044578678833, + "nauc_precision_at_1000_std": 0.3594797460983268, + "nauc_precision_at_100_diff1": 0.18709696772548315, + "nauc_precision_at_100_max": 0.05914065364769568, + "nauc_precision_at_100_std": 0.5691999897715838, + "nauc_precision_at_10_diff1": 0.01603423619314517, + "nauc_precision_at_10_max": -0.15505767249063485, + "nauc_precision_at_10_std": 0.5128202035008433, + "nauc_precision_at_1_diff1": 0.022610078297685174, + "nauc_precision_at_1_max": -0.26885098566430005, + "nauc_precision_at_1_std": 0.5088863436805715, + "nauc_precision_at_20_diff1": 0.06554906734510366, + "nauc_precision_at_20_max": -0.09830399091627853, + "nauc_precision_at_20_std": 0.5288432330175716, + "nauc_precision_at_3_diff1": 0.048022491377173404, + "nauc_precision_at_3_max": -0.1979909369182385, + "nauc_precision_at_3_std": 0.4920537354566277, + "nauc_precision_at_5_diff1": 0.025607028482404683, + "nauc_precision_at_5_max": -0.17581129989345295, + "nauc_precision_at_5_std": 0.49646722972998364, + "nauc_recall_at_1000_diff1": 0.1711514879189634, + "nauc_recall_at_1000_max": 0.18493881534662485, + "nauc_recall_at_1000_std": 0.5686213874233509, + "nauc_recall_at_100_diff1": 0.17290682644466546, + "nauc_recall_at_100_max": 0.13590877923865105, + "nauc_recall_at_100_std": 0.6981202425194263, + "nauc_recall_at_10_diff1": -0.006597004077683875, + "nauc_recall_at_10_max": -0.10733897831775142, + "nauc_recall_at_10_std": 0.5229036381756583, + "nauc_recall_at_1_diff1": -0.011487669434501354, + "nauc_recall_at_1_max": -0.2615492505845482, + "nauc_recall_at_1_std": 0.5338948529306528, + "nauc_recall_at_20_diff1": 0.044298137781235314, + "nauc_recall_at_20_max": -0.0515864144764878, + "nauc_recall_at_20_std": 0.5582367282119841, + "nauc_recall_at_3_diff1": 0.007517049934814512, + "nauc_recall_at_3_max": -0.17043638426573027, + "nauc_recall_at_3_std": 0.5120856186255163, + "nauc_recall_at_5_diff1": -0.001774157077876944, + "nauc_recall_at_5_max": -0.1353855992845261, + "nauc_recall_at_5_std": 0.5093071674598848, + "ndcg_at_1": 0.04647, + "ndcg_at_10": 0.10557, + "ndcg_at_100": 0.17138, + "ndcg_at_1000": 0.19289, + "ndcg_at_20": 0.12892, + "ndcg_at_3": 0.06064, + "ndcg_at_5": 0.08058, + "precision_at_1": 0.04647, + "precision_at_10": 0.03066, + "precision_at_100": 0.00775, + "precision_at_1000": 0.00108, + "precision_at_20": 0.02216, + "precision_at_3": 0.04211, + "precision_at_5": 0.03929, + "recall_at_1": 0.02662, + "recall_at_10": 0.18438, + "recall_at_100": 0.46689, + "recall_at_1000": 0.62641, + "recall_at_20": 0.26516, + "recall_at_3": 0.07216, + "recall_at_5": 0.11482 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL1.json b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL1.json new file mode 100644 index 000000000..9ef4b3e97 --- /dev/null +++ b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL1.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 7.441412687301636, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01801, + "map_at_1": 0.004, + "map_at_10": 0.01171, + "map_at_100": 0.01854, + "map_at_1000": 0.02061, + "map_at_20": 0.01425, + "map_at_3": 0.00754, + "map_at_5": 0.00889, + "mrr_at_1": 0.004, + "mrr_at_10": 0.011708035714285726, + "mrr_at_100": 0.018542026244864535, + "mrr_at_1000": 0.020611827730065566, + "mrr_at_20": 0.01425361959377056, + "mrr_at_3": 0.007541666666666666, + "mrr_at_5": 0.008891666666666666, + "nauc_map_at_1000_diff1": -0.003390477830108603, + "nauc_map_at_1000_max": 0.07752353940787876, + "nauc_map_at_1000_std": -0.00048180248515906416, + "nauc_map_at_100_diff1": 0.0015288777270910643, + "nauc_map_at_100_max": 0.07984952797393265, + "nauc_map_at_100_std": -0.0027591309588719864, + "nauc_map_at_10_diff1": 0.01733143823906299, + "nauc_map_at_10_max": 0.11203813076376448, + "nauc_map_at_10_std": -0.008584534506505995, + "nauc_map_at_1_diff1": -0.03261671585725788, + "nauc_map_at_1_max": 0.2989502280654681, + "nauc_map_at_1_std": 0.10615105983364624, + "nauc_map_at_20_diff1": 0.00917917195151758, + "nauc_map_at_20_max": 0.10098299512374888, + "nauc_map_at_20_std": 0.002209019474019968, + "nauc_map_at_3_diff1": 0.025133896739783064, + "nauc_map_at_3_max": 0.17662065826943008, + "nauc_map_at_3_std": 0.0076817371221207026, + "nauc_map_at_5_diff1": 0.010145700879797942, + "nauc_map_at_5_max": 0.14725002508355534, + "nauc_map_at_5_std": 0.004628701773250272, + "nauc_mrr_at_1000_diff1": -0.003390477830108603, + "nauc_mrr_at_1000_max": 0.07752353940787876, + "nauc_mrr_at_1000_std": -0.00048180248515906416, + "nauc_mrr_at_100_diff1": 0.0015288777270910643, + "nauc_mrr_at_100_max": 0.07984952797393265, + "nauc_mrr_at_100_std": -0.0027591309588719864, + "nauc_mrr_at_10_diff1": 0.01733143823906299, + "nauc_mrr_at_10_max": 0.11203813076376448, + "nauc_mrr_at_10_std": -0.008584534506505995, + "nauc_mrr_at_1_diff1": -0.03261671585725788, + "nauc_mrr_at_1_max": 0.2989502280654681, + "nauc_mrr_at_1_std": 0.10615105983364624, + "nauc_mrr_at_20_diff1": 0.00917917195151758, + "nauc_mrr_at_20_max": 0.10098299512374888, + "nauc_mrr_at_20_std": 0.002209019474019968, + "nauc_mrr_at_3_diff1": 0.025133896739783064, + "nauc_mrr_at_3_max": 0.17662065826943008, + "nauc_mrr_at_3_std": 0.0076817371221207026, + "nauc_mrr_at_5_diff1": 0.010145700879797942, + "nauc_mrr_at_5_max": 0.14725002508355534, + "nauc_mrr_at_5_std": 0.004628701773250272, + "nauc_ndcg_at_1000_diff1": -0.05778731587969963, + "nauc_ndcg_at_1000_max": 0.0063957573439519895, + "nauc_ndcg_at_1000_std": 0.020143674920574464, + "nauc_ndcg_at_100_diff1": -0.011378660087654258, + "nauc_ndcg_at_100_max": 0.021047343310137506, + "nauc_ndcg_at_100_std": -0.014125987369303187, + "nauc_ndcg_at_10_diff1": 0.027206469191796246, + "nauc_ndcg_at_10_max": 0.07767656167630826, + "nauc_ndcg_at_10_std": -0.02159727238274767, + "nauc_ndcg_at_1_diff1": -0.03261671585725788, + "nauc_ndcg_at_1_max": 0.2989502280654681, + "nauc_ndcg_at_1_std": 0.10615105983364624, + "nauc_ndcg_at_20_diff1": 0.007905677279826181, + "nauc_ndcg_at_20_max": 0.06871226887404563, + "nauc_ndcg_at_20_std": 0.002621610835357388, + "nauc_ndcg_at_3_diff1": 0.04028956517983068, + "nauc_ndcg_at_3_max": 0.16431730535212183, + "nauc_ndcg_at_3_std": -0.003924201726966041, + "nauc_ndcg_at_5_diff1": 0.015036636066962815, + "nauc_ndcg_at_5_max": 0.12538938789781381, + "nauc_ndcg_at_5_std": -0.005260916048973166, + "nauc_precision_at_1000_diff1": -0.15430020572670777, + "nauc_precision_at_1000_max": -0.06342205028012567, + "nauc_precision_at_1000_std": 0.08129051457554205, + "nauc_precision_at_100_diff1": -0.01968888578733332, + "nauc_precision_at_100_max": -0.009554200739721037, + "nauc_precision_at_100_std": -0.02109198720185404, + "nauc_precision_at_10_diff1": 0.037731205747694195, + "nauc_precision_at_10_max": 0.04208914463059199, + "nauc_precision_at_10_std": -0.03403464817761262, + "nauc_precision_at_1_diff1": -0.03261671585725788, + "nauc_precision_at_1_max": 0.2989502280654681, + "nauc_precision_at_1_std": 0.10615105983364624, + "nauc_precision_at_20_diff1": 0.004889730607465979, + "nauc_precision_at_20_max": 0.04701040842709733, + "nauc_precision_at_20_std": 0.00580443168315442, + "nauc_precision_at_3_diff1": 0.06812986316071916, + "nauc_precision_at_3_max": 0.1441212771666219, + "nauc_precision_at_3_std": -0.02351489133351214, + "nauc_precision_at_5_diff1": 0.020961440212297594, + "nauc_precision_at_5_max": 0.09301248571145045, + "nauc_precision_at_5_std": -0.018616464084742452, + "nauc_recall_at_1000_diff1": -0.15430020572670744, + "nauc_recall_at_1000_max": -0.06342205028012476, + "nauc_recall_at_1000_std": 0.08129051457554384, + "nauc_recall_at_100_diff1": -0.019688885787333327, + "nauc_recall_at_100_max": -0.009554200739721132, + "nauc_recall_at_100_std": -0.02109198720185414, + "nauc_recall_at_10_diff1": 0.03773120574769425, + "nauc_recall_at_10_max": 0.042089144630591956, + "nauc_recall_at_10_std": -0.03403464817761254, + "nauc_recall_at_1_diff1": -0.03261671585725788, + "nauc_recall_at_1_max": 0.2989502280654681, + "nauc_recall_at_1_std": 0.10615105983364624, + "nauc_recall_at_20_diff1": 0.004889730607466053, + "nauc_recall_at_20_max": 0.04701040842709747, + "nauc_recall_at_20_std": 0.0058044316831545395, + "nauc_recall_at_3_diff1": 0.06812986316071899, + "nauc_recall_at_3_max": 0.14412127716662193, + "nauc_recall_at_3_std": -0.023514891333512283, + "nauc_recall_at_5_diff1": 0.020961440212297584, + "nauc_recall_at_5_max": 0.09301248571145031, + "nauc_recall_at_5_std": -0.018616464084742525, + "ndcg_at_1": 0.004, + "ndcg_at_10": 0.01801, + "ndcg_at_100": 0.06252, + "ndcg_at_1000": 0.12765, + "ndcg_at_20": 0.02746, + "ndcg_at_3": 0.00881, + "ndcg_at_5": 0.01121, + "precision_at_1": 0.004, + "precision_at_10": 0.00392, + "precision_at_100": 0.00274, + "precision_at_1000": 0.00081, + "precision_at_20": 0.00385, + "precision_at_3": 0.00417, + "precision_at_5": 0.00365, + "recall_at_1": 0.004, + "recall_at_10": 0.03925, + "recall_at_100": 0.2745, + "recall_at_1000": 0.8075, + "recall_at_20": 0.077, + "recall_at_3": 0.0125, + "recall_at_5": 0.01825 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL2Fact.json b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL2Fact.json new file mode 100644 index 000000000..20a24a60f --- /dev/null +++ b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL2Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 25.195196628570557, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.22033, + "map_at_1": 0.08116, + "map_at_10": 0.16647, + "map_at_100": 0.17981, + "map_at_1000": 0.18076, + "map_at_20": 0.174, + "map_at_3": 0.13399, + "map_at_5": 0.15126, + "mrr_at_1": 0.0811561978877154, + "mrr_at_10": 0.1664723347185832, + "mrr_at_100": 0.17980728807461796, + "mrr_at_1000": 0.18076403411768363, + "mrr_at_20": 0.17399579942326077, + "mrr_at_3": 0.13399419430547868, + "mrr_at_5": 0.151263047371998, + "nauc_map_at_1000_diff1": -0.05256602939287384, + "nauc_map_at_1000_max": -0.10262134158532864, + "nauc_map_at_1000_std": -0.07684752124090953, + "nauc_map_at_100_diff1": -0.05292426920864483, + "nauc_map_at_100_max": -0.10292591345024756, + "nauc_map_at_100_std": -0.07693551766449568, + "nauc_map_at_10_diff1": -0.04885167730500792, + "nauc_map_at_10_max": -0.09958411473599105, + "nauc_map_at_10_std": -0.08212531802582171, + "nauc_map_at_1_diff1": -0.005430412784039319, + "nauc_map_at_1_max": -0.10127301923444389, + "nauc_map_at_1_std": -0.08269134959767414, + "nauc_map_at_20_diff1": -0.05128697778700698, + "nauc_map_at_20_max": -0.10157937384285687, + "nauc_map_at_20_std": -0.07973304362633411, + "nauc_map_at_3_diff1": -0.031871241075297756, + "nauc_map_at_3_max": -0.09186449536404251, + "nauc_map_at_3_std": -0.08422840632880575, + "nauc_map_at_5_diff1": -0.039816360912325294, + "nauc_map_at_5_max": -0.09581030741555592, + "nauc_map_at_5_std": -0.08227062986675988, + "nauc_mrr_at_1000_diff1": -0.05256602939287384, + "nauc_mrr_at_1000_max": -0.10262134158532864, + "nauc_mrr_at_1000_std": -0.07684752124090953, + "nauc_mrr_at_100_diff1": -0.05292426920864483, + "nauc_mrr_at_100_max": -0.10292591345024756, + "nauc_mrr_at_100_std": -0.07693551766449568, + "nauc_mrr_at_10_diff1": -0.04885167730500792, + "nauc_mrr_at_10_max": -0.09958411473599105, + "nauc_mrr_at_10_std": -0.08212531802582171, + "nauc_mrr_at_1_diff1": -0.005430412784039319, + "nauc_mrr_at_1_max": -0.10127301923444389, + "nauc_mrr_at_1_std": -0.08269134959767414, + "nauc_mrr_at_20_diff1": -0.05128697778700698, + "nauc_mrr_at_20_max": -0.10157937384285687, + "nauc_mrr_at_20_std": -0.07973304362633411, + "nauc_mrr_at_3_diff1": -0.031871241075297756, + "nauc_mrr_at_3_max": -0.09186449536404251, + "nauc_mrr_at_3_std": -0.08422840632880575, + "nauc_mrr_at_5_diff1": -0.039816360912325294, + "nauc_mrr_at_5_max": -0.09581030741555592, + "nauc_mrr_at_5_std": -0.08227062986675988, + "nauc_ndcg_at_1000_diff1": -0.08020584857729443, + "nauc_ndcg_at_1000_max": -0.11440809821283571, + "nauc_ndcg_at_1000_std": -0.06006824068064163, + "nauc_ndcg_at_100_diff1": -0.08850200264913753, + "nauc_ndcg_at_100_max": -0.11862396777195396, + "nauc_ndcg_at_100_std": -0.05645074495559649, + "nauc_ndcg_at_10_diff1": -0.06784261669428353, + "nauc_ndcg_at_10_max": -0.1044045363219669, + "nauc_ndcg_at_10_std": -0.08154842592568962, + "nauc_ndcg_at_1_diff1": -0.005430412784039319, + "nauc_ndcg_at_1_max": -0.10127301923444389, + "nauc_ndcg_at_1_std": -0.08269134959767414, + "nauc_ndcg_at_20_diff1": -0.07525274423343084, + "nauc_ndcg_at_20_max": -0.11031740299953399, + "nauc_ndcg_at_20_std": -0.07393736306296794, + "nauc_ndcg_at_3_diff1": -0.03735714906679138, + "nauc_ndcg_at_3_max": -0.09010217865442782, + "nauc_ndcg_at_3_std": -0.0849289045585087, + "nauc_ndcg_at_5_diff1": -0.0495764779109011, + "nauc_ndcg_at_5_max": -0.09669024748081667, + "nauc_ndcg_at_5_std": -0.08171727187234892, + "nauc_precision_at_1000_diff1": -0.38281544121091426, + "nauc_precision_at_1000_max": -0.28042985483570354, + "nauc_precision_at_1000_std": 0.1525261969600581, + "nauc_precision_at_100_diff1": -0.2261146469248095, + "nauc_precision_at_100_max": -0.1841849613370545, + "nauc_precision_at_100_std": 0.03822907511124577, + "nauc_precision_at_10_diff1": -0.10694430937569757, + "nauc_precision_at_10_max": -0.11547815868600261, + "nauc_precision_at_10_std": -0.0803159801465651, + "nauc_precision_at_1_diff1": -0.005430412784039319, + "nauc_precision_at_1_max": -0.10127301923444389, + "nauc_precision_at_1_std": -0.08269134959767414, + "nauc_precision_at_20_diff1": -0.12865943771182595, + "nauc_precision_at_20_max": -0.13201360661139033, + "nauc_precision_at_20_std": -0.05854047366892418, + "nauc_precision_at_3_diff1": -0.0486219883959563, + "nauc_precision_at_3_max": -0.08652745378373047, + "nauc_precision_at_3_std": -0.08645588343026761, + "nauc_precision_at_5_diff1": -0.06900596596119463, + "nauc_precision_at_5_max": -0.09909434160117096, + "nauc_precision_at_5_std": -0.08042980678536255, + "nauc_recall_at_1000_diff1": -0.38281544121091193, + "nauc_recall_at_1000_max": -0.28042985483570476, + "nauc_recall_at_1000_std": 0.15252619696005737, + "nauc_recall_at_100_diff1": -0.22611464692481034, + "nauc_recall_at_100_max": -0.18418496133705506, + "nauc_recall_at_100_std": 0.038229075111245195, + "nauc_recall_at_10_diff1": -0.10694430937569777, + "nauc_recall_at_10_max": -0.11547815868600275, + "nauc_recall_at_10_std": -0.08031598014656494, + "nauc_recall_at_1_diff1": -0.005430412784039319, + "nauc_recall_at_1_max": -0.10127301923444389, + "nauc_recall_at_1_std": -0.08269134959767414, + "nauc_recall_at_20_diff1": -0.1286594377118263, + "nauc_recall_at_20_max": -0.13201360661139067, + "nauc_recall_at_20_std": -0.05854047366892465, + "nauc_recall_at_3_diff1": -0.04862198839595607, + "nauc_recall_at_3_max": -0.08652745378373028, + "nauc_recall_at_3_std": -0.08645588343026729, + "nauc_recall_at_5_diff1": -0.06900596596119447, + "nauc_recall_at_5_max": -0.09909434160117078, + "nauc_recall_at_5_std": -0.08042980678536253, + "ndcg_at_1": 0.08116, + "ndcg_at_10": 0.22033, + "ndcg_at_100": 0.2903, + "ndcg_at_1000": 0.31623, + "ndcg_at_20": 0.24739, + "ndcg_at_3": 0.15218, + "ndcg_at_5": 0.18351, + "precision_at_1": 0.08116, + "precision_at_10": 0.03954, + "precision_at_100": 0.00735, + "precision_at_1000": 0.00094, + "precision_at_20": 0.02509, + "precision_at_3": 0.06837, + "precision_at_5": 0.05633, + "recall_at_1": 0.08116, + "recall_at_10": 0.3954, + "recall_at_100": 0.73485, + "recall_at_1000": 0.94015, + "recall_at_20": 0.50176, + "recall_at_3": 0.20511, + "recall_at_5": 0.28164 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL2Pure.json b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL2Pure.json new file mode 100644 index 000000000..079a8c047 --- /dev/null +++ b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL2Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 11.323631763458252, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.00936, + "map_at_1": 0.00204, + "map_at_10": 0.00594, + "map_at_100": 0.00844, + "map_at_1000": 0.00921, + "map_at_20": 0.00687, + "map_at_3": 0.00355, + "map_at_5": 0.00459, + "mrr_at_1": 0.0020381693533444508, + "mrr_at_10": 0.005941131316339763, + "mrr_at_100": 0.00843552862748995, + "mrr_at_1000": 0.009213092050935333, + "mrr_at_20": 0.006874582899404054, + "mrr_at_3": 0.003551355691433512, + "mrr_at_5": 0.004588969180408866, + "nauc_map_at_1000_diff1": 0.02163356822381339, + "nauc_map_at_1000_max": 0.19123630799392038, + "nauc_map_at_1000_std": 0.3369176298454259, + "nauc_map_at_100_diff1": 0.0223608596300594, + "nauc_map_at_100_max": 0.18809656886012335, + "nauc_map_at_100_std": 0.3269884577655722, + "nauc_map_at_10_diff1": 0.028052807449661443, + "nauc_map_at_10_max": 0.18369823906897167, + "nauc_map_at_10_std": 0.2910605585000429, + "nauc_map_at_1_diff1": -0.11126460515206658, + "nauc_map_at_1_max": 0.046064475959503484, + "nauc_map_at_1_std": 0.20999875537950857, + "nauc_map_at_20_diff1": 0.017568960890544966, + "nauc_map_at_20_max": 0.178323384398595, + "nauc_map_at_20_std": 0.3024182727975644, + "nauc_map_at_3_diff1": -0.014014143795209467, + "nauc_map_at_3_max": 0.1288371515308189, + "nauc_map_at_3_std": 0.24247586070926425, + "nauc_map_at_5_diff1": -0.0004163152224161625, + "nauc_map_at_5_max": 0.13211762059675983, + "nauc_map_at_5_std": 0.23701282150299915, + "nauc_mrr_at_1000_diff1": 0.021633578635027143, + "nauc_mrr_at_1000_max": 0.19123633133158432, + "nauc_mrr_at_1000_std": 0.33691764525175555, + "nauc_mrr_at_100_diff1": 0.0223608596300594, + "nauc_mrr_at_100_max": 0.18809656886012335, + "nauc_mrr_at_100_std": 0.3269884577655722, + "nauc_mrr_at_10_diff1": 0.028052807449661443, + "nauc_mrr_at_10_max": 0.18369823906897167, + "nauc_mrr_at_10_std": 0.2910605585000429, + "nauc_mrr_at_1_diff1": -0.11126460515206658, + "nauc_mrr_at_1_max": 0.046064475959503484, + "nauc_mrr_at_1_std": 0.20999875537950857, + "nauc_mrr_at_20_diff1": 0.017568960890544966, + "nauc_mrr_at_20_max": 0.178323384398595, + "nauc_mrr_at_20_std": 0.3024182727975644, + "nauc_mrr_at_3_diff1": -0.014014143795209467, + "nauc_mrr_at_3_max": 0.1288371515308189, + "nauc_mrr_at_3_std": 0.24247586070926425, + "nauc_mrr_at_5_diff1": -0.0004163152224161625, + "nauc_mrr_at_5_max": 0.13211762059675983, + "nauc_mrr_at_5_std": 0.23701282150299915, + "nauc_ndcg_at_1000_diff1": 0.018886120588997263, + "nauc_ndcg_at_1000_max": 0.217922767432762, + "nauc_ndcg_at_1000_std": 0.417125440873621, + "nauc_ndcg_at_100_diff1": 0.033401116319849614, + "nauc_ndcg_at_100_max": 0.2141269875971339, + "nauc_ndcg_at_100_std": 0.3887634775891189, + "nauc_ndcg_at_10_diff1": 0.05353727819287353, + "nauc_ndcg_at_10_max": 0.21742955799460525, + "nauc_ndcg_at_10_std": 0.32040781023335435, + "nauc_ndcg_at_1_diff1": -0.11126460515206658, + "nauc_ndcg_at_1_max": 0.046064475959503484, + "nauc_ndcg_at_1_std": 0.20999875537950857, + "nauc_ndcg_at_20_diff1": 0.026174152226821925, + "nauc_ndcg_at_20_max": 0.19827375581684353, + "nauc_ndcg_at_20_std": 0.33590684107700913, + "nauc_ndcg_at_3_diff1": -0.005981697858757688, + "nauc_ndcg_at_3_max": 0.13552157588209404, + "nauc_ndcg_at_3_std": 0.24421131318563818, + "nauc_ndcg_at_5_diff1": 0.013840291868604073, + "nauc_ndcg_at_5_max": 0.14315394019848826, + "nauc_ndcg_at_5_std": 0.24010476915929838, + "nauc_precision_at_1000_diff1": 0.010684026805723659, + "nauc_precision_at_1000_max": 0.22088326986767384, + "nauc_precision_at_1000_std": 0.4391469429665974, + "nauc_precision_at_100_diff1": 0.03638071997502885, + "nauc_precision_at_100_max": 0.2239188429787461, + "nauc_precision_at_100_std": 0.4185963918332394, + "nauc_precision_at_10_diff1": 0.07930782013936692, + "nauc_precision_at_10_max": 0.2523248595602475, + "nauc_precision_at_10_std": 0.35175131879951604, + "nauc_precision_at_1_diff1": -0.11126460515206658, + "nauc_precision_at_1_max": 0.046064475959503484, + "nauc_precision_at_1_std": 0.20999875537950857, + "nauc_precision_at_20_diff1": 0.028860973144457566, + "nauc_precision_at_20_max": 0.21051568344041346, + "nauc_precision_at_20_std": 0.36242155749034954, + "nauc_precision_at_3_diff1": 0.006680200827813536, + "nauc_precision_at_3_max": 0.14599339339095785, + "nauc_precision_at_3_std": 0.24654176217007795, + "nauc_precision_at_5_diff1": 0.03326223305370827, + "nauc_precision_at_5_max": 0.1586576064467303, + "nauc_precision_at_5_std": 0.24492195745453554, + "nauc_recall_at_1000_diff1": 0.010684026805723697, + "nauc_recall_at_1000_max": 0.22088326986767415, + "nauc_recall_at_1000_std": 0.43914694296659745, + "nauc_recall_at_100_diff1": 0.03638071997502878, + "nauc_recall_at_100_max": 0.22391884297874584, + "nauc_recall_at_100_std": 0.4185963918332392, + "nauc_recall_at_10_diff1": 0.0793078201393668, + "nauc_recall_at_10_max": 0.25232485956024714, + "nauc_recall_at_10_std": 0.3517513187995154, + "nauc_recall_at_1_diff1": -0.11126460515206658, + "nauc_recall_at_1_max": 0.046064475959503484, + "nauc_recall_at_1_std": 0.20999875537950857, + "nauc_recall_at_20_diff1": 0.028860973144457482, + "nauc_recall_at_20_max": 0.21051568344041338, + "nauc_recall_at_20_std": 0.36242155749034927, + "nauc_recall_at_3_diff1": 0.006680200827813642, + "nauc_recall_at_3_max": 0.14599339339095793, + "nauc_recall_at_3_std": 0.2465417621700784, + "nauc_recall_at_5_diff1": 0.03326223305370799, + "nauc_recall_at_5_max": 0.15865760644672994, + "nauc_recall_at_5_std": 0.2449219574545351, + "ndcg_at_1": 0.00204, + "ndcg_at_10": 0.00936, + "ndcg_at_100": 0.02552, + "ndcg_at_1000": 0.05211, + "ndcg_at_20": 0.0129, + "ndcg_at_3": 0.00411, + "ndcg_at_5": 0.00604, + "precision_at_1": 0.00204, + "precision_at_10": 0.00209, + "precision_at_100": 0.00106, + "precision_at_1000": 0.00033, + "precision_at_20": 0.00176, + "precision_at_3": 0.00191, + "precision_at_5": 0.00211, + "recall_at_1": 0.00204, + "recall_at_10": 0.02094, + "recall_at_100": 0.10617, + "recall_at_1000": 0.3287, + "recall_at_20": 0.0352, + "recall_at_3": 0.00574, + "recall_at_5": 0.01056 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL3Fact.json b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL3Fact.json new file mode 100644 index 000000000..5d5d08064 --- /dev/null +++ b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL3Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 22.160330533981323, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.20822, + "map_at_1": 0.05987, + "map_at_10": 0.15147, + "map_at_100": 0.16439, + "map_at_1000": 0.16535, + "map_at_20": 0.15867, + "map_at_3": 0.11715, + "map_at_5": 0.13621, + "mrr_at_1": 0.05987347492092183, + "mrr_at_10": 0.15147074645493083, + "mrr_at_100": 0.16439206646058727, + "mrr_at_1000": 0.16535180937641727, + "mrr_at_20": 0.15866630603079251, + "mrr_at_3": 0.11714866696791652, + "mrr_at_5": 0.1362065070040667, + "nauc_map_at_1000_diff1": -0.11781440239246121, + "nauc_map_at_1000_max": -0.10274797276007186, + "nauc_map_at_1000_std": -0.04860434413703376, + "nauc_map_at_100_diff1": -0.11790255453215392, + "nauc_map_at_100_max": -0.1029856775045485, + "nauc_map_at_100_std": -0.04869440629890414, + "nauc_map_at_10_diff1": -0.11440629907263125, + "nauc_map_at_10_max": -0.09948228224816172, + "nauc_map_at_10_std": -0.05325249332011153, + "nauc_map_at_1_diff1": -0.16632816576933204, + "nauc_map_at_1_max": -0.1264280881863667, + "nauc_map_at_1_std": -0.05469557195542031, + "nauc_map_at_20_diff1": -0.11641128688232076, + "nauc_map_at_20_max": -0.10318279518082282, + "nauc_map_at_20_std": -0.052032475483937565, + "nauc_map_at_3_diff1": -0.1011191164440161, + "nauc_map_at_3_max": -0.08793046812420424, + "nauc_map_at_3_std": -0.0564555623301593, + "nauc_map_at_5_diff1": -0.10713582553793867, + "nauc_map_at_5_max": -0.09337909580918165, + "nauc_map_at_5_std": -0.05410038259180754, + "nauc_mrr_at_1000_diff1": -0.11781440239246121, + "nauc_mrr_at_1000_max": -0.10274797276007186, + "nauc_mrr_at_1000_std": -0.04860434413703376, + "nauc_mrr_at_100_diff1": -0.11790255453215392, + "nauc_mrr_at_100_max": -0.1029856775045485, + "nauc_mrr_at_100_std": -0.04869440629890414, + "nauc_mrr_at_10_diff1": -0.11440629907263125, + "nauc_mrr_at_10_max": -0.09948228224816172, + "nauc_mrr_at_10_std": -0.05325249332011153, + "nauc_mrr_at_1_diff1": -0.16632816576933204, + "nauc_mrr_at_1_max": -0.1264280881863667, + "nauc_mrr_at_1_std": -0.05469557195542031, + "nauc_mrr_at_20_diff1": -0.11641128688232076, + "nauc_mrr_at_20_max": -0.10318279518082282, + "nauc_mrr_at_20_std": -0.052032475483937565, + "nauc_mrr_at_3_diff1": -0.1011191164440161, + "nauc_mrr_at_3_max": -0.08793046812420424, + "nauc_mrr_at_3_std": -0.0564555623301593, + "nauc_mrr_at_5_diff1": -0.10713582553793867, + "nauc_mrr_at_5_max": -0.09337909580918165, + "nauc_mrr_at_5_std": -0.05410038259180754, + "nauc_ndcg_at_1000_diff1": -0.12993605007699197, + "nauc_ndcg_at_1000_max": -0.11086174623606107, + "nauc_ndcg_at_1000_std": -0.02968769769284111, + "nauc_ndcg_at_100_diff1": -0.13310725420806324, + "nauc_ndcg_at_100_max": -0.11589005998289036, + "nauc_ndcg_at_100_std": -0.026224482423746046, + "nauc_ndcg_at_10_diff1": -0.11748685751443869, + "nauc_ndcg_at_10_max": -0.10556277792922376, + "nauc_ndcg_at_10_std": -0.05188482989752459, + "nauc_ndcg_at_1_diff1": -0.16632816576933204, + "nauc_ndcg_at_1_max": -0.1264280881863667, + "nauc_ndcg_at_1_std": -0.05469557195542031, + "nauc_ndcg_at_20_diff1": -0.12326154753525109, + "nauc_ndcg_at_20_max": -0.11654577869996133, + "nauc_ndcg_at_20_std": -0.048053803579503805, + "nauc_ndcg_at_3_diff1": -0.09267877536641161, + "nauc_ndcg_at_3_max": -0.0844586838482683, + "nauc_ndcg_at_3_std": -0.05779262667578146, + "nauc_ndcg_at_5_diff1": -0.10262839972069662, + "nauc_ndcg_at_5_max": -0.09309134379677739, + "nauc_ndcg_at_5_std": -0.05396798927746283, + "nauc_precision_at_1000_diff1": -0.2891858170419774, + "nauc_precision_at_1000_max": -0.15989175303667783, + "nauc_precision_at_1000_std": 0.20730860487453212, + "nauc_precision_at_100_diff1": -0.19758987068473446, + "nauc_precision_at_100_max": -0.15898196422378172, + "nauc_precision_at_100_std": 0.0705183576549791, + "nauc_precision_at_10_diff1": -0.1271513456233497, + "nauc_precision_at_10_max": -0.11948587277589413, + "nauc_precision_at_10_std": -0.04873601439109289, + "nauc_precision_at_1_diff1": -0.16632816576933204, + "nauc_precision_at_1_max": -0.1264280881863667, + "nauc_precision_at_1_std": -0.05469557195542031, + "nauc_precision_at_20_diff1": -0.14229403524051484, + "nauc_precision_at_20_max": -0.14854451717776526, + "nauc_precision_at_20_std": -0.03829784644122566, + "nauc_precision_at_3_diff1": -0.0774302577469947, + "nauc_precision_at_3_max": -0.07861578415334898, + "nauc_precision_at_3_std": -0.060523329189638674, + "nauc_precision_at_5_diff1": -0.09632618439622069, + "nauc_precision_at_5_max": -0.09389783210545066, + "nauc_precision_at_5_std": -0.05356024295022644, + "nauc_recall_at_1000_diff1": -0.28918581704198115, + "nauc_recall_at_1000_max": -0.1598917530366785, + "nauc_recall_at_1000_std": 0.20730860487453176, + "nauc_recall_at_100_diff1": -0.19758987068473438, + "nauc_recall_at_100_max": -0.15898196422378202, + "nauc_recall_at_100_std": 0.07051835765497942, + "nauc_recall_at_10_diff1": -0.12715134562335, + "nauc_recall_at_10_max": -0.11948587277589436, + "nauc_recall_at_10_std": -0.04873601439109304, + "nauc_recall_at_1_diff1": -0.16632816576933204, + "nauc_recall_at_1_max": -0.1264280881863667, + "nauc_recall_at_1_std": -0.05469557195542031, + "nauc_recall_at_20_diff1": -0.14229403524051504, + "nauc_recall_at_20_max": -0.14854451717776573, + "nauc_recall_at_20_std": -0.038297846441225615, + "nauc_recall_at_3_diff1": -0.07743025774699461, + "nauc_recall_at_3_max": -0.07861578415334897, + "nauc_recall_at_3_std": -0.060523329189638604, + "nauc_recall_at_5_diff1": -0.0963261843962209, + "nauc_recall_at_5_max": -0.0938978321054507, + "nauc_recall_at_5_std": -0.05356024295022665, + "ndcg_at_1": 0.05987, + "ndcg_at_10": 0.20822, + "ndcg_at_100": 0.27635, + "ndcg_at_1000": 0.30307, + "ndcg_at_20": 0.2344, + "ndcg_at_3": 0.13677, + "ndcg_at_5": 0.17107, + "precision_at_1": 0.05987, + "precision_at_10": 0.03922, + "precision_at_100": 0.00723, + "precision_at_1000": 0.00094, + "precision_at_20": 0.02479, + "precision_at_3": 0.06462, + "precision_at_5": 0.0554, + "recall_at_1": 0.05987, + "recall_at_10": 0.39223, + "recall_at_100": 0.723, + "recall_at_1000": 0.93583, + "recall_at_20": 0.49571, + "recall_at_3": 0.19385, + "recall_at_5": 0.277 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL3Pure.json b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL3Pure.json new file mode 100644 index 000000000..61746616b --- /dev/null +++ b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL3Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 9.730855941772461, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07146, + "map_at_1": 0.00316, + "map_at_10": 0.04388, + "map_at_100": 0.05212, + "map_at_1000": 0.05339, + "map_at_20": 0.04813, + "map_at_3": 0.02666, + "map_at_5": 0.03531, + "mrr_at_1": 0.0031631269769543608, + "mrr_at_10": 0.043882290075240735, + "mrr_at_100": 0.05211894477388727, + "mrr_at_1000": 0.05338541623647166, + "mrr_at_20": 0.04812633320794354, + "mrr_at_3": 0.026660641662900997, + "mrr_at_5": 0.035314053321283304, + "nauc_map_at_1000_diff1": -0.2820073510691976, + "nauc_map_at_1000_max": -0.22327770370483588, + "nauc_map_at_1000_std": -0.024717430734300883, + "nauc_map_at_100_diff1": -0.2818607923258023, + "nauc_map_at_100_max": -0.22416110181134336, + "nauc_map_at_100_std": -0.028024510414374093, + "nauc_map_at_10_diff1": -0.2906538378608659, + "nauc_map_at_10_max": -0.22821591258886104, + "nauc_map_at_10_std": -0.04316335492662491, + "nauc_map_at_1_diff1": -0.5209907834802938, + "nauc_map_at_1_max": -0.23639085506889307, + "nauc_map_at_1_std": 0.2177926602237001, + "nauc_map_at_20_diff1": -0.2860220902240123, + "nauc_map_at_20_max": -0.22700304117166167, + "nauc_map_at_20_std": -0.038147265275491685, + "nauc_map_at_3_diff1": -0.28041936945608975, + "nauc_map_at_3_max": -0.21056679409972542, + "nauc_map_at_3_std": -0.02597664911610537, + "nauc_map_at_5_diff1": -0.28068723178901134, + "nauc_map_at_5_max": -0.2166518208637452, + "nauc_map_at_5_std": -0.03955479230082604, + "nauc_mrr_at_1000_diff1": -0.28200661899250057, + "nauc_mrr_at_1000_max": -0.22327557643200574, + "nauc_mrr_at_1000_std": -0.024715344181347774, + "nauc_mrr_at_100_diff1": -0.2818600633082652, + "nauc_mrr_at_100_max": -0.22415898316044994, + "nauc_mrr_at_100_std": -0.028022431819882995, + "nauc_mrr_at_10_diff1": -0.2906538378608659, + "nauc_mrr_at_10_max": -0.22821591258886104, + "nauc_mrr_at_10_std": -0.04316335492662491, + "nauc_mrr_at_1_diff1": -0.5209907834802938, + "nauc_mrr_at_1_max": -0.23639085506889307, + "nauc_mrr_at_1_std": 0.2177926602237001, + "nauc_mrr_at_20_diff1": -0.2860220902240123, + "nauc_mrr_at_20_max": -0.22700304117166167, + "nauc_mrr_at_20_std": -0.038147265275491685, + "nauc_mrr_at_3_diff1": -0.28041936945608975, + "nauc_mrr_at_3_max": -0.21056679409972542, + "nauc_mrr_at_3_std": -0.02597664911610537, + "nauc_mrr_at_5_diff1": -0.28068723178901134, + "nauc_mrr_at_5_max": -0.2166518208637452, + "nauc_mrr_at_5_std": -0.03955479230082604, + "nauc_ndcg_at_1000_diff1": -0.26225243999359193, + "nauc_ndcg_at_1000_max": -0.20430930662176958, + "nauc_ndcg_at_1000_std": 0.05166312038320821, + "nauc_ndcg_at_100_diff1": -0.2612877426806319, + "nauc_ndcg_at_100_max": -0.21510338576460797, + "nauc_ndcg_at_100_std": 0.009409164374865846, + "nauc_ndcg_at_10_diff1": -0.29266981723692476, + "nauc_ndcg_at_10_max": -0.23714057041819225, + "nauc_ndcg_at_10_std": -0.05266149704278978, + "nauc_ndcg_at_1_diff1": -0.5209907834802938, + "nauc_ndcg_at_1_max": -0.23639085506889307, + "nauc_ndcg_at_1_std": 0.2177926602237001, + "nauc_ndcg_at_20_diff1": -0.282077142831363, + "nauc_ndcg_at_20_max": -0.23345985600434818, + "nauc_ndcg_at_20_std": -0.04019911129071246, + "nauc_ndcg_at_3_diff1": -0.2745377626136432, + "nauc_ndcg_at_3_max": -0.21238940923158822, + "nauc_ndcg_at_3_std": -0.0355342095396329, + "nauc_ndcg_at_5_diff1": -0.27662377955899115, + "nauc_ndcg_at_5_max": -0.21992515002236324, + "nauc_ndcg_at_5_std": -0.04931929555676223, + "nauc_precision_at_1000_diff1": -0.221354994577445, + "nauc_precision_at_1000_max": -0.14774044738127257, + "nauc_precision_at_1000_std": 0.2516839358348936, + "nauc_precision_at_100_diff1": -0.23209049485495, + "nauc_precision_at_100_max": -0.19520174165800488, + "nauc_precision_at_100_std": 0.07042437956308888, + "nauc_precision_at_10_diff1": -0.296424513978545, + "nauc_precision_at_10_max": -0.24742819789144843, + "nauc_precision_at_10_std": -0.06158964337752558, + "nauc_precision_at_1_diff1": -0.5209907834802938, + "nauc_precision_at_1_max": -0.23639085506889307, + "nauc_precision_at_1_std": 0.2177926602237001, + "nauc_precision_at_20_diff1": -0.2778119614670791, + "nauc_precision_at_20_max": -0.2393653195367634, + "nauc_precision_at_20_std": -0.0387208926012462, + "nauc_precision_at_3_diff1": -0.26711100877502325, + "nauc_precision_at_3_max": -0.21522504578706095, + "nauc_precision_at_3_std": -0.048385818469324486, + "nauc_precision_at_5_diff1": -0.27257238554708857, + "nauc_precision_at_5_max": -0.22417106151037294, + "nauc_precision_at_5_std": -0.06036804670012565, + "nauc_recall_at_1000_diff1": -0.22135499457744623, + "nauc_recall_at_1000_max": -0.14774044738127293, + "nauc_recall_at_1000_std": 0.2516839358348938, + "nauc_recall_at_100_diff1": -0.23209049485495017, + "nauc_recall_at_100_max": -0.19520174165800538, + "nauc_recall_at_100_std": 0.07042437956308875, + "nauc_recall_at_10_diff1": -0.29642451397854525, + "nauc_recall_at_10_max": -0.24742819789144851, + "nauc_recall_at_10_std": -0.0615896433775258, + "nauc_recall_at_1_diff1": -0.5209907834802938, + "nauc_recall_at_1_max": -0.23639085506889307, + "nauc_recall_at_1_std": 0.2177926602237001, + "nauc_recall_at_20_diff1": -0.2778119614670792, + "nauc_recall_at_20_max": -0.23936531953676354, + "nauc_recall_at_20_std": -0.03872089260124639, + "nauc_recall_at_3_diff1": -0.2671110087750233, + "nauc_recall_at_3_max": -0.21522504578706092, + "nauc_recall_at_3_std": -0.04838581846932453, + "nauc_recall_at_5_diff1": -0.2725723855470887, + "nauc_recall_at_5_max": -0.224171061510373, + "nauc_recall_at_5_std": -0.060368046700125806, + "ndcg_at_1": 0.00316, + "ndcg_at_10": 0.07146, + "ndcg_at_100": 0.11832, + "ndcg_at_1000": 0.15766, + "ndcg_at_20": 0.0869, + "ndcg_at_3": 0.03497, + "ndcg_at_5": 0.05058, + "precision_at_1": 0.00316, + "precision_at_10": 0.0162, + "precision_at_100": 0.00398, + "precision_at_1000": 0.00072, + "precision_at_20": 0.01115, + "precision_at_3": 0.01973, + "precision_at_5": 0.01943, + "recall_at_1": 0.00316, + "recall_at_10": 0.162, + "recall_at_100": 0.39765, + "recall_at_1000": 0.71939, + "recall_at_20": 0.223, + "recall_at_3": 0.0592, + "recall_at_5": 0.09715 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/WinoGrande.json b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/WinoGrande.json new file mode 100644 index 000000000..7fb9be08e --- /dev/null +++ b/results/contriever-instruct/2bd46a25019aeea091fd42d1f0fd4801675cf699/WinoGrande.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 2.7763383388519287, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.263, + "map_at_1": 0.10655, + "map_at_10": 0.20174, + "map_at_100": 0.21741, + "map_at_1000": 0.2181, + "map_at_20": 0.21133, + "map_at_3": 0.16325, + "map_at_5": 0.18373, + "mrr_at_1": 0.10655090765588003, + "mrr_at_10": 0.20189737036619418, + "mrr_at_100": 0.21756930148475523, + "mrr_at_1000": 0.21826527511639404, + "mrr_at_20": 0.211491522827722, + "mrr_at_3": 0.16311496974480416, + "mrr_at_5": 0.1838726650881348, + "nauc_map_at_1000_diff1": 0.06334979902748723, + "nauc_map_at_1000_max": 0.18969348781681808, + "nauc_map_at_1000_std": -0.011672905144389888, + "nauc_map_at_100_diff1": 0.06289384399706091, + "nauc_map_at_100_max": 0.18922823466241961, + "nauc_map_at_100_std": -0.011997919242770744, + "nauc_map_at_10_diff1": 0.06303493560685752, + "nauc_map_at_10_max": 0.18954266491393904, + "nauc_map_at_10_std": -0.011750833068116853, + "nauc_map_at_1_diff1": 0.12356431557127477, + "nauc_map_at_1_max": 0.2391579476431955, + "nauc_map_at_1_std": 0.029019339021245587, + "nauc_map_at_20_diff1": 0.06129997000795224, + "nauc_map_at_20_max": 0.18679445308026804, + "nauc_map_at_20_std": -0.015174768830729409, + "nauc_map_at_3_diff1": 0.07014010260190137, + "nauc_map_at_3_max": 0.20608840497795178, + "nauc_map_at_3_std": 0.004278615692103746, + "nauc_map_at_5_diff1": 0.06709221719832446, + "nauc_map_at_5_max": 0.19851309462140854, + "nauc_map_at_5_std": -0.0035577898103791783, + "nauc_mrr_at_1000_diff1": 0.0631353847849095, + "nauc_mrr_at_1000_max": 0.19182946083145958, + "nauc_mrr_at_1000_std": -0.010960831235162678, + "nauc_mrr_at_100_diff1": 0.06268067354433338, + "nauc_mrr_at_100_max": 0.1913591144182202, + "nauc_mrr_at_100_std": -0.011287664413010434, + "nauc_mrr_at_10_diff1": 0.06283835222139413, + "nauc_mrr_at_10_max": 0.19164705410021213, + "nauc_mrr_at_10_std": -0.011036072516202687, + "nauc_mrr_at_1_diff1": 0.12356431557127477, + "nauc_mrr_at_1_max": 0.24426742403910837, + "nauc_mrr_at_1_std": 0.03156903828784515, + "nauc_mrr_at_20_diff1": 0.061091028365006204, + "nauc_mrr_at_20_max": 0.18889568796273196, + "nauc_mrr_at_20_std": -0.014473110471894828, + "nauc_mrr_at_3_diff1": 0.0703675563904024, + "nauc_mrr_at_3_max": 0.2089061726994228, + "nauc_mrr_at_3_std": 0.0031396997327845615, + "nauc_mrr_at_5_diff1": 0.06689976724157556, + "nauc_mrr_at_5_max": 0.2006292397168067, + "nauc_mrr_at_5_std": -0.0029105146970695595, + "nauc_ndcg_at_1000_diff1": 0.053320484737705176, + "nauc_ndcg_at_1000_max": 0.17605990832477905, + "nauc_ndcg_at_1000_std": -0.024133717250398045, + "nauc_ndcg_at_100_diff1": 0.04577468609454854, + "nauc_ndcg_at_100_max": 0.16811847050125428, + "nauc_ndcg_at_100_std": -0.02804925985557146, + "nauc_ndcg_at_10_diff1": 0.04479572488457936, + "nauc_ndcg_at_10_max": 0.16598476079020788, + "nauc_ndcg_at_10_std": -0.031187710945724766, + "nauc_ndcg_at_1_diff1": 0.12356431557127477, + "nauc_ndcg_at_1_max": 0.2391579476431955, + "nauc_ndcg_at_1_std": 0.029019339021245587, + "nauc_ndcg_at_20_diff1": 0.03839876431129752, + "nauc_ndcg_at_20_max": 0.1558043701779071, + "nauc_ndcg_at_20_std": -0.04302890333369242, + "nauc_ndcg_at_3_diff1": 0.06012683610333158, + "nauc_ndcg_at_3_max": 0.19907592084459516, + "nauc_ndcg_at_3_std": -0.0007609908331273876, + "nauc_ndcg_at_5_diff1": 0.05481307026892617, + "nauc_ndcg_at_5_max": 0.18657913264062934, + "nauc_ndcg_at_5_std": -0.013566467497844974, + "nauc_precision_at_1000_diff1": -0.018813965642731377, + "nauc_precision_at_1000_max": 0.02592463079415616, + "nauc_precision_at_1000_std": -0.3264120329980501, + "nauc_precision_at_100_diff1": -0.02905383092408188, + "nauc_precision_at_100_max": 0.075991488344229, + "nauc_precision_at_100_std": -0.09430009469993228, + "nauc_precision_at_10_diff1": 0.0030350729361810864, + "nauc_precision_at_10_max": 0.10940108075758655, + "nauc_precision_at_10_std": -0.07743078190136082, + "nauc_precision_at_1_diff1": 0.12356431557127477, + "nauc_precision_at_1_max": 0.2391579476431955, + "nauc_precision_at_1_std": 0.029019339021245587, + "nauc_precision_at_20_diff1": -0.023231964379364162, + "nauc_precision_at_20_max": 0.06814684086420199, + "nauc_precision_at_20_std": -0.12222550483637137, + "nauc_precision_at_3_diff1": 0.0382322507593966, + "nauc_precision_at_3_max": 0.18348873424252965, + "nauc_precision_at_3_std": -0.011905916814032025, + "nauc_precision_at_5_diff1": 0.028920387065864837, + "nauc_precision_at_5_max": 0.16049704763072586, + "nauc_precision_at_5_std": -0.035564380269768, + "nauc_recall_at_1000_diff1": -0.018813965642725156, + "nauc_recall_at_1000_max": 0.02592463079415909, + "nauc_recall_at_1000_std": -0.32641203299804467, + "nauc_recall_at_100_diff1": -0.029053830924083035, + "nauc_recall_at_100_max": 0.07599148834422872, + "nauc_recall_at_100_std": -0.0943000946999332, + "nauc_recall_at_10_diff1": 0.0030350729361809017, + "nauc_recall_at_10_max": 0.10940108075758646, + "nauc_recall_at_10_std": -0.07743078190136075, + "nauc_recall_at_1_diff1": 0.12356431557127477, + "nauc_recall_at_1_max": 0.2391579476431955, + "nauc_recall_at_1_std": 0.029019339021245587, + "nauc_recall_at_20_diff1": -0.023231964379364298, + "nauc_recall_at_20_max": 0.06814684086420239, + "nauc_recall_at_20_std": -0.12222550483637079, + "nauc_recall_at_3_diff1": 0.03823225075939685, + "nauc_recall_at_3_max": 0.1834887342425298, + "nauc_recall_at_3_std": -0.011905916814031917, + "nauc_recall_at_5_diff1": 0.028920387065864844, + "nauc_recall_at_5_max": 0.1604970476307257, + "nauc_recall_at_5_std": -0.03556438026976824, + "ndcg_at_1": 0.10655, + "ndcg_at_10": 0.263, + "ndcg_at_100": 0.34074, + "ndcg_at_1000": 0.35976, + "ndcg_at_20": 0.29741, + "ndcg_at_3": 0.18191, + "ndcg_at_5": 0.2189, + "precision_at_1": 0.10655, + "precision_at_10": 0.04633, + "precision_at_100": 0.0083, + "precision_at_1000": 0.00098, + "precision_at_20": 0.02991, + "precision_at_3": 0.07866, + "precision_at_5": 0.06519, + "recall_at_1": 0.10655, + "recall_at_10": 0.4633, + "recall_at_100": 0.83031, + "recall_at_1000": 0.98106, + "recall_at_20": 0.59826, + "recall_at_3": 0.23599, + "recall_at_5": 0.32597 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/ARCChallenge.json b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/ARCChallenge.json new file mode 100644 index 000000000..d4dd7fd6e --- /dev/null +++ b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/ARCChallenge.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 4.198807001113892, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.08625, + "map_at_1": 0.02474, + "map_at_10": 0.06292, + "map_at_100": 0.0686, + "map_at_1000": 0.0697, + "map_at_20": 0.06594, + "map_at_3": 0.04778, + "map_at_5": 0.05742, + "mrr_at_1": 0.024744027303754267, + "mrr_at_10": 0.06292357386640664, + "mrr_at_100": 0.06859850570467571, + "mrr_at_1000": 0.06969824072125773, + "mrr_at_20": 0.06593766802556918, + "mrr_at_3": 0.047781569965870324, + "mrr_at_5": 0.05742320819112629, + "nauc_map_at_1000_diff1": -0.07503785534163065, + "nauc_map_at_1000_max": 0.20019055536973476, + "nauc_map_at_1000_std": -0.05564705364157619, + "nauc_map_at_100_diff1": -0.07574627852241933, + "nauc_map_at_100_max": 0.20122779928543025, + "nauc_map_at_100_std": -0.0559694195236952, + "nauc_map_at_10_diff1": -0.07229351127968939, + "nauc_map_at_10_max": 0.2195818129829862, + "nauc_map_at_10_std": -0.0572032521012294, + "nauc_map_at_1_diff1": -0.11669882690594369, + "nauc_map_at_1_max": 0.14675999430540396, + "nauc_map_at_1_std": -0.09771912891979467, + "nauc_map_at_20_diff1": -0.078281588607003, + "nauc_map_at_20_max": 0.20422527457649647, + "nauc_map_at_20_std": -0.05654640441357067, + "nauc_map_at_3_diff1": -0.07996717303285192, + "nauc_map_at_3_max": 0.22267375173973022, + "nauc_map_at_3_std": -0.05138316581591901, + "nauc_map_at_5_diff1": -0.07125996859899864, + "nauc_map_at_5_max": 0.23135433688158266, + "nauc_map_at_5_std": -0.06905887409771119, + "nauc_mrr_at_1000_diff1": -0.07503765046438331, + "nauc_mrr_at_1000_max": 0.20019084881989063, + "nauc_mrr_at_1000_std": -0.05564693577191147, + "nauc_mrr_at_100_diff1": -0.07574627852241933, + "nauc_mrr_at_100_max": 0.20122779928543025, + "nauc_mrr_at_100_std": -0.0559694195236952, + "nauc_mrr_at_10_diff1": -0.07229351127968939, + "nauc_mrr_at_10_max": 0.2195818129829862, + "nauc_mrr_at_10_std": -0.0572032521012294, + "nauc_mrr_at_1_diff1": -0.11669882690594369, + "nauc_mrr_at_1_max": 0.14675999430540396, + "nauc_mrr_at_1_std": -0.09771912891979467, + "nauc_mrr_at_20_diff1": -0.078281588607003, + "nauc_mrr_at_20_max": 0.20422527457649647, + "nauc_mrr_at_20_std": -0.05654640441357067, + "nauc_mrr_at_3_diff1": -0.07996717303285192, + "nauc_mrr_at_3_max": 0.22267375173973022, + "nauc_mrr_at_3_std": -0.05138316581591901, + "nauc_mrr_at_5_diff1": -0.07125996859899864, + "nauc_mrr_at_5_max": 0.23135433688158266, + "nauc_mrr_at_5_std": -0.06905887409771119, + "nauc_ndcg_at_1000_diff1": -0.05601318883823922, + "nauc_ndcg_at_1000_max": 0.14712040217319028, + "nauc_ndcg_at_1000_std": -0.04186712089726959, + "nauc_ndcg_at_100_diff1": -0.061627342554924254, + "nauc_ndcg_at_100_max": 0.16853977764493902, + "nauc_ndcg_at_100_std": -0.04054380403643003, + "nauc_ndcg_at_10_diff1": -0.06310838802791228, + "nauc_ndcg_at_10_max": 0.22225410415327415, + "nauc_ndcg_at_10_std": -0.04523772369483768, + "nauc_ndcg_at_1_diff1": -0.11669882690594369, + "nauc_ndcg_at_1_max": 0.14675999430540396, + "nauc_ndcg_at_1_std": -0.09771912891979467, + "nauc_ndcg_at_20_diff1": -0.080170609021867, + "nauc_ndcg_at_20_max": 0.18185538404402243, + "nauc_ndcg_at_20_std": -0.04265707675592225, + "nauc_ndcg_at_3_diff1": -0.07252105941696381, + "nauc_ndcg_at_3_max": 0.23733974863934196, + "nauc_ndcg_at_3_std": -0.03984862425775945, + "nauc_ndcg_at_5_diff1": -0.06048735739587417, + "nauc_ndcg_at_5_max": 0.2459227770599358, + "nauc_ndcg_at_5_std": -0.06751171839816543, + "nauc_precision_at_1000_diff1": -0.015316912457772973, + "nauc_precision_at_1000_max": 0.018350200466562716, + "nauc_precision_at_1000_std": -0.03022170695788968, + "nauc_precision_at_100_diff1": -0.03489159502408994, + "nauc_precision_at_100_max": 0.11377399596161465, + "nauc_precision_at_100_std": -0.020709209792981825, + "nauc_precision_at_10_diff1": -0.050782722529294055, + "nauc_precision_at_10_max": 0.2215363959940383, + "nauc_precision_at_10_std": -0.02684965342234736, + "nauc_precision_at_1_diff1": -0.11669882690594369, + "nauc_precision_at_1_max": 0.14675999430540396, + "nauc_precision_at_1_std": -0.09771912891979467, + "nauc_precision_at_20_diff1": -0.08803663168399224, + "nauc_precision_at_20_max": 0.13971742755777586, + "nauc_precision_at_20_std": -0.022743370324816055, + "nauc_precision_at_3_diff1": -0.0591023677426948, + "nauc_precision_at_3_max": 0.2636586729221896, + "nauc_precision_at_3_std": -0.0187340518472151, + "nauc_precision_at_5_diff1": -0.04359403826044569, + "nauc_precision_at_5_max": 0.2673745831813077, + "nauc_precision_at_5_std": -0.0664653489110818, + "nauc_recall_at_1000_diff1": -0.015316912457772959, + "nauc_recall_at_1000_max": 0.018350200466562553, + "nauc_recall_at_1000_std": -0.030221706957889893, + "nauc_recall_at_100_diff1": -0.034891595024089866, + "nauc_recall_at_100_max": 0.1137739959616146, + "nauc_recall_at_100_std": -0.02070920979298164, + "nauc_recall_at_10_diff1": -0.05078272252929419, + "nauc_recall_at_10_max": 0.22153639599403804, + "nauc_recall_at_10_std": -0.02684965342234745, + "nauc_recall_at_1_diff1": -0.11669882690594369, + "nauc_recall_at_1_max": 0.14675999430540396, + "nauc_recall_at_1_std": -0.09771912891979467, + "nauc_recall_at_20_diff1": -0.08803663168399235, + "nauc_recall_at_20_max": 0.1397174275577759, + "nauc_recall_at_20_std": -0.022743370324816332, + "nauc_recall_at_3_diff1": -0.05910236774269481, + "nauc_recall_at_3_max": 0.2636586729221899, + "nauc_recall_at_3_std": -0.018734051847215015, + "nauc_recall_at_5_diff1": -0.043594038260445625, + "nauc_recall_at_5_max": 0.2673745831813075, + "nauc_recall_at_5_std": -0.06646534891108165, + "ndcg_at_1": 0.02474, + "ndcg_at_10": 0.08625, + "ndcg_at_100": 0.11874, + "ndcg_at_1000": 0.15413, + "ndcg_at_20": 0.09738, + "ndcg_at_3": 0.05585, + "ndcg_at_5": 0.07314, + "precision_at_1": 0.02474, + "precision_at_10": 0.01613, + "precision_at_100": 0.00325, + "precision_at_1000": 0.00062, + "precision_at_20": 0.01028, + "precision_at_3": 0.02645, + "precision_at_5": 0.02423, + "recall_at_1": 0.02474, + "recall_at_10": 0.16126, + "recall_at_100": 0.32509, + "recall_at_1000": 0.61689, + "recall_at_20": 0.20563, + "recall_at_3": 0.07935, + "recall_at_5": 0.12116 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/AlphaNLI.json b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/AlphaNLI.json new file mode 100644 index 000000000..f65fdd2d7 --- /dev/null +++ b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/AlphaNLI.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 55.07283854484558, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.3177, + "map_at_1": 0.21084, + "map_at_10": 0.28355, + "map_at_100": 0.29035, + "map_at_1000": 0.29096, + "map_at_20": 0.28732, + "map_at_3": 0.26893, + "map_at_5": 0.27653, + "mrr_at_1": 0.2108355091383812, + "mrr_at_10": 0.28354521530108984, + "mrr_at_100": 0.2903483844863371, + "mrr_at_1000": 0.2909585825868258, + "mrr_at_20": 0.2873166714708405, + "mrr_at_3": 0.268929503916449, + "mrr_at_5": 0.2765339425587465, + "nauc_map_at_1000_diff1": 0.41464965983036034, + "nauc_map_at_1000_max": 0.3637737640433859, + "nauc_map_at_1000_std": 0.08080204491584193, + "nauc_map_at_100_diff1": 0.4146975526964894, + "nauc_map_at_100_max": 0.3637340029962519, + "nauc_map_at_100_std": 0.08064852674193054, + "nauc_map_at_10_diff1": 0.41730805380468017, + "nauc_map_at_10_max": 0.3659067568173936, + "nauc_map_at_10_std": 0.07723068494586076, + "nauc_map_at_1_diff1": 0.4298471703674125, + "nauc_map_at_1_max": 0.3402911966782907, + "nauc_map_at_1_std": 0.062304589193738553, + "nauc_map_at_20_diff1": 0.4155044649614464, + "nauc_map_at_20_max": 0.3642584226696012, + "nauc_map_at_20_std": 0.07871092346525088, + "nauc_map_at_3_diff1": 0.4266210342569162, + "nauc_map_at_3_max": 0.3741090092521068, + "nauc_map_at_3_std": 0.07653069936561765, + "nauc_map_at_5_diff1": 0.4233891426876927, + "nauc_map_at_5_max": 0.3732916203721649, + "nauc_map_at_5_std": 0.07750860764938167, + "nauc_mrr_at_1000_diff1": 0.41464965983036034, + "nauc_mrr_at_1000_max": 0.3637737640433859, + "nauc_mrr_at_1000_std": 0.08080204491584193, + "nauc_mrr_at_100_diff1": 0.4146975526964894, + "nauc_mrr_at_100_max": 0.3637340029962519, + "nauc_mrr_at_100_std": 0.08064852674193054, + "nauc_mrr_at_10_diff1": 0.41730805380468017, + "nauc_mrr_at_10_max": 0.3659067568173936, + "nauc_mrr_at_10_std": 0.07723068494586076, + "nauc_mrr_at_1_diff1": 0.4298471703674125, + "nauc_mrr_at_1_max": 0.3402911966782907, + "nauc_mrr_at_1_std": 0.062304589193738553, + "nauc_mrr_at_20_diff1": 0.4155044649614464, + "nauc_mrr_at_20_max": 0.3642584226696012, + "nauc_mrr_at_20_std": 0.07871092346525088, + "nauc_mrr_at_3_diff1": 0.4266210342569162, + "nauc_mrr_at_3_max": 0.3741090092521068, + "nauc_mrr_at_3_std": 0.07653069936561765, + "nauc_mrr_at_5_diff1": 0.4233891426876927, + "nauc_mrr_at_5_max": 0.3732916203721649, + "nauc_mrr_at_5_std": 0.07750860764938167, + "nauc_ndcg_at_1000_diff1": 0.39222150602732814, + "nauc_ndcg_at_1000_max": 0.3553990712423281, + "nauc_ndcg_at_1000_std": 0.10353744188570821, + "nauc_ndcg_at_100_diff1": 0.3920536607845743, + "nauc_ndcg_at_100_max": 0.3557795902539295, + "nauc_ndcg_at_100_std": 0.10171245798988388, + "nauc_ndcg_at_10_diff1": 0.4050387508242976, + "nauc_ndcg_at_10_max": 0.3647053439210174, + "nauc_ndcg_at_10_std": 0.08290227939710429, + "nauc_ndcg_at_1_diff1": 0.4298471703674125, + "nauc_ndcg_at_1_max": 0.3402911966782907, + "nauc_ndcg_at_1_std": 0.062304589193738553, + "nauc_ndcg_at_20_diff1": 0.3992730103751803, + "nauc_ndcg_at_20_max": 0.35915144542255706, + "nauc_ndcg_at_20_std": 0.08821255661683751, + "nauc_ndcg_at_3_diff1": 0.42472527744858046, + "nauc_ndcg_at_3_max": 0.3832096072843773, + "nauc_ndcg_at_3_std": 0.08192590583441198, + "nauc_ndcg_at_5_diff1": 0.4193575340185265, + "nauc_ndcg_at_5_max": 0.381796676017095, + "nauc_ndcg_at_5_std": 0.08402625380177318, + "nauc_precision_at_1000_diff1": 0.26461725747294856, + "nauc_precision_at_1000_max": 0.28820702870044435, + "nauc_precision_at_1000_std": 0.24807009057415993, + "nauc_precision_at_100_diff1": 0.2975074569937229, + "nauc_precision_at_100_max": 0.3146408575658512, + "nauc_precision_at_100_std": 0.19521410998816377, + "nauc_precision_at_10_diff1": 0.36699616925547074, + "nauc_precision_at_10_max": 0.3553134646564747, + "nauc_precision_at_10_std": 0.09783187149095915, + "nauc_precision_at_1_diff1": 0.4298471703674125, + "nauc_precision_at_1_max": 0.3402911966782907, + "nauc_precision_at_1_std": 0.062304589193738553, + "nauc_precision_at_20_diff1": 0.3461620115955797, + "nauc_precision_at_20_max": 0.3350327482910721, + "nauc_precision_at_20_std": 0.1178424599886613, + "nauc_precision_at_3_diff1": 0.4194227605969881, + "nauc_precision_at_3_max": 0.40713390770924496, + "nauc_precision_at_3_std": 0.09659534266799565, + "nauc_precision_at_5_diff1": 0.4080122206019544, + "nauc_precision_at_5_max": 0.4037466551126099, + "nauc_precision_at_5_std": 0.10200499931950503, + "nauc_recall_at_1000_diff1": 0.26461725747294995, + "nauc_recall_at_1000_max": 0.2882070287004462, + "nauc_recall_at_1000_std": 0.24807009057416066, + "nauc_recall_at_100_diff1": 0.2975074569937223, + "nauc_recall_at_100_max": 0.3146408575658501, + "nauc_recall_at_100_std": 0.1952141099881635, + "nauc_recall_at_10_diff1": 0.36699616925547074, + "nauc_recall_at_10_max": 0.35531346465647434, + "nauc_recall_at_10_std": 0.09783187149095901, + "nauc_recall_at_1_diff1": 0.4298471703674125, + "nauc_recall_at_1_max": 0.3402911966782907, + "nauc_recall_at_1_std": 0.062304589193738553, + "nauc_recall_at_20_diff1": 0.3461620115955795, + "nauc_recall_at_20_max": 0.33503274829107244, + "nauc_recall_at_20_std": 0.11784245998866137, + "nauc_recall_at_3_diff1": 0.4194227605969884, + "nauc_recall_at_3_max": 0.4071339077092453, + "nauc_recall_at_3_std": 0.0965953426679958, + "nauc_recall_at_5_diff1": 0.40801222060195425, + "nauc_recall_at_5_max": 0.4037466551126098, + "nauc_recall_at_5_std": 0.10200499931950462, + "ndcg_at_1": 0.21084, + "ndcg_at_10": 0.3177, + "ndcg_at_100": 0.35332, + "ndcg_at_1000": 0.37268, + "ndcg_at_20": 0.3313, + "ndcg_at_3": 0.28694, + "ndcg_at_5": 0.30065, + "precision_at_1": 0.21084, + "precision_at_10": 0.04249, + "precision_at_100": 0.00597, + "precision_at_1000": 0.00076, + "precision_at_20": 0.02392, + "precision_at_3": 0.11292, + "precision_at_5": 0.07441, + "recall_at_1": 0.21084, + "recall_at_10": 0.42493, + "recall_at_100": 0.59726, + "recall_at_1000": 0.75653, + "recall_at_20": 0.47846, + "recall_at_3": 0.33877, + "recall_at_5": 0.37206 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/HellaSwag.json b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/HellaSwag.json new file mode 100644 index 000000000..b2d7ae677 --- /dev/null +++ b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/HellaSwag.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 142.913836479187, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.14424, + "map_at_1": 0.07718, + "map_at_10": 0.1203, + "map_at_100": 0.12651, + "map_at_1000": 0.12738, + "map_at_20": 0.12345, + "map_at_3": 0.10737, + "map_at_5": 0.11478, + "mrr_at_1": 0.07717586138219479, + "mrr_at_10": 0.12029764670921807, + "mrr_at_100": 0.12651428015383653, + "mrr_at_1000": 0.12738349603943552, + "mrr_at_20": 0.12344804644577856, + "mrr_at_3": 0.10736573059815473, + "mrr_at_5": 0.1147795923786766, + "nauc_map_at_1000_diff1": 0.2489195520130454, + "nauc_map_at_1000_max": 0.23278008140787884, + "nauc_map_at_1000_std": -0.11989945735647656, + "nauc_map_at_100_diff1": 0.24887828620014288, + "nauc_map_at_100_max": 0.2326835275616637, + "nauc_map_at_100_std": -0.12063415796983029, + "nauc_map_at_10_diff1": 0.2524360535920799, + "nauc_map_at_10_max": 0.23647024566002295, + "nauc_map_at_10_std": -0.12471518297546637, + "nauc_map_at_1_diff1": 0.31523845029979625, + "nauc_map_at_1_max": 0.2360598136046342, + "nauc_map_at_1_std": -0.1322897141951276, + "nauc_map_at_20_diff1": 0.25027226099733235, + "nauc_map_at_20_max": 0.23442218318422964, + "nauc_map_at_20_std": -0.12289380440269947, + "nauc_map_at_3_diff1": 0.2679640162843905, + "nauc_map_at_3_max": 0.24194793050113345, + "nauc_map_at_3_std": -0.1259249344485724, + "nauc_map_at_5_diff1": 0.25708027662222704, + "nauc_map_at_5_max": 0.23734621693729924, + "nauc_map_at_5_std": -0.12721093042238046, + "nauc_mrr_at_1000_diff1": 0.2489195520130454, + "nauc_mrr_at_1000_max": 0.23278008140787884, + "nauc_mrr_at_1000_std": -0.11989945735647656, + "nauc_mrr_at_100_diff1": 0.24887828620014288, + "nauc_mrr_at_100_max": 0.2326835275616637, + "nauc_mrr_at_100_std": -0.12063415796983029, + "nauc_mrr_at_10_diff1": 0.2524360535920799, + "nauc_mrr_at_10_max": 0.23647024566002295, + "nauc_mrr_at_10_std": -0.12471518297546637, + "nauc_mrr_at_1_diff1": 0.31523845029979625, + "nauc_mrr_at_1_max": 0.2360598136046342, + "nauc_mrr_at_1_std": -0.1322897141951276, + "nauc_mrr_at_20_diff1": 0.25027226099733235, + "nauc_mrr_at_20_max": 0.23442218318422964, + "nauc_mrr_at_20_std": -0.12289380440269947, + "nauc_mrr_at_3_diff1": 0.2679640162843905, + "nauc_mrr_at_3_max": 0.24194793050113345, + "nauc_mrr_at_3_std": -0.1259249344485724, + "nauc_mrr_at_5_diff1": 0.25708027662222704, + "nauc_mrr_at_5_max": 0.23734621693729924, + "nauc_mrr_at_5_std": -0.12721093042238046, + "nauc_ndcg_at_1000_diff1": 0.21736980116073085, + "nauc_ndcg_at_1000_max": 0.21921615011747173, + "nauc_ndcg_at_1000_std": -0.08636244099150821, + "nauc_ndcg_at_100_diff1": 0.2178271648648035, + "nauc_ndcg_at_100_max": 0.21768530180967596, + "nauc_ndcg_at_100_std": -0.10261378222801311, + "nauc_ndcg_at_10_diff1": 0.2315335061861902, + "nauc_ndcg_at_10_max": 0.23468373047821003, + "nauc_ndcg_at_10_std": -0.12177418033327726, + "nauc_ndcg_at_1_diff1": 0.31523845029979625, + "nauc_ndcg_at_1_max": 0.2360598136046342, + "nauc_ndcg_at_1_std": -0.1322897141951276, + "nauc_ndcg_at_20_diff1": 0.2252566572716716, + "nauc_ndcg_at_20_max": 0.22819603035463087, + "nauc_ndcg_at_20_std": -0.11617099012806514, + "nauc_ndcg_at_3_diff1": 0.25740716602330715, + "nauc_ndcg_at_3_max": 0.24417440588778694, + "nauc_ndcg_at_3_std": -0.12530745725937403, + "nauc_ndcg_at_5_diff1": 0.2404522558499794, + "nauc_ndcg_at_5_max": 0.23648733584657466, + "nauc_ndcg_at_5_std": -0.12733870646681864, + "nauc_precision_at_1000_diff1": 0.1389254454468051, + "nauc_precision_at_1000_max": 0.1793143463245329, + "nauc_precision_at_1000_std": 0.0473611362929036, + "nauc_precision_at_100_diff1": 0.15544691602576272, + "nauc_precision_at_100_max": 0.17846268256873088, + "nauc_precision_at_100_std": -0.05507832598903149, + "nauc_precision_at_10_diff1": 0.18971343621630815, + "nauc_precision_at_10_max": 0.23042681226812622, + "nauc_precision_at_10_std": -0.11507044260938319, + "nauc_precision_at_1_diff1": 0.31523845029979625, + "nauc_precision_at_1_max": 0.2360598136046342, + "nauc_precision_at_1_std": -0.1322897141951276, + "nauc_precision_at_20_diff1": 0.1758679910069338, + "nauc_precision_at_20_max": 0.21303945928471682, + "nauc_precision_at_20_std": -0.10046871653503592, + "nauc_precision_at_3_diff1": 0.23388065463586646, + "nauc_precision_at_3_max": 0.24937644185225963, + "nauc_precision_at_3_std": -0.12414319565321476, + "nauc_precision_at_5_diff1": 0.20531166800417625, + "nauc_precision_at_5_max": 0.23415353992859314, + "nauc_precision_at_5_std": -0.12793011716377795, + "nauc_recall_at_1000_diff1": 0.13892544544680624, + "nauc_recall_at_1000_max": 0.17931434632453327, + "nauc_recall_at_1000_std": 0.04736113629290454, + "nauc_recall_at_100_diff1": 0.1554469160257624, + "nauc_recall_at_100_max": 0.1784626825687308, + "nauc_recall_at_100_std": -0.05507832598903161, + "nauc_recall_at_10_diff1": 0.18971343621630812, + "nauc_recall_at_10_max": 0.2304268122681262, + "nauc_recall_at_10_std": -0.1150704426093831, + "nauc_recall_at_1_diff1": 0.31523845029979625, + "nauc_recall_at_1_max": 0.2360598136046342, + "nauc_recall_at_1_std": -0.1322897141951276, + "nauc_recall_at_20_diff1": 0.175867991006934, + "nauc_recall_at_20_max": 0.213039459284717, + "nauc_recall_at_20_std": -0.10046871653503589, + "nauc_recall_at_3_diff1": 0.23388065463586655, + "nauc_recall_at_3_max": 0.24937644185225957, + "nauc_recall_at_3_std": -0.12414319565321492, + "nauc_recall_at_5_diff1": 0.2053116680041763, + "nauc_recall_at_5_max": 0.2341535399285932, + "nauc_recall_at_5_std": -0.12793011716377803, + "ndcg_at_1": 0.07718, + "ndcg_at_10": 0.14424, + "ndcg_at_100": 0.17918, + "ndcg_at_1000": 0.20685, + "ndcg_at_20": 0.15568, + "ndcg_at_3": 0.11735, + "ndcg_at_5": 0.13074, + "precision_at_1": 0.07718, + "precision_at_10": 0.02209, + "precision_at_100": 0.00396, + "precision_at_1000": 0.00062, + "precision_at_20": 0.0133, + "precision_at_3": 0.04876, + "precision_at_5": 0.03577, + "recall_at_1": 0.07718, + "recall_at_10": 0.22087, + "recall_at_100": 0.39554, + "recall_at_1000": 0.62378, + "recall_at_20": 0.26608, + "recall_at_3": 0.14629, + "recall_at_5": 0.17885 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/HellaSwagInstruct.json b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/HellaSwagInstruct.json new file mode 100644 index 000000000..d62c5eb74 --- /dev/null +++ b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/HellaSwagInstruct.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 144.09529757499695, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.17727, + "map_at_1": 0.0961, + "map_at_10": 0.14809, + "map_at_100": 0.15514, + "map_at_1000": 0.15596, + "map_at_20": 0.15181, + "map_at_3": 0.13223, + "map_at_5": 0.14082, + "mrr_at_1": 0.09609639514041028, + "mrr_at_10": 0.14808886012082562, + "mrr_at_100": 0.15513892570539206, + "mrr_at_1000": 0.15596442342131533, + "mrr_at_20": 0.15181476448253828, + "mrr_at_3": 0.13222797583482698, + "mrr_at_5": 0.14082188143132196, + "nauc_map_at_1000_diff1": 0.2416518476060783, + "nauc_map_at_1000_max": 0.258161542093426, + "nauc_map_at_1000_std": -0.037588836226125855, + "nauc_map_at_100_diff1": 0.24166569620050402, + "nauc_map_at_100_max": 0.25817818832117995, + "nauc_map_at_100_std": -0.038040436671362234, + "nauc_map_at_10_diff1": 0.24369286133492912, + "nauc_map_at_10_max": 0.2601721806850714, + "nauc_map_at_10_std": -0.04309866543129877, + "nauc_map_at_1_diff1": 0.275127505038763, + "nauc_map_at_1_max": 0.24017726683059373, + "nauc_map_at_1_std": -0.05703022980668142, + "nauc_map_at_20_diff1": 0.24188315603947844, + "nauc_map_at_20_max": 0.25867441686453435, + "nauc_map_at_20_std": -0.04047121013013198, + "nauc_map_at_3_diff1": 0.2524358587110016, + "nauc_map_at_3_max": 0.2613765057666734, + "nauc_map_at_3_std": -0.05013349046472182, + "nauc_map_at_5_diff1": 0.24660732730337048, + "nauc_map_at_5_max": 0.26025679170126187, + "nauc_map_at_5_std": -0.0457108923247949, + "nauc_mrr_at_1000_diff1": 0.2416518476060783, + "nauc_mrr_at_1000_max": 0.258161542093426, + "nauc_mrr_at_1000_std": -0.037588836226125855, + "nauc_mrr_at_100_diff1": 0.24166569620050402, + "nauc_mrr_at_100_max": 0.25817818832117995, + "nauc_mrr_at_100_std": -0.038040436671362234, + "nauc_mrr_at_10_diff1": 0.24369286133492912, + "nauc_mrr_at_10_max": 0.2601721806850714, + "nauc_mrr_at_10_std": -0.04309866543129877, + "nauc_mrr_at_1_diff1": 0.275127505038763, + "nauc_mrr_at_1_max": 0.24017726683059373, + "nauc_mrr_at_1_std": -0.05703022980668142, + "nauc_mrr_at_20_diff1": 0.24188315603947844, + "nauc_mrr_at_20_max": 0.25867441686453435, + "nauc_mrr_at_20_std": -0.04047121013013198, + "nauc_mrr_at_3_diff1": 0.2524358587110016, + "nauc_mrr_at_3_max": 0.2613765057666734, + "nauc_mrr_at_3_std": -0.05013349046472182, + "nauc_mrr_at_5_diff1": 0.24660732730337048, + "nauc_mrr_at_5_max": 0.26025679170126187, + "nauc_mrr_at_5_std": -0.0457108923247949, + "nauc_ndcg_at_1000_diff1": 0.22289654839471437, + "nauc_ndcg_at_1000_max": 0.2547732127011377, + "nauc_ndcg_at_1000_std": -0.002079319126649355, + "nauc_ndcg_at_100_diff1": 0.22278680893188396, + "nauc_ndcg_at_100_max": 0.25464981410817095, + "nauc_ndcg_at_100_std": -0.012083889546732786, + "nauc_ndcg_at_10_diff1": 0.230865551249667, + "nauc_ndcg_at_10_max": 0.26351180851012723, + "nauc_ndcg_at_10_std": -0.035301523296799975, + "nauc_ndcg_at_1_diff1": 0.275127505038763, + "nauc_ndcg_at_1_max": 0.24017726683059373, + "nauc_ndcg_at_1_std": -0.05703022980668142, + "nauc_ndcg_at_20_diff1": 0.22562872729908875, + "nauc_ndcg_at_20_max": 0.25863714027004225, + "nauc_ndcg_at_20_std": -0.027226029829870574, + "nauc_ndcg_at_3_diff1": 0.246034852793174, + "nauc_ndcg_at_3_max": 0.26625797978175436, + "nauc_ndcg_at_3_std": -0.04829415630441208, + "nauc_ndcg_at_5_diff1": 0.23702056998438903, + "nauc_ndcg_at_5_max": 0.26442587383489385, + "nauc_ndcg_at_5_std": -0.041190043076210395, + "nauc_precision_at_1000_diff1": 0.1663953093923317, + "nauc_precision_at_1000_max": 0.2357706782041582, + "nauc_precision_at_1000_std": 0.15172336782348889, + "nauc_precision_at_100_diff1": 0.17741889779138556, + "nauc_precision_at_100_max": 0.2383591190333661, + "nauc_precision_at_100_std": 0.0619035012060006, + "nauc_precision_at_10_diff1": 0.203009834601923, + "nauc_precision_at_10_max": 0.2692805188842993, + "nauc_precision_at_10_std": -0.017481966073983817, + "nauc_precision_at_1_diff1": 0.275127505038763, + "nauc_precision_at_1_max": 0.24017726683059373, + "nauc_precision_at_1_std": -0.05703022980668142, + "nauc_precision_at_20_diff1": 0.1901135222536406, + "nauc_precision_at_20_max": 0.25500317305442716, + "nauc_precision_at_20_std": 0.004298767433233511, + "nauc_precision_at_3_diff1": 0.23115386624613599, + "nauc_precision_at_3_max": 0.2773619758683157, + "nauc_precision_at_3_std": -0.04404170712059525, + "nauc_precision_at_5_diff1": 0.21574589129071764, + "nauc_precision_at_5_max": 0.27314010743007133, + "nauc_precision_at_5_std": -0.030902075442030275, + "nauc_recall_at_1000_diff1": 0.16639530939233207, + "nauc_recall_at_1000_max": 0.2357706782041586, + "nauc_recall_at_1000_std": 0.15172336782348897, + "nauc_recall_at_100_diff1": 0.1774188977913854, + "nauc_recall_at_100_max": 0.23835911903336635, + "nauc_recall_at_100_std": 0.06190350120600047, + "nauc_recall_at_10_diff1": 0.20300983460192343, + "nauc_recall_at_10_max": 0.26928051888429977, + "nauc_recall_at_10_std": -0.0174819660739838, + "nauc_recall_at_1_diff1": 0.275127505038763, + "nauc_recall_at_1_max": 0.24017726683059373, + "nauc_recall_at_1_std": -0.05703022980668142, + "nauc_recall_at_20_diff1": 0.19011352225364098, + "nauc_recall_at_20_max": 0.25500317305442755, + "nauc_recall_at_20_std": 0.004298767433233838, + "nauc_recall_at_3_diff1": 0.23115386624613588, + "nauc_recall_at_3_max": 0.27736197586831585, + "nauc_recall_at_3_std": -0.044041707120595276, + "nauc_recall_at_5_diff1": 0.21574589129071767, + "nauc_recall_at_5_max": 0.2731401074300715, + "nauc_recall_at_5_std": -0.030902075442030098, + "ndcg_at_1": 0.0961, + "ndcg_at_10": 0.17727, + "ndcg_at_100": 0.21634, + "ndcg_at_1000": 0.24213, + "ndcg_at_20": 0.19094, + "ndcg_at_3": 0.14431, + "ndcg_at_5": 0.15974, + "precision_at_1": 0.0961, + "precision_at_10": 0.02708, + "precision_at_100": 0.00465, + "precision_at_1000": 0.00068, + "precision_at_20": 0.01625, + "precision_at_3": 0.05978, + "precision_at_5": 0.04334, + "recall_at_1": 0.0961, + "recall_at_10": 0.27076, + "recall_at_100": 0.46465, + "recall_at_1000": 0.67626, + "recall_at_20": 0.32503, + "recall_at_3": 0.17935, + "recall_at_5": 0.21669 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/PIQA.json b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/PIQA.json new file mode 100644 index 000000000..4f6731f3b --- /dev/null +++ b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/PIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 17.49898338317871, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.24642, + "map_at_1": 0.11697, + "map_at_10": 0.2023, + "map_at_100": 0.21013, + "map_at_1000": 0.21081, + "map_at_20": 0.20638, + "map_at_3": 0.17873, + "map_at_5": 0.19178, + "mrr_at_1": 0.11697497279651796, + "mrr_at_10": 0.2022986942328617, + "mrr_at_100": 0.21013131713667582, + "mrr_at_1000": 0.21080886095649498, + "mrr_at_20": 0.20638444226893018, + "mrr_at_3": 0.17872687704026105, + "mrr_at_5": 0.1917845484221978, + "nauc_map_at_1000_diff1": -0.05808300327838839, + "nauc_map_at_1000_max": 0.13595025376921333, + "nauc_map_at_1000_std": -0.11853292927402584, + "nauc_map_at_100_diff1": -0.058150253772371006, + "nauc_map_at_100_max": 0.13628765276880694, + "nauc_map_at_100_std": -0.1181412617710445, + "nauc_map_at_10_diff1": -0.05575514038379583, + "nauc_map_at_10_max": 0.139855621786153, + "nauc_map_at_10_std": -0.11875818884800003, + "nauc_map_at_1_diff1": -0.018694666679524595, + "nauc_map_at_1_max": 0.1389253210817904, + "nauc_map_at_1_std": -0.11287467304783264, + "nauc_map_at_20_diff1": -0.05721992883949902, + "nauc_map_at_20_max": 0.138029378107834, + "nauc_map_at_20_std": -0.11854219814692339, + "nauc_map_at_3_diff1": -0.05232735694432252, + "nauc_map_at_3_max": 0.151356241022005, + "nauc_map_at_3_std": -0.12079124362643355, + "nauc_map_at_5_diff1": -0.05138462509004602, + "nauc_map_at_5_max": 0.14558526574883582, + "nauc_map_at_5_std": -0.11632719548453635, + "nauc_mrr_at_1000_diff1": -0.05808300410519006, + "nauc_mrr_at_1000_max": 0.1359502495405716, + "nauc_mrr_at_1000_std": -0.11853292411430014, + "nauc_mrr_at_100_diff1": -0.058150253772371006, + "nauc_mrr_at_100_max": 0.13628765276880694, + "nauc_mrr_at_100_std": -0.1181412617710445, + "nauc_mrr_at_10_diff1": -0.05575514038379583, + "nauc_mrr_at_10_max": 0.139855621786153, + "nauc_mrr_at_10_std": -0.11875818884800003, + "nauc_mrr_at_1_diff1": -0.018694666679524595, + "nauc_mrr_at_1_max": 0.1389253210817904, + "nauc_mrr_at_1_std": -0.11287467304783264, + "nauc_mrr_at_20_diff1": -0.05721992883949902, + "nauc_mrr_at_20_max": 0.138029378107834, + "nauc_mrr_at_20_std": -0.11854219814692339, + "nauc_mrr_at_3_diff1": -0.05232735694432252, + "nauc_mrr_at_3_max": 0.151356241022005, + "nauc_mrr_at_3_std": -0.12079124362643355, + "nauc_mrr_at_5_diff1": -0.05138462509004602, + "nauc_mrr_at_5_max": 0.14558526574883582, + "nauc_mrr_at_5_std": -0.11632719548453635, + "nauc_ndcg_at_1000_diff1": -0.07839344848680255, + "nauc_ndcg_at_1000_max": 0.1038585672298334, + "nauc_ndcg_at_1000_std": -0.12531741744193878, + "nauc_ndcg_at_100_diff1": -0.07834916945129443, + "nauc_ndcg_at_100_max": 0.11348330290501771, + "nauc_ndcg_at_100_std": -0.11322368272937897, + "nauc_ndcg_at_10_diff1": -0.06585910856174011, + "nauc_ndcg_at_10_max": 0.13214714585073, + "nauc_ndcg_at_10_std": -0.11862756814306573, + "nauc_ndcg_at_1_diff1": -0.018694666679524595, + "nauc_ndcg_at_1_max": 0.1389253210817904, + "nauc_ndcg_at_1_std": -0.11287467304783264, + "nauc_ndcg_at_20_diff1": -0.07149634349397264, + "nauc_ndcg_at_20_max": 0.12575012076823827, + "nauc_ndcg_at_20_std": -0.11818045085457259, + "nauc_ndcg_at_3_diff1": -0.058724174906017355, + "nauc_ndcg_at_3_max": 0.15367383016834896, + "nauc_ndcg_at_3_std": -0.12081733428187653, + "nauc_ndcg_at_5_diff1": -0.05637907145255812, + "nauc_ndcg_at_5_max": 0.1445753384831078, + "nauc_ndcg_at_5_std": -0.11317152589546775, + "nauc_precision_at_1000_diff1": -0.18202975553913586, + "nauc_precision_at_1000_max": -0.10805993589925253, + "nauc_precision_at_1000_std": -0.2027605042369537, + "nauc_precision_at_100_diff1": -0.14616394844901437, + "nauc_precision_at_100_max": 0.027846829686044253, + "nauc_precision_at_100_std": -0.08972774807207405, + "nauc_precision_at_10_diff1": -0.08904480286837882, + "nauc_precision_at_10_max": 0.1115504861248612, + "nauc_precision_at_10_std": -0.11869763819855404, + "nauc_precision_at_1_diff1": -0.018694666679524595, + "nauc_precision_at_1_max": 0.1389253210817904, + "nauc_precision_at_1_std": -0.11287467304783264, + "nauc_precision_at_20_diff1": -0.1083024273719949, + "nauc_precision_at_20_max": 0.09067992352770994, + "nauc_precision_at_20_std": -0.11772335192761743, + "nauc_precision_at_3_diff1": -0.07304974120133614, + "nauc_precision_at_3_max": 0.15884916488530768, + "nauc_precision_at_3_std": -0.12040499842601901, + "nauc_precision_at_5_diff1": -0.06630959960481465, + "nauc_precision_at_5_max": 0.1415682296567003, + "nauc_precision_at_5_std": -0.1049238006956388, + "nauc_recall_at_1000_diff1": -0.18202975553913547, + "nauc_recall_at_1000_max": -0.10805993589925156, + "nauc_recall_at_1000_std": -0.2027605042369527, + "nauc_recall_at_100_diff1": -0.14616394844901529, + "nauc_recall_at_100_max": 0.02784682968604321, + "nauc_recall_at_100_std": -0.08972774807207455, + "nauc_recall_at_10_diff1": -0.08904480286837879, + "nauc_recall_at_10_max": 0.11155048612486108, + "nauc_recall_at_10_std": -0.11869763819855389, + "nauc_recall_at_1_diff1": -0.018694666679524595, + "nauc_recall_at_1_max": 0.1389253210817904, + "nauc_recall_at_1_std": -0.11287467304783264, + "nauc_recall_at_20_diff1": -0.10830242737199511, + "nauc_recall_at_20_max": 0.09067992352770984, + "nauc_recall_at_20_std": -0.11772335192761758, + "nauc_recall_at_3_diff1": -0.07304974120133623, + "nauc_recall_at_3_max": 0.15884916488530784, + "nauc_recall_at_3_std": -0.1204049984260193, + "nauc_recall_at_5_diff1": -0.06630959960481475, + "nauc_recall_at_5_max": 0.14156822965670016, + "nauc_recall_at_5_std": -0.10492380069563878, + "ndcg_at_1": 0.11697, + "ndcg_at_10": 0.24642, + "ndcg_at_100": 0.28956, + "ndcg_at_1000": 0.31009, + "ndcg_at_20": 0.26147, + "ndcg_at_3": 0.19762, + "ndcg_at_5": 0.22092, + "precision_at_1": 0.11697, + "precision_at_10": 0.03868, + "precision_at_100": 0.006, + "precision_at_1000": 0.00077, + "precision_at_20": 0.02233, + "precision_at_3": 0.08397, + "precision_at_5": 0.06159, + "recall_at_1": 0.11697, + "recall_at_10": 0.38683, + "recall_at_100": 0.60011, + "recall_at_1000": 0.76714, + "recall_at_20": 0.44668, + "recall_at_3": 0.2519, + "recall_at_5": 0.30794 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/Quail.json b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/Quail.json new file mode 100644 index 000000000..24acc655e --- /dev/null +++ b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/Quail.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 26.636348009109497, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.04965, + "map_at_1": 0.01397, + "map_at_10": 0.03524, + "map_at_100": 0.0414, + "map_at_1000": 0.04226, + "map_at_20": 0.03831, + "map_at_3": 0.02598, + "map_at_5": 0.03098, + "mrr_at_1": 0.013970588235294118, + "mrr_at_10": 0.035243785014005616, + "mrr_at_100": 0.041399825520441046, + "mrr_at_1000": 0.042262161044586875, + "mrr_at_20": 0.038310321023638856, + "mrr_at_3": 0.025980392156862746, + "mrr_at_5": 0.03098039215686276, + "nauc_map_at_1000_diff1": 0.08390038158206269, + "nauc_map_at_1000_max": 0.13788969521275737, + "nauc_map_at_1000_std": 0.08133173758091956, + "nauc_map_at_100_diff1": 0.0844693453095357, + "nauc_map_at_100_max": 0.13876917235265573, + "nauc_map_at_100_std": 0.08159828616544933, + "nauc_map_at_10_diff1": 0.09510647372948101, + "nauc_map_at_10_max": 0.13651466717069302, + "nauc_map_at_10_std": 0.06954503499902728, + "nauc_map_at_1_diff1": 0.1797339471565955, + "nauc_map_at_1_max": 0.22530467569514065, + "nauc_map_at_1_std": 0.11890472088458325, + "nauc_map_at_20_diff1": 0.08866224375706397, + "nauc_map_at_20_max": 0.13666805223779105, + "nauc_map_at_20_std": 0.07610572550628704, + "nauc_map_at_3_diff1": 0.10652568457609185, + "nauc_map_at_3_max": 0.15910350780383845, + "nauc_map_at_3_std": 0.07908821906434946, + "nauc_map_at_5_diff1": 0.09931997474807516, + "nauc_map_at_5_max": 0.14245102026607068, + "nauc_map_at_5_std": 0.07493136171896489, + "nauc_mrr_at_1000_diff1": 0.08389748542485172, + "nauc_mrr_at_1000_max": 0.13787988694590386, + "nauc_mrr_at_1000_std": 0.0813465377158533, + "nauc_mrr_at_100_diff1": 0.08446632018686367, + "nauc_mrr_at_100_max": 0.1387592825611439, + "nauc_mrr_at_100_std": 0.08161325036800063, + "nauc_mrr_at_10_diff1": 0.09510647372948101, + "nauc_mrr_at_10_max": 0.13651466717069302, + "nauc_mrr_at_10_std": 0.06954503499902728, + "nauc_mrr_at_1_diff1": 0.1797339471565955, + "nauc_mrr_at_1_max": 0.22530467569514065, + "nauc_mrr_at_1_std": 0.11890472088458325, + "nauc_mrr_at_20_diff1": 0.08863940011032677, + "nauc_mrr_at_20_max": 0.13665389286634502, + "nauc_mrr_at_20_std": 0.07612677396026811, + "nauc_mrr_at_3_diff1": 0.10652568457609185, + "nauc_mrr_at_3_max": 0.15910350780383845, + "nauc_mrr_at_3_std": 0.07908821906434946, + "nauc_mrr_at_5_diff1": 0.09931997474807516, + "nauc_mrr_at_5_max": 0.14245102026607068, + "nauc_mrr_at_5_std": 0.07493136171896489, + "nauc_ndcg_at_1000_diff1": 0.04490828878345455, + "nauc_ndcg_at_1000_max": 0.11794841229792596, + "nauc_ndcg_at_1000_std": 0.09979623864187488, + "nauc_ndcg_at_100_diff1": 0.05514928442382914, + "nauc_ndcg_at_100_max": 0.12989795181173167, + "nauc_ndcg_at_100_std": 0.09864728638888845, + "nauc_ndcg_at_10_diff1": 0.08253827820697522, + "nauc_ndcg_at_10_max": 0.11692268729593873, + "nauc_ndcg_at_10_std": 0.05865295134287739, + "nauc_ndcg_at_1_diff1": 0.1797339471565955, + "nauc_ndcg_at_1_max": 0.22530467569514065, + "nauc_ndcg_at_1_std": 0.11890472088458325, + "nauc_ndcg_at_20_diff1": 0.06863473927053182, + "nauc_ndcg_at_20_max": 0.1206415520795786, + "nauc_ndcg_at_20_std": 0.07764665560795121, + "nauc_ndcg_at_3_diff1": 0.09434879433901047, + "nauc_ndcg_at_3_max": 0.1465399310474371, + "nauc_ndcg_at_3_std": 0.0712208275607836, + "nauc_ndcg_at_5_diff1": 0.08779402974534528, + "nauc_ndcg_at_5_max": 0.12466113755004062, + "nauc_ndcg_at_5_std": 0.06598075188240042, + "nauc_precision_at_1000_diff1": -0.002450708017673169, + "nauc_precision_at_1000_max": 0.09411580403147801, + "nauc_precision_at_1000_std": 0.12781524226810403, + "nauc_precision_at_100_diff1": 0.02670323836489142, + "nauc_precision_at_100_max": 0.12669751319391703, + "nauc_precision_at_100_std": 0.12172962619838262, + "nauc_precision_at_10_diff1": 0.06840033010545504, + "nauc_precision_at_10_max": 0.09319584359831233, + "nauc_precision_at_10_std": 0.045480970152287546, + "nauc_precision_at_1_diff1": 0.1797339471565955, + "nauc_precision_at_1_max": 0.22530467569514065, + "nauc_precision_at_1_std": 0.11890472088458325, + "nauc_precision_at_20_diff1": 0.04686242743142385, + "nauc_precision_at_20_max": 0.10616286558423219, + "nauc_precision_at_20_std": 0.08418958719117339, + "nauc_precision_at_3_diff1": 0.07208815840399282, + "nauc_precision_at_3_max": 0.12325982842258479, + "nauc_precision_at_3_std": 0.05658777967997223, + "nauc_precision_at_5_diff1": 0.07146976551970867, + "nauc_precision_at_5_max": 0.0975561990939063, + "nauc_precision_at_5_std": 0.052371788347843826, + "nauc_recall_at_1000_diff1": -0.002450708017673026, + "nauc_recall_at_1000_max": 0.09411580403147811, + "nauc_recall_at_1000_std": 0.12781524226810437, + "nauc_recall_at_100_diff1": 0.026703238364891118, + "nauc_recall_at_100_max": 0.12669751319391692, + "nauc_recall_at_100_std": 0.12172962619838243, + "nauc_recall_at_10_diff1": 0.06840033010545479, + "nauc_recall_at_10_max": 0.09319584359831205, + "nauc_recall_at_10_std": 0.04548097015228749, + "nauc_recall_at_1_diff1": 0.1797339471565955, + "nauc_recall_at_1_max": 0.22530467569514065, + "nauc_recall_at_1_std": 0.11890472088458325, + "nauc_recall_at_20_diff1": 0.04686242743142379, + "nauc_recall_at_20_max": 0.10616286558423198, + "nauc_recall_at_20_std": 0.08418958719117339, + "nauc_recall_at_3_diff1": 0.07208815840399273, + "nauc_recall_at_3_max": 0.12325982842258476, + "nauc_recall_at_3_std": 0.05658777967997232, + "nauc_recall_at_5_diff1": 0.07146976551970873, + "nauc_recall_at_5_max": 0.09755619909390634, + "nauc_recall_at_5_std": 0.05237178834784396, + "ndcg_at_1": 0.01397, + "ndcg_at_10": 0.04965, + "ndcg_at_100": 0.08459, + "ndcg_at_1000": 0.11202, + "ndcg_at_20": 0.06093, + "ndcg_at_3": 0.02997, + "ndcg_at_5": 0.0391, + "precision_at_1": 0.01397, + "precision_at_10": 0.00971, + "precision_at_100": 0.00272, + "precision_at_1000": 0.0005, + "precision_at_20": 0.0071, + "precision_at_3": 0.01385, + "precision_at_5": 0.01279, + "recall_at_1": 0.01397, + "recall_at_10": 0.09706, + "recall_at_100": 0.27206, + "recall_at_1000": 0.49816, + "recall_at_20": 0.14191, + "recall_at_3": 0.04154, + "recall_at_5": 0.06397 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/RARbCode.json b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/RARbCode.json new file mode 100644 index 000000000..ca5a25892 --- /dev/null +++ b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/RARbCode.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 954.8524498939514, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.09277, + "map_at_1": 0.05121, + "map_at_10": 0.0776, + "map_at_100": 0.08133, + "map_at_1000": 0.08188, + "map_at_20": 0.07938, + "map_at_3": 0.06941, + "map_at_5": 0.07382, + "mrr_at_1": 0.05121293800539083, + "mrr_at_10": 0.07759728105078509, + "mrr_at_100": 0.08133153199252423, + "mrr_at_1000": 0.08187924473846216, + "mrr_at_20": 0.0793776832253817, + "mrr_at_3": 0.06940700808625334, + "mrr_at_5": 0.07382075471698112, + "nauc_map_at_1000_diff1": 0.35401154915635275, + "nauc_map_at_1000_max": -0.26828043254162076, + "nauc_map_at_1000_std": -0.19159161519996362, + "nauc_map_at_100_diff1": 0.35455292850414655, + "nauc_map_at_100_max": -0.26800019575806217, + "nauc_map_at_100_std": -0.1915185900980698, + "nauc_map_at_10_diff1": 0.3704073345132165, + "nauc_map_at_10_max": -0.268388225596004, + "nauc_map_at_10_std": -0.19214369633242934, + "nauc_map_at_1_diff1": 0.5203524225124883, + "nauc_map_at_1_max": -0.2880958934098659, + "nauc_map_at_1_std": -0.20991404996199375, + "nauc_map_at_20_diff1": 0.36042514158301164, + "nauc_map_at_20_max": -0.26706484064293773, + "nauc_map_at_20_std": -0.19076466403904505, + "nauc_map_at_3_diff1": 0.4021516610271751, + "nauc_map_at_3_max": -0.26196452469599607, + "nauc_map_at_3_std": -0.1914376363150567, + "nauc_map_at_5_diff1": 0.3901633284335388, + "nauc_map_at_5_max": -0.2633913002123089, + "nauc_map_at_5_std": -0.19038831595551578, + "nauc_mrr_at_1000_diff1": 0.35401154915635275, + "nauc_mrr_at_1000_max": -0.26828043254162076, + "nauc_mrr_at_1000_std": -0.19159161519996362, + "nauc_mrr_at_100_diff1": 0.35455292850414655, + "nauc_mrr_at_100_max": -0.26800019575806217, + "nauc_mrr_at_100_std": -0.1915185900980698, + "nauc_mrr_at_10_diff1": 0.3704073345132165, + "nauc_mrr_at_10_max": -0.268388225596004, + "nauc_mrr_at_10_std": -0.19214369633242934, + "nauc_mrr_at_1_diff1": 0.5203524225124883, + "nauc_mrr_at_1_max": -0.2880958934098659, + "nauc_mrr_at_1_std": -0.20991404996199375, + "nauc_mrr_at_20_diff1": 0.36042514158301164, + "nauc_mrr_at_20_max": -0.26706484064293773, + "nauc_mrr_at_20_std": -0.19076466403904505, + "nauc_mrr_at_3_diff1": 0.4021516610271751, + "nauc_mrr_at_3_max": -0.26196452469599607, + "nauc_mrr_at_3_std": -0.1914376363150567, + "nauc_mrr_at_5_diff1": 0.3901633284335388, + "nauc_mrr_at_5_max": -0.2633913002123089, + "nauc_mrr_at_5_std": -0.19038831595551578, + "nauc_ndcg_at_1000_diff1": 0.25033308362211903, + "nauc_ndcg_at_1000_max": -0.2788306253536546, + "nauc_ndcg_at_1000_std": -0.1915178077579413, + "nauc_ndcg_at_100_diff1": 0.2630087611695114, + "nauc_ndcg_at_100_max": -0.2728068637780355, + "nauc_ndcg_at_100_std": -0.18959942175213487, + "nauc_ndcg_at_10_diff1": 0.318745010737214, + "nauc_ndcg_at_10_max": -0.2690073547696398, + "nauc_ndcg_at_10_std": -0.18899390806372954, + "nauc_ndcg_at_1_diff1": 0.5203524225124883, + "nauc_ndcg_at_1_max": -0.2880958934098659, + "nauc_ndcg_at_1_std": -0.20991404996199375, + "nauc_ndcg_at_20_diff1": 0.2906244548875524, + "nauc_ndcg_at_20_max": -0.2650258425398977, + "nauc_ndcg_at_20_std": -0.18486398328390657, + "nauc_ndcg_at_3_diff1": 0.3742442014226653, + "nauc_ndcg_at_3_max": -0.2551906894593382, + "nauc_ndcg_at_3_std": -0.18584199535676804, + "nauc_ndcg_at_5_diff1": 0.3568366180981496, + "nauc_ndcg_at_5_max": -0.2587395094317223, + "nauc_ndcg_at_5_std": -0.18555124237174458, + "nauc_precision_at_1000_diff1": 0.07103511646007994, + "nauc_precision_at_1000_max": -0.30976316020470634, + "nauc_precision_at_1000_std": -0.19744342984966773, + "nauc_precision_at_100_diff1": 0.1056353261730364, + "nauc_precision_at_100_max": -0.2883280475707598, + "nauc_precision_at_100_std": -0.19039696978046608, + "nauc_precision_at_10_diff1": 0.21962818990866584, + "nauc_precision_at_10_max": -0.272733242548255, + "nauc_precision_at_10_std": -0.1842208514816151, + "nauc_precision_at_1_diff1": 0.5203524225124883, + "nauc_precision_at_1_max": -0.2880958934098659, + "nauc_precision_at_1_std": -0.20991404996199375, + "nauc_precision_at_20_diff1": 0.15973513789563237, + "nauc_precision_at_20_max": -0.26235041682301113, + "nauc_precision_at_20_std": -0.174248306530238, + "nauc_precision_at_3_diff1": 0.3139829563659031, + "nauc_precision_at_3_max": -0.24042443233411498, + "nauc_precision_at_3_std": -0.17347472325114285, + "nauc_precision_at_5_diff1": 0.2899894324979175, + "nauc_precision_at_5_max": -0.2502392863067239, + "nauc_precision_at_5_std": -0.1763271432751085, + "nauc_recall_at_1000_diff1": 0.07103511646008033, + "nauc_recall_at_1000_max": -0.3097631602047062, + "nauc_recall_at_1000_std": -0.19744342984966767, + "nauc_recall_at_100_diff1": 0.10563532617303652, + "nauc_recall_at_100_max": -0.28832804757075975, + "nauc_recall_at_100_std": -0.19039696978046616, + "nauc_recall_at_10_diff1": 0.2196281899086657, + "nauc_recall_at_10_max": -0.27273324254825526, + "nauc_recall_at_10_std": -0.18422085148161535, + "nauc_recall_at_1_diff1": 0.5203524225124883, + "nauc_recall_at_1_max": -0.2880958934098659, + "nauc_recall_at_1_std": -0.20991404996199375, + "nauc_recall_at_20_diff1": 0.15973513789563226, + "nauc_recall_at_20_max": -0.26235041682301136, + "nauc_recall_at_20_std": -0.17424830653023818, + "nauc_recall_at_3_diff1": 0.31398295636590334, + "nauc_recall_at_3_max": -0.24042443233411476, + "nauc_recall_at_3_std": -0.1734747232511426, + "nauc_recall_at_5_diff1": 0.2899894324979172, + "nauc_recall_at_5_max": -0.25023928630672393, + "nauc_recall_at_5_std": -0.1763271432751085, + "ndcg_at_1": 0.05121, + "ndcg_at_10": 0.09277, + "ndcg_at_100": 0.11391, + "ndcg_at_1000": 0.13184, + "ndcg_at_20": 0.09925, + "ndcg_at_3": 0.07562, + "ndcg_at_5": 0.08362, + "precision_at_1": 0.05121, + "precision_at_10": 0.01415, + "precision_at_100": 0.00247, + "precision_at_1000": 0.0004, + "precision_at_20": 0.00836, + "precision_at_3": 0.03122, + "precision_at_5": 0.02264, + "recall_at_1": 0.05121, + "recall_at_10": 0.14151, + "recall_at_100": 0.2473, + "recall_at_1000": 0.39555, + "recall_at_20": 0.16712, + "recall_at_3": 0.09367, + "recall_at_5": 0.11321 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/RARbMath.json b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/RARbMath.json new file mode 100644 index 000000000..307993f5d --- /dev/null +++ b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/RARbMath.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 1472.4594745635986, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.30763, + "map_at_1": 0.26571, + "map_at_10": 0.29218, + "map_at_100": 0.29805, + "map_at_1000": 0.29888, + "map_at_20": 0.29504, + "map_at_3": 0.28335, + "map_at_5": 0.28804, + "mrr_at_1": 0.26570659914543443, + "mrr_at_10": 0.2921806117604504, + "mrr_at_100": 0.2980529656017837, + "mrr_at_1000": 0.29887527048737605, + "mrr_at_20": 0.2950446489024367, + "mrr_at_3": 0.28335179617028006, + "mrr_at_5": 0.2880439943028961, + "nauc_map_at_1000_diff1": 0.7417212432821269, + "nauc_map_at_1000_max": 0.08351475649398588, + "nauc_map_at_1000_std": 0.07959885309544415, + "nauc_map_at_100_diff1": 0.741755376553399, + "nauc_map_at_100_max": 0.0834667901747804, + "nauc_map_at_100_std": 0.07946753646483252, + "nauc_map_at_10_diff1": 0.7488626492382462, + "nauc_map_at_10_max": 0.08617214779364177, + "nauc_map_at_10_std": 0.07897928230698079, + "nauc_map_at_1_diff1": 0.8007829027463825, + "nauc_map_at_1_max": 0.09404452826283598, + "nauc_map_at_1_std": 0.0794655774594768, + "nauc_map_at_20_diff1": 0.7443885972757602, + "nauc_map_at_20_max": 0.08469625665764015, + "nauc_map_at_20_std": 0.07878195004756841, + "nauc_map_at_3_diff1": 0.7601864023700721, + "nauc_map_at_3_max": 0.08922543220970638, + "nauc_map_at_3_std": 0.08178632848277642, + "nauc_map_at_5_diff1": 0.7550473606839307, + "nauc_map_at_5_max": 0.08754910280952342, + "nauc_map_at_5_std": 0.08096667097049443, + "nauc_mrr_at_1000_diff1": 0.7417212302979967, + "nauc_mrr_at_1000_max": 0.08351479107504697, + "nauc_mrr_at_1000_std": 0.07959881348850427, + "nauc_mrr_at_100_diff1": 0.7417553603652478, + "nauc_mrr_at_100_max": 0.08346682346129579, + "nauc_mrr_at_100_std": 0.0794674975449608, + "nauc_mrr_at_10_diff1": 0.7488626492382462, + "nauc_mrr_at_10_max": 0.08617214779364177, + "nauc_mrr_at_10_std": 0.07897928230698079, + "nauc_mrr_at_1_diff1": 0.8007829027463825, + "nauc_mrr_at_1_max": 0.09404452826283598, + "nauc_mrr_at_1_std": 0.0794655774594768, + "nauc_mrr_at_20_diff1": 0.7443885972757602, + "nauc_mrr_at_20_max": 0.08469625665764015, + "nauc_mrr_at_20_std": 0.07878195004756841, + "nauc_mrr_at_3_diff1": 0.7601864023700721, + "nauc_mrr_at_3_max": 0.08922543220970638, + "nauc_mrr_at_3_std": 0.08178632848277642, + "nauc_mrr_at_5_diff1": 0.7550473606839307, + "nauc_mrr_at_5_max": 0.08754910280952342, + "nauc_mrr_at_5_std": 0.08096667097049443, + "nauc_ndcg_at_1000_diff1": 0.6906544129296731, + "nauc_ndcg_at_1000_max": 0.07396594903932102, + "nauc_ndcg_at_1000_std": 0.08979758904664599, + "nauc_ndcg_at_100_diff1": 0.6886757446913293, + "nauc_ndcg_at_100_max": 0.06680211228516182, + "nauc_ndcg_at_100_std": 0.08031304323773988, + "nauc_ndcg_at_10_diff1": 0.7238680597581191, + "nauc_ndcg_at_10_max": 0.08164852134457577, + "nauc_ndcg_at_10_std": 0.07618696648040828, + "nauc_ndcg_at_1_diff1": 0.8007829027463825, + "nauc_ndcg_at_1_max": 0.09404452826283598, + "nauc_ndcg_at_1_std": 0.0794655774594768, + "nauc_ndcg_at_20_diff1": 0.7079212421429188, + "nauc_ndcg_at_20_max": 0.07609715523845785, + "nauc_ndcg_at_20_std": 0.07561416664413816, + "nauc_ndcg_at_3_diff1": 0.7477960218831712, + "nauc_ndcg_at_3_max": 0.08808712516833783, + "nauc_ndcg_at_3_std": 0.08278216153068997, + "nauc_ndcg_at_5_diff1": 0.7386797870008486, + "nauc_ndcg_at_5_max": 0.0851222580119643, + "nauc_ndcg_at_5_std": 0.08118716622279157, + "nauc_precision_at_1000_diff1": 0.4106571690736353, + "nauc_precision_at_1000_max": 0.06153279928710612, + "nauc_precision_at_1000_std": 0.2226288570950737, + "nauc_precision_at_100_diff1": 0.47997064938377854, + "nauc_precision_at_100_max": -0.006050318325951343, + "nauc_precision_at_100_std": 0.08848486412291684, + "nauc_precision_at_10_diff1": 0.6485387686066915, + "nauc_precision_at_10_max": 0.06745835940784446, + "nauc_precision_at_10_std": 0.0661849212326936, + "nauc_precision_at_1_diff1": 0.8007829027463825, + "nauc_precision_at_1_max": 0.09404452826283598, + "nauc_precision_at_1_std": 0.0794655774594768, + "nauc_precision_at_20_diff1": 0.5902098596287434, + "nauc_precision_at_20_max": 0.04640968258160396, + "nauc_precision_at_20_std": 0.06447282824758756, + "nauc_precision_at_3_diff1": 0.7132083671535956, + "nauc_precision_at_3_max": 0.08501169010652858, + "nauc_precision_at_3_std": 0.08565034021323668, + "nauc_precision_at_5_diff1": 0.6920701036643534, + "nauc_precision_at_5_max": 0.07810184864134123, + "nauc_precision_at_5_std": 0.0815760126754957, + "nauc_recall_at_1000_diff1": 0.41065716907363564, + "nauc_recall_at_1000_max": 0.06153279928710715, + "nauc_recall_at_1000_std": 0.22262885709507485, + "nauc_recall_at_100_diff1": 0.4799706493837786, + "nauc_recall_at_100_max": -0.006050318325951978, + "nauc_recall_at_100_std": 0.08848486412291658, + "nauc_recall_at_10_diff1": 0.6485387686066917, + "nauc_recall_at_10_max": 0.06745835940784452, + "nauc_recall_at_10_std": 0.06618492123269397, + "nauc_recall_at_1_diff1": 0.8007829027463825, + "nauc_recall_at_1_max": 0.09404452826283598, + "nauc_recall_at_1_std": 0.0794655774594768, + "nauc_recall_at_20_diff1": 0.5902098596287434, + "nauc_recall_at_20_max": 0.04640968258160403, + "nauc_recall_at_20_std": 0.06447282824758775, + "nauc_recall_at_3_diff1": 0.7132083671535955, + "nauc_recall_at_3_max": 0.08501169010652876, + "nauc_recall_at_3_std": 0.08565034021323686, + "nauc_recall_at_5_diff1": 0.6920701036643533, + "nauc_recall_at_5_max": 0.07810184864134118, + "nauc_recall_at_5_std": 0.08157601267549597, + "ndcg_at_1": 0.26571, + "ndcg_at_10": 0.30763, + "ndcg_at_100": 0.34104, + "ndcg_at_1000": 0.36782, + "ndcg_at_20": 0.31808, + "ndcg_at_3": 0.28914, + "ndcg_at_5": 0.29761, + "precision_at_1": 0.26571, + "precision_at_10": 0.03575, + "precision_at_100": 0.00525, + "precision_at_1000": 0.00075, + "precision_at_20": 0.01994, + "precision_at_3": 0.10197, + "precision_at_5": 0.0653, + "recall_at_1": 0.26571, + "recall_at_10": 0.35749, + "recall_at_100": 0.52492, + "recall_at_1000": 0.74695, + "recall_at_20": 0.3988, + "recall_at_3": 0.3059, + "recall_at_5": 0.32648 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/SIQA.json b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/SIQA.json new file mode 100644 index 000000000..edb610c96 --- /dev/null +++ b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/SIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 12.704170942306519, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01273, + "map_at_1": 0.00665, + "map_at_10": 0.01061, + "map_at_100": 0.01141, + "map_at_1000": 0.01187, + "map_at_20": 0.01086, + "map_at_3": 0.00964, + "map_at_5": 0.01012, + "mrr_at_1": 0.006653019447287615, + "mrr_at_10": 0.010606245227534889, + "mrr_at_100": 0.011409576939383664, + "mrr_at_1000": 0.011865151365149243, + "mrr_at_20": 0.010862938403274016, + "mrr_at_3": 0.009638348686455134, + "mrr_at_5": 0.010124530876833845, + "nauc_map_at_1000_diff1": 0.3737510995993764, + "nauc_map_at_1000_max": 0.18511109844182103, + "nauc_map_at_1000_std": -0.2784552848496064, + "nauc_map_at_100_diff1": 0.38497840481567897, + "nauc_map_at_100_max": 0.19125541455976872, + "nauc_map_at_100_std": -0.28207828673317686, + "nauc_map_at_10_diff1": 0.41883719645347456, + "nauc_map_at_10_max": 0.21476610014545136, + "nauc_map_at_10_std": -0.28010527311251127, + "nauc_map_at_1_diff1": 0.48018089980177026, + "nauc_map_at_1_max": 0.1599204582025653, + "nauc_map_at_1_std": -0.33622525518437857, + "nauc_map_at_20_diff1": 0.40376888347829415, + "nauc_map_at_20_max": 0.20300339530256417, + "nauc_map_at_20_std": -0.2844127329664659, + "nauc_map_at_3_diff1": 0.45028062344066183, + "nauc_map_at_3_max": 0.24212225015873984, + "nauc_map_at_3_std": -0.2843845222335648, + "nauc_map_at_5_diff1": 0.4295397195235376, + "nauc_map_at_5_max": 0.2185445647380687, + "nauc_map_at_5_std": -0.28593297861016476, + "nauc_mrr_at_1000_diff1": 0.37375123538594507, + "nauc_mrr_at_1000_max": 0.18511120457301777, + "nauc_mrr_at_1000_std": -0.27845542978350085, + "nauc_mrr_at_100_diff1": 0.38497840481567897, + "nauc_mrr_at_100_max": 0.19125541455976872, + "nauc_mrr_at_100_std": -0.28207828673317686, + "nauc_mrr_at_10_diff1": 0.41883719645347456, + "nauc_mrr_at_10_max": 0.21476610014545136, + "nauc_mrr_at_10_std": -0.28010527311251127, + "nauc_mrr_at_1_diff1": 0.48018089980177026, + "nauc_mrr_at_1_max": 0.1599204582025653, + "nauc_mrr_at_1_std": -0.33622525518437857, + "nauc_mrr_at_20_diff1": 0.40376888347829415, + "nauc_mrr_at_20_max": 0.20300339530256417, + "nauc_mrr_at_20_std": -0.2844127329664659, + "nauc_mrr_at_3_diff1": 0.45028062344066183, + "nauc_mrr_at_3_max": 0.24212225015873984, + "nauc_mrr_at_3_std": -0.2843845222335648, + "nauc_mrr_at_5_diff1": 0.4295397195235376, + "nauc_mrr_at_5_max": 0.2185445647380687, + "nauc_mrr_at_5_std": -0.28593297861016476, + "nauc_ndcg_at_1000_diff1": 0.15948622664301848, + "nauc_ndcg_at_1000_max": 0.06738018325421476, + "nauc_ndcg_at_1000_std": -0.18443237137259905, + "nauc_ndcg_at_100_diff1": 0.28024772824667993, + "nauc_ndcg_at_100_max": 0.1266986020017747, + "nauc_ndcg_at_100_std": -0.2763025629567869, + "nauc_ndcg_at_10_diff1": 0.3920492301161086, + "nauc_ndcg_at_10_max": 0.21233243489898562, + "nauc_ndcg_at_10_std": -0.2676388516491353, + "nauc_ndcg_at_1_diff1": 0.48018089980177026, + "nauc_ndcg_at_1_max": 0.1599204582025653, + "nauc_ndcg_at_1_std": -0.33622525518437857, + "nauc_ndcg_at_20_diff1": 0.35166922375149196, + "nauc_ndcg_at_20_max": 0.17896431240663396, + "nauc_ndcg_at_20_std": -0.2804917526544537, + "nauc_ndcg_at_3_diff1": 0.44090088856711823, + "nauc_ndcg_at_3_max": 0.258301031282504, + "nauc_ndcg_at_3_std": -0.2744041139926692, + "nauc_ndcg_at_5_diff1": 0.41070945197458825, + "nauc_ndcg_at_5_max": 0.22048693334118202, + "nauc_ndcg_at_5_std": -0.27788377136635856, + "nauc_precision_at_1000_diff1": 0.054563741447668145, + "nauc_precision_at_1000_max": 0.010801144239414431, + "nauc_precision_at_1000_std": -0.11709427239040744, + "nauc_precision_at_100_diff1": 0.16146156716969012, + "nauc_precision_at_100_max": 0.04324413932849525, + "nauc_precision_at_100_std": -0.27517977569801055, + "nauc_precision_at_10_diff1": 0.3441993254582537, + "nauc_precision_at_10_max": 0.20361441937256072, + "nauc_precision_at_10_std": -0.24660806672359348, + "nauc_precision_at_1_diff1": 0.48018089980177026, + "nauc_precision_at_1_max": 0.1599204582025653, + "nauc_precision_at_1_std": -0.33622525518437857, + "nauc_precision_at_20_diff1": 0.25893474897464996, + "nauc_precision_at_20_max": 0.1275621369265935, + "nauc_precision_at_20_std": -0.27933761728137213, + "nauc_precision_at_3_diff1": 0.421201673760577, + "nauc_precision_at_3_max": 0.29081073874459373, + "nauc_precision_at_3_std": -0.2544037221923495, + "nauc_precision_at_5_diff1": 0.3733708750104791, + "nauc_precision_at_5_max": 0.22072599744668153, + "nauc_precision_at_5_std": -0.26361181553642943, + "nauc_recall_at_1000_diff1": 0.054563741447668304, + "nauc_recall_at_1000_max": 0.010801144239414669, + "nauc_recall_at_1000_std": -0.11709427239040723, + "nauc_recall_at_100_diff1": 0.16146156716969004, + "nauc_recall_at_100_max": 0.043244139328495225, + "nauc_recall_at_100_std": -0.27517977569801044, + "nauc_recall_at_10_diff1": 0.34419932545825394, + "nauc_recall_at_10_max": 0.20361441937256092, + "nauc_recall_at_10_std": -0.2466080667235934, + "nauc_recall_at_1_diff1": 0.48018089980177026, + "nauc_recall_at_1_max": 0.1599204582025653, + "nauc_recall_at_1_std": -0.33622525518437857, + "nauc_recall_at_20_diff1": 0.2589347489746495, + "nauc_recall_at_20_max": 0.12756213692659324, + "nauc_recall_at_20_std": -0.27933761728137235, + "nauc_recall_at_3_diff1": 0.4212016737605772, + "nauc_recall_at_3_max": 0.29081073874459373, + "nauc_recall_at_3_std": -0.2544037221923496, + "nauc_recall_at_5_diff1": 0.3733708750104793, + "nauc_recall_at_5_max": 0.2207259974466818, + "nauc_recall_at_5_std": -0.26361181553642943, + "ndcg_at_1": 0.00665, + "ndcg_at_10": 0.01273, + "ndcg_at_100": 0.01796, + "ndcg_at_1000": 0.03986, + "ndcg_at_20": 0.01364, + "ndcg_at_3": 0.0107, + "ndcg_at_5": 0.01156, + "precision_at_1": 0.00665, + "precision_at_10": 0.00194, + "precision_at_100": 0.00047, + "precision_at_1000": 0.00024, + "precision_at_20": 0.00115, + "precision_at_3": 0.00461, + "precision_at_5": 0.00317, + "recall_at_1": 0.00665, + "recall_at_10": 0.01945, + "recall_at_100": 0.04708, + "recall_at_1000": 0.24207, + "recall_at_20": 0.02303, + "recall_at_3": 0.01382, + "recall_at_5": 0.01586 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/SpartQA.json b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/SpartQA.json new file mode 100644 index 000000000..c3ecb25c7 --- /dev/null +++ b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/SpartQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 11.5154550075531, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.10937, + "map_at_1": 0.02606, + "map_at_10": 0.07023, + "map_at_100": 0.08188, + "map_at_1000": 0.08252, + "map_at_20": 0.07665, + "map_at_3": 0.04818, + "map_at_5": 0.05938, + "mrr_at_1": 0.040345019476905955, + "mrr_at_10": 0.09976967785815859, + "mrr_at_100": 0.11183545573479205, + "mrr_at_1000": 0.11249103127499037, + "mrr_at_20": 0.1069617031290768, + "mrr_at_3": 0.07248191430161391, + "mrr_at_5": 0.08720089037284343, + "nauc_map_at_1000_diff1": -0.012884299968845752, + "nauc_map_at_1000_max": 0.11367904844829944, + "nauc_map_at_1000_std": 0.4570038884592614, + "nauc_map_at_100_diff1": -0.013484789978007738, + "nauc_map_at_100_max": 0.11258573964023634, + "nauc_map_at_100_std": 0.4571742727123563, + "nauc_map_at_10_diff1": -0.01747644290972707, + "nauc_map_at_10_max": 0.09884507277165007, + "nauc_map_at_10_std": 0.42360159529448993, + "nauc_map_at_1_diff1": -0.027301694503940568, + "nauc_map_at_1_max": 0.0997758712085053, + "nauc_map_at_1_std": 0.4336939285129919, + "nauc_map_at_20_diff1": -0.015922745895045713, + "nauc_map_at_20_max": 0.10453397333888044, + "nauc_map_at_20_std": 0.44068041569566807, + "nauc_map_at_3_diff1": 0.0018425969899775875, + "nauc_map_at_3_max": 0.11094546731145903, + "nauc_map_at_3_std": 0.3973611401914857, + "nauc_map_at_5_diff1": -0.00763313771079115, + "nauc_map_at_5_max": 0.10495899113801982, + "nauc_map_at_5_std": 0.4029807494767868, + "nauc_mrr_at_1000_diff1": -0.006014478952540444, + "nauc_mrr_at_1000_max": 0.07496027080660356, + "nauc_mrr_at_1000_std": 0.40948492718996593, + "nauc_mrr_at_100_diff1": -0.006426612782753997, + "nauc_mrr_at_100_max": 0.07412341917815789, + "nauc_mrr_at_100_std": 0.4099245086211515, + "nauc_mrr_at_10_diff1": -0.009212802969849256, + "nauc_mrr_at_10_max": 0.05988294186016748, + "nauc_mrr_at_10_std": 0.3870675199399613, + "nauc_mrr_at_1_diff1": -0.024173488179495016, + "nauc_mrr_at_1_max": 0.04613132378411921, + "nauc_mrr_at_1_std": 0.38649095368590664, + "nauc_mrr_at_20_diff1": -0.008213504317931998, + "nauc_mrr_at_20_max": 0.06659158242719983, + "nauc_mrr_at_20_std": 0.40021399690217097, + "nauc_mrr_at_3_diff1": -0.003821899104035929, + "nauc_mrr_at_3_max": 0.056989723112852136, + "nauc_mrr_at_3_std": 0.3584739806259195, + "nauc_mrr_at_5_diff1": -0.00794275596688299, + "nauc_mrr_at_5_max": 0.061401598485793116, + "nauc_mrr_at_5_std": 0.36960260325510763, + "nauc_ndcg_at_1000_diff1": 0.002450964612785688, + "nauc_ndcg_at_1000_max": 0.16449774785492335, + "nauc_ndcg_at_1000_std": 0.5299474611268695, + "nauc_ndcg_at_100_diff1": -0.005944898353803195, + "nauc_ndcg_at_100_max": 0.1457333739007907, + "nauc_ndcg_at_100_std": 0.5414690809728447, + "nauc_ndcg_at_10_diff1": -0.022475269054429165, + "nauc_ndcg_at_10_max": 0.08679193527730004, + "nauc_ndcg_at_10_std": 0.4278508570871857, + "nauc_ndcg_at_1_diff1": -0.024173488179495016, + "nauc_ndcg_at_1_max": 0.04613132378411921, + "nauc_ndcg_at_1_std": 0.38649095368590664, + "nauc_ndcg_at_20_diff1": -0.017145780896402934, + "nauc_ndcg_at_20_max": 0.1041810811315712, + "nauc_ndcg_at_20_std": 0.46838077771682773, + "nauc_ndcg_at_3_diff1": 0.004098672646744799, + "nauc_ndcg_at_3_max": 0.09894085343772253, + "nauc_ndcg_at_3_std": 0.38130474061542635, + "nauc_ndcg_at_5_diff1": -0.008893202527574823, + "nauc_ndcg_at_5_max": 0.09498267767007358, + "nauc_ndcg_at_5_std": 0.393091608743451, + "nauc_precision_at_1000_diff1": 0.06676831410841157, + "nauc_precision_at_1000_max": 0.12676133543265386, + "nauc_precision_at_1000_std": 0.36561171188598024, + "nauc_precision_at_100_diff1": 0.03166426280366826, + "nauc_precision_at_100_max": 0.10076042389083528, + "nauc_precision_at_100_std": 0.5186787148006021, + "nauc_precision_at_10_diff1": -0.016451184133851524, + "nauc_precision_at_10_max": 0.03539422185408668, + "nauc_precision_at_10_std": 0.4296034616204549, + "nauc_precision_at_1_diff1": -0.024173488179495016, + "nauc_precision_at_1_max": 0.04613132378411921, + "nauc_precision_at_1_std": 0.38649095368590664, + "nauc_precision_at_20_diff1": -0.0006624404589841263, + "nauc_precision_at_20_max": 0.05442655960867483, + "nauc_precision_at_20_std": 0.46685004080462944, + "nauc_precision_at_3_diff1": 0.013766594544015217, + "nauc_precision_at_3_max": 0.06806307570800947, + "nauc_precision_at_3_std": 0.35553873496870875, + "nauc_precision_at_5_diff1": 0.006732873287153241, + "nauc_precision_at_5_max": 0.0630575469898749, + "nauc_precision_at_5_std": 0.37695024724894827, + "nauc_recall_at_1000_diff1": 0.02495509328726096, + "nauc_recall_at_1000_max": 0.30139335375208626, + "nauc_recall_at_1000_std": 0.5595555281773883, + "nauc_recall_at_100_diff1": -0.0019102880270316252, + "nauc_recall_at_100_max": 0.22794390809542112, + "nauc_recall_at_100_std": 0.6253771624288742, + "nauc_recall_at_10_diff1": -0.0386990639176558, + "nauc_recall_at_10_max": 0.09448471158428097, + "nauc_recall_at_10_std": 0.4318885913131627, + "nauc_recall_at_1_diff1": -0.027301694503940568, + "nauc_recall_at_1_max": 0.0997758712085053, + "nauc_recall_at_1_std": 0.4336939285129919, + "nauc_recall_at_20_diff1": -0.025363593453454663, + "nauc_recall_at_20_max": 0.12824665893407805, + "nauc_recall_at_20_std": 0.4870368759751516, + "nauc_recall_at_3_diff1": 0.01113843899942044, + "nauc_recall_at_3_max": 0.1192628715495262, + "nauc_recall_at_3_std": 0.3789377529277661, + "nauc_recall_at_5_diff1": -0.016783808587228794, + "nauc_recall_at_5_max": 0.10599053977495954, + "nauc_recall_at_5_std": 0.3837528423710706, + "ndcg_at_1": 0.04035, + "ndcg_at_10": 0.10937, + "ndcg_at_100": 0.16919, + "ndcg_at_1000": 0.19095, + "ndcg_at_20": 0.13296, + "ndcg_at_3": 0.0613, + "ndcg_at_5": 0.08267, + "precision_at_1": 0.04035, + "precision_at_10": 0.03166, + "precision_at_100": 0.0075, + "precision_at_1000": 0.00104, + "precision_at_20": 0.02273, + "precision_at_3": 0.04044, + "precision_at_5": 0.03929, + "recall_at_1": 0.02606, + "recall_at_10": 0.1957, + "recall_at_100": 0.44797, + "recall_at_1000": 0.60666, + "recall_at_20": 0.27787, + "recall_at_3": 0.07624, + "recall_at_5": 0.12261 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL1.json b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL1.json new file mode 100644 index 000000000..313575975 --- /dev/null +++ b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL1.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 6.714665412902832, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01935, + "map_at_1": 0.00475, + "map_at_10": 0.0127, + "map_at_100": 0.01996, + "map_at_1000": 0.02198, + "map_at_20": 0.01559, + "map_at_3": 0.00813, + "map_at_5": 0.00994, + "mrr_at_1": 0.00475, + "mrr_at_10": 0.012703373015873026, + "mrr_at_100": 0.019958378521746527, + "mrr_at_1000": 0.02198237669796602, + "mrr_at_20": 0.01558882004003912, + "mrr_at_3": 0.008125, + "mrr_at_5": 0.009937500000000004, + "nauc_map_at_1000_diff1": 0.03358758877614599, + "nauc_map_at_1000_max": 0.09016594682078828, + "nauc_map_at_1000_std": 0.0267307622372164, + "nauc_map_at_100_diff1": 0.03909357692406776, + "nauc_map_at_100_max": 0.09165539680311537, + "nauc_map_at_100_std": 0.024411136854882408, + "nauc_map_at_10_diff1": 0.06522595700067273, + "nauc_map_at_10_max": 0.10485595211740961, + "nauc_map_at_10_std": 0.03780953010561605, + "nauc_map_at_1_diff1": 0.005493341618064522, + "nauc_map_at_1_max": 0.08456074449606711, + "nauc_map_at_1_std": 0.08936212277406687, + "nauc_map_at_20_diff1": 0.04666058020523278, + "nauc_map_at_20_max": 0.10561066451793782, + "nauc_map_at_20_std": 0.029463259758038915, + "nauc_map_at_3_diff1": 0.07993643062062694, + "nauc_map_at_3_max": 0.12523305332535276, + "nauc_map_at_3_std": 0.06784036105205941, + "nauc_map_at_5_diff1": 0.0709249012391304, + "nauc_map_at_5_max": 0.12411396467164927, + "nauc_map_at_5_std": 0.042936607981081995, + "nauc_mrr_at_1000_diff1": 0.03358758877614599, + "nauc_mrr_at_1000_max": 0.09016594682078828, + "nauc_mrr_at_1000_std": 0.0267307622372164, + "nauc_mrr_at_100_diff1": 0.03909357692406776, + "nauc_mrr_at_100_max": 0.09165539680311537, + "nauc_mrr_at_100_std": 0.024411136854882408, + "nauc_mrr_at_10_diff1": 0.06522595700067273, + "nauc_mrr_at_10_max": 0.10485595211740961, + "nauc_mrr_at_10_std": 0.03780953010561605, + "nauc_mrr_at_1_diff1": 0.005493341618064522, + "nauc_mrr_at_1_max": 0.08456074449606711, + "nauc_mrr_at_1_std": 0.08936212277406687, + "nauc_mrr_at_20_diff1": 0.04666058020523278, + "nauc_mrr_at_20_max": 0.10561066451793782, + "nauc_mrr_at_20_std": 0.029463259758038915, + "nauc_mrr_at_3_diff1": 0.07993643062062694, + "nauc_mrr_at_3_max": 0.12523305332535276, + "nauc_mrr_at_3_std": 0.06784036105205941, + "nauc_mrr_at_5_diff1": 0.0709249012391304, + "nauc_mrr_at_5_max": 0.12411396467164927, + "nauc_mrr_at_5_std": 0.042936607981081995, + "nauc_ndcg_at_1000_diff1": -0.049346483238440805, + "nauc_ndcg_at_1000_max": 0.06673538017605923, + "nauc_ndcg_at_1000_std": 0.05268881319195131, + "nauc_ndcg_at_100_diff1": 0.013565125817110833, + "nauc_ndcg_at_100_max": 0.06293787352889285, + "nauc_ndcg_at_100_std": 0.006208612454200597, + "nauc_ndcg_at_10_diff1": 0.06221617840860352, + "nauc_ndcg_at_10_max": 0.09648540346482119, + "nauc_ndcg_at_10_std": 0.02927344457590965, + "nauc_ndcg_at_1_diff1": 0.005493341618064522, + "nauc_ndcg_at_1_max": 0.08456074449606711, + "nauc_ndcg_at_1_std": 0.08936212277406687, + "nauc_ndcg_at_20_diff1": 0.0272514316787008, + "nauc_ndcg_at_20_max": 0.1033325491708825, + "nauc_ndcg_at_20_std": 0.017221918767334702, + "nauc_ndcg_at_3_diff1": 0.09018677430994582, + "nauc_ndcg_at_3_max": 0.13149099248386933, + "nauc_ndcg_at_3_std": 0.06538008215485906, + "nauc_ndcg_at_5_diff1": 0.0752794611502017, + "nauc_ndcg_at_5_max": 0.1286189893817114, + "nauc_ndcg_at_5_std": 0.031773742303436936, + "nauc_precision_at_1000_diff1": -0.19819839215428073, + "nauc_precision_at_1000_max": 0.06219954206284369, + "nauc_precision_at_1000_std": 0.14590921294584241, + "nauc_precision_at_100_diff1": -0.0003492131167751439, + "nauc_precision_at_100_max": 0.044471636077227775, + "nauc_precision_at_100_std": -0.0029101093064604357, + "nauc_precision_at_10_diff1": 0.056433952593873175, + "nauc_precision_at_10_max": 0.08555306880202551, + "nauc_precision_at_10_std": 0.021575844822295173, + "nauc_precision_at_1_diff1": 0.005493341618064522, + "nauc_precision_at_1_max": 0.08456074449606711, + "nauc_precision_at_1_std": 0.08936212277406687, + "nauc_precision_at_20_diff1": 0.009596296188470056, + "nauc_precision_at_20_max": 0.10250553344973298, + "nauc_precision_at_20_std": 0.009087210944624505, + "nauc_precision_at_3_diff1": 0.10823822005737764, + "nauc_precision_at_3_max": 0.14268539349033044, + "nauc_precision_at_3_std": 0.061180367794266256, + "nauc_precision_at_5_diff1": 0.08025732428737545, + "nauc_precision_at_5_max": 0.13467681142754934, + "nauc_precision_at_5_std": 0.01505743161230167, + "nauc_recall_at_1000_diff1": -0.1981983921542804, + "nauc_recall_at_1000_max": 0.06219954206284466, + "nauc_recall_at_1000_std": 0.1459092129458426, + "nauc_recall_at_100_diff1": -0.0003492131167753125, + "nauc_recall_at_100_max": 0.04447163607722782, + "nauc_recall_at_100_std": -0.002910109306460616, + "nauc_recall_at_10_diff1": 0.05643395259387297, + "nauc_recall_at_10_max": 0.08555306880202564, + "nauc_recall_at_10_std": 0.02157584482229519, + "nauc_recall_at_1_diff1": 0.005493341618064522, + "nauc_recall_at_1_max": 0.08456074449606711, + "nauc_recall_at_1_std": 0.08936212277406687, + "nauc_recall_at_20_diff1": 0.009596296188470108, + "nauc_recall_at_20_max": 0.10250553344973316, + "nauc_recall_at_20_std": 0.009087210944624476, + "nauc_recall_at_3_diff1": 0.1082382200573776, + "nauc_recall_at_3_max": 0.14268539349033044, + "nauc_recall_at_3_std": 0.061180367794266326, + "nauc_recall_at_5_diff1": 0.0802573242873753, + "nauc_recall_at_5_max": 0.13467681142754934, + "nauc_recall_at_5_std": 0.015057431612301523, + "ndcg_at_1": 0.00475, + "ndcg_at_10": 0.01935, + "ndcg_at_100": 0.06616, + "ndcg_at_1000": 0.1292, + "ndcg_at_20": 0.03019, + "ndcg_at_3": 0.00937, + "ndcg_at_5": 0.01265, + "precision_at_1": 0.00475, + "precision_at_10": 0.00417, + "precision_at_100": 0.00288, + "precision_at_1000": 0.0008, + "precision_at_20": 0.00426, + "precision_at_3": 0.00433, + "precision_at_5": 0.0042, + "recall_at_1": 0.00475, + "recall_at_10": 0.04175, + "recall_at_100": 0.28825, + "recall_at_1000": 0.803, + "recall_at_20": 0.08525, + "recall_at_3": 0.013, + "recall_at_5": 0.021 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL2Fact.json b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL2Fact.json new file mode 100644 index 000000000..0f5debeeb --- /dev/null +++ b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL2Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 24.27752375602722, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.22682, + "map_at_1": 0.0819, + "map_at_10": 0.17124, + "map_at_100": 0.18447, + "map_at_1000": 0.18538, + "map_at_20": 0.17825, + "map_at_3": 0.13785, + "map_at_5": 0.15616, + "mrr_at_1": 0.08189735037984065, + "mrr_at_10": 0.17124262156224423, + "mrr_at_100": 0.1844705487225129, + "mrr_at_1000": 0.18538110747241496, + "mrr_at_20": 0.1782523035754543, + "mrr_at_3": 0.13785436353529784, + "mrr_at_5": 0.15616083009079249, + "nauc_map_at_1000_diff1": -0.09530996550480811, + "nauc_map_at_1000_max": -0.13695136768250496, + "nauc_map_at_1000_std": -0.07868436434425875, + "nauc_map_at_100_diff1": -0.09549445032429996, + "nauc_map_at_100_max": -0.13720310033546618, + "nauc_map_at_100_std": -0.07863487717005055, + "nauc_map_at_10_diff1": -0.0924469148214277, + "nauc_map_at_10_max": -0.13427486324899895, + "nauc_map_at_10_std": -0.08280723801445188, + "nauc_map_at_1_diff1": -0.06456623489805553, + "nauc_map_at_1_max": -0.1271205989845521, + "nauc_map_at_1_std": -0.08544254220751434, + "nauc_map_at_20_diff1": -0.0947634960882876, + "nauc_map_at_20_max": -0.13621935853713024, + "nauc_map_at_20_std": -0.08084177433445018, + "nauc_map_at_3_diff1": -0.08161466166090584, + "nauc_map_at_3_max": -0.12561366402743224, + "nauc_map_at_3_std": -0.08901520994075926, + "nauc_map_at_5_diff1": -0.08724239339667741, + "nauc_map_at_5_max": -0.12749295188541282, + "nauc_map_at_5_std": -0.08395972426003237, + "nauc_mrr_at_1000_diff1": -0.09530996550480811, + "nauc_mrr_at_1000_max": -0.13695136768250496, + "nauc_mrr_at_1000_std": -0.07868436434425875, + "nauc_mrr_at_100_diff1": -0.09549445032429996, + "nauc_mrr_at_100_max": -0.13720310033546618, + "nauc_mrr_at_100_std": -0.07863487717005055, + "nauc_mrr_at_10_diff1": -0.0924469148214277, + "nauc_mrr_at_10_max": -0.13427486324899895, + "nauc_mrr_at_10_std": -0.08280723801445188, + "nauc_mrr_at_1_diff1": -0.06456623489805553, + "nauc_mrr_at_1_max": -0.1271205989845521, + "nauc_mrr_at_1_std": -0.08544254220751434, + "nauc_mrr_at_20_diff1": -0.0947634960882876, + "nauc_mrr_at_20_max": -0.13621935853713024, + "nauc_mrr_at_20_std": -0.08084177433445018, + "nauc_mrr_at_3_diff1": -0.08161466166090584, + "nauc_mrr_at_3_max": -0.12561366402743224, + "nauc_mrr_at_3_std": -0.08901520994075926, + "nauc_mrr_at_5_diff1": -0.08724239339667741, + "nauc_mrr_at_5_max": -0.12749295188541282, + "nauc_mrr_at_5_std": -0.08395972426003237, + "nauc_ndcg_at_1000_diff1": -0.11679752864338895, + "nauc_ndcg_at_1000_max": -0.1535594204494968, + "nauc_ndcg_at_1000_std": -0.06550928007437334, + "nauc_ndcg_at_100_diff1": -0.1215256929655655, + "nauc_ndcg_at_100_max": -0.15660975700943205, + "nauc_ndcg_at_100_std": -0.05844606413666307, + "nauc_ndcg_at_10_diff1": -0.10463173813082961, + "nauc_ndcg_at_10_max": -0.14133767227663052, + "nauc_ndcg_at_10_std": -0.07881178207430915, + "nauc_ndcg_at_1_diff1": -0.06456623489805553, + "nauc_ndcg_at_1_max": -0.1271205989845521, + "nauc_ndcg_at_1_std": -0.08544254220751434, + "nauc_ndcg_at_20_diff1": -0.1126364166734997, + "nauc_ndcg_at_20_max": -0.14822590762492546, + "nauc_ndcg_at_20_std": -0.07233431754283381, + "nauc_ndcg_at_3_diff1": -0.08502871426203625, + "nauc_ndcg_at_3_max": -0.1248853164284835, + "nauc_ndcg_at_3_std": -0.08982069694486922, + "nauc_ndcg_at_5_diff1": -0.09381597511507132, + "nauc_ndcg_at_5_max": -0.12779791138352445, + "nauc_ndcg_at_5_std": -0.08178647709513506, + "nauc_precision_at_1000_diff1": -0.4338274328549514, + "nauc_precision_at_1000_max": -0.45189062089355614, + "nauc_precision_at_1000_std": 0.05808098617657643, + "nauc_precision_at_100_diff1": -0.23356571257994088, + "nauc_precision_at_100_max": -0.24444877780545998, + "nauc_precision_at_100_std": 0.0359770614514241, + "nauc_precision_at_10_diff1": -0.13008586641180409, + "nauc_precision_at_10_max": -0.15713213139342735, + "nauc_precision_at_10_std": -0.06980781579203044, + "nauc_precision_at_1_diff1": -0.06456623489805553, + "nauc_precision_at_1_max": -0.1271205989845521, + "nauc_precision_at_1_std": -0.08544254220751434, + "nauc_precision_at_20_diff1": -0.15489930434739205, + "nauc_precision_at_20_max": -0.1786080698923125, + "nauc_precision_at_20_std": -0.05053656142373881, + "nauc_precision_at_3_diff1": -0.09198320441395763, + "nauc_precision_at_3_max": -0.1232999978828446, + "nauc_precision_at_3_std": -0.09148294709204344, + "nauc_precision_at_5_diff1": -0.10690319056616097, + "nauc_precision_at_5_max": -0.12849297280696756, + "nauc_precision_at_5_std": -0.07702735534636664, + "nauc_recall_at_1000_diff1": -0.43382743285495534, + "nauc_recall_at_1000_max": -0.4518906208935608, + "nauc_recall_at_1000_std": 0.05808098617657445, + "nauc_recall_at_100_diff1": -0.23356571257994097, + "nauc_recall_at_100_max": -0.24444877780545968, + "nauc_recall_at_100_std": 0.035977061451423265, + "nauc_recall_at_10_diff1": -0.1300858664118045, + "nauc_recall_at_10_max": -0.15713213139342755, + "nauc_recall_at_10_std": -0.06980781579203064, + "nauc_recall_at_1_diff1": -0.06456623489805553, + "nauc_recall_at_1_max": -0.1271205989845521, + "nauc_recall_at_1_std": -0.08544254220751434, + "nauc_recall_at_20_diff1": -0.15489930434739202, + "nauc_recall_at_20_max": -0.17860806989231262, + "nauc_recall_at_20_std": -0.05053656142373883, + "nauc_recall_at_3_diff1": -0.09198320441395762, + "nauc_recall_at_3_max": -0.12329999788284451, + "nauc_recall_at_3_std": -0.09148294709204331, + "nauc_recall_at_5_diff1": -0.10690319056616104, + "nauc_recall_at_5_max": -0.12849297280696778, + "nauc_recall_at_5_std": -0.07702735534636673, + "ndcg_at_1": 0.0819, + "ndcg_at_10": 0.22682, + "ndcg_at_100": 0.29773, + "ndcg_at_1000": 0.32252, + "ndcg_at_20": 0.25251, + "ndcg_at_3": 0.15745, + "ndcg_at_5": 0.19059, + "precision_at_1": 0.0819, + "precision_at_10": 0.04067, + "precision_at_100": 0.00753, + "precision_at_1000": 0.00095, + "precision_at_20": 0.02543, + "precision_at_3": 0.07152, + "precision_at_5": 0.05907, + "recall_at_1": 0.0819, + "recall_at_10": 0.40671, + "recall_at_100": 0.75283, + "recall_at_1000": 0.94905, + "recall_at_20": 0.50862, + "recall_at_3": 0.21456, + "recall_at_5": 0.29535 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL2Pure.json b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL2Pure.json new file mode 100644 index 000000000..f0600e49c --- /dev/null +++ b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL2Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 10.520952939987183, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01119, + "map_at_1": 0.00278, + "map_at_10": 0.00732, + "map_at_100": 0.01006, + "map_at_1000": 0.01101, + "map_at_20": 0.00832, + "map_at_3": 0.00482, + "map_at_5": 0.00581, + "mrr_at_1": 0.0027793218454697055, + "mrr_at_10": 0.00732461596830691, + "mrr_at_100": 0.010062592378857416, + "mrr_at_1000": 0.011006031965819882, + "mrr_at_20": 0.008324169268523467, + "mrr_at_3": 0.004817491198814156, + "mrr_at_5": 0.005808782657031683, + "nauc_map_at_1000_diff1": -0.10403511237907898, + "nauc_map_at_1000_max": 0.08763315897075143, + "nauc_map_at_1000_std": 0.29653038496686535, + "nauc_map_at_100_diff1": -0.1102899898955154, + "nauc_map_at_100_max": 0.08027591496988629, + "nauc_map_at_100_std": 0.2890629978571588, + "nauc_map_at_10_diff1": -0.13903376816183438, + "nauc_map_at_10_max": 0.04626524450395466, + "nauc_map_at_10_std": 0.25179510207631123, + "nauc_map_at_1_diff1": -0.21924359705193444, + "nauc_map_at_1_max": -0.014820763351316088, + "nauc_map_at_1_std": 0.21144156623709837, + "nauc_map_at_20_diff1": -0.1229734569361482, + "nauc_map_at_20_max": 0.0599642494433844, + "nauc_map_at_20_std": 0.2630508415831677, + "nauc_map_at_3_diff1": -0.1757138612338217, + "nauc_map_at_3_max": 0.01333408515726601, + "nauc_map_at_3_std": 0.23216744090137598, + "nauc_map_at_5_diff1": -0.1649082892578988, + "nauc_map_at_5_max": 0.013102835600669617, + "nauc_map_at_5_std": 0.22702717990418833, + "nauc_mrr_at_1000_diff1": -0.10403331206232902, + "nauc_mrr_at_1000_max": 0.08763493936779344, + "nauc_mrr_at_1000_std": 0.29653217266006354, + "nauc_mrr_at_100_diff1": -0.11028820450564576, + "nauc_mrr_at_100_max": 0.08027781916856808, + "nauc_mrr_at_100_std": 0.2890649000595261, + "nauc_mrr_at_10_diff1": -0.13903376816183438, + "nauc_mrr_at_10_max": 0.04626524450395466, + "nauc_mrr_at_10_std": 0.25179510207631123, + "nauc_mrr_at_1_diff1": -0.21924359705193444, + "nauc_mrr_at_1_max": -0.014820763351316088, + "nauc_mrr_at_1_std": 0.21144156623709837, + "nauc_mrr_at_20_diff1": -0.1229734569361482, + "nauc_mrr_at_20_max": 0.0599642494433844, + "nauc_mrr_at_20_std": 0.2630508415831677, + "nauc_mrr_at_3_diff1": -0.1757138612338217, + "nauc_mrr_at_3_max": 0.01333408515726601, + "nauc_mrr_at_3_std": 0.23216744090137598, + "nauc_mrr_at_5_diff1": -0.1649082892578988, + "nauc_mrr_at_5_max": 0.013102835600669617, + "nauc_mrr_at_5_std": 0.22702717990418833, + "nauc_ndcg_at_1000_diff1": -0.03173402194217176, + "nauc_ndcg_at_1000_max": 0.17907340498668725, + "nauc_ndcg_at_1000_std": 0.3887095148496031, + "nauc_ndcg_at_100_diff1": -0.05790572470966761, + "nauc_ndcg_at_100_max": 0.14676708324808543, + "nauc_ndcg_at_100_std": 0.36341908219720936, + "nauc_ndcg_at_10_diff1": -0.11331111507692086, + "nauc_ndcg_at_10_max": 0.07438093512005185, + "nauc_ndcg_at_10_std": 0.2714318737056555, + "nauc_ndcg_at_1_diff1": -0.21924359705193444, + "nauc_ndcg_at_1_max": -0.014820763351316088, + "nauc_ndcg_at_1_std": 0.21144156623709837, + "nauc_ndcg_at_20_diff1": -0.08723391323648566, + "nauc_ndcg_at_20_max": 0.09180323820028069, + "nauc_ndcg_at_20_std": 0.2869546799510767, + "nauc_ndcg_at_3_diff1": -0.168225496149266, + "nauc_ndcg_at_3_max": 0.02246074089222968, + "nauc_ndcg_at_3_std": 0.2416552933480079, + "nauc_ndcg_at_5_diff1": -0.15262333665932923, + "nauc_ndcg_at_5_max": 0.02108948217445128, + "nauc_ndcg_at_5_std": 0.23243733871009487, + "nauc_precision_at_1000_diff1": -0.004745149866986641, + "nauc_precision_at_1000_max": 0.2153663339622308, + "nauc_precision_at_1000_std": 0.42311060396407923, + "nauc_precision_at_100_diff1": -0.03185523333939145, + "nauc_precision_at_100_max": 0.18244480239079805, + "nauc_precision_at_100_std": 0.40623454511376483, + "nauc_precision_at_10_diff1": -0.08473904572955739, + "nauc_precision_at_10_max": 0.10642287511819784, + "nauc_precision_at_10_std": 0.29330704411317476, + "nauc_precision_at_1_diff1": -0.21924359705193444, + "nauc_precision_at_1_max": -0.014820763351316088, + "nauc_precision_at_1_std": 0.21144156623709837, + "nauc_precision_at_20_diff1": -0.05654278662527382, + "nauc_precision_at_20_max": 0.11765496701921702, + "nauc_precision_at_20_std": 0.30631199934381137, + "nauc_precision_at_3_diff1": -0.1550616153067743, + "nauc_precision_at_3_max": 0.03936966844703108, + "nauc_precision_at_3_std": 0.25953023932612385, + "nauc_precision_at_5_diff1": -0.1341340370379066, + "nauc_precision_at_5_max": 0.03290326853443483, + "nauc_precision_at_5_std": 0.24016826729562024, + "nauc_recall_at_1000_diff1": -0.004745149866986594, + "nauc_recall_at_1000_max": 0.21536633396223095, + "nauc_recall_at_1000_std": 0.42311060396407957, + "nauc_recall_at_100_diff1": -0.03185523333939171, + "nauc_recall_at_100_max": 0.18244480239079786, + "nauc_recall_at_100_std": 0.40623454511376483, + "nauc_recall_at_10_diff1": -0.08473904572955762, + "nauc_recall_at_10_max": 0.10642287511819756, + "nauc_recall_at_10_std": 0.2933070441131743, + "nauc_recall_at_1_diff1": -0.21924359705193444, + "nauc_recall_at_1_max": -0.014820763351316088, + "nauc_recall_at_1_std": 0.21144156623709837, + "nauc_recall_at_20_diff1": -0.05654278662527394, + "nauc_recall_at_20_max": 0.11765496701921682, + "nauc_recall_at_20_std": 0.3063119993438112, + "nauc_recall_at_3_diff1": -0.15506161530677415, + "nauc_recall_at_3_max": 0.03936966844703131, + "nauc_recall_at_3_std": 0.2595302393261242, + "nauc_recall_at_5_diff1": -0.13413403703790688, + "nauc_recall_at_5_max": 0.032903268534434434, + "nauc_recall_at_5_std": 0.24016826729561974, + "ndcg_at_1": 0.00278, + "ndcg_at_10": 0.01119, + "ndcg_at_100": 0.02944, + "ndcg_at_1000": 0.06155, + "ndcg_at_20": 0.01491, + "ndcg_at_3": 0.00562, + "ndcg_at_5": 0.00743, + "precision_at_1": 0.00278, + "precision_at_10": 0.00243, + "precision_at_100": 0.00122, + "precision_at_1000": 0.00039, + "precision_at_20": 0.00195, + "precision_at_3": 0.00266, + "precision_at_5": 0.00248, + "recall_at_1": 0.00278, + "recall_at_10": 0.02427, + "recall_at_100": 0.12155, + "recall_at_1000": 0.39003, + "recall_at_20": 0.0391, + "recall_at_3": 0.00797, + "recall_at_5": 0.01241 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL3Fact.json b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL3Fact.json new file mode 100644 index 000000000..b8ad29687 --- /dev/null +++ b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL3Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 21.295192003250122, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.20624, + "map_at_1": 0.04835, + "map_at_10": 0.14642, + "map_at_100": 0.15979, + "map_at_1000": 0.16074, + "map_at_20": 0.15416, + "map_at_3": 0.1106, + "map_at_5": 0.13084, + "mrr_at_1": 0.04835065521915951, + "mrr_at_10": 0.1464222953829821, + "mrr_at_100": 0.15979387973727707, + "mrr_at_1000": 0.16074039268205167, + "mrr_at_20": 0.1541585500332734, + "mrr_at_3": 0.11059647537279671, + "mrr_at_5": 0.13084048802530468, + "nauc_map_at_1000_diff1": -0.12919880034622636, + "nauc_map_at_1000_max": -0.11396464720496118, + "nauc_map_at_1000_std": -0.01738113518283321, + "nauc_map_at_100_diff1": -0.12936611912148901, + "nauc_map_at_100_max": -0.11424704280175896, + "nauc_map_at_100_std": -0.01715041425230199, + "nauc_map_at_10_diff1": -0.12394870336069154, + "nauc_map_at_10_max": -0.10967197719303175, + "nauc_map_at_10_std": -0.021302665873594927, + "nauc_map_at_1_diff1": -0.20982651034081742, + "nauc_map_at_1_max": -0.14555311635786108, + "nauc_map_at_1_std": -0.01386136241327817, + "nauc_map_at_20_diff1": -0.12731179690589994, + "nauc_map_at_20_max": -0.11330064310532272, + "nauc_map_at_20_std": -0.019783359621365293, + "nauc_map_at_3_diff1": -0.12184901210755895, + "nauc_map_at_3_max": -0.10038600944380746, + "nauc_map_at_3_std": -0.025866714544687534, + "nauc_map_at_5_diff1": -0.1190873678614352, + "nauc_map_at_5_max": -0.1049233300756702, + "nauc_map_at_5_std": -0.02669573436107664, + "nauc_mrr_at_1000_diff1": -0.12919880034622636, + "nauc_mrr_at_1000_max": -0.11396464720496118, + "nauc_mrr_at_1000_std": -0.01738113518283321, + "nauc_mrr_at_100_diff1": -0.12936611912148901, + "nauc_mrr_at_100_max": -0.11424704280175896, + "nauc_mrr_at_100_std": -0.01715041425230199, + "nauc_mrr_at_10_diff1": -0.12394870336069154, + "nauc_mrr_at_10_max": -0.10967197719303175, + "nauc_mrr_at_10_std": -0.021302665873594927, + "nauc_mrr_at_1_diff1": -0.20982651034081742, + "nauc_mrr_at_1_max": -0.14555311635786108, + "nauc_mrr_at_1_std": -0.01386136241327817, + "nauc_mrr_at_20_diff1": -0.12731179690589994, + "nauc_mrr_at_20_max": -0.11330064310532272, + "nauc_mrr_at_20_std": -0.019783359621365293, + "nauc_mrr_at_3_diff1": -0.12184901210755895, + "nauc_mrr_at_3_max": -0.10038600944380746, + "nauc_mrr_at_3_std": -0.025866714544687534, + "nauc_mrr_at_5_diff1": -0.1190873678614352, + "nauc_mrr_at_5_max": -0.1049233300756702, + "nauc_mrr_at_5_std": -0.02669573436107664, + "nauc_ndcg_at_1000_diff1": -0.1400578882351063, + "nauc_ndcg_at_1000_max": -0.12454317687042422, + "nauc_ndcg_at_1000_std": -0.0016069165592934233, + "nauc_ndcg_at_100_diff1": -0.14261050599066688, + "nauc_ndcg_at_100_max": -0.12896987934909446, + "nauc_ndcg_at_100_std": 0.006888784754649178, + "nauc_ndcg_at_10_diff1": -0.11812807102958074, + "nauc_ndcg_at_10_max": -0.1118375297915098, + "nauc_ndcg_at_10_std": -0.01737548462752695, + "nauc_ndcg_at_1_diff1": -0.20982651034081742, + "nauc_ndcg_at_1_max": -0.14555311635786108, + "nauc_ndcg_at_1_std": -0.01386136241327817, + "nauc_ndcg_at_20_diff1": -0.12813279870632394, + "nauc_ndcg_at_20_max": -0.12356104581096368, + "nauc_ndcg_at_20_std": -0.013594027683333954, + "nauc_ndcg_at_3_diff1": -0.11196700297891596, + "nauc_ndcg_at_3_max": -0.09458722607475252, + "nauc_ndcg_at_3_std": -0.026111851604060283, + "nauc_ndcg_at_5_diff1": -0.10875879348484115, + "nauc_ndcg_at_5_max": -0.10228578284229461, + "nauc_ndcg_at_5_std": -0.02754941113478749, + "nauc_precision_at_1000_diff1": -0.3816290987409607, + "nauc_precision_at_1000_max": -0.26993925002895824, + "nauc_precision_at_1000_std": 0.17922059264293264, + "nauc_precision_at_100_diff1": -0.2133873054332952, + "nauc_precision_at_100_max": -0.18695901903739842, + "nauc_precision_at_100_std": 0.11015206180339242, + "nauc_precision_at_10_diff1": -0.11128710032042265, + "nauc_precision_at_10_max": -0.11815302303367273, + "nauc_precision_at_10_std": -0.009447673765642203, + "nauc_precision_at_1_diff1": -0.20982651034081742, + "nauc_precision_at_1_max": -0.14555311635786108, + "nauc_precision_at_1_std": -0.01386136241327817, + "nauc_precision_at_20_diff1": -0.13685950464469165, + "nauc_precision_at_20_max": -0.14978881491023902, + "nauc_precision_at_20_std": -0.0004100441099014205, + "nauc_precision_at_3_diff1": -0.09515892534672439, + "nauc_precision_at_3_max": -0.08453296484588774, + "nauc_precision_at_3_std": -0.026237915916877047, + "nauc_precision_at_5_diff1": -0.09258147828537393, + "nauc_precision_at_5_max": -0.09900799090986921, + "nauc_precision_at_5_std": -0.028863098307838033, + "nauc_recall_at_1000_diff1": -0.381629098740966, + "nauc_recall_at_1000_max": -0.2699392500289648, + "nauc_recall_at_1000_std": 0.17922059264292803, + "nauc_recall_at_100_diff1": -0.21338730543329526, + "nauc_recall_at_100_max": -0.1869590190373983, + "nauc_recall_at_100_std": 0.11015206180339274, + "nauc_recall_at_10_diff1": -0.11128710032042298, + "nauc_recall_at_10_max": -0.11815302303367296, + "nauc_recall_at_10_std": -0.009447673765642699, + "nauc_recall_at_1_diff1": -0.20982651034081742, + "nauc_recall_at_1_max": -0.14555311635786108, + "nauc_recall_at_1_std": -0.01386136241327817, + "nauc_recall_at_20_diff1": -0.13685950464469226, + "nauc_recall_at_20_max": -0.14978881491023943, + "nauc_recall_at_20_std": -0.0004100441099015618, + "nauc_recall_at_3_diff1": -0.09515892534672445, + "nauc_recall_at_3_max": -0.08453296484588772, + "nauc_recall_at_3_std": -0.026237915916877165, + "nauc_recall_at_5_diff1": -0.0925814782853742, + "nauc_recall_at_5_max": -0.09900799090986936, + "nauc_recall_at_5_std": -0.028863098307838203, + "ndcg_at_1": 0.04835, + "ndcg_at_10": 0.20624, + "ndcg_at_100": 0.27639, + "ndcg_at_1000": 0.30233, + "ndcg_at_20": 0.23418, + "ndcg_at_3": 0.13206, + "ndcg_at_5": 0.16869, + "precision_at_1": 0.04835, + "precision_at_10": 0.03995, + "precision_at_100": 0.0074, + "precision_at_1000": 0.00095, + "precision_at_20": 0.02547, + "precision_at_3": 0.06484, + "precision_at_5": 0.05676, + "recall_at_1": 0.04835, + "recall_at_10": 0.39946, + "recall_at_100": 0.74017, + "recall_at_1000": 0.946, + "recall_at_20": 0.50949, + "recall_at_3": 0.19453, + "recall_at_5": 0.28378 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL3Pure.json b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL3Pure.json new file mode 100644 index 000000000..263d98ee6 --- /dev/null +++ b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/TempReasonL3Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 9.139213562011719, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07805, + "map_at_1": 0.00271, + "map_at_10": 0.04775, + "map_at_100": 0.05604, + "map_at_1000": 0.05742, + "map_at_20": 0.05198, + "map_at_3": 0.02772, + "map_at_5": 0.03889, + "mrr_at_1": 0.0027112516945323093, + "mrr_at_10": 0.04775012731406759, + "mrr_at_100": 0.056035859165469624, + "mrr_at_1000": 0.05741938317392064, + "mrr_at_20": 0.0519828123082237, + "mrr_at_3": 0.02771501732188577, + "mrr_at_5": 0.03888763367977105, + "nauc_map_at_1000_diff1": -0.2587295575106721, + "nauc_map_at_1000_max": -0.22307477491934222, + "nauc_map_at_1000_std": -0.045723261829237985, + "nauc_map_at_100_diff1": -0.2587793692575839, + "nauc_map_at_100_max": -0.22377535724029726, + "nauc_map_at_100_std": -0.048211700701827426, + "nauc_map_at_10_diff1": -0.2661544585183297, + "nauc_map_at_10_max": -0.22907939715621647, + "nauc_map_at_10_std": -0.06524732413527014, + "nauc_map_at_1_diff1": -0.5057500961791453, + "nauc_map_at_1_max": -0.2550201337572068, + "nauc_map_at_1_std": -0.013348079902323012, + "nauc_map_at_20_diff1": -0.26402430127532883, + "nauc_map_at_20_max": -0.22840506105544237, + "nauc_map_at_20_std": -0.060982929371524684, + "nauc_map_at_3_diff1": -0.26680473551567013, + "nauc_map_at_3_max": -0.22225623027584004, + "nauc_map_at_3_std": -0.08066848806448147, + "nauc_map_at_5_diff1": -0.2651093818434174, + "nauc_map_at_5_max": -0.22244660558378465, + "nauc_map_at_5_std": -0.07200456990901744, + "nauc_mrr_at_1000_diff1": -0.2587295575106721, + "nauc_mrr_at_1000_max": -0.22307477491934222, + "nauc_mrr_at_1000_std": -0.045723261829237985, + "nauc_mrr_at_100_diff1": -0.2587793692575839, + "nauc_mrr_at_100_max": -0.22377535724029726, + "nauc_mrr_at_100_std": -0.048211700701827426, + "nauc_mrr_at_10_diff1": -0.2661544585183297, + "nauc_mrr_at_10_max": -0.22907939715621647, + "nauc_mrr_at_10_std": -0.06524732413527014, + "nauc_mrr_at_1_diff1": -0.5057500961791453, + "nauc_mrr_at_1_max": -0.2550201337572068, + "nauc_mrr_at_1_std": -0.013348079902323012, + "nauc_mrr_at_20_diff1": -0.26402430127532883, + "nauc_mrr_at_20_max": -0.22840506105544237, + "nauc_mrr_at_20_std": -0.060982929371524684, + "nauc_mrr_at_3_diff1": -0.26680473551567013, + "nauc_mrr_at_3_max": -0.22225623027584004, + "nauc_mrr_at_3_std": -0.08066848806448147, + "nauc_mrr_at_5_diff1": -0.2651093818434174, + "nauc_mrr_at_5_max": -0.22244660558378465, + "nauc_mrr_at_5_std": -0.07200456990901744, + "nauc_ndcg_at_1000_diff1": -0.23726153115055273, + "nauc_ndcg_at_1000_max": -0.2003246055305238, + "nauc_ndcg_at_1000_std": 0.037876900490719255, + "nauc_ndcg_at_100_diff1": -0.23903521725303173, + "nauc_ndcg_at_100_max": -0.21036771199987933, + "nauc_ndcg_at_100_std": 0.007798514177481373, + "nauc_ndcg_at_10_diff1": -0.2645518826833358, + "nauc_ndcg_at_10_max": -0.2341071356647767, + "nauc_ndcg_at_10_std": -0.0614376124468562, + "nauc_ndcg_at_1_diff1": -0.5057500961791453, + "nauc_ndcg_at_1_max": -0.2550201337572068, + "nauc_ndcg_at_1_std": -0.013348079902323012, + "nauc_ndcg_at_20_diff1": -0.260186501369197, + "nauc_ndcg_at_20_max": -0.2324900762047024, + "nauc_ndcg_at_20_std": -0.05226184766876896, + "nauc_ndcg_at_3_diff1": -0.2603686886686421, + "nauc_ndcg_at_3_max": -0.2214534120742971, + "nauc_ndcg_at_3_std": -0.08231555093166834, + "nauc_ndcg_at_5_diff1": -0.2609991534327599, + "nauc_ndcg_at_5_max": -0.22293470227174175, + "nauc_ndcg_at_5_std": -0.07194267015583403, + "nauc_precision_at_1000_diff1": -0.18686863059606032, + "nauc_precision_at_1000_max": -0.1300953828102505, + "nauc_precision_at_1000_std": 0.2619515001957535, + "nauc_precision_at_100_diff1": -0.2123718018666909, + "nauc_precision_at_100_max": -0.18667051554617659, + "nauc_precision_at_100_std": 0.09186931256662216, + "nauc_precision_at_10_diff1": -0.26428802839606974, + "nauc_precision_at_10_max": -0.24055093528120597, + "nauc_precision_at_10_std": -0.0567046670778961, + "nauc_precision_at_1_diff1": -0.5057500961791453, + "nauc_precision_at_1_max": -0.2550201337572068, + "nauc_precision_at_1_std": -0.013348079902323012, + "nauc_precision_at_20_diff1": -0.25703527407857546, + "nauc_precision_at_20_max": -0.23710414559006293, + "nauc_precision_at_20_std": -0.04173220112843988, + "nauc_precision_at_3_diff1": -0.25208523352813283, + "nauc_precision_at_3_max": -0.22043282573858022, + "nauc_precision_at_3_std": -0.08440895047961451, + "nauc_precision_at_5_diff1": -0.2569546903151044, + "nauc_precision_at_5_max": -0.22385116231461225, + "nauc_precision_at_5_std": -0.07173421241216263, + "nauc_recall_at_1000_diff1": -0.18686863059606118, + "nauc_recall_at_1000_max": -0.13009538281025126, + "nauc_recall_at_1000_std": 0.2619515001957533, + "nauc_recall_at_100_diff1": -0.21237180186669072, + "nauc_recall_at_100_max": -0.18667051554617664, + "nauc_recall_at_100_std": 0.09186931256662192, + "nauc_recall_at_10_diff1": -0.26428802839606996, + "nauc_recall_at_10_max": -0.2405509352812061, + "nauc_recall_at_10_std": -0.056704667077896224, + "nauc_recall_at_1_diff1": -0.5057500961791453, + "nauc_recall_at_1_max": -0.2550201337572068, + "nauc_recall_at_1_std": -0.013348079902323012, + "nauc_recall_at_20_diff1": -0.2570352740785754, + "nauc_recall_at_20_max": -0.237104145590063, + "nauc_recall_at_20_std": -0.04173220112844001, + "nauc_recall_at_3_diff1": -0.2520852335281326, + "nauc_recall_at_3_max": -0.22043282573858014, + "nauc_recall_at_3_std": -0.08440895047961444, + "nauc_recall_at_5_diff1": -0.2569546903151044, + "nauc_recall_at_5_max": -0.22385116231461225, + "nauc_recall_at_5_std": -0.07173421241216264, + "ndcg_at_1": 0.00271, + "ndcg_at_10": 0.07805, + "ndcg_at_100": 0.1256, + "ndcg_at_1000": 0.16788, + "ndcg_at_20": 0.09362, + "ndcg_at_3": 0.03672, + "ndcg_at_5": 0.05674, + "precision_at_1": 0.00271, + "precision_at_10": 0.01769, + "precision_at_100": 0.00417, + "precision_at_1000": 0.00076, + "precision_at_20": 0.01194, + "precision_at_3": 0.02101, + "precision_at_5": 0.02228, + "recall_at_1": 0.00271, + "recall_at_10": 0.17691, + "recall_at_100": 0.41663, + "recall_at_1000": 0.76141, + "recall_at_20": 0.23882, + "recall_at_3": 0.06304, + "recall_at_5": 0.11139 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/WinoGrande.json b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/WinoGrande.json new file mode 100644 index 000000000..282b77c37 --- /dev/null +++ b/results/contriever/2bd46a25019aeea091fd42d1f0fd4801675cf699/WinoGrande.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 2.4591352939605713, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.47155, + "map_at_1": 0.2423, + "map_at_10": 0.39359, + "map_at_100": 0.40304, + "map_at_1000": 0.40339, + "map_at_20": 0.3999, + "map_at_3": 0.35017, + "map_at_5": 0.37898, + "mrr_at_1": 0.2430939226519337, + "mrr_at_10": 0.3940541962641405, + "mrr_at_100": 0.40351615876119556, + "mrr_at_1000": 0.40386566256464185, + "mrr_at_20": 0.40037462755805886, + "mrr_at_3": 0.3509602736122068, + "mrr_at_5": 0.37941331228623953, + "nauc_map_at_1000_diff1": 0.13374782948364, + "nauc_map_at_1000_max": 0.16355847497245132, + "nauc_map_at_1000_std": -0.22402784476231138, + "nauc_map_at_100_diff1": 0.13365304968766778, + "nauc_map_at_100_max": 0.16359186707264503, + "nauc_map_at_100_std": -0.22401374496237225, + "nauc_map_at_10_diff1": 0.1347114536985411, + "nauc_map_at_10_max": 0.16567090645145235, + "nauc_map_at_10_std": -0.22717166926458127, + "nauc_map_at_1_diff1": 0.14634669350875223, + "nauc_map_at_1_max": 0.1472593831145049, + "nauc_map_at_1_std": -0.16767391813133242, + "nauc_map_at_20_diff1": 0.1339863426278205, + "nauc_map_at_20_max": 0.16374691298459834, + "nauc_map_at_20_std": -0.22555683316491784, + "nauc_map_at_3_diff1": 0.13778276171623174, + "nauc_map_at_3_max": 0.16493635301899362, + "nauc_map_at_3_std": -0.21750995505141152, + "nauc_map_at_5_diff1": 0.1377746799480422, + "nauc_map_at_5_max": 0.16436444019984356, + "nauc_map_at_5_std": -0.2327225263764665, + "nauc_mrr_at_1000_diff1": 0.13237636604478517, + "nauc_mrr_at_1000_max": 0.16432723859944715, + "nauc_mrr_at_1000_std": -0.2239054577909489, + "nauc_mrr_at_100_diff1": 0.13228321805466114, + "nauc_mrr_at_100_max": 0.16435961450669645, + "nauc_mrr_at_100_std": -0.22389156865580734, + "nauc_mrr_at_10_diff1": 0.1333474397345267, + "nauc_mrr_at_10_max": 0.16640903131993173, + "nauc_mrr_at_10_std": -0.22705238389103366, + "nauc_mrr_at_1_diff1": 0.14362138584943698, + "nauc_mrr_at_1_max": 0.14770292110749697, + "nauc_mrr_at_1_std": -0.16685415140250695, + "nauc_mrr_at_20_diff1": 0.1326291613765374, + "nauc_mrr_at_20_max": 0.16450804599692664, + "nauc_mrr_at_20_std": -0.22543557988150875, + "nauc_mrr_at_3_diff1": 0.13574722685880034, + "nauc_mrr_at_3_max": 0.16630840921769321, + "nauc_mrr_at_3_std": -0.21645822999368924, + "nauc_mrr_at_5_diff1": 0.1364734217989441, + "nauc_mrr_at_5_max": 0.16506753368899285, + "nauc_mrr_at_5_std": -0.23262859939875727, + "nauc_ndcg_at_1000_diff1": 0.12599893599210793, + "nauc_ndcg_at_1000_max": 0.16339737052105446, + "nauc_ndcg_at_1000_std": -0.23340391203463595, + "nauc_ndcg_at_100_diff1": 0.12107346993375764, + "nauc_ndcg_at_100_max": 0.1620607894880593, + "nauc_ndcg_at_100_std": -0.2327181577156523, + "nauc_ndcg_at_10_diff1": 0.1273670604451928, + "nauc_ndcg_at_10_max": 0.17097375419321695, + "nauc_ndcg_at_10_std": -0.24938236323481267, + "nauc_ndcg_at_1_diff1": 0.14634669350875223, + "nauc_ndcg_at_1_max": 0.1472593831145049, + "nauc_ndcg_at_1_std": -0.16767391813133242, + "nauc_ndcg_at_20_diff1": 0.12404102191888855, + "nauc_ndcg_at_20_max": 0.16288848723727575, + "nauc_ndcg_at_20_std": -0.24450831711653476, + "nauc_ndcg_at_3_diff1": 0.1354134582533898, + "nauc_ndcg_at_3_max": 0.16753654866710854, + "nauc_ndcg_at_3_std": -0.23434322741896021, + "nauc_ndcg_at_5_diff1": 0.13500799798199625, + "nauc_ndcg_at_5_max": 0.1666565844976348, + "nauc_ndcg_at_5_std": -0.2628804091881896, + "nauc_precision_at_1000_diff1": -0.17728206805201466, + "nauc_precision_at_1000_max": 0.1823411790123221, + "nauc_precision_at_1000_std": -0.30128899532581904, + "nauc_precision_at_100_diff1": -0.06359429956557046, + "nauc_precision_at_100_max": 0.11611011898239995, + "nauc_precision_at_100_std": -0.22373824661263014, + "nauc_precision_at_10_diff1": 0.0961919204767552, + "nauc_precision_at_10_max": 0.19266676560541374, + "nauc_precision_at_10_std": -0.32931542641972955, + "nauc_precision_at_1_diff1": 0.14634669350875223, + "nauc_precision_at_1_max": 0.1472593831145049, + "nauc_precision_at_1_std": -0.16767391813133242, + "nauc_precision_at_20_diff1": 0.06383015906306069, + "nauc_precision_at_20_max": 0.14759579362795053, + "nauc_precision_at_20_std": -0.32921151929660836, + "nauc_precision_at_3_diff1": 0.1289613451077145, + "nauc_precision_at_3_max": 0.1738844635130439, + "nauc_precision_at_3_std": -0.28115845278162793, + "nauc_precision_at_5_diff1": 0.12643838792520043, + "nauc_precision_at_5_max": 0.17257453907218748, + "nauc_precision_at_5_std": -0.35929931068467064, + "nauc_recall_at_1000_diff1": -0.17728206805203703, + "nauc_recall_at_1000_max": 0.1823411790123119, + "nauc_recall_at_1000_std": -0.30128899532584225, + "nauc_recall_at_100_diff1": -0.06359429956557018, + "nauc_recall_at_100_max": 0.11611011898240063, + "nauc_recall_at_100_std": -0.22373824661263028, + "nauc_recall_at_10_diff1": 0.09619192047675525, + "nauc_recall_at_10_max": 0.19266676560541382, + "nauc_recall_at_10_std": -0.3293154264197286, + "nauc_recall_at_1_diff1": 0.14634669350875223, + "nauc_recall_at_1_max": 0.1472593831145049, + "nauc_recall_at_1_std": -0.16767391813133242, + "nauc_recall_at_20_diff1": 0.06383015906305857, + "nauc_recall_at_20_max": 0.1475957936279494, + "nauc_recall_at_20_std": -0.32921151929660797, + "nauc_recall_at_3_diff1": 0.12896134510771448, + "nauc_recall_at_3_max": 0.1738844635130437, + "nauc_recall_at_3_std": -0.281158452781628, + "nauc_recall_at_5_diff1": 0.1264383879252009, + "nauc_recall_at_5_max": 0.1725745390721877, + "nauc_recall_at_5_std": -0.35929931068467114, + "ndcg_at_1": 0.2423, + "ndcg_at_10": 0.47155, + "ndcg_at_100": 0.51595, + "ndcg_at_1000": 0.52469, + "ndcg_at_20": 0.49438, + "ndcg_at_3": 0.38512, + "ndcg_at_5": 0.43625, + "precision_at_1": 0.2423, + "precision_at_10": 0.07174, + "precision_at_100": 0.00921, + "precision_at_1000": 0.00099, + "precision_at_20": 0.04037, + "precision_at_3": 0.16206, + "precision_at_5": 0.1217, + "recall_at_1": 0.2423, + "recall_at_10": 0.71744, + "recall_at_100": 0.92107, + "recall_at_1000": 0.98895, + "recall_at_20": 0.80742, + "recall_at_3": 0.48619, + "recall_at_5": 0.60852 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/dragon-plus-instruct/no_revision_available/ARCChallenge.json b/results/dragon-plus-instruct/no_revision_available/ARCChallenge.json new file mode 100644 index 000000000..acc0bea10 --- /dev/null +++ b/results/dragon-plus-instruct/no_revision_available/ARCChallenge.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 4.175339460372925, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.0824, + "map_at_1": 0.02645, + "map_at_10": 0.06051, + "map_at_100": 0.06739, + "map_at_1000": 0.06868, + "map_at_20": 0.06373, + "map_at_3": 0.0475, + "map_at_5": 0.05424, + "mrr_at_1": 0.026450511945392493, + "mrr_at_10": 0.060510794192534856, + "mrr_at_100": 0.06739475018542364, + "mrr_at_1000": 0.06867732592170883, + "mrr_at_20": 0.06372974040961084, + "mrr_at_3": 0.04749715585893063, + "mrr_at_5": 0.05423777019340164, + "nauc_map_at_1000_diff1": 0.028312569988540853, + "nauc_map_at_1000_max": 0.18438008190002175, + "nauc_map_at_1000_std": -0.014277133877795337, + "nauc_map_at_100_diff1": 0.027287912385569497, + "nauc_map_at_100_max": 0.1861677413481939, + "nauc_map_at_100_std": -0.014956050319648397, + "nauc_map_at_10_diff1": 0.029708596243737236, + "nauc_map_at_10_max": 0.1887852016833154, + "nauc_map_at_10_std": -0.02035340604329732, + "nauc_map_at_1_diff1": 0.033812896394878555, + "nauc_map_at_1_max": 0.20264563231079596, + "nauc_map_at_1_std": -0.02114360629187156, + "nauc_map_at_20_diff1": 0.029492954117528128, + "nauc_map_at_20_max": 0.18921628427847276, + "nauc_map_at_20_std": -0.018663578056413613, + "nauc_map_at_3_diff1": 0.015366177470779053, + "nauc_map_at_3_max": 0.18848166238944403, + "nauc_map_at_3_std": -0.009515724321275268, + "nauc_map_at_5_diff1": 0.031166516977127735, + "nauc_map_at_5_max": 0.19787587162880169, + "nauc_map_at_5_std": -0.015682255043174265, + "nauc_mrr_at_1000_diff1": 0.028312477272742883, + "nauc_mrr_at_1000_max": 0.18438005773960361, + "nauc_mrr_at_1000_std": -0.014277565754202746, + "nauc_mrr_at_100_diff1": 0.027287912385569497, + "nauc_mrr_at_100_max": 0.1861677413481939, + "nauc_mrr_at_100_std": -0.014956050319648397, + "nauc_mrr_at_10_diff1": 0.029708596243737236, + "nauc_mrr_at_10_max": 0.1887852016833154, + "nauc_mrr_at_10_std": -0.02035340604329732, + "nauc_mrr_at_1_diff1": 0.033812896394878555, + "nauc_mrr_at_1_max": 0.20264563231079596, + "nauc_mrr_at_1_std": -0.02114360629187156, + "nauc_mrr_at_20_diff1": 0.029492954117528128, + "nauc_mrr_at_20_max": 0.18921628427847276, + "nauc_mrr_at_20_std": -0.018663578056413613, + "nauc_mrr_at_3_diff1": 0.015366177470779053, + "nauc_mrr_at_3_max": 0.18848166238944403, + "nauc_mrr_at_3_std": -0.009515724321275268, + "nauc_mrr_at_5_diff1": 0.031166516977127735, + "nauc_mrr_at_5_max": 0.19787587162880169, + "nauc_mrr_at_5_std": -0.015682255043174265, + "nauc_ndcg_at_1000_diff1": 0.04264038790206534, + "nauc_ndcg_at_1000_max": 0.13817032022775555, + "nauc_ndcg_at_1000_std": 0.0016530565976938369, + "nauc_ndcg_at_100_diff1": 0.02576835290181988, + "nauc_ndcg_at_100_max": 0.1706708186467138, + "nauc_ndcg_at_100_std": -0.005948094392178291, + "nauc_ndcg_at_10_diff1": 0.03296027302332775, + "nauc_ndcg_at_10_max": 0.18391290851105208, + "nauc_ndcg_at_10_std": -0.021688356407934935, + "nauc_ndcg_at_1_diff1": 0.033812896394878555, + "nauc_ndcg_at_1_max": 0.20264563231079596, + "nauc_ndcg_at_1_std": -0.02114360629187156, + "nauc_ndcg_at_20_diff1": 0.03173483269938486, + "nauc_ndcg_at_20_max": 0.18458039850779429, + "nauc_ndcg_at_20_std": -0.018171013876517587, + "nauc_ndcg_at_3_diff1": 0.009458018539411714, + "nauc_ndcg_at_3_max": 0.18699549106557542, + "nauc_ndcg_at_3_std": -0.0025209351061929054, + "nauc_ndcg_at_5_diff1": 0.035329170845777164, + "nauc_ndcg_at_5_max": 0.2008436181267699, + "nauc_ndcg_at_5_std": -0.01257171626980885, + "nauc_precision_at_1000_diff1": 0.0962127244783692, + "nauc_precision_at_1000_max": -0.0060972345669278935, + "nauc_precision_at_1000_std": 0.03422396498549233, + "nauc_precision_at_100_diff1": 0.024229827799522305, + "nauc_precision_at_100_max": 0.1458603678039765, + "nauc_precision_at_100_std": 0.00613032481619865, + "nauc_precision_at_10_diff1": 0.038727213945697135, + "nauc_precision_at_10_max": 0.17580991276952526, + "nauc_precision_at_10_std": -0.025067523040013355, + "nauc_precision_at_1_diff1": 0.033812896394878555, + "nauc_precision_at_1_max": 0.20264563231079596, + "nauc_precision_at_1_std": -0.02114360629187156, + "nauc_precision_at_20_diff1": 0.034832925854525805, + "nauc_precision_at_20_max": 0.17759797140571207, + "nauc_precision_at_20_std": -0.018461261522170334, + "nauc_precision_at_3_diff1": -0.0016379839329853177, + "nauc_precision_at_3_max": 0.1845274822772543, + "nauc_precision_at_3_std": 0.01096232551060898, + "nauc_precision_at_5_diff1": 0.04372603131975369, + "nauc_precision_at_5_max": 0.20633921436463423, + "nauc_precision_at_5_std": -0.007776689601034794, + "nauc_recall_at_1000_diff1": 0.09621272447836801, + "nauc_recall_at_1000_max": -0.006097234566928889, + "nauc_recall_at_1000_std": 0.034223964985492114, + "nauc_recall_at_100_diff1": 0.024229827799522125, + "nauc_recall_at_100_max": 0.14586036780397627, + "nauc_recall_at_100_std": 0.006130324816198477, + "nauc_recall_at_10_diff1": 0.0387272139456971, + "nauc_recall_at_10_max": 0.17580991276952512, + "nauc_recall_at_10_std": -0.025067523040013494, + "nauc_recall_at_1_diff1": 0.033812896394878555, + "nauc_recall_at_1_max": 0.20264563231079596, + "nauc_recall_at_1_std": -0.02114360629187156, + "nauc_recall_at_20_diff1": 0.03483292585452566, + "nauc_recall_at_20_max": 0.17759797140571212, + "nauc_recall_at_20_std": -0.018461261522170362, + "nauc_recall_at_3_diff1": -0.0016379839329854083, + "nauc_recall_at_3_max": 0.1845274822772543, + "nauc_recall_at_3_std": 0.01096232551060892, + "nauc_recall_at_5_diff1": 0.043726031319753556, + "nauc_recall_at_5_max": 0.20633921436463393, + "nauc_recall_at_5_std": -0.007776689601035019, + "ndcg_at_1": 0.02645, + "ndcg_at_10": 0.0824, + "ndcg_at_100": 0.1214, + "ndcg_at_1000": 0.16315, + "ndcg_at_20": 0.09393, + "ndcg_at_3": 0.05518, + "ndcg_at_5": 0.06722, + "precision_at_1": 0.02645, + "precision_at_10": 0.01536, + "precision_at_100": 0.00349, + "precision_at_1000": 0.00069, + "precision_at_20": 0.00994, + "precision_at_3": 0.02588, + "precision_at_5": 0.02133, + "recall_at_1": 0.02645, + "recall_at_10": 0.15358, + "recall_at_100": 0.34898, + "recall_at_1000": 0.69454, + "recall_at_20": 0.19881, + "recall_at_3": 0.07765, + "recall_at_5": 0.10666 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/dragon-plus-instruct/no_revision_available/AlphaNLI.json b/results/dragon-plus-instruct/no_revision_available/AlphaNLI.json new file mode 100644 index 000000000..9348da7ee --- /dev/null +++ b/results/dragon-plus-instruct/no_revision_available/AlphaNLI.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 55.010433197021484, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.25177, + "map_at_1": 0.1547, + "map_at_10": 0.2191, + "map_at_100": 0.22596, + "map_at_1000": 0.22664, + "map_at_20": 0.22289, + "map_at_3": 0.20398, + "map_at_5": 0.21198, + "mrr_at_1": 0.15469973890339425, + "mrr_at_10": 0.2191014961249948, + "mrr_at_100": 0.2259609928387054, + "mrr_at_1000": 0.22664411124891495, + "mrr_at_20": 0.22289448214196497, + "mrr_at_3": 0.2039817232375978, + "mrr_at_5": 0.21197780678851152, + "nauc_map_at_1000_diff1": 0.3922364773668702, + "nauc_map_at_1000_max": 0.18037215542123264, + "nauc_map_at_1000_std": 0.0223034380979675, + "nauc_map_at_100_diff1": 0.3922344506573504, + "nauc_map_at_100_max": 0.1801798237366287, + "nauc_map_at_100_std": 0.02227287841826456, + "nauc_map_at_10_diff1": 0.3953104324986655, + "nauc_map_at_10_max": 0.18292918835826316, + "nauc_map_at_10_std": 0.018552565954239573, + "nauc_map_at_1_diff1": 0.4519506017232632, + "nauc_map_at_1_max": 0.1958063667846311, + "nauc_map_at_1_std": -0.0027198839307285413, + "nauc_map_at_20_diff1": 0.3927408611884983, + "nauc_map_at_20_max": 0.1812935690295326, + "nauc_map_at_20_std": 0.0208795942762441, + "nauc_map_at_3_diff1": 0.407201486182724, + "nauc_map_at_3_max": 0.18637393511116282, + "nauc_map_at_3_std": 0.009618713521409996, + "nauc_map_at_5_diff1": 0.39798354071865893, + "nauc_map_at_5_max": 0.18419279974885236, + "nauc_map_at_5_std": 0.01669931491526469, + "nauc_mrr_at_1000_diff1": 0.3922364773668702, + "nauc_mrr_at_1000_max": 0.18037215542123264, + "nauc_mrr_at_1000_std": 0.0223034380979675, + "nauc_mrr_at_100_diff1": 0.3922344506573504, + "nauc_mrr_at_100_max": 0.1801798237366287, + "nauc_mrr_at_100_std": 0.02227287841826456, + "nauc_mrr_at_10_diff1": 0.3953104324986655, + "nauc_mrr_at_10_max": 0.18292918835826316, + "nauc_mrr_at_10_std": 0.018552565954239573, + "nauc_mrr_at_1_diff1": 0.4519506017232632, + "nauc_mrr_at_1_max": 0.1958063667846311, + "nauc_mrr_at_1_std": -0.0027198839307285413, + "nauc_mrr_at_20_diff1": 0.3927408611884983, + "nauc_mrr_at_20_max": 0.1812935690295326, + "nauc_mrr_at_20_std": 0.0208795942762441, + "nauc_mrr_at_3_diff1": 0.407201486182724, + "nauc_mrr_at_3_max": 0.18637393511116282, + "nauc_mrr_at_3_std": 0.009618713521409996, + "nauc_mrr_at_5_diff1": 0.39798354071865893, + "nauc_mrr_at_5_max": 0.18419279974885236, + "nauc_mrr_at_5_std": 0.01669931491526469, + "nauc_ndcg_at_1000_diff1": 0.3603118346168483, + "nauc_ndcg_at_1000_max": 0.16845588595609584, + "nauc_ndcg_at_1000_std": 0.05091051095271745, + "nauc_ndcg_at_100_diff1": 0.3596275906295944, + "nauc_ndcg_at_100_max": 0.16279511339337024, + "nauc_ndcg_at_100_std": 0.04914850734854474, + "nauc_ndcg_at_10_diff1": 0.37295892881266735, + "nauc_ndcg_at_10_max": 0.17683405862093796, + "nauc_ndcg_at_10_std": 0.029841292184418194, + "nauc_ndcg_at_1_diff1": 0.4519506017232632, + "nauc_ndcg_at_1_max": 0.1958063667846311, + "nauc_ndcg_at_1_std": -0.0027198839307285413, + "nauc_ndcg_at_20_diff1": 0.3643814860540615, + "nauc_ndcg_at_20_max": 0.1717831938524571, + "nauc_ndcg_at_20_std": 0.03844108471870648, + "nauc_ndcg_at_3_diff1": 0.3948543611458991, + "nauc_ndcg_at_3_max": 0.18346601757469316, + "nauc_ndcg_at_3_std": 0.014220331048213268, + "nauc_ndcg_at_5_diff1": 0.3795588351221598, + "nauc_ndcg_at_5_max": 0.17980091219927666, + "nauc_ndcg_at_5_std": 0.025934269500249883, + "nauc_precision_at_1000_diff1": 0.23793254606837994, + "nauc_precision_at_1000_max": 0.12947699674412405, + "nauc_precision_at_1000_std": 0.1891623488662091, + "nauc_precision_at_100_diff1": 0.25970435952748244, + "nauc_precision_at_100_max": 0.09823529943790159, + "nauc_precision_at_100_std": 0.14409634190050163, + "nauc_precision_at_10_diff1": 0.31671616522590185, + "nauc_precision_at_10_max": 0.16118006227789136, + "nauc_precision_at_10_std": 0.05860923932827503, + "nauc_precision_at_1_diff1": 0.4519506017232632, + "nauc_precision_at_1_max": 0.1958063667846311, + "nauc_precision_at_1_std": -0.0027198839307285413, + "nauc_precision_at_20_diff1": 0.28942750159366176, + "nauc_precision_at_20_max": 0.14547489241039124, + "nauc_precision_at_20_std": 0.08777117345334903, + "nauc_precision_at_3_diff1": 0.3643225694887193, + "nauc_precision_at_3_max": 0.17619541166647418, + "nauc_precision_at_3_std": 0.025912616083608907, + "nauc_precision_at_5_diff1": 0.33412577492269097, + "nauc_precision_at_5_max": 0.16886622757186362, + "nauc_precision_at_5_std": 0.04935245608491472, + "nauc_recall_at_1000_diff1": 0.23793254606838016, + "nauc_recall_at_1000_max": 0.12947699674412447, + "nauc_recall_at_1000_std": 0.1891623488662088, + "nauc_recall_at_100_diff1": 0.25970435952748255, + "nauc_recall_at_100_max": 0.0982352994379018, + "nauc_recall_at_100_std": 0.14409634190050186, + "nauc_recall_at_10_diff1": 0.31671616522590185, + "nauc_recall_at_10_max": 0.1611800622778913, + "nauc_recall_at_10_std": 0.05860923932827497, + "nauc_recall_at_1_diff1": 0.4519506017232632, + "nauc_recall_at_1_max": 0.1958063667846311, + "nauc_recall_at_1_std": -0.0027198839307285413, + "nauc_recall_at_20_diff1": 0.28942750159366193, + "nauc_recall_at_20_max": 0.14547489241039158, + "nauc_recall_at_20_std": 0.08777117345334905, + "nauc_recall_at_3_diff1": 0.3643225694887193, + "nauc_recall_at_3_max": 0.176195411666474, + "nauc_recall_at_3_std": 0.0259126160836088, + "nauc_recall_at_5_diff1": 0.33412577492269097, + "nauc_recall_at_5_max": 0.16886622757186365, + "nauc_recall_at_5_std": 0.04935245608491468, + "ndcg_at_1": 0.1547, + "ndcg_at_10": 0.25177, + "ndcg_at_100": 0.28878, + "ndcg_at_1000": 0.30962, + "ndcg_at_20": 0.26572, + "ndcg_at_3": 0.22015, + "ndcg_at_5": 0.23448, + "precision_at_1": 0.1547, + "precision_at_10": 0.03551, + "precision_at_100": 0.00537, + "precision_at_1000": 0.00071, + "precision_at_20": 0.02053, + "precision_at_3": 0.08899, + "precision_at_5": 0.06031, + "recall_at_1": 0.1547, + "recall_at_10": 0.35509, + "recall_at_100": 0.53655, + "recall_at_1000": 0.70627, + "recall_at_20": 0.41057, + "recall_at_3": 0.26697, + "recall_at_5": 0.30157 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/dragon-plus-instruct/no_revision_available/HellaSwag.json b/results/dragon-plus-instruct/no_revision_available/HellaSwag.json new file mode 100644 index 000000000..0bce0e7a4 --- /dev/null +++ b/results/dragon-plus-instruct/no_revision_available/HellaSwag.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 140.72930717468262, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.24055, + "map_at_1": 0.12906, + "map_at_10": 0.20188, + "map_at_100": 0.20902, + "map_at_1000": 0.20979, + "map_at_20": 0.20559, + "map_at_3": 0.18184, + "map_at_5": 0.19362, + "mrr_at_1": 0.1290579565823541, + "mrr_at_10": 0.20187834112599984, + "mrr_at_100": 0.20901679185809569, + "mrr_at_1000": 0.20979468140819177, + "mrr_at_20": 0.20559163850409753, + "mrr_at_3": 0.18183628759211204, + "mrr_at_5": 0.19362178848834835, + "nauc_map_at_1000_diff1": 0.24416573357835025, + "nauc_map_at_1000_max": -0.21364784001283602, + "nauc_map_at_1000_std": -0.026464988417571948, + "nauc_map_at_100_diff1": 0.2441613941218789, + "nauc_map_at_100_max": -0.21337714318124948, + "nauc_map_at_100_std": -0.026738326852922937, + "nauc_map_at_10_diff1": 0.24524054124561062, + "nauc_map_at_10_max": -0.20792825299044607, + "nauc_map_at_10_std": -0.029165252403777008, + "nauc_map_at_1_diff1": 0.2777567395778181, + "nauc_map_at_1_max": -0.17691837995965673, + "nauc_map_at_1_std": -0.03474267255841733, + "nauc_map_at_20_diff1": 0.24407836167316102, + "nauc_map_at_20_max": -0.21112741721028033, + "nauc_map_at_20_std": -0.028130362112442114, + "nauc_map_at_3_diff1": 0.24949389503289537, + "nauc_map_at_3_max": -0.19504453993397033, + "nauc_map_at_3_std": -0.03375257264405467, + "nauc_map_at_5_diff1": 0.24619662253780783, + "nauc_map_at_5_max": -0.20176361767352038, + "nauc_map_at_5_std": -0.03270214544244487, + "nauc_mrr_at_1000_diff1": 0.24416558250795126, + "nauc_mrr_at_1000_max": -0.2136478052822235, + "nauc_mrr_at_1000_std": -0.026464839164954474, + "nauc_mrr_at_100_diff1": 0.24416124347497856, + "nauc_mrr_at_100_max": -0.21337711159869072, + "nauc_mrr_at_100_std": -0.026738204954778196, + "nauc_mrr_at_10_diff1": 0.24524054124561062, + "nauc_mrr_at_10_max": -0.20792825299044607, + "nauc_mrr_at_10_std": -0.029165252403777008, + "nauc_mrr_at_1_diff1": 0.2777567395778181, + "nauc_mrr_at_1_max": -0.17691837995965673, + "nauc_mrr_at_1_std": -0.03474267255841733, + "nauc_mrr_at_20_diff1": 0.24407836167316102, + "nauc_mrr_at_20_max": -0.21112741721028033, + "nauc_mrr_at_20_std": -0.028130362112442114, + "nauc_mrr_at_3_diff1": 0.24949389503289537, + "nauc_mrr_at_3_max": -0.19504453993397033, + "nauc_mrr_at_3_std": -0.03375257264405467, + "nauc_mrr_at_5_diff1": 0.24619662253780783, + "nauc_mrr_at_5_max": -0.20176361767352038, + "nauc_mrr_at_5_std": -0.03270214544244487, + "nauc_ndcg_at_1000_diff1": 0.2327674014010483, + "nauc_ndcg_at_1000_max": -0.25971118931270715, + "nauc_ndcg_at_1000_std": -0.004748295374106445, + "nauc_ndcg_at_100_diff1": 0.23209109343109469, + "nauc_ndcg_at_100_max": -0.2519941688358104, + "nauc_ndcg_at_100_std": -0.011041706033333392, + "nauc_ndcg_at_10_diff1": 0.2353711099347271, + "nauc_ndcg_at_10_max": -0.22592656249205292, + "nauc_ndcg_at_10_std": -0.02418815065915398, + "nauc_ndcg_at_1_diff1": 0.2777567395778181, + "nauc_ndcg_at_1_max": -0.17691837995965673, + "nauc_ndcg_at_1_std": -0.03474267255841733, + "nauc_ndcg_at_20_diff1": 0.23154495514757473, + "nauc_ndcg_at_20_max": -0.23691773051716808, + "nauc_ndcg_at_20_std": -0.02080197278385441, + "nauc_ndcg_at_3_diff1": 0.24305249150922584, + "nauc_ndcg_at_3_max": -0.20129501122765034, + "nauc_ndcg_at_3_std": -0.03326415864001344, + "nauc_ndcg_at_5_diff1": 0.23763760034262285, + "nauc_ndcg_at_5_max": -0.2123515463987263, + "nauc_ndcg_at_5_std": -0.03164468563989357, + "nauc_precision_at_1000_diff1": 0.1942689529035835, + "nauc_precision_at_1000_max": -0.5186710005813253, + "nauc_precision_at_1000_std": 0.1329214957799766, + "nauc_precision_at_100_diff1": 0.20092766251471497, + "nauc_precision_at_100_max": -0.38146142432135977, + "nauc_precision_at_100_std": 0.046617331135407246, + "nauc_precision_at_10_diff1": 0.2126104010426623, + "nauc_precision_at_10_max": -0.27064358959422674, + "nauc_precision_at_10_std": -0.011292008037606967, + "nauc_precision_at_1_diff1": 0.2777567395778181, + "nauc_precision_at_1_max": -0.17691837995965673, + "nauc_precision_at_1_std": -0.03474267255841733, + "nauc_precision_at_20_diff1": 0.20075445498898867, + "nauc_precision_at_20_max": -0.3056840149756214, + "nauc_precision_at_20_std": -0.0007914238252687699, + "nauc_precision_at_3_diff1": 0.22804381922774314, + "nauc_precision_at_3_max": -0.2164638652556238, + "nauc_precision_at_3_std": -0.03205112176791107, + "nauc_precision_at_5_diff1": 0.21811366021178524, + "nauc_precision_at_5_max": -0.23750698371527806, + "nauc_precision_at_5_std": -0.029129996705266045, + "nauc_recall_at_1000_diff1": 0.1942689529035835, + "nauc_recall_at_1000_max": -0.5186710005813246, + "nauc_recall_at_1000_std": 0.13292149577997597, + "nauc_recall_at_100_diff1": 0.20092766251471544, + "nauc_recall_at_100_max": -0.38146142432135877, + "nauc_recall_at_100_std": 0.04661733113540787, + "nauc_recall_at_10_diff1": 0.21261040104266268, + "nauc_recall_at_10_max": -0.27064358959422663, + "nauc_recall_at_10_std": -0.011292008037606785, + "nauc_recall_at_1_diff1": 0.2777567395778181, + "nauc_recall_at_1_max": -0.17691837995965673, + "nauc_recall_at_1_std": -0.03474267255841733, + "nauc_recall_at_20_diff1": 0.20075445498898892, + "nauc_recall_at_20_max": -0.30568401497562075, + "nauc_recall_at_20_std": -0.0007914238252684068, + "nauc_recall_at_3_diff1": 0.22804381922774317, + "nauc_recall_at_3_max": -0.21646386525562394, + "nauc_recall_at_3_std": -0.032051121767911014, + "nauc_recall_at_5_diff1": 0.21811366021178571, + "nauc_recall_at_5_max": -0.23750698371527795, + "nauc_recall_at_5_std": -0.02912999670526599, + "ndcg_at_1": 0.12906, + "ndcg_at_10": 0.24055, + "ndcg_at_100": 0.27992, + "ndcg_at_1000": 0.30394, + "ndcg_at_20": 0.25425, + "ndcg_at_3": 0.19943, + "ndcg_at_5": 0.22059, + "precision_at_1": 0.12906, + "precision_at_10": 0.03633, + "precision_at_100": 0.00558, + "precision_at_1000": 0.00075, + "precision_at_20": 0.02089, + "precision_at_3": 0.08348, + "precision_at_5": 0.06033, + "recall_at_1": 0.12906, + "recall_at_10": 0.36327, + "recall_at_100": 0.55806, + "recall_at_1000": 0.75463, + "recall_at_20": 0.41785, + "recall_at_3": 0.25045, + "recall_at_5": 0.30163 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/dragon-plus-instruct/no_revision_available/PIQA.json b/results/dragon-plus-instruct/no_revision_available/PIQA.json new file mode 100644 index 000000000..6bbccaac4 --- /dev/null +++ b/results/dragon-plus-instruct/no_revision_available/PIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 17.057050943374634, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.26351, + "map_at_1": 0.14418, + "map_at_10": 0.22368, + "map_at_100": 0.23117, + "map_at_1000": 0.23181, + "map_at_20": 0.22809, + "map_at_3": 0.20394, + "map_at_5": 0.21552, + "mrr_at_1": 0.1441784548422198, + "mrr_at_10": 0.22367911981622499, + "mrr_at_100": 0.23117165708332257, + "mrr_at_1000": 0.23180998101471648, + "mrr_at_20": 0.22808743468314163, + "mrr_at_3": 0.203935437069278, + "mrr_at_5": 0.21552412042074684, + "nauc_map_at_1000_diff1": -0.12483985700159446, + "nauc_map_at_1000_max": 0.051624167609575604, + "nauc_map_at_1000_std": 0.11651174065404195, + "nauc_map_at_100_diff1": -0.12455776113268659, + "nauc_map_at_100_max": 0.0518194214235007, + "nauc_map_at_100_std": 0.11659461297764417, + "nauc_map_at_10_diff1": -0.12029829517240735, + "nauc_map_at_10_max": 0.056764125018558806, + "nauc_map_at_10_std": 0.11442190850257976, + "nauc_map_at_1_diff1": -0.0798207566360514, + "nauc_map_at_1_max": 0.06940546960669645, + "nauc_map_at_1_std": 0.0827582036922033, + "nauc_map_at_20_diff1": -0.12364713430247348, + "nauc_map_at_20_max": 0.0538782774029719, + "nauc_map_at_20_std": 0.11486481869154634, + "nauc_map_at_3_diff1": -0.11247683113407525, + "nauc_map_at_3_max": 0.0702313003049327, + "nauc_map_at_3_std": 0.106265672438128, + "nauc_map_at_5_diff1": -0.1161003811316977, + "nauc_map_at_5_max": 0.06211940372019851, + "nauc_map_at_5_std": 0.10965548162544393, + "nauc_mrr_at_1000_diff1": -0.12483931100120613, + "nauc_mrr_at_1000_max": 0.05162496855378314, + "nauc_mrr_at_1000_std": 0.11650917715000263, + "nauc_mrr_at_100_diff1": -0.1245572158174884, + "nauc_mrr_at_100_max": 0.051820221401782635, + "nauc_mrr_at_100_std": 0.11659205243820006, + "nauc_mrr_at_10_diff1": -0.12029829517240735, + "nauc_mrr_at_10_max": 0.056764125018558806, + "nauc_mrr_at_10_std": 0.11442190850257976, + "nauc_mrr_at_1_diff1": -0.0798207566360514, + "nauc_mrr_at_1_max": 0.06940546960669645, + "nauc_mrr_at_1_std": 0.0827582036922033, + "nauc_mrr_at_20_diff1": -0.12364713430247348, + "nauc_mrr_at_20_max": 0.0538782774029719, + "nauc_mrr_at_20_std": 0.11486481869154634, + "nauc_mrr_at_3_diff1": -0.11247683113407525, + "nauc_mrr_at_3_max": 0.0702313003049327, + "nauc_mrr_at_3_std": 0.106265672438128, + "nauc_mrr_at_5_diff1": -0.1161003811316977, + "nauc_mrr_at_5_max": 0.06211940372019851, + "nauc_mrr_at_5_std": 0.10965548162544393, + "nauc_ndcg_at_1000_diff1": -0.1595172329823983, + "nauc_ndcg_at_1000_max": 0.01214224318243086, + "nauc_ndcg_at_1000_std": 0.13885957000367372, + "nauc_ndcg_at_100_diff1": -0.15169092023025654, + "nauc_ndcg_at_100_max": 0.017511764976533575, + "nauc_ndcg_at_100_std": 0.14175541605926487, + "nauc_ndcg_at_10_diff1": -0.13547657179963613, + "nauc_ndcg_at_10_max": 0.04216991647478316, + "nauc_ndcg_at_10_std": 0.12934997771916015, + "nauc_ndcg_at_1_diff1": -0.0798207566360514, + "nauc_ndcg_at_1_max": 0.06940546960669645, + "nauc_ndcg_at_1_std": 0.0827582036922033, + "nauc_ndcg_at_20_diff1": -0.14639405993548066, + "nauc_ndcg_at_20_max": 0.0320893425324151, + "nauc_ndcg_at_20_std": 0.13040434017498456, + "nauc_ndcg_at_3_diff1": -0.11942237932957087, + "nauc_ndcg_at_3_max": 0.0682009376640014, + "nauc_ndcg_at_3_std": 0.11170040502139816, + "nauc_ndcg_at_5_diff1": -0.1256163413042666, + "nauc_ndcg_at_5_max": 0.054245630863150825, + "nauc_ndcg_at_5_std": 0.11746741029858865, + "nauc_precision_at_1000_diff1": -0.34253224641589125, + "nauc_precision_at_1000_max": -0.2034857458549881, + "nauc_precision_at_1000_std": 0.2303905648522858, + "nauc_precision_at_100_diff1": -0.2391746052247934, + "nauc_precision_at_100_max": -0.10935579191218614, + "nauc_precision_at_100_std": 0.22983436363142118, + "nauc_precision_at_10_diff1": -0.1737096259329609, + "nauc_precision_at_10_max": 0.00309677785865738, + "nauc_precision_at_10_std": 0.1683542406575799, + "nauc_precision_at_1_diff1": -0.0798207566360514, + "nauc_precision_at_1_max": 0.06940546960669645, + "nauc_precision_at_1_std": 0.0827582036922033, + "nauc_precision_at_20_diff1": -0.20957743458042163, + "nauc_precision_at_20_max": -0.03133156462418934, + "nauc_precision_at_20_std": 0.17151086833658613, + "nauc_precision_at_3_diff1": -0.13571390793610077, + "nauc_precision_at_3_max": 0.0627395440110123, + "nauc_precision_at_3_std": 0.12458597467623356, + "nauc_precision_at_5_diff1": -0.14812511370991863, + "nauc_precision_at_5_max": 0.03370103454215239, + "nauc_precision_at_5_std": 0.13615279798784885, + "nauc_recall_at_1000_diff1": -0.34253224641589053, + "nauc_recall_at_1000_max": -0.20348574585498708, + "nauc_recall_at_1000_std": 0.2303905648522861, + "nauc_recall_at_100_diff1": -0.23917460522479383, + "nauc_recall_at_100_max": -0.10935579191218613, + "nauc_recall_at_100_std": 0.22983436363142073, + "nauc_recall_at_10_diff1": -0.173709625932961, + "nauc_recall_at_10_max": 0.0030967778586572445, + "nauc_recall_at_10_std": 0.16835424065758006, + "nauc_recall_at_1_diff1": -0.0798207566360514, + "nauc_recall_at_1_max": 0.06940546960669645, + "nauc_recall_at_1_std": 0.0827582036922033, + "nauc_recall_at_20_diff1": -0.20957743458042133, + "nauc_recall_at_20_max": -0.03133156462418915, + "nauc_recall_at_20_std": 0.1715108683365865, + "nauc_recall_at_3_diff1": -0.13571390793610089, + "nauc_recall_at_3_max": 0.06273954401101235, + "nauc_recall_at_3_std": 0.12458597467623338, + "nauc_recall_at_5_diff1": -0.14812511370991843, + "nauc_recall_at_5_max": 0.03370103454215269, + "nauc_recall_at_5_std": 0.13615279798784893, + "ndcg_at_1": 0.14418, + "ndcg_at_10": 0.26351, + "ndcg_at_100": 0.30274, + "ndcg_at_1000": 0.32146, + "ndcg_at_20": 0.27959, + "ndcg_at_3": 0.22261, + "ndcg_at_5": 0.24347, + "precision_at_1": 0.14418, + "precision_at_10": 0.03896, + "precision_at_100": 0.00579, + "precision_at_1000": 0.00073, + "precision_at_20": 0.02266, + "precision_at_3": 0.09213, + "precision_at_5": 0.0654, + "recall_at_1": 0.14418, + "recall_at_10": 0.38955, + "recall_at_100": 0.57943, + "recall_at_1000": 0.73069, + "recall_at_20": 0.45321, + "recall_at_3": 0.27639, + "recall_at_5": 0.32699 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/dragon-plus-instruct/no_revision_available/Quail.json b/results/dragon-plus-instruct/no_revision_available/Quail.json new file mode 100644 index 000000000..ed2cbad89 --- /dev/null +++ b/results/dragon-plus-instruct/no_revision_available/Quail.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 25.593027591705322, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.04195, + "map_at_1": 0.01581, + "map_at_10": 0.0307, + "map_at_100": 0.03518, + "map_at_1000": 0.03592, + "map_at_20": 0.03284, + "map_at_3": 0.02316, + "map_at_5": 0.02678, + "mrr_at_1": 0.015808823529411764, + "mrr_at_10": 0.030695903361344545, + "mrr_at_100": 0.03518113954384856, + "mrr_at_1000": 0.03592369523937361, + "mrr_at_20": 0.03283505841373263, + "mrr_at_3": 0.02316176470588236, + "mrr_at_5": 0.02678308823529413, + "nauc_map_at_1000_diff1": 0.07957605736536157, + "nauc_map_at_1000_max": 0.009703344441833555, + "nauc_map_at_1000_std": 0.1281341425860126, + "nauc_map_at_100_diff1": 0.08085924340086048, + "nauc_map_at_100_max": 0.010606660767598204, + "nauc_map_at_100_std": 0.12814977395963276, + "nauc_map_at_10_diff1": 0.08373092083883311, + "nauc_map_at_10_max": 0.021576971413586412, + "nauc_map_at_10_std": 0.12299710362924215, + "nauc_map_at_1_diff1": 0.11199855236146032, + "nauc_map_at_1_max": 0.015636992156544686, + "nauc_map_at_1_std": 0.08000698859984666, + "nauc_map_at_20_diff1": 0.085213800267144, + "nauc_map_at_20_max": 0.01512049495934279, + "nauc_map_at_20_std": 0.12499214218694502, + "nauc_map_at_3_diff1": 0.09297234679579716, + "nauc_map_at_3_max": 0.017014407945451518, + "nauc_map_at_3_std": 0.11118706195175204, + "nauc_map_at_5_diff1": 0.09072786667400842, + "nauc_map_at_5_max": 0.01646446869097305, + "nauc_map_at_5_std": 0.11608120133693334, + "nauc_mrr_at_1000_diff1": 0.07957325676820261, + "nauc_mrr_at_1000_max": 0.00969335653255178, + "nauc_mrr_at_1000_std": 0.12812498901150943, + "nauc_mrr_at_100_diff1": 0.08085645215171826, + "nauc_mrr_at_100_max": 0.010596403310849756, + "nauc_mrr_at_100_std": 0.12814041981585755, + "nauc_mrr_at_10_diff1": 0.08373092083883311, + "nauc_mrr_at_10_max": 0.021576971413586412, + "nauc_mrr_at_10_std": 0.12299710362924215, + "nauc_mrr_at_1_diff1": 0.11199855236146032, + "nauc_mrr_at_1_max": 0.015636992156544686, + "nauc_mrr_at_1_std": 0.08000698859984666, + "nauc_mrr_at_20_diff1": 0.085213800267144, + "nauc_mrr_at_20_max": 0.01512049495934279, + "nauc_mrr_at_20_std": 0.12499214218694502, + "nauc_mrr_at_3_diff1": 0.09297234679579716, + "nauc_mrr_at_3_max": 0.017014407945451518, + "nauc_mrr_at_3_std": 0.11118706195175204, + "nauc_mrr_at_5_diff1": 0.09072786667400842, + "nauc_mrr_at_5_max": 0.01646446869097305, + "nauc_mrr_at_5_std": 0.11608120133693334, + "nauc_ndcg_at_1000_diff1": 0.04127779337995637, + "nauc_ndcg_at_1000_max": -0.011640937779348558, + "nauc_ndcg_at_1000_std": 0.14175081637990172, + "nauc_ndcg_at_100_diff1": 0.059620980695701396, + "nauc_ndcg_at_100_max": -0.004029943495575439, + "nauc_ndcg_at_100_std": 0.14419036194946158, + "nauc_ndcg_at_10_diff1": 0.06960205335607622, + "nauc_ndcg_at_10_max": 0.022956385848332133, + "nauc_ndcg_at_10_std": 0.13201878422897004, + "nauc_ndcg_at_1_diff1": 0.11199855236146032, + "nauc_ndcg_at_1_max": 0.015636992156544686, + "nauc_ndcg_at_1_std": 0.08000698859984666, + "nauc_ndcg_at_20_diff1": 0.07535606201423213, + "nauc_ndcg_at_20_max": 0.006913467094655207, + "nauc_ndcg_at_20_std": 0.1351400004306507, + "nauc_ndcg_at_3_diff1": 0.0852648843162417, + "nauc_ndcg_at_3_max": 0.016585743837722534, + "nauc_ndcg_at_3_std": 0.11604863899321144, + "nauc_ndcg_at_5_diff1": 0.0836790160710671, + "nauc_ndcg_at_5_max": 0.015181367420637687, + "nauc_ndcg_at_5_std": 0.12213667271159179, + "nauc_precision_at_1000_diff1": -0.003748716363745301, + "nauc_precision_at_1000_max": -0.031107794111154337, + "nauc_precision_at_1000_std": 0.14879973185473608, + "nauc_precision_at_100_diff1": 0.039177065119948194, + "nauc_precision_at_100_max": -0.017329780187113415, + "nauc_precision_at_100_std": 0.15806234156549132, + "nauc_precision_at_10_diff1": 0.049704856452911374, + "nauc_precision_at_10_max": 0.02446610817955077, + "nauc_precision_at_10_std": 0.14310859692533984, + "nauc_precision_at_1_diff1": 0.11199855236146032, + "nauc_precision_at_1_max": 0.015636992156544686, + "nauc_precision_at_1_std": 0.08000698859984666, + "nauc_precision_at_20_diff1": 0.06531623878193055, + "nauc_precision_at_20_max": -0.005145464875330173, + "nauc_precision_at_20_std": 0.14545108544762894, + "nauc_precision_at_3_diff1": 0.06892088324876094, + "nauc_precision_at_3_max": 0.015562114301046336, + "nauc_precision_at_3_std": 0.12545517267814021, + "nauc_precision_at_5_diff1": 0.07204483796917396, + "nauc_precision_at_5_max": 0.012664341293265385, + "nauc_precision_at_5_std": 0.13169364696061778, + "nauc_recall_at_1000_diff1": -0.0037487163637451503, + "nauc_recall_at_1000_max": -0.031107794111154045, + "nauc_recall_at_1000_std": 0.14879973185473613, + "nauc_recall_at_100_diff1": 0.03917706511994793, + "nauc_recall_at_100_max": -0.01732978018711364, + "nauc_recall_at_100_std": 0.15806234156549095, + "nauc_recall_at_10_diff1": 0.04970485645291116, + "nauc_recall_at_10_max": 0.024466108179550517, + "nauc_recall_at_10_std": 0.14310859692533967, + "nauc_recall_at_1_diff1": 0.11199855236146032, + "nauc_recall_at_1_max": 0.015636992156544686, + "nauc_recall_at_1_std": 0.08000698859984666, + "nauc_recall_at_20_diff1": 0.06531623878193045, + "nauc_recall_at_20_max": -0.005145464875330302, + "nauc_recall_at_20_std": 0.14545108544762886, + "nauc_recall_at_3_diff1": 0.068920883248761, + "nauc_recall_at_3_max": 0.015562114301046474, + "nauc_recall_at_3_std": 0.12545517267814033, + "nauc_recall_at_5_diff1": 0.07204483796917387, + "nauc_recall_at_5_max": 0.012664341293265335, + "nauc_recall_at_5_std": 0.13169364696061767, + "ndcg_at_1": 0.01581, + "ndcg_at_10": 0.04195, + "ndcg_at_100": 0.0675, + "ndcg_at_1000": 0.09184, + "ndcg_at_20": 0.04987, + "ndcg_at_3": 0.02579, + "ndcg_at_5": 0.03238, + "precision_at_1": 0.01581, + "precision_at_10": 0.00794, + "precision_at_100": 0.00207, + "precision_at_1000": 0.00041, + "precision_at_20": 0.00555, + "precision_at_3": 0.01115, + "precision_at_5": 0.00993, + "recall_at_1": 0.01581, + "recall_at_10": 0.07941, + "recall_at_100": 0.20735, + "recall_at_1000": 0.40919, + "recall_at_20": 0.11103, + "recall_at_3": 0.03346, + "recall_at_5": 0.04963 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/dragon-plus-instruct/no_revision_available/RARbCode.json b/results/dragon-plus-instruct/no_revision_available/RARbCode.json new file mode 100644 index 000000000..8063be6c5 --- /dev/null +++ b/results/dragon-plus-instruct/no_revision_available/RARbCode.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 884.8957123756409, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.1284, + "map_at_1": 0.06873, + "map_at_10": 0.10705, + "map_at_100": 0.11327, + "map_at_1000": 0.11406, + "map_at_20": 0.11041, + "map_at_3": 0.09546, + "map_at_5": 0.10207, + "mrr_at_1": 0.06873315363881402, + "mrr_at_10": 0.10705113806528899, + "mrr_at_100": 0.1132658175614359, + "mrr_at_1000": 0.11406307336260896, + "mrr_at_20": 0.11041148999941135, + "mrr_at_3": 0.09546271338724169, + "mrr_at_5": 0.10206648697214735, + "nauc_map_at_1000_diff1": 0.29660864491065553, + "nauc_map_at_1000_max": -0.14572209087248125, + "nauc_map_at_1000_std": 0.023589862220722815, + "nauc_map_at_100_diff1": 0.29638973211481634, + "nauc_map_at_100_max": -0.14580643436009288, + "nauc_map_at_100_std": 0.022817128651546906, + "nauc_map_at_10_diff1": 0.30390235805189786, + "nauc_map_at_10_max": -0.1445608070053889, + "nauc_map_at_10_std": 0.015852505021221517, + "nauc_map_at_1_diff1": 0.47400586317107846, + "nauc_map_at_1_max": -0.13895097665810216, + "nauc_map_at_1_std": -0.032971191647526994, + "nauc_map_at_20_diff1": 0.2994304991601027, + "nauc_map_at_20_max": -0.14698518302898014, + "nauc_map_at_20_std": 0.020270140569263843, + "nauc_map_at_3_diff1": 0.33520391211893397, + "nauc_map_at_3_max": -0.14827467636751646, + "nauc_map_at_3_std": 0.01066314454841034, + "nauc_map_at_5_diff1": 0.31818713519992786, + "nauc_map_at_5_max": -0.1443032584640947, + "nauc_map_at_5_std": 0.014119453876019754, + "nauc_mrr_at_1000_diff1": 0.29660865128513547, + "nauc_mrr_at_1000_max": -0.14572208596298614, + "nauc_mrr_at_1000_std": 0.023589858917100012, + "nauc_mrr_at_100_diff1": 0.29638973211481634, + "nauc_mrr_at_100_max": -0.14580643436009288, + "nauc_mrr_at_100_std": 0.022817128651546906, + "nauc_mrr_at_10_diff1": 0.30390235805189786, + "nauc_mrr_at_10_max": -0.1445608070053889, + "nauc_mrr_at_10_std": 0.015852505021221517, + "nauc_mrr_at_1_diff1": 0.47400586317107846, + "nauc_mrr_at_1_max": -0.13895097665810216, + "nauc_mrr_at_1_std": -0.032971191647526994, + "nauc_mrr_at_20_diff1": 0.2994304991601027, + "nauc_mrr_at_20_max": -0.14698518302898014, + "nauc_mrr_at_20_std": 0.020270140569263843, + "nauc_mrr_at_3_diff1": 0.33520391211893397, + "nauc_mrr_at_3_max": -0.14827467636751646, + "nauc_mrr_at_3_std": 0.01066314454841034, + "nauc_mrr_at_5_diff1": 0.31818713519992786, + "nauc_mrr_at_5_max": -0.1443032584640947, + "nauc_mrr_at_5_std": 0.014119453876019754, + "nauc_ndcg_at_1000_diff1": 0.23108887343720785, + "nauc_ndcg_at_1000_max": -0.15558603719949932, + "nauc_ndcg_at_1000_std": 0.07453641544704631, + "nauc_ndcg_at_100_diff1": 0.2272796580798676, + "nauc_ndcg_at_100_max": -0.14975929689515388, + "nauc_ndcg_at_100_std": 0.058369328841010766, + "nauc_ndcg_at_10_diff1": 0.2547513152264155, + "nauc_ndcg_at_10_max": -0.14758462066584704, + "nauc_ndcg_at_10_std": 0.028312797147009065, + "nauc_ndcg_at_1_diff1": 0.47400586317107846, + "nauc_ndcg_at_1_max": -0.13895097665810216, + "nauc_ndcg_at_1_std": -0.032971191647526994, + "nauc_ndcg_at_20_diff1": 0.2435140608782302, + "nauc_ndcg_at_20_max": -0.1549868970589191, + "nauc_ndcg_at_20_std": 0.04176004683396784, + "nauc_ndcg_at_3_diff1": 0.30694793561397704, + "nauc_ndcg_at_3_max": -0.15044954623524873, + "nauc_ndcg_at_3_std": 0.020164564400168162, + "nauc_ndcg_at_5_diff1": 0.2814554044489692, + "nauc_ndcg_at_5_max": -0.14493732716484978, + "nauc_ndcg_at_5_std": 0.025340776848997465, + "nauc_precision_at_1000_diff1": 0.10772201004762307, + "nauc_precision_at_1000_max": -0.19808267283949574, + "nauc_precision_at_1000_std": 0.22520530828173252, + "nauc_precision_at_100_diff1": 0.09945908774403095, + "nauc_precision_at_100_max": -0.15709048163783848, + "nauc_precision_at_100_std": 0.136962246637586, + "nauc_precision_at_10_diff1": 0.16081397086143995, + "nauc_precision_at_10_max": -0.15502529288432235, + "nauc_precision_at_10_std": 0.05143552453011208, + "nauc_precision_at_1_diff1": 0.47400586317107846, + "nauc_precision_at_1_max": -0.13895097665810216, + "nauc_precision_at_1_std": -0.032971191647526994, + "nauc_precision_at_20_diff1": 0.14106958965927463, + "nauc_precision_at_20_max": -0.17373064415096207, + "nauc_precision_at_20_std": 0.08490186116158263, + "nauc_precision_at_3_diff1": 0.2451698884431849, + "nauc_precision_at_3_max": -0.1552823422225991, + "nauc_precision_at_3_std": 0.04111191113019968, + "nauc_precision_at_5_diff1": 0.20612708328888832, + "nauc_precision_at_5_max": -0.1462461208850518, + "nauc_precision_at_5_std": 0.04836765407114392, + "nauc_recall_at_1000_diff1": 0.10772201004762313, + "nauc_recall_at_1000_max": -0.1980826728394952, + "nauc_recall_at_1000_std": 0.22520530828173363, + "nauc_recall_at_100_diff1": 0.09945908774403091, + "nauc_recall_at_100_max": -0.15709048163783831, + "nauc_recall_at_100_std": 0.13696224663758616, + "nauc_recall_at_10_diff1": 0.16081397086143995, + "nauc_recall_at_10_max": -0.15502529288432232, + "nauc_recall_at_10_std": 0.0514355245301119, + "nauc_recall_at_1_diff1": 0.47400586317107846, + "nauc_recall_at_1_max": -0.13895097665810216, + "nauc_recall_at_1_std": -0.032971191647526994, + "nauc_recall_at_20_diff1": 0.1410695896592744, + "nauc_recall_at_20_max": -0.17373064415096218, + "nauc_recall_at_20_std": 0.0849018611615825, + "nauc_recall_at_3_diff1": 0.2451698884431848, + "nauc_recall_at_3_max": -0.15528234222259876, + "nauc_recall_at_3_std": 0.04111191113019982, + "nauc_recall_at_5_diff1": 0.2061270832888882, + "nauc_recall_at_5_max": -0.14624612088505184, + "nauc_recall_at_5_std": 0.048367654071143726, + "ndcg_at_1": 0.06873, + "ndcg_at_10": 0.1284, + "ndcg_at_100": 0.16152, + "ndcg_at_1000": 0.1867, + "ndcg_at_20": 0.14044, + "ndcg_at_3": 0.10433, + "ndcg_at_5": 0.11625, + "precision_at_1": 0.06873, + "precision_at_10": 0.01968, + "precision_at_100": 0.00358, + "precision_at_1000": 0.00057, + "precision_at_20": 0.0122, + "precision_at_3": 0.04335, + "precision_at_5": 0.03181, + "recall_at_1": 0.06873, + "recall_at_10": 0.19677, + "recall_at_100": 0.35849, + "recall_at_1000": 0.56536, + "recall_at_20": 0.24394, + "recall_at_3": 0.13005, + "recall_at_5": 0.15903 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/dragon-plus-instruct/no_revision_available/RARbMath.json b/results/dragon-plus-instruct/no_revision_available/RARbMath.json new file mode 100644 index 000000000..ff6fa8ac9 --- /dev/null +++ b/results/dragon-plus-instruct/no_revision_available/RARbMath.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 1369.9309537410736, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.36154, + "map_at_1": 0.31192, + "map_at_10": 0.34269, + "map_at_100": 0.34907, + "map_at_1000": 0.34986, + "map_at_20": 0.3458, + "map_at_3": 0.3313, + "map_at_5": 0.3374, + "mrr_at_1": 0.31191644247507516, + "mrr_at_10": 0.3426888421666079, + "mrr_at_100": 0.3490710998056446, + "mrr_at_1000": 0.34985981236026925, + "mrr_at_20": 0.3458046295465339, + "mrr_at_3": 0.3313024212691882, + "mrr_at_5": 0.3373951574616239, + "nauc_map_at_1000_diff1": 0.7836112453270794, + "nauc_map_at_1000_max": 0.4357027853656558, + "nauc_map_at_1000_std": 0.08372422950270067, + "nauc_map_at_100_diff1": 0.7835181569180224, + "nauc_map_at_100_max": 0.435750558652354, + "nauc_map_at_100_std": 0.08354621587963475, + "nauc_map_at_10_diff1": 0.788502284901747, + "nauc_map_at_10_max": 0.43899323826082515, + "nauc_map_at_10_std": 0.08247666263399442, + "nauc_map_at_1_diff1": 0.8334859432246678, + "nauc_map_at_1_max": 0.4565579849951537, + "nauc_map_at_1_std": 0.0882687399249475, + "nauc_map_at_20_diff1": 0.7855798320725648, + "nauc_map_at_20_max": 0.43714518716066275, + "nauc_map_at_20_std": 0.08287625257076903, + "nauc_map_at_3_diff1": 0.8047450438413818, + "nauc_map_at_3_max": 0.4477826241147712, + "nauc_map_at_3_std": 0.08409588978795027, + "nauc_map_at_5_diff1": 0.7944103038621568, + "nauc_map_at_5_max": 0.44237860964611986, + "nauc_map_at_5_std": 0.08448706451864091, + "nauc_mrr_at_1000_diff1": 0.7836112464158018, + "nauc_mrr_at_1000_max": 0.4357027777472772, + "nauc_mrr_at_1000_std": 0.08372421760295808, + "nauc_mrr_at_100_diff1": 0.7835181569180224, + "nauc_mrr_at_100_max": 0.435750558652354, + "nauc_mrr_at_100_std": 0.08354621587963475, + "nauc_mrr_at_10_diff1": 0.788502284901747, + "nauc_mrr_at_10_max": 0.43899323826082515, + "nauc_mrr_at_10_std": 0.08247666263399442, + "nauc_mrr_at_1_diff1": 0.8334859432246678, + "nauc_mrr_at_1_max": 0.4565579849951537, + "nauc_mrr_at_1_std": 0.0882687399249475, + "nauc_mrr_at_20_diff1": 0.7855798320725648, + "nauc_mrr_at_20_max": 0.43714518716066275, + "nauc_mrr_at_20_std": 0.08287625257076903, + "nauc_mrr_at_3_diff1": 0.8047450438413818, + "nauc_mrr_at_3_max": 0.4477826241147712, + "nauc_mrr_at_3_std": 0.08409588978795027, + "nauc_mrr_at_5_diff1": 0.7944103038621568, + "nauc_mrr_at_5_max": 0.44237860964611986, + "nauc_mrr_at_5_std": 0.08448706451864091, + "nauc_ndcg_at_1000_diff1": 0.7404548790223437, + "nauc_ndcg_at_1000_max": 0.4137391767466584, + "nauc_ndcg_at_1000_std": 0.0937031455020343, + "nauc_ndcg_at_100_diff1": 0.7369624835880764, + "nauc_ndcg_at_100_max": 0.4104960640495113, + "nauc_ndcg_at_100_std": 0.08532666189013596, + "nauc_ndcg_at_10_diff1": 0.7632024803578513, + "nauc_ndcg_at_10_max": 0.4270594168271953, + "nauc_ndcg_at_10_std": 0.07873067638846484, + "nauc_ndcg_at_1_diff1": 0.8334859432246678, + "nauc_ndcg_at_1_max": 0.4565579849951537, + "nauc_ndcg_at_1_std": 0.0882687399249475, + "nauc_ndcg_at_20_diff1": 0.7521170174148304, + "nauc_ndcg_at_20_max": 0.4203916316150513, + "nauc_ndcg_at_20_std": 0.08032217174434664, + "nauc_ndcg_at_3_diff1": 0.7954872050014714, + "nauc_ndcg_at_3_max": 0.4445738266273162, + "nauc_ndcg_at_3_std": 0.08274736970332768, + "nauc_ndcg_at_5_diff1": 0.7770029112033605, + "nauc_ndcg_at_5_max": 0.4347971861424772, + "nauc_ndcg_at_5_std": 0.08341407253260702, + "nauc_precision_at_1000_diff1": 0.4392423198642246, + "nauc_precision_at_1000_max": 0.281159114500259, + "nauc_precision_at_1000_std": 0.25194107904276597, + "nauc_precision_at_100_diff1": 0.5334878101887933, + "nauc_precision_at_100_max": 0.29677449781647236, + "nauc_precision_at_100_std": 0.10202457305280277, + "nauc_precision_at_10_diff1": 0.6841117427966766, + "nauc_precision_at_10_max": 0.38915471033097326, + "nauc_precision_at_10_std": 0.06652959544400644, + "nauc_precision_at_1_diff1": 0.8334859432246678, + "nauc_precision_at_1_max": 0.4565579849951537, + "nauc_precision_at_1_std": 0.0882687399249475, + "nauc_precision_at_20_diff1": 0.6384676226741547, + "nauc_precision_at_20_max": 0.3625139168432989, + "nauc_precision_at_20_std": 0.0729460354089473, + "nauc_precision_at_3_diff1": 0.7690205125028138, + "nauc_precision_at_3_max": 0.43528475922045695, + "nauc_precision_at_3_std": 0.07889083711261215, + "nauc_precision_at_5_diff1": 0.7251891911125816, + "nauc_precision_at_5_max": 0.4118099040595989, + "nauc_precision_at_5_std": 0.08043820236235855, + "nauc_recall_at_1000_diff1": 0.4392423198642261, + "nauc_recall_at_1000_max": 0.28115911450026004, + "nauc_recall_at_1000_std": 0.2519410790427675, + "nauc_recall_at_100_diff1": 0.5334878101887929, + "nauc_recall_at_100_max": 0.2967744978164714, + "nauc_recall_at_100_std": 0.10202457305280217, + "nauc_recall_at_10_diff1": 0.6841117427966766, + "nauc_recall_at_10_max": 0.3891547103309732, + "nauc_recall_at_10_std": 0.0665295954440066, + "nauc_recall_at_1_diff1": 0.8334859432246678, + "nauc_recall_at_1_max": 0.4565579849951537, + "nauc_recall_at_1_std": 0.0882687399249475, + "nauc_recall_at_20_diff1": 0.6384676226741547, + "nauc_recall_at_20_max": 0.36251391684329864, + "nauc_recall_at_20_std": 0.07294603540894712, + "nauc_recall_at_3_diff1": 0.7690205125028143, + "nauc_recall_at_3_max": 0.4352847592204573, + "nauc_recall_at_3_std": 0.07889083711261237, + "nauc_recall_at_5_diff1": 0.7251891911125818, + "nauc_recall_at_5_max": 0.41180990405959894, + "nauc_recall_at_5_std": 0.08043820236235881, + "ndcg_at_1": 0.31192, + "ndcg_at_10": 0.36154, + "ndcg_at_100": 0.3981, + "ndcg_at_1000": 0.42317, + "ndcg_at_20": 0.37306, + "ndcg_at_3": 0.33774, + "ndcg_at_5": 0.34873, + "precision_at_1": 0.31192, + "precision_at_10": 0.04227, + "precision_at_100": 0.00606, + "precision_at_1000": 0.00081, + "precision_at_20": 0.02343, + "precision_at_3": 0.1188, + "precision_at_5": 0.07663, + "recall_at_1": 0.31192, + "recall_at_10": 0.42269, + "recall_at_100": 0.60643, + "recall_at_1000": 0.81279, + "recall_at_20": 0.46859, + "recall_at_3": 0.35639, + "recall_at_5": 0.38313 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/dragon-plus-instruct/no_revision_available/SIQA.json b/results/dragon-plus-instruct/no_revision_available/SIQA.json new file mode 100644 index 000000000..e134e58ec --- /dev/null +++ b/results/dragon-plus-instruct/no_revision_available/SIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 13.77496337890625, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01748, + "map_at_1": 0.01126, + "map_at_10": 0.01516, + "map_at_100": 0.01624, + "map_at_1000": 0.01677, + "map_at_20": 0.01561, + "map_at_3": 0.0139, + "map_at_5": 0.01447, + "mrr_at_1": 0.011258955987717503, + "mrr_at_10": 0.015161207778915047, + "mrr_at_100": 0.016237450092231393, + "mrr_at_1000": 0.01676890385560605, + "mrr_at_20": 0.015609460353571027, + "mrr_at_3": 0.013903104742408733, + "mrr_at_5": 0.014466052541794608, + "nauc_map_at_1000_diff1": 0.24593862504165834, + "nauc_map_at_1000_max": -0.07049953465042125, + "nauc_map_at_1000_std": -0.3496353481495969, + "nauc_map_at_100_diff1": 0.2515162766549995, + "nauc_map_at_100_max": -0.07129682661100908, + "nauc_map_at_100_std": -0.3530942074406207, + "nauc_map_at_10_diff1": 0.2670499662815176, + "nauc_map_at_10_max": -0.07951486952577923, + "nauc_map_at_10_std": -0.3633499210268088, + "nauc_map_at_1_diff1": 0.29582814872472407, + "nauc_map_at_1_max": -0.1849504051033388, + "nauc_map_at_1_std": -0.38018003257877575, + "nauc_map_at_20_diff1": 0.2606541080848006, + "nauc_map_at_20_max": -0.07651163588184756, + "nauc_map_at_20_std": -0.3581193976151509, + "nauc_map_at_3_diff1": 0.2703384021085199, + "nauc_map_at_3_max": -0.10908342515491422, + "nauc_map_at_3_std": -0.36756460492255144, + "nauc_map_at_5_diff1": 0.2692093562917327, + "nauc_map_at_5_max": -0.08556676524284597, + "nauc_map_at_5_std": -0.36793462615462647, + "nauc_mrr_at_1000_diff1": 0.24593872758170682, + "nauc_mrr_at_1000_max": -0.07049956995290532, + "nauc_mrr_at_1000_std": -0.3496353832286841, + "nauc_mrr_at_100_diff1": 0.2515162766549995, + "nauc_mrr_at_100_max": -0.07129682661100908, + "nauc_mrr_at_100_std": -0.3530942074406207, + "nauc_mrr_at_10_diff1": 0.2670499662815176, + "nauc_mrr_at_10_max": -0.07951486952577923, + "nauc_mrr_at_10_std": -0.3633499210268088, + "nauc_mrr_at_1_diff1": 0.29582814872472407, + "nauc_mrr_at_1_max": -0.1849504051033388, + "nauc_mrr_at_1_std": -0.38018003257877575, + "nauc_mrr_at_20_diff1": 0.2606541080848006, + "nauc_mrr_at_20_max": -0.07651163588184756, + "nauc_mrr_at_20_std": -0.3581193976151509, + "nauc_mrr_at_3_diff1": 0.2703384021085199, + "nauc_mrr_at_3_max": -0.10908342515491422, + "nauc_mrr_at_3_std": -0.36756460492255144, + "nauc_mrr_at_5_diff1": 0.2692093562917327, + "nauc_mrr_at_5_max": -0.08556676524284597, + "nauc_mrr_at_5_std": -0.36793462615462647, + "nauc_ndcg_at_1000_diff1": 0.1267762655036532, + "nauc_ndcg_at_1000_max": -0.018837477649638137, + "nauc_ndcg_at_1000_std": -0.25102507605060853, + "nauc_ndcg_at_100_diff1": 0.19056693749468945, + "nauc_ndcg_at_100_max": -0.028099500756226435, + "nauc_ndcg_at_100_std": -0.3209465334260444, + "nauc_ndcg_at_10_diff1": 0.2618346649353551, + "nauc_ndcg_at_10_max": -0.04433561408924102, + "nauc_ndcg_at_10_std": -0.3587300396908446, + "nauc_ndcg_at_1_diff1": 0.29582814872472407, + "nauc_ndcg_at_1_max": -0.1849504051033388, + "nauc_ndcg_at_1_std": -0.38018003257877575, + "nauc_ndcg_at_20_diff1": 0.24082269355586824, + "nauc_ndcg_at_20_max": -0.0384385708434315, + "nauc_ndcg_at_20_std": -0.34378923894191293, + "nauc_ndcg_at_3_diff1": 0.2644038855338936, + "nauc_ndcg_at_3_max": -0.09411549418916441, + "nauc_ndcg_at_3_std": -0.3647579090483734, + "nauc_ndcg_at_5_diff1": 0.2626974487875725, + "nauc_ndcg_at_5_max": -0.054613475708951156, + "nauc_ndcg_at_5_std": -0.3660320065239745, + "nauc_precision_at_1000_diff1": 0.048078750546092244, + "nauc_precision_at_1000_max": 0.007699747172731412, + "nauc_precision_at_1000_std": -0.17190023361038836, + "nauc_precision_at_100_diff1": 0.10376975548917719, + "nauc_precision_at_100_max": 0.009691572960651852, + "nauc_precision_at_100_std": -0.27916393472552775, + "nauc_precision_at_10_diff1": 0.2544481433842745, + "nauc_precision_at_10_max": 0.023444710904956173, + "nauc_precision_at_10_std": -0.35072563146389724, + "nauc_precision_at_1_diff1": 0.29582814872472407, + "nauc_precision_at_1_max": -0.1849504051033388, + "nauc_precision_at_1_std": -0.38018003257877575, + "nauc_precision_at_20_diff1": 0.20269744968414538, + "nauc_precision_at_20_max": 0.023315579701759754, + "nauc_precision_at_20_std": -0.316947173767352, + "nauc_precision_at_3_diff1": 0.2503742216770504, + "nauc_precision_at_3_max": -0.05949886156369146, + "nauc_precision_at_3_std": -0.358159856712661, + "nauc_precision_at_5_diff1": 0.24847140457316463, + "nauc_precision_at_5_max": 0.016119508418380016, + "nauc_precision_at_5_std": -0.36241665162096415, + "nauc_recall_at_1000_diff1": 0.04807875054609259, + "nauc_recall_at_1000_max": 0.007699747172731706, + "nauc_recall_at_1000_std": -0.17190023361038806, + "nauc_recall_at_100_diff1": 0.10376975548917752, + "nauc_recall_at_100_max": 0.009691572960651861, + "nauc_recall_at_100_std": -0.27916393472552764, + "nauc_recall_at_10_diff1": 0.25444814338427424, + "nauc_recall_at_10_max": 0.023444710904956003, + "nauc_recall_at_10_std": -0.3507256314638974, + "nauc_recall_at_1_diff1": 0.29582814872472407, + "nauc_recall_at_1_max": -0.1849504051033388, + "nauc_recall_at_1_std": -0.38018003257877575, + "nauc_recall_at_20_diff1": 0.2026974496841453, + "nauc_recall_at_20_max": 0.02331557970175962, + "nauc_recall_at_20_std": -0.316947173767352, + "nauc_recall_at_3_diff1": 0.2503742216770507, + "nauc_recall_at_3_max": -0.0594988615636913, + "nauc_recall_at_3_std": -0.35815985671266093, + "nauc_recall_at_5_diff1": 0.24847140457316486, + "nauc_recall_at_5_max": 0.016119508418380144, + "nauc_recall_at_5_std": -0.36241665162096415, + "ndcg_at_1": 0.01126, + "ndcg_at_10": 0.01748, + "ndcg_at_100": 0.02424, + "ndcg_at_1000": 0.04648, + "ndcg_at_20": 0.01914, + "ndcg_at_3": 0.01468, + "ndcg_at_5": 0.01571, + "precision_at_1": 0.01126, + "precision_at_10": 0.00251, + "precision_at_100": 0.0006, + "precision_at_1000": 0.00025, + "precision_at_20": 0.00159, + "precision_at_3": 0.00563, + "precision_at_5": 0.00389, + "recall_at_1": 0.01126, + "recall_at_10": 0.02508, + "recall_at_100": 0.06039, + "recall_at_1000": 0.25384, + "recall_at_20": 0.03173, + "recall_at_3": 0.01689, + "recall_at_5": 0.01945 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/dragon-plus-instruct/no_revision_available/SpartQA.json b/results/dragon-plus-instruct/no_revision_available/SpartQA.json new file mode 100644 index 000000000..64d6ea4eb --- /dev/null +++ b/results/dragon-plus-instruct/no_revision_available/SpartQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 11.513362884521484, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.10818, + "map_at_1": 0.02068, + "map_at_10": 0.06901, + "map_at_100": 0.07952, + "map_at_1000": 0.0806, + "map_at_20": 0.0752, + "map_at_3": 0.04959, + "map_at_5": 0.05793, + "mrr_at_1": 0.028658875904284918, + "mrr_at_10": 0.09434010387683173, + "mrr_at_100": 0.10543551707865938, + "mrr_at_1000": 0.10647446152947969, + "mrr_at_20": 0.10095083341780603, + "mrr_at_3": 0.06956037840845863, + "mrr_at_5": 0.08116304952698931, + "nauc_map_at_1000_diff1": -0.11421051974819836, + "nauc_map_at_1000_max": 0.307039686918496, + "nauc_map_at_1000_std": 0.5315367854970233, + "nauc_map_at_100_diff1": -0.11322505588895271, + "nauc_map_at_100_max": 0.3082431648261639, + "nauc_map_at_100_std": 0.5314040205367461, + "nauc_map_at_10_diff1": -0.12162875975509331, + "nauc_map_at_10_max": 0.3085165862171762, + "nauc_map_at_10_std": 0.5042543954361752, + "nauc_map_at_1_diff1": -0.14085131199514353, + "nauc_map_at_1_max": 0.3489313982886576, + "nauc_map_at_1_std": 0.5185288736644467, + "nauc_map_at_20_diff1": -0.11893442990042652, + "nauc_map_at_20_max": 0.30691578664789726, + "nauc_map_at_20_std": 0.5197387508952567, + "nauc_map_at_3_diff1": -0.13949293370396282, + "nauc_map_at_3_max": 0.3078496766645952, + "nauc_map_at_3_std": 0.5026310472716021, + "nauc_map_at_5_diff1": -0.12789335154976184, + "nauc_map_at_5_max": 0.30902082156668237, + "nauc_map_at_5_std": 0.48850014322417984, + "nauc_mrr_at_1000_diff1": -0.10103811076500205, + "nauc_mrr_at_1000_max": 0.2535419375441269, + "nauc_mrr_at_1000_std": 0.48178752808820324, + "nauc_mrr_at_100_diff1": -0.09992219147734924, + "nauc_mrr_at_100_max": 0.2543072647505637, + "nauc_mrr_at_100_std": 0.4820208805407892, + "nauc_mrr_at_10_diff1": -0.11410235553733059, + "nauc_mrr_at_10_max": 0.24994800340833268, + "nauc_mrr_at_10_std": 0.4666912943973357, + "nauc_mrr_at_1_diff1": -0.14936758487256643, + "nauc_mrr_at_1_max": 0.27610607945289073, + "nauc_mrr_at_1_std": 0.4792697392484231, + "nauc_mrr_at_20_diff1": -0.1059200057725449, + "nauc_mrr_at_20_max": 0.2518928866022518, + "nauc_mrr_at_20_std": 0.47559460830820954, + "nauc_mrr_at_3_diff1": -0.13943029616508457, + "nauc_mrr_at_3_max": 0.2434980842405587, + "nauc_mrr_at_3_std": 0.4732210038309973, + "nauc_mrr_at_5_diff1": -0.12632050798972486, + "nauc_mrr_at_5_max": 0.24562557352396847, + "nauc_mrr_at_5_std": 0.456528542036715, + "nauc_ndcg_at_1000_diff1": -0.09018590158578318, + "nauc_ndcg_at_1000_max": 0.2701113313957752, + "nauc_ndcg_at_1000_std": 0.5609685624528382, + "nauc_ndcg_at_100_diff1": -0.07048147691537233, + "nauc_ndcg_at_100_max": 0.2922552316619319, + "nauc_ndcg_at_100_std": 0.5862964546073035, + "nauc_ndcg_at_10_diff1": -0.1075436520156729, + "nauc_ndcg_at_10_max": 0.28914822791688893, + "nauc_ndcg_at_10_std": 0.49492150322940154, + "nauc_ndcg_at_1_diff1": -0.14936758487256643, + "nauc_ndcg_at_1_max": 0.27610607945289073, + "nauc_ndcg_at_1_std": 0.4792697392484231, + "nauc_ndcg_at_20_diff1": -0.09737642760035964, + "nauc_ndcg_at_20_max": 0.2885995222961228, + "nauc_ndcg_at_20_std": 0.528216799257781, + "nauc_ndcg_at_3_diff1": -0.14019760822305502, + "nauc_ndcg_at_3_max": 0.28425275843091324, + "nauc_ndcg_at_3_std": 0.49227245158216815, + "nauc_ndcg_at_5_diff1": -0.12215257225177308, + "nauc_ndcg_at_5_max": 0.28683111180236726, + "nauc_ndcg_at_5_std": 0.4704258412564576, + "nauc_precision_at_1000_diff1": 0.023023777418203502, + "nauc_precision_at_1000_max": -0.04845476252244222, + "nauc_precision_at_1000_std": 0.19487730380618287, + "nauc_precision_at_100_diff1": 0.04476292482769822, + "nauc_precision_at_100_max": 0.15713509890396848, + "nauc_precision_at_100_std": 0.5345829927328175, + "nauc_precision_at_10_diff1": -0.0743959135112426, + "nauc_precision_at_10_max": 0.2414627559521359, + "nauc_precision_at_10_std": 0.4816784027912501, + "nauc_precision_at_1_diff1": -0.14936758487256643, + "nauc_precision_at_1_max": 0.27610607945289073, + "nauc_precision_at_1_std": 0.4792697392484231, + "nauc_precision_at_20_diff1": -0.037498405602946115, + "nauc_precision_at_20_max": 0.21752389580937895, + "nauc_precision_at_20_std": 0.5166211065110954, + "nauc_precision_at_3_diff1": -0.13642355635665718, + "nauc_precision_at_3_max": 0.23363202707803699, + "nauc_precision_at_3_std": 0.47268999242691373, + "nauc_precision_at_5_diff1": -0.09935416389654193, + "nauc_precision_at_5_max": 0.24017585467381938, + "nauc_precision_at_5_std": 0.43745582532287547, + "nauc_recall_at_1000_diff1": -0.07696649680379755, + "nauc_recall_at_1000_max": 0.13802998757889617, + "nauc_recall_at_1000_std": 0.44576658592937346, + "nauc_recall_at_100_diff1": -0.019122719732818164, + "nauc_recall_at_100_max": 0.2713582194109226, + "nauc_recall_at_100_std": 0.631251481687701, + "nauc_recall_at_10_diff1": -0.09039473069710131, + "nauc_recall_at_10_max": 0.284572056157999, + "nauc_recall_at_10_std": 0.4793487879472638, + "nauc_recall_at_1_diff1": -0.14085131199514353, + "nauc_recall_at_1_max": 0.3489313982886576, + "nauc_recall_at_1_std": 0.5185288736644467, + "nauc_recall_at_20_diff1": -0.07533175154134963, + "nauc_recall_at_20_max": 0.274987193389494, + "nauc_recall_at_20_std": 0.5155043519950205, + "nauc_recall_at_3_diff1": -0.14295381052356712, + "nauc_recall_at_3_max": 0.28575386503202665, + "nauc_recall_at_3_std": 0.49217722001280684, + "nauc_recall_at_5_diff1": -0.11353851491204525, + "nauc_recall_at_5_max": 0.2827313672532604, + "nauc_recall_at_5_std": 0.446096330829175, + "ndcg_at_1": 0.02866, + "ndcg_at_10": 0.10818, + "ndcg_at_100": 0.16249, + "ndcg_at_1000": 0.19705, + "ndcg_at_20": 0.13043, + "ndcg_at_3": 0.06398, + "ndcg_at_5": 0.08017, + "precision_at_1": 0.02866, + "precision_at_10": 0.03022, + "precision_at_100": 0.00707, + "precision_at_1000": 0.00116, + "precision_at_20": 0.02165, + "precision_at_3": 0.04137, + "precision_at_5": 0.03606, + "recall_at_1": 0.02068, + "recall_at_10": 0.20052, + "recall_at_100": 0.4284, + "recall_at_1000": 0.67659, + "recall_at_20": 0.27731, + "recall_at_3": 0.08625, + "recall_at_5": 0.1215 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/dragon-plus-instruct/no_revision_available/TempReasonL1.json b/results/dragon-plus-instruct/no_revision_available/TempReasonL1.json new file mode 100644 index 000000000..68c3f9330 --- /dev/null +++ b/results/dragon-plus-instruct/no_revision_available/TempReasonL1.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 7.4700026512146, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01545, + "map_at_1": 0.0025, + "map_at_10": 0.00983, + "map_at_100": 0.01351, + "map_at_1000": 0.01475, + "map_at_20": 0.01163, + "map_at_3": 0.00646, + "map_at_5": 0.00773, + "mrr_at_1": 0.0025, + "mrr_at_10": 0.00983035714285715, + "mrr_at_100": 0.013514771143450625, + "mrr_at_1000": 0.014749646032922462, + "mrr_at_20": 0.01163078364811146, + "mrr_at_3": 0.0064583333333333316, + "mrr_at_5": 0.00773333333333333, + "nauc_map_at_1000_diff1": 0.1981906181687216, + "nauc_map_at_1000_max": 0.09706257242268354, + "nauc_map_at_1000_std": 0.14547629385437405, + "nauc_map_at_100_diff1": 0.20230033481940604, + "nauc_map_at_100_max": 0.09382606447652266, + "nauc_map_at_100_std": 0.15068405216420644, + "nauc_map_at_10_diff1": 0.23426495300960226, + "nauc_map_at_10_max": 0.09379567100593937, + "nauc_map_at_10_std": 0.18288188276666198, + "nauc_map_at_1_diff1": 0.13276093372685802, + "nauc_map_at_1_max": 0.15559431177891062, + "nauc_map_at_1_std": 0.31258384759860464, + "nauc_map_at_20_diff1": 0.21747219191470188, + "nauc_map_at_20_max": 0.10176082074318869, + "nauc_map_at_20_std": 0.16122503941020214, + "nauc_map_at_3_diff1": 0.3045846785012595, + "nauc_map_at_3_max": 0.04665691510079013, + "nauc_map_at_3_std": 0.22229761894458044, + "nauc_map_at_5_diff1": 0.2588567640146924, + "nauc_map_at_5_max": 0.04182910934189463, + "nauc_map_at_5_std": 0.19178490141835453, + "nauc_mrr_at_1000_diff1": 0.1981905644708489, + "nauc_mrr_at_1000_max": 0.09706277828648532, + "nauc_mrr_at_1000_std": 0.14547645462777664, + "nauc_mrr_at_100_diff1": 0.20230033481940604, + "nauc_mrr_at_100_max": 0.09382606447652266, + "nauc_mrr_at_100_std": 0.15068405216420644, + "nauc_mrr_at_10_diff1": 0.23426495300960226, + "nauc_mrr_at_10_max": 0.09379567100593937, + "nauc_mrr_at_10_std": 0.18288188276666198, + "nauc_mrr_at_1_diff1": 0.13276093372685802, + "nauc_mrr_at_1_max": 0.15559431177891062, + "nauc_mrr_at_1_std": 0.31258384759860464, + "nauc_mrr_at_20_diff1": 0.21747219191470188, + "nauc_mrr_at_20_max": 0.10176082074318869, + "nauc_mrr_at_20_std": 0.16122503941020214, + "nauc_mrr_at_3_diff1": 0.3045846785012595, + "nauc_mrr_at_3_max": 0.04665691510079013, + "nauc_mrr_at_3_std": 0.22229761894458044, + "nauc_mrr_at_5_diff1": 0.2588567640146924, + "nauc_mrr_at_5_max": 0.04182910934189463, + "nauc_mrr_at_5_std": 0.19178490141835453, + "nauc_ndcg_at_1000_diff1": 0.13780586119743457, + "nauc_ndcg_at_1000_max": 0.14919727926499496, + "nauc_ndcg_at_1000_std": 0.08342472163202548, + "nauc_ndcg_at_100_diff1": 0.15241579480374165, + "nauc_ndcg_at_100_max": 0.09222541727216471, + "nauc_ndcg_at_100_std": 0.11421175690979904, + "nauc_ndcg_at_10_diff1": 0.213512536642379, + "nauc_ndcg_at_10_max": 0.1148308285564571, + "nauc_ndcg_at_10_std": 0.16411048113345675, + "nauc_ndcg_at_1_diff1": 0.13276093372685802, + "nauc_ndcg_at_1_max": 0.15559431177891062, + "nauc_ndcg_at_1_std": 0.31258384759860464, + "nauc_ndcg_at_20_diff1": 0.18519842026352104, + "nauc_ndcg_at_20_max": 0.12189070972107198, + "nauc_ndcg_at_20_std": 0.12791993864349438, + "nauc_ndcg_at_3_diff1": 0.3158463340985696, + "nauc_ndcg_at_3_max": 0.03617800077313549, + "nauc_ndcg_at_3_std": 0.20510843924937813, + "nauc_ndcg_at_5_diff1": 0.24938308116982827, + "nauc_ndcg_at_5_max": 0.03345242497168804, + "nauc_ndcg_at_5_std": 0.1666026059089263, + "nauc_precision_at_1000_diff1": 0.11177413736920283, + "nauc_precision_at_1000_max": 0.20346971010217368, + "nauc_precision_at_1000_std": 0.05173943255132265, + "nauc_precision_at_100_diff1": 0.12446288158672122, + "nauc_precision_at_100_max": 0.08658807778422976, + "nauc_precision_at_100_std": 0.09880138853319072, + "nauc_precision_at_10_diff1": 0.1892326463624097, + "nauc_precision_at_10_max": 0.14031950708873303, + "nauc_precision_at_10_std": 0.14756981506035072, + "nauc_precision_at_1_diff1": 0.13276093372685802, + "nauc_precision_at_1_max": 0.15559431177891062, + "nauc_precision_at_1_std": 0.31258384759860464, + "nauc_precision_at_20_diff1": 0.1572210794105077, + "nauc_precision_at_20_max": 0.13780211359438005, + "nauc_precision_at_20_std": 0.10260682529114099, + "nauc_precision_at_3_diff1": 0.3317106826631914, + "nauc_precision_at_3_max": 0.020380784457598368, + "nauc_precision_at_3_std": 0.1773982466611544, + "nauc_precision_at_5_diff1": 0.2324099224099593, + "nauc_precision_at_5_max": 0.023732775635771648, + "nauc_precision_at_5_std": 0.1321934348019453, + "nauc_recall_at_1000_diff1": 0.11177413736920343, + "nauc_recall_at_1000_max": 0.20346971010217482, + "nauc_recall_at_1000_std": 0.051739432551323045, + "nauc_recall_at_100_diff1": 0.12446288158672131, + "nauc_recall_at_100_max": 0.08658807778422958, + "nauc_recall_at_100_std": 0.09880138853319076, + "nauc_recall_at_10_diff1": 0.18923264636240955, + "nauc_recall_at_10_max": 0.14031950708873314, + "nauc_recall_at_10_std": 0.14756981506035066, + "nauc_recall_at_1_diff1": 0.13276093372685802, + "nauc_recall_at_1_max": 0.15559431177891062, + "nauc_recall_at_1_std": 0.31258384759860464, + "nauc_recall_at_20_diff1": 0.1572210794105079, + "nauc_recall_at_20_max": 0.1378021135943802, + "nauc_recall_at_20_std": 0.10260682529114089, + "nauc_recall_at_3_diff1": 0.3317106826631914, + "nauc_recall_at_3_max": 0.02038078445759842, + "nauc_recall_at_3_std": 0.17739824666115458, + "nauc_recall_at_5_diff1": 0.23240992240995922, + "nauc_recall_at_5_max": 0.023732775635771527, + "nauc_recall_at_5_std": 0.13219343480194512, + "ndcg_at_1": 0.0025, + "ndcg_at_10": 0.01545, + "ndcg_at_100": 0.03768, + "ndcg_at_1000": 0.08455, + "ndcg_at_20": 0.0221, + "ndcg_at_3": 0.00793, + "ndcg_at_5": 0.01032, + "precision_at_1": 0.0025, + "precision_at_10": 0.00342, + "precision_at_100": 0.00149, + "precision_at_1000": 0.00055, + "precision_at_20": 0.00304, + "precision_at_3": 0.00408, + "precision_at_5": 0.00365, + "recall_at_1": 0.0025, + "recall_at_10": 0.03425, + "recall_at_100": 0.14875, + "recall_at_1000": 0.54925, + "recall_at_20": 0.06075, + "recall_at_3": 0.01225, + "recall_at_5": 0.01825 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/dragon-plus-instruct/no_revision_available/TempReasonL2Fact.json b/results/dragon-plus-instruct/no_revision_available/TempReasonL2Fact.json new file mode 100644 index 000000000..045e134b8 --- /dev/null +++ b/results/dragon-plus-instruct/no_revision_available/TempReasonL2Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 24.457796335220337, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.16115, + "map_at_1": 0.06207, + "map_at_10": 0.1217, + "map_at_100": 0.13462, + "map_at_1000": 0.13565, + "map_at_20": 0.1292, + "map_at_3": 0.09663, + "map_at_5": 0.11005, + "mrr_at_1": 0.06207152121549009, + "mrr_at_10": 0.12170098908564729, + "mrr_at_100": 0.13462400926099052, + "mrr_at_1000": 0.13565107351543765, + "mrr_at_20": 0.12920024955196308, + "mrr_at_3": 0.0966277561608299, + "mrr_at_5": 0.11005188067444875, + "nauc_map_at_1000_diff1": -0.02481686094585857, + "nauc_map_at_1000_max": 0.02250786427083756, + "nauc_map_at_1000_std": 0.1148885265535853, + "nauc_map_at_100_diff1": -0.02521933077923412, + "nauc_map_at_100_max": 0.022470742420503873, + "nauc_map_at_100_std": 0.11541206887737633, + "nauc_map_at_10_diff1": -0.01768309116832568, + "nauc_map_at_10_max": 0.0239485739386088, + "nauc_map_at_10_std": 0.10100221050817622, + "nauc_map_at_1_diff1": 0.010021440842550564, + "nauc_map_at_1_max": 0.007440464988833348, + "nauc_map_at_1_std": 0.027192384102019164, + "nauc_map_at_20_diff1": -0.022825383552307916, + "nauc_map_at_20_max": 0.02275294413233487, + "nauc_map_at_20_std": 0.11274245403716246, + "nauc_map_at_3_diff1": 0.0018312544134827763, + "nauc_map_at_3_max": 0.024396851618634523, + "nauc_map_at_3_std": 0.06876504915926326, + "nauc_map_at_5_diff1": -0.008513603859823247, + "nauc_map_at_5_max": 0.02814590355391354, + "nauc_map_at_5_std": 0.08238311150037582, + "nauc_mrr_at_1000_diff1": -0.02481689181814856, + "nauc_mrr_at_1000_max": 0.022507791540650572, + "nauc_mrr_at_1000_std": 0.1148884786025841, + "nauc_mrr_at_100_diff1": -0.02521933077923412, + "nauc_mrr_at_100_max": 0.022470742420503873, + "nauc_mrr_at_100_std": 0.11541206887737633, + "nauc_mrr_at_10_diff1": -0.01768309116832568, + "nauc_mrr_at_10_max": 0.0239485739386088, + "nauc_mrr_at_10_std": 0.10100221050817622, + "nauc_mrr_at_1_diff1": 0.010021440842550564, + "nauc_mrr_at_1_max": 0.007440464988833348, + "nauc_mrr_at_1_std": 0.027192384102019164, + "nauc_mrr_at_20_diff1": -0.022825383552307916, + "nauc_mrr_at_20_max": 0.02275294413233487, + "nauc_mrr_at_20_std": 0.11274245403716246, + "nauc_mrr_at_3_diff1": 0.0018312544134827763, + "nauc_mrr_at_3_max": 0.024396851618634523, + "nauc_mrr_at_3_std": 0.06876504915926326, + "nauc_mrr_at_5_diff1": -0.008513603859823247, + "nauc_mrr_at_5_max": 0.02814590355391354, + "nauc_mrr_at_5_std": 0.08238311150037582, + "nauc_ndcg_at_1000_diff1": -0.05300208087623433, + "nauc_ndcg_at_1000_max": 0.020032868277757954, + "nauc_ndcg_at_1000_std": 0.16983612104555101, + "nauc_ndcg_at_100_diff1": -0.062197352986233, + "nauc_ndcg_at_100_max": 0.019216068690103137, + "nauc_ndcg_at_100_std": 0.1824903842923459, + "nauc_ndcg_at_10_diff1": -0.03540469336978975, + "nauc_ndcg_at_10_max": 0.02470730916559289, + "nauc_ndcg_at_10_std": 0.13578092400300362, + "nauc_ndcg_at_1_diff1": 0.010021440842550564, + "nauc_ndcg_at_1_max": 0.007440464988833348, + "nauc_ndcg_at_1_std": 0.027192384102019164, + "nauc_ndcg_at_20_diff1": -0.049430995826418835, + "nauc_ndcg_at_20_max": 0.021157809519614552, + "nauc_ndcg_at_20_std": 0.16825694066577915, + "nauc_ndcg_at_3_diff1": -0.0019910562946793327, + "nauc_ndcg_at_3_max": 0.028096316224526425, + "nauc_ndcg_at_3_std": 0.07868110428368516, + "nauc_ndcg_at_5_diff1": -0.017622152420914198, + "nauc_ndcg_at_5_max": 0.03383865352416197, + "nauc_ndcg_at_5_std": 0.09865565323211953, + "nauc_precision_at_1000_diff1": -0.16299284024938143, + "nauc_precision_at_1000_max": -0.0006720667091204734, + "nauc_precision_at_1000_std": 0.39759428466825303, + "nauc_precision_at_100_diff1": -0.1536054004941214, + "nauc_precision_at_100_max": 0.007118284104353023, + "nauc_precision_at_100_std": 0.34230300868467667, + "nauc_precision_at_10_diff1": -0.06823523382658578, + "nauc_precision_at_10_max": 0.024283307899462245, + "nauc_precision_at_10_std": 0.2000135345413119, + "nauc_precision_at_1_diff1": 0.010021440842550564, + "nauc_precision_at_1_max": 0.007440464988833348, + "nauc_precision_at_1_std": 0.027192384102019164, + "nauc_precision_at_20_diff1": -0.0997331109155896, + "nauc_precision_at_20_max": 0.015563979654454484, + "nauc_precision_at_20_std": 0.2740391863092514, + "nauc_precision_at_3_diff1": -0.01040163156575795, + "nauc_precision_at_3_max": 0.03580096748102645, + "nauc_precision_at_3_std": 0.09951972782861034, + "nauc_precision_at_5_diff1": -0.03523389705243311, + "nauc_precision_at_5_max": 0.044479574829445194, + "nauc_precision_at_5_std": 0.12901427523891887, + "nauc_recall_at_1000_diff1": -0.16299284024938143, + "nauc_recall_at_1000_max": -0.0006720667091210506, + "nauc_recall_at_1000_std": 0.39759428466825447, + "nauc_recall_at_100_diff1": -0.15360540049412172, + "nauc_recall_at_100_max": 0.007118284104352888, + "nauc_recall_at_100_std": 0.3423030086846761, + "nauc_recall_at_10_diff1": -0.06823523382658582, + "nauc_recall_at_10_max": 0.024283307899462266, + "nauc_recall_at_10_std": 0.2000135345413117, + "nauc_recall_at_1_diff1": 0.010021440842550564, + "nauc_recall_at_1_max": 0.007440464988833348, + "nauc_recall_at_1_std": 0.027192384102019164, + "nauc_recall_at_20_diff1": -0.09973311091559008, + "nauc_recall_at_20_max": 0.015563979654454487, + "nauc_recall_at_20_std": 0.2740391863092512, + "nauc_recall_at_3_diff1": -0.01040163156575791, + "nauc_recall_at_3_max": 0.0358009674810267, + "nauc_recall_at_3_std": 0.09951972782861031, + "nauc_recall_at_5_diff1": -0.03523389705243354, + "nauc_recall_at_5_max": 0.04447957482944481, + "nauc_recall_at_5_std": 0.12901427523891829, + "ndcg_at_1": 0.06207, + "ndcg_at_10": 0.16115, + "ndcg_at_100": 0.22866, + "ndcg_at_1000": 0.25964, + "ndcg_at_20": 0.18834, + "ndcg_at_3": 0.10837, + "ndcg_at_5": 0.13272, + "precision_at_1": 0.06207, + "precision_at_10": 0.02903, + "precision_at_100": 0.00617, + "precision_at_1000": 0.00087, + "precision_at_20": 0.01988, + "precision_at_3": 0.0475, + "precision_at_5": 0.04039, + "recall_at_1": 0.06207, + "recall_at_10": 0.29035, + "recall_at_100": 0.61719, + "recall_at_1000": 0.86882, + "recall_at_20": 0.39763, + "recall_at_3": 0.14249, + "recall_at_5": 0.20196 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/dragon-plus-instruct/no_revision_available/TempReasonL2Pure.json b/results/dragon-plus-instruct/no_revision_available/TempReasonL2Pure.json new file mode 100644 index 000000000..468575bd2 --- /dev/null +++ b/results/dragon-plus-instruct/no_revision_available/TempReasonL2Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 11.231105089187622, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.00573, + "map_at_1": 0.00148, + "map_at_10": 0.0038, + "map_at_100": 0.00533, + "map_at_1000": 0.00614, + "map_at_20": 0.00429, + "map_at_3": 0.00232, + "map_at_5": 0.00309, + "mrr_at_1": 0.0014823049842505095, + "mrr_at_10": 0.0038005388060974505, + "mrr_at_100": 0.00533191235216907, + "mrr_at_1000": 0.006140847330946008, + "mrr_at_20": 0.00429477343748172, + "mrr_at_3": 0.002316101537891421, + "mrr_at_5": 0.003085047248471373, + "nauc_map_at_1000_diff1": -0.04595006830054852, + "nauc_map_at_1000_max": -0.1055807424364868, + "nauc_map_at_1000_std": 0.2600119839279514, + "nauc_map_at_100_diff1": -0.05322329599929052, + "nauc_map_at_100_max": -0.10815881434615283, + "nauc_map_at_100_std": 0.26848710022258426, + "nauc_map_at_10_diff1": -0.06424230273468179, + "nauc_map_at_10_max": -0.08448575841655075, + "nauc_map_at_10_std": 0.30720639824737467, + "nauc_map_at_1_diff1": -0.264924451501461, + "nauc_map_at_1_max": -0.12242668876542913, + "nauc_map_at_1_std": 0.5919167426008881, + "nauc_map_at_20_diff1": -0.07253792213187725, + "nauc_map_at_20_max": -0.10246161207445231, + "nauc_map_at_20_std": 0.2868472311634222, + "nauc_map_at_3_diff1": -0.10970830603831723, + "nauc_map_at_3_max": -0.09737116920859264, + "nauc_map_at_3_std": 0.4142546155475142, + "nauc_map_at_5_diff1": -0.07293128832008787, + "nauc_map_at_5_max": -0.07001000916681241, + "nauc_map_at_5_std": 0.37376069462696193, + "nauc_mrr_at_1000_diff1": -0.04595060746298304, + "nauc_mrr_at_1000_max": -0.1055813188698278, + "nauc_mrr_at_1000_std": 0.2600110716040033, + "nauc_mrr_at_100_diff1": -0.05322329599929052, + "nauc_mrr_at_100_max": -0.10815881434615283, + "nauc_mrr_at_100_std": 0.26848710022258426, + "nauc_mrr_at_10_diff1": -0.06424230273468179, + "nauc_mrr_at_10_max": -0.08448575841655075, + "nauc_mrr_at_10_std": 0.30720639824737467, + "nauc_mrr_at_1_diff1": -0.264924451501461, + "nauc_mrr_at_1_max": -0.12242668876542913, + "nauc_mrr_at_1_std": 0.5919167426008881, + "nauc_mrr_at_20_diff1": -0.07253792213187725, + "nauc_mrr_at_20_max": -0.10246161207445231, + "nauc_mrr_at_20_std": 0.2868472311634222, + "nauc_mrr_at_3_diff1": -0.10970830603831723, + "nauc_mrr_at_3_max": -0.09737116920859264, + "nauc_mrr_at_3_std": 0.4142546155475142, + "nauc_mrr_at_5_diff1": -0.07293128832008787, + "nauc_mrr_at_5_max": -0.07001000916681241, + "nauc_mrr_at_5_std": 0.37376069462696193, + "nauc_ndcg_at_1000_diff1": -0.003139932104079352, + "nauc_ndcg_at_1000_max": -0.10828120393738973, + "nauc_ndcg_at_1000_std": 0.19216374579982626, + "nauc_ndcg_at_100_diff1": -0.005960349786605753, + "nauc_ndcg_at_100_max": -0.11762613745150846, + "nauc_ndcg_at_100_std": 0.19276737005755967, + "nauc_ndcg_at_10_diff1": -0.02745412065651988, + "nauc_ndcg_at_10_max": -0.08829170317134093, + "nauc_ndcg_at_10_std": 0.23519229770355654, + "nauc_ndcg_at_1_diff1": -0.264924451501461, + "nauc_ndcg_at_1_max": -0.12242668876542913, + "nauc_ndcg_at_1_std": 0.5919167426008881, + "nauc_ndcg_at_20_diff1": -0.05222186685153471, + "nauc_ndcg_at_20_max": -0.12338142015614956, + "nauc_ndcg_at_20_std": 0.20995064068242056, + "nauc_ndcg_at_3_diff1": -0.08033862729994233, + "nauc_ndcg_at_3_max": -0.09408882439245364, + "nauc_ndcg_at_3_std": 0.38487194010233183, + "nauc_ndcg_at_5_diff1": -0.04051833379393147, + "nauc_ndcg_at_5_max": -0.060754499936120275, + "nauc_ndcg_at_5_std": 0.3373652881799536, + "nauc_precision_at_1000_diff1": 0.0005300489075512341, + "nauc_precision_at_1000_max": -0.10822834080678584, + "nauc_precision_at_1000_std": 0.18502416008137118, + "nauc_precision_at_100_diff1": 0.015132433244028127, + "nauc_precision_at_100_max": -0.11713310807663765, + "nauc_precision_at_100_std": 0.1663299486211631, + "nauc_precision_at_10_diff1": 0.01239147686222082, + "nauc_precision_at_10_max": -0.09543917482744495, + "nauc_precision_at_10_std": 0.15485794349183232, + "nauc_precision_at_1_diff1": -0.264924451501461, + "nauc_precision_at_1_max": -0.12242668876542913, + "nauc_precision_at_1_std": 0.5919167426008881, + "nauc_precision_at_20_diff1": -0.03955003839309295, + "nauc_precision_at_20_max": -0.14549980738962873, + "nauc_precision_at_20_std": 0.14633819513631396, + "nauc_precision_at_3_diff1": -0.021228606775885537, + "nauc_precision_at_3_max": -0.0878239476192244, + "nauc_precision_at_3_std": 0.3267263396414817, + "nauc_precision_at_5_diff1": 0.004463690930916906, + "nauc_precision_at_5_max": -0.048318391476061456, + "nauc_precision_at_5_std": 0.28610861212458677, + "nauc_recall_at_1000_diff1": 0.0005300489075515079, + "nauc_recall_at_1000_max": -0.10822834080678587, + "nauc_recall_at_1000_std": 0.1850241600813713, + "nauc_recall_at_100_diff1": 0.015132433244027927, + "nauc_recall_at_100_max": -0.11713310807663792, + "nauc_recall_at_100_std": 0.16632994862116277, + "nauc_recall_at_10_diff1": 0.01239147686222055, + "nauc_recall_at_10_max": -0.09543917482744507, + "nauc_recall_at_10_std": 0.1548579434918321, + "nauc_recall_at_1_diff1": -0.264924451501461, + "nauc_recall_at_1_max": -0.12242668876542913, + "nauc_recall_at_1_std": 0.5919167426008881, + "nauc_recall_at_20_diff1": -0.039550038393093095, + "nauc_recall_at_20_max": -0.14549980738962884, + "nauc_recall_at_20_std": 0.14633819513631377, + "nauc_recall_at_3_diff1": -0.021228606775885613, + "nauc_recall_at_3_max": -0.08782394761922446, + "nauc_recall_at_3_std": 0.32672633964148146, + "nauc_recall_at_5_diff1": 0.004463690930917302, + "nauc_recall_at_5_max": -0.04831839147606127, + "nauc_recall_at_5_std": 0.2861086121245869, + "ndcg_at_1": 0.00148, + "ndcg_at_10": 0.00573, + "ndcg_at_100": 0.01632, + "ndcg_at_1000": 0.04583, + "ndcg_at_20": 0.00758, + "ndcg_at_3": 0.00258, + "ndcg_at_5": 0.00396, + "precision_at_1": 0.00148, + "precision_at_10": 0.00122, + "precision_at_100": 0.00069, + "precision_at_1000": 0.00032, + "precision_at_20": 0.00098, + "precision_at_3": 0.00111, + "precision_at_5": 0.00133, + "recall_at_1": 0.00148, + "recall_at_10": 0.01223, + "recall_at_100": 0.0693, + "recall_at_1000": 0.31944, + "recall_at_20": 0.01964, + "recall_at_3": 0.00334, + "recall_at_5": 0.00667 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/dragon-plus-instruct/no_revision_available/TempReasonL3Fact.json b/results/dragon-plus-instruct/no_revision_available/TempReasonL3Fact.json new file mode 100644 index 000000000..1e2853ef9 --- /dev/null +++ b/results/dragon-plus-instruct/no_revision_available/TempReasonL3Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 21.08042597770691, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.14813, + "map_at_1": 0.04067, + "map_at_10": 0.10629, + "map_at_100": 0.11913, + "map_at_1000": 0.1202, + "map_at_20": 0.11379, + "map_at_3": 0.08058, + "map_at_5": 0.09441, + "mrr_at_1": 0.04066877541798464, + "mrr_at_10": 0.10629370817463878, + "mrr_at_100": 0.1191347488511155, + "mrr_at_1000": 0.12020295500571988, + "mrr_at_20": 0.11378513913305083, + "mrr_at_3": 0.08058442536526574, + "mrr_at_5": 0.09441180900738025, + "nauc_map_at_1000_diff1": -0.10219702648265594, + "nauc_map_at_1000_max": 0.07123619511539847, + "nauc_map_at_1000_std": 0.24539455580637257, + "nauc_map_at_100_diff1": -0.10246312282318372, + "nauc_map_at_100_max": 0.07108662265068164, + "nauc_map_at_100_std": 0.24590052930259823, + "nauc_map_at_10_diff1": -0.1006214828802061, + "nauc_map_at_10_max": 0.076036579565178, + "nauc_map_at_10_std": 0.23269645515370577, + "nauc_map_at_1_diff1": -0.15150109960446714, + "nauc_map_at_1_max": 0.05740332502193559, + "nauc_map_at_1_std": 0.17306414286739907, + "nauc_map_at_20_diff1": -0.10132787116262365, + "nauc_map_at_20_max": 0.07231807037899575, + "nauc_map_at_20_std": 0.24181126875226253, + "nauc_map_at_3_diff1": -0.09014019467151207, + "nauc_map_at_3_max": 0.0866720501563522, + "nauc_map_at_3_std": 0.19572983001248745, + "nauc_map_at_5_diff1": -0.09782708817034855, + "nauc_map_at_5_max": 0.07714870503191794, + "nauc_map_at_5_std": 0.21615490001155224, + "nauc_mrr_at_1000_diff1": -0.10219701831621267, + "nauc_mrr_at_1000_max": 0.07123619251657386, + "nauc_mrr_at_1000_std": 0.24539455434681381, + "nauc_mrr_at_100_diff1": -0.10246312282318372, + "nauc_mrr_at_100_max": 0.07108662265068164, + "nauc_mrr_at_100_std": 0.24590052930259823, + "nauc_mrr_at_10_diff1": -0.1006214828802061, + "nauc_mrr_at_10_max": 0.076036579565178, + "nauc_mrr_at_10_std": 0.23269645515370577, + "nauc_mrr_at_1_diff1": -0.15150109960446714, + "nauc_mrr_at_1_max": 0.05740332502193559, + "nauc_mrr_at_1_std": 0.17306414286739907, + "nauc_mrr_at_20_diff1": -0.10132787116262365, + "nauc_mrr_at_20_max": 0.07231807037899575, + "nauc_mrr_at_20_std": 0.24181126875226253, + "nauc_mrr_at_3_diff1": -0.09014019467151207, + "nauc_mrr_at_3_max": 0.0866720501563522, + "nauc_mrr_at_3_std": 0.19572983001248745, + "nauc_mrr_at_5_diff1": -0.09782708817034855, + "nauc_mrr_at_5_max": 0.07714870503191794, + "nauc_mrr_at_5_std": 0.21615490001155224, + "nauc_ndcg_at_1000_diff1": -0.09849665695940367, + "nauc_ndcg_at_1000_max": 0.06484582545644209, + "nauc_ndcg_at_1000_std": 0.2940561093817588, + "nauc_ndcg_at_100_diff1": -0.10616780694373618, + "nauc_ndcg_at_100_max": 0.05793501171972292, + "nauc_ndcg_at_100_std": 0.30186812519148615, + "nauc_ndcg_at_10_diff1": -0.1003900172998107, + "nauc_ndcg_at_10_max": 0.07404977339741996, + "nauc_ndcg_at_10_std": 0.26262110511146924, + "nauc_ndcg_at_1_diff1": -0.15150109960446714, + "nauc_ndcg_at_1_max": 0.05740332502193559, + "nauc_ndcg_at_1_std": 0.17306414286739907, + "nauc_ndcg_at_20_diff1": -0.10204036357141429, + "nauc_ndcg_at_20_max": 0.0649010297831887, + "nauc_ndcg_at_20_std": 0.28539709301999455, + "nauc_ndcg_at_3_diff1": -0.08196734606015565, + "nauc_ndcg_at_3_max": 0.09241868284893018, + "nauc_ndcg_at_3_std": 0.20328583310396117, + "nauc_ndcg_at_5_diff1": -0.09436493932451041, + "nauc_ndcg_at_5_max": 0.07769407317132658, + "nauc_ndcg_at_5_std": 0.23255575887143007, + "nauc_precision_at_1000_diff1": -0.04824221232642565, + "nauc_precision_at_1000_max": 0.06585874047955668, + "nauc_precision_at_1000_std": 0.47392665131354467, + "nauc_precision_at_100_diff1": -0.11737821829562183, + "nauc_precision_at_100_max": 0.02450288764763787, + "nauc_precision_at_100_std": 0.41436796475171467, + "nauc_precision_at_10_diff1": -0.10240338580046358, + "nauc_precision_at_10_max": 0.06907481601250876, + "nauc_precision_at_10_std": 0.31155688035243245, + "nauc_precision_at_1_diff1": -0.15150109960446714, + "nauc_precision_at_1_max": 0.05740332502193559, + "nauc_precision_at_1_std": 0.17306414286739907, + "nauc_precision_at_20_diff1": -0.10555054398510408, + "nauc_precision_at_20_max": 0.05013503562760596, + "nauc_precision_at_20_std": 0.3577039690046134, + "nauc_precision_at_3_diff1": -0.06737472758492168, + "nauc_precision_at_3_max": 0.10313802105407012, + "nauc_precision_at_3_std": 0.21790316540183666, + "nauc_precision_at_5_diff1": -0.09008290221265694, + "nauc_precision_at_5_max": 0.07773102449303378, + "nauc_precision_at_5_std": 0.2607324674569665, + "nauc_recall_at_1000_diff1": -0.04824221232642786, + "nauc_recall_at_1000_max": 0.06585874047955494, + "nauc_recall_at_1000_std": 0.4739266513135459, + "nauc_recall_at_100_diff1": -0.11737821829562226, + "nauc_recall_at_100_max": 0.024502887647637518, + "nauc_recall_at_100_std": 0.41436796475171445, + "nauc_recall_at_10_diff1": -0.10240338580046372, + "nauc_recall_at_10_max": 0.06907481601250856, + "nauc_recall_at_10_std": 0.31155688035243245, + "nauc_recall_at_1_diff1": -0.15150109960446714, + "nauc_recall_at_1_max": 0.05740332502193559, + "nauc_recall_at_1_std": 0.17306414286739907, + "nauc_recall_at_20_diff1": -0.10555054398510462, + "nauc_recall_at_20_max": 0.050135035627605753, + "nauc_recall_at_20_std": 0.35770396900461343, + "nauc_recall_at_3_diff1": -0.06737472758492168, + "nauc_recall_at_3_max": 0.10313802105407019, + "nauc_recall_at_3_std": 0.21790316540183668, + "nauc_recall_at_5_diff1": -0.09008290221265713, + "nauc_recall_at_5_max": 0.0777310244930336, + "nauc_recall_at_5_std": 0.26073246745696627, + "ndcg_at_1": 0.04067, + "ndcg_at_10": 0.14813, + "ndcg_at_100": 0.21438, + "ndcg_at_1000": 0.24571, + "ndcg_at_20": 0.17524, + "ndcg_at_3": 0.09425, + "ndcg_at_5": 0.11913, + "precision_at_1": 0.04067, + "precision_at_10": 0.02845, + "precision_at_100": 0.00603, + "precision_at_1000": 0.00086, + "precision_at_20": 0.01957, + "precision_at_3": 0.04466, + "precision_at_5": 0.03886, + "recall_at_1": 0.04067, + "recall_at_10": 0.28446, + "recall_at_100": 0.60325, + "recall_at_1000": 0.85653, + "recall_at_20": 0.39132, + "recall_at_3": 0.13398, + "recall_at_5": 0.19431 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/dragon-plus-instruct/no_revision_available/TempReasonL3Pure.json b/results/dragon-plus-instruct/no_revision_available/TempReasonL3Pure.json new file mode 100644 index 000000000..d6ed954c4 --- /dev/null +++ b/results/dragon-plus-instruct/no_revision_available/TempReasonL3Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 9.763681411743164, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07456, + "map_at_1": 0.00316, + "map_at_10": 0.04809, + "map_at_100": 0.05389, + "map_at_1000": 0.05493, + "map_at_20": 0.05101, + "map_at_3": 0.03257, + "map_at_5": 0.04167, + "mrr_at_1": 0.0031631269769543608, + "mrr_at_10": 0.04808885446029593, + "mrr_at_100": 0.05388764241777582, + "mrr_at_1000": 0.05492809427468016, + "mrr_at_20": 0.05101037926973959, + "mrr_at_3": 0.03257267660792287, + "mrr_at_5": 0.04166666666666669, + "nauc_map_at_1000_diff1": -0.3174429803753282, + "nauc_map_at_1000_max": 0.039543228950756334, + "nauc_map_at_1000_std": 0.6595934246252697, + "nauc_map_at_100_diff1": -0.318714513954041, + "nauc_map_at_100_max": 0.03990423135357456, + "nauc_map_at_100_std": 0.6609017014003948, + "nauc_map_at_10_diff1": -0.33071272891301734, + "nauc_map_at_10_max": 0.05098776479582128, + "nauc_map_at_10_std": 0.6744526416778118, + "nauc_map_at_1_diff1": -0.49992380003143133, + "nauc_map_at_1_max": -0.06782779858276015, + "nauc_map_at_1_std": 0.6885305059030336, + "nauc_map_at_20_diff1": -0.3268570285639456, + "nauc_map_at_20_max": 0.04403127377817707, + "nauc_map_at_20_std": 0.670286598944299, + "nauc_map_at_3_diff1": -0.30840678451804815, + "nauc_map_at_3_max": 0.06026176934526377, + "nauc_map_at_3_std": 0.6144028214884028, + "nauc_map_at_5_diff1": -0.3153710700180537, + "nauc_map_at_5_max": 0.06264698438534119, + "nauc_map_at_5_std": 0.6465255444059163, + "nauc_mrr_at_1000_diff1": -0.3174430242571683, + "nauc_mrr_at_1000_max": 0.039543198247872266, + "nauc_mrr_at_1000_std": 0.6595934069096246, + "nauc_mrr_at_100_diff1": -0.318714513954041, + "nauc_mrr_at_100_max": 0.03990423135357456, + "nauc_mrr_at_100_std": 0.6609017014003948, + "nauc_mrr_at_10_diff1": -0.33071272891301734, + "nauc_mrr_at_10_max": 0.05098776479582128, + "nauc_mrr_at_10_std": 0.6744526416778118, + "nauc_mrr_at_1_diff1": -0.49992380003143133, + "nauc_mrr_at_1_max": -0.06782779858276015, + "nauc_mrr_at_1_std": 0.6885305059030336, + "nauc_mrr_at_20_diff1": -0.3268570285639456, + "nauc_mrr_at_20_max": 0.04403127377817707, + "nauc_mrr_at_20_std": 0.670286598944299, + "nauc_mrr_at_3_diff1": -0.30840678451804815, + "nauc_mrr_at_3_max": 0.06026176934526377, + "nauc_mrr_at_3_std": 0.6144028214884028, + "nauc_mrr_at_5_diff1": -0.3153710700180537, + "nauc_mrr_at_5_max": 0.06264698438534119, + "nauc_mrr_at_5_std": 0.6465255444059163, + "nauc_ndcg_at_1000_diff1": -0.26816296532449707, + "nauc_ndcg_at_1000_max": 0.008573279888880594, + "nauc_ndcg_at_1000_std": 0.6234588403226539, + "nauc_ndcg_at_100_diff1": -0.28738923306854464, + "nauc_ndcg_at_100_max": 0.014495971254146015, + "nauc_ndcg_at_100_std": 0.6425088870367897, + "nauc_ndcg_at_10_diff1": -0.33849591205055374, + "nauc_ndcg_at_10_max": 0.04435860103919783, + "nauc_ndcg_at_10_std": 0.700248858989874, + "nauc_ndcg_at_1_diff1": -0.49992380003143133, + "nauc_ndcg_at_1_max": -0.06782779858276015, + "nauc_ndcg_at_1_std": 0.6885305059030336, + "nauc_ndcg_at_20_diff1": -0.3269569312350864, + "nauc_ndcg_at_20_max": 0.029467675669010575, + "nauc_ndcg_at_20_std": 0.6866460928236544, + "nauc_ndcg_at_3_diff1": -0.30340142177830093, + "nauc_ndcg_at_3_max": 0.059811452225387, + "nauc_ndcg_at_3_std": 0.6148402625278913, + "nauc_ndcg_at_5_diff1": -0.31361218007144376, + "nauc_ndcg_at_5_max": 0.06362660701040129, + "nauc_ndcg_at_5_std": 0.6563585089972982, + "nauc_precision_at_1000_diff1": -0.16135728347449474, + "nauc_precision_at_1000_max": -0.04286853984099866, + "nauc_precision_at_1000_std": 0.5296932660800094, + "nauc_precision_at_100_diff1": -0.23626338629367336, + "nauc_precision_at_100_max": -0.017353460844523532, + "nauc_precision_at_100_std": 0.6016048101828143, + "nauc_precision_at_10_diff1": -0.3497532793142504, + "nauc_precision_at_10_max": 0.03522977066591603, + "nauc_precision_at_10_std": 0.7330693070389963, + "nauc_precision_at_1_diff1": -0.49992380003143133, + "nauc_precision_at_1_max": -0.06782779858276015, + "nauc_precision_at_1_std": 0.6885305059030336, + "nauc_precision_at_20_diff1": -0.3256499732294911, + "nauc_precision_at_20_max": 0.010753600766808476, + "nauc_precision_at_20_std": 0.7020650557606127, + "nauc_precision_at_3_diff1": -0.29677750968182726, + "nauc_precision_at_3_max": 0.05857829978210639, + "nauc_precision_at_3_std": 0.6158175949385649, + "nauc_precision_at_5_diff1": -0.3121911800733753, + "nauc_precision_at_5_max": 0.06472238715882271, + "nauc_precision_at_5_std": 0.6698988387032873, + "nauc_recall_at_1000_diff1": -0.16135728347449516, + "nauc_recall_at_1000_max": -0.04286853984099918, + "nauc_recall_at_1000_std": 0.5296932660800093, + "nauc_recall_at_100_diff1": -0.23626338629367352, + "nauc_recall_at_100_max": -0.017353460844523903, + "nauc_recall_at_100_std": 0.6016048101828141, + "nauc_recall_at_10_diff1": -0.34975327931425065, + "nauc_recall_at_10_max": 0.035229770665915726, + "nauc_recall_at_10_std": 0.733069307038996, + "nauc_recall_at_1_diff1": -0.49992380003143133, + "nauc_recall_at_1_max": -0.06782779858276015, + "nauc_recall_at_1_std": 0.6885305059030336, + "nauc_recall_at_20_diff1": -0.32564997322949096, + "nauc_recall_at_20_max": 0.01075360076680833, + "nauc_recall_at_20_std": 0.7020650557606123, + "nauc_recall_at_3_diff1": -0.29677750968182715, + "nauc_recall_at_3_max": 0.05857829978210653, + "nauc_recall_at_3_std": 0.6158175949385651, + "nauc_recall_at_5_diff1": -0.31219118007337526, + "nauc_recall_at_5_max": 0.06472238715882284, + "nauc_recall_at_5_std": 0.6698988387032875, + "ndcg_at_1": 0.00316, + "ndcg_at_10": 0.07456, + "ndcg_at_100": 0.10815, + "ndcg_at_1000": 0.14311, + "ndcg_at_20": 0.08516, + "ndcg_at_3": 0.04262, + "ndcg_at_5": 0.05896, + "precision_at_1": 0.00316, + "precision_at_10": 0.01597, + "precision_at_100": 0.0033, + "precision_at_1000": 0.00062, + "precision_at_20": 0.01008, + "precision_at_3": 0.02395, + "precision_at_5": 0.02228, + "recall_at_1": 0.00316, + "recall_at_10": 0.15974, + "recall_at_100": 0.33009, + "recall_at_1000": 0.62133, + "recall_at_20": 0.20154, + "recall_at_3": 0.07185, + "recall_at_5": 0.11139 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/dragon-plus-instruct/no_revision_available/WinoGrande.json b/results/dragon-plus-instruct/no_revision_available/WinoGrande.json new file mode 100644 index 000000000..3f643e580 --- /dev/null +++ b/results/dragon-plus-instruct/no_revision_available/WinoGrande.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 3.090428352355957, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.60844, + "map_at_1": 0.31176, + "map_at_10": 0.51764, + "map_at_100": 0.52321, + "map_at_1000": 0.52325, + "map_at_20": 0.52175, + "map_at_3": 0.47764, + "map_at_5": 0.50325, + "mrr_at_1": 0.31333859510655093, + "mrr_at_10": 0.5187438142844609, + "mrr_at_100": 0.5243199022999294, + "mrr_at_1000": 0.5243631702528475, + "mrr_at_20": 0.5228555838591855, + "mrr_at_3": 0.47921599579058133, + "mrr_at_5": 0.5044330439358062, + "nauc_map_at_1000_diff1": 0.08877211713507256, + "nauc_map_at_1000_max": 0.1051542977997938, + "nauc_map_at_1000_std": -0.14836457617916668, + "nauc_map_at_100_diff1": 0.08879859041682388, + "nauc_map_at_100_max": 0.10512276998315163, + "nauc_map_at_100_std": -0.14823493364153711, + "nauc_map_at_10_diff1": 0.08993755884889039, + "nauc_map_at_10_max": 0.10838629118632256, + "nauc_map_at_10_std": -0.1508300069115558, + "nauc_map_at_1_diff1": 0.08202664411950601, + "nauc_map_at_1_max": 0.07399413401616893, + "nauc_map_at_1_std": -0.11663267681297426, + "nauc_map_at_20_diff1": 0.08874255141236412, + "nauc_map_at_20_max": 0.10613262895277344, + "nauc_map_at_20_std": -0.14700909258796882, + "nauc_map_at_3_diff1": 0.0882046948657768, + "nauc_map_at_3_max": 0.10381927596952283, + "nauc_map_at_3_std": -0.15834293057045962, + "nauc_map_at_5_diff1": 0.09207792336994315, + "nauc_map_at_5_max": 0.10704772322310128, + "nauc_map_at_5_std": -0.15508511562822958, + "nauc_mrr_at_1000_diff1": 0.08639016217971052, + "nauc_mrr_at_1000_max": 0.10622127152865886, + "nauc_mrr_at_1000_std": -0.1472962375055015, + "nauc_mrr_at_100_diff1": 0.08641700591018035, + "nauc_mrr_at_100_max": 0.10618957257474182, + "nauc_mrr_at_100_std": -0.147166723718272, + "nauc_mrr_at_10_diff1": 0.08760441046194568, + "nauc_mrr_at_10_max": 0.10940165359826905, + "nauc_mrr_at_10_std": -0.14976831656844336, + "nauc_mrr_at_1_diff1": 0.07742458332438473, + "nauc_mrr_at_1_max": 0.07324319018061629, + "nauc_mrr_at_1_std": -0.11487393865111939, + "nauc_mrr_at_20_diff1": 0.08637292823490722, + "nauc_mrr_at_20_max": 0.10719113290715279, + "nauc_mrr_at_20_std": -0.1459404966812676, + "nauc_mrr_at_3_diff1": 0.08651832861901163, + "nauc_mrr_at_3_max": 0.10559852287082061, + "nauc_mrr_at_3_std": -0.15719741317974553, + "nauc_mrr_at_5_diff1": 0.08974079619263288, + "nauc_mrr_at_5_max": 0.10860400581069872, + "nauc_mrr_at_5_std": -0.15458980470710004, + "nauc_ndcg_at_1000_diff1": 0.09024019420737404, + "nauc_ndcg_at_1000_max": 0.10919205251447911, + "nauc_ndcg_at_1000_std": -0.1462946975859358, + "nauc_ndcg_at_100_diff1": 0.09067653604818536, + "nauc_ndcg_at_100_max": 0.10840430878008855, + "nauc_ndcg_at_100_std": -0.1428169088541872, + "nauc_ndcg_at_10_diff1": 0.0955111895740253, + "nauc_ndcg_at_10_max": 0.1241669909707342, + "nauc_ndcg_at_10_std": -0.14855953676492858, + "nauc_ndcg_at_1_diff1": 0.08202664411950601, + "nauc_ndcg_at_1_max": 0.07399413401616893, + "nauc_ndcg_at_1_std": -0.11663267681297426, + "nauc_ndcg_at_20_diff1": 0.09096827516073783, + "nauc_ndcg_at_20_max": 0.11497404350756567, + "nauc_ndcg_at_20_std": -0.13196293992768024, + "nauc_ndcg_at_3_diff1": 0.09139399955004245, + "nauc_ndcg_at_3_max": 0.11223554412143871, + "nauc_ndcg_at_3_std": -0.1672560161182274, + "nauc_ndcg_at_5_diff1": 0.09965680462657919, + "nauc_ndcg_at_5_max": 0.1191405276557286, + "nauc_ndcg_at_5_std": -0.1619223571766474, + "nauc_precision_at_1000_diff1": 1.0, + "nauc_precision_at_1000_max": 1.0, + "nauc_precision_at_1000_std": 1.0, + "nauc_precision_at_100_diff1": 0.18293979913666986, + "nauc_precision_at_100_max": -0.08253263417633373, + "nauc_precision_at_100_std": 0.76779052991348, + "nauc_precision_at_10_diff1": 0.1407516432382942, + "nauc_precision_at_10_max": 0.2496360917656251, + "nauc_precision_at_10_std": -0.10499678448523063, + "nauc_precision_at_1_diff1": 0.08202664411950601, + "nauc_precision_at_1_max": 0.07399413401616893, + "nauc_precision_at_1_std": -0.11663267681297426, + "nauc_precision_at_20_diff1": 0.11360739642494025, + "nauc_precision_at_20_max": 0.22221536676538048, + "nauc_precision_at_20_std": 0.22463948778320622, + "nauc_precision_at_3_diff1": 0.10242558145314576, + "nauc_precision_at_3_max": 0.13964088373166014, + "nauc_precision_at_3_std": -0.19500178148364547, + "nauc_precision_at_5_diff1": 0.13543441334411466, + "nauc_precision_at_5_max": 0.17213149118767446, + "nauc_precision_at_5_std": -0.18777893723520858, + "nauc_recall_at_1000_diff1": NaN, + "nauc_recall_at_1000_max": NaN, + "nauc_recall_at_1000_std": NaN, + "nauc_recall_at_100_diff1": 0.18293979913665973, + "nauc_recall_at_100_max": -0.08253263417634701, + "nauc_recall_at_100_std": 0.7677905299134785, + "nauc_recall_at_10_diff1": 0.14075164323829328, + "nauc_recall_at_10_max": 0.2496360917656245, + "nauc_recall_at_10_std": -0.10499678448523182, + "nauc_recall_at_1_diff1": 0.08202664411950601, + "nauc_recall_at_1_max": 0.07399413401616893, + "nauc_recall_at_1_std": -0.11663267681297426, + "nauc_recall_at_20_diff1": 0.11360739642494279, + "nauc_recall_at_20_max": 0.22221536676538062, + "nauc_recall_at_20_std": 0.22463948778320822, + "nauc_recall_at_3_diff1": 0.10242558145314638, + "nauc_recall_at_3_max": 0.13964088373166064, + "nauc_recall_at_3_std": -0.1950017814836454, + "nauc_recall_at_5_diff1": 0.13543441334411455, + "nauc_recall_at_5_max": 0.17213149118767432, + "nauc_recall_at_5_std": -0.1877789372352071, + "ndcg_at_1": 0.31176, + "ndcg_at_10": 0.60844, + "ndcg_at_100": 0.6323, + "ndcg_at_1000": 0.63317, + "ndcg_at_20": 0.62314, + "ndcg_at_3": 0.52797, + "ndcg_at_5": 0.57396, + "precision_at_1": 0.31176, + "precision_at_10": 0.08895, + "precision_at_100": 0.00994, + "precision_at_1000": 0.001, + "precision_at_20": 0.04736, + "precision_at_3": 0.22415, + "precision_at_5": 0.15675, + "recall_at_1": 0.31176, + "recall_at_10": 0.8895, + "recall_at_100": 0.99369, + "recall_at_1000": 1.0, + "recall_at_20": 0.94712, + "recall_at_3": 0.67245, + "recall_at_5": 0.78374 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/dragon-plus/no_revision_available/ARCChallenge.json b/results/dragon-plus/no_revision_available/ARCChallenge.json new file mode 100644 index 000000000..09c84d1d4 --- /dev/null +++ b/results/dragon-plus/no_revision_available/ARCChallenge.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 4.120171308517456, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.08911, + "map_at_1": 0.02474, + "map_at_10": 0.06544, + "map_at_100": 0.07214, + "map_at_1000": 0.07346, + "map_at_20": 0.06857, + "map_at_3": 0.05233, + "map_at_5": 0.05886, + "mrr_at_1": 0.024744027303754267, + "mrr_at_10": 0.06543928435993288, + "mrr_at_100": 0.0721382230478502, + "mrr_at_1000": 0.07346215357175684, + "mrr_at_20": 0.06857280487621845, + "mrr_at_3": 0.05233219567690559, + "mrr_at_5": 0.05885949943117181, + "nauc_map_at_1000_diff1": 0.0018627009195180415, + "nauc_map_at_1000_max": 0.08103795387386761, + "nauc_map_at_1000_std": -0.08858511646727395, + "nauc_map_at_100_diff1": 0.0010504125485052893, + "nauc_map_at_100_max": 0.08208978721107968, + "nauc_map_at_100_std": -0.08955245806490188, + "nauc_map_at_10_diff1": 0.0039020857407207755, + "nauc_map_at_10_max": 0.08369906781238644, + "nauc_map_at_10_std": -0.09663543793992191, + "nauc_map_at_1_diff1": 0.04636088404745407, + "nauc_map_at_1_max": -0.008628706458685853, + "nauc_map_at_1_std": -0.08061730642343735, + "nauc_map_at_20_diff1": 0.002341357792996885, + "nauc_map_at_20_max": 0.08612728543100501, + "nauc_map_at_20_std": -0.09212907103103066, + "nauc_map_at_3_diff1": -0.003161371040765943, + "nauc_map_at_3_max": 0.06546698926422963, + "nauc_map_at_3_std": -0.09926580142585423, + "nauc_map_at_5_diff1": 0.0009946143647876953, + "nauc_map_at_5_max": 0.10205249940000645, + "nauc_map_at_5_std": -0.09483092725468259, + "nauc_mrr_at_1000_diff1": 0.0018625932576776026, + "nauc_mrr_at_1000_max": 0.08103775091916325, + "nauc_mrr_at_1000_std": -0.08858524231192948, + "nauc_mrr_at_100_diff1": 0.0010504125485052893, + "nauc_mrr_at_100_max": 0.08208978721107968, + "nauc_mrr_at_100_std": -0.08955245806490188, + "nauc_mrr_at_10_diff1": 0.0039020857407207755, + "nauc_mrr_at_10_max": 0.08369906781238644, + "nauc_mrr_at_10_std": -0.09663543793992191, + "nauc_mrr_at_1_diff1": 0.04636088404745407, + "nauc_mrr_at_1_max": -0.008628706458685853, + "nauc_mrr_at_1_std": -0.08061730642343735, + "nauc_mrr_at_20_diff1": 0.002341357792996885, + "nauc_mrr_at_20_max": 0.08612728543100501, + "nauc_mrr_at_20_std": -0.09212907103103066, + "nauc_mrr_at_3_diff1": -0.003161371040765943, + "nauc_mrr_at_3_max": 0.06546698926422963, + "nauc_mrr_at_3_std": -0.09926580142585423, + "nauc_mrr_at_5_diff1": 0.0009946143647876953, + "nauc_mrr_at_5_max": 0.10205249940000645, + "nauc_mrr_at_5_std": -0.09483092725468259, + "nauc_ndcg_at_1000_diff1": -0.0027675655200407635, + "nauc_ndcg_at_1000_max": 0.05315858324134535, + "nauc_ndcg_at_1000_std": -0.06482095469312368, + "nauc_ndcg_at_100_diff1": -0.008779580392680134, + "nauc_ndcg_at_100_max": 0.07334079843382137, + "nauc_ndcg_at_100_std": -0.07805609352039108, + "nauc_ndcg_at_10_diff1": 0.0012207554220928468, + "nauc_ndcg_at_10_max": 0.08862818178192124, + "nauc_ndcg_at_10_std": -0.10043882525132766, + "nauc_ndcg_at_1_diff1": 0.04636088404745407, + "nauc_ndcg_at_1_max": -0.008628706458685853, + "nauc_ndcg_at_1_std": -0.08061730642343735, + "nauc_ndcg_at_20_diff1": -0.0035080225173475467, + "nauc_ndcg_at_20_max": 0.09362916979146042, + "nauc_ndcg_at_20_std": -0.08930060729736819, + "nauc_ndcg_at_3_diff1": -0.009436934172087892, + "nauc_ndcg_at_3_max": 0.07215632148740825, + "nauc_ndcg_at_3_std": -0.1039794624247726, + "nauc_ndcg_at_5_diff1": -0.002787848740369951, + "nauc_ndcg_at_5_max": 0.12523504278193243, + "nauc_ndcg_at_5_std": -0.09743031810135339, + "nauc_precision_at_1000_diff1": -0.013746393201233165, + "nauc_precision_at_1000_max": -0.06021422197655787, + "nauc_precision_at_1000_std": 0.0057686876027050775, + "nauc_precision_at_100_diff1": -0.023379380131040527, + "nauc_precision_at_100_max": 0.04810050709871539, + "nauc_precision_at_100_std": -0.057393557409650006, + "nauc_precision_at_10_diff1": -0.002089682159259329, + "nauc_precision_at_10_max": 0.09108177592097903, + "nauc_precision_at_10_std": -0.10587572268602301, + "nauc_precision_at_1_diff1": 0.04636088404745407, + "nauc_precision_at_1_max": -0.008628706458685853, + "nauc_precision_at_1_std": -0.08061730642343735, + "nauc_precision_at_20_diff1": -0.012129177707903659, + "nauc_precision_at_20_max": 0.09995563635989285, + "nauc_precision_at_20_std": -0.08320254218893348, + "nauc_precision_at_3_diff1": -0.020199509392739255, + "nauc_precision_at_3_max": 0.0830309622600597, + "nauc_precision_at_3_std": -0.11258353024655716, + "nauc_precision_at_5_diff1": -0.008064506474884894, + "nauc_precision_at_5_max": 0.16402880124999009, + "nauc_precision_at_5_std": -0.10148491749209904, + "nauc_recall_at_1000_diff1": -0.013746393201232523, + "nauc_recall_at_1000_max": -0.06021422197655861, + "nauc_recall_at_1000_std": 0.005768687602705267, + "nauc_recall_at_100_diff1": -0.023379380131040736, + "nauc_recall_at_100_max": 0.04810050709871514, + "nauc_recall_at_100_std": -0.05739355740965012, + "nauc_recall_at_10_diff1": -0.0020896821592595576, + "nauc_recall_at_10_max": 0.09108177592097894, + "nauc_recall_at_10_std": -0.10587572268602305, + "nauc_recall_at_1_diff1": 0.04636088404745407, + "nauc_recall_at_1_max": -0.008628706458685853, + "nauc_recall_at_1_std": -0.08061730642343735, + "nauc_recall_at_20_diff1": -0.012129177707903909, + "nauc_recall_at_20_max": 0.09995563635989278, + "nauc_recall_at_20_std": -0.08320254218893364, + "nauc_recall_at_3_diff1": -0.020199509392739123, + "nauc_recall_at_3_max": 0.08303096226005979, + "nauc_recall_at_3_std": -0.11258353024655716, + "nauc_recall_at_5_diff1": -0.00806450647488496, + "nauc_recall_at_5_max": 0.16402880124999, + "nauc_recall_at_5_std": -0.10148491749209922, + "ndcg_at_1": 0.02474, + "ndcg_at_10": 0.08911, + "ndcg_at_100": 0.12769, + "ndcg_at_1000": 0.17086, + "ndcg_at_20": 0.10097, + "ndcg_at_3": 0.06145, + "ndcg_at_5": 0.07313, + "precision_at_1": 0.02474, + "precision_at_10": 0.01655, + "precision_at_100": 0.00359, + "precision_at_1000": 0.00072, + "precision_at_20": 0.01067, + "precision_at_3": 0.02929, + "precision_at_5": 0.02321, + "recall_at_1": 0.02474, + "recall_at_10": 0.16553, + "recall_at_100": 0.35922, + "recall_at_1000": 0.71672, + "recall_at_20": 0.21331, + "recall_at_3": 0.08788, + "recall_at_5": 0.11604 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/dragon-plus/no_revision_available/AlphaNLI.json b/results/dragon-plus/no_revision_available/AlphaNLI.json new file mode 100644 index 000000000..5b3f6bd17 --- /dev/null +++ b/results/dragon-plus/no_revision_available/AlphaNLI.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 54.46732044219971, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.32102, + "map_at_1": 0.2154, + "map_at_10": 0.28772, + "map_at_100": 0.2949, + "map_at_1000": 0.29559, + "map_at_20": 0.29202, + "map_at_3": 0.27285, + "map_at_5": 0.28133, + "mrr_at_1": 0.2154046997389034, + "mrr_at_10": 0.28772146587094355, + "mrr_at_100": 0.29489881303380094, + "mrr_at_1000": 0.29558674143361324, + "mrr_at_20": 0.29201521284408294, + "mrr_at_3": 0.2728459530026108, + "mrr_at_5": 0.28133159268929475, + "nauc_map_at_1000_diff1": 0.37298096334276043, + "nauc_map_at_1000_max": 0.14829321097831608, + "nauc_map_at_1000_std": -0.019130589126821626, + "nauc_map_at_100_diff1": 0.37293340088651583, + "nauc_map_at_100_max": 0.14822541984650942, + "nauc_map_at_100_std": -0.01902639496950006, + "nauc_map_at_10_diff1": 0.374244312082563, + "nauc_map_at_10_max": 0.14916753994636267, + "nauc_map_at_10_std": -0.021840117802827182, + "nauc_map_at_1_diff1": 0.4190414397891443, + "nauc_map_at_1_max": 0.1418358185720944, + "nauc_map_at_1_std": -0.03975947027873804, + "nauc_map_at_20_diff1": 0.37342251201146454, + "nauc_map_at_20_max": 0.14925200031616023, + "nauc_map_at_20_std": -0.020367757085556652, + "nauc_map_at_3_diff1": 0.3832817893961845, + "nauc_map_at_3_max": 0.1541531571073056, + "nauc_map_at_3_std": -0.02410974104783912, + "nauc_map_at_5_diff1": 0.3807606541432604, + "nauc_map_at_5_max": 0.15361105535087183, + "nauc_map_at_5_std": -0.021781510164242998, + "nauc_mrr_at_1000_diff1": 0.37298089438403526, + "nauc_mrr_at_1000_max": 0.14829314642778224, + "nauc_mrr_at_1000_std": -0.019130594815328295, + "nauc_mrr_at_100_diff1": 0.37293340088651583, + "nauc_mrr_at_100_max": 0.14822541984650942, + "nauc_mrr_at_100_std": -0.01902639496950006, + "nauc_mrr_at_10_diff1": 0.374244312082563, + "nauc_mrr_at_10_max": 0.14916753994636267, + "nauc_mrr_at_10_std": -0.021840117802827182, + "nauc_mrr_at_1_diff1": 0.4190414397891443, + "nauc_mrr_at_1_max": 0.1418358185720944, + "nauc_mrr_at_1_std": -0.03975947027873804, + "nauc_mrr_at_20_diff1": 0.37342251201146454, + "nauc_mrr_at_20_max": 0.14925200031616023, + "nauc_mrr_at_20_std": -0.020367757085556652, + "nauc_mrr_at_3_diff1": 0.3832817893961845, + "nauc_mrr_at_3_max": 0.1541531571073056, + "nauc_mrr_at_3_std": -0.02410974104783912, + "nauc_mrr_at_5_diff1": 0.3807606541432604, + "nauc_mrr_at_5_max": 0.15361105535087183, + "nauc_mrr_at_5_std": -0.021781510164242998, + "nauc_ndcg_at_1000_diff1": 0.34912071025284286, + "nauc_ndcg_at_1000_max": 0.14041406060452122, + "nauc_ndcg_at_1000_std": 0.001005605780569279, + "nauc_ndcg_at_100_diff1": 0.3489935620800606, + "nauc_ndcg_at_100_max": 0.14046251016191177, + "nauc_ndcg_at_100_std": 0.0013538182111690247, + "nauc_ndcg_at_10_diff1": 0.355599470654065, + "nauc_ndcg_at_10_max": 0.14490320033299595, + "nauc_ndcg_at_10_std": -0.014425073058047905, + "nauc_ndcg_at_1_diff1": 0.4190414397891443, + "nauc_ndcg_at_1_max": 0.1418358185720944, + "nauc_ndcg_at_1_std": -0.03975947027873804, + "nauc_ndcg_at_20_diff1": 0.35276139249507815, + "nauc_ndcg_at_20_max": 0.14515164753478624, + "nauc_ndcg_at_20_std": -0.010020498023659286, + "nauc_ndcg_at_3_diff1": 0.3741043262332059, + "nauc_ndcg_at_3_max": 0.15594632015935767, + "nauc_ndcg_at_3_std": -0.01884147355015237, + "nauc_ndcg_at_5_diff1": 0.37017223268122673, + "nauc_ndcg_at_5_max": 0.15468302968739128, + "nauc_ndcg_at_5_std": -0.014699188362109084, + "nauc_precision_at_1000_diff1": 0.21900349978103817, + "nauc_precision_at_1000_max": 0.08441103189818785, + "nauc_precision_at_1000_std": 0.13916991423490577, + "nauc_precision_at_100_diff1": 0.26241096916809475, + "nauc_precision_at_100_max": 0.10762129473231274, + "nauc_precision_at_100_std": 0.0911478183684166, + "nauc_precision_at_10_diff1": 0.3021854756533361, + "nauc_precision_at_10_max": 0.1299119031528831, + "nauc_precision_at_10_std": 0.006316072592827808, + "nauc_precision_at_1_diff1": 0.4190414397891443, + "nauc_precision_at_1_max": 0.1418358185720944, + "nauc_precision_at_1_std": -0.03975947027873804, + "nauc_precision_at_20_diff1": 0.29081321567136637, + "nauc_precision_at_20_max": 0.13048143834530607, + "nauc_precision_at_20_std": 0.0214761902696838, + "nauc_precision_at_3_diff1": 0.35004486590734585, + "nauc_precision_at_3_max": 0.16019888748571878, + "nauc_precision_at_3_std": -0.004619988951065039, + "nauc_precision_at_5_diff1": 0.34248011439201936, + "nauc_precision_at_5_max": 0.15663178688470336, + "nauc_precision_at_5_std": 0.004701442602336849, + "nauc_recall_at_1000_diff1": 0.21900349978103784, + "nauc_recall_at_1000_max": 0.08441103189818697, + "nauc_recall_at_1000_std": 0.13916991423490593, + "nauc_recall_at_100_diff1": 0.2624109691680945, + "nauc_recall_at_100_max": 0.1076212947323121, + "nauc_recall_at_100_std": 0.09114781836841623, + "nauc_recall_at_10_diff1": 0.30218547565333614, + "nauc_recall_at_10_max": 0.1299119031528829, + "nauc_recall_at_10_std": 0.006316072592827627, + "nauc_recall_at_1_diff1": 0.4190414397891443, + "nauc_recall_at_1_max": 0.1418358185720944, + "nauc_recall_at_1_std": -0.03975947027873804, + "nauc_recall_at_20_diff1": 0.29081321567136603, + "nauc_recall_at_20_max": 0.13048143834530593, + "nauc_recall_at_20_std": 0.021476190269683757, + "nauc_recall_at_3_diff1": 0.3500448659073462, + "nauc_recall_at_3_max": 0.16019888748571906, + "nauc_recall_at_3_std": -0.004619988951064714, + "nauc_recall_at_5_diff1": 0.34248011439201953, + "nauc_recall_at_5_max": 0.15663178688470328, + "nauc_recall_at_5_std": 0.00470144260233703, + "ndcg_at_1": 0.2154, + "ndcg_at_10": 0.32102, + "ndcg_at_100": 0.35741, + "ndcg_at_1000": 0.37834, + "ndcg_at_20": 0.33615, + "ndcg_at_3": 0.29053, + "ndcg_at_5": 0.3057, + "precision_at_1": 0.2154, + "precision_at_10": 0.04249, + "precision_at_100": 0.00599, + "precision_at_1000": 0.00077, + "precision_at_20": 0.02418, + "precision_at_3": 0.11379, + "precision_at_5": 0.07559, + "recall_at_1": 0.2154, + "recall_at_10": 0.42493, + "recall_at_100": 0.59922, + "recall_at_1000": 0.76958, + "recall_at_20": 0.48368, + "recall_at_3": 0.34138, + "recall_at_5": 0.37794 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/dragon-plus/no_revision_available/HellaSwag.json b/results/dragon-plus/no_revision_available/HellaSwag.json new file mode 100644 index 000000000..a721142c9 --- /dev/null +++ b/results/dragon-plus/no_revision_available/HellaSwag.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 137.2667374610901, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.27693, + "map_at_1": 0.14619, + "map_at_10": 0.23136, + "map_at_100": 0.239, + "map_at_1000": 0.23975, + "map_at_20": 0.23534, + "map_at_3": 0.20779, + "map_at_5": 0.22193, + "mrr_at_1": 0.14618601872137024, + "mrr_at_10": 0.2313583346768966, + "mrr_at_100": 0.23899915022044996, + "mrr_at_1000": 0.2397495221173882, + "mrr_at_20": 0.2353342360844788, + "mrr_at_3": 0.2077939321516283, + "mrr_at_5": 0.22192956250414897, + "nauc_map_at_1000_diff1": 0.21497589482168525, + "nauc_map_at_1000_max": -0.2543626077728985, + "nauc_map_at_1000_std": -0.04113077181982725, + "nauc_map_at_100_diff1": 0.21492686029212574, + "nauc_map_at_100_max": -0.2541184672544985, + "nauc_map_at_100_std": -0.041287236523364405, + "nauc_map_at_10_diff1": 0.21568898411343063, + "nauc_map_at_10_max": -0.24801742562383572, + "nauc_map_at_10_std": -0.043794694795846856, + "nauc_map_at_1_diff1": 0.24134230070468263, + "nauc_map_at_1_max": -0.20229856739249727, + "nauc_map_at_1_std": -0.057426017720444235, + "nauc_map_at_20_diff1": 0.21524145596425145, + "nauc_map_at_20_max": -0.25148325253251247, + "nauc_map_at_20_std": -0.04273440797914141, + "nauc_map_at_3_diff1": 0.21836169979333073, + "nauc_map_at_3_max": -0.2270326793451032, + "nauc_map_at_3_std": -0.04488992811717459, + "nauc_map_at_5_diff1": 0.2177600915418545, + "nauc_map_at_5_max": -0.2388442678770311, + "nauc_map_at_5_std": -0.044758461706534455, + "nauc_mrr_at_1000_diff1": 0.21496883137708747, + "nauc_mrr_at_1000_max": -0.2543620901886603, + "nauc_mrr_at_1000_std": -0.04112444852547847, + "nauc_mrr_at_100_diff1": 0.21491979051879467, + "nauc_mrr_at_100_max": -0.2541179648114117, + "nauc_mrr_at_100_std": -0.041280940550348894, + "nauc_mrr_at_10_diff1": 0.21568195609659002, + "nauc_mrr_at_10_max": -0.248016919500352, + "nauc_mrr_at_10_std": -0.043788437984155625, + "nauc_mrr_at_1_diff1": 0.24134230070468263, + "nauc_mrr_at_1_max": -0.20229856739249727, + "nauc_mrr_at_1_std": -0.057426017720444235, + "nauc_mrr_at_20_diff1": 0.21523441527981868, + "nauc_mrr_at_20_max": -0.25148274928143344, + "nauc_mrr_at_20_std": -0.042728139173813844, + "nauc_mrr_at_3_diff1": 0.21836169979333073, + "nauc_mrr_at_3_max": -0.2270326793451032, + "nauc_mrr_at_3_std": -0.04488992811717459, + "nauc_mrr_at_5_diff1": 0.2177600915418545, + "nauc_mrr_at_5_max": -0.2388442678770311, + "nauc_mrr_at_5_std": -0.044758461706534455, + "nauc_ndcg_at_1000_diff1": 0.2019028927185279, + "nauc_ndcg_at_1000_max": -0.31439124454528133, + "nauc_ndcg_at_1000_std": -0.022615146553221322, + "nauc_ndcg_at_100_diff1": 0.2014283775168188, + "nauc_ndcg_at_100_max": -0.3059637233413758, + "nauc_ndcg_at_100_std": -0.025370827934529924, + "nauc_ndcg_at_10_diff1": 0.20670942641863463, + "nauc_ndcg_at_10_max": -0.274930495300011, + "nauc_ndcg_at_10_std": -0.03928771137366075, + "nauc_ndcg_at_1_diff1": 0.24134230070468263, + "nauc_ndcg_at_1_max": -0.20229856739249727, + "nauc_ndcg_at_1_std": -0.057426017720444235, + "nauc_ndcg_at_20_diff1": 0.20489084108378366, + "nauc_ndcg_at_20_max": -0.2868749832096585, + "nauc_ndcg_at_20_std": -0.03556681112160076, + "nauc_ndcg_at_3_diff1": 0.21220328528089197, + "nauc_ndcg_at_3_max": -0.23468022076209227, + "nauc_ndcg_at_3_std": -0.041440473553818406, + "nauc_ndcg_at_5_diff1": 0.21145617795331076, + "nauc_ndcg_at_5_max": -0.25456838194684595, + "nauc_ndcg_at_5_std": -0.04131289707012348, + "nauc_precision_at_1000_diff1": 0.1265928290230275, + "nauc_precision_at_1000_max": -0.7298310673011819, + "nauc_precision_at_1000_std": 0.10978678921870944, + "nauc_precision_at_100_diff1": 0.1529058051363585, + "nauc_precision_at_100_max": -0.5026152330463236, + "nauc_precision_at_100_std": 0.04093146573973347, + "nauc_precision_at_10_diff1": 0.1845838327951236, + "nauc_precision_at_10_max": -0.34503688017191775, + "nauc_precision_at_10_std": -0.028436464891327277, + "nauc_precision_at_1_diff1": 0.24134230070468263, + "nauc_precision_at_1_max": -0.20229856739249727, + "nauc_precision_at_1_std": -0.057426017720444235, + "nauc_precision_at_20_diff1": 0.17760381584479046, + "nauc_precision_at_20_max": -0.386441268730416, + "nauc_precision_at_20_std": -0.015605178621553892, + "nauc_precision_at_3_diff1": 0.1975442256255445, + "nauc_precision_at_3_max": -0.2531370923071631, + "nauc_precision_at_3_std": -0.03320727632250895, + "nauc_precision_at_5_diff1": 0.19688717422154658, + "nauc_precision_at_5_max": -0.29339264130624865, + "nauc_precision_at_5_std": -0.03332789543598621, + "nauc_recall_at_1000_diff1": 0.12659282902302837, + "nauc_recall_at_1000_max": -0.72983106730118, + "nauc_recall_at_1000_std": 0.10978678921871077, + "nauc_recall_at_100_diff1": 0.1529058051363591, + "nauc_recall_at_100_max": -0.502615233046324, + "nauc_recall_at_100_std": 0.040931465739733844, + "nauc_recall_at_10_diff1": 0.18458383279512375, + "nauc_recall_at_10_max": -0.34503688017191747, + "nauc_recall_at_10_std": -0.028436464891326764, + "nauc_recall_at_1_diff1": 0.24134230070468263, + "nauc_recall_at_1_max": -0.20229856739249727, + "nauc_recall_at_1_std": -0.057426017720444235, + "nauc_recall_at_20_diff1": 0.17760381584479065, + "nauc_recall_at_20_max": -0.386441268730416, + "nauc_recall_at_20_std": -0.015605178621554116, + "nauc_recall_at_3_diff1": 0.19754422562554447, + "nauc_recall_at_3_max": -0.2531370923071631, + "nauc_recall_at_3_std": -0.03320727632250908, + "nauc_recall_at_5_diff1": 0.19688717422154667, + "nauc_recall_at_5_max": -0.2933926413062485, + "nauc_recall_at_5_std": -0.033327895435985966, + "ndcg_at_1": 0.14619, + "ndcg_at_10": 0.27693, + "ndcg_at_100": 0.3184, + "ndcg_at_1000": 0.34066, + "ndcg_at_20": 0.29136, + "ndcg_at_3": 0.22885, + "ndcg_at_5": 0.25426, + "precision_at_1": 0.14619, + "precision_at_10": 0.04213, + "precision_at_100": 0.00625, + "precision_at_1000": 0.00081, + "precision_at_20": 0.02391, + "precision_at_3": 0.09669, + "precision_at_5": 0.07032, + "recall_at_1": 0.14619, + "recall_at_10": 0.42133, + "recall_at_100": 0.62517, + "recall_at_1000": 0.80552, + "recall_at_20": 0.47829, + "recall_at_3": 0.29008, + "recall_at_5": 0.35162 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/dragon-plus/no_revision_available/PIQA.json b/results/dragon-plus/no_revision_available/PIQA.json new file mode 100644 index 000000000..3116a678d --- /dev/null +++ b/results/dragon-plus/no_revision_available/PIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 16.765268087387085, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.28012, + "map_at_1": 0.15452, + "map_at_10": 0.23842, + "map_at_100": 0.24679, + "map_at_1000": 0.24748, + "map_at_20": 0.24335, + "map_at_3": 0.21708, + "map_at_5": 0.22962, + "mrr_at_1": 0.15451577801958652, + "mrr_at_10": 0.23841822546936778, + "mrr_at_100": 0.24679249182613444, + "mrr_at_1000": 0.24748124384494222, + "mrr_at_20": 0.24335077092577376, + "mrr_at_3": 0.21708378672470058, + "mrr_at_5": 0.2296245919477689, + "nauc_map_at_1000_diff1": -0.014126431899704344, + "nauc_map_at_1000_max": -0.012306987804794178, + "nauc_map_at_1000_std": -0.05874165973271011, + "nauc_map_at_100_diff1": -0.01413300563185513, + "nauc_map_at_100_max": -0.011991547560875256, + "nauc_map_at_100_std": -0.05857409559187097, + "nauc_map_at_10_diff1": -0.012392509246310007, + "nauc_map_at_10_max": -0.006005811611442519, + "nauc_map_at_10_std": -0.05731995917531734, + "nauc_map_at_1_diff1": 0.03330494874570158, + "nauc_map_at_1_max": 0.009424825257397004, + "nauc_map_at_1_std": -0.0591048739737853, + "nauc_map_at_20_diff1": -0.014821774218838612, + "nauc_map_at_20_max": -0.008598646074649, + "nauc_map_at_20_std": -0.0580973213394695, + "nauc_map_at_3_diff1": -0.00857582186109721, + "nauc_map_at_3_max": 0.013822755806937443, + "nauc_map_at_3_std": -0.055996573716106744, + "nauc_map_at_5_diff1": -0.012769667228970136, + "nauc_map_at_5_max": -0.0014150985288572944, + "nauc_map_at_5_std": -0.056077037857375195, + "nauc_mrr_at_1000_diff1": -0.014126431899704344, + "nauc_mrr_at_1000_max": -0.012306987804794178, + "nauc_mrr_at_1000_std": -0.05874165973271011, + "nauc_mrr_at_100_diff1": -0.01413300563185513, + "nauc_mrr_at_100_max": -0.011991547560875256, + "nauc_mrr_at_100_std": -0.05857409559187097, + "nauc_mrr_at_10_diff1": -0.012392509246310007, + "nauc_mrr_at_10_max": -0.006005811611442519, + "nauc_mrr_at_10_std": -0.05731995917531734, + "nauc_mrr_at_1_diff1": 0.03330494874570158, + "nauc_mrr_at_1_max": 0.009424825257397004, + "nauc_mrr_at_1_std": -0.0591048739737853, + "nauc_mrr_at_20_diff1": -0.014821774218838612, + "nauc_mrr_at_20_max": -0.008598646074649, + "nauc_mrr_at_20_std": -0.0580973213394695, + "nauc_mrr_at_3_diff1": -0.00857582186109721, + "nauc_mrr_at_3_max": 0.013822755806937443, + "nauc_mrr_at_3_std": -0.055996573716106744, + "nauc_mrr_at_5_diff1": -0.012769667228970136, + "nauc_mrr_at_5_max": -0.0014150985288572944, + "nauc_mrr_at_5_std": -0.056077037857375195, + "nauc_ndcg_at_1000_diff1": -0.029708253245062058, + "nauc_ndcg_at_1000_max": -0.06626687444925108, + "nauc_ndcg_at_1000_std": -0.07152235736577021, + "nauc_ndcg_at_100_diff1": -0.029431973025652886, + "nauc_ndcg_at_100_max": -0.05741598305145044, + "nauc_ndcg_at_100_std": -0.06739424365665067, + "nauc_ndcg_at_10_diff1": -0.025111198389416098, + "nauc_ndcg_at_10_max": -0.023583381526226355, + "nauc_ndcg_at_10_std": -0.05904200199954207, + "nauc_ndcg_at_1_diff1": 0.03330494874570158, + "nauc_ndcg_at_1_max": 0.009424825257397004, + "nauc_ndcg_at_1_std": -0.0591048739737853, + "nauc_ndcg_at_20_diff1": -0.03296607621475219, + "nauc_ndcg_at_20_max": -0.032528869667387016, + "nauc_ndcg_at_20_std": -0.06169342065486604, + "nauc_ndcg_at_3_diff1": -0.018421071688653916, + "nauc_ndcg_at_3_max": 0.012635854749113096, + "nauc_ndcg_at_3_std": -0.05623028199842326, + "nauc_ndcg_at_5_diff1": -0.025785380001794412, + "nauc_ndcg_at_5_max": -0.01349922471864673, + "nauc_ndcg_at_5_std": -0.056317137457893005, + "nauc_precision_at_1000_diff1": -0.09715466320219329, + "nauc_precision_at_1000_max": -0.43695414423662904, + "nauc_precision_at_1000_std": -0.17444243966840386, + "nauc_precision_at_100_diff1": -0.07234240042392935, + "nauc_precision_at_100_max": -0.24474889311307932, + "nauc_precision_at_100_std": -0.10962931596810088, + "nauc_precision_at_10_diff1": -0.055503481855220166, + "nauc_precision_at_10_max": -0.07116330948987953, + "nauc_precision_at_10_std": -0.06409409311088647, + "nauc_precision_at_1_diff1": 0.03330494874570158, + "nauc_precision_at_1_max": 0.009424825257397004, + "nauc_precision_at_1_std": -0.0591048739737853, + "nauc_precision_at_20_diff1": -0.08203190344762658, + "nauc_precision_at_20_max": -0.10277496660886512, + "nauc_precision_at_20_std": -0.07317740792025178, + "nauc_precision_at_3_diff1": -0.04203767248748975, + "nauc_precision_at_3_max": 0.009135310422792909, + "nauc_precision_at_3_std": -0.05707465926065452, + "nauc_precision_at_5_diff1": -0.05740753392876337, + "nauc_precision_at_5_max": -0.04589201503263521, + "nauc_precision_at_5_std": -0.05713513817162139, + "nauc_recall_at_1000_diff1": -0.09715466320219238, + "nauc_recall_at_1000_max": -0.4369541442366271, + "nauc_recall_at_1000_std": -0.17444243966840198, + "nauc_recall_at_100_diff1": -0.0723424004239295, + "nauc_recall_at_100_max": -0.24474889311307957, + "nauc_recall_at_100_std": -0.10962931596810103, + "nauc_recall_at_10_diff1": -0.05550348185522003, + "nauc_recall_at_10_max": -0.07116330948987953, + "nauc_recall_at_10_std": -0.06409409311088637, + "nauc_recall_at_1_diff1": 0.03330494874570158, + "nauc_recall_at_1_max": 0.009424825257397004, + "nauc_recall_at_1_std": -0.0591048739737853, + "nauc_recall_at_20_diff1": -0.08203190344762655, + "nauc_recall_at_20_max": -0.10277496660886505, + "nauc_recall_at_20_std": -0.0731774079202517, + "nauc_recall_at_3_diff1": -0.042037672487489484, + "nauc_recall_at_3_max": 0.009135310422793287, + "nauc_recall_at_3_std": -0.0570746592606541, + "nauc_recall_at_5_diff1": -0.057407533928763264, + "nauc_recall_at_5_max": -0.04589201503263529, + "nauc_recall_at_5_std": -0.05713513817162159, + "ndcg_at_1": 0.15452, + "ndcg_at_10": 0.28012, + "ndcg_at_100": 0.3229, + "ndcg_at_1000": 0.34329, + "ndcg_at_20": 0.29785, + "ndcg_at_3": 0.23632, + "ndcg_at_5": 0.25882, + "precision_at_1": 0.15452, + "precision_at_10": 0.04119, + "precision_at_100": 0.00617, + "precision_at_1000": 0.00078, + "precision_at_20": 0.02408, + "precision_at_3": 0.09721, + "precision_at_5": 0.06921, + "recall_at_1": 0.15452, + "recall_at_10": 0.41186, + "recall_at_100": 0.61697, + "recall_at_1000": 0.78237, + "recall_at_20": 0.4815, + "recall_at_3": 0.29162, + "recall_at_5": 0.34603 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/dragon-plus/no_revision_available/Quail.json b/results/dragon-plus/no_revision_available/Quail.json new file mode 100644 index 000000000..9f6461026 --- /dev/null +++ b/results/dragon-plus/no_revision_available/Quail.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 25.34874677658081, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.04091, + "map_at_1": 0.01213, + "map_at_10": 0.02883, + "map_at_100": 0.03331, + "map_at_1000": 0.03404, + "map_at_20": 0.03096, + "map_at_3": 0.02047, + "map_at_5": 0.02488, + "mrr_at_1": 0.01213235294117647, + "mrr_at_10": 0.02882644724556491, + "mrr_at_100": 0.03330784786605341, + "mrr_at_1000": 0.03404462228232151, + "mrr_at_20": 0.030964709757236777, + "mrr_at_3": 0.020465686274509808, + "mrr_at_5": 0.02487745098039217, + "nauc_map_at_1000_diff1": 0.08514559789739183, + "nauc_map_at_1000_max": 0.003867553070773906, + "nauc_map_at_1000_std": 0.1375932103776312, + "nauc_map_at_100_diff1": 0.08626368958479717, + "nauc_map_at_100_max": 0.0047120523751619575, + "nauc_map_at_100_std": 0.13729167858054303, + "nauc_map_at_10_diff1": 0.09857283046038588, + "nauc_map_at_10_max": 0.010258570791977683, + "nauc_map_at_10_std": 0.1310719335828677, + "nauc_map_at_1_diff1": 0.18609491751428958, + "nauc_map_at_1_max": 0.0273272028034571, + "nauc_map_at_1_std": 0.20673870445804987, + "nauc_map_at_20_diff1": 0.09573057269896512, + "nauc_map_at_20_max": 0.007283405443212244, + "nauc_map_at_20_std": 0.13800241814396777, + "nauc_map_at_3_diff1": 0.12255687176759979, + "nauc_map_at_3_max": 0.02218717916996684, + "nauc_map_at_3_std": 0.12693502182648383, + "nauc_map_at_5_diff1": 0.09800497236911859, + "nauc_map_at_5_max": 0.01628338538768492, + "nauc_map_at_5_std": 0.12395976108308308, + "nauc_mrr_at_1000_diff1": 0.0851224165162607, + "nauc_mrr_at_1000_max": 0.0038447866345533667, + "nauc_mrr_at_1000_std": 0.137562337879444, + "nauc_mrr_at_100_diff1": 0.08624038819193243, + "nauc_mrr_at_100_max": 0.004689181382851332, + "nauc_mrr_at_100_std": 0.1372606297632316, + "nauc_mrr_at_10_diff1": 0.09857283046038588, + "nauc_mrr_at_10_max": 0.010258570791977683, + "nauc_mrr_at_10_std": 0.1310719335828677, + "nauc_mrr_at_1_diff1": 0.18609491751428958, + "nauc_mrr_at_1_max": 0.0273272028034571, + "nauc_mrr_at_1_std": 0.20673870445804987, + "nauc_mrr_at_20_diff1": 0.09570088973607058, + "nauc_mrr_at_20_max": 0.007262346514471032, + "nauc_mrr_at_20_std": 0.13796688167129129, + "nauc_mrr_at_3_diff1": 0.12255687176759979, + "nauc_mrr_at_3_max": 0.02218717916996684, + "nauc_mrr_at_3_std": 0.12693502182648383, + "nauc_mrr_at_5_diff1": 0.09800497236911859, + "nauc_mrr_at_5_max": 0.01628338538768492, + "nauc_mrr_at_5_std": 0.12395976108308308, + "nauc_ndcg_at_1000_diff1": 0.03047588347467243, + "nauc_ndcg_at_1000_max": -0.01918505000841383, + "nauc_ndcg_at_1000_std": 0.13977976708073403, + "nauc_ndcg_at_100_diff1": 0.04568732716649164, + "nauc_ndcg_at_100_max": -0.010760439114051492, + "nauc_ndcg_at_100_std": 0.13481019362124025, + "nauc_ndcg_at_10_diff1": 0.08256291748329563, + "nauc_ndcg_at_10_max": 0.005001857194459644, + "nauc_ndcg_at_10_std": 0.12467019449996251, + "nauc_ndcg_at_1_diff1": 0.18609491751428958, + "nauc_ndcg_at_1_max": 0.0273272028034571, + "nauc_ndcg_at_1_std": 0.20673870445804987, + "nauc_ndcg_at_20_diff1": 0.07832538100308627, + "nauc_ndcg_at_20_max": -0.0019632010596990182, + "nauc_ndcg_at_20_std": 0.1400330419818926, + "nauc_ndcg_at_3_diff1": 0.11408831098229862, + "nauc_ndcg_at_3_max": 0.02539725336607836, + "nauc_ndcg_at_3_std": 0.11147166589616841, + "nauc_ndcg_at_5_diff1": 0.08094306729689286, + "nauc_ndcg_at_5_max": 0.01711184292549, + "nauc_ndcg_at_5_std": 0.10956292320231573, + "nauc_precision_at_1000_diff1": -0.02537593671523559, + "nauc_precision_at_1000_max": -0.042798875822611306, + "nauc_precision_at_1000_std": 0.14617021692202348, + "nauc_precision_at_100_diff1": 0.0071581857579646885, + "nauc_precision_at_100_max": -0.026409617540077385, + "nauc_precision_at_100_std": 0.13262271403381326, + "nauc_precision_at_10_diff1": 0.06346927823987127, + "nauc_precision_at_10_max": -0.002707515184037891, + "nauc_precision_at_10_std": 0.11923799302387975, + "nauc_precision_at_1_diff1": 0.18609491751428958, + "nauc_precision_at_1_max": 0.0273272028034571, + "nauc_precision_at_1_std": 0.20673870445804987, + "nauc_precision_at_20_diff1": 0.06111979799665507, + "nauc_precision_at_20_max": -0.013534913419363742, + "nauc_precision_at_20_std": 0.14581662972220927, + "nauc_precision_at_3_diff1": 0.09875765158085867, + "nauc_precision_at_3_max": 0.03232539420070992, + "nauc_precision_at_3_std": 0.08209420882185922, + "nauc_precision_at_5_diff1": 0.05510633081943357, + "nauc_precision_at_5_max": 0.018745186303331978, + "nauc_precision_at_5_std": 0.08823807602697033, + "nauc_recall_at_1000_diff1": -0.02537593671523548, + "nauc_recall_at_1000_max": -0.04279887582261104, + "nauc_recall_at_1000_std": 0.14617021692202364, + "nauc_recall_at_100_diff1": 0.0071581857579646364, + "nauc_recall_at_100_max": -0.026409617540077278, + "nauc_recall_at_100_std": 0.13262271403381318, + "nauc_recall_at_10_diff1": 0.06346927823987118, + "nauc_recall_at_10_max": -0.002707515184037962, + "nauc_recall_at_10_std": 0.11923799302387973, + "nauc_recall_at_1_diff1": 0.18609491751428958, + "nauc_recall_at_1_max": 0.0273272028034571, + "nauc_recall_at_1_std": 0.20673870445804987, + "nauc_recall_at_20_diff1": 0.06111979799665506, + "nauc_recall_at_20_max": -0.013534913419363725, + "nauc_recall_at_20_std": 0.14581662972220924, + "nauc_recall_at_3_diff1": 0.09875765158085882, + "nauc_recall_at_3_max": 0.03232539420071014, + "nauc_recall_at_3_std": 0.0820942088218594, + "nauc_recall_at_5_diff1": 0.055106330819433606, + "nauc_recall_at_5_max": 0.01874518630333189, + "nauc_recall_at_5_std": 0.0882380760269702, + "ndcg_at_1": 0.01213, + "ndcg_at_10": 0.04091, + "ndcg_at_100": 0.06691, + "ndcg_at_1000": 0.09174, + "ndcg_at_20": 0.04895, + "ndcg_at_3": 0.02332, + "ndcg_at_5": 0.03131, + "precision_at_1": 0.01213, + "precision_at_10": 0.00809, + "precision_at_100": 0.00212, + "precision_at_1000": 0.00042, + "precision_at_20": 0.00566, + "precision_at_3": 0.01054, + "precision_at_5": 0.01022, + "recall_at_1": 0.01213, + "recall_at_10": 0.08088, + "recall_at_100": 0.21213, + "recall_at_1000": 0.41949, + "recall_at_20": 0.11324, + "recall_at_3": 0.03162, + "recall_at_5": 0.0511 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/dragon-plus/no_revision_available/RARbCode.json b/results/dragon-plus/no_revision_available/RARbCode.json new file mode 100644 index 000000000..115eb0a05 --- /dev/null +++ b/results/dragon-plus/no_revision_available/RARbCode.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 884.9297256469727, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.17576, + "map_at_1": 0.11388, + "map_at_10": 0.15261, + "map_at_100": 0.159, + "map_at_1000": 0.15982, + "map_at_20": 0.15599, + "map_at_3": 0.13859, + "map_at_5": 0.14657, + "mrr_at_1": 0.11388140161725067, + "mrr_at_10": 0.1526371240320027, + "mrr_at_100": 0.15902166045010097, + "mrr_at_1000": 0.15984241022176682, + "mrr_at_20": 0.15600920294819823, + "mrr_at_3": 0.1385893980233603, + "mrr_at_5": 0.14670934411500444, + "nauc_map_at_1000_diff1": 0.3348161503254674, + "nauc_map_at_1000_max": -0.18698490514064084, + "nauc_map_at_1000_std": 0.167926971004469, + "nauc_map_at_100_diff1": 0.3346068289049779, + "nauc_map_at_100_max": -0.18658231532238484, + "nauc_map_at_100_std": 0.16752599296869722, + "nauc_map_at_10_diff1": 0.34033579117806817, + "nauc_map_at_10_max": -0.18764681166193978, + "nauc_map_at_10_std": 0.1646096731097932, + "nauc_map_at_1_diff1": 0.4222015432593503, + "nauc_map_at_1_max": -0.17229856256941298, + "nauc_map_at_1_std": 0.17171195709791257, + "nauc_map_at_20_diff1": 0.33693949968566583, + "nauc_map_at_20_max": -0.18728899397839383, + "nauc_map_at_20_std": 0.16504522188554682, + "nauc_map_at_3_diff1": 0.360547850505415, + "nauc_map_at_3_max": -0.18204522985754087, + "nauc_map_at_3_std": 0.1590004335162215, + "nauc_map_at_5_diff1": 0.34558668163886924, + "nauc_map_at_5_max": -0.1848312901468148, + "nauc_map_at_5_std": 0.1612787176595853, + "nauc_mrr_at_1000_diff1": 0.33478609798429426, + "nauc_mrr_at_1000_max": -0.18707129322465924, + "nauc_mrr_at_1000_std": 0.1678832738010047, + "nauc_mrr_at_100_diff1": 0.3345767903783509, + "nauc_mrr_at_100_max": -0.18666866479840416, + "nauc_mrr_at_100_std": 0.16748233491978826, + "nauc_mrr_at_10_diff1": 0.34030513390949885, + "nauc_mrr_at_10_max": -0.18773397675538628, + "nauc_mrr_at_10_std": 0.164565733308597, + "nauc_mrr_at_1_diff1": 0.4222015432593503, + "nauc_mrr_at_1_max": -0.17229856256941298, + "nauc_mrr_at_1_std": 0.17171195709791257, + "nauc_mrr_at_20_diff1": 0.3369092781656182, + "nauc_mrr_at_20_max": -0.1873754656931815, + "nauc_mrr_at_20_std": 0.16500161771439367, + "nauc_mrr_at_3_diff1": 0.360547850505415, + "nauc_mrr_at_3_max": -0.18204522985754087, + "nauc_mrr_at_3_std": 0.1590004335162215, + "nauc_mrr_at_5_diff1": 0.34539827654506733, + "nauc_mrr_at_5_max": -0.18536291468659657, + "nauc_mrr_at_5_std": 0.161012314992662, + "nauc_ndcg_at_1000_diff1": 0.28617514040348935, + "nauc_ndcg_at_1000_max": -0.2030908237349141, + "nauc_ndcg_at_1000_std": 0.1924511211267081, + "nauc_ndcg_at_100_diff1": 0.2832859854542661, + "nauc_ndcg_at_100_max": -0.19197275293638633, + "nauc_ndcg_at_100_std": 0.18559791450736166, + "nauc_ndcg_at_10_diff1": 0.3089516983017786, + "nauc_ndcg_at_10_max": -0.19631935990062888, + "nauc_ndcg_at_10_std": 0.16653559591632264, + "nauc_ndcg_at_1_diff1": 0.4222015432593503, + "nauc_ndcg_at_1_max": -0.17229856256941298, + "nauc_ndcg_at_1_std": 0.17171195709791257, + "nauc_ndcg_at_20_diff1": 0.29848328347426684, + "nauc_ndcg_at_20_max": -0.19531024675083763, + "nauc_ndcg_at_20_std": 0.16765870176109535, + "nauc_ndcg_at_3_diff1": 0.34384469246909644, + "nauc_ndcg_at_3_max": -0.18470315138548857, + "nauc_ndcg_at_3_std": 0.15470172330660878, + "nauc_ndcg_at_5_diff1": 0.3200060964659145, + "nauc_ndcg_at_5_max": -0.18982435097312297, + "nauc_ndcg_at_5_std": 0.15928145469840954, + "nauc_precision_at_1000_diff1": 0.14432907602098993, + "nauc_precision_at_1000_max": -0.2803102154333895, + "nauc_precision_at_1000_std": 0.3009086127099, + "nauc_precision_at_100_diff1": 0.15484908886352955, + "nauc_precision_at_100_max": -0.20175955999815037, + "nauc_precision_at_100_std": 0.247913150909398, + "nauc_precision_at_10_diff1": 0.2374259267107325, + "nauc_precision_at_10_max": -0.21753583495195764, + "nauc_precision_at_10_std": 0.17303396576066704, + "nauc_precision_at_1_diff1": 0.4222015432593503, + "nauc_precision_at_1_max": -0.17229856256941298, + "nauc_precision_at_1_std": 0.17171195709791257, + "nauc_precision_at_20_diff1": 0.21183016090162785, + "nauc_precision_at_20_max": -0.2134878603403194, + "nauc_precision_at_20_std": 0.1754102750975114, + "nauc_precision_at_3_diff1": 0.3023604899443388, + "nauc_precision_at_3_max": -0.19130917078591916, + "nauc_precision_at_3_std": 0.1437906604512952, + "nauc_precision_at_5_diff1": 0.26000088947202626, + "nauc_precision_at_5_max": -0.2019710586946008, + "nauc_precision_at_5_std": 0.15535841887815255, + "nauc_recall_at_1000_diff1": 0.14432907602099015, + "nauc_recall_at_1000_max": -0.28031021543338874, + "nauc_recall_at_1000_std": 0.3009086127099001, + "nauc_recall_at_100_diff1": 0.1548490888635295, + "nauc_recall_at_100_max": -0.20175955999815048, + "nauc_recall_at_100_std": 0.24791315090939814, + "nauc_recall_at_10_diff1": 0.2374259267107324, + "nauc_recall_at_10_max": -0.21753583495195755, + "nauc_recall_at_10_std": 0.17303396576066699, + "nauc_recall_at_1_diff1": 0.4222015432593503, + "nauc_recall_at_1_max": -0.17229856256941298, + "nauc_recall_at_1_std": 0.17171195709791257, + "nauc_recall_at_20_diff1": 0.21183016090162773, + "nauc_recall_at_20_max": -0.21348786034031958, + "nauc_recall_at_20_std": 0.17541027509751117, + "nauc_recall_at_3_diff1": 0.3023604899443388, + "nauc_recall_at_3_max": -0.19130917078591902, + "nauc_recall_at_3_std": 0.1437906604512954, + "nauc_recall_at_5_diff1": 0.26000088947202626, + "nauc_recall_at_5_max": -0.20197105869460075, + "nauc_recall_at_5_std": 0.15535841887815255, + "ndcg_at_1": 0.11388, + "ndcg_at_10": 0.17576, + "ndcg_at_100": 0.21129, + "ndcg_at_1000": 0.23626, + "ndcg_at_20": 0.18804, + "ndcg_at_3": 0.14661, + "ndcg_at_5": 0.16102, + "precision_at_1": 0.11388, + "precision_at_10": 0.02507, + "precision_at_100": 0.00427, + "precision_at_1000": 0.00063, + "precision_at_20": 0.01496, + "precision_at_3": 0.0566, + "precision_at_5": 0.04097, + "recall_at_1": 0.11388, + "recall_at_10": 0.25067, + "recall_at_100": 0.42722, + "recall_at_1000": 0.63073, + "recall_at_20": 0.29919, + "recall_at_3": 0.16981, + "recall_at_5": 0.20485 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/dragon-plus/no_revision_available/RARbMath.json b/results/dragon-plus/no_revision_available/RARbMath.json new file mode 100644 index 000000000..0c43a4ecf --- /dev/null +++ b/results/dragon-plus/no_revision_available/RARbMath.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 1370.2824981212616, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.45089, + "map_at_1": 0.39674, + "map_at_10": 0.43057, + "map_at_100": 0.43693, + "map_at_1000": 0.43762, + "map_at_20": 0.43367, + "map_at_3": 0.41882, + "map_at_5": 0.4248, + "mrr_at_1": 0.3967399905048267, + "mrr_at_10": 0.4305652265653846, + "mrr_at_100": 0.4369255850467424, + "mrr_at_1000": 0.43762047094283846, + "mrr_at_20": 0.4336749613688122, + "mrr_at_3": 0.418816268396898, + "mrr_at_5": 0.424798227567653, + "nauc_map_at_1000_diff1": 0.81933790331564, + "nauc_map_at_1000_max": 0.3201569057475442, + "nauc_map_at_1000_std": 0.02408620377946622, + "nauc_map_at_100_diff1": 0.819172265051684, + "nauc_map_at_100_max": 0.32011919881743395, + "nauc_map_at_100_std": 0.023947237196689314, + "nauc_map_at_10_diff1": 0.8227566492496312, + "nauc_map_at_10_max": 0.3227024449950014, + "nauc_map_at_10_std": 0.02352911918728159, + "nauc_map_at_1_diff1": 0.8577554337372869, + "nauc_map_at_1_max": 0.3413435044641657, + "nauc_map_at_1_std": 0.03399264680832797, + "nauc_map_at_20_diff1": 0.8204583562540538, + "nauc_map_at_20_max": 0.3210619080668148, + "nauc_map_at_20_std": 0.023040138400725784, + "nauc_map_at_3_diff1": 0.8348481683470111, + "nauc_map_at_3_max": 0.3305830725924007, + "nauc_map_at_3_std": 0.02749849393482312, + "nauc_map_at_5_diff1": 0.8278604593317966, + "nauc_map_at_5_max": 0.32678449529995857, + "nauc_map_at_5_std": 0.024527071020035686, + "nauc_mrr_at_1000_diff1": 0.8193378953914099, + "nauc_mrr_at_1000_max": 0.32015688636286627, + "nauc_mrr_at_1000_std": 0.024086239707079477, + "nauc_mrr_at_100_diff1": 0.8191722598377701, + "nauc_mrr_at_100_max": 0.32011917985543226, + "nauc_mrr_at_100_std": 0.02394728373828766, + "nauc_mrr_at_10_diff1": 0.8227566492496312, + "nauc_mrr_at_10_max": 0.3227024449950014, + "nauc_mrr_at_10_std": 0.02352911918728159, + "nauc_mrr_at_1_diff1": 0.8577554337372869, + "nauc_mrr_at_1_max": 0.3413435044641657, + "nauc_mrr_at_1_std": 0.03399264680832797, + "nauc_mrr_at_20_diff1": 0.8204583562540538, + "nauc_mrr_at_20_max": 0.3210619080668148, + "nauc_mrr_at_20_std": 0.023040138400725784, + "nauc_mrr_at_3_diff1": 0.8348481683470111, + "nauc_mrr_at_3_max": 0.3305830725924007, + "nauc_mrr_at_3_std": 0.02749849393482312, + "nauc_mrr_at_5_diff1": 0.8278604593317966, + "nauc_mrr_at_5_max": 0.32678449529995857, + "nauc_mrr_at_5_std": 0.024527071020035686, + "nauc_ndcg_at_1000_diff1": 0.7901188546551418, + "nauc_ndcg_at_1000_max": 0.3003025756448561, + "nauc_ndcg_at_1000_std": 0.02838712700070479, + "nauc_ndcg_at_100_diff1": 0.784174016176596, + "nauc_ndcg_at_100_max": 0.29566364347035623, + "nauc_ndcg_at_100_std": 0.021507225317742577, + "nauc_ndcg_at_10_diff1": 0.8024486968373842, + "nauc_ndcg_at_10_max": 0.3100851261630225, + "nauc_ndcg_at_10_std": 0.017670093192162072, + "nauc_ndcg_at_1_diff1": 0.8577554337372869, + "nauc_ndcg_at_1_max": 0.3413435044641657, + "nauc_ndcg_at_1_std": 0.03399264680832797, + "nauc_ndcg_at_20_diff1": 0.7935628482069548, + "nauc_ndcg_at_20_max": 0.30382530762961735, + "nauc_ndcg_at_20_std": 0.015637334084238164, + "nauc_ndcg_at_3_diff1": 0.827374182141992, + "nauc_ndcg_at_3_max": 0.326938556648087, + "nauc_ndcg_at_3_std": 0.025399594179749466, + "nauc_ndcg_at_5_diff1": 0.8148245982886253, + "nauc_ndcg_at_5_max": 0.31999936900249915, + "nauc_ndcg_at_5_std": 0.019954022570589744, + "nauc_precision_at_1000_diff1": 0.5320718521860633, + "nauc_precision_at_1000_max": 0.12863584986293122, + "nauc_precision_at_1000_std": 0.18248998400091276, + "nauc_precision_at_100_diff1": 0.6056333453609815, + "nauc_precision_at_100_max": 0.1635114484313615, + "nauc_precision_at_100_std": 0.02061405053939103, + "nauc_precision_at_10_diff1": 0.7347651486750955, + "nauc_precision_at_10_max": 0.26711751300721204, + "nauc_precision_at_10_std": -0.0015588803650624088, + "nauc_precision_at_1_diff1": 0.8577554337372869, + "nauc_precision_at_1_max": 0.3413435044641657, + "nauc_precision_at_1_std": 0.03399264680832797, + "nauc_precision_at_20_diff1": 0.6935129204992327, + "nauc_precision_at_20_max": 0.2384037769214232, + "nauc_precision_at_20_std": -0.011471166863321306, + "nauc_precision_at_3_diff1": 0.8055833562896962, + "nauc_precision_at_3_max": 0.31627135875962387, + "nauc_precision_at_3_std": 0.019286315189504386, + "nauc_precision_at_5_diff1": 0.7748407981915492, + "nauc_precision_at_5_max": 0.29900642001541305, + "nauc_precision_at_5_std": 0.0057112206874499, + "nauc_recall_at_1000_diff1": 0.5320718521860645, + "nauc_recall_at_1000_max": 0.12863584986293392, + "nauc_recall_at_1000_std": 0.1824899840009135, + "nauc_recall_at_100_diff1": 0.6056333453609813, + "nauc_recall_at_100_max": 0.16351144843136037, + "nauc_recall_at_100_std": 0.020614050539389698, + "nauc_recall_at_10_diff1": 0.7347651486750956, + "nauc_recall_at_10_max": 0.2671175130072119, + "nauc_recall_at_10_std": -0.0015588803650618864, + "nauc_recall_at_1_diff1": 0.8577554337372869, + "nauc_recall_at_1_max": 0.3413435044641657, + "nauc_recall_at_1_std": 0.03399264680832797, + "nauc_recall_at_20_diff1": 0.6935129204992329, + "nauc_recall_at_20_max": 0.2384037769214231, + "nauc_recall_at_20_std": -0.0114711668633213, + "nauc_recall_at_3_diff1": 0.8055833562896965, + "nauc_recall_at_3_max": 0.31627135875962376, + "nauc_recall_at_3_std": 0.019286315189504112, + "nauc_recall_at_5_diff1": 0.7748407981915487, + "nauc_recall_at_5_max": 0.2990064200154132, + "nauc_recall_at_5_std": 0.005711220687450082, + "ndcg_at_1": 0.39674, + "ndcg_at_10": 0.45089, + "ndcg_at_100": 0.48678, + "ndcg_at_1000": 0.50905, + "ndcg_at_20": 0.46235, + "ndcg_at_3": 0.42607, + "ndcg_at_5": 0.4368, + "precision_at_1": 0.39674, + "precision_at_10": 0.05169, + "precision_at_100": 0.00696, + "precision_at_1000": 0.00088, + "precision_at_20": 0.02812, + "precision_at_3": 0.14902, + "precision_at_5": 0.0946, + "recall_at_1": 0.39674, + "recall_at_10": 0.51685, + "recall_at_100": 0.696, + "recall_at_1000": 0.87941, + "recall_at_20": 0.56243, + "recall_at_3": 0.44706, + "recall_at_5": 0.47302 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/dragon-plus/no_revision_available/SIQA.json b/results/dragon-plus/no_revision_available/SIQA.json new file mode 100644 index 000000000..0b240a692 --- /dev/null +++ b/results/dragon-plus/no_revision_available/SIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 13.317318201065063, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02002, + "map_at_1": 0.01279, + "map_at_10": 0.01748, + "map_at_100": 0.0185, + "map_at_1000": 0.01906, + "map_at_20": 0.01782, + "map_at_3": 0.01604, + "map_at_5": 0.01693, + "mrr_at_1": 0.0127942681678608, + "mrr_at_10": 0.01747737648454127, + "mrr_at_100": 0.018504333102922474, + "mrr_at_1000": 0.019060545519492232, + "mrr_at_20": 0.017824575815943048, + "mrr_at_3": 0.01603548277038553, + "mrr_at_5": 0.016931081542135788, + "nauc_map_at_1000_diff1": 0.2770314938547433, + "nauc_map_at_1000_max": 0.00763697936497271, + "nauc_map_at_1000_std": -0.2756001903887372, + "nauc_map_at_100_diff1": 0.28295756973324143, + "nauc_map_at_100_max": 0.007460905197079196, + "nauc_map_at_100_std": -0.2785657261557506, + "nauc_map_at_10_diff1": 0.29482378216452537, + "nauc_map_at_10_max": 0.006889286556730222, + "nauc_map_at_10_std": -0.28038205640082287, + "nauc_map_at_1_diff1": 0.3741051950392871, + "nauc_map_at_1_max": -0.13118431453893206, + "nauc_map_at_1_std": -0.2703268649483305, + "nauc_map_at_20_diff1": 0.29112601734688703, + "nauc_map_at_20_max": 0.009674270178210875, + "nauc_map_at_20_std": -0.2798797409034542, + "nauc_map_at_3_diff1": 0.32518288417545665, + "nauc_map_at_3_max": -0.005730842111903754, + "nauc_map_at_3_std": -0.2705034746856464, + "nauc_map_at_5_diff1": 0.305456264774814, + "nauc_map_at_5_max": -0.0008370571433337167, + "nauc_map_at_5_std": -0.2826083656012021, + "nauc_mrr_at_1000_diff1": 0.2770312045585099, + "nauc_mrr_at_1000_max": 0.007636419071067198, + "nauc_mrr_at_1000_std": -0.2756002980910242, + "nauc_mrr_at_100_diff1": 0.28295756973324143, + "nauc_mrr_at_100_max": 0.007460905197079196, + "nauc_mrr_at_100_std": -0.2785657261557506, + "nauc_mrr_at_10_diff1": 0.29482378216452537, + "nauc_mrr_at_10_max": 0.006889286556730222, + "nauc_mrr_at_10_std": -0.28038205640082287, + "nauc_mrr_at_1_diff1": 0.3741051950392871, + "nauc_mrr_at_1_max": -0.13118431453893206, + "nauc_mrr_at_1_std": -0.2703268649483305, + "nauc_mrr_at_20_diff1": 0.29112601734688703, + "nauc_mrr_at_20_max": 0.009674270178210875, + "nauc_mrr_at_20_std": -0.2798797409034542, + "nauc_mrr_at_3_diff1": 0.32518288417545665, + "nauc_mrr_at_3_max": -0.005730842111903754, + "nauc_mrr_at_3_std": -0.2705034746856464, + "nauc_mrr_at_5_diff1": 0.305456264774814, + "nauc_mrr_at_5_max": -0.0008370571433337167, + "nauc_mrr_at_5_std": -0.2826083656012021, + "nauc_ndcg_at_1000_diff1": 0.15654394978162461, + "nauc_ndcg_at_1000_max": 0.02329175873087817, + "nauc_ndcg_at_1000_std": -0.19488397700761956, + "nauc_ndcg_at_100_diff1": 0.21959152102565496, + "nauc_ndcg_at_100_max": 0.021530940141856414, + "nauc_ndcg_at_100_std": -0.2749388279327059, + "nauc_ndcg_at_10_diff1": 0.2620258985157016, + "nauc_ndcg_at_10_max": 0.04290286634318879, + "nauc_ndcg_at_10_std": -0.2863721850776478, + "nauc_ndcg_at_1_diff1": 0.3741051950392871, + "nauc_ndcg_at_1_max": -0.13118431453893206, + "nauc_ndcg_at_1_std": -0.2703268649483305, + "nauc_ndcg_at_20_diff1": 0.25202455303125976, + "nauc_ndcg_at_20_max": 0.04930621816395165, + "nauc_ndcg_at_20_std": -0.28407016131416285, + "nauc_ndcg_at_3_diff1": 0.3124124037856468, + "nauc_ndcg_at_3_max": 0.023528918129411915, + "nauc_ndcg_at_3_std": -0.26970095584917764, + "nauc_ndcg_at_5_diff1": 0.28163259405407925, + "nauc_ndcg_at_5_max": 0.0291296596741042, + "nauc_ndcg_at_5_std": -0.2898709576280079, + "nauc_precision_at_1000_diff1": 0.08201529990856365, + "nauc_precision_at_1000_max": 0.024123082410471546, + "nauc_precision_at_1000_std": -0.11133178567644414, + "nauc_precision_at_100_diff1": 0.14410614154414683, + "nauc_precision_at_100_max": 0.013217224034257218, + "nauc_precision_at_100_std": -0.26540207957846845, + "nauc_precision_at_10_diff1": 0.19650083368436588, + "nauc_precision_at_10_max": 0.11081342057464721, + "nauc_precision_at_10_std": -0.29908039698108313, + "nauc_precision_at_1_diff1": 0.3741051950392871, + "nauc_precision_at_1_max": -0.13118431453893206, + "nauc_precision_at_1_std": -0.2703268649483305, + "nauc_precision_at_20_diff1": 0.18034718074511602, + "nauc_precision_at_20_max": 0.11650600961449345, + "nauc_precision_at_20_std": -0.2908189369684112, + "nauc_precision_at_3_diff1": 0.282505425979169, + "nauc_precision_at_3_max": 0.09119871440405798, + "nauc_precision_at_3_std": -0.2676139862373594, + "nauc_precision_at_5_diff1": 0.230055326488182, + "nauc_precision_at_5_max": 0.09050212521088803, + "nauc_precision_at_5_std": -0.30665789571185936, + "nauc_recall_at_1000_diff1": 0.08201529990856385, + "nauc_recall_at_1000_max": 0.02412308241047198, + "nauc_recall_at_1000_std": -0.1113317856764438, + "nauc_recall_at_100_diff1": 0.14410614154414683, + "nauc_recall_at_100_max": 0.013217224034257279, + "nauc_recall_at_100_std": -0.26540207957846834, + "nauc_recall_at_10_diff1": 0.19650083368436577, + "nauc_recall_at_10_max": 0.1108134205746471, + "nauc_recall_at_10_std": -0.2990803969810831, + "nauc_recall_at_1_diff1": 0.3741051950392871, + "nauc_recall_at_1_max": -0.13118431453893206, + "nauc_recall_at_1_std": -0.2703268649483305, + "nauc_recall_at_20_diff1": 0.18034718074511566, + "nauc_recall_at_20_max": 0.11650600961449337, + "nauc_recall_at_20_std": -0.29081893696841127, + "nauc_recall_at_3_diff1": 0.282505425979169, + "nauc_recall_at_3_max": 0.09119871440405805, + "nauc_recall_at_3_std": -0.2676139862373594, + "nauc_recall_at_5_diff1": 0.23005532648818183, + "nauc_recall_at_5_max": 0.09050212521088775, + "nauc_recall_at_5_std": -0.3066578957118596, + "ndcg_at_1": 0.01279, + "ndcg_at_10": 0.02002, + "ndcg_at_100": 0.02699, + "ndcg_at_1000": 0.05138, + "ndcg_at_20": 0.02131, + "ndcg_at_3": 0.01705, + "ndcg_at_5": 0.0187, + "precision_at_1": 0.01279, + "precision_at_10": 0.00281, + "precision_at_100": 0.00066, + "precision_at_1000": 0.00028, + "precision_at_20": 0.00166, + "precision_at_3": 0.00665, + "precision_at_5": 0.00481, + "recall_at_1": 0.01279, + "recall_at_10": 0.02815, + "recall_at_100": 0.06551, + "recall_at_1000": 0.27943, + "recall_at_20": 0.03327, + "recall_at_3": 0.01996, + "recall_at_5": 0.02405 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/dragon-plus/no_revision_available/SpartQA.json b/results/dragon-plus/no_revision_available/SpartQA.json new file mode 100644 index 000000000..99fd59262 --- /dev/null +++ b/results/dragon-plus/no_revision_available/SpartQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 10.95421314239502, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.10343, + "map_at_1": 0.03061, + "map_at_10": 0.07052, + "map_at_100": 0.07925, + "map_at_1000": 0.08058, + "map_at_20": 0.0762, + "map_at_3": 0.05288, + "map_at_5": 0.06143, + "mrr_at_1": 0.04006677796327212, + "mrr_at_10": 0.09205885470493122, + "mrr_at_100": 0.10210854604714593, + "mrr_at_1000": 0.10337817467725365, + "mrr_at_20": 0.09877591163974643, + "mrr_at_3": 0.07062697087738833, + "mrr_at_5": 0.08121406047115545, + "nauc_map_at_1000_diff1": -0.18000928316969605, + "nauc_map_at_1000_max": 0.3272090408529495, + "nauc_map_at_1000_std": 0.4054442265477953, + "nauc_map_at_100_diff1": -0.17851775823792268, + "nauc_map_at_100_max": 0.3283970597092301, + "nauc_map_at_100_std": 0.40323122655415383, + "nauc_map_at_10_diff1": -0.18628482058253742, + "nauc_map_at_10_max": 0.3230364476504984, + "nauc_map_at_10_std": 0.38745093895921745, + "nauc_map_at_1_diff1": -0.19747548660426426, + "nauc_map_at_1_max": 0.3029078248695158, + "nauc_map_at_1_std": 0.3407078431210166, + "nauc_map_at_20_diff1": -0.18393357693270554, + "nauc_map_at_20_max": 0.3262381259621524, + "nauc_map_at_20_std": 0.3999202617994682, + "nauc_map_at_3_diff1": -0.1867462413551298, + "nauc_map_at_3_max": 0.3058401285490093, + "nauc_map_at_3_std": 0.36941563696503316, + "nauc_map_at_5_diff1": -0.18102691710439725, + "nauc_map_at_5_max": 0.3113133186432563, + "nauc_map_at_5_std": 0.3701692461848353, + "nauc_mrr_at_1000_diff1": -0.16297176219666576, + "nauc_mrr_at_1000_max": 0.29679888519566483, + "nauc_mrr_at_1000_std": 0.39013711100500836, + "nauc_mrr_at_100_diff1": -0.16144201025891353, + "nauc_mrr_at_100_max": 0.29784179883315537, + "nauc_mrr_at_100_std": 0.3889244649196762, + "nauc_mrr_at_10_diff1": -0.17461262031571173, + "nauc_mrr_at_10_max": 0.2896017181293673, + "nauc_mrr_at_10_std": 0.3821647331967955, + "nauc_mrr_at_1_diff1": -0.19861306732388095, + "nauc_mrr_at_1_max": 0.2684168072592136, + "nauc_mrr_at_1_std": 0.3434739503704007, + "nauc_mrr_at_20_diff1": -0.1682612343514382, + "nauc_mrr_at_20_max": 0.29530048306722745, + "nauc_mrr_at_20_std": 0.3892134077959744, + "nauc_mrr_at_3_diff1": -0.1854692899392885, + "nauc_mrr_at_3_max": 0.2778944664981061, + "nauc_mrr_at_3_std": 0.3729128958923524, + "nauc_mrr_at_5_diff1": -0.1750905200285906, + "nauc_mrr_at_5_max": 0.28032971579526056, + "nauc_mrr_at_5_std": 0.3714883838984472, + "nauc_ndcg_at_1000_diff1": -0.16439308789979165, + "nauc_ndcg_at_1000_max": 0.3098121345094591, + "nauc_ndcg_at_1000_std": 0.45177584878698357, + "nauc_ndcg_at_100_diff1": -0.14144712360890194, + "nauc_ndcg_at_100_max": 0.339293873189398, + "nauc_ndcg_at_100_std": 0.445484052080243, + "nauc_ndcg_at_10_diff1": -0.17942614373887963, + "nauc_ndcg_at_10_max": 0.32479563598048106, + "nauc_ndcg_at_10_std": 0.40115611366531745, + "nauc_ndcg_at_1_diff1": -0.19861306732388095, + "nauc_ndcg_at_1_max": 0.2684168072592136, + "nauc_ndcg_at_1_std": 0.3434739503704007, + "nauc_ndcg_at_20_diff1": -0.16915483807236587, + "nauc_ndcg_at_20_max": 0.33347770786798786, + "nauc_ndcg_at_20_std": 0.4280307531589512, + "nauc_ndcg_at_3_diff1": -0.18133909907241388, + "nauc_ndcg_at_3_max": 0.2987465424116531, + "nauc_ndcg_at_3_std": 0.37313335019503857, + "nauc_ndcg_at_5_diff1": -0.17153015042018385, + "nauc_ndcg_at_5_max": 0.30521909661764235, + "nauc_ndcg_at_5_std": 0.37227623670203563, + "nauc_precision_at_1000_diff1": -0.026768575189335602, + "nauc_precision_at_1000_max": 0.006290942905529581, + "nauc_precision_at_1000_std": 0.22286259981509637, + "nauc_precision_at_100_diff1": -0.027499623912926034, + "nauc_precision_at_100_max": 0.2716562552358467, + "nauc_precision_at_100_std": 0.43363165402697784, + "nauc_precision_at_10_diff1": -0.1660576624148959, + "nauc_precision_at_10_max": 0.31848137164263424, + "nauc_precision_at_10_std": 0.4281725418096907, + "nauc_precision_at_1_diff1": -0.19861306732388095, + "nauc_precision_at_1_max": 0.2684168072592136, + "nauc_precision_at_1_std": 0.3434739503704007, + "nauc_precision_at_20_diff1": -0.12943045796789224, + "nauc_precision_at_20_max": 0.3280578095601442, + "nauc_precision_at_20_std": 0.4558724955104887, + "nauc_precision_at_3_diff1": -0.1699237073665629, + "nauc_precision_at_3_max": 0.2835271482982869, + "nauc_precision_at_3_std": 0.38720298609134557, + "nauc_precision_at_5_diff1": -0.15641375439259966, + "nauc_precision_at_5_max": 0.2899133581325759, + "nauc_precision_at_5_std": 0.3832139855163691, + "nauc_recall_at_1000_diff1": -0.14227649479315263, + "nauc_recall_at_1000_max": 0.15986130362116002, + "nauc_recall_at_1000_std": 0.40793328843281873, + "nauc_recall_at_100_diff1": -0.08769840749963342, + "nauc_recall_at_100_max": 0.33709261988572004, + "nauc_recall_at_100_std": 0.47497513484086906, + "nauc_recall_at_10_diff1": -0.17203176600447354, + "nauc_recall_at_10_max": 0.3362319688324045, + "nauc_recall_at_10_std": 0.4098478906469946, + "nauc_recall_at_1_diff1": -0.19747548660426426, + "nauc_recall_at_1_max": 0.3029078248695158, + "nauc_recall_at_1_std": 0.3407078431210166, + "nauc_recall_at_20_diff1": -0.14792668798710615, + "nauc_recall_at_20_max": 0.33418014015254244, + "nauc_recall_at_20_std": 0.4426239219928674, + "nauc_recall_at_3_diff1": -0.17144659192198272, + "nauc_recall_at_3_max": 0.3038733929961745, + "nauc_recall_at_3_std": 0.37530930215556474, + "nauc_recall_at_5_diff1": -0.1531854243766788, + "nauc_recall_at_5_max": 0.30370061353281824, + "nauc_recall_at_5_std": 0.35927805578907224, + "ndcg_at_1": 0.04007, + "ndcg_at_10": 0.10343, + "ndcg_at_100": 0.14818, + "ndcg_at_1000": 0.18995, + "ndcg_at_20": 0.1248, + "ndcg_at_3": 0.0644, + "ndcg_at_5": 0.08073, + "precision_at_1": 0.04007, + "precision_at_10": 0.02618, + "precision_at_100": 0.0059, + "precision_at_1000": 0.00113, + "precision_at_20": 0.01916, + "precision_at_3": 0.0371, + "precision_at_5": 0.03311, + "recall_at_1": 0.03061, + "recall_at_10": 0.18188, + "recall_at_100": 0.36746, + "recall_at_1000": 0.665, + "recall_at_20": 0.25756, + "recall_at_3": 0.08125, + "recall_at_5": 0.11807 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/dragon-plus/no_revision_available/TempReasonL1.json b/results/dragon-plus/no_revision_available/TempReasonL1.json new file mode 100644 index 000000000..7676e6c8b --- /dev/null +++ b/results/dragon-plus/no_revision_available/TempReasonL1.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 6.616170883178711, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01823, + "map_at_1": 0.0025, + "map_at_10": 0.01131, + "map_at_100": 0.01562, + "map_at_1000": 0.01707, + "map_at_20": 0.01318, + "map_at_3": 0.00683, + "map_at_5": 0.00833, + "mrr_at_1": 0.0025, + "mrr_at_10": 0.011312500000000003, + "mrr_at_100": 0.015616032728738552, + "mrr_at_1000": 0.01706988731368254, + "mrr_at_20": 0.01318115135316183, + "mrr_at_3": 0.006833333333333332, + "mrr_at_5": 0.008333333333333328, + "nauc_map_at_1000_diff1": 0.12402133614289207, + "nauc_map_at_1000_max": 0.0827626610717434, + "nauc_map_at_1000_std": 0.14960751696910282, + "nauc_map_at_100_diff1": 0.12496510798789234, + "nauc_map_at_100_max": 0.07971281431169808, + "nauc_map_at_100_std": 0.15313758521019957, + "nauc_map_at_10_diff1": 0.1323396530377988, + "nauc_map_at_10_max": 0.07834461960393829, + "nauc_map_at_10_std": 0.17700451217877436, + "nauc_map_at_1_diff1": -0.3192379930238798, + "nauc_map_at_1_max": 0.12693855647974225, + "nauc_map_at_1_std": 0.07888382076737309, + "nauc_map_at_20_diff1": 0.12583173524991514, + "nauc_map_at_20_max": 0.07999391462538322, + "nauc_map_at_20_std": 0.16255324486486306, + "nauc_map_at_3_diff1": 0.15033179108286926, + "nauc_map_at_3_max": 0.007175718389864416, + "nauc_map_at_3_std": 0.1724184755933956, + "nauc_map_at_5_diff1": 0.14348242554333251, + "nauc_map_at_5_max": 0.011915481620606393, + "nauc_map_at_5_std": 0.19625449423128513, + "nauc_mrr_at_1000_diff1": 0.12402102640647134, + "nauc_mrr_at_1000_max": 0.08276241283526121, + "nauc_mrr_at_1000_std": 0.14960835537681363, + "nauc_mrr_at_100_diff1": 0.12496510798789234, + "nauc_mrr_at_100_max": 0.07971281431169808, + "nauc_mrr_at_100_std": 0.15313758521019957, + "nauc_mrr_at_10_diff1": 0.1323396530377988, + "nauc_mrr_at_10_max": 0.07834461960393829, + "nauc_mrr_at_10_std": 0.17700451217877436, + "nauc_mrr_at_1_diff1": -0.3192379930238798, + "nauc_mrr_at_1_max": 0.12693855647974225, + "nauc_mrr_at_1_std": 0.07888382076737309, + "nauc_mrr_at_20_diff1": 0.12583173524991514, + "nauc_mrr_at_20_max": 0.07999391462538322, + "nauc_mrr_at_20_std": 0.16255324486486306, + "nauc_mrr_at_3_diff1": 0.15033179108286926, + "nauc_mrr_at_3_max": 0.007175718389864416, + "nauc_mrr_at_3_std": 0.1724184755933956, + "nauc_mrr_at_5_diff1": 0.14348242554333251, + "nauc_mrr_at_5_max": 0.011915481620606393, + "nauc_mrr_at_5_std": 0.19625449423128513, + "nauc_ndcg_at_1000_diff1": 0.1220546811738364, + "nauc_ndcg_at_1000_max": 0.14514873650927151, + "nauc_ndcg_at_1000_std": 0.10612967191937213, + "nauc_ndcg_at_100_diff1": 0.12198966366539568, + "nauc_ndcg_at_100_max": 0.09647145100439065, + "nauc_ndcg_at_100_std": 0.12553980583547547, + "nauc_ndcg_at_10_diff1": 0.14423769513853094, + "nauc_ndcg_at_10_max": 0.10675606078952288, + "nauc_ndcg_at_10_std": 0.18321350014775797, + "nauc_ndcg_at_1_diff1": -0.3192379930238798, + "nauc_ndcg_at_1_max": 0.12693855647974225, + "nauc_ndcg_at_1_std": 0.07888382076737309, + "nauc_ndcg_at_20_diff1": 0.1286377261477196, + "nauc_ndcg_at_20_max": 0.1012865431390094, + "nauc_ndcg_at_20_std": 0.15409874848558808, + "nauc_ndcg_at_3_diff1": 0.19175290754233687, + "nauc_ndcg_at_3_max": -0.0027449604908398374, + "nauc_ndcg_at_3_std": 0.18725009004744442, + "nauc_ndcg_at_5_diff1": 0.1735416685257033, + "nauc_ndcg_at_5_max": 0.007406169531017914, + "nauc_ndcg_at_5_std": 0.2174459194438175, + "nauc_precision_at_1000_diff1": 0.12081871475851452, + "nauc_precision_at_1000_max": 0.2170479820670521, + "nauc_precision_at_1000_std": 0.07362831887735845, + "nauc_precision_at_100_diff1": 0.11577428188634228, + "nauc_precision_at_100_max": 0.10376123398301514, + "nauc_precision_at_100_std": 0.10490087919985581, + "nauc_precision_at_10_diff1": 0.14990253474321222, + "nauc_precision_at_10_max": 0.13847986526196032, + "nauc_precision_at_10_std": 0.18752767980965993, + "nauc_precision_at_1_diff1": -0.3192379930238798, + "nauc_precision_at_1_max": 0.12693855647974225, + "nauc_precision_at_1_std": 0.07888382076737309, + "nauc_precision_at_20_diff1": 0.12524526184842788, + "nauc_precision_at_20_max": 0.117333463424153, + "nauc_precision_at_20_std": 0.14402712393589764, + "nauc_precision_at_3_diff1": 0.2562704588140596, + "nauc_precision_at_3_max": -0.01805205258921378, + "nauc_precision_at_3_std": 0.2118379393614169, + "nauc_precision_at_5_diff1": 0.2099874903738602, + "nauc_precision_at_5_max": 0.00310127221852478, + "nauc_precision_at_5_std": 0.24702504364430844, + "nauc_recall_at_1000_diff1": 0.12081871475851548, + "nauc_recall_at_1000_max": 0.21704798206705309, + "nauc_recall_at_1000_std": 0.07362831887735993, + "nauc_recall_at_100_diff1": 0.11577428188634224, + "nauc_recall_at_100_max": 0.1037612339830151, + "nauc_recall_at_100_std": 0.10490087919985568, + "nauc_recall_at_10_diff1": 0.1499025347432122, + "nauc_recall_at_10_max": 0.13847986526196013, + "nauc_recall_at_10_std": 0.18752767980965995, + "nauc_recall_at_1_diff1": -0.3192379930238798, + "nauc_recall_at_1_max": 0.12693855647974225, + "nauc_recall_at_1_std": 0.07888382076737309, + "nauc_recall_at_20_diff1": 0.12524526184842782, + "nauc_recall_at_20_max": 0.11733346342415311, + "nauc_recall_at_20_std": 0.14402712393589773, + "nauc_recall_at_3_diff1": 0.2562704588140595, + "nauc_recall_at_3_max": -0.01805205258921392, + "nauc_recall_at_3_std": 0.21183793936141668, + "nauc_recall_at_5_diff1": 0.20998749037386016, + "nauc_recall_at_5_max": 0.003101272218524719, + "nauc_recall_at_5_std": 0.24702504364430858, + "ndcg_at_1": 0.0025, + "ndcg_at_10": 0.01823, + "ndcg_at_100": 0.04411, + "ndcg_at_1000": 0.10061, + "ndcg_at_20": 0.0251, + "ndcg_at_3": 0.00829, + "ndcg_at_5": 0.01103, + "precision_at_1": 0.0025, + "precision_at_10": 0.00415, + "precision_at_100": 0.00174, + "precision_at_1000": 0.00066, + "precision_at_20": 0.00344, + "precision_at_3": 0.00417, + "precision_at_5": 0.00385, + "recall_at_1": 0.0025, + "recall_at_10": 0.0415, + "recall_at_100": 0.17425, + "recall_at_1000": 0.65925, + "recall_at_20": 0.06875, + "recall_at_3": 0.0125, + "recall_at_5": 0.01925 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/dragon-plus/no_revision_available/TempReasonL2Fact.json b/results/dragon-plus/no_revision_available/TempReasonL2Fact.json new file mode 100644 index 000000000..2c3c68486 --- /dev/null +++ b/results/dragon-plus/no_revision_available/TempReasonL2Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 23.29045581817627, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.17452, + "map_at_1": 0.06967, + "map_at_10": 0.13334, + "map_at_100": 0.14587, + "map_at_1000": 0.14689, + "map_at_20": 0.14046, + "map_at_3": 0.10784, + "map_at_5": 0.1214, + "mrr_at_1": 0.06966833425977395, + "mrr_at_10": 0.13330465779048348, + "mrr_at_100": 0.14584069211411896, + "mrr_at_1000": 0.14686387925118458, + "mrr_at_20": 0.14042583799272712, + "mrr_at_3": 0.10780680625038597, + "mrr_at_5": 0.12136989685627834, + "nauc_map_at_1000_diff1": -0.0004911244780183812, + "nauc_map_at_1000_max": 0.07543095261621284, + "nauc_map_at_1000_std": 0.1354078152667221, + "nauc_map_at_100_diff1": -0.000698396561379915, + "nauc_map_at_100_max": 0.07535231630804683, + "nauc_map_at_100_std": 0.13586976978379514, + "nauc_map_at_10_diff1": 0.005942747183590755, + "nauc_map_at_10_max": 0.07658816504155798, + "nauc_map_at_10_std": 0.12185585452158265, + "nauc_map_at_1_diff1": 0.04058341980037689, + "nauc_map_at_1_max": 0.0666870431371975, + "nauc_map_at_1_std": 0.0724739122462184, + "nauc_map_at_20_diff1": 0.0013287429033165944, + "nauc_map_at_20_max": 0.07657732193504772, + "nauc_map_at_20_std": 0.13368648671811734, + "nauc_map_at_3_diff1": 0.018487411292376986, + "nauc_map_at_3_max": 0.07964235952500336, + "nauc_map_at_3_std": 0.09386452166903052, + "nauc_map_at_5_diff1": 0.013575278622566257, + "nauc_map_at_5_max": 0.07664711955355634, + "nauc_map_at_5_std": 0.10584705075659236, + "nauc_mrr_at_1000_diff1": -0.0003759511000168848, + "nauc_mrr_at_1000_max": 0.07560411840438963, + "nauc_mrr_at_1000_std": 0.13515594794947036, + "nauc_mrr_at_100_diff1": -0.0005836652638112827, + "nauc_mrr_at_100_max": 0.0755248645171975, + "nauc_mrr_at_100_std": 0.13561884946519032, + "nauc_mrr_at_10_diff1": 0.006058919412389731, + "nauc_mrr_at_10_max": 0.07676156487020375, + "nauc_mrr_at_10_std": 0.12160099545499604, + "nauc_mrr_at_1_diff1": 0.04058341980037689, + "nauc_mrr_at_1_max": 0.0666870431371975, + "nauc_mrr_at_1_std": 0.0724739122462184, + "nauc_mrr_at_20_diff1": 0.0014434361802351154, + "nauc_mrr_at_20_max": 0.07674976942659543, + "nauc_mrr_at_20_std": 0.13343518403631255, + "nauc_mrr_at_3_diff1": 0.01861931515576051, + "nauc_mrr_at_3_max": 0.07983603833968796, + "nauc_mrr_at_3_std": 0.09357505427495492, + "nauc_mrr_at_5_diff1": 0.013696851282054806, + "nauc_mrr_at_5_max": 0.07682642914217541, + "nauc_mrr_at_5_std": 0.10558048379058861, + "nauc_ndcg_at_1000_diff1": -0.027529795051437548, + "nauc_ndcg_at_1000_max": 0.07174223212591602, + "nauc_ndcg_at_1000_std": 0.1852385997780606, + "nauc_ndcg_at_100_diff1": -0.03289194352860711, + "nauc_ndcg_at_100_max": 0.06992816569662022, + "nauc_ndcg_at_100_std": 0.195205292921706, + "nauc_ndcg_at_10_diff1": -0.010357908141860111, + "nauc_ndcg_at_10_max": 0.07563440314047265, + "nauc_ndcg_at_10_std": 0.15107968674925137, + "nauc_ndcg_at_1_diff1": 0.04058341980037689, + "nauc_ndcg_at_1_max": 0.0666870431371975, + "nauc_ndcg_at_1_std": 0.0724739122462184, + "nauc_ndcg_at_20_diff1": -0.022642268717353673, + "nauc_ndcg_at_20_max": 0.07635826968723333, + "nauc_ndcg_at_20_std": 0.1845093111997685, + "nauc_ndcg_at_3_diff1": 0.012250331533250638, + "nauc_ndcg_at_3_max": 0.08097141036684909, + "nauc_ndcg_at_3_std": 0.10004766337019909, + "nauc_ndcg_at_5_diff1": 0.004856039202206156, + "nauc_ndcg_at_5_max": 0.07626583837142115, + "nauc_ndcg_at_5_std": 0.11880965163516727, + "nauc_precision_at_1000_diff1": -0.1516238504288263, + "nauc_precision_at_1000_max": 0.05045522427927591, + "nauc_precision_at_1000_std": 0.41787051540023384, + "nauc_precision_at_100_diff1": -0.11555687785446027, + "nauc_precision_at_100_max": 0.05196121059319851, + "nauc_precision_at_100_std": 0.3472817680731818, + "nauc_precision_at_10_diff1": -0.041508366521590935, + "nauc_precision_at_10_max": 0.07303176795968773, + "nauc_precision_at_10_std": 0.20828822786198048, + "nauc_precision_at_1_diff1": 0.04058341980037689, + "nauc_precision_at_1_max": 0.0666870431371975, + "nauc_precision_at_1_std": 0.0724739122462184, + "nauc_precision_at_20_diff1": -0.06988691990260729, + "nauc_precision_at_20_max": 0.07598110428743628, + "nauc_precision_at_20_std": 0.2892736822972039, + "nauc_precision_at_3_diff1": -0.0011300345020575277, + "nauc_precision_at_3_max": 0.08341147985611921, + "nauc_precision_at_3_std": 0.11333795660630581, + "nauc_precision_at_5_diff1": -0.01209362836642062, + "nauc_precision_at_5_max": 0.07496193322542524, + "nauc_precision_at_5_std": 0.1446059533342157, + "nauc_recall_at_1000_diff1": -0.15162385042882534, + "nauc_recall_at_1000_max": 0.05045522427927619, + "nauc_recall_at_1000_std": 0.41787051540023523, + "nauc_recall_at_100_diff1": -0.11555687785446044, + "nauc_recall_at_100_max": 0.05196121059319849, + "nauc_recall_at_100_std": 0.34728176807318156, + "nauc_recall_at_10_diff1": -0.041508366521591, + "nauc_recall_at_10_max": 0.07303176795968777, + "nauc_recall_at_10_std": 0.20828822786198029, + "nauc_recall_at_1_diff1": 0.04058341980037689, + "nauc_recall_at_1_max": 0.0666870431371975, + "nauc_recall_at_1_std": 0.0724739122462184, + "nauc_recall_at_20_diff1": -0.06988691990260712, + "nauc_recall_at_20_max": 0.07598110428743637, + "nauc_recall_at_20_std": 0.2892736822972039, + "nauc_recall_at_3_diff1": -0.001130034502057561, + "nauc_recall_at_3_max": 0.08341147985611942, + "nauc_recall_at_3_std": 0.11333795660630584, + "nauc_recall_at_5_diff1": -0.01209362836642048, + "nauc_recall_at_5_max": 0.07496193322542508, + "nauc_recall_at_5_std": 0.14460595333421553, + "ndcg_at_1": 0.06967, + "ndcg_at_10": 0.17452, + "ndcg_at_100": 0.24055, + "ndcg_at_1000": 0.27047, + "ndcg_at_20": 0.20023, + "ndcg_at_3": 0.12097, + "ndcg_at_5": 0.14555, + "precision_at_1": 0.06967, + "precision_at_10": 0.03089, + "precision_at_100": 0.0063, + "precision_at_1000": 0.00087, + "precision_at_20": 0.0205, + "precision_at_3": 0.05305, + "precision_at_5": 0.04384, + "recall_at_1": 0.06967, + "recall_at_10": 0.30888, + "recall_at_100": 0.62979, + "recall_at_1000": 0.87122, + "recall_at_20": 0.41004, + "recall_at_3": 0.15916, + "recall_at_5": 0.2192 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/dragon-plus/no_revision_available/TempReasonL2Pure.json b/results/dragon-plus/no_revision_available/TempReasonL2Pure.json new file mode 100644 index 000000000..829d98f19 --- /dev/null +++ b/results/dragon-plus/no_revision_available/TempReasonL2Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 10.431001424789429, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.00554, + "map_at_1": 0.00111, + "map_at_10": 0.00369, + "map_at_100": 0.00546, + "map_at_1000": 0.0063, + "map_at_20": 0.0043, + "map_at_3": 0.00241, + "map_at_5": 0.00309, + "mrr_at_1": 0.0011117287381878821, + "mrr_at_10": 0.003687454229421989, + "mrr_at_100": 0.0054634610815452195, + "mrr_at_1000": 0.006297001846909679, + "mrr_at_20": 0.0043030225787201205, + "mrr_at_3": 0.002408745599407078, + "mrr_at_5": 0.0030943116546229394, + "nauc_map_at_1000_diff1": 0.01508995890443778, + "nauc_map_at_1000_max": -0.14913542301059513, + "nauc_map_at_1000_std": 0.29997561223242153, + "nauc_map_at_100_diff1": 0.016288653463809116, + "nauc_map_at_100_max": -0.15525487581141262, + "nauc_map_at_100_std": 0.3095514824244667, + "nauc_map_at_10_diff1": -0.007571019823757543, + "nauc_map_at_10_max": -0.17279307537876448, + "nauc_map_at_10_std": 0.3767084421411463, + "nauc_map_at_1_diff1": -0.1585056064748404, + "nauc_map_at_1_max": -0.2826150515225471, + "nauc_map_at_1_std": 0.6374220322559159, + "nauc_map_at_20_diff1": 0.017545443234931717, + "nauc_map_at_20_max": -0.16258553671999806, + "nauc_map_at_20_std": 0.33726074087907965, + "nauc_map_at_3_diff1": -0.04282003247737464, + "nauc_map_at_3_max": -0.14783989443618106, + "nauc_map_at_3_std": 0.4728855875049986, + "nauc_map_at_5_diff1": 0.019913304342413445, + "nauc_map_at_5_max": -0.14810375359482664, + "nauc_map_at_5_std": 0.4347306984245359, + "nauc_mrr_at_1000_diff1": 0.015082067076644818, + "nauc_mrr_at_1000_max": -0.14913470167158493, + "nauc_mrr_at_1000_std": 0.29997206327639736, + "nauc_mrr_at_100_diff1": 0.016280112336997343, + "nauc_mrr_at_100_max": -0.1552556108649914, + "nauc_mrr_at_100_std": 0.3095484215371621, + "nauc_mrr_at_10_diff1": -0.007571019823757543, + "nauc_mrr_at_10_max": -0.17279307537876448, + "nauc_mrr_at_10_std": 0.3767084421411463, + "nauc_mrr_at_1_diff1": -0.1585056064748404, + "nauc_mrr_at_1_max": -0.2826150515225471, + "nauc_mrr_at_1_std": 0.6374220322559159, + "nauc_mrr_at_20_diff1": 0.017545443234931717, + "nauc_mrr_at_20_max": -0.16258553671999806, + "nauc_mrr_at_20_std": 0.33726074087907965, + "nauc_mrr_at_3_diff1": -0.04282003247737464, + "nauc_mrr_at_3_max": -0.14783989443618106, + "nauc_mrr_at_3_std": 0.4728855875049986, + "nauc_mrr_at_5_diff1": 0.019913304342413445, + "nauc_mrr_at_5_max": -0.14810375359482664, + "nauc_mrr_at_5_std": 0.4347306984245359, + "nauc_ndcg_at_1000_diff1": 0.01924713698790995, + "nauc_ndcg_at_1000_max": -0.11708346455793457, + "nauc_ndcg_at_1000_std": 0.2035928610459679, + "nauc_ndcg_at_100_diff1": 0.035655552696145856, + "nauc_ndcg_at_100_max": -0.1323298967477974, + "nauc_ndcg_at_100_std": 0.22383800995550676, + "nauc_ndcg_at_10_diff1": 0.002485238334922835, + "nauc_ndcg_at_10_max": -0.18064531650421456, + "nauc_ndcg_at_10_std": 0.31654865643229485, + "nauc_ndcg_at_1_diff1": -0.1585056064748404, + "nauc_ndcg_at_1_max": -0.2826150515225471, + "nauc_ndcg_at_1_std": 0.6374220322559159, + "nauc_ndcg_at_20_diff1": 0.04820448843441268, + "nauc_ndcg_at_20_max": -0.15739092507533436, + "nauc_ndcg_at_20_std": 0.2572685303043185, + "nauc_ndcg_at_3_diff1": -0.024816794556758198, + "nauc_ndcg_at_3_max": -0.1278143667367376, + "nauc_ndcg_at_3_std": 0.45650476225227204, + "nauc_ndcg_at_5_diff1": 0.05346759468313397, + "nauc_ndcg_at_5_max": -0.13682819358820525, + "nauc_ndcg_at_5_std": 0.40752187367704173, + "nauc_precision_at_1000_diff1": 0.01609909621573746, + "nauc_precision_at_1000_max": -0.10901512137358874, + "nauc_precision_at_1000_std": 0.1819228554141281, + "nauc_precision_at_100_diff1": 0.04134441273741092, + "nauc_precision_at_100_max": -0.11980415405757963, + "nauc_precision_at_100_std": 0.19336836413697275, + "nauc_precision_at_10_diff1": 0.008816902378239663, + "nauc_precision_at_10_max": -0.19438447866308464, + "nauc_precision_at_10_std": 0.24687820727049434, + "nauc_precision_at_1_diff1": -0.1585056064748404, + "nauc_precision_at_1_max": -0.2826150515225471, + "nauc_precision_at_1_std": 0.6374220322559159, + "nauc_precision_at_20_diff1": 0.0723104269754572, + "nauc_precision_at_20_max": -0.15342695923484437, + "nauc_precision_at_20_std": 0.1915366992135061, + "nauc_precision_at_3_diff1": 0.006645274960937697, + "nauc_precision_at_3_max": -0.09298374339338426, + "nauc_precision_at_3_std": 0.4294881582958719, + "nauc_precision_at_5_diff1": 0.10006127055621306, + "nauc_precision_at_5_max": -0.1236874219513619, + "nauc_precision_at_5_std": 0.37006164622675464, + "nauc_recall_at_1000_diff1": 0.016099096215737713, + "nauc_recall_at_1000_max": -0.10901512137358862, + "nauc_recall_at_1000_std": 0.1819228554141283, + "nauc_recall_at_100_diff1": 0.041344412737410845, + "nauc_recall_at_100_max": -0.11980415405757981, + "nauc_recall_at_100_std": 0.19336836413697284, + "nauc_recall_at_10_diff1": 0.008816902378239332, + "nauc_recall_at_10_max": -0.1943844786630848, + "nauc_recall_at_10_std": 0.24687820727049392, + "nauc_recall_at_1_diff1": -0.1585056064748404, + "nauc_recall_at_1_max": -0.2826150515225471, + "nauc_recall_at_1_std": 0.6374220322559159, + "nauc_recall_at_20_diff1": 0.0723104269754569, + "nauc_recall_at_20_max": -0.15342695923484445, + "nauc_recall_at_20_std": 0.19153669921350583, + "nauc_recall_at_3_diff1": 0.006645274960937517, + "nauc_recall_at_3_max": -0.09298374339338461, + "nauc_recall_at_3_std": 0.42948815829587156, + "nauc_recall_at_5_diff1": 0.10006127055621312, + "nauc_recall_at_5_max": -0.12368742195136173, + "nauc_recall_at_5_std": 0.37006164622675475, + "ndcg_at_1": 0.00111, + "ndcg_at_10": 0.00554, + "ndcg_at_100": 0.01773, + "ndcg_at_1000": 0.04902, + "ndcg_at_20": 0.00785, + "ndcg_at_3": 0.00284, + "ndcg_at_5": 0.00406, + "precision_at_1": 0.00111, + "precision_at_10": 0.00117, + "precision_at_100": 0.00077, + "precision_at_1000": 0.00034, + "precision_at_20": 0.00105, + "precision_at_3": 0.00136, + "precision_at_5": 0.00141, + "recall_at_1": 0.00111, + "recall_at_10": 0.01167, + "recall_at_100": 0.07745, + "recall_at_1000": 0.34427, + "recall_at_20": 0.02094, + "recall_at_3": 0.00408, + "recall_at_5": 0.00704 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/dragon-plus/no_revision_available/TempReasonL3Fact.json b/results/dragon-plus/no_revision_available/TempReasonL3Fact.json new file mode 100644 index 000000000..cb1ff1af1 --- /dev/null +++ b/results/dragon-plus/no_revision_available/TempReasonL3Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 20.532850980758667, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.15712, + "map_at_1": 0.04044, + "map_at_10": 0.11206, + "map_at_100": 0.12404, + "map_at_1000": 0.12509, + "map_at_20": 0.11889, + "map_at_3": 0.08552, + "map_at_5": 0.09861, + "mrr_at_1": 0.04044283777677361, + "mrr_at_10": 0.1120579870749323, + "mrr_at_100": 0.12404120066212605, + "mrr_at_1000": 0.12509180027233532, + "mrr_at_20": 0.11888236743515082, + "mrr_at_3": 0.08551739719837306, + "mrr_at_5": 0.09861048350655177, + "nauc_map_at_1000_diff1": -0.08448479889798517, + "nauc_map_at_1000_max": 0.1138395172033553, + "nauc_map_at_1000_std": 0.2700714060374297, + "nauc_map_at_100_diff1": -0.08475663677260109, + "nauc_map_at_100_max": 0.11351365195942857, + "nauc_map_at_100_std": 0.27053059186863804, + "nauc_map_at_10_diff1": -0.0800571206024878, + "nauc_map_at_10_max": 0.1160718969132597, + "nauc_map_at_10_std": 0.25862335141654663, + "nauc_map_at_1_diff1": -0.1441110424442076, + "nauc_map_at_1_max": 0.08524713903633281, + "nauc_map_at_1_std": 0.1735110497783827, + "nauc_map_at_20_diff1": -0.08399049519180021, + "nauc_map_at_20_max": 0.11470398928027632, + "nauc_map_at_20_std": 0.26753954304105704, + "nauc_map_at_3_diff1": -0.08077990718114236, + "nauc_map_at_3_max": 0.12662108768962993, + "nauc_map_at_3_std": 0.2313921991552081, + "nauc_map_at_5_diff1": -0.0757520908886553, + "nauc_map_at_5_max": 0.12360277602814103, + "nauc_map_at_5_std": 0.2424717596519776, + "nauc_mrr_at_1000_diff1": -0.08448339610516668, + "nauc_mrr_at_1000_max": 0.1138548451003512, + "nauc_mrr_at_1000_std": 0.27007669523258593, + "nauc_mrr_at_100_diff1": -0.08475518362457377, + "nauc_mrr_at_100_max": 0.11352887690880195, + "nauc_mrr_at_100_std": 0.270535922017564, + "nauc_mrr_at_10_diff1": -0.08005561519972147, + "nauc_mrr_at_10_max": 0.11608715963582199, + "nauc_mrr_at_10_std": 0.2586285549906214, + "nauc_mrr_at_1_diff1": -0.1441110424442076, + "nauc_mrr_at_1_max": 0.08524713903633281, + "nauc_mrr_at_1_std": 0.1735110497783827, + "nauc_mrr_at_20_diff1": -0.08398904301896329, + "nauc_mrr_at_20_max": 0.11471912988483522, + "nauc_mrr_at_20_std": 0.2675448067122912, + "nauc_mrr_at_3_diff1": -0.08077990718114236, + "nauc_mrr_at_3_max": 0.12662108768962993, + "nauc_mrr_at_3_std": 0.2313921991552081, + "nauc_mrr_at_5_diff1": -0.0757520908886553, + "nauc_mrr_at_5_max": 0.12360277602814103, + "nauc_mrr_at_5_std": 0.2424717596519776, + "nauc_ndcg_at_1000_diff1": -0.08422767416248217, + "nauc_ndcg_at_1000_max": 0.1083104450415131, + "nauc_ndcg_at_1000_std": 0.31727661282527064, + "nauc_ndcg_at_100_diff1": -0.09105231242441655, + "nauc_ndcg_at_100_max": 0.10055682549686616, + "nauc_ndcg_at_100_std": 0.325410003671986, + "nauc_ndcg_at_10_diff1": -0.07604210965584512, + "nauc_ndcg_at_10_max": 0.11232265395348842, + "nauc_ndcg_at_10_std": 0.2887351816014575, + "nauc_ndcg_at_1_diff1": -0.1441110424442076, + "nauc_ndcg_at_1_max": 0.08524713903633281, + "nauc_ndcg_at_1_std": 0.1735110497783827, + "nauc_ndcg_at_20_diff1": -0.08653695056539025, + "nauc_ndcg_at_20_max": 0.10911322952089476, + "nauc_ndcg_at_20_std": 0.31216100066113184, + "nauc_ndcg_at_3_diff1": -0.07486768697003664, + "nauc_ndcg_at_3_max": 0.132128611779768, + "nauc_ndcg_at_3_std": 0.2452964628074623, + "nauc_ndcg_at_5_diff1": -0.06795986070220641, + "nauc_ndcg_at_5_max": 0.12692988426378102, + "nauc_ndcg_at_5_std": 0.25959673301917247, + "nauc_precision_at_1000_diff1": -0.06533849689303099, + "nauc_precision_at_1000_max": 0.09959557394168818, + "nauc_precision_at_1000_std": 0.4943959911507207, + "nauc_precision_at_100_diff1": -0.11261873787337, + "nauc_precision_at_100_max": 0.0633495779987957, + "nauc_precision_at_100_std": 0.4387764357679572, + "nauc_precision_at_10_diff1": -0.07167351899401814, + "nauc_precision_at_10_max": 0.1038769067699581, + "nauc_precision_at_10_std": 0.33711325735643277, + "nauc_precision_at_1_diff1": -0.1441110424442076, + "nauc_precision_at_1_max": 0.08524713903633281, + "nauc_precision_at_1_std": 0.1735110497783827, + "nauc_precision_at_20_diff1": -0.09521854310879055, + "nauc_precision_at_20_max": 0.09754758345209494, + "nauc_precision_at_20_std": 0.3874505926520348, + "nauc_precision_at_3_diff1": -0.06496875234556844, + "nauc_precision_at_3_max": 0.14189531512925235, + "nauc_precision_at_3_std": 0.27139468545023193, + "nauc_precision_at_5_diff1": -0.05581860556768657, + "nauc_precision_at_5_max": 0.1315931413535534, + "nauc_precision_at_5_std": 0.28796592860987497, + "nauc_recall_at_1000_diff1": -0.06533849689303295, + "nauc_recall_at_1000_max": 0.09959557394168607, + "nauc_recall_at_1000_std": 0.4943959911507197, + "nauc_recall_at_100_diff1": -0.11261873787337069, + "nauc_recall_at_100_max": 0.06334957799879563, + "nauc_recall_at_100_std": 0.4387764357679567, + "nauc_recall_at_10_diff1": -0.07167351899401847, + "nauc_recall_at_10_max": 0.10387690676995803, + "nauc_recall_at_10_std": 0.3371132573564324, + "nauc_recall_at_1_diff1": -0.1441110424442076, + "nauc_recall_at_1_max": 0.08524713903633281, + "nauc_recall_at_1_std": 0.1735110497783827, + "nauc_recall_at_20_diff1": -0.095218543108791, + "nauc_recall_at_20_max": 0.09754758345209491, + "nauc_recall_at_20_std": 0.3874505926520345, + "nauc_recall_at_3_diff1": -0.06496875234556841, + "nauc_recall_at_3_max": 0.1418953151292524, + "nauc_recall_at_3_std": 0.27139468545023193, + "nauc_recall_at_5_diff1": -0.05581860556768681, + "nauc_recall_at_5_max": 0.13159314135355324, + "nauc_recall_at_5_std": 0.2879659286098747, + "ndcg_at_1": 0.04044, + "ndcg_at_10": 0.15712, + "ndcg_at_100": 0.21972, + "ndcg_at_1000": 0.251, + "ndcg_at_20": 0.18186, + "ndcg_at_3": 0.10087, + "ndcg_at_5": 0.12454, + "precision_at_1": 0.04044, + "precision_at_10": 0.03039, + "precision_at_100": 0.00607, + "precision_at_1000": 0.00086, + "precision_at_20": 0.02007, + "precision_at_3": 0.0485, + "precision_at_5": 0.04062, + "recall_at_1": 0.04044, + "recall_at_10": 0.30389, + "recall_at_100": 0.60687, + "recall_at_1000": 0.86037, + "recall_at_20": 0.40149, + "recall_at_3": 0.1455, + "recall_at_5": 0.20312 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/dragon-plus/no_revision_available/TempReasonL3Pure.json b/results/dragon-plus/no_revision_available/TempReasonL3Pure.json new file mode 100644 index 000000000..98426a61b --- /dev/null +++ b/results/dragon-plus/no_revision_available/TempReasonL3Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 9.356485366821289, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07974, + "map_at_1": 0.00339, + "map_at_10": 0.05222, + "map_at_100": 0.05745, + "map_at_1000": 0.05851, + "map_at_20": 0.05467, + "map_at_3": 0.03698, + "map_at_5": 0.04593, + "mrr_at_1": 0.0033890646181653863, + "mrr_at_10": 0.05221786485342737, + "mrr_at_100": 0.057445556624399666, + "mrr_at_1000": 0.058511053944098675, + "mrr_at_20": 0.054667847169095736, + "mrr_at_3": 0.03697846061153789, + "mrr_at_5": 0.045925591203494494, + "nauc_map_at_1000_diff1": -0.32663139965821897, + "nauc_map_at_1000_max": -0.08952791081009956, + "nauc_map_at_1000_std": 0.6862739470976232, + "nauc_map_at_100_diff1": -0.32724584513218946, + "nauc_map_at_100_max": -0.0898302791473927, + "nauc_map_at_100_std": 0.6874392714107542, + "nauc_map_at_10_diff1": -0.3433385545411559, + "nauc_map_at_10_max": -0.08732214301599232, + "nauc_map_at_10_std": 0.7089824458364012, + "nauc_map_at_1_diff1": -0.5099296228812507, + "nauc_map_at_1_max": -0.0007739834258980141, + "nauc_map_at_1_std": 0.69581485758732, + "nauc_map_at_20_diff1": -0.33538228452387076, + "nauc_map_at_20_max": -0.08882496717614767, + "nauc_map_at_20_std": 0.6980005634426412, + "nauc_map_at_3_diff1": -0.3216836871266069, + "nauc_map_at_3_max": -0.07833579448988363, + "nauc_map_at_3_std": 0.6475834142206127, + "nauc_map_at_5_diff1": -0.3365771726715037, + "nauc_map_at_5_max": -0.07669935304544338, + "nauc_map_at_5_std": 0.689047331720201, + "nauc_mrr_at_1000_diff1": -0.3266313157430708, + "nauc_mrr_at_1000_max": -0.08952733861899448, + "nauc_mrr_at_1000_std": 0.6862753282251424, + "nauc_mrr_at_100_diff1": -0.32724567822323886, + "nauc_mrr_at_100_max": -0.08982963377583165, + "nauc_mrr_at_100_std": 0.6874406045926508, + "nauc_mrr_at_10_diff1": -0.3433385545411559, + "nauc_mrr_at_10_max": -0.08732214301599232, + "nauc_mrr_at_10_std": 0.7089824458364012, + "nauc_mrr_at_1_diff1": -0.5099296228812507, + "nauc_mrr_at_1_max": -0.0007739834258980141, + "nauc_mrr_at_1_std": 0.69581485758732, + "nauc_mrr_at_20_diff1": -0.33538228452387076, + "nauc_mrr_at_20_max": -0.08882496717614767, + "nauc_mrr_at_20_std": 0.6980005634426412, + "nauc_mrr_at_3_diff1": -0.3216836871266069, + "nauc_mrr_at_3_max": -0.07833579448988363, + "nauc_mrr_at_3_std": 0.6475834142206127, + "nauc_mrr_at_5_diff1": -0.3365771726715037, + "nauc_mrr_at_5_max": -0.07669935304544338, + "nauc_mrr_at_5_std": 0.689047331720201, + "nauc_ndcg_at_1000_diff1": -0.2745991432790036, + "nauc_ndcg_at_1000_max": -0.09570767577709959, + "nauc_ndcg_at_1000_std": 0.6361621233304705, + "nauc_ndcg_at_100_diff1": -0.28694782201539404, + "nauc_ndcg_at_100_max": -0.10199879088371484, + "nauc_ndcg_at_100_std": 0.654961142889804, + "nauc_ndcg_at_10_diff1": -0.3478803378786446, + "nauc_ndcg_at_10_max": -0.09582395177141755, + "nauc_ndcg_at_10_std": 0.7323610335005969, + "nauc_ndcg_at_1_diff1": -0.5099296228812507, + "nauc_ndcg_at_1_max": -0.0007739834258980141, + "nauc_ndcg_at_1_std": 0.69581485758732, + "nauc_ndcg_at_20_diff1": -0.32886258545665864, + "nauc_ndcg_at_20_max": -0.09890811038088311, + "nauc_ndcg_at_20_std": 0.7049353486791277, + "nauc_ndcg_at_3_diff1": -0.3172825542160997, + "nauc_ndcg_at_3_max": -0.08292892821431022, + "nauc_ndcg_at_3_std": 0.6479741117424644, + "nauc_ndcg_at_5_diff1": -0.3376850282893099, + "nauc_ndcg_at_5_max": -0.08005281402237435, + "nauc_ndcg_at_5_std": 0.7030046904763474, + "nauc_precision_at_1000_diff1": -0.16525417288097996, + "nauc_precision_at_1000_max": -0.09305695948420782, + "nauc_precision_at_1000_std": 0.5164595059042382, + "nauc_precision_at_100_diff1": -0.2212473925187627, + "nauc_precision_at_100_max": -0.11550774121176549, + "nauc_precision_at_100_std": 0.5930822771413365, + "nauc_precision_at_10_diff1": -0.3544921616399267, + "nauc_precision_at_10_max": -0.10615289378890543, + "nauc_precision_at_10_std": 0.7620685406974003, + "nauc_precision_at_1_diff1": -0.5099296228812507, + "nauc_precision_at_1_max": -0.0007739834258980141, + "nauc_precision_at_1_std": 0.69581485758732, + "nauc_precision_at_20_diff1": -0.3188119731695775, + "nauc_precision_at_20_max": -0.11062489404136708, + "nauc_precision_at_20_std": 0.7080062638844563, + "nauc_precision_at_3_diff1": -0.31157661950305343, + "nauc_precision_at_3_max": -0.08936912191844205, + "nauc_precision_at_3_std": 0.6487457344681189, + "nauc_precision_at_5_diff1": -0.34018202022920174, + "nauc_precision_at_5_max": -0.08408650327584544, + "nauc_precision_at_5_std": 0.7226058517615978, + "nauc_recall_at_1000_diff1": -0.16525417288097974, + "nauc_recall_at_1000_max": -0.09305695948420742, + "nauc_recall_at_1000_std": 0.5164595059042382, + "nauc_recall_at_100_diff1": -0.22124739251876288, + "nauc_recall_at_100_max": -0.11550774121176563, + "nauc_recall_at_100_std": 0.5930822771413363, + "nauc_recall_at_10_diff1": -0.3544921616399266, + "nauc_recall_at_10_max": -0.10615289378890524, + "nauc_recall_at_10_std": 0.7620685406974002, + "nauc_recall_at_1_diff1": -0.5099296228812507, + "nauc_recall_at_1_max": -0.0007739834258980141, + "nauc_recall_at_1_std": 0.69581485758732, + "nauc_recall_at_20_diff1": -0.3188119731695777, + "nauc_recall_at_20_max": -0.1106248940413672, + "nauc_recall_at_20_std": 0.7080062638844562, + "nauc_recall_at_3_diff1": -0.3115766195030534, + "nauc_recall_at_3_max": -0.08936912191844208, + "nauc_recall_at_3_std": 0.6487457344681192, + "nauc_recall_at_5_diff1": -0.34018202022920185, + "nauc_recall_at_5_max": -0.08408650327584563, + "nauc_recall_at_5_std": 0.7226058517615978, + "ndcg_at_1": 0.00339, + "ndcg_at_10": 0.07974, + "ndcg_at_100": 0.11065, + "ndcg_at_1000": 0.14602, + "ndcg_at_20": 0.08851, + "ndcg_at_3": 0.04866, + "ndcg_at_5": 0.06482, + "precision_at_1": 0.00339, + "precision_at_10": 0.01674, + "precision_at_100": 0.00325, + "precision_at_1000": 0.00062, + "precision_at_20": 0.01009, + "precision_at_3": 0.02756, + "precision_at_5": 0.0244, + "recall_at_1": 0.00339, + "recall_at_10": 0.16742, + "recall_at_100": 0.32535, + "recall_at_1000": 0.6193, + "recall_at_20": 0.20176, + "recall_at_3": 0.08269, + "recall_at_5": 0.12201 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/dragon-plus/no_revision_available/WinoGrande.json b/results/dragon-plus/no_revision_available/WinoGrande.json new file mode 100644 index 000000000..afbf2e683 --- /dev/null +++ b/results/dragon-plus/no_revision_available/WinoGrande.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 2.839853286743164, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.67185, + "map_at_1": 0.35517, + "map_at_10": 0.58114, + "map_at_100": 0.58415, + "map_at_1000": 0.58415, + "map_at_20": 0.58338, + "map_at_3": 0.54762, + "map_at_5": 0.57003, + "mrr_at_1": 0.35753749013417524, + "mrr_at_10": 0.582893599428722, + "mrr_at_100": 0.5858324923358585, + "mrr_at_1000": 0.5858324923358585, + "mrr_at_20": 0.585055461736226, + "mrr_at_3": 0.5495922125756384, + "mrr_at_5": 0.5719284398842415, + "nauc_map_at_1000_diff1": 0.11031625506984258, + "nauc_map_at_1000_max": 0.07600823792414033, + "nauc_map_at_1000_std": -0.2011424295809202, + "nauc_map_at_100_diff1": 0.11031625506984258, + "nauc_map_at_100_max": 0.07600823792414033, + "nauc_map_at_100_std": -0.2011424295809202, + "nauc_map_at_10_diff1": 0.10974401665346578, + "nauc_map_at_10_max": 0.07787488830259606, + "nauc_map_at_10_std": -0.20277895443632984, + "nauc_map_at_1_diff1": 0.08819052135360456, + "nauc_map_at_1_max": 0.037498741625882875, + "nauc_map_at_1_std": -0.13106267393512058, + "nauc_map_at_20_diff1": 0.1097076078720903, + "nauc_map_at_20_max": 0.07705332314910673, + "nauc_map_at_20_std": -0.20179878533886791, + "nauc_map_at_3_diff1": 0.12217632603338709, + "nauc_map_at_3_max": 0.0793022245061279, + "nauc_map_at_3_std": -0.21999930600050463, + "nauc_map_at_5_diff1": 0.11588934206122226, + "nauc_map_at_5_max": 0.07761927331908292, + "nauc_map_at_5_std": -0.21171587688857224, + "nauc_mrr_at_1000_diff1": 0.10601794080659802, + "nauc_mrr_at_1000_max": 0.07169101248836475, + "nauc_mrr_at_1000_std": -0.19812399009828427, + "nauc_mrr_at_100_diff1": 0.10601794080659802, + "nauc_mrr_at_100_max": 0.07169101248836475, + "nauc_mrr_at_100_std": -0.19812399009828427, + "nauc_mrr_at_10_diff1": 0.10521838848916053, + "nauc_mrr_at_10_max": 0.07346218091651396, + "nauc_mrr_at_10_std": -0.1997804285333286, + "nauc_mrr_at_1_diff1": 0.08142754714252469, + "nauc_mrr_at_1_max": 0.03116685147495027, + "nauc_mrr_at_1_std": -0.1266736366990877, + "nauc_mrr_at_20_diff1": 0.10540673000611633, + "nauc_mrr_at_20_max": 0.0727472329932723, + "nauc_mrr_at_20_std": -0.1987847332579416, + "nauc_mrr_at_3_diff1": 0.11782114044291381, + "nauc_mrr_at_3_max": 0.07487899110184852, + "nauc_mrr_at_3_std": -0.21855315717637255, + "nauc_mrr_at_5_diff1": 0.11244612738655384, + "nauc_mrr_at_5_max": 0.07316515065303178, + "nauc_mrr_at_5_std": -0.20932564881431429, + "nauc_ndcg_at_1000_diff1": 0.1113419286254207, + "nauc_ndcg_at_1000_max": 0.08069073441687355, + "nauc_ndcg_at_1000_std": -0.20670542703005496, + "nauc_ndcg_at_100_diff1": 0.1113419286254207, + "nauc_ndcg_at_100_max": 0.08069073441687355, + "nauc_ndcg_at_100_std": -0.20670542703005496, + "nauc_ndcg_at_10_diff1": 0.10601750740680453, + "nauc_ndcg_at_10_max": 0.09110445199903455, + "nauc_ndcg_at_10_std": -0.2130945921839936, + "nauc_ndcg_at_1_diff1": 0.08819052135360456, + "nauc_ndcg_at_1_max": 0.037498741625882875, + "nauc_ndcg_at_1_std": -0.13106267393512058, + "nauc_ndcg_at_20_diff1": 0.10726701726662846, + "nauc_ndcg_at_20_max": 0.08802285092247464, + "nauc_ndcg_at_20_std": -0.21003887914769087, + "nauc_ndcg_at_3_diff1": 0.13577964224982594, + "nauc_ndcg_at_3_max": 0.09212981736973626, + "nauc_ndcg_at_3_std": -0.2493278013501143, + "nauc_ndcg_at_5_diff1": 0.12500526962355848, + "nauc_ndcg_at_5_max": 0.08931010669064432, + "nauc_ndcg_at_5_std": -0.2353970094999871, + "nauc_precision_at_1000_diff1": 1.0, + "nauc_precision_at_1000_max": 1.0, + "nauc_precision_at_1000_std": 1.0, + "nauc_precision_at_100_diff1": 1.0, + "nauc_precision_at_100_max": 1.0, + "nauc_precision_at_100_std": 1.0, + "nauc_precision_at_10_diff1": 0.0016393266856252569, + "nauc_precision_at_10_max": 0.2724781827748728, + "nauc_precision_at_10_std": -0.30234979255637523, + "nauc_precision_at_1_diff1": 0.08819052135360456, + "nauc_precision_at_1_max": 0.037498741625882875, + "nauc_precision_at_1_std": -0.13106267393512058, + "nauc_precision_at_20_diff1": -0.07764650365717614, + "nauc_precision_at_20_max": 0.43432842939905875, + "nauc_precision_at_20_std": -0.341518869839284, + "nauc_precision_at_3_diff1": 0.19088386685688455, + "nauc_precision_at_3_max": 0.1424269807443222, + "nauc_precision_at_3_std": -0.36545851108565414, + "nauc_precision_at_5_diff1": 0.17793005245793422, + "nauc_precision_at_5_max": 0.15588710322138408, + "nauc_precision_at_5_std": -0.37065336563074813, + "nauc_recall_at_1000_diff1": NaN, + "nauc_recall_at_1000_max": NaN, + "nauc_recall_at_1000_std": NaN, + "nauc_recall_at_100_diff1": NaN, + "nauc_recall_at_100_max": NaN, + "nauc_recall_at_100_std": NaN, + "nauc_recall_at_10_diff1": 0.0016393266856183637, + "nauc_recall_at_10_max": 0.2724781827748719, + "nauc_recall_at_10_std": -0.30234979255637995, + "nauc_recall_at_1_diff1": 0.08819052135360456, + "nauc_recall_at_1_max": 0.037498741625882875, + "nauc_recall_at_1_std": -0.13106267393512058, + "nauc_recall_at_20_diff1": -0.07764650365718886, + "nauc_recall_at_20_max": 0.434328429399054, + "nauc_recall_at_20_std": -0.3415188698392792, + "nauc_recall_at_3_diff1": 0.1908838668568851, + "nauc_recall_at_3_max": 0.14242698074432297, + "nauc_recall_at_3_std": -0.36545851108565225, + "nauc_recall_at_5_diff1": 0.17793005245793347, + "nauc_recall_at_5_max": 0.15588710322138177, + "nauc_recall_at_5_std": -0.3706533656307502, + "ndcg_at_1": 0.35517, + "ndcg_at_10": 0.67185, + "ndcg_at_100": 0.68416, + "ndcg_at_1000": 0.68416, + "ndcg_at_20": 0.67989, + "ndcg_at_3": 0.60559, + "ndcg_at_5": 0.64544, + "precision_at_1": 0.35517, + "precision_at_10": 0.09479, + "precision_at_100": 0.01, + "precision_at_1000": 0.001, + "precision_at_20": 0.04897, + "precision_at_3": 0.2573, + "precision_at_5": 0.17348, + "recall_at_1": 0.35517, + "recall_at_10": 0.94791, + "recall_at_100": 1.0, + "recall_at_1000": 1.0, + "recall_at_20": 0.97948, + "recall_at_3": 0.7719, + "recall_at_5": 0.8674 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/ARCChallenge.json b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/ARCChallenge.json new file mode 100644 index 000000000..7a1ef59ed --- /dev/null +++ b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/ARCChallenge.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 69.13668990135193, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.20483, + "map_at_1": 0.11433, + "map_at_10": 0.17063, + "map_at_100": 0.18075, + "map_at_1000": 0.18188, + "map_at_20": 0.17614, + "map_at_3": 0.15131, + "map_at_5": 0.16104, + "mrr_at_1": 0.11433447098976109, + "mrr_at_10": 0.1706301803998049, + "mrr_at_100": 0.18075173032972486, + "mrr_at_1000": 0.18187863024870832, + "mrr_at_20": 0.1761357563708471, + "mrr_at_3": 0.1513083048919227, + "mrr_at_5": 0.16103526734926052, + "nauc_map_at_1000_diff1": 0.1337902500173192, + "nauc_map_at_1000_max": 0.07866378121511343, + "nauc_map_at_1000_std": -0.06225041233069145, + "nauc_map_at_100_diff1": 0.1338220079269349, + "nauc_map_at_100_max": 0.07888250919334919, + "nauc_map_at_100_std": -0.062415761077498105, + "nauc_map_at_10_diff1": 0.13499367181865793, + "nauc_map_at_10_max": 0.07715879679935932, + "nauc_map_at_10_std": -0.06811102040768705, + "nauc_map_at_1_diff1": 0.1958932320252226, + "nauc_map_at_1_max": 0.09240983554371536, + "nauc_map_at_1_std": -0.09363396079540326, + "nauc_map_at_20_diff1": 0.13509459200693652, + "nauc_map_at_20_max": 0.0790473765872642, + "nauc_map_at_20_std": -0.06550177298341626, + "nauc_map_at_3_diff1": 0.15106843600634676, + "nauc_map_at_3_max": 0.08552522192584323, + "nauc_map_at_3_std": -0.06422905653438499, + "nauc_map_at_5_diff1": 0.141102604514319, + "nauc_map_at_5_max": 0.08484391549149216, + "nauc_map_at_5_std": -0.06438591545334925, + "nauc_mrr_at_1000_diff1": 0.1337902500173192, + "nauc_mrr_at_1000_max": 0.07866378121511343, + "nauc_mrr_at_1000_std": -0.06225041233069145, + "nauc_mrr_at_100_diff1": 0.1338220079269349, + "nauc_mrr_at_100_max": 0.07888250919334919, + "nauc_mrr_at_100_std": -0.062415761077498105, + "nauc_mrr_at_10_diff1": 0.13499367181865793, + "nauc_mrr_at_10_max": 0.07715879679935932, + "nauc_mrr_at_10_std": -0.06811102040768705, + "nauc_mrr_at_1_diff1": 0.1958932320252226, + "nauc_mrr_at_1_max": 0.09240983554371536, + "nauc_mrr_at_1_std": -0.09363396079540326, + "nauc_mrr_at_20_diff1": 0.13509459200693652, + "nauc_mrr_at_20_max": 0.0790473765872642, + "nauc_mrr_at_20_std": -0.06550177298341626, + "nauc_mrr_at_3_diff1": 0.15106843600634676, + "nauc_mrr_at_3_max": 0.08552522192584323, + "nauc_mrr_at_3_std": -0.06422905653438499, + "nauc_mrr_at_5_diff1": 0.141102604514319, + "nauc_mrr_at_5_max": 0.08484391549149216, + "nauc_mrr_at_5_std": -0.06438591545334925, + "nauc_ndcg_at_1000_diff1": 0.10408423434197266, + "nauc_ndcg_at_1000_max": 0.0605742687768787, + "nauc_ndcg_at_1000_std": -0.037775921016008095, + "nauc_ndcg_at_100_diff1": 0.10193899775699326, + "nauc_ndcg_at_100_max": 0.06478935807610503, + "nauc_ndcg_at_100_std": -0.0395984379390953, + "nauc_ndcg_at_10_diff1": 0.10885902889490892, + "nauc_ndcg_at_10_max": 0.061888344862218315, + "nauc_ndcg_at_10_std": -0.06696516105283623, + "nauc_ndcg_at_1_diff1": 0.1958932320252226, + "nauc_ndcg_at_1_max": 0.09240983554371536, + "nauc_ndcg_at_1_std": -0.09363396079540326, + "nauc_ndcg_at_20_diff1": 0.11006214100065978, + "nauc_ndcg_at_20_max": 0.0679259167205363, + "nauc_ndcg_at_20_std": -0.05860245444329408, + "nauc_ndcg_at_3_diff1": 0.1375230045862512, + "nauc_ndcg_at_3_max": 0.08064667166410323, + "nauc_ndcg_at_3_std": -0.05732500831839399, + "nauc_ndcg_at_5_diff1": 0.1218424042581605, + "nauc_ndcg_at_5_max": 0.07916263183927673, + "nauc_ndcg_at_5_std": -0.05818644094568432, + "nauc_precision_at_1000_diff1": -0.04009748158847765, + "nauc_precision_at_1000_max": -0.0702656009249182, + "nauc_precision_at_1000_std": 0.14198913826282172, + "nauc_precision_at_100_diff1": 0.014412061279985114, + "nauc_precision_at_100_max": 0.02267519061126684, + "nauc_precision_at_100_std": 0.04111171097281212, + "nauc_precision_at_10_diff1": 0.05015069270243222, + "nauc_precision_at_10_max": 0.024520068917746708, + "nauc_precision_at_10_std": -0.06773972034976955, + "nauc_precision_at_1_diff1": 0.1958932320252226, + "nauc_precision_at_1_max": 0.09240983554371536, + "nauc_precision_at_1_std": -0.09363396079540326, + "nauc_precision_at_20_diff1": 0.05678878436232621, + "nauc_precision_at_20_max": 0.04347552513887974, + "nauc_precision_at_20_std": -0.043011185379652074, + "nauc_precision_at_3_diff1": 0.10537121416108922, + "nauc_precision_at_3_max": 0.06845943686068197, + "nauc_precision_at_3_std": -0.04136754299153727, + "nauc_precision_at_5_diff1": 0.0774159840124382, + "nauc_precision_at_5_max": 0.06542853896169025, + "nauc_precision_at_5_std": -0.04493953590991495, + "nauc_recall_at_1000_diff1": -0.040097481588478756, + "nauc_recall_at_1000_max": -0.07026560092491911, + "nauc_recall_at_1000_std": 0.14198913826282125, + "nauc_recall_at_100_diff1": 0.014412061279984966, + "nauc_recall_at_100_max": 0.02267519061126672, + "nauc_recall_at_100_std": 0.04111171097281195, + "nauc_recall_at_10_diff1": 0.05015069270243188, + "nauc_recall_at_10_max": 0.024520068917746433, + "nauc_recall_at_10_std": -0.06773972034976984, + "nauc_recall_at_1_diff1": 0.1958932320252226, + "nauc_recall_at_1_max": 0.09240983554371536, + "nauc_recall_at_1_std": -0.09363396079540326, + "nauc_recall_at_20_diff1": 0.056788784362326226, + "nauc_recall_at_20_max": 0.04347552513887966, + "nauc_recall_at_20_std": -0.04301118537965222, + "nauc_recall_at_3_diff1": 0.10537121416108908, + "nauc_recall_at_3_max": 0.06845943686068176, + "nauc_recall_at_3_std": -0.04136754299153745, + "nauc_recall_at_5_diff1": 0.07741598401243796, + "nauc_recall_at_5_max": 0.0654285389616901, + "nauc_recall_at_5_std": -0.04493953590991499, + "ndcg_at_1": 0.11433, + "ndcg_at_10": 0.20483, + "ndcg_at_100": 0.25992, + "ndcg_at_1000": 0.29203, + "ndcg_at_20": 0.22517, + "ndcg_at_3": 0.1639, + "ndcg_at_5": 0.18145, + "precision_at_1": 0.11433, + "precision_at_10": 0.03157, + "precision_at_100": 0.00587, + "precision_at_1000": 0.00084, + "precision_at_20": 0.01984, + "precision_at_3": 0.06684, + "precision_at_5": 0.04863, + "recall_at_1": 0.11433, + "recall_at_10": 0.3157, + "recall_at_100": 0.58703, + "recall_at_1000": 0.84386, + "recall_at_20": 0.39676, + "recall_at_3": 0.20051, + "recall_at_5": 0.24317 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/AlphaNLI.json b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/AlphaNLI.json new file mode 100644 index 000000000..f65ad2470 --- /dev/null +++ b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/AlphaNLI.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 1021.2575719356537, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.18876, + "map_at_1": 0.12076, + "map_at_10": 0.16429, + "map_at_100": 0.1725, + "map_at_1000": 0.17351, + "map_at_20": 0.16878, + "map_at_3": 0.15067, + "map_at_5": 0.15792, + "mrr_at_1": 0.12075718015665797, + "mrr_at_10": 0.16429296696920723, + "mrr_at_100": 0.17249697140911577, + "mrr_at_1000": 0.1735123779617205, + "mrr_at_20": 0.16877850089795565, + "mrr_at_3": 0.15067449956483908, + "mrr_at_5": 0.15791993037423854, + "nauc_map_at_1000_diff1": 0.33946610836009095, + "nauc_map_at_1000_max": 0.22835439985804767, + "nauc_map_at_1000_std": -0.007057936879482369, + "nauc_map_at_100_diff1": 0.33927809170099343, + "nauc_map_at_100_max": 0.22819348532649314, + "nauc_map_at_100_std": -0.007358559601857391, + "nauc_map_at_10_diff1": 0.3431794149487871, + "nauc_map_at_10_max": 0.23186789027682733, + "nauc_map_at_10_std": -0.010300384982173207, + "nauc_map_at_1_diff1": 0.4384676339455301, + "nauc_map_at_1_max": 0.2665396884669798, + "nauc_map_at_1_std": -0.017873591198354997, + "nauc_map_at_20_diff1": 0.34121603277499085, + "nauc_map_at_20_max": 0.2292438169521434, + "nauc_map_at_20_std": -0.008427389766423519, + "nauc_map_at_3_diff1": 0.3593435755546036, + "nauc_map_at_3_max": 0.24233528366517715, + "nauc_map_at_3_std": -0.012201053347356739, + "nauc_map_at_5_diff1": 0.3507099116230074, + "nauc_map_at_5_max": 0.23852681684772833, + "nauc_map_at_5_std": -0.012508073669048166, + "nauc_mrr_at_1000_diff1": 0.3394660977920746, + "nauc_mrr_at_1000_max": 0.2283543818701591, + "nauc_mrr_at_1000_std": -0.007057961318209065, + "nauc_mrr_at_100_diff1": 0.33927809170099343, + "nauc_mrr_at_100_max": 0.22819348532649314, + "nauc_mrr_at_100_std": -0.007358559601857391, + "nauc_mrr_at_10_diff1": 0.3431794149487871, + "nauc_mrr_at_10_max": 0.23186789027682733, + "nauc_mrr_at_10_std": -0.010300384982173207, + "nauc_mrr_at_1_diff1": 0.4384676339455301, + "nauc_mrr_at_1_max": 0.2665396884669798, + "nauc_mrr_at_1_std": -0.017873591198354997, + "nauc_mrr_at_20_diff1": 0.34121603277499085, + "nauc_mrr_at_20_max": 0.2292438169521434, + "nauc_mrr_at_20_std": -0.008427389766423519, + "nauc_mrr_at_3_diff1": 0.3593435755546036, + "nauc_mrr_at_3_max": 0.24233528366517715, + "nauc_mrr_at_3_std": -0.012201053347356739, + "nauc_mrr_at_5_diff1": 0.3507099116230074, + "nauc_mrr_at_5_max": 0.23852681684772833, + "nauc_mrr_at_5_std": -0.012508073669048166, + "nauc_ndcg_at_1000_diff1": 0.29891317067701284, + "nauc_ndcg_at_1000_max": 0.2059598155169217, + "nauc_ndcg_at_1000_std": 0.013022866411227754, + "nauc_ndcg_at_100_diff1": 0.29306225231257454, + "nauc_ndcg_at_100_max": 0.2020892445080802, + "nauc_ndcg_at_100_std": 0.009427752897664591, + "nauc_ndcg_at_10_diff1": 0.3091123059633984, + "nauc_ndcg_at_10_max": 0.21627064321052528, + "nauc_ndcg_at_10_std": -0.0046609879692124994, + "nauc_ndcg_at_1_diff1": 0.4384676339455301, + "nauc_ndcg_at_1_max": 0.2665396884669798, + "nauc_ndcg_at_1_std": -0.017873591198354997, + "nauc_ndcg_at_20_diff1": 0.3040565551395817, + "nauc_ndcg_at_20_max": 0.20816987635338874, + "nauc_ndcg_at_20_std": 0.00096710707906824, + "nauc_ndcg_at_3_diff1": 0.3393476231138896, + "nauc_ndcg_at_3_max": 0.2364350664014335, + "nauc_ndcg_at_3_std": -0.009297033065211173, + "nauc_ndcg_at_5_diff1": 0.32553449808187673, + "nauc_ndcg_at_5_max": 0.23081474009542347, + "nauc_ndcg_at_5_std": -0.009093966047686978, + "nauc_precision_at_1000_diff1": 0.17561103798702277, + "nauc_precision_at_1000_max": 0.1314972048647355, + "nauc_precision_at_1000_std": 0.11035336709951889, + "nauc_precision_at_100_diff1": 0.17812856616164663, + "nauc_precision_at_100_max": 0.13361378697143175, + "nauc_precision_at_100_std": 0.06211331332651912, + "nauc_precision_at_10_diff1": 0.22967797136116508, + "nauc_precision_at_10_max": 0.17840447846080804, + "nauc_precision_at_10_std": 0.009220695595576717, + "nauc_precision_at_1_diff1": 0.4384676339455301, + "nauc_precision_at_1_max": 0.2665396884669798, + "nauc_precision_at_1_std": -0.017873591198354997, + "nauc_precision_at_20_diff1": 0.22072421740695006, + "nauc_precision_at_20_max": 0.15680846129767814, + "nauc_precision_at_20_std": 0.024677654315927867, + "nauc_precision_at_3_diff1": 0.2906444524006793, + "nauc_precision_at_3_max": 0.22212572856422744, + "nauc_precision_at_3_std": -0.001806163338373157, + "nauc_precision_at_5_diff1": 0.2662205100615465, + "nauc_precision_at_5_max": 0.2128861516725413, + "nauc_precision_at_5_std": -0.0003679890785216233, + "nauc_recall_at_1000_diff1": 0.1756110379870234, + "nauc_recall_at_1000_max": 0.13149720486473554, + "nauc_recall_at_1000_std": 0.11035336709951965, + "nauc_recall_at_100_diff1": 0.1781285661616462, + "nauc_recall_at_100_max": 0.13361378697143156, + "nauc_recall_at_100_std": 0.062113313326518385, + "nauc_recall_at_10_diff1": 0.229677971361165, + "nauc_recall_at_10_max": 0.1784044784608079, + "nauc_recall_at_10_std": 0.009220695595576664, + "nauc_recall_at_1_diff1": 0.4384676339455301, + "nauc_recall_at_1_max": 0.2665396884669798, + "nauc_recall_at_1_std": -0.017873591198354997, + "nauc_recall_at_20_diff1": 0.22072421740695006, + "nauc_recall_at_20_max": 0.15680846129767792, + "nauc_recall_at_20_std": 0.024677654315927916, + "nauc_recall_at_3_diff1": 0.29064445240067965, + "nauc_recall_at_3_max": 0.2221257285642277, + "nauc_recall_at_3_std": -0.0018061633383731565, + "nauc_recall_at_5_diff1": 0.26622051006154634, + "nauc_recall_at_5_max": 0.21288615167254119, + "nauc_recall_at_5_std": -0.0003679890785217051, + "ndcg_at_1": 0.12076, + "ndcg_at_10": 0.18876, + "ndcg_at_100": 0.23366, + "ndcg_at_1000": 0.26489, + "ndcg_at_20": 0.20521, + "ndcg_at_3": 0.16011, + "ndcg_at_5": 0.17309, + "precision_at_1": 0.12076, + "precision_at_10": 0.02676, + "precision_at_100": 0.0049, + "precision_at_1000": 0.00074, + "precision_at_20": 0.01664, + "precision_at_3": 0.06245, + "precision_at_5": 0.04373, + "recall_at_1": 0.12076, + "recall_at_10": 0.26762, + "recall_at_100": 0.48956, + "recall_at_1000": 0.74478, + "recall_at_20": 0.3329, + "recall_at_3": 0.18734, + "recall_at_5": 0.21867 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/HellaSwag.json b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/HellaSwag.json new file mode 100644 index 000000000..909698bf0 --- /dev/null +++ b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/HellaSwag.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 2425.1825420856476, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.32253, + "map_at_1": 0.18751, + "map_at_10": 0.27571, + "map_at_100": 0.28464, + "map_at_1000": 0.28543, + "map_at_20": 0.28076, + "map_at_3": 0.25168, + "map_at_5": 0.26558, + "mrr_at_1": 0.18751244771957779, + "mrr_at_10": 0.2757071885382982, + "mrr_at_100": 0.2846447168637092, + "mrr_at_1000": 0.285427169877633, + "mrr_at_20": 0.2807615481966953, + "mrr_at_3": 0.25167629290314014, + "mrr_at_5": 0.2655779061275973, + "nauc_map_at_1000_diff1": 0.23354047187691637, + "nauc_map_at_1000_max": -0.07116970569503851, + "nauc_map_at_1000_std": -0.3281137175845148, + "nauc_map_at_100_diff1": 0.2334090132622773, + "nauc_map_at_100_max": -0.07154569899162559, + "nauc_map_at_100_std": -0.32848199699731245, + "nauc_map_at_10_diff1": 0.23534625918807317, + "nauc_map_at_10_max": -0.0677493157077122, + "nauc_map_at_10_std": -0.32629331451280935, + "nauc_map_at_1_diff1": 0.2725911203499127, + "nauc_map_at_1_max": -0.037984881279605136, + "nauc_map_at_1_std": -0.2752311665292973, + "nauc_map_at_20_diff1": 0.23419355645173418, + "nauc_map_at_20_max": -0.07036855047155913, + "nauc_map_at_20_std": -0.32831247408475533, + "nauc_map_at_3_diff1": 0.23947517211761993, + "nauc_map_at_3_max": -0.05662530058235545, + "nauc_map_at_3_std": -0.3118653375553111, + "nauc_map_at_5_diff1": 0.23736968691319094, + "nauc_map_at_5_max": -0.061952649117744535, + "nauc_map_at_5_std": -0.3204097170388561, + "nauc_mrr_at_1000_diff1": 0.2335404708430542, + "nauc_mrr_at_1000_max": -0.07116970812028442, + "nauc_mrr_at_1000_std": -0.32811371728363165, + "nauc_mrr_at_100_diff1": 0.2334090132622773, + "nauc_mrr_at_100_max": -0.07154569899162559, + "nauc_mrr_at_100_std": -0.32848199699731245, + "nauc_mrr_at_10_diff1": 0.23534625918807317, + "nauc_mrr_at_10_max": -0.0677493157077122, + "nauc_mrr_at_10_std": -0.32629331451280935, + "nauc_mrr_at_1_diff1": 0.2725911203499127, + "nauc_mrr_at_1_max": -0.037984881279605136, + "nauc_mrr_at_1_std": -0.2752311665292973, + "nauc_mrr_at_20_diff1": 0.23419355645173418, + "nauc_mrr_at_20_max": -0.07036855047155913, + "nauc_mrr_at_20_std": -0.32831247408475533, + "nauc_mrr_at_3_diff1": 0.23947517211761993, + "nauc_mrr_at_3_max": -0.05662530058235545, + "nauc_mrr_at_3_std": -0.3118653375553111, + "nauc_mrr_at_5_diff1": 0.23736968691319094, + "nauc_mrr_at_5_max": -0.061952649117744535, + "nauc_mrr_at_5_std": -0.3204097170388561, + "nauc_ndcg_at_1000_diff1": 0.21593065774616413, + "nauc_ndcg_at_1000_max": -0.09130596598195562, + "nauc_ndcg_at_1000_std": -0.3505507181767997, + "nauc_ndcg_at_100_diff1": 0.21272026732282376, + "nauc_ndcg_at_100_max": -0.10082678009015998, + "nauc_ndcg_at_100_std": -0.35917648281048825, + "nauc_ndcg_at_10_diff1": 0.2225563437664966, + "nauc_ndcg_at_10_max": -0.08505251767239122, + "nauc_ndcg_at_10_std": -0.35130653205819284, + "nauc_ndcg_at_1_diff1": 0.2725911203499127, + "nauc_ndcg_at_1_max": -0.037984881279605136, + "nauc_ndcg_at_1_std": -0.2752311665292973, + "nauc_ndcg_at_20_diff1": 0.21830355705446225, + "nauc_ndcg_at_20_max": -0.09449669432465646, + "nauc_ndcg_at_20_std": -0.3589349136814208, + "nauc_ndcg_at_3_diff1": 0.2308353846842339, + "nauc_ndcg_at_3_max": -0.06207786129844879, + "nauc_ndcg_at_3_std": -0.3229181932964629, + "nauc_ndcg_at_5_diff1": 0.2273595578536427, + "nauc_ndcg_at_5_max": -0.07142855743998634, + "nauc_ndcg_at_5_std": -0.33765134536989155, + "nauc_precision_at_1000_diff1": 0.07381772661579307, + "nauc_precision_at_1000_max": -0.20251845086604617, + "nauc_precision_at_1000_std": -0.46289917704781564, + "nauc_precision_at_100_diff1": 0.12167072828070796, + "nauc_precision_at_100_max": -0.23007165480117558, + "nauc_precision_at_100_std": -0.480029835086516, + "nauc_precision_at_10_diff1": 0.1880103898930653, + "nauc_precision_at_10_max": -0.13539683594461352, + "nauc_precision_at_10_std": -0.4218430222318866, + "nauc_precision_at_1_diff1": 0.2725911203499127, + "nauc_precision_at_1_max": -0.037984881279605136, + "nauc_precision_at_1_std": -0.2752311665292973, + "nauc_precision_at_20_diff1": 0.17014813819652855, + "nauc_precision_at_20_max": -0.17345988164293613, + "nauc_precision_at_20_std": -0.45465107453510156, + "nauc_precision_at_3_diff1": 0.2089437617792142, + "nauc_precision_at_3_max": -0.07606955502317768, + "nauc_precision_at_3_std": -0.351370364779125, + "nauc_precision_at_5_diff1": 0.202113859970414, + "nauc_precision_at_5_max": -0.09645856379890154, + "nauc_precision_at_5_std": -0.3828397145740712, + "nauc_recall_at_1000_diff1": 0.07381772661579364, + "nauc_recall_at_1000_max": -0.20251845086604534, + "nauc_recall_at_1000_std": -0.46289917704781397, + "nauc_recall_at_100_diff1": 0.1216707282807082, + "nauc_recall_at_100_max": -0.230071654801176, + "nauc_recall_at_100_std": -0.48002983508651625, + "nauc_recall_at_10_diff1": 0.18801038989306545, + "nauc_recall_at_10_max": -0.1353968359446134, + "nauc_recall_at_10_std": -0.4218430222318865, + "nauc_recall_at_1_diff1": 0.2725911203499127, + "nauc_recall_at_1_max": -0.037984881279605136, + "nauc_recall_at_1_std": -0.2752311665292973, + "nauc_recall_at_20_diff1": 0.17014813819652855, + "nauc_recall_at_20_max": -0.17345988164293613, + "nauc_recall_at_20_std": -0.45465107453510156, + "nauc_recall_at_3_diff1": 0.20894376177921423, + "nauc_recall_at_3_max": -0.07606955502317743, + "nauc_recall_at_3_std": -0.35137036477912503, + "nauc_recall_at_5_diff1": 0.20211385997041434, + "nauc_recall_at_5_max": -0.09645856379890128, + "nauc_recall_at_5_std": -0.38283971457407084, + "ndcg_at_1": 0.18751, + "ndcg_at_10": 0.32253, + "ndcg_at_100": 0.3701, + "ndcg_at_1000": 0.39265, + "ndcg_at_20": 0.34084, + "ndcg_at_3": 0.27299, + "ndcg_at_5": 0.29807, + "precision_at_1": 0.18751, + "precision_at_10": 0.04712, + "precision_at_100": 0.00703, + "precision_at_1000": 0.00088, + "precision_at_20": 0.02717, + "precision_at_3": 0.1116, + "precision_at_5": 0.07915, + "recall_at_1": 0.18751, + "recall_at_10": 0.47122, + "recall_at_100": 0.70345, + "recall_at_1000": 0.88468, + "recall_at_20": 0.54342, + "recall_at_3": 0.33479, + "recall_at_5": 0.39574 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/PIQA.json b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/PIQA.json new file mode 100644 index 000000000..db89b631b --- /dev/null +++ b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/PIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 334.83041858673096, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.32804, + "map_at_1": 0.19423, + "map_at_10": 0.28088, + "map_at_100": 0.29022, + "map_at_1000": 0.29093, + "map_at_20": 0.28593, + "map_at_3": 0.25426, + "map_at_5": 0.2699, + "mrr_at_1": 0.19423286180631122, + "mrr_at_10": 0.28087897473098766, + "mrr_at_100": 0.29022212282162574, + "mrr_at_1000": 0.2909300544395448, + "mrr_at_20": 0.28592660080621035, + "mrr_at_3": 0.2542618788538263, + "mrr_at_5": 0.2699038810301046, + "nauc_map_at_1000_diff1": 0.0569516836160146, + "nauc_map_at_1000_max": -0.10186749939840982, + "nauc_map_at_1000_std": -0.05401908653725594, + "nauc_map_at_100_diff1": 0.05687025707909078, + "nauc_map_at_100_max": -0.1019784680253085, + "nauc_map_at_100_std": -0.05390967513534692, + "nauc_map_at_10_diff1": 0.0579769056831052, + "nauc_map_at_10_max": -0.1006461435556538, + "nauc_map_at_10_std": -0.05929574641569058, + "nauc_map_at_1_diff1": 0.10193218383921525, + "nauc_map_at_1_max": -0.05570284949873295, + "nauc_map_at_1_std": -0.05660464317817137, + "nauc_map_at_20_diff1": 0.05713748806353312, + "nauc_map_at_20_max": -0.10167289756471311, + "nauc_map_at_20_std": -0.0559096605336951, + "nauc_map_at_3_diff1": 0.06116887750780058, + "nauc_map_at_3_max": -0.08129603152220896, + "nauc_map_at_3_std": -0.056656619959203354, + "nauc_map_at_5_diff1": 0.059721328971534954, + "nauc_map_at_5_max": -0.09409689961091562, + "nauc_map_at_5_std": -0.06077231146360233, + "nauc_mrr_at_1000_diff1": 0.056951688166200096, + "nauc_mrr_at_1000_max": -0.10186749818926144, + "nauc_mrr_at_1000_std": -0.054019089200821366, + "nauc_mrr_at_100_diff1": 0.05687025707909078, + "nauc_mrr_at_100_max": -0.1019784680253085, + "nauc_mrr_at_100_std": -0.05390967513534692, + "nauc_mrr_at_10_diff1": 0.0579769056831052, + "nauc_mrr_at_10_max": -0.1006461435556538, + "nauc_mrr_at_10_std": -0.05929574641569058, + "nauc_mrr_at_1_diff1": 0.10193218383921525, + "nauc_mrr_at_1_max": -0.05570284949873295, + "nauc_mrr_at_1_std": -0.05660464317817137, + "nauc_mrr_at_20_diff1": 0.05713748806353312, + "nauc_mrr_at_20_max": -0.10167289756471311, + "nauc_mrr_at_20_std": -0.0559096605336951, + "nauc_mrr_at_3_diff1": 0.06116887750780058, + "nauc_mrr_at_3_max": -0.08129603152220896, + "nauc_mrr_at_3_std": -0.056656619959203354, + "nauc_mrr_at_5_diff1": 0.059721328971534954, + "nauc_mrr_at_5_max": -0.09409689961091562, + "nauc_mrr_at_5_std": -0.06077231146360233, + "nauc_ndcg_at_1000_diff1": 0.0392948412666206, + "nauc_ndcg_at_1000_max": -0.13361681144463394, + "nauc_ndcg_at_1000_std": -0.04101622762895679, + "nauc_ndcg_at_100_diff1": 0.03736940822045447, + "nauc_ndcg_at_100_max": -0.13559199747206394, + "nauc_ndcg_at_100_std": -0.03663205460443955, + "nauc_ndcg_at_10_diff1": 0.04342330813738993, + "nauc_ndcg_at_10_max": -0.12754321493762236, + "nauc_ndcg_at_10_std": -0.061452897251571, + "nauc_ndcg_at_1_diff1": 0.10193218383921525, + "nauc_ndcg_at_1_max": -0.05570284949873295, + "nauc_ndcg_at_1_std": -0.05660464317817137, + "nauc_ndcg_at_20_diff1": 0.040337309494185875, + "nauc_ndcg_at_20_max": -0.131863689847467, + "nauc_ndcg_at_20_std": -0.04991473974860315, + "nauc_ndcg_at_3_diff1": 0.050283378482957004, + "nauc_ndcg_at_3_max": -0.0896996222491922, + "nauc_ndcg_at_3_std": -0.05738214818402206, + "nauc_ndcg_at_5_diff1": 0.04752198140274356, + "nauc_ndcg_at_5_max": -0.11223232917167546, + "nauc_ndcg_at_5_std": -0.06455556698218685, + "nauc_precision_at_1000_diff1": -0.11135225949226654, + "nauc_precision_at_1000_max": -0.4360074592723618, + "nauc_precision_at_1000_std": 0.10204408377994204, + "nauc_precision_at_100_diff1": -0.04853150282048244, + "nauc_precision_at_100_max": -0.2877637058771226, + "nauc_precision_at_100_std": 0.06920634052117874, + "nauc_precision_at_10_diff1": 0.003924968091921391, + "nauc_precision_at_10_max": -0.20598300124588398, + "nauc_precision_at_10_std": -0.06733165344487986, + "nauc_precision_at_1_diff1": 0.10193218383921525, + "nauc_precision_at_1_max": -0.05570284949873295, + "nauc_precision_at_1_std": -0.05660464317817137, + "nauc_precision_at_20_diff1": -0.010054984057144301, + "nauc_precision_at_20_max": -0.2279153216610879, + "nauc_precision_at_20_std": -0.0247963670018298, + "nauc_precision_at_3_diff1": 0.022268040733677285, + "nauc_precision_at_3_max": -0.11179879258364782, + "nauc_precision_at_3_std": -0.05946317252558645, + "nauc_precision_at_5_diff1": 0.01624980785406651, + "nauc_precision_at_5_max": -0.16150238659103666, + "nauc_precision_at_5_std": -0.07523966823764423, + "nauc_recall_at_1000_diff1": -0.11135225949226353, + "nauc_recall_at_1000_max": -0.43600745927235646, + "nauc_recall_at_1000_std": 0.10204408377994482, + "nauc_recall_at_100_diff1": -0.04853150282048254, + "nauc_recall_at_100_max": -0.2877637058771223, + "nauc_recall_at_100_std": 0.06920634052117854, + "nauc_recall_at_10_diff1": 0.003924968091921712, + "nauc_recall_at_10_max": -0.20598300124588384, + "nauc_recall_at_10_std": -0.06733165344487944, + "nauc_recall_at_1_diff1": 0.10193218383921525, + "nauc_recall_at_1_max": -0.05570284949873295, + "nauc_recall_at_1_std": -0.05660464317817137, + "nauc_recall_at_20_diff1": -0.0100549840571442, + "nauc_recall_at_20_max": -0.2279153216610876, + "nauc_recall_at_20_std": -0.024796367001829647, + "nauc_recall_at_3_diff1": 0.022268040733677472, + "nauc_recall_at_3_max": -0.11179879258364772, + "nauc_recall_at_3_std": -0.059463172525586215, + "nauc_recall_at_5_diff1": 0.016249807854066323, + "nauc_recall_at_5_max": -0.1615023865910364, + "nauc_recall_at_5_std": -0.0752396682376439, + "ndcg_at_1": 0.19423, + "ndcg_at_10": 0.32804, + "ndcg_at_100": 0.37792, + "ndcg_at_1000": 0.39896, + "ndcg_at_20": 0.34646, + "ndcg_at_3": 0.27378, + "ndcg_at_5": 0.30188, + "precision_at_1": 0.19423, + "precision_at_10": 0.04782, + "precision_at_100": 0.00721, + "precision_at_1000": 0.00089, + "precision_at_20": 0.02756, + "precision_at_3": 0.11008, + "precision_at_5": 0.07965, + "recall_at_1": 0.19423, + "recall_at_10": 0.47824, + "recall_at_100": 0.72144, + "recall_at_1000": 0.89173, + "recall_at_20": 0.55114, + "recall_at_3": 0.33025, + "recall_at_5": 0.39826 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/Quail.json b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/Quail.json new file mode 100644 index 000000000..69a31d8a8 --- /dev/null +++ b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/Quail.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 430.8551936149597, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.06252, + "map_at_1": 0.02574, + "map_at_10": 0.04706, + "map_at_100": 0.05238, + "map_at_1000": 0.0532, + "map_at_20": 0.05003, + "map_at_3": 0.03744, + "map_at_5": 0.04145, + "mrr_at_1": 0.025735294117647058, + "mrr_at_10": 0.047058531746031744, + "mrr_at_100": 0.05237605795167233, + "mrr_at_1000": 0.053201557702728504, + "mrr_at_20": 0.05002694128892115, + "mrr_at_3": 0.03743872549019606, + "mrr_at_5": 0.041446078431372546, + "nauc_map_at_1000_diff1": 0.1958014863635123, + "nauc_map_at_1000_max": 0.11399844329778983, + "nauc_map_at_1000_std": 0.06946102844001077, + "nauc_map_at_100_diff1": 0.1965564653860409, + "nauc_map_at_100_max": 0.11420861627050467, + "nauc_map_at_100_std": 0.06953598506499241, + "nauc_map_at_10_diff1": 0.2039824118190521, + "nauc_map_at_10_max": 0.10979765889001797, + "nauc_map_at_10_std": 0.060344950315159414, + "nauc_map_at_1_diff1": 0.26505807045114815, + "nauc_map_at_1_max": 0.09645061136877603, + "nauc_map_at_1_std": 0.026628080800337257, + "nauc_map_at_20_diff1": 0.1992735587350968, + "nauc_map_at_20_max": 0.11498528212556418, + "nauc_map_at_20_std": 0.06908771276769637, + "nauc_map_at_3_diff1": 0.2211029612282116, + "nauc_map_at_3_max": 0.09464969433913706, + "nauc_map_at_3_std": 0.05412706937520122, + "nauc_map_at_5_diff1": 0.21378854768144676, + "nauc_map_at_5_max": 0.10615068299050656, + "nauc_map_at_5_std": 0.05668343605416209, + "nauc_mrr_at_1000_diff1": 0.1958014863635123, + "nauc_mrr_at_1000_max": 0.11399844329778983, + "nauc_mrr_at_1000_std": 0.06946102844001077, + "nauc_mrr_at_100_diff1": 0.1965564653860409, + "nauc_mrr_at_100_max": 0.11420861627050467, + "nauc_mrr_at_100_std": 0.06953598506499241, + "nauc_mrr_at_10_diff1": 0.2039824118190521, + "nauc_mrr_at_10_max": 0.10979765889001797, + "nauc_mrr_at_10_std": 0.060344950315159414, + "nauc_mrr_at_1_diff1": 0.26505807045114815, + "nauc_mrr_at_1_max": 0.09645061136877603, + "nauc_mrr_at_1_std": 0.026628080800337257, + "nauc_mrr_at_20_diff1": 0.1992735587350968, + "nauc_mrr_at_20_max": 0.11498528212556418, + "nauc_mrr_at_20_std": 0.06908771276769637, + "nauc_mrr_at_3_diff1": 0.2211029612282116, + "nauc_mrr_at_3_max": 0.09464969433913706, + "nauc_mrr_at_3_std": 0.05412706937520122, + "nauc_mrr_at_5_diff1": 0.21378854768144676, + "nauc_mrr_at_5_max": 0.10615068299050656, + "nauc_mrr_at_5_std": 0.05668343605416209, + "nauc_ndcg_at_1000_diff1": 0.15434148342134119, + "nauc_ndcg_at_1000_max": 0.12433182323400105, + "nauc_ndcg_at_1000_std": 0.09086116851448006, + "nauc_ndcg_at_100_diff1": 0.16472669133244175, + "nauc_ndcg_at_100_max": 0.12743852735085662, + "nauc_ndcg_at_100_std": 0.09209300790506982, + "nauc_ndcg_at_10_diff1": 0.1868398238962617, + "nauc_ndcg_at_10_max": 0.11855497774344248, + "nauc_ndcg_at_10_std": 0.07052909787249945, + "nauc_ndcg_at_1_diff1": 0.26505807045114815, + "nauc_ndcg_at_1_max": 0.09645061136877603, + "nauc_ndcg_at_1_std": 0.026628080800337257, + "nauc_ndcg_at_20_diff1": 0.17661987064096912, + "nauc_ndcg_at_20_max": 0.13208036810378457, + "nauc_ndcg_at_20_std": 0.09172625509333025, + "nauc_ndcg_at_3_diff1": 0.2123706683074307, + "nauc_ndcg_at_3_max": 0.09288414190458376, + "nauc_ndcg_at_3_std": 0.0600572716141246, + "nauc_ndcg_at_5_diff1": 0.2032030261075941, + "nauc_ndcg_at_5_max": 0.11229790886525771, + "nauc_ndcg_at_5_std": 0.06311864669440317, + "nauc_precision_at_1000_diff1": 0.09881998039412196, + "nauc_precision_at_1000_max": 0.13100051092624312, + "nauc_precision_at_1000_std": 0.11223753914452846, + "nauc_precision_at_100_diff1": 0.12733641449252467, + "nauc_precision_at_100_max": 0.1411607586934287, + "nauc_precision_at_100_std": 0.11739811022000388, + "nauc_precision_at_10_diff1": 0.16256760783393095, + "nauc_precision_at_10_max": 0.13210412735103716, + "nauc_precision_at_10_std": 0.08554840224290977, + "nauc_precision_at_1_diff1": 0.26505807045114815, + "nauc_precision_at_1_max": 0.09645061136877603, + "nauc_precision_at_1_std": 0.026628080800337257, + "nauc_precision_at_20_diff1": 0.14763854096657944, + "nauc_precision_at_20_max": 0.15697871254568935, + "nauc_precision_at_20_std": 0.12382879466933132, + "nauc_precision_at_3_diff1": 0.19455065140267722, + "nauc_precision_at_3_max": 0.08893807948007024, + "nauc_precision_at_3_std": 0.07227290343737879, + "nauc_precision_at_5_diff1": 0.18506496200752942, + "nauc_precision_at_5_max": 0.12465458247007775, + "nauc_precision_at_5_std": 0.0742533587446304, + "nauc_recall_at_1000_diff1": 0.09881998039412204, + "nauc_recall_at_1000_max": 0.13100051092624326, + "nauc_recall_at_1000_std": 0.11223753914452857, + "nauc_recall_at_100_diff1": 0.12733641449252422, + "nauc_recall_at_100_max": 0.1411607586934285, + "nauc_recall_at_100_std": 0.1173981102200036, + "nauc_recall_at_10_diff1": 0.16256760783393087, + "nauc_recall_at_10_max": 0.13210412735103702, + "nauc_recall_at_10_std": 0.08554840224290972, + "nauc_recall_at_1_diff1": 0.26505807045114815, + "nauc_recall_at_1_max": 0.09645061136877603, + "nauc_recall_at_1_std": 0.026628080800337257, + "nauc_recall_at_20_diff1": 0.1476385409665792, + "nauc_recall_at_20_max": 0.15697871254568915, + "nauc_recall_at_20_std": 0.123828794669331, + "nauc_recall_at_3_diff1": 0.19455065140267716, + "nauc_recall_at_3_max": 0.08893807948007032, + "nauc_recall_at_3_std": 0.07227290343737897, + "nauc_recall_at_5_diff1": 0.1850649620075294, + "nauc_recall_at_5_max": 0.12465458247007763, + "nauc_recall_at_5_std": 0.07425335874463024, + "ndcg_at_1": 0.02574, + "ndcg_at_10": 0.06252, + "ndcg_at_100": 0.09198, + "ndcg_at_1000": 0.11999, + "ndcg_at_20": 0.07326, + "ndcg_at_3": 0.04141, + "ndcg_at_5": 0.04881, + "precision_at_1": 0.02574, + "precision_at_10": 0.0114, + "precision_at_100": 0.00261, + "precision_at_1000": 0.00049, + "precision_at_20": 0.00781, + "precision_at_3": 0.01765, + "precision_at_5": 0.01426, + "recall_at_1": 0.02574, + "recall_at_10": 0.11397, + "recall_at_100": 0.26066, + "recall_at_1000": 0.49449, + "recall_at_20": 0.15625, + "recall_at_3": 0.05294, + "recall_at_5": 0.07132 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/RARbCode.json b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/RARbCode.json new file mode 100644 index 000000000..7fd67dfc0 --- /dev/null +++ b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/RARbCode.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 17045.41863155365, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.79836, + "map_at_1": 0.6341, + "map_at_10": 0.74757, + "map_at_100": 0.7497, + "map_at_1000": 0.74971, + "map_at_20": 0.74918, + "map_at_3": 0.72316, + "map_at_5": 0.74078, + "mrr_at_1": 0.6340970350404312, + "mrr_at_10": 0.7475725195738677, + "mrr_at_100": 0.7496935493290456, + "mrr_at_1000": 0.7497038716736989, + "mrr_at_20": 0.7491743315434154, + "mrr_at_3": 0.7231581311769995, + "mrr_at_5": 0.7407794249775386, + "nauc_map_at_1000_diff1": 0.6016110616845028, + "nauc_map_at_1000_max": 0.45573194720301385, + "nauc_map_at_1000_std": 0.017621892718810424, + "nauc_map_at_100_diff1": 0.6016252214348548, + "nauc_map_at_100_max": 0.45575597050602595, + "nauc_map_at_100_std": 0.01765785734687929, + "nauc_map_at_10_diff1": 0.599089667165, + "nauc_map_at_10_max": 0.457496321331605, + "nauc_map_at_10_std": 0.017484702241464752, + "nauc_map_at_1_diff1": 0.638355463775883, + "nauc_map_at_1_max": 0.4446071082504682, + "nauc_map_at_1_std": 0.012264071898701377, + "nauc_map_at_20_diff1": 0.6004670227580752, + "nauc_map_at_20_max": 0.4560744398155951, + "nauc_map_at_20_std": 0.017768679791421754, + "nauc_map_at_3_diff1": 0.5944380592736077, + "nauc_map_at_3_max": 0.4525942926939192, + "nauc_map_at_3_std": 0.012789535299176456, + "nauc_map_at_5_diff1": 0.5962319305071606, + "nauc_map_at_5_max": 0.453496694342548, + "nauc_map_at_5_std": 0.012344049912633236, + "nauc_mrr_at_1000_diff1": 0.601616750357641, + "nauc_mrr_at_1000_max": 0.45574242085917016, + "nauc_mrr_at_1000_std": 0.017640797173073892, + "nauc_mrr_at_100_diff1": 0.6016309095571203, + "nauc_mrr_at_100_max": 0.4557664431873346, + "nauc_mrr_at_100_std": 0.01767676018391302, + "nauc_mrr_at_10_diff1": 0.599089667165, + "nauc_mrr_at_10_max": 0.457496321331605, + "nauc_mrr_at_10_std": 0.017484702241464752, + "nauc_mrr_at_1_diff1": 0.638355463775883, + "nauc_mrr_at_1_max": 0.4446071082504682, + "nauc_mrr_at_1_std": 0.012264071898701377, + "nauc_mrr_at_20_diff1": 0.60047401894567, + "nauc_mrr_at_20_max": 0.45608396444928867, + "nauc_mrr_at_20_std": 0.017785879559575307, + "nauc_mrr_at_3_diff1": 0.5944380592736077, + "nauc_mrr_at_3_max": 0.4525942926939192, + "nauc_mrr_at_3_std": 0.012789535299176456, + "nauc_mrr_at_5_diff1": 0.5962319305071606, + "nauc_mrr_at_5_max": 0.453496694342548, + "nauc_mrr_at_5_std": 0.012344049912633236, + "nauc_ndcg_at_1000_diff1": 0.5967061385465808, + "nauc_ndcg_at_1000_max": 0.46193516065009627, + "nauc_ndcg_at_1000_std": 0.023604060875194042, + "nauc_ndcg_at_100_diff1": 0.5973766554086164, + "nauc_ndcg_at_100_max": 0.4631235925167023, + "nauc_ndcg_at_100_std": 0.025489256939479853, + "nauc_ndcg_at_10_diff1": 0.582733216458855, + "nauc_ndcg_at_10_max": 0.47269515557536557, + "nauc_ndcg_at_10_std": 0.025258721410909124, + "nauc_ndcg_at_1_diff1": 0.638355463775883, + "nauc_ndcg_at_1_max": 0.4446071082504682, + "nauc_ndcg_at_1_std": 0.012264071898701377, + "nauc_ndcg_at_20_diff1": 0.588657764185486, + "nauc_ndcg_at_20_max": 0.4666185029208031, + "nauc_ndcg_at_20_std": 0.02694408266632946, + "nauc_ndcg_at_3_diff1": 0.5753556438705278, + "nauc_ndcg_at_3_max": 0.45872664286781556, + "nauc_ndcg_at_3_std": 0.01172515846323917, + "nauc_ndcg_at_5_diff1": 0.5762237524517811, + "nauc_ndcg_at_5_max": 0.4615677368981994, + "nauc_ndcg_at_5_std": 0.010944710776767985, + "nauc_precision_at_1000_diff1": 0.7373979785718978, + "nauc_precision_at_1000_max": 1.0, + "nauc_precision_at_1000_std": 1.0, + "nauc_precision_at_100_diff1": 0.80886544946404, + "nauc_precision_at_100_max": 0.9709600407029401, + "nauc_precision_at_100_std": 0.8905642948846083, + "nauc_precision_at_10_diff1": 0.37132120437705957, + "nauc_precision_at_10_max": 0.6994578760804712, + "nauc_precision_at_10_std": 0.15062049547636577, + "nauc_precision_at_1_diff1": 0.638355463775883, + "nauc_precision_at_1_max": 0.4446071082504682, + "nauc_precision_at_1_std": 0.012264071898701377, + "nauc_precision_at_20_diff1": 0.3452259483788484, + "nauc_precision_at_20_max": 0.7365023909426298, + "nauc_precision_at_20_std": 0.31344339550091777, + "nauc_precision_at_3_diff1": 0.4943912375781529, + "nauc_precision_at_3_max": 0.4858724469600009, + "nauc_precision_at_3_std": 0.006661835869183681, + "nauc_precision_at_5_diff1": 0.4389197136184526, + "nauc_precision_at_5_max": 0.5199791707691143, + "nauc_precision_at_5_std": 0.0005669823652879886, + "nauc_recall_at_1000_diff1": 0.7373979785719185, + "nauc_recall_at_1000_max": 1.0, + "nauc_recall_at_1000_std": 1.0, + "nauc_recall_at_100_diff1": 0.8088654494639961, + "nauc_recall_at_100_max": 0.9709600407029123, + "nauc_recall_at_100_std": 0.8905642948845832, + "nauc_recall_at_10_diff1": 0.3713212043770638, + "nauc_recall_at_10_max": 0.6994578760804744, + "nauc_recall_at_10_std": 0.15062049547636414, + "nauc_recall_at_1_diff1": 0.638355463775883, + "nauc_recall_at_1_max": 0.4446071082504682, + "nauc_recall_at_1_std": 0.012264071898701377, + "nauc_recall_at_20_diff1": 0.34522594837884524, + "nauc_recall_at_20_max": 0.7365023909426307, + "nauc_recall_at_20_std": 0.3134433955009227, + "nauc_recall_at_3_diff1": 0.49439123757815423, + "nauc_recall_at_3_max": 0.48587244696000026, + "nauc_recall_at_3_std": 0.006661835869185709, + "nauc_recall_at_5_diff1": 0.4389197136184529, + "nauc_recall_at_5_max": 0.519979170769113, + "nauc_recall_at_5_std": 0.0005669823652915247, + "ndcg_at_1": 0.6341, + "ndcg_at_10": 0.79836, + "ndcg_at_100": 0.80734, + "ndcg_at_1000": 0.80774, + "ndcg_at_20": 0.80395, + "ndcg_at_3": 0.75092, + "ndcg_at_5": 0.78262, + "precision_at_1": 0.6341, + "precision_at_10": 0.09549, + "precision_at_100": 0.00994, + "precision_at_1000": 0.001, + "precision_at_20": 0.04882, + "precision_at_3": 0.27695, + "precision_at_5": 0.18154, + "recall_at_1": 0.6341, + "recall_at_10": 0.95485, + "recall_at_100": 0.99394, + "recall_at_1000": 0.9973, + "recall_at_20": 0.97642, + "recall_at_3": 0.83086, + "recall_at_5": 0.90768 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/RARbMath.json b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/RARbMath.json new file mode 100644 index 000000000..3ec727396 --- /dev/null +++ b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/RARbMath.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 24416.904141187668, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.76188, + "map_at_1": 0.696, + "map_at_10": 0.73968, + "map_at_100": 0.74434, + "map_at_1000": 0.74455, + "map_at_20": 0.74223, + "map_at_3": 0.72868, + "map_at_5": 0.73477, + "mrr_at_1": 0.6959962019306852, + "mrr_at_10": 0.7396818488961239, + "mrr_at_100": 0.7443449956876291, + "mrr_at_1000": 0.7445502620141883, + "mrr_at_20": 0.7422309651649016, + "mrr_at_3": 0.7286754233264767, + "mrr_at_5": 0.734768159518912, + "nauc_map_at_1000_diff1": 0.8820896330539754, + "nauc_map_at_1000_max": 0.3594578211268095, + "nauc_map_at_1000_std": -0.26124997120937654, + "nauc_map_at_100_diff1": 0.8820127895687121, + "nauc_map_at_100_max": 0.35952231781380584, + "nauc_map_at_100_std": -0.2611655052416251, + "nauc_map_at_10_diff1": 0.8819255025289826, + "nauc_map_at_10_max": 0.3584651291722926, + "nauc_map_at_10_std": -0.26328112180018665, + "nauc_map_at_1_diff1": 0.8987259107915673, + "nauc_map_at_1_max": 0.36150308942175235, + "nauc_map_at_1_std": -0.24345710819094907, + "nauc_map_at_20_diff1": 0.8817566814245247, + "nauc_map_at_20_max": 0.3592286432875952, + "nauc_map_at_20_std": -0.26313847722655553, + "nauc_map_at_3_diff1": 0.8858847174695265, + "nauc_map_at_3_max": 0.358405798697708, + "nauc_map_at_3_std": -0.2642500762052916, + "nauc_map_at_5_diff1": 0.8822279832957293, + "nauc_map_at_5_max": 0.3579662637639966, + "nauc_map_at_5_std": -0.26253696045577646, + "nauc_mrr_at_1000_diff1": 0.8820896330539754, + "nauc_mrr_at_1000_max": 0.3594578211268095, + "nauc_mrr_at_1000_std": -0.26124997120937654, + "nauc_mrr_at_100_diff1": 0.8820127895687121, + "nauc_mrr_at_100_max": 0.35952231781380584, + "nauc_mrr_at_100_std": -0.2611655052416251, + "nauc_mrr_at_10_diff1": 0.8819255025289826, + "nauc_mrr_at_10_max": 0.3584651291722926, + "nauc_mrr_at_10_std": -0.26328112180018665, + "nauc_mrr_at_1_diff1": 0.8987259107915673, + "nauc_mrr_at_1_max": 0.36150308942175235, + "nauc_mrr_at_1_std": -0.24345710819094907, + "nauc_mrr_at_20_diff1": 0.8817566814245247, + "nauc_mrr_at_20_max": 0.3592286432875952, + "nauc_mrr_at_20_std": -0.26313847722655553, + "nauc_mrr_at_3_diff1": 0.8858847174695265, + "nauc_mrr_at_3_max": 0.358405798697708, + "nauc_mrr_at_3_std": -0.2642500762052916, + "nauc_mrr_at_5_diff1": 0.8822279832957293, + "nauc_mrr_at_5_max": 0.3579662637639966, + "nauc_mrr_at_5_std": -0.26253696045577646, + "nauc_ndcg_at_1000_diff1": 0.8767522513008145, + "nauc_ndcg_at_1000_max": 0.36156991763246094, + "nauc_ndcg_at_1000_std": -0.2562876096714577, + "nauc_ndcg_at_100_diff1": 0.8744602201135336, + "nauc_ndcg_at_100_max": 0.36356211680365125, + "nauc_ndcg_at_100_std": -0.2517773576888666, + "nauc_ndcg_at_10_diff1": 0.8727728635226566, + "nauc_ndcg_at_10_max": 0.35762398961466024, + "nauc_ndcg_at_10_std": -0.26997471106275256, + "nauc_ndcg_at_1_diff1": 0.8987259107915673, + "nauc_ndcg_at_1_max": 0.36150308942175235, + "nauc_ndcg_at_1_std": -0.24345710819094907, + "nauc_ndcg_at_20_diff1": 0.871748825200818, + "nauc_ndcg_at_20_max": 0.3607851107501, + "nauc_ndcg_at_20_std": -0.2691239565353886, + "nauc_ndcg_at_3_diff1": 0.8809937817324377, + "nauc_ndcg_at_3_max": 0.3567340555026721, + "nauc_ndcg_at_3_std": -0.27117495512134365, + "nauc_ndcg_at_5_diff1": 0.8740020960455916, + "nauc_ndcg_at_5_max": 0.3560043708049709, + "nauc_ndcg_at_5_std": -0.26791994081357556, + "nauc_precision_at_1000_diff1": 0.7907114013457688, + "nauc_precision_at_1000_max": 0.59213605098206, + "nauc_precision_at_1000_std": 0.5879219138518168, + "nauc_precision_at_100_diff1": 0.7916464951161569, + "nauc_precision_at_100_max": 0.4589994099453366, + "nauc_precision_at_100_std": 0.02997194206437065, + "nauc_precision_at_10_diff1": 0.8324006600366312, + "nauc_precision_at_10_max": 0.35535272412272306, + "nauc_precision_at_10_std": -0.2976184711016344, + "nauc_precision_at_1_diff1": 0.8987259107915673, + "nauc_precision_at_1_max": 0.36150308942175235, + "nauc_precision_at_1_std": -0.24345710819094907, + "nauc_precision_at_20_diff1": 0.8156993141745086, + "nauc_precision_at_20_max": 0.37532302221739755, + "nauc_precision_at_20_std": -0.29744629703876413, + "nauc_precision_at_3_diff1": 0.8648220706337919, + "nauc_precision_at_3_max": 0.35104558339682923, + "nauc_precision_at_3_std": -0.2937465370234221, + "nauc_precision_at_5_diff1": 0.8435693675026527, + "nauc_precision_at_5_max": 0.34883455424517584, + "nauc_precision_at_5_std": -0.2860290822122895, + "nauc_recall_at_1000_diff1": 0.7907114013457711, + "nauc_recall_at_1000_max": 0.5921360509820673, + "nauc_recall_at_1000_std": 0.5879219138518271, + "nauc_recall_at_100_diff1": 0.7916464951161586, + "nauc_recall_at_100_max": 0.45899940994533517, + "nauc_recall_at_100_std": 0.029971942064365712, + "nauc_recall_at_10_diff1": 0.8324006600366293, + "nauc_recall_at_10_max": 0.35535272412272345, + "nauc_recall_at_10_std": -0.29761847110163464, + "nauc_recall_at_1_diff1": 0.8987259107915673, + "nauc_recall_at_1_max": 0.36150308942175235, + "nauc_recall_at_1_std": -0.24345710819094907, + "nauc_recall_at_20_diff1": 0.8156993141745094, + "nauc_recall_at_20_max": 0.37532302221739905, + "nauc_recall_at_20_std": -0.29744629703876313, + "nauc_recall_at_3_diff1": 0.8648220706337917, + "nauc_recall_at_3_max": 0.3510455833968292, + "nauc_recall_at_3_std": -0.29374653702342307, + "nauc_recall_at_5_diff1": 0.8435693675026517, + "nauc_recall_at_5_max": 0.34883455424517607, + "nauc_recall_at_5_std": -0.2860290822122894, + "ndcg_at_1": 0.696, + "ndcg_at_10": 0.76188, + "ndcg_at_100": 0.78655, + "ndcg_at_1000": 0.79179, + "ndcg_at_20": 0.77121, + "ndcg_at_3": 0.73915, + "ndcg_at_5": 0.75005, + "precision_at_1": 0.696, + "precision_at_10": 0.08321, + "precision_at_100": 0.00952, + "precision_at_1000": 0.00099, + "precision_at_20": 0.04346, + "precision_at_3": 0.25648, + "precision_at_5": 0.15914, + "recall_at_1": 0.696, + "recall_at_10": 0.83209, + "recall_at_100": 0.95173, + "recall_at_1000": 0.99256, + "recall_at_20": 0.86912, + "recall_at_3": 0.76943, + "recall_at_5": 0.7957 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/SIQA.json b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/SIQA.json new file mode 100644 index 000000000..e042d9b00 --- /dev/null +++ b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/SIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 215.30377578735352, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.0508, + "map_at_1": 0.02149, + "map_at_10": 0.03933, + "map_at_100": 0.044, + "map_at_1000": 0.04485, + "map_at_20": 0.04185, + "map_at_3": 0.03199, + "map_at_5": 0.03634, + "mrr_at_1": 0.021494370522006142, + "mrr_at_10": 0.03933120501697781, + "mrr_at_100": 0.04400034679821153, + "mrr_at_1000": 0.04485260392938189, + "mrr_at_20": 0.04184692623548305, + "mrr_at_3": 0.031985670419652, + "mrr_at_5": 0.036335721596724685, + "nauc_map_at_1000_diff1": 0.1103208791259316, + "nauc_map_at_1000_max": 0.058279437111824706, + "nauc_map_at_1000_std": -0.05634931028556701, + "nauc_map_at_100_diff1": 0.11063910323347786, + "nauc_map_at_100_max": 0.05866981302001407, + "nauc_map_at_100_std": -0.05659004285476881, + "nauc_map_at_10_diff1": 0.12788616427428895, + "nauc_map_at_10_max": 0.06254195587677619, + "nauc_map_at_10_std": -0.06877894037488357, + "nauc_map_at_1_diff1": 0.22441184607248155, + "nauc_map_at_1_max": 0.0734028080029568, + "nauc_map_at_1_std": -0.14261888744437848, + "nauc_map_at_20_diff1": 0.1173331138541737, + "nauc_map_at_20_max": 0.057431266504166426, + "nauc_map_at_20_std": -0.05940454150275563, + "nauc_map_at_3_diff1": 0.15247153671964866, + "nauc_map_at_3_max": 0.07753938618506788, + "nauc_map_at_3_std": -0.08436713888091985, + "nauc_map_at_5_diff1": 0.134694173499034, + "nauc_map_at_5_max": 0.06647103042909938, + "nauc_map_at_5_std": -0.0704513170131114, + "nauc_mrr_at_1000_diff1": 0.1103208791259316, + "nauc_mrr_at_1000_max": 0.058279437111824706, + "nauc_mrr_at_1000_std": -0.05634931028556701, + "nauc_mrr_at_100_diff1": 0.11063910323347786, + "nauc_mrr_at_100_max": 0.05866981302001407, + "nauc_mrr_at_100_std": -0.05659004285476881, + "nauc_mrr_at_10_diff1": 0.12788616427428895, + "nauc_mrr_at_10_max": 0.06254195587677619, + "nauc_mrr_at_10_std": -0.06877894037488357, + "nauc_mrr_at_1_diff1": 0.22441184607248155, + "nauc_mrr_at_1_max": 0.0734028080029568, + "nauc_mrr_at_1_std": -0.14261888744437848, + "nauc_mrr_at_20_diff1": 0.1173331138541737, + "nauc_mrr_at_20_max": 0.057431266504166426, + "nauc_mrr_at_20_std": -0.05940454150275563, + "nauc_mrr_at_3_diff1": 0.15247153671964866, + "nauc_mrr_at_3_max": 0.07753938618506788, + "nauc_mrr_at_3_std": -0.08436713888091985, + "nauc_mrr_at_5_diff1": 0.134694173499034, + "nauc_mrr_at_5_max": 0.06647103042909938, + "nauc_mrr_at_5_std": -0.0704513170131114, + "nauc_ndcg_at_1000_diff1": 0.04961557649906177, + "nauc_ndcg_at_1000_max": 0.0457272737696651, + "nauc_ndcg_at_1000_std": -0.016567699131351647, + "nauc_ndcg_at_100_diff1": 0.04752012792438027, + "nauc_ndcg_at_100_max": 0.041876827303307176, + "nauc_ndcg_at_100_std": -0.02461471345780892, + "nauc_ndcg_at_10_diff1": 0.09831132550582464, + "nauc_ndcg_at_10_max": 0.049617638850392165, + "nauc_ndcg_at_10_std": -0.056002955002036336, + "nauc_ndcg_at_1_diff1": 0.22441184607248155, + "nauc_ndcg_at_1_max": 0.0734028080029568, + "nauc_ndcg_at_1_std": -0.14261888744437848, + "nauc_ndcg_at_20_diff1": 0.07486726956436117, + "nauc_ndcg_at_20_max": 0.03695619560550802, + "nauc_ndcg_at_20_std": -0.03401582562194365, + "nauc_ndcg_at_3_diff1": 0.13153342582567082, + "nauc_ndcg_at_3_max": 0.07176164265029976, + "nauc_ndcg_at_3_std": -0.07316915718059087, + "nauc_ndcg_at_5_diff1": 0.10834650228536925, + "nauc_ndcg_at_5_max": 0.056237880406384055, + "nauc_ndcg_at_5_std": -0.05475172035118284, + "nauc_precision_at_1000_diff1": -0.003922062924332143, + "nauc_precision_at_1000_max": 0.04531376054730061, + "nauc_precision_at_1000_std": 0.03128640631490687, + "nauc_precision_at_100_diff1": -0.022782390340660104, + "nauc_precision_at_100_max": 0.02537758386194942, + "nauc_precision_at_100_std": 0.008319725560440106, + "nauc_precision_at_10_diff1": 0.05545332058266898, + "nauc_precision_at_10_max": 0.029678323103139673, + "nauc_precision_at_10_std": -0.04007722258190036, + "nauc_precision_at_1_diff1": 0.22441184607248155, + "nauc_precision_at_1_max": 0.0734028080029568, + "nauc_precision_at_1_std": -0.14261888744437848, + "nauc_precision_at_20_diff1": 0.0199190592872757, + "nauc_precision_at_20_max": 0.008550978065177793, + "nauc_precision_at_20_std": -0.0013730868697590934, + "nauc_precision_at_3_diff1": 0.08836434858157466, + "nauc_precision_at_3_max": 0.05874667679751824, + "nauc_precision_at_3_std": -0.050990904364044985, + "nauc_precision_at_5_diff1": 0.06311022406945976, + "nauc_precision_at_5_max": 0.03759785166362334, + "nauc_precision_at_5_std": -0.028454798504169373, + "nauc_recall_at_1000_diff1": -0.003922062924331724, + "nauc_recall_at_1000_max": 0.04531376054730104, + "nauc_recall_at_1000_std": 0.031286406314907325, + "nauc_recall_at_100_diff1": -0.022782390340660135, + "nauc_recall_at_100_max": 0.025377583861949438, + "nauc_recall_at_100_std": 0.008319725560440076, + "nauc_recall_at_10_diff1": 0.055453320582669115, + "nauc_recall_at_10_max": 0.029678323103139725, + "nauc_recall_at_10_std": -0.04007722258190014, + "nauc_recall_at_1_diff1": 0.22441184607248155, + "nauc_recall_at_1_max": 0.0734028080029568, + "nauc_recall_at_1_std": -0.14261888744437848, + "nauc_recall_at_20_diff1": 0.019919059287275696, + "nauc_recall_at_20_max": 0.008550978065177812, + "nauc_recall_at_20_std": -0.0013730868697591535, + "nauc_recall_at_3_diff1": 0.08836434858157471, + "nauc_recall_at_3_max": 0.05874667679751819, + "nauc_recall_at_3_std": -0.05099090436404491, + "nauc_recall_at_5_diff1": 0.06311022406945965, + "nauc_recall_at_5_max": 0.03759785166362331, + "nauc_recall_at_5_std": -0.028454798504169588, + "ndcg_at_1": 0.02149, + "ndcg_at_10": 0.0508, + "ndcg_at_100": 0.07746, + "ndcg_at_1000": 0.10634, + "ndcg_at_20": 0.06007, + "ndcg_at_3": 0.03571, + "ndcg_at_5": 0.04353, + "precision_at_1": 0.02149, + "precision_at_10": 0.0088, + "precision_at_100": 0.00222, + "precision_at_1000": 0.00046, + "precision_at_20": 0.00624, + "precision_at_3": 0.01552, + "precision_at_5": 0.0131, + "recall_at_1": 0.02149, + "recall_at_10": 0.08802, + "recall_at_100": 0.22211, + "recall_at_1000": 0.46315, + "recall_at_20": 0.12487, + "recall_at_3": 0.04657, + "recall_at_5": 0.06551 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/SpartQA.json b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/SpartQA.json new file mode 100644 index 000000000..b35b629c6 --- /dev/null +++ b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/SpartQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 202.13757276535034, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.10869, + "map_at_1": 0.03459, + "map_at_10": 0.07452, + "map_at_100": 0.08251, + "map_at_1000": 0.08371, + "map_at_20": 0.07941, + "map_at_3": 0.05531, + "map_at_5": 0.06545, + "mrr_at_1": 0.05036171396772399, + "mrr_at_10": 0.10297078022453636, + "mrr_at_100": 0.11235632861540824, + "mrr_at_1000": 0.1134396907844537, + "mrr_at_20": 0.10837822958378603, + "mrr_at_3": 0.08133926915229091, + "mrr_at_5": 0.09305323687627509, + "nauc_map_at_1000_diff1": -0.23665067334595763, + "nauc_map_at_1000_max": -0.13774006754208612, + "nauc_map_at_1000_std": 0.6103681797046406, + "nauc_map_at_100_diff1": -0.2372943348410183, + "nauc_map_at_100_max": -0.1370324362976993, + "nauc_map_at_100_std": 0.6089502736005363, + "nauc_map_at_10_diff1": -0.24605902050386488, + "nauc_map_at_10_max": -0.15063969651167802, + "nauc_map_at_10_std": 0.6127501496278064, + "nauc_map_at_1_diff1": -0.3215956891686685, + "nauc_map_at_1_max": -0.23165776667941895, + "nauc_map_at_1_std": 0.5856587658187781, + "nauc_map_at_20_diff1": -0.24042788165206308, + "nauc_map_at_20_max": -0.14076422069235103, + "nauc_map_at_20_std": 0.6120362658009871, + "nauc_map_at_3_diff1": -0.2539607258364847, + "nauc_map_at_3_max": -0.18609113935050373, + "nauc_map_at_3_std": 0.5931075175826942, + "nauc_map_at_5_diff1": -0.24992972998418533, + "nauc_map_at_5_max": -0.1732351577760941, + "nauc_map_at_5_std": 0.6043611472592919, + "nauc_mrr_at_1000_diff1": -0.21403350050773967, + "nauc_mrr_at_1000_max": -0.13110284701552496, + "nauc_mrr_at_1000_std": 0.596759047498446, + "nauc_mrr_at_100_diff1": -0.21405766813960508, + "nauc_mrr_at_100_max": -0.13095633917965085, + "nauc_mrr_at_100_std": 0.5959440672085847, + "nauc_mrr_at_10_diff1": -0.22777648693411687, + "nauc_mrr_at_10_max": -0.14540727782711055, + "nauc_mrr_at_10_std": 0.6043693732399822, + "nauc_mrr_at_1_diff1": -0.32498404407740034, + "nauc_mrr_at_1_max": -0.21428538684139356, + "nauc_mrr_at_1_std": 0.5871371345082067, + "nauc_mrr_at_20_diff1": -0.2173149580134912, + "nauc_mrr_at_20_max": -0.13446548912235898, + "nauc_mrr_at_20_std": 0.6001231976592016, + "nauc_mrr_at_3_diff1": -0.24052338813620944, + "nauc_mrr_at_3_max": -0.1756463820483699, + "nauc_mrr_at_3_std": 0.5937728468109587, + "nauc_mrr_at_5_diff1": -0.2371169347013465, + "nauc_mrr_at_5_max": -0.16706903275050972, + "nauc_mrr_at_5_std": 0.6003814209253139, + "nauc_ndcg_at_1000_diff1": -0.18411605541879053, + "nauc_ndcg_at_1000_max": -0.0835725924861405, + "nauc_ndcg_at_1000_std": 0.6189298242906907, + "nauc_ndcg_at_100_diff1": -0.19695882119653643, + "nauc_ndcg_at_100_max": -0.0819913566027737, + "nauc_ndcg_at_100_std": 0.6022478123428812, + "nauc_ndcg_at_10_diff1": -0.2246015224025933, + "nauc_ndcg_at_10_max": -0.11853814222021289, + "nauc_ndcg_at_10_std": 0.6216765201506307, + "nauc_ndcg_at_1_diff1": -0.32498404407740034, + "nauc_ndcg_at_1_max": -0.21428538684139356, + "nauc_ndcg_at_1_std": 0.5871371345082067, + "nauc_ndcg_at_20_diff1": -0.20714353133769456, + "nauc_ndcg_at_20_max": -0.09381076794274006, + "nauc_ndcg_at_20_std": 0.6158483464160176, + "nauc_ndcg_at_3_diff1": -0.23734952495552164, + "nauc_ndcg_at_3_max": -0.17650453835549515, + "nauc_ndcg_at_3_std": 0.5945658509735908, + "nauc_ndcg_at_5_diff1": -0.23338024487353212, + "nauc_ndcg_at_5_max": -0.15870704448816514, + "nauc_ndcg_at_5_std": 0.6086451542556347, + "nauc_precision_at_1000_diff1": 0.09305811914209015, + "nauc_precision_at_1000_max": 0.023462955177703408, + "nauc_precision_at_1000_std": 0.2377566004065032, + "nauc_precision_at_100_diff1": -0.07514244366803523, + "nauc_precision_at_100_max": -0.01837385507130614, + "nauc_precision_at_100_std": 0.4670743079514633, + "nauc_precision_at_10_diff1": -0.16682137787948723, + "nauc_precision_at_10_max": -0.06445814922165147, + "nauc_precision_at_10_std": 0.628209603062335, + "nauc_precision_at_1_diff1": -0.32498404407740034, + "nauc_precision_at_1_max": -0.21428538684139356, + "nauc_precision_at_1_std": 0.5871371345082067, + "nauc_precision_at_20_diff1": -0.11704277023952506, + "nauc_precision_at_20_max": -0.020012616233637044, + "nauc_precision_at_20_std": 0.5820952415951943, + "nauc_precision_at_3_diff1": -0.1962215248429827, + "nauc_precision_at_3_max": -0.15655729826473758, + "nauc_precision_at_3_std": 0.5987974228194456, + "nauc_precision_at_5_diff1": -0.19374845272075208, + "nauc_precision_at_5_max": -0.13924409789744283, + "nauc_precision_at_5_std": 0.6125081325957354, + "nauc_recall_at_1000_diff1": -0.07300131776353046, + "nauc_recall_at_1000_max": 0.04099077423772824, + "nauc_recall_at_1000_std": 0.5129007750480573, + "nauc_recall_at_100_diff1": -0.14771163952660385, + "nauc_recall_at_100_max": 0.004847971845085425, + "nauc_recall_at_100_std": 0.5365564331284651, + "nauc_recall_at_10_diff1": -0.20046028487165102, + "nauc_recall_at_10_max": -0.06650298629370437, + "nauc_recall_at_10_std": 0.6098034641021554, + "nauc_recall_at_1_diff1": -0.3215956891686685, + "nauc_recall_at_1_max": -0.23165776667941895, + "nauc_recall_at_1_std": 0.5856587658187781, + "nauc_recall_at_20_diff1": -0.16780766241584683, + "nauc_recall_at_20_max": -0.022457538179559686, + "nauc_recall_at_20_std": 0.5813204649193596, + "nauc_recall_at_3_diff1": -0.2163524830236067, + "nauc_recall_at_3_max": -0.16483661475099418, + "nauc_recall_at_3_std": 0.5935476590272782, + "nauc_recall_at_5_diff1": -0.20604071019634718, + "nauc_recall_at_5_max": -0.12759678497390708, + "nauc_recall_at_5_std": 0.5869112656354495, + "ndcg_at_1": 0.05036, + "ndcg_at_10": 0.10869, + "ndcg_at_100": 0.1503, + "ndcg_at_1000": 0.19096, + "ndcg_at_20": 0.12635, + "ndcg_at_3": 0.06811, + "ndcg_at_5": 0.08683, + "precision_at_1": 0.05036, + "precision_at_10": 0.02724, + "precision_at_100": 0.00578, + "precision_at_1000": 0.00112, + "precision_at_20": 0.01861, + "precision_at_3": 0.0409, + "precision_at_5": 0.03634, + "recall_at_1": 0.03459, + "recall_at_10": 0.18485, + "recall_at_100": 0.35819, + "recall_at_1000": 0.6522, + "recall_at_20": 0.24652, + "recall_at_3": 0.08152, + "recall_at_5": 0.12363 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL1.json b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL1.json new file mode 100644 index 000000000..f1e2853bf --- /dev/null +++ b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL1.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 63.693828105926514, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.03039, + "map_at_1": 0.009, + "map_at_10": 0.02131, + "map_at_100": 0.02772, + "map_at_1000": 0.02961, + "map_at_20": 0.02394, + "map_at_3": 0.01504, + "map_at_5": 0.0183, + "mrr_at_1": 0.009, + "mrr_at_10": 0.02130912698412702, + "mrr_at_100": 0.02772205788912586, + "mrr_at_1000": 0.02960583287026326, + "mrr_at_20": 0.02394449261393926, + "mrr_at_3": 0.015041666666666672, + "mrr_at_5": 0.018304166666666687, + "nauc_map_at_1000_diff1": 0.11960427256642311, + "nauc_map_at_1000_max": -0.008232317441652634, + "nauc_map_at_1000_std": 0.18247395383211837, + "nauc_map_at_100_diff1": 0.12149473120164432, + "nauc_map_at_100_max": -0.008517211633455627, + "nauc_map_at_100_std": 0.17996500063192167, + "nauc_map_at_10_diff1": 0.13770052453236425, + "nauc_map_at_10_max": 0.0006749591939085635, + "nauc_map_at_10_std": 0.18902792750014275, + "nauc_map_at_1_diff1": 0.14242912082997955, + "nauc_map_at_1_max": -0.07698327519899828, + "nauc_map_at_1_std": 0.2129281817368751, + "nauc_map_at_20_diff1": 0.12961622563480554, + "nauc_map_at_20_max": -0.006487847414316753, + "nauc_map_at_20_std": 0.18489143923882215, + "nauc_map_at_3_diff1": 0.16102529493915402, + "nauc_map_at_3_max": -0.020822076231914042, + "nauc_map_at_3_std": 0.18778814773082833, + "nauc_map_at_5_diff1": 0.1486965719971482, + "nauc_map_at_5_max": -0.0013334383047499368, + "nauc_map_at_5_std": 0.1839512100347951, + "nauc_mrr_at_1000_diff1": 0.1196040115498147, + "nauc_mrr_at_1000_max": -0.008232099945797875, + "nauc_mrr_at_1000_std": 0.18247349850470124, + "nauc_mrr_at_100_diff1": 0.12149473120164432, + "nauc_mrr_at_100_max": -0.008517211633455627, + "nauc_mrr_at_100_std": 0.17996500063192167, + "nauc_mrr_at_10_diff1": 0.13770052453236425, + "nauc_mrr_at_10_max": 0.0006749591939085635, + "nauc_mrr_at_10_std": 0.18902792750014275, + "nauc_mrr_at_1_diff1": 0.14242912082997955, + "nauc_mrr_at_1_max": -0.07698327519899828, + "nauc_mrr_at_1_std": 0.2129281817368751, + "nauc_mrr_at_20_diff1": 0.12961622563480554, + "nauc_mrr_at_20_max": -0.006487847414316753, + "nauc_mrr_at_20_std": 0.18489143923882215, + "nauc_mrr_at_3_diff1": 0.16102529493915402, + "nauc_mrr_at_3_max": -0.020822076231914042, + "nauc_mrr_at_3_std": 0.18778814773082833, + "nauc_mrr_at_5_diff1": 0.1486965719971482, + "nauc_mrr_at_5_max": -0.0013334383047499368, + "nauc_mrr_at_5_std": 0.1839512100347951, + "nauc_ndcg_at_1000_diff1": 0.07521785333755308, + "nauc_ndcg_at_1000_max": 0.012030656139890376, + "nauc_ndcg_at_1000_std": 0.20777163573540328, + "nauc_ndcg_at_100_diff1": 0.09260300998571486, + "nauc_ndcg_at_100_max": -0.011518325965394366, + "nauc_ndcg_at_100_std": 0.1698617317875406, + "nauc_ndcg_at_10_diff1": 0.1262649526793197, + "nauc_ndcg_at_10_max": 0.013856897749248177, + "nauc_ndcg_at_10_std": 0.18657739693380812, + "nauc_ndcg_at_1_diff1": 0.14242912082997955, + "nauc_ndcg_at_1_max": -0.07698327519899828, + "nauc_ndcg_at_1_std": 0.2129281817368751, + "nauc_ndcg_at_20_diff1": 0.112218587829113, + "nauc_ndcg_at_20_max": -0.003669355988044664, + "nauc_ndcg_at_20_std": 0.18025873003558116, + "nauc_ndcg_at_3_diff1": 0.16105383429417094, + "nauc_ndcg_at_3_max": -0.011163813292230219, + "nauc_ndcg_at_3_std": 0.18091741627652208, + "nauc_ndcg_at_5_diff1": 0.14431762538505236, + "nauc_ndcg_at_5_max": 0.014889816246692089, + "nauc_ndcg_at_5_std": 0.1786831008662385, + "nauc_precision_at_1000_diff1": 0.007936092488660371, + "nauc_precision_at_1000_max": 0.08258085342127452, + "nauc_precision_at_1000_std": 0.29513788921750683, + "nauc_precision_at_100_diff1": 0.07344352325383505, + "nauc_precision_at_100_max": -0.01730983995255711, + "nauc_precision_at_100_std": 0.1645618015934748, + "nauc_precision_at_10_diff1": 0.11136069823290835, + "nauc_precision_at_10_max": 0.027999831473256284, + "nauc_precision_at_10_std": 0.18420083952927815, + "nauc_precision_at_1_diff1": 0.14242912082997955, + "nauc_precision_at_1_max": -0.07698327519899828, + "nauc_precision_at_1_std": 0.2129281817368751, + "nauc_precision_at_20_diff1": 0.0953016887414524, + "nauc_precision_at_20_max": -0.004535562222710107, + "nauc_precision_at_20_std": 0.17679003612730465, + "nauc_precision_at_3_diff1": 0.16038951948764, + "nauc_precision_at_3_max": 0.0071073599234725265, + "nauc_precision_at_3_std": 0.1673423081858586, + "nauc_precision_at_5_diff1": 0.13710048562752208, + "nauc_precision_at_5_max": 0.03950587888275456, + "nauc_precision_at_5_std": 0.17144268511328645, + "nauc_recall_at_1000_diff1": 0.007936092488661924, + "nauc_recall_at_1000_max": 0.08258085342127552, + "nauc_recall_at_1000_std": 0.29513788921750783, + "nauc_recall_at_100_diff1": 0.07344352325383499, + "nauc_recall_at_100_max": -0.017309839952557478, + "nauc_recall_at_100_std": 0.1645618015934747, + "nauc_recall_at_10_diff1": 0.11136069823290844, + "nauc_recall_at_10_max": 0.027999831473256357, + "nauc_recall_at_10_std": 0.18420083952927832, + "nauc_recall_at_1_diff1": 0.14242912082997955, + "nauc_recall_at_1_max": -0.07698327519899828, + "nauc_recall_at_1_std": 0.2129281817368751, + "nauc_recall_at_20_diff1": 0.09530168874145262, + "nauc_recall_at_20_max": -0.004535562222710178, + "nauc_recall_at_20_std": 0.17679003612730465, + "nauc_recall_at_3_diff1": 0.16038951948764005, + "nauc_recall_at_3_max": 0.007107359923472654, + "nauc_recall_at_3_std": 0.16734230818585882, + "nauc_recall_at_5_diff1": 0.13710048562752222, + "nauc_recall_at_5_max": 0.03950587888275465, + "nauc_recall_at_5_std": 0.17144268511328647, + "ndcg_at_1": 0.009, + "ndcg_at_10": 0.03039, + "ndcg_at_100": 0.07053, + "ndcg_at_1000": 0.13413, + "ndcg_at_20": 0.04007, + "ndcg_at_3": 0.01708, + "ndcg_at_5": 0.02306, + "precision_at_1": 0.009, + "precision_at_10": 0.00605, + "precision_at_100": 0.0027, + "precision_at_1000": 0.0008, + "precision_at_20": 0.00495, + "precision_at_3": 0.00767, + "precision_at_5": 0.00755, + "recall_at_1": 0.009, + "recall_at_10": 0.0605, + "recall_at_100": 0.26975, + "recall_at_1000": 0.7995, + "recall_at_20": 0.099, + "recall_at_3": 0.023, + "recall_at_5": 0.03775 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL2Fact.json b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL2Fact.json new file mode 100644 index 000000000..0500e9987 --- /dev/null +++ b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL2Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 1326.0471720695496, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.35632, + "map_at_1": 0.15861, + "map_at_10": 0.28469, + "map_at_100": 0.29623, + "map_at_1000": 0.29678, + "map_at_20": 0.29191, + "map_at_3": 0.24436, + "map_at_5": 0.26778, + "mrr_at_1": 0.1586066333148045, + "mrr_at_10": 0.2846895394560753, + "mrr_at_100": 0.29622892169353154, + "mrr_at_1000": 0.2967782647425824, + "mrr_at_20": 0.29190625603411496, + "mrr_at_3": 0.2443641529244637, + "mrr_at_5": 0.2677753072694709, + "nauc_map_at_1000_diff1": 0.104372647768114, + "nauc_map_at_1000_max": 0.12583188545033366, + "nauc_map_at_1000_std": 0.003428519451363609, + "nauc_map_at_100_diff1": 0.10413530428473189, + "nauc_map_at_100_max": 0.12637591774528406, + "nauc_map_at_100_std": 0.004039137055454766, + "nauc_map_at_10_diff1": 0.10430179689853385, + "nauc_map_at_10_max": 0.12380023944850083, + "nauc_map_at_10_std": -0.0022189360464385656, + "nauc_map_at_1_diff1": 0.14971049521398105, + "nauc_map_at_1_max": 0.10030906413087089, + "nauc_map_at_1_std": -0.02682210646417934, + "nauc_map_at_20_diff1": 0.10346218130108954, + "nauc_map_at_20_max": 0.1272006418075369, + "nauc_map_at_20_std": 0.0030714237070854924, + "nauc_map_at_3_diff1": 0.11978537916614981, + "nauc_map_at_3_max": 0.10378242088546585, + "nauc_map_at_3_std": -0.027260607059924318, + "nauc_map_at_5_diff1": 0.11129494950089261, + "nauc_map_at_5_max": 0.11395604659443048, + "nauc_map_at_5_std": -0.014220509491511303, + "nauc_mrr_at_1000_diff1": 0.104372647768114, + "nauc_mrr_at_1000_max": 0.12583188545033366, + "nauc_mrr_at_1000_std": 0.003428519451363609, + "nauc_mrr_at_100_diff1": 0.10413530428473189, + "nauc_mrr_at_100_max": 0.12637591774528406, + "nauc_mrr_at_100_std": 0.004039137055454766, + "nauc_mrr_at_10_diff1": 0.10430179689853385, + "nauc_mrr_at_10_max": 0.12380023944850083, + "nauc_mrr_at_10_std": -0.0022189360464385656, + "nauc_mrr_at_1_diff1": 0.14971049521398105, + "nauc_mrr_at_1_max": 0.10030906413087089, + "nauc_mrr_at_1_std": -0.02682210646417934, + "nauc_mrr_at_20_diff1": 0.10346218130108954, + "nauc_mrr_at_20_max": 0.1272006418075369, + "nauc_mrr_at_20_std": 0.0030714237070854924, + "nauc_mrr_at_3_diff1": 0.11978537916614981, + "nauc_mrr_at_3_max": 0.10378242088546585, + "nauc_mrr_at_3_std": -0.027260607059924318, + "nauc_mrr_at_5_diff1": 0.11129494950089261, + "nauc_mrr_at_5_max": 0.11395604659443048, + "nauc_mrr_at_5_std": -0.014220509491511303, + "nauc_ndcg_at_1000_diff1": 0.08585506690951576, + "nauc_ndcg_at_1000_max": 0.1416732505795474, + "nauc_ndcg_at_1000_std": 0.03452673545030057, + "nauc_ndcg_at_100_diff1": 0.07830112214305644, + "nauc_ndcg_at_100_max": 0.15575825999396894, + "nauc_ndcg_at_100_std": 0.05473388969127367, + "nauc_ndcg_at_10_diff1": 0.07998038307485761, + "nauc_ndcg_at_10_max": 0.14568635520083922, + "nauc_ndcg_at_10_std": 0.025169957295077986, + "nauc_ndcg_at_1_diff1": 0.14971049521398105, + "nauc_ndcg_at_1_max": 0.10030906413087089, + "nauc_ndcg_at_1_std": -0.02682210646417934, + "nauc_ndcg_at_20_diff1": 0.07597064436872261, + "nauc_ndcg_at_20_max": 0.1589402321639446, + "nauc_ndcg_at_20_std": 0.0452218529294874, + "nauc_ndcg_at_3_diff1": 0.11175195418896217, + "nauc_ndcg_at_3_max": 0.10501005697533254, + "nauc_ndcg_at_3_std": -0.0259894448897697, + "nauc_ndcg_at_5_diff1": 0.0967754379756143, + "nauc_ndcg_at_5_max": 0.12271206843865778, + "nauc_ndcg_at_5_std": -0.0033562220118591567, + "nauc_precision_at_1000_diff1": -0.2631346334926752, + "nauc_precision_at_1000_max": 0.26055622757683944, + "nauc_precision_at_1000_std": 0.6447780685575815, + "nauc_precision_at_100_diff1": -0.09876962628253155, + "nauc_precision_at_100_max": 0.37345786590316005, + "nauc_precision_at_100_std": 0.46850202726987256, + "nauc_precision_at_10_diff1": 0.007390661387360592, + "nauc_precision_at_10_max": 0.21427969610044514, + "nauc_precision_at_10_std": 0.11174033305914102, + "nauc_precision_at_1_diff1": 0.14971049521398105, + "nauc_precision_at_1_max": 0.10030906413087089, + "nauc_precision_at_1_std": -0.02682210646417934, + "nauc_precision_at_20_diff1": -0.02382377566827449, + "nauc_precision_at_20_max": 0.283891246985588, + "nauc_precision_at_20_std": 0.21310776944152499, + "nauc_precision_at_3_diff1": 0.09237626363161154, + "nauc_precision_at_3_max": 0.10804538791466671, + "nauc_precision_at_3_std": -0.022573448683642836, + "nauc_precision_at_5_diff1": 0.059676786451433886, + "nauc_precision_at_5_max": 0.1461887347117818, + "nauc_precision_at_5_std": 0.02608301636472132, + "nauc_recall_at_1000_diff1": -0.26313463349268934, + "nauc_recall_at_1000_max": 0.26055622757683344, + "nauc_recall_at_1000_std": 0.6447780685575811, + "nauc_recall_at_100_diff1": -0.09876962628253429, + "nauc_recall_at_100_max": 0.3734578659031579, + "nauc_recall_at_100_std": 0.46850202726987145, + "nauc_recall_at_10_diff1": 0.007390661387359879, + "nauc_recall_at_10_max": 0.21427969610044467, + "nauc_recall_at_10_std": 0.11174033305914075, + "nauc_recall_at_1_diff1": 0.14971049521398105, + "nauc_recall_at_1_max": 0.10030906413087089, + "nauc_recall_at_1_std": -0.02682210646417934, + "nauc_recall_at_20_diff1": -0.02382377566827467, + "nauc_recall_at_20_max": 0.28389124698558804, + "nauc_recall_at_20_std": 0.21310776944152485, + "nauc_recall_at_3_diff1": 0.09237626363161157, + "nauc_recall_at_3_max": 0.10804538791466672, + "nauc_recall_at_3_std": -0.02257344868364284, + "nauc_recall_at_5_diff1": 0.05967678645143392, + "nauc_recall_at_5_max": 0.14618873471178215, + "nauc_recall_at_5_std": 0.026083016364721334, + "ndcg_at_1": 0.15861, + "ndcg_at_10": 0.35632, + "ndcg_at_100": 0.41401, + "ndcg_at_1000": 0.4287, + "ndcg_at_20": 0.3823, + "ndcg_at_3": 0.27354, + "ndcg_at_5": 0.31562, + "precision_at_1": 0.15861, + "precision_at_10": 0.05855, + "precision_at_100": 0.0086, + "precision_at_1000": 0.00098, + "precision_at_20": 0.03438, + "precision_at_3": 0.11945, + "precision_at_5": 0.09205, + "recall_at_1": 0.15861, + "recall_at_10": 0.58551, + "recall_at_100": 0.85955, + "recall_at_1000": 0.97536, + "recall_at_20": 0.6876, + "recall_at_3": 0.35835, + "recall_at_5": 0.46026 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL2Pure.json b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL2Pure.json new file mode 100644 index 000000000..1ee0a7c34 --- /dev/null +++ b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL2Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 105.08298921585083, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.0932, + "map_at_1": 0.0378, + "map_at_10": 0.07165, + "map_at_100": 0.08, + "map_at_1000": 0.08134, + "map_at_20": 0.0755, + "map_at_3": 0.05846, + "map_at_5": 0.06554, + "mrr_at_1": 0.03779877709838799, + "mrr_at_10": 0.07164871136522043, + "mrr_at_100": 0.07999747585266709, + "mrr_at_1000": 0.081335894223115, + "mrr_at_20": 0.07549945880436049, + "mrr_at_3": 0.05845840281637945, + "mrr_at_5": 0.06553640911617546, + "nauc_map_at_1000_diff1": 0.18251686709697493, + "nauc_map_at_1000_max": 0.2918722193048036, + "nauc_map_at_1000_std": 0.22000460538048797, + "nauc_map_at_100_diff1": 0.1827000428080685, + "nauc_map_at_100_max": 0.29209732772644353, + "nauc_map_at_100_std": 0.21913703173164317, + "nauc_map_at_10_diff1": 0.19565974097062275, + "nauc_map_at_10_max": 0.293194092920179, + "nauc_map_at_10_std": 0.21094973327459995, + "nauc_map_at_1_diff1": 0.26861428701175377, + "nauc_map_at_1_max": 0.2797987411481758, + "nauc_map_at_1_std": 0.20878165478723262, + "nauc_map_at_20_diff1": 0.18774632512968614, + "nauc_map_at_20_max": 0.2921703771246905, + "nauc_map_at_20_std": 0.20971074492959674, + "nauc_map_at_3_diff1": 0.21948583323302215, + "nauc_map_at_3_max": 0.29374331602423054, + "nauc_map_at_3_std": 0.20600441868799962, + "nauc_map_at_5_diff1": 0.20408498257240731, + "nauc_map_at_5_max": 0.29111174587205774, + "nauc_map_at_5_std": 0.20425718413822336, + "nauc_mrr_at_1000_diff1": 0.18251686175406306, + "nauc_mrr_at_1000_max": 0.2918721638203569, + "nauc_mrr_at_1000_std": 0.22000456165334312, + "nauc_mrr_at_100_diff1": 0.1827000428080685, + "nauc_mrr_at_100_max": 0.29209732772644353, + "nauc_mrr_at_100_std": 0.21913703173164317, + "nauc_mrr_at_10_diff1": 0.19565974097062275, + "nauc_mrr_at_10_max": 0.293194092920179, + "nauc_mrr_at_10_std": 0.21094973327459995, + "nauc_mrr_at_1_diff1": 0.26861428701175377, + "nauc_mrr_at_1_max": 0.2797987411481758, + "nauc_mrr_at_1_std": 0.20878165478723262, + "nauc_mrr_at_20_diff1": 0.18774632512968614, + "nauc_mrr_at_20_max": 0.2921703771246905, + "nauc_mrr_at_20_std": 0.20971074492959674, + "nauc_mrr_at_3_diff1": 0.21948583323302215, + "nauc_mrr_at_3_max": 0.29374331602423054, + "nauc_mrr_at_3_std": 0.20600441868799962, + "nauc_mrr_at_5_diff1": 0.20408498257240731, + "nauc_mrr_at_5_max": 0.29111174587205774, + "nauc_mrr_at_5_std": 0.20425718413822336, + "nauc_ndcg_at_1000_diff1": 0.12824649205228808, + "nauc_ndcg_at_1000_max": 0.2840614171076694, + "nauc_ndcg_at_1000_std": 0.2740490624304542, + "nauc_ndcg_at_100_diff1": 0.1287036664800668, + "nauc_ndcg_at_100_max": 0.29298659835299523, + "nauc_ndcg_at_100_std": 0.26554479594880787, + "nauc_ndcg_at_10_diff1": 0.17233557000271504, + "nauc_ndcg_at_10_max": 0.29553556756748517, + "nauc_ndcg_at_10_std": 0.21455760039309055, + "nauc_ndcg_at_1_diff1": 0.26861428701175377, + "nauc_ndcg_at_1_max": 0.2797987411481758, + "nauc_ndcg_at_1_std": 0.20878165478723262, + "nauc_ndcg_at_20_diff1": 0.1532683882234257, + "nauc_ndcg_at_20_max": 0.29255364235169284, + "nauc_ndcg_at_20_std": 0.21112786182783294, + "nauc_ndcg_at_3_diff1": 0.2096498114528877, + "nauc_ndcg_at_3_max": 0.29698253391298884, + "nauc_ndcg_at_3_std": 0.2054665241471033, + "nauc_ndcg_at_5_diff1": 0.18737924288985283, + "nauc_ndcg_at_5_max": 0.29254536878653276, + "nauc_ndcg_at_5_std": 0.20313345105153327, + "nauc_precision_at_1000_diff1": -0.00811643405297364, + "nauc_precision_at_1000_max": 0.2370734974560671, + "nauc_precision_at_1000_std": 0.4597581140103228, + "nauc_precision_at_100_diff1": 0.04493268470832822, + "nauc_precision_at_100_max": 0.2939507780787366, + "nauc_precision_at_100_std": 0.36061808487711755, + "nauc_precision_at_10_diff1": 0.13482452770443867, + "nauc_precision_at_10_max": 0.29877012171922757, + "nauc_precision_at_10_std": 0.22086168288668911, + "nauc_precision_at_1_diff1": 0.26861428701175377, + "nauc_precision_at_1_max": 0.2797987411481758, + "nauc_precision_at_1_std": 0.20878165478723262, + "nauc_precision_at_20_diff1": 0.10121201421320047, + "nauc_precision_at_20_max": 0.29183519896431365, + "nauc_precision_at_20_std": 0.2126807475304392, + "nauc_precision_at_3_diff1": 0.1902528504382182, + "nauc_precision_at_3_max": 0.3034678080627226, + "nauc_precision_at_3_std": 0.20440972811983507, + "nauc_precision_at_5_diff1": 0.15762643101218055, + "nauc_precision_at_5_max": 0.29468455142735245, + "nauc_precision_at_5_std": 0.20119367177936037, + "nauc_recall_at_1000_diff1": -0.00811643405297506, + "nauc_recall_at_1000_max": 0.23707349745606598, + "nauc_recall_at_1000_std": 0.4597581140103223, + "nauc_recall_at_100_diff1": 0.044932684708328174, + "nauc_recall_at_100_max": 0.2939507780787364, + "nauc_recall_at_100_std": 0.36061808487711744, + "nauc_recall_at_10_diff1": 0.1348245277044386, + "nauc_recall_at_10_max": 0.2987701217192275, + "nauc_recall_at_10_std": 0.22086168288668895, + "nauc_recall_at_1_diff1": 0.26861428701175377, + "nauc_recall_at_1_max": 0.2797987411481758, + "nauc_recall_at_1_std": 0.20878165478723262, + "nauc_recall_at_20_diff1": 0.10121201421320011, + "nauc_recall_at_20_max": 0.2918351989643134, + "nauc_recall_at_20_std": 0.21268074753043903, + "nauc_recall_at_3_diff1": 0.1902528504382181, + "nauc_recall_at_3_max": 0.30346780806272255, + "nauc_recall_at_3_std": 0.20440972811983504, + "nauc_recall_at_5_diff1": 0.1576264310121804, + "nauc_recall_at_5_max": 0.29468455142735245, + "nauc_recall_at_5_std": 0.20119367177936043, + "ndcg_at_1": 0.0378, + "ndcg_at_10": 0.0932, + "ndcg_at_100": 0.14295, + "ndcg_at_1000": 0.18567, + "ndcg_at_20": 0.10727, + "ndcg_at_3": 0.06559, + "ndcg_at_5": 0.0785, + "precision_at_1": 0.0378, + "precision_at_10": 0.01632, + "precision_at_100": 0.00418, + "precision_at_1000": 0.00077, + "precision_at_20": 0.01095, + "precision_at_3": 0.02878, + "precision_at_5": 0.02361, + "recall_at_1": 0.0378, + "recall_at_10": 0.16324, + "recall_at_100": 0.41764, + "recall_at_1000": 0.7695, + "recall_at_20": 0.21901, + "recall_at_3": 0.08634, + "recall_at_5": 0.11803 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL3Fact.json b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL3Fact.json new file mode 100644 index 000000000..1846e0624 --- /dev/null +++ b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL3Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 1208.2107796669006, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.30407, + "map_at_1": 0.10235, + "map_at_10": 0.22972, + "map_at_100": 0.24195, + "map_at_1000": 0.24258, + "map_at_20": 0.23716, + "map_at_3": 0.18602, + "map_at_5": 0.21169, + "mrr_at_1": 0.10234975146859467, + "mrr_at_10": 0.22972344156822347, + "mrr_at_100": 0.24194807600219648, + "mrr_at_1000": 0.2425825604073465, + "mrr_at_20": 0.2371584520923105, + "mrr_at_3": 0.18602199126374513, + "mrr_at_5": 0.21168850730531893, + "nauc_map_at_1000_diff1": 0.03691003046384813, + "nauc_map_at_1000_max": 0.1457996678002418, + "nauc_map_at_1000_std": 0.07641572615962662, + "nauc_map_at_100_diff1": 0.036846209519761704, + "nauc_map_at_100_max": 0.14646072218025621, + "nauc_map_at_100_std": 0.0771935910624049, + "nauc_map_at_10_diff1": 0.037532453831230925, + "nauc_map_at_10_max": 0.145614601236934, + "nauc_map_at_10_std": 0.07195737099420549, + "nauc_map_at_1_diff1": 0.028070233253170485, + "nauc_map_at_1_max": 0.0442348935020762, + "nauc_map_at_1_std": -0.0064431408475998835, + "nauc_map_at_20_diff1": 0.03587820597563016, + "nauc_map_at_20_max": 0.14754216022907063, + "nauc_map_at_20_std": 0.07697369649290443, + "nauc_map_at_3_diff1": 0.050762366345740925, + "nauc_map_at_3_max": 0.11486049157831703, + "nauc_map_at_3_std": 0.034659719939784804, + "nauc_map_at_5_diff1": 0.04258781470456559, + "nauc_map_at_5_max": 0.13102610860649577, + "nauc_map_at_5_std": 0.05592283253274901, + "nauc_mrr_at_1000_diff1": 0.03691003046384813, + "nauc_mrr_at_1000_max": 0.1457996678002418, + "nauc_mrr_at_1000_std": 0.07641572615962662, + "nauc_mrr_at_100_diff1": 0.036846209519761704, + "nauc_mrr_at_100_max": 0.14646072218025621, + "nauc_mrr_at_100_std": 0.0771935910624049, + "nauc_mrr_at_10_diff1": 0.037532453831230925, + "nauc_mrr_at_10_max": 0.145614601236934, + "nauc_mrr_at_10_std": 0.07195737099420549, + "nauc_mrr_at_1_diff1": 0.028070233253170485, + "nauc_mrr_at_1_max": 0.0442348935020762, + "nauc_mrr_at_1_std": -0.0064431408475998835, + "nauc_mrr_at_20_diff1": 0.03587820597563016, + "nauc_mrr_at_20_max": 0.14754216022907063, + "nauc_mrr_at_20_std": 0.07697369649290443, + "nauc_mrr_at_3_diff1": 0.050762366345740925, + "nauc_mrr_at_3_max": 0.11486049157831703, + "nauc_mrr_at_3_std": 0.034659719939784804, + "nauc_mrr_at_5_diff1": 0.04258781470456559, + "nauc_mrr_at_5_max": 0.13102610860649577, + "nauc_mrr_at_5_std": 0.05592283253274901, + "nauc_ndcg_at_1000_diff1": 0.02810366801467689, + "nauc_ndcg_at_1000_max": 0.17444294167837696, + "nauc_ndcg_at_1000_std": 0.11834988142523134, + "nauc_ndcg_at_100_diff1": 0.025620188758029853, + "nauc_ndcg_at_100_max": 0.19152165126692902, + "nauc_ndcg_at_100_std": 0.1427695833786269, + "nauc_ndcg_at_10_diff1": 0.028642188602351827, + "nauc_ndcg_at_10_max": 0.1908219371367876, + "nauc_ndcg_at_10_std": 0.11673013068174236, + "nauc_ndcg_at_1_diff1": 0.028070233253170485, + "nauc_ndcg_at_1_max": 0.0442348935020762, + "nauc_ndcg_at_1_std": -0.0064431408475998835, + "nauc_ndcg_at_20_diff1": 0.02208792940227136, + "nauc_ndcg_at_20_max": 0.1988409987590661, + "nauc_ndcg_at_20_std": 0.13572793470684866, + "nauc_ndcg_at_3_diff1": 0.05402111752802242, + "nauc_ndcg_at_3_max": 0.13082942761311503, + "nauc_ndcg_at_3_std": 0.04476207265304625, + "nauc_ndcg_at_5_diff1": 0.04031357570687762, + "nauc_ndcg_at_5_max": 0.15706846587244291, + "nauc_ndcg_at_5_std": 0.07988871528170254, + "nauc_precision_at_1000_diff1": -0.1753377971353503, + "nauc_precision_at_1000_max": 0.30163234971463315, + "nauc_precision_at_1000_std": 0.6571719224233935, + "nauc_precision_at_100_diff1": -0.04363926714480774, + "nauc_precision_at_100_max": 0.40387274773884096, + "nauc_precision_at_100_std": 0.5270057981336054, + "nauc_precision_at_10_diff1": 0.0029336898490629803, + "nauc_precision_at_10_max": 0.3048077420774797, + "nauc_precision_at_10_std": 0.23212554097497423, + "nauc_precision_at_1_diff1": 0.028070233253170485, + "nauc_precision_at_1_max": 0.0442348935020762, + "nauc_precision_at_1_std": -0.0064431408475998835, + "nauc_precision_at_20_diff1": -0.025954283849874468, + "nauc_precision_at_20_max": 0.35161374848628896, + "nauc_precision_at_20_std": 0.31951978586525404, + "nauc_precision_at_3_diff1": 0.06058608222200392, + "nauc_precision_at_3_max": 0.16507575538632502, + "nauc_precision_at_3_std": 0.06661016160507352, + "nauc_precision_at_5_diff1": 0.033664858624606095, + "nauc_precision_at_5_max": 0.21386677360691514, + "nauc_precision_at_5_std": 0.13366937276804694, + "nauc_recall_at_1000_diff1": -0.17533779713535805, + "nauc_recall_at_1000_max": 0.3016323497146322, + "nauc_recall_at_1000_std": 0.6571719224233921, + "nauc_recall_at_100_diff1": -0.04363926714480706, + "nauc_recall_at_100_max": 0.4038727477388406, + "nauc_recall_at_100_std": 0.5270057981336057, + "nauc_recall_at_10_diff1": 0.0029336898490628345, + "nauc_recall_at_10_max": 0.30480774207747946, + "nauc_recall_at_10_std": 0.2321255409749741, + "nauc_recall_at_1_diff1": 0.028070233253170485, + "nauc_recall_at_1_max": 0.0442348935020762, + "nauc_recall_at_1_std": -0.0064431408475998835, + "nauc_recall_at_20_diff1": -0.025954283849874128, + "nauc_recall_at_20_max": 0.35161374848628923, + "nauc_recall_at_20_std": 0.31951978586525404, + "nauc_recall_at_3_diff1": 0.0605860822220039, + "nauc_recall_at_3_max": 0.1650757553863248, + "nauc_recall_at_3_std": 0.06661016160507355, + "nauc_recall_at_5_diff1": 0.03366485862460557, + "nauc_recall_at_5_max": 0.2138667736069152, + "nauc_recall_at_5_std": 0.1336693727680465, + "ndcg_at_1": 0.10235, + "ndcg_at_10": 0.30407, + "ndcg_at_100": 0.36539, + "ndcg_at_1000": 0.38271, + "ndcg_at_20": 0.33108, + "ndcg_at_3": 0.21451, + "ndcg_at_5": 0.26072, + "precision_at_1": 0.10235, + "precision_at_10": 0.05427, + "precision_at_100": 0.00834, + "precision_at_1000": 0.00097, + "precision_at_20": 0.03247, + "precision_at_3": 0.09911, + "precision_at_5": 0.08188, + "recall_at_1": 0.10235, + "recall_at_10": 0.5427, + "recall_at_100": 0.83371, + "recall_at_1000": 0.97085, + "recall_at_20": 0.64934, + "recall_at_3": 0.29733, + "recall_at_5": 0.4094 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL3Pure.json b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL3Pure.json new file mode 100644 index 000000000..8da4f6433 --- /dev/null +++ b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL3Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 98.27742457389832, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.14393, + "map_at_1": 0.03208, + "map_at_10": 0.10127, + "map_at_100": 0.11262, + "map_at_1000": 0.11371, + "map_at_20": 0.10711, + "map_at_3": 0.07565, + "map_at_5": 0.08986, + "mrr_at_1": 0.032083145051965654, + "mrr_at_10": 0.10127224409872392, + "mrr_at_100": 0.11261836576230885, + "mrr_at_1000": 0.11371334690807339, + "mrr_at_20": 0.1071105607638164, + "mrr_at_3": 0.07565145353215834, + "mrr_at_5": 0.08986293116433164, + "nauc_map_at_1000_diff1": -0.05204768415647506, + "nauc_map_at_1000_max": 0.23358413159369318, + "nauc_map_at_1000_std": 0.2066724961430342, + "nauc_map_at_100_diff1": -0.05231459619198734, + "nauc_map_at_100_max": 0.23456686694947693, + "nauc_map_at_100_std": 0.20720604675646173, + "nauc_map_at_10_diff1": -0.0524670907513093, + "nauc_map_at_10_max": 0.21777680787836717, + "nauc_map_at_10_std": 0.1869728682918591, + "nauc_map_at_1_diff1": -0.11521733848005848, + "nauc_map_at_1_max": 0.06332689630817503, + "nauc_map_at_1_std": 0.06790534412166474, + "nauc_map_at_20_diff1": -0.052890994547723585, + "nauc_map_at_20_max": 0.23012343944276495, + "nauc_map_at_20_std": 0.2002693401229446, + "nauc_map_at_3_diff1": -0.03749430625555806, + "nauc_map_at_3_max": 0.17056510378136122, + "nauc_map_at_3_std": 0.1308512848145269, + "nauc_map_at_5_diff1": -0.04409826097752947, + "nauc_map_at_5_max": 0.19756098871798106, + "nauc_map_at_5_std": 0.15877153890929793, + "nauc_mrr_at_1000_diff1": -0.05204763458676561, + "nauc_mrr_at_1000_max": 0.23358420704455143, + "nauc_mrr_at_1000_std": 0.20667248280471934, + "nauc_mrr_at_100_diff1": -0.05231459619198734, + "nauc_mrr_at_100_max": 0.23456686694947693, + "nauc_mrr_at_100_std": 0.20720604675646173, + "nauc_mrr_at_10_diff1": -0.0524670907513093, + "nauc_mrr_at_10_max": 0.21777680787836717, + "nauc_mrr_at_10_std": 0.1869728682918591, + "nauc_mrr_at_1_diff1": -0.11521733848005848, + "nauc_mrr_at_1_max": 0.06332689630817503, + "nauc_mrr_at_1_std": 0.06790534412166474, + "nauc_mrr_at_20_diff1": -0.052890994547723585, + "nauc_mrr_at_20_max": 0.23012343944276495, + "nauc_mrr_at_20_std": 0.2002693401229446, + "nauc_mrr_at_3_diff1": -0.03749430625555806, + "nauc_mrr_at_3_max": 0.17056510378136122, + "nauc_mrr_at_3_std": 0.1308512848145269, + "nauc_mrr_at_5_diff1": -0.04409826097752947, + "nauc_mrr_at_5_max": 0.19756098871798106, + "nauc_mrr_at_5_std": 0.15877153890929793, + "nauc_ndcg_at_1000_diff1": -0.05406589873459794, + "nauc_ndcg_at_1000_max": 0.288010428515032, + "nauc_ndcg_at_1000_std": 0.2869035079047364, + "nauc_ndcg_at_100_diff1": -0.054513029202350974, + "nauc_ndcg_at_100_max": 0.31244178652608623, + "nauc_ndcg_at_100_std": 0.29991141487963174, + "nauc_ndcg_at_10_diff1": -0.0562590731480349, + "nauc_ndcg_at_10_max": 0.2574317224685073, + "nauc_ndcg_at_10_std": 0.22999405163521838, + "nauc_ndcg_at_1_diff1": -0.11521733848005848, + "nauc_ndcg_at_1_max": 0.06332689630817503, + "nauc_ndcg_at_1_std": 0.06790534412166474, + "nauc_ndcg_at_20_diff1": -0.05744476612033314, + "nauc_ndcg_at_20_max": 0.2901136918146636, + "nauc_ndcg_at_20_std": 0.2649916567285768, + "nauc_ndcg_at_3_diff1": -0.028585996184097292, + "nauc_ndcg_at_3_max": 0.18612793428789712, + "nauc_ndcg_at_3_std": 0.14105402010993018, + "nauc_ndcg_at_5_diff1": -0.03963688198203913, + "nauc_ndcg_at_5_max": 0.22229342724341714, + "nauc_ndcg_at_5_std": 0.17950847123484645, + "nauc_precision_at_1000_diff1": -0.07781392077543103, + "nauc_precision_at_1000_max": 0.39975371188868203, + "nauc_precision_at_1000_std": 0.5840848651835543, + "nauc_precision_at_100_diff1": -0.059608106226479475, + "nauc_precision_at_100_max": 0.46403114822828967, + "nauc_precision_at_100_std": 0.4888598260124073, + "nauc_precision_at_10_diff1": -0.06557195038916463, + "nauc_precision_at_10_max": 0.317209650173431, + "nauc_precision_at_10_std": 0.29739230445825615, + "nauc_precision_at_1_diff1": -0.11521733848005848, + "nauc_precision_at_1_max": 0.06332689630817503, + "nauc_precision_at_1_std": 0.06790534412166474, + "nauc_precision_at_20_diff1": -0.06776324387870311, + "nauc_precision_at_20_max": 0.38570504498858926, + "nauc_precision_at_20_std": 0.3703256611572462, + "nauc_precision_at_3_diff1": -0.013714098764550903, + "nauc_precision_at_3_max": 0.21284994744295835, + "nauc_precision_at_3_std": 0.1587634808368424, + "nauc_precision_at_5_diff1": -0.03419639683816657, + "nauc_precision_at_5_max": 0.26064545120504196, + "nauc_precision_at_5_std": 0.2123565912044208, + "nauc_recall_at_1000_diff1": -0.07781392077543194, + "nauc_recall_at_1000_max": 0.39975371188868253, + "nauc_recall_at_1000_std": 0.5840848651835532, + "nauc_recall_at_100_diff1": -0.05960810622647942, + "nauc_recall_at_100_max": 0.4640311482282895, + "nauc_recall_at_100_std": 0.4888598260124072, + "nauc_recall_at_10_diff1": -0.06557195038916491, + "nauc_recall_at_10_max": 0.3172096501734306, + "nauc_recall_at_10_std": 0.297392304458256, + "nauc_recall_at_1_diff1": -0.11521733848005848, + "nauc_recall_at_1_max": 0.06332689630817503, + "nauc_recall_at_1_std": 0.06790534412166474, + "nauc_recall_at_20_diff1": -0.06776324387870337, + "nauc_recall_at_20_max": 0.3857050449885892, + "nauc_recall_at_20_std": 0.3703256611572461, + "nauc_recall_at_3_diff1": -0.01371409876455083, + "nauc_recall_at_3_max": 0.2128499474429582, + "nauc_recall_at_3_std": 0.15876348083684216, + "nauc_recall_at_5_diff1": -0.03419639683816658, + "nauc_recall_at_5_max": 0.26064545120504173, + "nauc_recall_at_5_std": 0.21235659120442074, + "ndcg_at_1": 0.03208, + "ndcg_at_10": 0.14393, + "ndcg_at_100": 0.20539, + "ndcg_at_1000": 0.23897, + "ndcg_at_20": 0.1653, + "ndcg_at_3": 0.09079, + "ndcg_at_5": 0.11634, + "precision_at_1": 0.03208, + "precision_at_10": 0.0282, + "precision_at_100": 0.00583, + "precision_at_1000": 0.00086, + "precision_at_20": 0.01833, + "precision_at_3": 0.04496, + "precision_at_5": 0.03936, + "recall_at_1": 0.03208, + "recall_at_10": 0.28197, + "recall_at_100": 0.58337, + "recall_at_1000": 0.85721, + "recall_at_20": 0.3667, + "recall_at_3": 0.13488, + "recall_at_5": 0.19679 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/WinoGrande.json b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/WinoGrande.json new file mode 100644 index 000000000..8932c3d55 --- /dev/null +++ b/results/e5-mistral-7b-instruct-noinstruct/07163b72af1488142a360786df853f237b1a3ca1/WinoGrande.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 24.997589349746704, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.45184, + "map_at_1": 0.21784, + "map_at_10": 0.37405, + "map_at_100": 0.38361, + "map_at_1000": 0.38402, + "map_at_20": 0.38086, + "map_at_3": 0.33478, + "map_at_5": 0.36091, + "mrr_at_1": 0.21783741120757696, + "mrr_at_10": 0.3740450508011669, + "mrr_at_100": 0.3836068408640154, + "mrr_at_1000": 0.38402227340581985, + "mrr_at_20": 0.38086069107453724, + "mrr_at_3": 0.3347803209681658, + "mrr_at_5": 0.3609050249934218, + "nauc_map_at_1000_diff1": 0.024794532418328963, + "nauc_map_at_1000_max": -0.23511164675679141, + "nauc_map_at_1000_std": 0.0636480177514929, + "nauc_map_at_100_diff1": 0.024666457461038047, + "nauc_map_at_100_max": -0.2353340709462896, + "nauc_map_at_100_std": 0.06371100705347542, + "nauc_map_at_10_diff1": 0.023459549115722584, + "nauc_map_at_10_max": -0.23844612051203523, + "nauc_map_at_10_std": 0.06149930918020157, + "nauc_map_at_1_diff1": 0.05671782955713586, + "nauc_map_at_1_max": -0.141737369448423, + "nauc_map_at_1_std": 0.03770733759593746, + "nauc_map_at_20_diff1": 0.02307123916920139, + "nauc_map_at_20_max": -0.23722006016919261, + "nauc_map_at_20_std": 0.0635482292721878, + "nauc_map_at_3_diff1": 0.024648441522097546, + "nauc_map_at_3_max": -0.22659790599180413, + "nauc_map_at_3_std": 0.0625034910902976, + "nauc_map_at_5_diff1": 0.027379219005609547, + "nauc_map_at_5_max": -0.23328259021466682, + "nauc_map_at_5_std": 0.06312577743673946, + "nauc_mrr_at_1000_diff1": 0.024794532418328963, + "nauc_mrr_at_1000_max": -0.23511164675679141, + "nauc_mrr_at_1000_std": 0.0636480177514929, + "nauc_mrr_at_100_diff1": 0.024666457461038047, + "nauc_mrr_at_100_max": -0.2353340709462896, + "nauc_mrr_at_100_std": 0.06371100705347542, + "nauc_mrr_at_10_diff1": 0.023459549115722584, + "nauc_mrr_at_10_max": -0.23844612051203523, + "nauc_mrr_at_10_std": 0.06149930918020157, + "nauc_mrr_at_1_diff1": 0.05671782955713586, + "nauc_mrr_at_1_max": -0.141737369448423, + "nauc_mrr_at_1_std": 0.03770733759593746, + "nauc_mrr_at_20_diff1": 0.02307123916920139, + "nauc_mrr_at_20_max": -0.23722006016919261, + "nauc_mrr_at_20_std": 0.0635482292721878, + "nauc_mrr_at_3_diff1": 0.024648441522097546, + "nauc_mrr_at_3_max": -0.22659790599180413, + "nauc_mrr_at_3_std": 0.0625034910902976, + "nauc_mrr_at_5_diff1": 0.027379219005609547, + "nauc_mrr_at_5_max": -0.23328259021466682, + "nauc_mrr_at_5_std": 0.06312577743673946, + "nauc_ndcg_at_1000_diff1": 0.020861496451865375, + "nauc_ndcg_at_1000_max": -0.2568961240185842, + "nauc_ndcg_at_1000_std": 0.07163944251991279, + "nauc_ndcg_at_100_diff1": 0.01864803029281553, + "nauc_ndcg_at_100_max": -0.2645588953630292, + "nauc_ndcg_at_100_std": 0.07510423340603145, + "nauc_ndcg_at_10_diff1": 0.012147503016596598, + "nauc_ndcg_at_10_max": -0.2785757747005708, + "nauc_ndcg_at_10_std": 0.06550263732518624, + "nauc_ndcg_at_1_diff1": 0.05671782955713586, + "nauc_ndcg_at_1_max": -0.141737369448423, + "nauc_ndcg_at_1_std": 0.03770733759593746, + "nauc_ndcg_at_20_diff1": 0.009299831797946054, + "nauc_ndcg_at_20_max": -0.2763535867348536, + "nauc_ndcg_at_20_std": 0.07334431787929652, + "nauc_ndcg_at_3_diff1": 0.017947888347810918, + "nauc_ndcg_at_3_max": -0.2502646204835159, + "nauc_ndcg_at_3_std": 0.06844301538143151, + "nauc_ndcg_at_5_diff1": 0.022953467246643124, + "nauc_ndcg_at_5_max": -0.2635228664301234, + "nauc_ndcg_at_5_std": 0.06992437288275918, + "nauc_precision_at_1000_diff1": 0.04323679613429218, + "nauc_precision_at_1000_max": -0.6691319982233335, + "nauc_precision_at_1000_std": 0.3484582744341752, + "nauc_precision_at_100_diff1": -0.012261354585992538, + "nauc_precision_at_100_max": -0.4718881728195939, + "nauc_precision_at_100_std": 0.1901787675967456, + "nauc_precision_at_10_diff1": -0.03074902315917401, + "nauc_precision_at_10_max": -0.42706306846877146, + "nauc_precision_at_10_std": 0.0760741127053075, + "nauc_precision_at_1_diff1": 0.05671782955713586, + "nauc_precision_at_1_max": -0.141737369448423, + "nauc_precision_at_1_std": 0.03770733759593746, + "nauc_precision_at_20_diff1": -0.06490250996221861, + "nauc_precision_at_20_max": -0.4681257827871245, + "nauc_precision_at_20_std": 0.12428584005223522, + "nauc_precision_at_3_diff1": 0.0007060133428383545, + "nauc_precision_at_3_max": -0.3135651485076944, + "nauc_precision_at_3_std": 0.08403350014423926, + "nauc_precision_at_5_diff1": 0.011872816931005496, + "nauc_precision_at_5_max": -0.35385510993632124, + "nauc_precision_at_5_std": 0.08970893221898076, + "nauc_recall_at_1000_diff1": 0.043236796134276466, + "nauc_recall_at_1000_max": -0.6691319982233626, + "nauc_recall_at_1000_std": 0.34845827443416655, + "nauc_recall_at_100_diff1": -0.012261354585993416, + "nauc_recall_at_100_max": -0.4718881728195965, + "nauc_recall_at_100_std": 0.19017876759674515, + "nauc_recall_at_10_diff1": -0.03074902315917447, + "nauc_recall_at_10_max": -0.42706306846877223, + "nauc_recall_at_10_std": 0.07607411270530781, + "nauc_recall_at_1_diff1": 0.05671782955713586, + "nauc_recall_at_1_max": -0.141737369448423, + "nauc_recall_at_1_std": 0.03770733759593746, + "nauc_recall_at_20_diff1": -0.06490250996221895, + "nauc_recall_at_20_max": -0.46812578278712513, + "nauc_recall_at_20_std": 0.12428584005223406, + "nauc_recall_at_3_diff1": 0.0007060133428385397, + "nauc_recall_at_3_max": -0.3135651485076944, + "nauc_recall_at_3_std": 0.08403350014423878, + "nauc_recall_at_5_diff1": 0.011872816931006003, + "nauc_recall_at_5_max": -0.3538551099363207, + "nauc_recall_at_5_std": 0.08970893221898124, + "ndcg_at_1": 0.21784, + "ndcg_at_10": 0.45184, + "ndcg_at_100": 0.49564, + "ndcg_at_1000": 0.50713, + "ndcg_at_20": 0.47649, + "ndcg_at_3": 0.37267, + "ndcg_at_5": 0.42011, + "precision_at_1": 0.21784, + "precision_at_10": 0.06961, + "precision_at_100": 0.00895, + "precision_at_1000": 0.00099, + "precision_at_20": 0.03966, + "precision_at_3": 0.16075, + "precision_at_5": 0.11965, + "recall_at_1": 0.21784, + "recall_at_10": 0.69613, + "recall_at_100": 0.89503, + "recall_at_1000": 0.98658, + "recall_at_20": 0.79321, + "recall_at_3": 0.48224, + "recall_at_5": 0.59826 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/ARCChallenge.json b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/ARCChallenge.json new file mode 100644 index 000000000..c5a8a3a49 --- /dev/null +++ b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/ARCChallenge.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 71.00392484664917, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.17806, + "map_at_1": 0.093, + "map_at_10": 0.14741, + "map_at_100": 0.15601, + "map_at_1000": 0.15698, + "map_at_20": 0.15136, + "map_at_3": 0.13069, + "map_at_5": 0.13969, + "mrr_at_1": 0.09300341296928327, + "mrr_at_10": 0.14741217021507116, + "mrr_at_100": 0.15600767896298354, + "mrr_at_1000": 0.15697702470614933, + "mrr_at_20": 0.15135724026944877, + "mrr_at_3": 0.13068828213879408, + "mrr_at_5": 0.1396899886234357, + "nauc_map_at_1000_diff1": 0.10122131164859459, + "nauc_map_at_1000_max": 0.15097973727786798, + "nauc_map_at_1000_std": -0.036718821329664586, + "nauc_map_at_100_diff1": 0.10120968592103016, + "nauc_map_at_100_max": 0.151260101456411, + "nauc_map_at_100_std": -0.036954620891838305, + "nauc_map_at_10_diff1": 0.10301330155764753, + "nauc_map_at_10_max": 0.15489480329797783, + "nauc_map_at_10_std": -0.038029983144342555, + "nauc_map_at_1_diff1": 0.17289281576093476, + "nauc_map_at_1_max": 0.14000152363142093, + "nauc_map_at_1_std": -0.0874878944177405, + "nauc_map_at_20_diff1": 0.10271941238842114, + "nauc_map_at_20_max": 0.15394504670217551, + "nauc_map_at_20_std": -0.037868216336509275, + "nauc_map_at_3_diff1": 0.10968144177246247, + "nauc_map_at_3_max": 0.15580318904160148, + "nauc_map_at_3_std": -0.05000827154036474, + "nauc_map_at_5_diff1": 0.10641723440798306, + "nauc_map_at_5_max": 0.1531969588422023, + "nauc_map_at_5_std": -0.040834821594641836, + "nauc_mrr_at_1000_diff1": 0.10122131164859459, + "nauc_mrr_at_1000_max": 0.15097973727786798, + "nauc_mrr_at_1000_std": -0.036718821329664586, + "nauc_mrr_at_100_diff1": 0.10120968592103016, + "nauc_mrr_at_100_max": 0.151260101456411, + "nauc_mrr_at_100_std": -0.036954620891838305, + "nauc_mrr_at_10_diff1": 0.10301330155764753, + "nauc_mrr_at_10_max": 0.15489480329797783, + "nauc_mrr_at_10_std": -0.038029983144342555, + "nauc_mrr_at_1_diff1": 0.17289281576093476, + "nauc_mrr_at_1_max": 0.14000152363142093, + "nauc_mrr_at_1_std": -0.0874878944177405, + "nauc_mrr_at_20_diff1": 0.10271941238842114, + "nauc_mrr_at_20_max": 0.15394504670217551, + "nauc_mrr_at_20_std": -0.037868216336509275, + "nauc_mrr_at_3_diff1": 0.10968144177246247, + "nauc_mrr_at_3_max": 0.15580318904160148, + "nauc_mrr_at_3_std": -0.05000827154036474, + "nauc_mrr_at_5_diff1": 0.10641723440798306, + "nauc_mrr_at_5_max": 0.1531969588422023, + "nauc_mrr_at_5_std": -0.040834821594641836, + "nauc_ndcg_at_1000_diff1": 0.07572930595475345, + "nauc_ndcg_at_1000_max": 0.132605039019562, + "nauc_ndcg_at_1000_std": -0.006355911173801275, + "nauc_ndcg_at_100_diff1": 0.07867666815969483, + "nauc_ndcg_at_100_max": 0.14142917504743796, + "nauc_ndcg_at_100_std": -0.010819076553611428, + "nauc_ndcg_at_10_diff1": 0.08304077001958372, + "nauc_ndcg_at_10_max": 0.15696231036082872, + "nauc_ndcg_at_10_std": -0.020560316565649633, + "nauc_ndcg_at_1_diff1": 0.17289281576093476, + "nauc_ndcg_at_1_max": 0.14000152363142093, + "nauc_ndcg_at_1_std": -0.0874878944177405, + "nauc_ndcg_at_20_diff1": 0.08319343679206094, + "nauc_ndcg_at_20_max": 0.1543514525743874, + "nauc_ndcg_at_20_std": -0.019314658350174617, + "nauc_ndcg_at_3_diff1": 0.09395050061224525, + "nauc_ndcg_at_3_max": 0.15672969930073452, + "nauc_ndcg_at_3_std": -0.040833500124821884, + "nauc_ndcg_at_5_diff1": 0.09010169900298327, + "nauc_ndcg_at_5_max": 0.15340779728325532, + "nauc_ndcg_at_5_std": -0.025847879344562306, + "nauc_precision_at_1000_diff1": -0.02772769412369316, + "nauc_precision_at_1000_max": 0.0006473919084699476, + "nauc_precision_at_1000_std": 0.138910720873758, + "nauc_precision_at_100_diff1": 0.03414020388378616, + "nauc_precision_at_100_max": 0.10984397283028678, + "nauc_precision_at_100_std": 0.05844161271952554, + "nauc_precision_at_10_diff1": 0.04220203926810661, + "nauc_precision_at_10_max": 0.16142576314416376, + "nauc_precision_at_10_std": 0.016067354778399073, + "nauc_precision_at_1_diff1": 0.17289281576093476, + "nauc_precision_at_1_max": 0.14000152363142093, + "nauc_precision_at_1_std": -0.0874878944177405, + "nauc_precision_at_20_diff1": 0.0458740535904596, + "nauc_precision_at_20_max": 0.15441266244921958, + "nauc_precision_at_20_std": 0.019176908435482823, + "nauc_precision_at_3_diff1": 0.05818103129476479, + "nauc_precision_at_3_max": 0.15810192384176544, + "nauc_precision_at_3_std": -0.020008903188241566, + "nauc_precision_at_5_diff1": 0.055861006485065055, + "nauc_precision_at_5_max": 0.15341367452908983, + "nauc_precision_at_5_std": 0.007254767591235081, + "nauc_recall_at_1000_diff1": -0.027727694123693664, + "nauc_recall_at_1000_max": 0.0006473919084700042, + "nauc_recall_at_1000_std": 0.13891072087375825, + "nauc_recall_at_100_diff1": 0.034140203883785705, + "nauc_recall_at_100_max": 0.10984397283028648, + "nauc_recall_at_100_std": 0.058441612719525395, + "nauc_recall_at_10_diff1": 0.0422020392681068, + "nauc_recall_at_10_max": 0.16142576314416365, + "nauc_recall_at_10_std": 0.016067354778399053, + "nauc_recall_at_1_diff1": 0.17289281576093476, + "nauc_recall_at_1_max": 0.14000152363142093, + "nauc_recall_at_1_std": -0.0874878944177405, + "nauc_recall_at_20_diff1": 0.04587405359045933, + "nauc_recall_at_20_max": 0.1544126624492196, + "nauc_recall_at_20_std": 0.01917690843548258, + "nauc_recall_at_3_diff1": 0.05818103129476499, + "nauc_recall_at_3_max": 0.15810192384176536, + "nauc_recall_at_3_std": -0.020008903188241632, + "nauc_recall_at_5_diff1": 0.05586100648506483, + "nauc_recall_at_5_max": 0.15341367452908952, + "nauc_recall_at_5_std": 0.007254767591234917, + "ndcg_at_1": 0.093, + "ndcg_at_10": 0.17806, + "ndcg_at_100": 0.22771, + "ndcg_at_1000": 0.25872, + "ndcg_at_20": 0.19263, + "ndcg_at_3": 0.14313, + "ndcg_at_5": 0.15932, + "precision_at_1": 0.093, + "precision_at_10": 0.02765, + "precision_at_100": 0.00526, + "precision_at_1000": 0.00078, + "precision_at_20": 0.01672, + "precision_at_3": 0.05973, + "precision_at_5": 0.04369, + "recall_at_1": 0.093, + "recall_at_10": 0.27645, + "recall_at_100": 0.52645, + "recall_at_1000": 0.78157, + "recall_at_20": 0.33447, + "recall_at_3": 0.17918, + "recall_at_5": 0.21843 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/AlphaNLI.json b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/AlphaNLI.json new file mode 100644 index 000000000..f4527b1b0 --- /dev/null +++ b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/AlphaNLI.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 1026.5618908405304, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.26117, + "map_at_1": 0.16188, + "map_at_10": 0.22513, + "map_at_100": 0.23406, + "map_at_1000": 0.23499, + "map_at_20": 0.22936, + "map_at_3": 0.20496, + "map_at_5": 0.21554, + "mrr_at_1": 0.1618798955613577, + "mrr_at_10": 0.22513339757138706, + "mrr_at_100": 0.23406031799620008, + "mrr_at_1000": 0.23499242584772584, + "mrr_at_20": 0.22936441685893535, + "mrr_at_3": 0.20496083550913838, + "mrr_at_5": 0.21553524804177537, + "nauc_map_at_1000_diff1": 0.3683315582761917, + "nauc_map_at_1000_max": 0.2159077253184962, + "nauc_map_at_1000_std": -0.07515630250890855, + "nauc_map_at_100_diff1": 0.36822946604941736, + "nauc_map_at_100_max": 0.2157095376191426, + "nauc_map_at_100_std": -0.07544521467301019, + "nauc_map_at_10_diff1": 0.3692606098267009, + "nauc_map_at_10_max": 0.21562699489840736, + "nauc_map_at_10_std": -0.07989094513925549, + "nauc_map_at_1_diff1": 0.4671216535619137, + "nauc_map_at_1_max": 0.27421744448522517, + "nauc_map_at_1_std": -0.0741815254318315, + "nauc_map_at_20_diff1": 0.36934561848872094, + "nauc_map_at_20_max": 0.2153782677268793, + "nauc_map_at_20_std": -0.07683366741913283, + "nauc_map_at_3_diff1": 0.39057775770184416, + "nauc_map_at_3_max": 0.23202745245779383, + "nauc_map_at_3_std": -0.08051379867493536, + "nauc_map_at_5_diff1": 0.38073040660296587, + "nauc_map_at_5_max": 0.22656489479186498, + "nauc_map_at_5_std": -0.08246836499601316, + "nauc_mrr_at_1000_diff1": 0.3683315582761917, + "nauc_mrr_at_1000_max": 0.2159077253184962, + "nauc_mrr_at_1000_std": -0.07515630250890855, + "nauc_mrr_at_100_diff1": 0.36822946604941736, + "nauc_mrr_at_100_max": 0.2157095376191426, + "nauc_mrr_at_100_std": -0.07544521467301019, + "nauc_mrr_at_10_diff1": 0.3692606098267009, + "nauc_mrr_at_10_max": 0.21562699489840736, + "nauc_mrr_at_10_std": -0.07989094513925549, + "nauc_mrr_at_1_diff1": 0.4671216535619137, + "nauc_mrr_at_1_max": 0.27421744448522517, + "nauc_mrr_at_1_std": -0.0741815254318315, + "nauc_mrr_at_20_diff1": 0.36934561848872094, + "nauc_mrr_at_20_max": 0.2153782677268793, + "nauc_mrr_at_20_std": -0.07683366741913283, + "nauc_mrr_at_3_diff1": 0.39057775770184416, + "nauc_mrr_at_3_max": 0.23202745245779383, + "nauc_mrr_at_3_std": -0.08051379867493536, + "nauc_mrr_at_5_diff1": 0.38073040660296587, + "nauc_mrr_at_5_max": 0.22656489479186498, + "nauc_mrr_at_5_std": -0.08246836499601316, + "nauc_ndcg_at_1000_diff1": 0.3268541228812355, + "nauc_ndcg_at_1000_max": 0.1906548170062251, + "nauc_ndcg_at_1000_std": -0.05773004535645095, + "nauc_ndcg_at_100_diff1": 0.32327225096051493, + "nauc_ndcg_at_100_max": 0.1862770674023753, + "nauc_ndcg_at_100_std": -0.06405487948837829, + "nauc_ndcg_at_10_diff1": 0.328019332904574, + "nauc_ndcg_at_10_max": 0.1856934220148671, + "nauc_ndcg_at_10_std": -0.08159682842688963, + "nauc_ndcg_at_1_diff1": 0.4671216535619137, + "nauc_ndcg_at_1_max": 0.27421744448522517, + "nauc_ndcg_at_1_std": -0.0741815254318315, + "nauc_ndcg_at_20_diff1": 0.3285495608923083, + "nauc_ndcg_at_20_max": 0.18452322282833614, + "nauc_ndcg_at_20_std": -0.07146868029556899, + "nauc_ndcg_at_3_diff1": 0.3700692607115185, + "nauc_ndcg_at_3_max": 0.2203348900432913, + "nauc_ndcg_at_3_std": -0.08233196602904289, + "nauc_ndcg_at_5_diff1": 0.3538486414388821, + "nauc_ndcg_at_5_max": 0.21090880761283662, + "nauc_ndcg_at_5_std": -0.08638336860452796, + "nauc_precision_at_1000_diff1": 0.10290495257430915, + "nauc_precision_at_1000_max": 0.0697039522132307, + "nauc_precision_at_1000_std": 0.1243886346627172, + "nauc_precision_at_100_diff1": 0.18232397788568727, + "nauc_precision_at_100_max": 0.09520302530069495, + "nauc_precision_at_100_std": -0.013567022324614186, + "nauc_precision_at_10_diff1": 0.22197049816051923, + "nauc_precision_at_10_max": 0.1061814384241075, + "nauc_precision_at_10_std": -0.08587806364179106, + "nauc_precision_at_1_diff1": 0.4671216535619137, + "nauc_precision_at_1_max": 0.27421744448522517, + "nauc_precision_at_1_std": -0.0741815254318315, + "nauc_precision_at_20_diff1": 0.22383122503169026, + "nauc_precision_at_20_max": 0.10146927945817863, + "nauc_precision_at_20_std": -0.05237067199481295, + "nauc_precision_at_3_diff1": 0.3185132132825787, + "nauc_precision_at_3_max": 0.19083119543505891, + "nauc_precision_at_3_std": -0.08693701864474902, + "nauc_precision_at_5_diff1": 0.28769357556009095, + "nauc_precision_at_5_max": 0.17201466086534953, + "nauc_precision_at_5_std": -0.09671507948906985, + "nauc_recall_at_1000_diff1": 0.10290495257430933, + "nauc_recall_at_1000_max": 0.06970395221323117, + "nauc_recall_at_1000_std": 0.12438863466271813, + "nauc_recall_at_100_diff1": 0.1823239778856869, + "nauc_recall_at_100_max": 0.09520302530069447, + "nauc_recall_at_100_std": -0.013567022324614332, + "nauc_recall_at_10_diff1": 0.22197049816051917, + "nauc_recall_at_10_max": 0.1061814384241075, + "nauc_recall_at_10_std": -0.0858780636417911, + "nauc_recall_at_1_diff1": 0.4671216535619137, + "nauc_recall_at_1_max": 0.27421744448522517, + "nauc_recall_at_1_std": -0.0741815254318315, + "nauc_recall_at_20_diff1": 0.22383122503169006, + "nauc_recall_at_20_max": 0.10146927945817824, + "nauc_recall_at_20_std": -0.05237067199481305, + "nauc_recall_at_3_diff1": 0.3185132132825789, + "nauc_recall_at_3_max": 0.19083119543505886, + "nauc_recall_at_3_std": -0.08693701864474879, + "nauc_recall_at_5_diff1": 0.2876935755600909, + "nauc_recall_at_5_max": 0.17201466086534942, + "nauc_recall_at_5_std": -0.09671507948906971, + "ndcg_at_1": 0.16188, + "ndcg_at_10": 0.26117, + "ndcg_at_100": 0.31152, + "ndcg_at_1000": 0.33861, + "ndcg_at_20": 0.27666, + "ndcg_at_3": 0.21888, + "ndcg_at_5": 0.23782, + "precision_at_1": 0.16188, + "precision_at_10": 0.03773, + "precision_at_100": 0.00629, + "precision_at_1000": 0.00085, + "precision_at_20": 0.02193, + "precision_at_3": 0.08638, + "precision_at_5": 0.06097, + "recall_at_1": 0.16188, + "recall_at_10": 0.37728, + "recall_at_100": 0.62859, + "recall_at_1000": 0.84661, + "recall_at_20": 0.43864, + "recall_at_3": 0.25914, + "recall_at_5": 0.30483 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/HellaSwag.json b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/HellaSwag.json new file mode 100644 index 000000000..4910ec25f --- /dev/null +++ b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/HellaSwag.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 2467.7000045776367, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.34846, + "map_at_1": 0.20106, + "map_at_10": 0.29812, + "map_at_100": 0.30695, + "map_at_1000": 0.30765, + "map_at_20": 0.30324, + "map_at_3": 0.27264, + "map_at_5": 0.28798, + "mrr_at_1": 0.2010555666201952, + "mrr_at_10": 0.29811533622278547, + "mrr_at_100": 0.30694777444653465, + "mrr_at_1000": 0.30765301717784854, + "mrr_at_20": 0.3032405120823701, + "mrr_at_3": 0.2726382526721113, + "mrr_at_5": 0.2879788222797588, + "nauc_map_at_1000_diff1": 0.21161198342754284, + "nauc_map_at_1000_max": -0.07165183460299479, + "nauc_map_at_1000_std": -0.35476222147699465, + "nauc_map_at_100_diff1": 0.21149323339978915, + "nauc_map_at_100_max": -0.07200629548250094, + "nauc_map_at_100_std": -0.35510550119699186, + "nauc_map_at_10_diff1": 0.21320719681823366, + "nauc_map_at_10_max": -0.06915962445318562, + "nauc_map_at_10_std": -0.3534674877619398, + "nauc_map_at_1_diff1": 0.24939930748384873, + "nauc_map_at_1_max": -0.04027325429092402, + "nauc_map_at_1_std": -0.29324722375976053, + "nauc_map_at_20_diff1": 0.2119076724395323, + "nauc_map_at_20_max": -0.07151133359449023, + "nauc_map_at_20_std": -0.3554663955812581, + "nauc_map_at_3_diff1": 0.21865797149445526, + "nauc_map_at_3_max": -0.05979150368422437, + "nauc_map_at_3_std": -0.33960127942809265, + "nauc_map_at_5_diff1": 0.21546981629353626, + "nauc_map_at_5_max": -0.06435553536376357, + "nauc_map_at_5_std": -0.3490831989565639, + "nauc_mrr_at_1000_diff1": 0.21161198320267302, + "nauc_mrr_at_1000_max": -0.0716518347409213, + "nauc_mrr_at_1000_std": -0.3547622213933109, + "nauc_mrr_at_100_diff1": 0.21149323339978915, + "nauc_mrr_at_100_max": -0.07200629548250094, + "nauc_mrr_at_100_std": -0.35510550119699186, + "nauc_mrr_at_10_diff1": 0.21320719681823366, + "nauc_mrr_at_10_max": -0.06915962445318562, + "nauc_mrr_at_10_std": -0.3534674877619398, + "nauc_mrr_at_1_diff1": 0.24939930748384873, + "nauc_mrr_at_1_max": -0.04027325429092402, + "nauc_mrr_at_1_std": -0.29324722375976053, + "nauc_mrr_at_20_diff1": 0.2119076724395323, + "nauc_mrr_at_20_max": -0.07151133359449023, + "nauc_mrr_at_20_std": -0.3554663955812581, + "nauc_mrr_at_3_diff1": 0.21865797149445526, + "nauc_mrr_at_3_max": -0.05979150368422437, + "nauc_mrr_at_3_std": -0.33960127942809265, + "nauc_mrr_at_5_diff1": 0.21546981629353626, + "nauc_mrr_at_5_max": -0.06435553536376357, + "nauc_mrr_at_5_std": -0.3490831989565639, + "nauc_ndcg_at_1000_diff1": 0.19506955836307194, + "nauc_ndcg_at_1000_max": -0.08682209814498709, + "nauc_ndcg_at_1000_std": -0.37685830501084955, + "nauc_ndcg_at_100_diff1": 0.1915216012456815, + "nauc_ndcg_at_100_max": -0.09689367691268687, + "nauc_ndcg_at_100_std": -0.3860351284824477, + "nauc_ndcg_at_10_diff1": 0.1999723559646755, + "nauc_ndcg_at_10_max": -0.0854933728626911, + "nauc_ndcg_at_10_std": -0.38153482044136666, + "nauc_ndcg_at_1_diff1": 0.24939930748384873, + "nauc_ndcg_at_1_max": -0.04027325429092402, + "nauc_ndcg_at_1_std": -0.29324722375976053, + "nauc_ndcg_at_20_diff1": 0.19492684809060795, + "nauc_ndcg_at_20_max": -0.09408717843530683, + "nauc_ndcg_at_20_std": -0.3892379722477807, + "nauc_ndcg_at_3_diff1": 0.2108778872489904, + "nauc_ndcg_at_3_max": -0.06622605555876224, + "nauc_ndcg_at_3_std": -0.35460478111726956, + "nauc_ndcg_at_5_diff1": 0.20551557682723776, + "nauc_ndcg_at_5_max": -0.07405484231036626, + "nauc_ndcg_at_5_std": -0.3711839697985486, + "nauc_precision_at_1000_diff1": 0.057523546076936605, + "nauc_precision_at_1000_max": -0.13966155642173142, + "nauc_precision_at_1000_std": -0.4678997924853692, + "nauc_precision_at_100_diff1": 0.09559140997850567, + "nauc_precision_at_100_max": -0.2158191204895721, + "nauc_precision_at_100_std": -0.5128449566054458, + "nauc_precision_at_10_diff1": 0.16220110878384555, + "nauc_precision_at_10_max": -0.13457099231402522, + "nauc_precision_at_10_std": -0.4629111676802513, + "nauc_precision_at_1_diff1": 0.24939930748384873, + "nauc_precision_at_1_max": -0.04027325429092402, + "nauc_precision_at_1_std": -0.29324722375976053, + "nauc_precision_at_20_diff1": 0.13901716406047337, + "nauc_precision_at_20_max": -0.17203675590504094, + "nauc_precision_at_20_std": -0.4997626479968452, + "nauc_precision_at_3_diff1": 0.19086869862120834, + "nauc_precision_at_3_max": -0.08325259857666086, + "nauc_precision_at_3_std": -0.3942375060814894, + "nauc_precision_at_5_diff1": 0.179345226092613, + "nauc_precision_at_5_max": -0.10044110423686131, + "nauc_precision_at_5_std": -0.4313118067160001, + "nauc_recall_at_1000_diff1": 0.05752354607693916, + "nauc_recall_at_1000_max": -0.13966155642172917, + "nauc_recall_at_1000_std": -0.4678997924853668, + "nauc_recall_at_100_diff1": 0.095591409978507, + "nauc_recall_at_100_max": -0.2158191204895722, + "nauc_recall_at_100_std": -0.5128449566054453, + "nauc_recall_at_10_diff1": 0.16220110878384578, + "nauc_recall_at_10_max": -0.1345709923140249, + "nauc_recall_at_10_std": -0.46291116768025076, + "nauc_recall_at_1_diff1": 0.24939930748384873, + "nauc_recall_at_1_max": -0.04027325429092402, + "nauc_recall_at_1_std": -0.29324722375976053, + "nauc_recall_at_20_diff1": 0.13901716406047343, + "nauc_recall_at_20_max": -0.1720367559050407, + "nauc_recall_at_20_std": -0.4997626479968452, + "nauc_recall_at_3_diff1": 0.1908686986212081, + "nauc_recall_at_3_max": -0.0832525985766609, + "nauc_recall_at_3_std": -0.3942375060814895, + "nauc_recall_at_5_diff1": 0.1793452260926134, + "nauc_recall_at_5_max": -0.10044110423686085, + "nauc_recall_at_5_std": -0.4313118067159998, + "ndcg_at_1": 0.20106, + "ndcg_at_10": 0.34846, + "ndcg_at_100": 0.39495, + "ndcg_at_1000": 0.41518, + "ndcg_at_20": 0.36699, + "ndcg_at_3": 0.29642, + "ndcg_at_5": 0.32411, + "precision_at_1": 0.20106, + "precision_at_10": 0.05076, + "precision_at_100": 0.00734, + "precision_at_1000": 0.0009, + "precision_at_20": 0.02903, + "precision_at_3": 0.12179, + "precision_at_5": 0.08654, + "recall_at_1": 0.20106, + "recall_at_10": 0.50757, + "recall_at_100": 0.73362, + "recall_at_1000": 0.89594, + "recall_at_20": 0.58056, + "recall_at_3": 0.36537, + "recall_at_5": 0.43268 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/PIQA.json b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/PIQA.json new file mode 100644 index 000000000..ca4f50d7a --- /dev/null +++ b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/PIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 338.34544491767883, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.3937, + "map_at_1": 0.24157, + "map_at_10": 0.34106, + "map_at_100": 0.34965, + "map_at_1000": 0.35023, + "map_at_20": 0.34616, + "map_at_3": 0.31311, + "map_at_5": 0.32992, + "mrr_at_1": 0.24156692056583243, + "mrr_at_10": 0.34105523602259186, + "mrr_at_100": 0.34964932423802847, + "mrr_at_1000": 0.35023132996133033, + "mrr_at_20": 0.3461592194199229, + "mrr_at_3": 0.3131120783460282, + "mrr_at_5": 0.32992383025027194, + "nauc_map_at_1000_diff1": 0.1706309343823077, + "nauc_map_at_1000_max": 0.04062035620543155, + "nauc_map_at_1000_std": -0.027489147485052184, + "nauc_map_at_100_diff1": 0.1703066825072172, + "nauc_map_at_100_max": 0.0402600933797749, + "nauc_map_at_100_std": -0.027383099366090288, + "nauc_map_at_10_diff1": 0.17107455323664242, + "nauc_map_at_10_max": 0.04367095976740331, + "nauc_map_at_10_std": -0.030210698952544298, + "nauc_map_at_1_diff1": 0.21770376392146593, + "nauc_map_at_1_max": 0.0714668106501985, + "nauc_map_at_1_std": -0.06051855035302245, + "nauc_map_at_20_diff1": 0.16975113916996026, + "nauc_map_at_20_max": 0.040643468020252725, + "nauc_map_at_20_std": -0.02923181499452345, + "nauc_map_at_3_diff1": 0.1796668138276226, + "nauc_map_at_3_max": 0.05781698878930715, + "nauc_map_at_3_std": -0.0424954808298209, + "nauc_map_at_5_diff1": 0.17437030018846633, + "nauc_map_at_5_max": 0.0489003304664027, + "nauc_map_at_5_std": -0.03444524699652663, + "nauc_mrr_at_1000_diff1": 0.1706309343823077, + "nauc_mrr_at_1000_max": 0.04062035620543155, + "nauc_mrr_at_1000_std": -0.027489147485052184, + "nauc_mrr_at_100_diff1": 0.1703066825072172, + "nauc_mrr_at_100_max": 0.0402600933797749, + "nauc_mrr_at_100_std": -0.027383099366090288, + "nauc_mrr_at_10_diff1": 0.17107455323664242, + "nauc_mrr_at_10_max": 0.04367095976740331, + "nauc_mrr_at_10_std": -0.030210698952544298, + "nauc_mrr_at_1_diff1": 0.21770376392146593, + "nauc_mrr_at_1_max": 0.0714668106501985, + "nauc_mrr_at_1_std": -0.06051855035302245, + "nauc_mrr_at_20_diff1": 0.16975113916996026, + "nauc_mrr_at_20_max": 0.040643468020252725, + "nauc_mrr_at_20_std": -0.02923181499452345, + "nauc_mrr_at_3_diff1": 0.1796668138276226, + "nauc_mrr_at_3_max": 0.05781698878930715, + "nauc_mrr_at_3_std": -0.0424954808298209, + "nauc_mrr_at_5_diff1": 0.17437030018846633, + "nauc_mrr_at_5_max": 0.0489003304664027, + "nauc_mrr_at_5_std": -0.03444524699652663, + "nauc_ndcg_at_1000_diff1": 0.15359190781079626, + "nauc_ndcg_at_1000_max": 0.011397762087509474, + "nauc_ndcg_at_1000_std": -0.002879152633998066, + "nauc_ndcg_at_100_diff1": 0.14699934244396257, + "nauc_ndcg_at_100_max": 0.005346697226467319, + "nauc_ndcg_at_100_std": 0.004150184601061039, + "nauc_ndcg_at_10_diff1": 0.1517053949525763, + "nauc_ndcg_at_10_max": 0.023594752967799844, + "nauc_ndcg_at_10_std": -0.011868363645725211, + "nauc_ndcg_at_1_diff1": 0.21770376392146593, + "nauc_ndcg_at_1_max": 0.0714668106501985, + "nauc_ndcg_at_1_std": -0.06051855035302245, + "nauc_ndcg_at_20_diff1": 0.14509229255775455, + "nauc_ndcg_at_20_max": 0.011310826191002633, + "nauc_ndcg_at_20_std": -0.007614690369484128, + "nauc_ndcg_at_3_diff1": 0.1685633716178798, + "nauc_ndcg_at_3_max": 0.05237266287303212, + "nauc_ndcg_at_3_std": -0.03675345370021543, + "nauc_ndcg_at_5_diff1": 0.1592178725564276, + "nauc_ndcg_at_5_max": 0.03685505347725154, + "nauc_ndcg_at_5_std": -0.022114775836671232, + "nauc_precision_at_1000_diff1": 0.03421164592649859, + "nauc_precision_at_1000_max": -0.32863555139012474, + "nauc_precision_at_1000_std": 0.20635313101813535, + "nauc_precision_at_100_diff1": 0.029242804943172097, + "nauc_precision_at_100_max": -0.20283897931673664, + "nauc_precision_at_100_std": 0.18790868665856303, + "nauc_precision_at_10_diff1": 0.09182460092551102, + "nauc_precision_at_10_max": -0.043151811557356486, + "nauc_precision_at_10_std": 0.047914430216606026, + "nauc_precision_at_1_diff1": 0.21770376392146593, + "nauc_precision_at_1_max": 0.0714668106501985, + "nauc_precision_at_1_std": -0.06051855035302245, + "nauc_precision_at_20_diff1": 0.0536816823400446, + "nauc_precision_at_20_max": -0.10520557955043415, + "nauc_precision_at_20_std": 0.07349893463430764, + "nauc_precision_at_3_diff1": 0.13881040331390226, + "nauc_precision_at_3_max": 0.037353967352202415, + "nauc_precision_at_3_std": -0.0212253763429309, + "nauc_precision_at_5_diff1": 0.11665659354353938, + "nauc_precision_at_5_max": 0.0016109531898813726, + "nauc_precision_at_5_std": 0.013928761991671411, + "nauc_recall_at_1000_diff1": 0.03421164592650202, + "nauc_recall_at_1000_max": -0.32863555139012063, + "nauc_recall_at_1000_std": 0.20635313101813785, + "nauc_recall_at_100_diff1": 0.02924280494317279, + "nauc_recall_at_100_max": -0.20283897931673722, + "nauc_recall_at_100_std": 0.18790868665856267, + "nauc_recall_at_10_diff1": 0.09182460092551126, + "nauc_recall_at_10_max": -0.0431518115573568, + "nauc_recall_at_10_std": 0.04791443021660595, + "nauc_recall_at_1_diff1": 0.21770376392146593, + "nauc_recall_at_1_max": 0.0714668106501985, + "nauc_recall_at_1_std": -0.06051855035302245, + "nauc_recall_at_20_diff1": 0.053681682340044584, + "nauc_recall_at_20_max": -0.10520557955043396, + "nauc_recall_at_20_std": 0.07349893463430783, + "nauc_recall_at_3_diff1": 0.13881040331390224, + "nauc_recall_at_3_max": 0.03735396735220242, + "nauc_recall_at_3_std": -0.021225376342930813, + "nauc_recall_at_5_diff1": 0.11665659354353947, + "nauc_recall_at_5_max": 0.0016109531898813726, + "nauc_recall_at_5_std": 0.013928761991671826, + "ndcg_at_1": 0.24157, + "ndcg_at_10": 0.3937, + "ndcg_at_100": 0.43703, + "ndcg_at_1000": 0.45411, + "ndcg_at_20": 0.41246, + "ndcg_at_3": 0.33638, + "ndcg_at_5": 0.36666, + "precision_at_1": 0.24157, + "precision_at_10": 0.05609, + "precision_at_100": 0.00767, + "precision_at_1000": 0.0009, + "precision_at_20": 0.03177, + "precision_at_3": 0.13457, + "precision_at_5": 0.09543, + "recall_at_1": 0.24157, + "recall_at_10": 0.56094, + "recall_at_100": 0.76659, + "recall_at_1000": 0.90479, + "recall_at_20": 0.63547, + "recall_at_3": 0.4037, + "recall_at_5": 0.47715 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/Quail.json b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/Quail.json new file mode 100644 index 000000000..4e8414755 --- /dev/null +++ b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/Quail.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 432.97549533843994, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07011, + "map_at_1": 0.02978, + "map_at_10": 0.05334, + "map_at_100": 0.05896, + "map_at_1000": 0.05981, + "map_at_20": 0.05626, + "map_at_3": 0.04283, + "map_at_5": 0.04756, + "mrr_at_1": 0.02977941176470588, + "mrr_at_10": 0.05334471288515405, + "mrr_at_100": 0.058961210510967706, + "mrr_at_1000": 0.05980581361366177, + "mrr_at_20": 0.05626325551036157, + "mrr_at_3": 0.04283088235294114, + "mrr_at_5": 0.047555147058823515, + "nauc_map_at_1000_diff1": 0.2024467766874177, + "nauc_map_at_1000_max": 0.12377946891542632, + "nauc_map_at_1000_std": 0.04921396246399497, + "nauc_map_at_100_diff1": 0.2024923024223881, + "nauc_map_at_100_max": 0.12379935962150498, + "nauc_map_at_100_std": 0.049053031764973526, + "nauc_map_at_10_diff1": 0.20612119131950568, + "nauc_map_at_10_max": 0.1230481196250419, + "nauc_map_at_10_std": 0.04682537251938641, + "nauc_map_at_1_diff1": 0.353665444355007, + "nauc_map_at_1_max": 0.13533540695690785, + "nauc_map_at_1_std": 0.020166486135540687, + "nauc_map_at_20_diff1": 0.20537576019784143, + "nauc_map_at_20_max": 0.12537881014844163, + "nauc_map_at_20_std": 0.048441100393077904, + "nauc_map_at_3_diff1": 0.24247449209706992, + "nauc_map_at_3_max": 0.11698532112838568, + "nauc_map_at_3_std": 0.03586134202987663, + "nauc_map_at_5_diff1": 0.22313925270888801, + "nauc_map_at_5_max": 0.11996194881239912, + "nauc_map_at_5_std": 0.03687408442873462, + "nauc_mrr_at_1000_diff1": 0.2024467766874177, + "nauc_mrr_at_1000_max": 0.12377946891542632, + "nauc_mrr_at_1000_std": 0.04921396246399497, + "nauc_mrr_at_100_diff1": 0.2024923024223881, + "nauc_mrr_at_100_max": 0.12379935962150498, + "nauc_mrr_at_100_std": 0.049053031764973526, + "nauc_mrr_at_10_diff1": 0.20612119131950568, + "nauc_mrr_at_10_max": 0.1230481196250419, + "nauc_mrr_at_10_std": 0.04682537251938641, + "nauc_mrr_at_1_diff1": 0.353665444355007, + "nauc_mrr_at_1_max": 0.13533540695690785, + "nauc_mrr_at_1_std": 0.020166486135540687, + "nauc_mrr_at_20_diff1": 0.20537576019784143, + "nauc_mrr_at_20_max": 0.12537881014844163, + "nauc_mrr_at_20_std": 0.048441100393077904, + "nauc_mrr_at_3_diff1": 0.24247449209706992, + "nauc_mrr_at_3_max": 0.11698532112838568, + "nauc_mrr_at_3_std": 0.03586134202987663, + "nauc_mrr_at_5_diff1": 0.22313925270888801, + "nauc_mrr_at_5_max": 0.11996194881239912, + "nauc_mrr_at_5_std": 0.03687408442873462, + "nauc_ndcg_at_1000_diff1": 0.14799879953438663, + "nauc_ndcg_at_1000_max": 0.12154944524543689, + "nauc_ndcg_at_1000_std": 0.0650172803982339, + "nauc_ndcg_at_100_diff1": 0.15563432105071673, + "nauc_ndcg_at_100_max": 0.12275230291552561, + "nauc_ndcg_at_100_std": 0.06324153537528845, + "nauc_ndcg_at_10_diff1": 0.1688729248337304, + "nauc_ndcg_at_10_max": 0.12789856577055045, + "nauc_ndcg_at_10_std": 0.058589205915158274, + "nauc_ndcg_at_1_diff1": 0.353665444355007, + "nauc_ndcg_at_1_max": 0.13533540695690785, + "nauc_ndcg_at_1_std": 0.020166486135540687, + "nauc_ndcg_at_20_diff1": 0.16915012378164426, + "nauc_ndcg_at_20_max": 0.13283463066681286, + "nauc_ndcg_at_20_std": 0.060183609328134456, + "nauc_ndcg_at_3_diff1": 0.2191662274274943, + "nauc_ndcg_at_3_max": 0.11390185789259234, + "nauc_ndcg_at_3_std": 0.03799595746282158, + "nauc_ndcg_at_5_diff1": 0.19321918110789582, + "nauc_ndcg_at_5_max": 0.11998241089205404, + "nauc_ndcg_at_5_std": 0.03954576183856076, + "nauc_precision_at_1000_diff1": 0.07104830742681356, + "nauc_precision_at_1000_max": 0.11161254017282095, + "nauc_precision_at_1000_std": 0.08416471794615281, + "nauc_precision_at_100_diff1": 0.10158045660819826, + "nauc_precision_at_100_max": 0.11730160103053909, + "nauc_precision_at_100_std": 0.0804727295618214, + "nauc_precision_at_10_diff1": 0.11612823668227261, + "nauc_precision_at_10_max": 0.13762461284816233, + "nauc_precision_at_10_std": 0.07783071656558006, + "nauc_precision_at_1_diff1": 0.353665444355007, + "nauc_precision_at_1_max": 0.13533540695690785, + "nauc_precision_at_1_std": 0.020166486135540687, + "nauc_precision_at_20_diff1": 0.1255005272299782, + "nauc_precision_at_20_max": 0.14498039523479675, + "nauc_precision_at_20_std": 0.07571227234414313, + "nauc_precision_at_3_diff1": 0.1723060165842565, + "nauc_precision_at_3_max": 0.10787752181634672, + "nauc_precision_at_3_std": 0.042022819323597416, + "nauc_precision_at_5_diff1": 0.14135289031988807, + "nauc_precision_at_5_max": 0.12111975673016731, + "nauc_precision_at_5_std": 0.044074769698595834, + "nauc_recall_at_1000_diff1": 0.07104830742681315, + "nauc_recall_at_1000_max": 0.11161254017282135, + "nauc_recall_at_1000_std": 0.08416471794615268, + "nauc_recall_at_100_diff1": 0.10158045660819816, + "nauc_recall_at_100_max": 0.11730160103053915, + "nauc_recall_at_100_std": 0.08047272956182146, + "nauc_recall_at_10_diff1": 0.1161282366822724, + "nauc_recall_at_10_max": 0.13762461284816208, + "nauc_recall_at_10_std": 0.07783071656557997, + "nauc_recall_at_1_diff1": 0.353665444355007, + "nauc_recall_at_1_max": 0.13533540695690785, + "nauc_recall_at_1_std": 0.020166486135540687, + "nauc_recall_at_20_diff1": 0.12550052722997806, + "nauc_recall_at_20_max": 0.14498039523479653, + "nauc_recall_at_20_std": 0.07571227234414303, + "nauc_recall_at_3_diff1": 0.17230601658425632, + "nauc_recall_at_3_max": 0.10787752181634658, + "nauc_recall_at_3_std": 0.042022819323597374, + "nauc_recall_at_5_diff1": 0.14135289031988788, + "nauc_recall_at_5_max": 0.12111975673016734, + "nauc_recall_at_5_std": 0.04407476969859602, + "ndcg_at_1": 0.02978, + "ndcg_at_10": 0.07011, + "ndcg_at_100": 0.10149, + "ndcg_at_1000": 0.13002, + "ndcg_at_20": 0.08072, + "ndcg_at_3": 0.04765, + "ndcg_at_5": 0.05622, + "precision_at_1": 0.02978, + "precision_at_10": 0.01254, + "precision_at_100": 0.00282, + "precision_at_1000": 0.00052, + "precision_at_20": 0.00836, + "precision_at_3": 0.02059, + "precision_at_5": 0.01654, + "recall_at_1": 0.02978, + "recall_at_10": 0.12537, + "recall_at_100": 0.28199, + "recall_at_1000": 0.52022, + "recall_at_20": 0.16728, + "recall_at_3": 0.06176, + "recall_at_5": 0.08272 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/RARbCode.json b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/RARbCode.json new file mode 100644 index 000000000..e156f5443 --- /dev/null +++ b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/RARbCode.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 17084.712911844254, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.78463, + "map_at_1": 0.62062, + "map_at_10": 0.7326, + "map_at_100": 0.73495, + "map_at_1000": 0.73497, + "map_at_20": 0.73419, + "map_at_3": 0.70766, + "map_at_5": 0.72414, + "mrr_at_1": 0.6206199460916442, + "mrr_at_10": 0.732620438112352, + "mrr_at_100": 0.7349754579338906, + "mrr_at_1000": 0.7349992638541668, + "mrr_at_20": 0.7342191816912368, + "mrr_at_3": 0.7076594788858942, + "mrr_at_5": 0.7242699910152743, + "nauc_map_at_1000_diff1": 0.5929652688857213, + "nauc_map_at_1000_max": 0.3734840092501638, + "nauc_map_at_1000_std": 0.03765795742099434, + "nauc_map_at_100_diff1": 0.5929397288945404, + "nauc_map_at_100_max": 0.37354411604063864, + "nauc_map_at_100_std": 0.03771810349556059, + "nauc_map_at_10_diff1": 0.5900021182420004, + "nauc_map_at_10_max": 0.3755328467059497, + "nauc_map_at_10_std": 0.03700027305172713, + "nauc_map_at_1_diff1": 0.6350519079656883, + "nauc_map_at_1_max": 0.3541674970713597, + "nauc_map_at_1_std": 0.03469724914248448, + "nauc_map_at_20_diff1": 0.5916321199415635, + "nauc_map_at_20_max": 0.37424316436783445, + "nauc_map_at_20_std": 0.03779932846386142, + "nauc_map_at_3_diff1": 0.5929482851181918, + "nauc_map_at_3_max": 0.3672808917096664, + "nauc_map_at_3_std": 0.0351406839835828, + "nauc_map_at_5_diff1": 0.5885179681849393, + "nauc_map_at_5_max": 0.37407555083835786, + "nauc_map_at_5_std": 0.03406549187362853, + "nauc_mrr_at_1000_diff1": 0.592964744810121, + "nauc_mrr_at_1000_max": 0.37347556695934825, + "nauc_mrr_at_1000_std": 0.03758674332614449, + "nauc_mrr_at_100_diff1": 0.592939202251854, + "nauc_mrr_at_100_max": 0.3735356808319797, + "nauc_mrr_at_100_std": 0.03764690323840936, + "nauc_mrr_at_10_diff1": 0.5899979709985809, + "nauc_mrr_at_10_max": 0.3755296759088841, + "nauc_mrr_at_10_std": 0.03693097939119071, + "nauc_mrr_at_1_diff1": 0.6350519079656883, + "nauc_mrr_at_1_max": 0.3541674970713597, + "nauc_mrr_at_1_std": 0.03469724914248448, + "nauc_mrr_at_20_diff1": 0.5916314612327869, + "nauc_mrr_at_20_max": 0.37423482944456343, + "nauc_mrr_at_20_std": 0.03772837897699405, + "nauc_mrr_at_3_diff1": 0.5929482851181918, + "nauc_mrr_at_3_max": 0.3672808917096664, + "nauc_mrr_at_3_std": 0.0351406839835828, + "nauc_mrr_at_5_diff1": 0.5884932010837262, + "nauc_mrr_at_5_max": 0.3740564519490051, + "nauc_mrr_at_5_std": 0.03366272616562256, + "nauc_ndcg_at_1000_diff1": 0.585334296523051, + "nauc_ndcg_at_1000_max": 0.38108219942399346, + "nauc_ndcg_at_1000_std": 0.042438338743430275, + "nauc_ndcg_at_100_diff1": 0.5844616849209289, + "nauc_ndcg_at_100_max": 0.38324222568654076, + "nauc_ndcg_at_100_std": 0.04471778728708908, + "nauc_ndcg_at_10_diff1": 0.5684382976274647, + "nauc_ndcg_at_10_max": 0.39386513916782834, + "nauc_ndcg_at_10_std": 0.041779896544423455, + "nauc_ndcg_at_1_diff1": 0.6350519079656883, + "nauc_ndcg_at_1_max": 0.3541674970713597, + "nauc_ndcg_at_1_std": 0.03469724914248448, + "nauc_ndcg_at_20_diff1": 0.5749196930505863, + "nauc_ndcg_at_20_max": 0.3888669678320748, + "nauc_ndcg_at_20_std": 0.04517153637336839, + "nauc_ndcg_at_3_diff1": 0.577304497234603, + "nauc_ndcg_at_3_max": 0.37297081733336734, + "nauc_ndcg_at_3_std": 0.034390533410145946, + "nauc_ndcg_at_5_diff1": 0.5656957438290487, + "nauc_ndcg_at_5_max": 0.3875099410088198, + "nauc_ndcg_at_5_std": 0.03203423367664053, + "nauc_precision_at_1000_diff1": 0.45611842798096025, + "nauc_precision_at_1000_max": 1.0, + "nauc_precision_at_1000_std": 1.0, + "nauc_precision_at_100_diff1": 0.39833219411944226, + "nauc_precision_at_100_max": 0.9550730789770656, + "nauc_precision_at_100_std": 0.7572804627757854, + "nauc_precision_at_10_diff1": 0.3116113979218008, + "nauc_precision_at_10_max": 0.6338810024605501, + "nauc_precision_at_10_std": 0.11558485414216631, + "nauc_precision_at_1_diff1": 0.6350519079656883, + "nauc_precision_at_1_max": 0.3541674970713597, + "nauc_precision_at_1_std": 0.03469724914248448, + "nauc_precision_at_20_diff1": 0.27199362833381735, + "nauc_precision_at_20_max": 0.695373110697573, + "nauc_precision_at_20_std": 0.23793020377342916, + "nauc_precision_at_3_diff1": 0.5143503216353648, + "nauc_precision_at_3_max": 0.39624989122091825, + "nauc_precision_at_3_std": 0.03094482737291809, + "nauc_precision_at_5_diff1": 0.4260657147474439, + "nauc_precision_at_5_max": 0.47222992126820107, + "nauc_precision_at_5_std": 0.01849934741635202, + "nauc_recall_at_1000_diff1": 0.4561184279810061, + "nauc_recall_at_1000_max": 1.0, + "nauc_recall_at_1000_std": 1.0, + "nauc_recall_at_100_diff1": 0.3983321941194253, + "nauc_recall_at_100_max": 0.9550730789770921, + "nauc_recall_at_100_std": 0.7572804627757659, + "nauc_recall_at_10_diff1": 0.31161139792180087, + "nauc_recall_at_10_max": 0.6338810024605501, + "nauc_recall_at_10_std": 0.11558485414216489, + "nauc_recall_at_1_diff1": 0.6350519079656883, + "nauc_recall_at_1_max": 0.3541674970713597, + "nauc_recall_at_1_std": 0.03469724914248448, + "nauc_recall_at_20_diff1": 0.27199362833381724, + "nauc_recall_at_20_max": 0.695373110697576, + "nauc_recall_at_20_std": 0.2379302037734288, + "nauc_recall_at_3_diff1": 0.5143503216353644, + "nauc_recall_at_3_max": 0.3962498912209181, + "nauc_recall_at_3_std": 0.03094482737291975, + "nauc_recall_at_5_diff1": 0.42606571474744315, + "nauc_recall_at_5_max": 0.4722299212682, + "nauc_recall_at_5_std": 0.018499347416351442, + "ndcg_at_1": 0.62062, + "ndcg_at_10": 0.78463, + "ndcg_at_100": 0.79498, + "ndcg_at_1000": 0.79566, + "ndcg_at_20": 0.79032, + "ndcg_at_3": 0.73521, + "ndcg_at_5": 0.76491, + "precision_at_1": 0.62062, + "precision_at_10": 0.09461, + "precision_at_100": 0.00992, + "precision_at_1000": 0.001, + "precision_at_20": 0.04842, + "precision_at_3": 0.27156, + "precision_at_5": 0.17736, + "recall_at_1": 0.62062, + "recall_at_10": 0.94609, + "recall_at_100": 0.99191, + "recall_at_1000": 0.9973, + "recall_at_20": 0.96833, + "recall_at_3": 0.81469, + "recall_at_5": 0.88679 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/RARbMath.json b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/RARbMath.json new file mode 100644 index 000000000..dddda4214 --- /dev/null +++ b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/RARbMath.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 24413.236557483673, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.7216, + "map_at_1": 0.652, + "map_at_10": 0.69736, + "map_at_100": 0.70286, + "map_at_1000": 0.70312, + "map_at_20": 0.70038, + "map_at_3": 0.68413, + "map_at_5": 0.69172, + "mrr_at_1": 0.6520018990346573, + "mrr_at_10": 0.697356862774651, + "mrr_at_100": 0.7028647253665379, + "mrr_at_1000": 0.7031181758467018, + "mrr_at_20": 0.7003754874371995, + "mrr_at_3": 0.6841272353220453, + "mrr_at_5": 0.6917154613071691, + "nauc_map_at_1000_diff1": 0.8807811803918761, + "nauc_map_at_1000_max": 0.18324053898580422, + "nauc_map_at_1000_std": -0.2878386705703647, + "nauc_map_at_100_diff1": 0.8806461825183529, + "nauc_map_at_100_max": 0.18326468537107612, + "nauc_map_at_100_std": -0.28774339821671213, + "nauc_map_at_10_diff1": 0.8802898680502851, + "nauc_map_at_10_max": 0.18118094235802124, + "nauc_map_at_10_std": -0.28998049696952083, + "nauc_map_at_1_diff1": 0.9045380164886351, + "nauc_map_at_1_max": 0.2002779578246019, + "nauc_map_at_1_std": -0.27894946161818707, + "nauc_map_at_20_diff1": 0.8804813110600248, + "nauc_map_at_20_max": 0.18265906564843482, + "nauc_map_at_20_std": -0.289400327511264, + "nauc_map_at_3_diff1": 0.8848372819544533, + "nauc_map_at_3_max": 0.18518181517414667, + "nauc_map_at_3_std": -0.2894431544748379, + "nauc_map_at_5_diff1": 0.8821130326103354, + "nauc_map_at_5_max": 0.18167565302732744, + "nauc_map_at_5_std": -0.29101704559667635, + "nauc_mrr_at_1000_diff1": 0.8807811803918761, + "nauc_mrr_at_1000_max": 0.18324053898580422, + "nauc_mrr_at_1000_std": -0.2878386705703647, + "nauc_mrr_at_100_diff1": 0.8806461825183529, + "nauc_mrr_at_100_max": 0.18326468537107612, + "nauc_mrr_at_100_std": -0.28774339821671213, + "nauc_mrr_at_10_diff1": 0.8802898680502851, + "nauc_mrr_at_10_max": 0.18118094235802124, + "nauc_mrr_at_10_std": -0.28998049696952083, + "nauc_mrr_at_1_diff1": 0.9045380164886351, + "nauc_mrr_at_1_max": 0.2002779578246019, + "nauc_mrr_at_1_std": -0.27894946161818707, + "nauc_mrr_at_20_diff1": 0.8804813110600248, + "nauc_mrr_at_20_max": 0.18265906564843482, + "nauc_mrr_at_20_std": -0.289400327511264, + "nauc_mrr_at_3_diff1": 0.8848372819544533, + "nauc_mrr_at_3_max": 0.18518181517414667, + "nauc_mrr_at_3_std": -0.2894431544748379, + "nauc_mrr_at_5_diff1": 0.8821130326103354, + "nauc_mrr_at_5_max": 0.18167565302732744, + "nauc_mrr_at_5_std": -0.29101704559667635, + "nauc_ndcg_at_1000_diff1": 0.874151708370118, + "nauc_ndcg_at_1000_max": 0.1821374458796071, + "nauc_ndcg_at_1000_std": -0.2807889085928365, + "nauc_ndcg_at_100_diff1": 0.870435921519535, + "nauc_ndcg_at_100_max": 0.1829872365222251, + "nauc_ndcg_at_100_std": -0.2767436645030936, + "nauc_ndcg_at_10_diff1": 0.868664703406769, + "nauc_ndcg_at_10_max": 0.1717941012674471, + "nauc_ndcg_at_10_std": -0.29362885620154056, + "nauc_ndcg_at_1_diff1": 0.9045380164886351, + "nauc_ndcg_at_1_max": 0.2002779578246019, + "nauc_ndcg_at_1_std": -0.27894946161818707, + "nauc_ndcg_at_20_diff1": 0.869003954612079, + "nauc_ndcg_at_20_max": 0.17746748129159398, + "nauc_ndcg_at_20_std": -0.2910124885438584, + "nauc_ndcg_at_3_diff1": 0.8789064535469379, + "nauc_ndcg_at_3_max": 0.18041302975232817, + "nauc_ndcg_at_3_std": -0.2932902988046104, + "nauc_ndcg_at_5_diff1": 0.8735470370853947, + "nauc_ndcg_at_5_max": 0.17378112969469686, + "nauc_ndcg_at_5_std": -0.29636222572363785, + "nauc_precision_at_1000_diff1": 0.7827021897718202, + "nauc_precision_at_1000_max": 0.36083216257154666, + "nauc_precision_at_1000_std": 0.4875377837336022, + "nauc_precision_at_100_diff1": 0.757582110628509, + "nauc_precision_at_100_max": 0.2372313452029244, + "nauc_precision_at_100_std": -0.023512766953351773, + "nauc_precision_at_10_diff1": 0.8197116161406102, + "nauc_precision_at_10_max": 0.13218128864895698, + "nauc_precision_at_10_std": -0.3068407289403753, + "nauc_precision_at_1_diff1": 0.9045380164886351, + "nauc_precision_at_1_max": 0.2002779578246019, + "nauc_precision_at_1_std": -0.27894946161818707, + "nauc_precision_at_20_diff1": 0.8097908317042212, + "nauc_precision_at_20_max": 0.15726738564771447, + "nauc_precision_at_20_std": -0.29287200162290233, + "nauc_precision_at_3_diff1": 0.8603719780621519, + "nauc_precision_at_3_max": 0.16542250924125684, + "nauc_precision_at_3_std": -0.3055817958437867, + "nauc_precision_at_5_diff1": 0.8433716304248922, + "nauc_precision_at_5_max": 0.14566288749696646, + "nauc_precision_at_5_std": -0.31540157304294675, + "nauc_recall_at_1000_diff1": 0.7827021897718263, + "nauc_recall_at_1000_max": 0.3608321625715521, + "nauc_recall_at_1000_std": 0.48753778373360623, + "nauc_recall_at_100_diff1": 0.75758211062851, + "nauc_recall_at_100_max": 0.237231345202925, + "nauc_recall_at_100_std": -0.02351276695335371, + "nauc_recall_at_10_diff1": 0.81971161614061, + "nauc_recall_at_10_max": 0.13218128864895715, + "nauc_recall_at_10_std": -0.3068407289403745, + "nauc_recall_at_1_diff1": 0.9045380164886351, + "nauc_recall_at_1_max": 0.2002779578246019, + "nauc_recall_at_1_std": -0.27894946161818707, + "nauc_recall_at_20_diff1": 0.8097908317042211, + "nauc_recall_at_20_max": 0.15726738564771262, + "nauc_recall_at_20_std": -0.2928720016229017, + "nauc_recall_at_3_diff1": 0.8603719780621517, + "nauc_recall_at_3_max": 0.1654225092412561, + "nauc_recall_at_3_std": -0.3055817958437884, + "nauc_recall_at_5_diff1": 0.843371630424892, + "nauc_recall_at_5_max": 0.14566288749696776, + "nauc_recall_at_5_std": -0.31540157304294536, + "ndcg_at_1": 0.652, + "ndcg_at_10": 0.7216, + "ndcg_at_100": 0.75052, + "ndcg_at_1000": 0.75702, + "ndcg_at_20": 0.73252, + "ndcg_at_3": 0.69431, + "ndcg_at_5": 0.70799, + "precision_at_1": 0.652, + "precision_at_10": 0.07989, + "precision_at_100": 0.00939, + "precision_at_1000": 0.00099, + "precision_at_20": 0.0421, + "precision_at_3": 0.24123, + "precision_at_5": 0.15138, + "recall_at_1": 0.652, + "recall_at_10": 0.79886, + "recall_at_100": 0.93876, + "recall_at_1000": 0.9894, + "recall_at_20": 0.84191, + "recall_at_3": 0.72369, + "recall_at_5": 0.75692 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/SIQA.json b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/SIQA.json new file mode 100644 index 000000000..2e6c11256 --- /dev/null +++ b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/SIQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 219.73563075065613, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.05424, + "map_at_1": 0.02405, + "map_at_10": 0.04312, + "map_at_100": 0.04732, + "map_at_1000": 0.04817, + "map_at_20": 0.04539, + "map_at_3": 0.03676, + "map_at_5": 0.04022, + "mrr_at_1": 0.024053224155578302, + "mrr_at_10": 0.04312013614725999, + "mrr_at_100": 0.04731591772578734, + "mrr_at_1000": 0.048169530144554544, + "mrr_at_20": 0.04539300513312702, + "mrr_at_3": 0.03676219720232003, + "mrr_at_5": 0.04021664960764245, + "nauc_map_at_1000_diff1": 0.11495644253255556, + "nauc_map_at_1000_max": 0.041122481450470275, + "nauc_map_at_1000_std": -0.08833458071543211, + "nauc_map_at_100_diff1": 0.11606902947199363, + "nauc_map_at_100_max": 0.04133498452028611, + "nauc_map_at_100_std": -0.08883466760855378, + "nauc_map_at_10_diff1": 0.1282384289609259, + "nauc_map_at_10_max": 0.041745107796087616, + "nauc_map_at_10_std": -0.10236315086838316, + "nauc_map_at_1_diff1": 0.2020131610815739, + "nauc_map_at_1_max": 0.06408781320560564, + "nauc_map_at_1_std": -0.1734745448329328, + "nauc_map_at_20_diff1": 0.12274109333509235, + "nauc_map_at_20_max": 0.04067753296833567, + "nauc_map_at_20_std": -0.09508828140024912, + "nauc_map_at_3_diff1": 0.15826409735297287, + "nauc_map_at_3_max": 0.057926232641085276, + "nauc_map_at_3_std": -0.12146136660725182, + "nauc_map_at_5_diff1": 0.14329024860896722, + "nauc_map_at_5_max": 0.05267947251643237, + "nauc_map_at_5_std": -0.11068169382346991, + "nauc_mrr_at_1000_diff1": 0.11495644253255556, + "nauc_mrr_at_1000_max": 0.041122481450470275, + "nauc_mrr_at_1000_std": -0.08833458071543211, + "nauc_mrr_at_100_diff1": 0.11606902947199363, + "nauc_mrr_at_100_max": 0.04133498452028611, + "nauc_mrr_at_100_std": -0.08883466760855378, + "nauc_mrr_at_10_diff1": 0.1282384289609259, + "nauc_mrr_at_10_max": 0.041745107796087616, + "nauc_mrr_at_10_std": -0.10236315086838316, + "nauc_mrr_at_1_diff1": 0.2020131610815739, + "nauc_mrr_at_1_max": 0.06408781320560564, + "nauc_mrr_at_1_std": -0.1734745448329328, + "nauc_mrr_at_20_diff1": 0.12274109333509235, + "nauc_mrr_at_20_max": 0.04067753296833567, + "nauc_mrr_at_20_std": -0.09508828140024912, + "nauc_mrr_at_3_diff1": 0.15826409735297287, + "nauc_mrr_at_3_max": 0.057926232641085276, + "nauc_mrr_at_3_std": -0.12146136660725182, + "nauc_mrr_at_5_diff1": 0.14329024860896722, + "nauc_mrr_at_5_max": 0.05267947251643237, + "nauc_mrr_at_5_std": -0.11068169382346991, + "nauc_ndcg_at_1000_diff1": 0.04898656015038281, + "nauc_ndcg_at_1000_max": 0.03209728123747616, + "nauc_ndcg_at_1000_std": -0.032544428843204576, + "nauc_ndcg_at_100_diff1": 0.06030970386306457, + "nauc_ndcg_at_100_max": 0.028352589843281477, + "nauc_ndcg_at_100_std": -0.04039101633233152, + "nauc_ndcg_at_10_diff1": 0.09910493338674464, + "nauc_ndcg_at_10_max": 0.026304974873432044, + "nauc_ndcg_at_10_std": -0.08094282133843679, + "nauc_ndcg_at_1_diff1": 0.2020131610815739, + "nauc_ndcg_at_1_max": 0.06408781320560564, + "nauc_ndcg_at_1_std": -0.1734745448329328, + "nauc_ndcg_at_20_diff1": 0.08644905178421834, + "nauc_ndcg_at_20_max": 0.02590488892312487, + "nauc_ndcg_at_20_std": -0.06357435197245333, + "nauc_ndcg_at_3_diff1": 0.14993391293957414, + "nauc_ndcg_at_3_max": 0.054084145898853464, + "nauc_ndcg_at_3_std": -0.1123610524255521, + "nauc_ndcg_at_5_diff1": 0.1277435430037909, + "nauc_ndcg_at_5_max": 0.046871916824644914, + "nauc_ndcg_at_5_std": -0.0971570838500936, + "nauc_precision_at_1000_diff1": -0.02573141081731376, + "nauc_precision_at_1000_max": 0.033490405974938665, + "nauc_precision_at_1000_std": 0.033567602828138386, + "nauc_precision_at_100_diff1": -0.007232867443680597, + "nauc_precision_at_100_max": 0.015960731399952622, + "nauc_precision_at_100_std": 0.01864625977827737, + "nauc_precision_at_10_diff1": 0.0506341313691547, + "nauc_precision_at_10_max": 5.985564007662635e-05, + "nauc_precision_at_10_std": -0.04616769777922553, + "nauc_precision_at_1_diff1": 0.2020131610815739, + "nauc_precision_at_1_max": 0.06408781320560564, + "nauc_precision_at_1_std": -0.1734745448329328, + "nauc_precision_at_20_diff1": 0.03373505540713122, + "nauc_precision_at_20_max": 0.00584526737642769, + "nauc_precision_at_20_std": -0.01743273821628674, + "nauc_precision_at_3_diff1": 0.1332977766823, + "nauc_precision_at_3_max": 0.045780235905457725, + "nauc_precision_at_3_std": -0.09437682451548596, + "nauc_precision_at_5_diff1": 0.09916644847006209, + "nauc_precision_at_5_max": 0.036010317911862176, + "nauc_precision_at_5_std": -0.07298734051028002, + "nauc_recall_at_1000_diff1": -0.025731410817313515, + "nauc_recall_at_1000_max": 0.03349040597493892, + "nauc_recall_at_1000_std": 0.033567602828138886, + "nauc_recall_at_100_diff1": -0.007232867443680518, + "nauc_recall_at_100_max": 0.01596073139995275, + "nauc_recall_at_100_std": 0.018646259778277465, + "nauc_recall_at_10_diff1": 0.0506341313691544, + "nauc_recall_at_10_max": 5.985564007665236e-05, + "nauc_recall_at_10_std": -0.04616769777922568, + "nauc_recall_at_1_diff1": 0.2020131610815739, + "nauc_recall_at_1_max": 0.06408781320560564, + "nauc_recall_at_1_std": -0.1734745448329328, + "nauc_recall_at_20_diff1": 0.03373505540713114, + "nauc_recall_at_20_max": 0.00584526737642767, + "nauc_recall_at_20_std": -0.01743273821628683, + "nauc_recall_at_3_diff1": 0.13329777668230008, + "nauc_recall_at_3_max": 0.045780235905457704, + "nauc_recall_at_3_std": -0.09437682451548596, + "nauc_recall_at_5_diff1": 0.0991664484700619, + "nauc_recall_at_5_max": 0.03601031791186213, + "nauc_recall_at_5_std": -0.07298734051028014, + "ndcg_at_1": 0.02405, + "ndcg_at_10": 0.05424, + "ndcg_at_100": 0.0777, + "ndcg_at_1000": 0.10581, + "ndcg_at_20": 0.06252, + "ndcg_at_3": 0.04098, + "ndcg_at_5": 0.04715, + "precision_at_1": 0.02405, + "precision_at_10": 0.00901, + "precision_at_100": 0.00207, + "precision_at_1000": 0.00044, + "precision_at_20": 0.00614, + "precision_at_3": 0.01774, + "precision_at_5": 0.01361, + "recall_at_1": 0.02405, + "recall_at_10": 0.09007, + "recall_at_100": 0.20727, + "recall_at_1000": 0.44063, + "recall_at_20": 0.12282, + "recall_at_3": 0.05322, + "recall_at_5": 0.06807 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/SpartQA.json b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/SpartQA.json new file mode 100644 index 000000000..7170b7489 --- /dev/null +++ b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/SpartQA.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 211.3927867412567, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.0992, + "map_at_1": 0.01104, + "map_at_10": 0.05876, + "map_at_100": 0.07063, + "map_at_1000": 0.07185, + "map_at_20": 0.06584, + "map_at_3": 0.03909, + "map_at_5": 0.04592, + "mrr_at_1": 0.015859766277128547, + "mrr_at_10": 0.0832573689835792, + "mrr_at_100": 0.09588350305963929, + "mrr_at_1000": 0.09701851206611416, + "mrr_at_20": 0.09125288495662597, + "mrr_at_3": 0.05643665368206277, + "mrr_at_5": 0.06688462251901323, + "nauc_map_at_1000_diff1": -0.23286075466699604, + "nauc_map_at_1000_max": -0.046050958388278176, + "nauc_map_at_1000_std": 0.5725109770031583, + "nauc_map_at_100_diff1": -0.23281092447303997, + "nauc_map_at_100_max": -0.04625739811778326, + "nauc_map_at_100_std": 0.5727456304470528, + "nauc_map_at_10_diff1": -0.2462890191925425, + "nauc_map_at_10_max": -0.04987283102453695, + "nauc_map_at_10_std": 0.5557180974308498, + "nauc_map_at_1_diff1": -0.3702259502073089, + "nauc_map_at_1_max": -0.1677613236690472, + "nauc_map_at_1_std": 0.5909418451415736, + "nauc_map_at_20_diff1": -0.2349635270186612, + "nauc_map_at_20_max": -0.03748656555941486, + "nauc_map_at_20_std": 0.5671205118465689, + "nauc_map_at_3_diff1": -0.2966089580202498, + "nauc_map_at_3_max": -0.12304349866256868, + "nauc_map_at_3_std": 0.5376268193863688, + "nauc_map_at_5_diff1": -0.27055926876789543, + "nauc_map_at_5_max": -0.10209913327837979, + "nauc_map_at_5_std": 0.5353864468916979, + "nauc_mrr_at_1000_diff1": -0.19860301855912524, + "nauc_mrr_at_1000_max": -0.044814454105442984, + "nauc_mrr_at_1000_std": 0.5339695433913254, + "nauc_mrr_at_100_diff1": -0.19771799626217132, + "nauc_mrr_at_100_max": -0.0451398078256146, + "nauc_mrr_at_100_std": 0.5339383756834271, + "nauc_mrr_at_10_diff1": -0.2128534390935401, + "nauc_mrr_at_10_max": -0.047665610931982544, + "nauc_mrr_at_10_std": 0.5295041747001401, + "nauc_mrr_at_1_diff1": -0.37120258927150906, + "nauc_mrr_at_1_max": -0.15190845850418566, + "nauc_mrr_at_1_std": 0.5668083223386812, + "nauc_mrr_at_20_diff1": -0.19830914845593706, + "nauc_mrr_at_20_max": -0.04154073520085975, + "nauc_mrr_at_20_std": 0.5310456052857289, + "nauc_mrr_at_3_diff1": -0.2788332124318274, + "nauc_mrr_at_3_max": -0.11138784611414146, + "nauc_mrr_at_3_std": 0.5301807344999788, + "nauc_mrr_at_5_diff1": -0.24875778756082018, + "nauc_mrr_at_5_max": -0.09521566955615747, + "nauc_mrr_at_5_std": 0.5235105552831472, + "nauc_ndcg_at_1000_diff1": -0.17363972349974255, + "nauc_ndcg_at_1000_max": -0.01492151056343056, + "nauc_ndcg_at_1000_std": 0.576591054375062, + "nauc_ndcg_at_100_diff1": -0.16800016782713395, + "nauc_ndcg_at_100_max": -0.020429135525155826, + "nauc_ndcg_at_100_std": 0.5980823643771044, + "nauc_ndcg_at_10_diff1": -0.20130991884528562, + "nauc_ndcg_at_10_max": -0.006093738668531763, + "nauc_ndcg_at_10_std": 0.5513138832579529, + "nauc_ndcg_at_1_diff1": -0.37120258927150906, + "nauc_ndcg_at_1_max": -0.15190845850418566, + "nauc_ndcg_at_1_std": 0.5668083223386812, + "nauc_ndcg_at_20_diff1": -0.17633251719157558, + "nauc_ndcg_at_20_max": 0.01472335085495324, + "nauc_ndcg_at_20_std": 0.5696378216367146, + "nauc_ndcg_at_3_diff1": -0.2812280134212883, + "nauc_ndcg_at_3_max": -0.11335957860949537, + "nauc_ndcg_at_3_std": 0.5320705978538605, + "nauc_ndcg_at_5_diff1": -0.2432217723535717, + "nauc_ndcg_at_5_max": -0.08592251933280144, + "nauc_ndcg_at_5_std": 0.5256172037859747, + "nauc_precision_at_1000_diff1": 0.08204880661058148, + "nauc_precision_at_1000_max": -0.031093233913889178, + "nauc_precision_at_1000_std": 0.03805382891912894, + "nauc_precision_at_100_diff1": -0.02310919898420372, + "nauc_precision_at_100_max": -0.061875816822936115, + "nauc_precision_at_100_std": 0.43992046382513766, + "nauc_precision_at_10_diff1": -0.11928036382899963, + "nauc_precision_at_10_max": 0.050727485727328936, + "nauc_precision_at_10_std": 0.5299975061001752, + "nauc_precision_at_1_diff1": -0.37120258927150906, + "nauc_precision_at_1_max": -0.15190845850418566, + "nauc_precision_at_1_std": 0.5668083223386812, + "nauc_precision_at_20_diff1": -0.06772319429128673, + "nauc_precision_at_20_max": 0.06469662226912691, + "nauc_precision_at_20_std": 0.5302187193129839, + "nauc_precision_at_3_diff1": -0.24841877439759735, + "nauc_precision_at_3_max": -0.09155982282705014, + "nauc_precision_at_3_std": 0.5238056465040731, + "nauc_precision_at_5_diff1": -0.1928195114743962, + "nauc_precision_at_5_max": -0.06154087459512756, + "nauc_precision_at_5_std": 0.5105996492834357, + "nauc_recall_at_1000_diff1": -0.07268550136544791, + "nauc_recall_at_1000_max": 0.04573345824260608, + "nauc_recall_at_1000_std": 0.37144997658969625, + "nauc_recall_at_100_diff1": -0.10075965504004485, + "nauc_recall_at_100_max": 0.013639105534376387, + "nauc_recall_at_100_std": 0.5895682830538508, + "nauc_recall_at_10_diff1": -0.16287906975051672, + "nauc_recall_at_10_max": 0.04666142750674828, + "nauc_recall_at_10_std": 0.5415438647678746, + "nauc_recall_at_1_diff1": -0.3702259502073089, + "nauc_recall_at_1_max": -0.1677613236690472, + "nauc_recall_at_1_std": 0.5909418451415736, + "nauc_recall_at_20_diff1": -0.12388178421819335, + "nauc_recall_at_20_max": 0.07554652716256682, + "nauc_recall_at_20_std": 0.548334996039985, + "nauc_recall_at_3_diff1": -0.27024938854086766, + "nauc_recall_at_3_max": -0.10688703298201796, + "nauc_recall_at_3_std": 0.5275377569455324, + "nauc_recall_at_5_diff1": -0.21489673389259972, + "nauc_recall_at_5_max": -0.06458573061127922, + "nauc_recall_at_5_std": 0.5102432147383027, + "ndcg_at_1": 0.01586, + "ndcg_at_10": 0.0992, + "ndcg_at_100": 0.15982, + "ndcg_at_1000": 0.1994, + "ndcg_at_20": 0.12502, + "ndcg_at_3": 0.05294, + "ndcg_at_5": 0.06667, + "precision_at_1": 0.01586, + "precision_at_10": 0.02997, + "precision_at_100": 0.0075, + "precision_at_1000": 0.00126, + "precision_at_20": 0.02244, + "precision_at_3": 0.03664, + "precision_at_5": 0.03161, + "recall_at_1": 0.01104, + "recall_at_10": 0.19616, + "recall_at_100": 0.44871, + "recall_at_1000": 0.73363, + "recall_at_20": 0.28594, + "recall_at_3": 0.07596, + "recall_at_5": 0.10592 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL1.json b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL1.json new file mode 100644 index 000000000..933132761 --- /dev/null +++ b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL1.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 75.03464198112488, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.03311, + "map_at_1": 0.009, + "map_at_10": 0.02267, + "map_at_100": 0.02932, + "map_at_1000": 0.0312, + "map_at_20": 0.02535, + "map_at_3": 0.01558, + "map_at_5": 0.01886, + "mrr_at_1": 0.009, + "mrr_at_10": 0.022669742063492076, + "mrr_at_100": 0.029315116151917762, + "mrr_at_1000": 0.031200759670001185, + "mrr_at_20": 0.025353779550557815, + "mrr_at_3": 0.01558333333333334, + "mrr_at_5": 0.018858333333333345, + "nauc_map_at_1000_diff1": 0.09560746002206057, + "nauc_map_at_1000_max": 0.052908908825937434, + "nauc_map_at_1000_std": 0.12617326943823495, + "nauc_map_at_100_diff1": 0.09575440511543094, + "nauc_map_at_100_max": 0.053297822840770614, + "nauc_map_at_100_std": 0.12362945783281672, + "nauc_map_at_10_diff1": 0.11078449139340565, + "nauc_map_at_10_max": 0.056054350493140156, + "nauc_map_at_10_std": 0.11514133782818865, + "nauc_map_at_1_diff1": 0.18878007333869976, + "nauc_map_at_1_max": -0.05663625793757267, + "nauc_map_at_1_std": 0.09233670214351726, + "nauc_map_at_20_diff1": 0.10190928387679968, + "nauc_map_at_20_max": 0.05339640743990952, + "nauc_map_at_20_std": 0.12231309894498237, + "nauc_map_at_3_diff1": 0.15831861441798464, + "nauc_map_at_3_max": 0.06627385934982334, + "nauc_map_at_3_std": 0.11843764751796768, + "nauc_map_at_5_diff1": 0.1340212902206148, + "nauc_map_at_5_max": 0.06454630379332903, + "nauc_map_at_5_std": 0.11425124916989762, + "nauc_mrr_at_1000_diff1": 0.09560746002206057, + "nauc_mrr_at_1000_max": 0.052908908825937434, + "nauc_mrr_at_1000_std": 0.12617326943823495, + "nauc_mrr_at_100_diff1": 0.09575440511543094, + "nauc_mrr_at_100_max": 0.053297822840770614, + "nauc_mrr_at_100_std": 0.12362945783281672, + "nauc_mrr_at_10_diff1": 0.11078449139340565, + "nauc_mrr_at_10_max": 0.056054350493140156, + "nauc_mrr_at_10_std": 0.11514133782818865, + "nauc_mrr_at_1_diff1": 0.18878007333869976, + "nauc_mrr_at_1_max": -0.05663625793757267, + "nauc_mrr_at_1_std": 0.09233670214351726, + "nauc_mrr_at_20_diff1": 0.10190928387679968, + "nauc_mrr_at_20_max": 0.05339640743990952, + "nauc_mrr_at_20_std": 0.12231309894498237, + "nauc_mrr_at_3_diff1": 0.15831861441798464, + "nauc_mrr_at_3_max": 0.06627385934982334, + "nauc_mrr_at_3_std": 0.11843764751796768, + "nauc_mrr_at_5_diff1": 0.1340212902206148, + "nauc_mrr_at_5_max": 0.06454630379332903, + "nauc_mrr_at_5_std": 0.11425124916989762, + "nauc_ndcg_at_1000_diff1": 0.05927909836115439, + "nauc_ndcg_at_1000_max": 0.07125815840686432, + "nauc_ndcg_at_1000_std": 0.176892699268648, + "nauc_ndcg_at_100_diff1": 0.05746333991907111, + "nauc_ndcg_at_100_max": 0.047778204610374075, + "nauc_ndcg_at_100_std": 0.1353633341804153, + "nauc_ndcg_at_10_diff1": 0.08370675649936146, + "nauc_ndcg_at_10_max": 0.06086929276495771, + "nauc_ndcg_at_10_std": 0.11486713413131758, + "nauc_ndcg_at_1_diff1": 0.18878007333869976, + "nauc_ndcg_at_1_max": -0.05663625793757267, + "nauc_ndcg_at_1_std": 0.09233670214351726, + "nauc_ndcg_at_20_diff1": 0.07045181764106269, + "nauc_ndcg_at_20_max": 0.05397353826847814, + "nauc_ndcg_at_20_std": 0.13049327504651637, + "nauc_ndcg_at_3_diff1": 0.1555449894182965, + "nauc_ndcg_at_3_max": 0.08636434386990435, + "nauc_ndcg_at_3_std": 0.12142488941227564, + "nauc_ndcg_at_5_diff1": 0.12060732184048115, + "nauc_ndcg_at_5_max": 0.07962197914477366, + "nauc_ndcg_at_5_std": 0.11535360041933491, + "nauc_precision_at_1000_diff1": 0.02398187935203316, + "nauc_precision_at_1000_max": 0.15225966345408654, + "nauc_precision_at_1000_std": 0.31788693933587736, + "nauc_precision_at_100_diff1": 0.033050909682302634, + "nauc_precision_at_100_max": 0.03830183487308776, + "nauc_precision_at_100_std": 0.1445510671688852, + "nauc_precision_at_10_diff1": 0.05069129878943789, + "nauc_precision_at_10_max": 0.06276239366151601, + "nauc_precision_at_10_std": 0.11356614687731802, + "nauc_precision_at_1_diff1": 0.18878007333869976, + "nauc_precision_at_1_max": -0.05663625793757267, + "nauc_precision_at_1_std": 0.09233670214351726, + "nauc_precision_at_20_diff1": 0.0412043634690471, + "nauc_precision_at_20_max": 0.05100874866597211, + "nauc_precision_at_20_std": 0.13897406074858912, + "nauc_precision_at_3_diff1": 0.15089386726562085, + "nauc_precision_at_3_max": 0.123667082504654, + "nauc_precision_at_3_std": 0.1266821384214937, + "nauc_precision_at_5_diff1": 0.09947116508131593, + "nauc_precision_at_5_max": 0.10070020859118707, + "nauc_precision_at_5_std": 0.116618918614816, + "nauc_recall_at_1000_diff1": 0.023981879352034864, + "nauc_recall_at_1000_max": 0.15225966345408717, + "nauc_recall_at_1000_std": 0.3178869393358775, + "nauc_recall_at_100_diff1": 0.03305090968230267, + "nauc_recall_at_100_max": 0.03830183487308781, + "nauc_recall_at_100_std": 0.14455106716888524, + "nauc_recall_at_10_diff1": 0.0506912987894379, + "nauc_recall_at_10_max": 0.06276239366151605, + "nauc_recall_at_10_std": 0.11356614687731814, + "nauc_recall_at_1_diff1": 0.18878007333869976, + "nauc_recall_at_1_max": -0.05663625793757267, + "nauc_recall_at_1_std": 0.09233670214351726, + "nauc_recall_at_20_diff1": 0.04120436346904743, + "nauc_recall_at_20_max": 0.05100874866597228, + "nauc_recall_at_20_std": 0.13897406074858937, + "nauc_recall_at_3_diff1": 0.15089386726562098, + "nauc_recall_at_3_max": 0.12366708250465393, + "nauc_recall_at_3_std": 0.12668213842149376, + "nauc_recall_at_5_diff1": 0.09947116508131586, + "nauc_recall_at_5_max": 0.10070020859118711, + "nauc_recall_at_5_std": 0.1166189186148159, + "ndcg_at_1": 0.009, + "ndcg_at_10": 0.03311, + "ndcg_at_100": 0.07548, + "ndcg_at_1000": 0.13896, + "ndcg_at_20": 0.04302, + "ndcg_at_3": 0.0178, + "ndcg_at_5": 0.02374, + "precision_at_1": 0.009, + "precision_at_10": 0.0068, + "precision_at_100": 0.0029, + "precision_at_1000": 0.00082, + "precision_at_20": 0.00538, + "precision_at_3": 0.00808, + "precision_at_5": 0.00775, + "recall_at_1": 0.009, + "recall_at_10": 0.068, + "recall_at_100": 0.2905, + "recall_at_1000": 0.81925, + "recall_at_20": 0.1075, + "recall_at_3": 0.02425, + "recall_at_5": 0.03875 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL2Fact.json b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL2Fact.json new file mode 100644 index 000000000..c1df3f764 --- /dev/null +++ b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL2Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 677.7236580848694, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.36901, + "map_at_1": 0.16583, + "map_at_10": 0.29571, + "map_at_100": 0.30762, + "map_at_1000": 0.30813, + "map_at_20": 0.3033, + "map_at_3": 0.25301, + "map_at_5": 0.27889, + "mrr_at_1": 0.16583287011302575, + "mrr_at_10": 0.2957102858436926, + "mrr_at_100": 0.3076189277653598, + "mrr_at_1000": 0.3081307307365851, + "mrr_at_20": 0.30330070012028937, + "mrr_at_3": 0.2530109319992581, + "mrr_at_5": 0.2788864183805819, + "nauc_map_at_1000_diff1": 0.10798400244789594, + "nauc_map_at_1000_max": 0.11065044791576518, + "nauc_map_at_1000_std": -0.0071313026394219355, + "nauc_map_at_100_diff1": 0.10778009099432584, + "nauc_map_at_100_max": 0.11111205585192899, + "nauc_map_at_100_std": -0.00657374394115593, + "nauc_map_at_10_diff1": 0.10688973244064244, + "nauc_map_at_10_max": 0.10957588233839809, + "nauc_map_at_10_std": -0.011773458167177871, + "nauc_map_at_1_diff1": 0.15185102164494405, + "nauc_map_at_1_max": 0.08188223512940723, + "nauc_map_at_1_std": -0.035124354879624245, + "nauc_map_at_20_diff1": 0.1076459122525317, + "nauc_map_at_20_max": 0.11209081194915155, + "nauc_map_at_20_std": -0.006787718625418808, + "nauc_map_at_3_diff1": 0.11721262573795455, + "nauc_map_at_3_max": 0.08779326667030785, + "nauc_map_at_3_std": -0.03276223224334703, + "nauc_map_at_5_diff1": 0.11357025587495595, + "nauc_map_at_5_max": 0.09947013860387215, + "nauc_map_at_5_std": -0.02423376691620934, + "nauc_mrr_at_1000_diff1": 0.10797518012604988, + "nauc_mrr_at_1000_max": 0.11065368785250737, + "nauc_mrr_at_1000_std": -0.0071321228559090635, + "nauc_mrr_at_100_diff1": 0.10777128415189297, + "nauc_mrr_at_100_max": 0.11111528905515, + "nauc_mrr_at_100_std": -0.006574564282057013, + "nauc_mrr_at_10_diff1": 0.10688973244064244, + "nauc_mrr_at_10_max": 0.10957588233839809, + "nauc_mrr_at_10_std": -0.011773458167177871, + "nauc_mrr_at_1_diff1": 0.15185102164494405, + "nauc_mrr_at_1_max": 0.08188223512940723, + "nauc_mrr_at_1_std": -0.035124354879624245, + "nauc_mrr_at_20_diff1": 0.10763720563658352, + "nauc_mrr_at_20_max": 0.1120940058645664, + "nauc_mrr_at_20_std": -0.006788529090192044, + "nauc_mrr_at_3_diff1": 0.11721262573795455, + "nauc_mrr_at_3_max": 0.08779326667030785, + "nauc_mrr_at_3_std": -0.03276223224334703, + "nauc_mrr_at_5_diff1": 0.11357025587495595, + "nauc_mrr_at_5_max": 0.09947013860387215, + "nauc_mrr_at_5_std": -0.02423376691620934, + "nauc_ndcg_at_1000_diff1": 0.0923005365140789, + "nauc_ndcg_at_1000_max": 0.1262920187915749, + "nauc_ndcg_at_1000_std": 0.020387410866576923, + "nauc_ndcg_at_100_diff1": 0.08606368475732293, + "nauc_ndcg_at_100_max": 0.13844577180266504, + "nauc_ndcg_at_100_std": 0.03897135196406021, + "nauc_ndcg_at_10_diff1": 0.08454059007443096, + "nauc_ndcg_at_10_max": 0.13319885825935276, + "nauc_ndcg_at_10_std": 0.01443495682662275, + "nauc_ndcg_at_1_diff1": 0.15185102164494405, + "nauc_ndcg_at_1_max": 0.08188223512940723, + "nauc_ndcg_at_1_std": -0.035124354879624245, + "nauc_ndcg_at_20_diff1": 0.08613559989830545, + "nauc_ndcg_at_20_max": 0.14347040981195883, + "nauc_ndcg_at_20_std": 0.03333203868971001, + "nauc_ndcg_at_3_diff1": 0.10772651553501, + "nauc_ndcg_at_3_max": 0.08877238362491177, + "nauc_ndcg_at_3_std": -0.03079851972872417, + "nauc_ndcg_at_5_diff1": 0.10077122004965888, + "nauc_ndcg_at_5_max": 0.10906460814426072, + "nauc_ndcg_at_5_std": -0.015477374178039682, + "nauc_precision_at_1000_diff1": -0.28002461173726695, + "nauc_precision_at_1000_max": 0.28916455308017497, + "nauc_precision_at_1000_std": 0.6692414056810747, + "nauc_precision_at_100_diff1": -0.07882668350502285, + "nauc_precision_at_100_max": 0.3565236831501692, + "nauc_precision_at_100_std": 0.45770712328466956, + "nauc_precision_at_10_diff1": 0.015748508281446305, + "nauc_precision_at_10_max": 0.2097153593116054, + "nauc_precision_at_10_std": 0.10075179510595494, + "nauc_precision_at_1_diff1": 0.15185102164494405, + "nauc_precision_at_1_max": 0.08188223512940723, + "nauc_precision_at_1_std": -0.035124354879624245, + "nauc_precision_at_20_diff1": 0.0065394376030746765, + "nauc_precision_at_20_max": 0.2730725993178367, + "nauc_precision_at_20_std": 0.20346720690047768, + "nauc_precision_at_3_diff1": 0.08446352709249763, + "nauc_precision_at_3_max": 0.09101059353027233, + "nauc_precision_at_3_std": -0.0256475307991083, + "nauc_precision_at_5_diff1": 0.06788405208374436, + "nauc_precision_at_5_max": 0.13517468997617982, + "nauc_precision_at_5_std": 0.008738674356857554, + "nauc_recall_at_1000_diff1": -0.2800246117372565, + "nauc_recall_at_1000_max": 0.28916455308017186, + "nauc_recall_at_1000_std": 0.6692414056810699, + "nauc_recall_at_100_diff1": -0.07882668350502572, + "nauc_recall_at_100_max": 0.35652368315016647, + "nauc_recall_at_100_std": 0.457707123284666, + "nauc_recall_at_10_diff1": 0.015748508281446603, + "nauc_recall_at_10_max": 0.20971535931160507, + "nauc_recall_at_10_std": 0.10075179510595492, + "nauc_recall_at_1_diff1": 0.15185102164494405, + "nauc_recall_at_1_max": 0.08188223512940723, + "nauc_recall_at_1_std": -0.035124354879624245, + "nauc_recall_at_20_diff1": 0.006539437603074937, + "nauc_recall_at_20_max": 0.27307259931783684, + "nauc_recall_at_20_std": 0.2034672069004771, + "nauc_recall_at_3_diff1": 0.08446352709249759, + "nauc_recall_at_3_max": 0.09101059353027213, + "nauc_recall_at_3_std": -0.025647530799108195, + "nauc_recall_at_5_diff1": 0.0678840520837444, + "nauc_recall_at_5_max": 0.13517468997617985, + "nauc_recall_at_5_std": 0.008738674356857136, + "ndcg_at_1": 0.16583, + "ndcg_at_10": 0.36901, + "ndcg_at_100": 0.42716, + "ndcg_at_1000": 0.44042, + "ndcg_at_20": 0.39607, + "ndcg_at_3": 0.28202, + "ndcg_at_5": 0.32861, + "precision_at_1": 0.16583, + "precision_at_10": 0.06033, + "precision_at_100": 0.00877, + "precision_at_1000": 0.00098, + "precision_at_20": 0.03545, + "precision_at_3": 0.12204, + "precision_at_5": 0.09583, + "recall_at_1": 0.16583, + "recall_at_10": 0.6033, + "recall_at_100": 0.8766, + "recall_at_1000": 0.98054, + "recall_at_20": 0.7091, + "recall_at_3": 0.36613, + "recall_at_5": 0.47916 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL2Pure.json b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL2Pure.json new file mode 100644 index 000000000..2d61fe3d8 --- /dev/null +++ b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL2Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 115.93518805503845, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.09179, + "map_at_1": 0.03706, + "map_at_10": 0.06976, + "map_at_100": 0.07763, + "map_at_1000": 0.07895, + "map_at_20": 0.07318, + "map_at_3": 0.0559, + "map_at_5": 0.06243, + "mrr_at_1": 0.03705762460626274, + "mrr_at_10": 0.0697596548346965, + "mrr_at_100": 0.0776334501690106, + "mrr_at_1000": 0.07894597044730152, + "mrr_at_20": 0.07317639197736397, + "mrr_at_3": 0.05589525044777963, + "mrr_at_5": 0.06242665678463333, + "nauc_map_at_1000_diff1": 0.1779908535099438, + "nauc_map_at_1000_max": 0.17155439874137512, + "nauc_map_at_1000_std": 0.14718956073095557, + "nauc_map_at_100_diff1": 0.1780985518605007, + "nauc_map_at_100_max": 0.17205137728697736, + "nauc_map_at_100_std": 0.14583943773147703, + "nauc_map_at_10_diff1": 0.191632818160112, + "nauc_map_at_10_max": 0.16963120067174986, + "nauc_map_at_10_std": 0.13008044841837554, + "nauc_map_at_1_diff1": 0.2581320026293719, + "nauc_map_at_1_max": 0.12488688380183438, + "nauc_map_at_1_std": 0.11343645853976699, + "nauc_map_at_20_diff1": 0.18511610490030908, + "nauc_map_at_20_max": 0.1698584047585038, + "nauc_map_at_20_std": 0.13390986667567956, + "nauc_map_at_3_diff1": 0.2283947060916413, + "nauc_map_at_3_max": 0.15891246880718274, + "nauc_map_at_3_std": 0.11498064798607774, + "nauc_map_at_5_diff1": 0.2120172842464332, + "nauc_map_at_5_max": 0.16958255643738757, + "nauc_map_at_5_std": 0.1255016163894116, + "nauc_mrr_at_1000_diff1": 0.1779908535099438, + "nauc_mrr_at_1000_max": 0.17155439874137512, + "nauc_mrr_at_1000_std": 0.14718956073095557, + "nauc_mrr_at_100_diff1": 0.1780985518605007, + "nauc_mrr_at_100_max": 0.17205137728697736, + "nauc_mrr_at_100_std": 0.14583943773147703, + "nauc_mrr_at_10_diff1": 0.191632818160112, + "nauc_mrr_at_10_max": 0.16963120067174986, + "nauc_mrr_at_10_std": 0.13008044841837554, + "nauc_mrr_at_1_diff1": 0.2581320026293719, + "nauc_mrr_at_1_max": 0.12488688380183438, + "nauc_mrr_at_1_std": 0.11343645853976699, + "nauc_mrr_at_20_diff1": 0.18511610490030908, + "nauc_mrr_at_20_max": 0.1698584047585038, + "nauc_mrr_at_20_std": 0.13390986667567956, + "nauc_mrr_at_3_diff1": 0.2283947060916413, + "nauc_mrr_at_3_max": 0.15891246880718274, + "nauc_mrr_at_3_std": 0.11498064798607774, + "nauc_mrr_at_5_diff1": 0.2120172842464332, + "nauc_mrr_at_5_max": 0.16958255643738757, + "nauc_mrr_at_5_std": 0.1255016163894116, + "nauc_ndcg_at_1000_diff1": 0.10986405114312818, + "nauc_ndcg_at_1000_max": 0.17043467515825708, + "nauc_ndcg_at_1000_std": 0.2305788027792979, + "nauc_ndcg_at_100_diff1": 0.1119130550353275, + "nauc_ndcg_at_100_max": 0.18996168142347686, + "nauc_ndcg_at_100_std": 0.21536836127131495, + "nauc_ndcg_at_10_diff1": 0.16055934778537445, + "nauc_ndcg_at_10_max": 0.17856804048078834, + "nauc_ndcg_at_10_std": 0.1382259885537814, + "nauc_ndcg_at_1_diff1": 0.2581320026293719, + "nauc_ndcg_at_1_max": 0.12488688380183438, + "nauc_ndcg_at_1_std": 0.11343645853976699, + "nauc_ndcg_at_20_diff1": 0.14599989821455817, + "nauc_ndcg_at_20_max": 0.17887675112694462, + "nauc_ndcg_at_20_std": 0.14856650801095395, + "nauc_ndcg_at_3_diff1": 0.22123715239168978, + "nauc_ndcg_at_3_max": 0.16469533855385018, + "nauc_ndcg_at_3_std": 0.11404215648750336, + "nauc_ndcg_at_5_diff1": 0.19694919164276095, + "nauc_ndcg_at_5_max": 0.17972394653132362, + "nauc_ndcg_at_5_std": 0.13059307576897905, + "nauc_precision_at_1000_diff1": -0.05950660626424406, + "nauc_precision_at_1000_max": 0.11114085738817492, + "nauc_precision_at_1000_std": 0.4856991677653216, + "nauc_precision_at_100_diff1": 0.009759931923144413, + "nauc_precision_at_100_max": 0.21732838540647234, + "nauc_precision_at_100_std": 0.3461575362334147, + "nauc_precision_at_10_diff1": 0.11007071288065474, + "nauc_precision_at_10_max": 0.19122059328447683, + "nauc_precision_at_10_std": 0.15143880678170443, + "nauc_precision_at_1_diff1": 0.2581320026293719, + "nauc_precision_at_1_max": 0.12488688380183438, + "nauc_precision_at_1_std": 0.11343645853976699, + "nauc_precision_at_20_diff1": 0.08843822112982429, + "nauc_precision_at_20_max": 0.19025587738795785, + "nauc_precision_at_20_std": 0.1718267883112007, + "nauc_precision_at_3_diff1": 0.2066863382234092, + "nauc_precision_at_3_max": 0.17599776789601523, + "nauc_precision_at_3_std": 0.11188727047963463, + "nauc_precision_at_5_diff1": 0.16942124664146774, + "nauc_precision_at_5_max": 0.19752947783087324, + "nauc_precision_at_5_std": 0.14038476838531275, + "nauc_recall_at_1000_diff1": -0.05950660626424417, + "nauc_recall_at_1000_max": 0.11114085738817545, + "nauc_recall_at_1000_std": 0.4856991677653214, + "nauc_recall_at_100_diff1": 0.00975993192314393, + "nauc_recall_at_100_max": 0.21732838540647215, + "nauc_recall_at_100_std": 0.3461575362334142, + "nauc_recall_at_10_diff1": 0.11007071288065473, + "nauc_recall_at_10_max": 0.1912205932844766, + "nauc_recall_at_10_std": 0.15143880678170413, + "nauc_recall_at_1_diff1": 0.2581320026293719, + "nauc_recall_at_1_max": 0.12488688380183438, + "nauc_recall_at_1_std": 0.11343645853976699, + "nauc_recall_at_20_diff1": 0.08843822112982425, + "nauc_recall_at_20_max": 0.19025587738795788, + "nauc_recall_at_20_std": 0.17182678831120066, + "nauc_recall_at_3_diff1": 0.20668633822340926, + "nauc_recall_at_3_max": 0.17599776789601534, + "nauc_recall_at_3_std": 0.1118872704796347, + "nauc_recall_at_5_diff1": 0.16942124664146768, + "nauc_recall_at_5_max": 0.19752947783087313, + "nauc_recall_at_5_std": 0.14038476838531266, + "ndcg_at_1": 0.03706, + "ndcg_at_10": 0.09179, + "ndcg_at_100": 0.13999, + "ndcg_at_1000": 0.18138, + "ndcg_at_20": 0.10449, + "ndcg_at_3": 0.0624, + "ndcg_at_5": 0.07428, + "precision_at_1": 0.03706, + "precision_at_10": 0.0164, + "precision_at_100": 0.00413, + "precision_at_1000": 0.00075, + "precision_at_20": 0.01074, + "precision_at_3": 0.02711, + "precision_at_5": 0.02209, + "recall_at_1": 0.03706, + "recall_at_10": 0.16398, + "recall_at_100": 0.41282, + "recall_at_1000": 0.75283, + "recall_at_20": 0.21475, + "recall_at_3": 0.08134, + "recall_at_5": 0.11043 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL3Fact.json b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL3Fact.json new file mode 100644 index 000000000..83a7fca5b --- /dev/null +++ b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL3Fact.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 600.2640588283539, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.30178, + "map_at_1": 0.09489, + "map_at_10": 0.22575, + "map_at_100": 0.23839, + "map_at_1000": 0.23901, + "map_at_20": 0.23336, + "map_at_3": 0.18128, + "map_at_5": 0.20646, + "mrr_at_1": 0.09489380930863081, + "mrr_at_10": 0.22575482896879273, + "mrr_at_100": 0.23839322617860317, + "mrr_at_1000": 0.2390142706317883, + "mrr_at_20": 0.233361825243469, + "mrr_at_3": 0.18127730079831345, + "mrr_at_5": 0.20645805091128341, + "nauc_map_at_1000_diff1": 0.03724887911609598, + "nauc_map_at_1000_max": 0.10883598602337559, + "nauc_map_at_1000_std": 0.07183046169594055, + "nauc_map_at_100_diff1": 0.037125607113830485, + "nauc_map_at_100_max": 0.10938095647963059, + "nauc_map_at_100_std": 0.0725175754630326, + "nauc_map_at_10_diff1": 0.0379545973625009, + "nauc_map_at_10_max": 0.1090184024433112, + "nauc_map_at_10_std": 0.0674235775430351, + "nauc_map_at_1_diff1": 0.057592277912781646, + "nauc_map_at_1_max": 0.004950175112919832, + "nauc_map_at_1_std": -0.012474752493762547, + "nauc_map_at_20_diff1": 0.03668351655126937, + "nauc_map_at_20_max": 0.11129948937896958, + "nauc_map_at_20_std": 0.07216724498194978, + "nauc_map_at_3_diff1": 0.04870053193586836, + "nauc_map_at_3_max": 0.07492487441935004, + "nauc_map_at_3_std": 0.03322110019097862, + "nauc_map_at_5_diff1": 0.044263927860569104, + "nauc_map_at_5_max": 0.09249325698696167, + "nauc_map_at_5_std": 0.047692373175135395, + "nauc_mrr_at_1000_diff1": 0.03724887571425186, + "nauc_mrr_at_1000_max": 0.10883598473616013, + "nauc_mrr_at_1000_std": 0.07183046347299794, + "nauc_mrr_at_100_diff1": 0.037125607113830485, + "nauc_mrr_at_100_max": 0.10938095647963059, + "nauc_mrr_at_100_std": 0.0725175754630326, + "nauc_mrr_at_10_diff1": 0.0379545973625009, + "nauc_mrr_at_10_max": 0.1090184024433112, + "nauc_mrr_at_10_std": 0.0674235775430351, + "nauc_mrr_at_1_diff1": 0.057592277912781646, + "nauc_mrr_at_1_max": 0.004950175112919832, + "nauc_mrr_at_1_std": -0.012474752493762547, + "nauc_mrr_at_20_diff1": 0.03668351655126937, + "nauc_mrr_at_20_max": 0.11129948937896958, + "nauc_mrr_at_20_std": 0.07216724498194978, + "nauc_mrr_at_3_diff1": 0.04870053193586836, + "nauc_mrr_at_3_max": 0.07492487441935004, + "nauc_mrr_at_3_std": 0.03322110019097862, + "nauc_mrr_at_5_diff1": 0.044263927860569104, + "nauc_mrr_at_5_max": 0.09249325698696167, + "nauc_mrr_at_5_std": 0.047692373175135395, + "nauc_ndcg_at_1000_diff1": 0.024414812799289656, + "nauc_ndcg_at_1000_max": 0.136747656453027, + "nauc_ndcg_at_1000_std": 0.11261084748583747, + "nauc_ndcg_at_100_diff1": 0.020733678738652957, + "nauc_ndcg_at_100_max": 0.15154180331275935, + "nauc_ndcg_at_100_std": 0.13438436761170616, + "nauc_ndcg_at_10_diff1": 0.02476201080777624, + "nauc_ndcg_at_10_max": 0.15396948016826184, + "nauc_ndcg_at_10_std": 0.11077663712421623, + "nauc_ndcg_at_1_diff1": 0.057592277912781646, + "nauc_ndcg_at_1_max": 0.004950175112919832, + "nauc_ndcg_at_1_std": -0.012474752493762547, + "nauc_ndcg_at_20_diff1": 0.020188151180667874, + "nauc_ndcg_at_20_max": 0.16340247535275365, + "nauc_ndcg_at_20_std": 0.12768250135600298, + "nauc_ndcg_at_3_diff1": 0.045793531185688206, + "nauc_ndcg_at_3_max": 0.08929545433788426, + "nauc_ndcg_at_3_std": 0.04429729136686767, + "nauc_ndcg_at_5_diff1": 0.038252115973877406, + "nauc_ndcg_at_5_max": 0.11745107119986356, + "nauc_ndcg_at_5_std": 0.0676754811431249, + "nauc_precision_at_1000_diff1": -0.2578374776582962, + "nauc_precision_at_1000_max": 0.26904397558672216, + "nauc_precision_at_1000_std": 0.6976740123879938, + "nauc_precision_at_100_diff1": -0.07424813704337356, + "nauc_precision_at_100_max": 0.34618287417941146, + "nauc_precision_at_100_std": 0.5001652267423938, + "nauc_precision_at_10_diff1": -0.00879006722689268, + "nauc_precision_at_10_max": 0.26488294941643314, + "nauc_precision_at_10_std": 0.22004888196800584, + "nauc_precision_at_1_diff1": 0.057592277912781646, + "nauc_precision_at_1_max": 0.004950175112919832, + "nauc_precision_at_1_std": -0.012474752493762547, + "nauc_precision_at_20_diff1": -0.03006928278444131, + "nauc_precision_at_20_max": 0.31660123838039833, + "nauc_precision_at_20_std": 0.29643194753840696, + "nauc_precision_at_3_diff1": 0.03947619539997362, + "nauc_precision_at_3_max": 0.11927760317570002, + "nauc_precision_at_3_std": 0.06780103408946563, + "nauc_precision_at_5_diff1": 0.024904276991256608, + "nauc_precision_at_5_max": 0.17064335595324343, + "nauc_precision_at_5_std": 0.11081361537057274, + "nauc_recall_at_1000_diff1": -0.2578374776583054, + "nauc_recall_at_1000_max": 0.2690439755867107, + "nauc_recall_at_1000_std": 0.697674012387989, + "nauc_recall_at_100_diff1": -0.07424813704337309, + "nauc_recall_at_100_max": 0.34618287417941124, + "nauc_recall_at_100_std": 0.500165226742394, + "nauc_recall_at_10_diff1": -0.00879006722689288, + "nauc_recall_at_10_max": 0.26488294941643314, + "nauc_recall_at_10_std": 0.2200488819680057, + "nauc_recall_at_1_diff1": 0.057592277912781646, + "nauc_recall_at_1_max": 0.004950175112919832, + "nauc_recall_at_1_std": -0.012474752493762547, + "nauc_recall_at_20_diff1": -0.030069282784441417, + "nauc_recall_at_20_max": 0.31660123838039717, + "nauc_recall_at_20_std": 0.2964319475384064, + "nauc_recall_at_3_diff1": 0.03947619539997377, + "nauc_recall_at_3_max": 0.11927760317570016, + "nauc_recall_at_3_std": 0.06780103408946547, + "nauc_recall_at_5_diff1": 0.024904276991256403, + "nauc_recall_at_5_max": 0.1706433559532433, + "nauc_recall_at_5_std": 0.1108136153705726, + "ndcg_at_1": 0.09489, + "ndcg_at_10": 0.30178, + "ndcg_at_100": 0.36469, + "ndcg_at_1000": 0.38124, + "ndcg_at_20": 0.32907, + "ndcg_at_3": 0.21053, + "ndcg_at_5": 0.25579, + "precision_at_1": 0.09489, + "precision_at_10": 0.05456, + "precision_at_100": 0.00843, + "precision_at_1000": 0.00097, + "precision_at_20": 0.03264, + "precision_at_3": 0.09851, + "precision_at_5": 0.08102, + "recall_at_1": 0.09489, + "recall_at_10": 0.54564, + "recall_at_100": 0.8432, + "recall_at_1000": 0.97357, + "recall_at_20": 0.65273, + "recall_at_3": 0.29553, + "recall_at_5": 0.40511 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL3Pure.json b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL3Pure.json new file mode 100644 index 000000000..5ac9e91a5 --- /dev/null +++ b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/TempReasonL3Pure.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 107.60992360115051, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.14307, + "map_at_1": 0.02915, + "map_at_10": 0.09914, + "map_at_100": 0.1099, + "map_at_1000": 0.11095, + "map_at_20": 0.1046, + "map_at_3": 0.07305, + "map_at_5": 0.087, + "mrr_at_1": 0.029145955716222322, + "mrr_at_10": 0.09914125764780964, + "mrr_at_100": 0.10990090034301175, + "mrr_at_1000": 0.11095459398197137, + "mrr_at_20": 0.10460143308190409, + "mrr_at_3": 0.07305317065823164, + "mrr_at_5": 0.08700482000301217, + "nauc_map_at_1000_diff1": -0.05431856456887418, + "nauc_map_at_1000_max": 0.17057748839419623, + "nauc_map_at_1000_std": 0.1906410669814937, + "nauc_map_at_100_diff1": -0.05437721717518394, + "nauc_map_at_100_max": 0.17132553444433926, + "nauc_map_at_100_std": 0.19082109541467848, + "nauc_map_at_10_diff1": -0.05320929561653756, + "nauc_map_at_10_max": 0.15905703611222305, + "nauc_map_at_10_std": 0.17292554976697502, + "nauc_map_at_1_diff1": -0.11786932589453815, + "nauc_map_at_1_max": -0.028478638888659452, + "nauc_map_at_1_std": -0.0007118466864463999, + "nauc_map_at_20_diff1": -0.05558027259631608, + "nauc_map_at_20_max": 0.1679677855101044, + "nauc_map_at_20_std": 0.18509495221559966, + "nauc_map_at_3_diff1": -0.03434208244815758, + "nauc_map_at_3_max": 0.10735181721376574, + "nauc_map_at_3_std": 0.10130799992506055, + "nauc_map_at_5_diff1": -0.04345038450979126, + "nauc_map_at_5_max": 0.1378323147025714, + "nauc_map_at_5_std": 0.13813769360932607, + "nauc_mrr_at_1000_diff1": -0.05431856456887418, + "nauc_mrr_at_1000_max": 0.17057748839419623, + "nauc_mrr_at_1000_std": 0.1906410669814937, + "nauc_mrr_at_100_diff1": -0.05437721717518394, + "nauc_mrr_at_100_max": 0.17132553444433926, + "nauc_mrr_at_100_std": 0.19082109541467848, + "nauc_mrr_at_10_diff1": -0.05320929561653756, + "nauc_mrr_at_10_max": 0.15905703611222305, + "nauc_mrr_at_10_std": 0.17292554976697502, + "nauc_mrr_at_1_diff1": -0.11786932589453815, + "nauc_mrr_at_1_max": -0.028478638888659452, + "nauc_mrr_at_1_std": -0.0007118466864463999, + "nauc_mrr_at_20_diff1": -0.05558027259631608, + "nauc_mrr_at_20_max": 0.1679677855101044, + "nauc_mrr_at_20_std": 0.18509495221559966, + "nauc_mrr_at_3_diff1": -0.03434208244815758, + "nauc_mrr_at_3_max": 0.10735181721376574, + "nauc_mrr_at_3_std": 0.10130799992506055, + "nauc_mrr_at_5_diff1": -0.04345038450979126, + "nauc_mrr_at_5_max": 0.1378323147025714, + "nauc_mrr_at_5_std": 0.13813769360932607, + "nauc_ndcg_at_1000_diff1": -0.06496181798413737, + "nauc_ndcg_at_1000_max": 0.22142387963506485, + "nauc_ndcg_at_1000_std": 0.2835688076784791, + "nauc_ndcg_at_100_diff1": -0.06061296396187632, + "nauc_ndcg_at_100_max": 0.2418096576228028, + "nauc_ndcg_at_100_std": 0.2880508096304826, + "nauc_ndcg_at_10_diff1": -0.058138117926207655, + "nauc_ndcg_at_10_max": 0.20192658856562146, + "nauc_ndcg_at_10_std": 0.22799309261499867, + "nauc_ndcg_at_1_diff1": -0.11786932589453815, + "nauc_ndcg_at_1_max": -0.028478638888659452, + "nauc_ndcg_at_1_std": -0.0007118466864463999, + "nauc_ndcg_at_20_diff1": -0.06498330727020375, + "nauc_ndcg_at_20_max": 0.2263543959268336, + "nauc_ndcg_at_20_std": 0.26080037620932767, + "nauc_ndcg_at_3_diff1": -0.025756829847810213, + "nauc_ndcg_at_3_max": 0.12554318324090272, + "nauc_ndcg_at_3_std": 0.11704963553163023, + "nauc_ndcg_at_5_diff1": -0.040233997972921105, + "nauc_ndcg_at_5_max": 0.16591412663515365, + "nauc_ndcg_at_5_std": 0.1673036247070124, + "nauc_precision_at_1000_diff1": -0.14154922682229462, + "nauc_precision_at_1000_max": 0.31124206440438135, + "nauc_precision_at_1000_std": 0.6211890129557128, + "nauc_precision_at_100_diff1": -0.07381914776188685, + "nauc_precision_at_100_max": 0.36944568761696367, + "nauc_precision_at_100_std": 0.47178884708242025, + "nauc_precision_at_10_diff1": -0.06852526725664888, + "nauc_precision_at_10_max": 0.26432399024431963, + "nauc_precision_at_10_std": 0.3110504042168929, + "nauc_precision_at_1_diff1": -0.11786932589453815, + "nauc_precision_at_1_max": -0.028478638888659452, + "nauc_precision_at_1_std": -0.0007118466864463999, + "nauc_precision_at_20_diff1": -0.08345935173211756, + "nauc_precision_at_20_max": 0.3155811755529319, + "nauc_precision_at_20_std": 0.3792255942939401, + "nauc_precision_at_3_diff1": -0.011798701151154382, + "nauc_precision_at_3_max": 0.15610143510355637, + "nauc_precision_at_3_std": 0.14386316267478047, + "nauc_precision_at_5_diff1": -0.03694353866313133, + "nauc_precision_at_5_max": 0.2084441230442611, + "nauc_precision_at_5_std": 0.21245322374577133, + "nauc_recall_at_1000_diff1": -0.14154922682229573, + "nauc_recall_at_1000_max": 0.3112420644043808, + "nauc_recall_at_1000_std": 0.6211890129557123, + "nauc_recall_at_100_diff1": -0.073819147761887, + "nauc_recall_at_100_max": 0.3694456876169637, + "nauc_recall_at_100_std": 0.4717888470824191, + "nauc_recall_at_10_diff1": -0.06852526725664908, + "nauc_recall_at_10_max": 0.2643239902443192, + "nauc_recall_at_10_std": 0.3110504042168929, + "nauc_recall_at_1_diff1": -0.11786932589453815, + "nauc_recall_at_1_max": -0.028478638888659452, + "nauc_recall_at_1_std": -0.0007118466864463999, + "nauc_recall_at_20_diff1": -0.0834593517321178, + "nauc_recall_at_20_max": 0.31558117555293164, + "nauc_recall_at_20_std": 0.37922559429394026, + "nauc_recall_at_3_diff1": -0.011798701151154344, + "nauc_recall_at_3_max": 0.15610143510355648, + "nauc_recall_at_3_std": 0.14386316267478064, + "nauc_recall_at_5_diff1": -0.03694353866313169, + "nauc_recall_at_5_max": 0.20844412304426105, + "nauc_recall_at_5_std": 0.21245322374577108, + "ndcg_at_1": 0.02915, + "ndcg_at_10": 0.14307, + "ndcg_at_100": 0.20279, + "ndcg_at_1000": 0.23507, + "ndcg_at_20": 0.16326, + "ndcg_at_3": 0.08828, + "ndcg_at_5": 0.11361, + "precision_at_1": 0.02915, + "precision_at_10": 0.02858, + "precision_at_100": 0.00582, + "precision_at_1000": 0.00084, + "precision_at_20": 0.01831, + "precision_at_3": 0.04421, + "precision_at_5": 0.03891, + "recall_at_1": 0.02915, + "recall_at_10": 0.28581, + "recall_at_100": 0.58179, + "recall_at_1000": 0.84478, + "recall_at_20": 0.36624, + "recall_at_3": 0.13263, + "recall_at_5": 0.19453 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/WinoGrande.json b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/WinoGrande.json new file mode 100644 index 000000000..b6e16ff1e --- /dev/null +++ b/results/e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/WinoGrande.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 30.699522972106934, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.41205, + "map_at_1": 0.18232, + "map_at_10": 0.32896, + "map_at_100": 0.34034, + "map_at_1000": 0.34072, + "map_at_20": 0.33729, + "map_at_3": 0.28295, + "map_at_5": 0.31002, + "mrr_at_1": 0.18232044198895028, + "mrr_at_10": 0.3289563523383567, + "mrr_at_100": 0.3403428062649534, + "mrr_at_1000": 0.34072442223682137, + "mrr_at_20": 0.33728603890898157, + "mrr_at_3": 0.28295185477505896, + "mrr_at_5": 0.31002367797947833, + "nauc_map_at_1000_diff1": -0.002357271863585553, + "nauc_map_at_1000_max": -0.18360168841597801, + "nauc_map_at_1000_std": -0.08646067514595294, + "nauc_map_at_100_diff1": -0.0023925586806218357, + "nauc_map_at_100_max": -0.18385199802803578, + "nauc_map_at_100_std": -0.08648299791911704, + "nauc_map_at_10_diff1": -0.0018835362630197526, + "nauc_map_at_10_max": -0.18713187515173374, + "nauc_map_at_10_std": -0.09208161424870344, + "nauc_map_at_1_diff1": 0.02109445472300063, + "nauc_map_at_1_max": -0.10966463242914876, + "nauc_map_at_1_std": -0.03302115552975712, + "nauc_map_at_20_diff1": -0.002326541296204376, + "nauc_map_at_20_max": -0.18553411730664243, + "nauc_map_at_20_std": -0.08879995799702338, + "nauc_map_at_3_diff1": -0.0029952558482351484, + "nauc_map_at_3_max": -0.16517651986466364, + "nauc_map_at_3_std": -0.07079925396732104, + "nauc_map_at_5_diff1": -0.0005832008866637332, + "nauc_map_at_5_max": -0.18143328154509147, + "nauc_map_at_5_std": -0.08795427436043407, + "nauc_mrr_at_1000_diff1": -0.002357271863585553, + "nauc_mrr_at_1000_max": -0.18360168841597801, + "nauc_mrr_at_1000_std": -0.08646067514595294, + "nauc_mrr_at_100_diff1": -0.0023925586806218357, + "nauc_mrr_at_100_max": -0.18385199802803578, + "nauc_mrr_at_100_std": -0.08648299791911704, + "nauc_mrr_at_10_diff1": -0.0018835362630197526, + "nauc_mrr_at_10_max": -0.18713187515173374, + "nauc_mrr_at_10_std": -0.09208161424870344, + "nauc_mrr_at_1_diff1": 0.02109445472300063, + "nauc_mrr_at_1_max": -0.10966463242914876, + "nauc_mrr_at_1_std": -0.03302115552975712, + "nauc_mrr_at_20_diff1": -0.002326541296204376, + "nauc_mrr_at_20_max": -0.18553411730664243, + "nauc_mrr_at_20_std": -0.08879995799702338, + "nauc_mrr_at_3_diff1": -0.0029952558482351484, + "nauc_mrr_at_3_max": -0.16517651986466364, + "nauc_mrr_at_3_std": -0.07079925396732104, + "nauc_mrr_at_5_diff1": -0.0005832008866637332, + "nauc_mrr_at_5_max": -0.18143328154509147, + "nauc_mrr_at_5_std": -0.08795427436043407, + "nauc_ndcg_at_1000_diff1": -0.00398696507213063, + "nauc_ndcg_at_1000_max": -0.20166934420902977, + "nauc_ndcg_at_1000_std": -0.09723422926036995, + "nauc_ndcg_at_100_diff1": -0.004639283372445723, + "nauc_ndcg_at_100_max": -0.20904302067330205, + "nauc_ndcg_at_100_std": -0.09757890829615057, + "nauc_ndcg_at_10_diff1": -0.005767857540408127, + "nauc_ndcg_at_10_max": -0.22600642386781936, + "nauc_ndcg_at_10_std": -0.125498520920987, + "nauc_ndcg_at_1_diff1": 0.02109445472300063, + "nauc_ndcg_at_1_max": -0.10966463242914876, + "nauc_ndcg_at_1_std": -0.03302115552975712, + "nauc_ndcg_at_20_diff1": -0.006787204923971058, + "nauc_ndcg_at_20_max": -0.22239129283594516, + "nauc_ndcg_at_20_std": -0.11533349620231903, + "nauc_ndcg_at_3_diff1": -0.007484815134638149, + "nauc_ndcg_at_3_max": -0.18112203225330323, + "nauc_ndcg_at_3_std": -0.08223477756155548, + "nauc_ndcg_at_5_diff1": -0.0032660062483348268, + "nauc_ndcg_at_5_max": -0.20950689958324117, + "nauc_ndcg_at_5_std": -0.11222910081326722, + "nauc_precision_at_1000_diff1": 0.2860792439451145, + "nauc_precision_at_1000_max": -0.37405385486588977, + "nauc_precision_at_1000_std": -0.07198299466712164, + "nauc_precision_at_100_diff1": 0.0064207867085220305, + "nauc_precision_at_100_max": -0.3875418243058469, + "nauc_precision_at_100_std": -0.09895861243244268, + "nauc_precision_at_10_diff1": -0.016828916543548494, + "nauc_precision_at_10_max": -0.36303554611845734, + "nauc_precision_at_10_std": -0.24502842281981643, + "nauc_precision_at_1_diff1": 0.02109445472300063, + "nauc_precision_at_1_max": -0.10966463242914876, + "nauc_precision_at_1_std": -0.03302115552975712, + "nauc_precision_at_20_diff1": -0.02442806755987545, + "nauc_precision_at_20_max": -0.4005693519116794, + "nauc_precision_at_20_std": -0.23864031503593217, + "nauc_precision_at_3_diff1": -0.01820686243131798, + "nauc_precision_at_3_max": -0.22143490751895953, + "nauc_precision_at_3_std": -0.1112966404852547, + "nauc_precision_at_5_diff1": -0.009116494310715562, + "nauc_precision_at_5_max": -0.2874672884598583, + "nauc_precision_at_5_std": -0.18055416189531698, + "nauc_recall_at_1000_diff1": 0.28607924394514894, + "nauc_recall_at_1000_max": -0.3740538548658987, + "nauc_recall_at_1000_std": -0.07198299466712185, + "nauc_recall_at_100_diff1": 0.006420786708522207, + "nauc_recall_at_100_max": -0.38754182430584855, + "nauc_recall_at_100_std": -0.09895861243244161, + "nauc_recall_at_10_diff1": -0.01682891654354807, + "nauc_recall_at_10_max": -0.36303554611845684, + "nauc_recall_at_10_std": -0.2450284228198164, + "nauc_recall_at_1_diff1": 0.02109445472300063, + "nauc_recall_at_1_max": -0.10966463242914876, + "nauc_recall_at_1_std": -0.03302115552975712, + "nauc_recall_at_20_diff1": -0.02442806755987422, + "nauc_recall_at_20_max": -0.4005693519116786, + "nauc_recall_at_20_std": -0.23864031503593144, + "nauc_recall_at_3_diff1": -0.01820686243131784, + "nauc_recall_at_3_max": -0.2214349075189594, + "nauc_recall_at_3_std": -0.11129664048525463, + "nauc_recall_at_5_diff1": -0.00911649431071532, + "nauc_recall_at_5_max": -0.2874672884598585, + "nauc_recall_at_5_std": -0.18055416189531703, + "ndcg_at_1": 0.18232, + "ndcg_at_10": 0.41205, + "ndcg_at_100": 0.46405, + "ndcg_at_1000": 0.47412, + "ndcg_at_20": 0.44214, + "ndcg_at_3": 0.31701, + "ndcg_at_5": 0.36628, + "precision_at_1": 0.18232, + "precision_at_10": 0.0678, + "precision_at_100": 0.00914, + "precision_at_1000": 0.00099, + "precision_at_20": 0.03982, + "precision_at_3": 0.13865, + "precision_at_5": 0.10734, + "recall_at_1": 0.18232, + "recall_at_10": 0.67798, + "recall_at_100": 0.91397, + "recall_at_1000": 0.9929, + "recall_at_20": 0.79637, + "recall_at_3": 0.41594, + "recall_at_5": 0.5367 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/text-embedding-3-large-instruct/no_revision_available/ARCChallenge.json b/results/text-embedding-3-large-instruct/no_revision_available/ARCChallenge.json new file mode 100644 index 000000000..d0dd52a46 --- /dev/null +++ b/results/text-embedding-3-large-instruct/no_revision_available/ARCChallenge.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.21216, + "ndcg_at_1": 0.08703, + "ndcg_at_3": 0.16213, + "ndcg_at_5": 0.18468, + "ndcg_at_10": 0.21216, + "ndcg_at_100": 0.27681, + "ndcg_at_1000": 0.3099, + "map_at_1": 0.08703, + "map_at_3": 0.14306, + "map_at_5": 0.1556, + "map_at_10": 0.16688, + "map_at_100": 0.17883, + "map_at_1000": 0.18002, + "recall_at_1": 0.08703, + "recall_at_3": 0.21758, + "recall_at_5": 0.27218, + "recall_at_10": 0.35751, + "recall_at_100": 0.67491, + "recall_at_1000": 0.93857, + "precision_at_1": 0.08703, + "precision_at_3": 0.07253, + "precision_at_5": 0.05444, + "precision_at_10": 0.03575, + "precision_at_100": 0.00675, + "precision_at_1000": 0.00094 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/text-embedding-3-large-instruct/no_revision_available/AlphaNLI.json b/results/text-embedding-3-large-instruct/no_revision_available/AlphaNLI.json new file mode 100644 index 000000000..1f96e66ad --- /dev/null +++ b/results/text-embedding-3-large-instruct/no_revision_available/AlphaNLI.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.34229, + "ndcg_at_1": 0.22389, + "ndcg_at_3": 0.30144, + "ndcg_at_5": 0.32363, + "ndcg_at_10": 0.34229, + "ndcg_at_100": 0.38785, + "ndcg_at_1000": 0.40985, + "map_at_1": 0.22389, + "map_at_3": 0.28264, + "map_at_5": 0.29488, + "map_at_10": 0.30262, + "map_at_100": 0.31106, + "map_at_1000": 0.3118, + "recall_at_1": 0.22389, + "recall_at_3": 0.35574, + "recall_at_5": 0.40992, + "recall_at_10": 0.46736, + "recall_at_100": 0.69125, + "recall_at_1000": 0.86945, + "precision_at_1": 0.22389, + "precision_at_3": 0.11858, + "precision_at_5": 0.08198, + "precision_at_10": 0.04674, + "precision_at_100": 0.00691, + "precision_at_1000": 0.00087 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/text-embedding-3-large-instruct/no_revision_available/HellaSwag.json b/results/text-embedding-3-large-instruct/no_revision_available/HellaSwag.json new file mode 100644 index 000000000..43ae17e11 --- /dev/null +++ b/results/text-embedding-3-large-instruct/no_revision_available/HellaSwag.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.31397, + "ndcg_at_1": 0.17367, + "ndcg_at_3": 0.26257, + "ndcg_at_5": 0.28811, + "ndcg_at_10": 0.31397, + "ndcg_at_100": 0.36292, + "ndcg_at_1000": 0.38575, + "map_at_1": 0.17367, + "map_at_3": 0.24062, + "map_at_5": 0.25483, + "map_at_10": 0.26558, + "map_at_100": 0.27477, + "map_at_1000": 0.27557, + "recall_at_1": 0.17367, + "recall_at_3": 0.32613, + "recall_at_5": 0.38797, + "recall_at_10": 0.46754, + "recall_at_100": 0.70623, + "recall_at_1000": 0.88966, + "precision_at_1": 0.17367, + "precision_at_3": 0.10871, + "precision_at_5": 0.07759, + "precision_at_10": 0.04675, + "precision_at_100": 0.00706, + "precision_at_1000": 0.00089 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/text-embedding-3-large-instruct/no_revision_available/PIQA.json b/results/text-embedding-3-large-instruct/no_revision_available/PIQA.json new file mode 100644 index 000000000..46fa3c517 --- /dev/null +++ b/results/text-embedding-3-large-instruct/no_revision_available/PIQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.37523, + "ndcg_at_1": 0.20511, + "ndcg_at_3": 0.31236, + "ndcg_at_5": 0.3449, + "ndcg_at_10": 0.37523, + "ndcg_at_100": 0.41679, + "ndcg_at_1000": 0.43246, + "map_at_1": 0.20511, + "map_at_3": 0.28654, + "map_at_5": 0.30463, + "map_at_10": 0.31719, + "map_at_100": 0.32522, + "map_at_1000": 0.32577, + "recall_at_1": 0.20511, + "recall_at_3": 0.38683, + "recall_at_5": 0.46572, + "recall_at_10": 0.5593, + "recall_at_100": 0.75898, + "recall_at_1000": 0.88466, + "precision_at_1": 0.20511, + "precision_at_3": 0.12894, + "precision_at_5": 0.09314, + "precision_at_10": 0.05593, + "precision_at_100": 0.00759, + "precision_at_1000": 0.00088 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/text-embedding-3-large-instruct/no_revision_available/Quail.json b/results/text-embedding-3-large-instruct/no_revision_available/Quail.json new file mode 100644 index 000000000..3f51148e8 --- /dev/null +++ b/results/text-embedding-3-large-instruct/no_revision_available/Quail.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.13603, + "ndcg_at_1": 0.05625, + "ndcg_at_3": 0.09908, + "ndcg_at_5": 0.11503, + "ndcg_at_10": 0.13603, + "ndcg_at_100": 0.18531, + "ndcg_at_1000": 0.21869, + "map_at_1": 0.05625, + "map_at_3": 0.08848, + "map_at_5": 0.09727, + "map_at_10": 0.10598, + "map_at_100": 0.11494, + "map_at_1000": 0.11606, + "recall_at_1": 0.05625, + "recall_at_3": 0.12978, + "recall_at_5": 0.16875, + "recall_at_10": 0.23346, + "recall_at_100": 0.47757, + "recall_at_1000": 0.74816, + "precision_at_1": 0.05625, + "precision_at_3": 0.04326, + "precision_at_5": 0.03375, + "precision_at_10": 0.02335, + "precision_at_100": 0.00478, + "precision_at_1000": 0.00075 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/text-embedding-3-large-instruct/no_revision_available/RARbCode.json b/results/text-embedding-3-large-instruct/no_revision_available/RARbCode.json new file mode 100644 index 000000000..1c10cc23a --- /dev/null +++ b/results/text-embedding-3-large-instruct/no_revision_available/RARbCode.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.89414, + "ndcg_at_1": 0.81739, + "ndcg_at_3": 0.8771, + "ndcg_at_5": 0.88658, + "ndcg_at_10": 0.89414, + "ndcg_at_100": 0.90002, + "ndcg_at_1000": 0.901, + "map_at_1": 0.81739, + "map_at_3": 0.86276, + "map_at_5": 0.86805, + "map_at_10": 0.87126, + "map_at_100": 0.87253, + "map_at_1000": 0.87258, + "recall_at_1": 0.81739, + "recall_at_3": 0.91846, + "recall_at_5": 0.94137, + "recall_at_10": 0.96429, + "recall_at_100": 0.99124, + "recall_at_1000": 0.99865, + "precision_at_1": 0.81739, + "precision_at_3": 0.30615, + "precision_at_5": 0.18827, + "precision_at_10": 0.09643, + "precision_at_100": 0.00991, + "precision_at_1000": 0.001 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/text-embedding-3-large-instruct/no_revision_available/RARbMath.json b/results/text-embedding-3-large-instruct/no_revision_available/RARbMath.json new file mode 100644 index 000000000..335f302c5 --- /dev/null +++ b/results/text-embedding-3-large-instruct/no_revision_available/RARbMath.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.87733, + "ndcg_at_1": 0.83605, + "ndcg_at_3": 0.86391, + "ndcg_at_5": 0.87065, + "ndcg_at_10": 0.87733, + "ndcg_at_100": 0.89052, + "ndcg_at_1000": 0.89259, + "map_at_1": 0.83605, + "map_at_3": 0.85707, + "map_at_5": 0.86079, + "map_at_10": 0.86353, + "map_at_100": 0.86619, + "map_at_1000": 0.86628, + "recall_at_1": 0.83605, + "recall_at_3": 0.88368, + "recall_at_5": 0.90014, + "recall_at_10": 0.92087, + "recall_at_100": 0.98323, + "recall_at_1000": 0.99921, + "precision_at_1": 0.83605, + "precision_at_3": 0.29456, + "precision_at_5": 0.18003, + "precision_at_10": 0.09209, + "precision_at_100": 0.00983, + "precision_at_1000": 0.001 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/text-embedding-3-large-instruct/no_revision_available/SIQA.json b/results/text-embedding-3-large-instruct/no_revision_available/SIQA.json new file mode 100644 index 000000000..efdaed4f3 --- /dev/null +++ b/results/text-embedding-3-large-instruct/no_revision_available/SIQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.04986, + "ndcg_at_1": 0.02252, + "ndcg_at_3": 0.03559, + "ndcg_at_5": 0.04215, + "ndcg_at_10": 0.04986, + "ndcg_at_100": 0.07404, + "ndcg_at_1000": 0.11084, + "map_at_1": 0.02252, + "map_at_3": 0.03233, + "map_at_5": 0.03599, + "map_at_10": 0.03913, + "map_at_100": 0.04326, + "map_at_1000": 0.04438, + "recall_at_1": 0.02252, + "recall_at_3": 0.04504, + "recall_at_5": 0.0609, + "recall_at_10": 0.08495, + "recall_at_100": 0.20778, + "recall_at_1000": 0.51279, + "precision_at_1": 0.02252, + "precision_at_3": 0.01501, + "precision_at_5": 0.01218, + "precision_at_10": 0.0085, + "precision_at_100": 0.00208, + "precision_at_1000": 0.00051 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/text-embedding-3-large-instruct/no_revision_available/SpartQA.json b/results/text-embedding-3-large-instruct/no_revision_available/SpartQA.json new file mode 100644 index 000000000..1403ff779 --- /dev/null +++ b/results/text-embedding-3-large-instruct/no_revision_available/SpartQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07447, + "ndcg_at_1": 0.00918, + "ndcg_at_3": 0.02799, + "ndcg_at_5": 0.04622, + "ndcg_at_10": 0.07447, + "ndcg_at_100": 0.11063, + "ndcg_at_1000": 0.14752, + "map_at_1": 0.00659, + "map_at_3": 0.02084, + "map_at_5": 0.03039, + "map_at_10": 0.04189, + "map_at_100": 0.04963, + "map_at_1000": 0.05054, + "recall_at_1": 0.00659, + "recall_at_3": 0.04053, + "recall_at_5": 0.08115, + "recall_at_10": 0.1598, + "recall_at_100": 0.30477, + "recall_at_1000": 0.57726, + "precision_at_1": 0.00918, + "precision_at_3": 0.0192, + "precision_at_5": 0.02332, + "precision_at_10": 0.02373, + "precision_at_100": 0.00475, + "precision_at_1000": 0.00098 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/text-embedding-3-large-instruct/no_revision_available/TempReasonL1.json b/results/text-embedding-3-large-instruct/no_revision_available/TempReasonL1.json new file mode 100644 index 000000000..ccb5ed1fd --- /dev/null +++ b/results/text-embedding-3-large-instruct/no_revision_available/TempReasonL1.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.0207, + "ndcg_at_1": 0.00025, + "ndcg_at_3": 0.00842, + "ndcg_at_5": 0.01331, + "ndcg_at_10": 0.0207, + "ndcg_at_100": 0.05832, + "ndcg_at_1000": 0.12926, + "map_at_1": 0.00025, + "map_at_3": 0.00633, + "map_at_5": 0.00901, + "map_at_10": 0.01204, + "map_at_100": 0.0179, + "map_at_1000": 0.02002, + "recall_at_1": 0.00025, + "recall_at_3": 0.0145, + "recall_at_5": 0.0265, + "recall_at_10": 0.0495, + "recall_at_100": 0.24775, + "recall_at_1000": 0.836, + "precision_at_1": 0.00025, + "precision_at_3": 0.00483, + "precision_at_5": 0.0053, + "precision_at_10": 0.00495, + "precision_at_100": 0.00248, + "precision_at_1000": 0.00084 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/text-embedding-3-large-instruct/no_revision_available/TempReasonL2Fact.json b/results/text-embedding-3-large-instruct/no_revision_available/TempReasonL2Fact.json new file mode 100644 index 000000000..2fb451efa --- /dev/null +++ b/results/text-embedding-3-large-instruct/no_revision_available/TempReasonL2Fact.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.3977, + "ndcg_at_1": 0.18418, + "ndcg_at_3": 0.31125, + "ndcg_at_5": 0.35571, + "ndcg_at_10": 0.3977, + "ndcg_at_100": 0.45229, + "ndcg_at_1000": 0.46269, + "map_at_1": 0.18418, + "map_at_3": 0.27898, + "map_at_5": 0.30363, + "map_at_10": 0.3211, + "map_at_100": 0.33227, + "map_at_1000": 0.33266, + "recall_at_1": 0.18418, + "recall_at_3": 0.40504, + "recall_at_5": 0.51306, + "recall_at_10": 0.64221, + "recall_at_100": 0.89828, + "recall_at_1000": 0.98036, + "precision_at_1": 0.18418, + "precision_at_3": 0.13501, + "precision_at_5": 0.10261, + "precision_at_10": 0.06422, + "precision_at_100": 0.00898, + "precision_at_1000": 0.00098 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/text-embedding-3-large-instruct/no_revision_available/TempReasonL2Pure.json b/results/text-embedding-3-large-instruct/no_revision_available/TempReasonL2Pure.json new file mode 100644 index 000000000..a3cd724ce --- /dev/null +++ b/results/text-embedding-3-large-instruct/no_revision_available/TempReasonL2Pure.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.11044, + "ndcg_at_1": 0.04317, + "ndcg_at_3": 0.07677, + "ndcg_at_5": 0.09259, + "ndcg_at_10": 0.11044, + "ndcg_at_100": 0.16784, + "ndcg_at_1000": 0.21115, + "map_at_1": 0.04317, + "map_at_3": 0.06831, + "map_at_5": 0.07705, + "map_at_10": 0.08455, + "map_at_100": 0.09407, + "map_at_1000": 0.09551, + "recall_at_1": 0.04317, + "recall_at_3": 0.10135, + "recall_at_5": 0.13989, + "recall_at_10": 0.19437, + "recall_at_100": 0.48898, + "recall_at_1000": 0.84028, + "precision_at_1": 0.04317, + "precision_at_3": 0.03378, + "precision_at_5": 0.02798, + "precision_at_10": 0.01944, + "precision_at_100": 0.00489, + "precision_at_1000": 0.00084 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/text-embedding-3-large-instruct/no_revision_available/TempReasonL3Fact.json b/results/text-embedding-3-large-instruct/no_revision_available/TempReasonL3Fact.json new file mode 100644 index 000000000..348db2902 --- /dev/null +++ b/results/text-embedding-3-large-instruct/no_revision_available/TempReasonL3Fact.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.37039, + "ndcg_at_1": 0.16177, + "ndcg_at_3": 0.27965, + "ndcg_at_5": 0.32735, + "ndcg_at_10": 0.37039, + "ndcg_at_100": 0.42486, + "ndcg_at_1000": 0.43816, + "map_at_1": 0.16177, + "map_at_3": 0.2497, + "map_at_5": 0.2761, + "map_at_10": 0.29404, + "map_at_100": 0.30512, + "map_at_1000": 0.30563, + "recall_at_1": 0.16177, + "recall_at_3": 0.3667, + "recall_at_5": 0.48283, + "recall_at_10": 0.615, + "recall_at_100": 0.87099, + "recall_at_1000": 0.97537, + "precision_at_1": 0.16177, + "precision_at_3": 0.12223, + "precision_at_5": 0.09657, + "precision_at_10": 0.0615, + "precision_at_100": 0.00871, + "precision_at_1000": 0.00098 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/text-embedding-3-large-instruct/no_revision_available/TempReasonL3Pure.json b/results/text-embedding-3-large-instruct/no_revision_available/TempReasonL3Pure.json new file mode 100644 index 000000000..b3e8ce58b --- /dev/null +++ b/results/text-embedding-3-large-instruct/no_revision_available/TempReasonL3Pure.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.15513, + "ndcg_at_1": 0.02689, + "ndcg_at_3": 0.09313, + "ndcg_at_5": 0.1249, + "ndcg_at_10": 0.15513, + "ndcg_at_100": 0.22698, + "ndcg_at_1000": 0.25855, + "map_at_1": 0.02689, + "map_at_3": 0.07614, + "map_at_5": 0.09374, + "map_at_10": 0.10624, + "map_at_100": 0.11981, + "map_at_1000": 0.12092, + "recall_at_1": 0.02689, + "recall_at_3": 0.14257, + "recall_at_5": 0.21984, + "recall_at_10": 0.31315, + "recall_at_100": 0.66268, + "recall_at_1000": 0.91527, + "precision_at_1": 0.02689, + "precision_at_3": 0.04752, + "precision_at_5": 0.04397, + "precision_at_10": 0.03131, + "precision_at_100": 0.00663, + "precision_at_1000": 0.00092 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/text-embedding-3-large-instruct/no_revision_available/WinoGrande.json b/results/text-embedding-3-large-instruct/no_revision_available/WinoGrande.json new file mode 100644 index 000000000..6534deb41 --- /dev/null +++ b/results/text-embedding-3-large-instruct/no_revision_available/WinoGrande.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.33925, + "ndcg_at_1": 0.14207, + "ndcg_at_3": 0.25037, + "ndcg_at_5": 0.2915, + "ndcg_at_10": 0.33925, + "ndcg_at_100": 0.40961, + "ndcg_at_1000": 0.42144, + "map_at_1": 0.14207, + "map_at_3": 0.22323, + "map_at_5": 0.24596, + "map_at_10": 0.26569, + "map_at_100": 0.28023, + "map_at_1000": 0.2807, + "recall_at_1": 0.14207, + "recall_at_3": 0.32912, + "recall_at_5": 0.42936, + "recall_at_10": 0.57695, + "recall_at_100": 0.90529, + "recall_at_1000": 0.99684, + "precision_at_1": 0.14207, + "precision_at_3": 0.10971, + "precision_at_5": 0.08587, + "precision_at_10": 0.0577, + "precision_at_100": 0.00905, + "precision_at_1000": 0.001 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/text-embedding-3-large/no_revision_available/ARCChallenge.json b/results/text-embedding-3-large/no_revision_available/ARCChallenge.json new file mode 100644 index 000000000..d2846e0c0 --- /dev/null +++ b/results/text-embedding-3-large/no_revision_available/ARCChallenge.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.23983, + "ndcg_at_1": 0.11348, + "ndcg_at_3": 0.18484, + "ndcg_at_5": 0.21344, + "ndcg_at_10": 0.23983, + "ndcg_at_100": 0.30422, + "ndcg_at_1000": 0.33415, + "map_at_1": 0.11348, + "map_at_3": 0.16681, + "map_at_5": 0.18276, + "map_at_10": 0.19359, + "map_at_100": 0.20558, + "map_at_1000": 0.20668, + "recall_at_1": 0.11348, + "recall_at_3": 0.2372, + "recall_at_5": 0.30631, + "recall_at_10": 0.38823, + "recall_at_100": 0.70392, + "recall_at_1000": 0.94113, + "precision_at_1": 0.11348, + "precision_at_3": 0.07907, + "precision_at_5": 0.06126, + "precision_at_10": 0.03882, + "precision_at_100": 0.00704, + "precision_at_1000": 0.00094 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/text-embedding-3-large/no_revision_available/AlphaNLI.json b/results/text-embedding-3-large/no_revision_available/AlphaNLI.json new file mode 100644 index 000000000..501f345d0 --- /dev/null +++ b/results/text-embedding-3-large/no_revision_available/AlphaNLI.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.3727, + "ndcg_at_1": 0.24935, + "ndcg_at_3": 0.3283, + "ndcg_at_5": 0.35235, + "ndcg_at_10": 0.3727, + "ndcg_at_100": 0.41623, + "ndcg_at_1000": 0.43574, + "map_at_1": 0.24935, + "map_at_3": 0.30929, + "map_at_5": 0.3227, + "map_at_10": 0.33115, + "map_at_100": 0.33919, + "map_at_1000": 0.33986, + "recall_at_1": 0.24935, + "recall_at_3": 0.38316, + "recall_at_5": 0.44125, + "recall_at_10": 0.50392, + "recall_at_100": 0.71802, + "recall_at_1000": 0.87533, + "precision_at_1": 0.24935, + "precision_at_3": 0.12772, + "precision_at_5": 0.08825, + "precision_at_10": 0.05039, + "precision_at_100": 0.00718, + "precision_at_1000": 0.00088 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/text-embedding-3-large/no_revision_available/HellaSwag.json b/results/text-embedding-3-large/no_revision_available/HellaSwag.json new file mode 100644 index 000000000..dacd84c4a --- /dev/null +++ b/results/text-embedding-3-large/no_revision_available/HellaSwag.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.34119, + "ndcg_at_1": 0.19837, + "ndcg_at_3": 0.28807, + "ndcg_at_5": 0.31605, + "ndcg_at_10": 0.34119, + "ndcg_at_100": 0.38857, + "ndcg_at_1000": 0.40998, + "map_at_1": 0.19837, + "map_at_3": 0.2658, + "map_at_5": 0.28133, + "map_at_10": 0.29179, + "map_at_100": 0.30071, + "map_at_1000": 0.30146, + "recall_at_1": 0.19837, + "recall_at_3": 0.35262, + "recall_at_5": 0.42053, + "recall_at_10": 0.49781, + "recall_at_100": 0.72874, + "recall_at_1000": 0.90062, + "precision_at_1": 0.19837, + "precision_at_3": 0.11754, + "precision_at_5": 0.08411, + "precision_at_10": 0.04978, + "precision_at_100": 0.00729, + "precision_at_1000": 0.0009 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/text-embedding-3-large/no_revision_available/PIQA.json b/results/text-embedding-3-large/no_revision_available/PIQA.json new file mode 100644 index 000000000..39fd7bba2 --- /dev/null +++ b/results/text-embedding-3-large/no_revision_available/PIQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.41962, + "ndcg_at_1": 0.25517, + "ndcg_at_3": 0.36221, + "ndcg_at_5": 0.38876, + "ndcg_at_10": 0.41962, + "ndcg_at_100": 0.46082, + "ndcg_at_1000": 0.47622, + "map_at_1": 0.25517, + "map_at_3": 0.33651, + "map_at_5": 0.35103, + "map_at_10": 0.36402, + "map_at_100": 0.37224, + "map_at_1000": 0.37277, + "recall_at_1": 0.25517, + "recall_at_3": 0.43634, + "recall_at_5": 0.50163, + "recall_at_10": 0.59576, + "recall_at_100": 0.79108, + "recall_at_1000": 0.91567, + "precision_at_1": 0.25517, + "precision_at_3": 0.14545, + "precision_at_5": 0.10033, + "precision_at_10": 0.05958, + "precision_at_100": 0.00791, + "precision_at_1000": 0.00092 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/text-embedding-3-large/no_revision_available/Quail.json b/results/text-embedding-3-large/no_revision_available/Quail.json new file mode 100644 index 000000000..487739e14 --- /dev/null +++ b/results/text-embedding-3-large/no_revision_available/Quail.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.10147, + "ndcg_at_1": 0.03529, + "ndcg_at_3": 0.06668, + "ndcg_at_5": 0.08212, + "ndcg_at_10": 0.10147, + "ndcg_at_100": 0.14534, + "ndcg_at_1000": 0.17849, + "map_at_1": 0.03529, + "map_at_3": 0.05864, + "map_at_5": 0.06711, + "map_at_10": 0.07494, + "map_at_100": 0.08284, + "map_at_1000": 0.08387, + "recall_at_1": 0.03529, + "recall_at_3": 0.09007, + "recall_at_5": 0.12794, + "recall_at_10": 0.1886, + "recall_at_100": 0.40662, + "recall_at_1000": 0.68015, + "precision_at_1": 0.03529, + "precision_at_3": 0.03002, + "precision_at_5": 0.02559, + "precision_at_10": 0.01886, + "precision_at_100": 0.00407, + "precision_at_1000": 0.00068 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/text-embedding-3-large/no_revision_available/RARbCode.json b/results/text-embedding-3-large/no_revision_available/RARbCode.json new file mode 100644 index 000000000..51d0bccf4 --- /dev/null +++ b/results/text-embedding-3-large/no_revision_available/RARbCode.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.89642, + "ndcg_at_1": 0.81941, + "ndcg_at_3": 0.88024, + "ndcg_at_5": 0.88937, + "ndcg_at_10": 0.89642, + "ndcg_at_100": 0.90194, + "ndcg_at_1000": 0.90283, + "map_at_1": 0.81941, + "map_at_3": 0.86579, + "map_at_5": 0.87084, + "map_at_10": 0.87379, + "map_at_100": 0.87489, + "map_at_1000": 0.87493, + "recall_at_1": 0.81941, + "recall_at_3": 0.92183, + "recall_at_5": 0.94407, + "recall_at_10": 0.96563, + "recall_at_100": 0.99191, + "recall_at_1000": 0.99865, + "precision_at_1": 0.81941, + "precision_at_3": 0.30728, + "precision_at_5": 0.18881, + "precision_at_10": 0.09656, + "precision_at_100": 0.00992, + "precision_at_1000": 0.001 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/text-embedding-3-large/no_revision_available/RARbMath.json b/results/text-embedding-3-large/no_revision_available/RARbMath.json new file mode 100644 index 000000000..f18a2f19b --- /dev/null +++ b/results/text-embedding-3-large/no_revision_available/RARbMath.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.90079, + "ndcg_at_1": 0.862, + "ndcg_at_3": 0.88939, + "ndcg_at_5": 0.89523, + "ndcg_at_10": 0.90079, + "ndcg_at_100": 0.91074, + "ndcg_at_1000": 0.91228, + "map_at_1": 0.862, + "map_at_3": 0.88271, + "map_at_5": 0.88598, + "map_at_10": 0.88826, + "map_at_100": 0.89025, + "map_at_1000": 0.89031, + "recall_at_1": 0.862, + "recall_at_3": 0.90869, + "recall_at_5": 0.92277, + "recall_at_10": 0.94002, + "recall_at_100": 0.98718, + "recall_at_1000": 0.99889, + "precision_at_1": 0.862, + "precision_at_3": 0.3029, + "precision_at_5": 0.18455, + "precision_at_10": 0.094, + "precision_at_100": 0.00987, + "precision_at_1000": 0.001 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/text-embedding-3-large/no_revision_available/SIQA.json b/results/text-embedding-3-large/no_revision_available/SIQA.json new file mode 100644 index 000000000..c6ac55d3d --- /dev/null +++ b/results/text-embedding-3-large/no_revision_available/SIQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.03445, + "ndcg_at_1": 0.01996, + "ndcg_at_3": 0.02619, + "ndcg_at_5": 0.03002, + "ndcg_at_10": 0.03445, + "ndcg_at_100": 0.04981, + "ndcg_at_1000": 0.08539, + "map_at_1": 0.01996, + "map_at_3": 0.02448, + "map_at_5": 0.02663, + "map_at_10": 0.02843, + "map_at_100": 0.03094, + "map_at_1000": 0.0318, + "recall_at_1": 0.01996, + "recall_at_3": 0.03122, + "recall_at_5": 0.04043, + "recall_at_10": 0.05425, + "recall_at_100": 0.13408, + "recall_at_1000": 0.44166, + "precision_at_1": 0.01996, + "precision_at_3": 0.01041, + "precision_at_5": 0.00809, + "precision_at_10": 0.00542, + "precision_at_100": 0.00134, + "precision_at_1000": 0.00044 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/text-embedding-3-large/no_revision_available/SpartQA.json b/results/text-embedding-3-large/no_revision_available/SpartQA.json new file mode 100644 index 000000000..2995f28d5 --- /dev/null +++ b/results/text-embedding-3-large/no_revision_available/SpartQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07507, + "ndcg_at_1": 0.00612, + "ndcg_at_3": 0.02492, + "ndcg_at_5": 0.04697, + "ndcg_at_10": 0.07507, + "ndcg_at_100": 0.10817, + "ndcg_at_1000": 0.14251, + "map_at_1": 0.00371, + "map_at_3": 0.01733, + "map_at_5": 0.02875, + "map_at_10": 0.0399, + "map_at_100": 0.04733, + "map_at_1000": 0.0481, + "recall_at_1": 0.00371, + "recall_at_3": 0.03738, + "recall_at_5": 0.08755, + "recall_at_10": 0.16667, + "recall_at_100": 0.29744, + "recall_at_1000": 0.55463, + "precision_at_1": 0.00612, + "precision_at_3": 0.01976, + "precision_at_5": 0.02582, + "precision_at_10": 0.0249, + "precision_at_100": 0.00458, + "precision_at_1000": 0.00094 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/text-embedding-3-large/no_revision_available/TempReasonL1.json b/results/text-embedding-3-large/no_revision_available/TempReasonL1.json new file mode 100644 index 000000000..4c3c1fcf5 --- /dev/null +++ b/results/text-embedding-3-large/no_revision_available/TempReasonL1.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02126, + "ndcg_at_1": 0.0005, + "ndcg_at_3": 0.00751, + "ndcg_at_5": 0.01259, + "ndcg_at_10": 0.02126, + "ndcg_at_100": 0.05812, + "ndcg_at_1000": 0.13041, + "map_at_1": 0.0005, + "map_at_3": 0.00579, + "map_at_5": 0.00863, + "map_at_10": 0.01217, + "map_at_100": 0.01785, + "map_at_1000": 0.02004, + "recall_at_1": 0.0005, + "recall_at_3": 0.0125, + "recall_at_5": 0.02475, + "recall_at_10": 0.05175, + "recall_at_100": 0.24675, + "recall_at_1000": 0.845, + "precision_at_1": 0.0005, + "precision_at_3": 0.00417, + "precision_at_5": 0.00495, + "precision_at_10": 0.00518, + "precision_at_100": 0.00247, + "precision_at_1000": 0.00084 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/text-embedding-3-large/no_revision_available/TempReasonL2Fact.json b/results/text-embedding-3-large/no_revision_available/TempReasonL2Fact.json new file mode 100644 index 000000000..77b449138 --- /dev/null +++ b/results/text-embedding-3-large/no_revision_available/TempReasonL2Fact.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.28646, + "ndcg_at_1": 0.11821, + "ndcg_at_3": 0.20739, + "ndcg_at_5": 0.24449, + "ndcg_at_10": 0.28646, + "ndcg_at_100": 0.35731, + "ndcg_at_1000": 0.37428, + "map_at_1": 0.11821, + "map_at_3": 0.18482, + "map_at_5": 0.20538, + "map_at_10": 0.22289, + "map_at_100": 0.237, + "map_at_1000": 0.23764, + "recall_at_1": 0.11821, + "recall_at_3": 0.27293, + "recall_at_5": 0.36316, + "recall_at_10": 0.49194, + "recall_at_100": 0.82842, + "recall_at_1000": 0.96202, + "precision_at_1": 0.11821, + "precision_at_3": 0.09098, + "precision_at_5": 0.07263, + "precision_at_10": 0.04919, + "precision_at_100": 0.00828, + "precision_at_1000": 0.00096 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/text-embedding-3-large/no_revision_available/TempReasonL2Pure.json b/results/text-embedding-3-large/no_revision_available/TempReasonL2Pure.json new file mode 100644 index 000000000..c493583da --- /dev/null +++ b/results/text-embedding-3-large/no_revision_available/TempReasonL2Pure.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.10335, + "ndcg_at_1": 0.03947, + "ndcg_at_3": 0.07099, + "ndcg_at_5": 0.08615, + "ndcg_at_10": 0.10335, + "ndcg_at_100": 0.16041, + "ndcg_at_1000": 0.20319, + "map_at_1": 0.03947, + "map_at_3": 0.06303, + "map_at_5": 0.07138, + "map_at_10": 0.07841, + "map_at_100": 0.08798, + "map_at_1000": 0.0894, + "recall_at_1": 0.03947, + "recall_at_3": 0.09413, + "recall_at_5": 0.13118, + "recall_at_10": 0.18473, + "recall_at_100": 0.47656, + "recall_at_1000": 0.82398, + "precision_at_1": 0.03947, + "precision_at_3": 0.03138, + "precision_at_5": 0.02624, + "precision_at_10": 0.01847, + "precision_at_100": 0.00477, + "precision_at_1000": 0.00082 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/text-embedding-3-large/no_revision_available/TempReasonL3Fact.json b/results/text-embedding-3-large/no_revision_available/TempReasonL3Fact.json new file mode 100644 index 000000000..bc0c33301 --- /dev/null +++ b/results/text-embedding-3-large/no_revision_available/TempReasonL3Fact.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.25518, + "ndcg_at_1": 0.06417, + "ndcg_at_3": 0.1662, + "ndcg_at_5": 0.21155, + "ndcg_at_10": 0.25518, + "ndcg_at_100": 0.32115, + "ndcg_at_1000": 0.34134, + "map_at_1": 0.06417, + "map_at_3": 0.14008, + "map_at_5": 0.16532, + "map_at_10": 0.18342, + "map_at_100": 0.19668, + "map_at_1000": 0.19744, + "recall_at_1": 0.06417, + "recall_at_3": 0.24221, + "recall_at_5": 0.35201, + "recall_at_10": 0.48644, + "recall_at_100": 0.79824, + "recall_at_1000": 0.9573, + "precision_at_1": 0.06417, + "precision_at_3": 0.08074, + "precision_at_5": 0.0704, + "precision_at_10": 0.04864, + "precision_at_100": 0.00798, + "precision_at_1000": 0.00096 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/text-embedding-3-large/no_revision_available/TempReasonL3Pure.json b/results/text-embedding-3-large/no_revision_available/TempReasonL3Pure.json new file mode 100644 index 000000000..b998b005d --- /dev/null +++ b/results/text-embedding-3-large/no_revision_available/TempReasonL3Pure.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.15285, + "ndcg_at_1": 0.0192, + "ndcg_at_3": 0.09176, + "ndcg_at_5": 0.12052, + "ndcg_at_10": 0.15285, + "ndcg_at_100": 0.2184, + "ndcg_at_1000": 0.25131, + "map_at_1": 0.0192, + "map_at_3": 0.07294, + "map_at_5": 0.08879, + "map_at_10": 0.10207, + "map_at_100": 0.11416, + "map_at_1000": 0.1153, + "recall_at_1": 0.0192, + "recall_at_3": 0.14663, + "recall_at_5": 0.2169, + "recall_at_10": 0.31722, + "recall_at_100": 0.63918, + "recall_at_1000": 0.90398, + "precision_at_1": 0.0192, + "precision_at_3": 0.04888, + "precision_at_5": 0.04338, + "precision_at_10": 0.03172, + "precision_at_100": 0.00639, + "precision_at_1000": 0.0009 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/text-embedding-3-large/no_revision_available/WinoGrande.json b/results/text-embedding-3-large/no_revision_available/WinoGrande.json new file mode 100644 index 000000000..8774e3ce3 --- /dev/null +++ b/results/text-embedding-3-large/no_revision_available/WinoGrande.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.2911, + "ndcg_at_1": 0.11997, + "ndcg_at_3": 0.20283, + "ndcg_at_5": 0.24125, + "ndcg_at_10": 0.2911, + "ndcg_at_100": 0.37412, + "ndcg_at_1000": 0.38575, + "map_at_1": 0.11997, + "map_at_3": 0.18166, + "map_at_5": 0.20301, + "map_at_10": 0.22379, + "map_at_100": 0.24023, + "map_at_1000": 0.24072, + "recall_at_1": 0.11997, + "recall_at_3": 0.2644, + "recall_at_5": 0.35754, + "recall_at_10": 0.51066, + "recall_at_100": 0.9045, + "recall_at_1000": 0.9929, + "precision_at_1": 0.11997, + "precision_at_3": 0.08813, + "precision_at_5": 0.07151, + "precision_at_10": 0.05107, + "precision_at_100": 0.00904, + "precision_at_1000": 0.00099 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/text-embedding-3-small-instruct/no_revision_available/ARCChallenge.json b/results/text-embedding-3-small-instruct/no_revision_available/ARCChallenge.json new file mode 100644 index 000000000..2ef0b40d7 --- /dev/null +++ b/results/text-embedding-3-small-instruct/no_revision_available/ARCChallenge.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.1376, + "ndcg_at_1": 0.0529, + "ndcg_at_3": 0.10375, + "ndcg_at_5": 0.11891, + "ndcg_at_10": 0.1376, + "ndcg_at_100": 0.19501, + "ndcg_at_1000": 0.23606, + "map_at_1": 0.0529, + "map_at_3": 0.09073, + "map_at_5": 0.09918, + "map_at_10": 0.107, + "map_at_100": 0.11735, + "map_at_1000": 0.1187, + "recall_at_1": 0.0529, + "recall_at_3": 0.14164, + "recall_at_5": 0.17833, + "recall_at_10": 0.23549, + "recall_at_100": 0.52133, + "recall_at_1000": 0.85495, + "precision_at_1": 0.0529, + "precision_at_3": 0.04721, + "precision_at_5": 0.03567, + "precision_at_10": 0.02355, + "precision_at_100": 0.00521, + "precision_at_1000": 0.00085 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/text-embedding-3-small-instruct/no_revision_available/AlphaNLI.json b/results/text-embedding-3-small-instruct/no_revision_available/AlphaNLI.json new file mode 100644 index 000000000..240fbc8a3 --- /dev/null +++ b/results/text-embedding-3-small-instruct/no_revision_available/AlphaNLI.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.21138, + "ndcg_at_1": 0.12467, + "ndcg_at_3": 0.17617, + "ndcg_at_5": 0.19193, + "ndcg_at_10": 0.21138, + "ndcg_at_100": 0.25275, + "ndcg_at_1000": 0.27876, + "map_at_1": 0.12467, + "map_at_3": 0.16351, + "map_at_5": 0.17236, + "map_at_10": 0.18041, + "map_at_100": 0.18797, + "map_at_1000": 0.18881, + "recall_at_1": 0.12467, + "recall_at_3": 0.21279, + "recall_at_5": 0.25065, + "recall_at_10": 0.3107, + "recall_at_100": 0.51567, + "recall_at_1000": 0.72781, + "precision_at_1": 0.12467, + "precision_at_3": 0.07093, + "precision_at_5": 0.05013, + "precision_at_10": 0.03107, + "precision_at_100": 0.00516, + "precision_at_1000": 0.00073 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/text-embedding-3-small-instruct/no_revision_available/HellaSwag.json b/results/text-embedding-3-small-instruct/no_revision_available/HellaSwag.json new file mode 100644 index 000000000..9e5efd0e5 --- /dev/null +++ b/results/text-embedding-3-small-instruct/no_revision_available/HellaSwag.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.27196, + "ndcg_at_1": 0.14439, + "ndcg_at_3": 0.22268, + "ndcg_at_5": 0.24819, + "ndcg_at_10": 0.27196, + "ndcg_at_100": 0.31973, + "ndcg_at_1000": 0.34411, + "map_at_1": 0.14439, + "map_at_3": 0.203, + "map_at_5": 0.21715, + "map_at_10": 0.22699, + "map_at_100": 0.23598, + "map_at_1000": 0.2368, + "recall_at_1": 0.14439, + "recall_at_3": 0.27982, + "recall_at_5": 0.34176, + "recall_at_10": 0.41506, + "recall_at_100": 0.64798, + "recall_at_1000": 0.84505, + "precision_at_1": 0.14439, + "precision_at_3": 0.09327, + "precision_at_5": 0.06835, + "precision_at_10": 0.04151, + "precision_at_100": 0.00648, + "precision_at_1000": 0.00085 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/text-embedding-3-small-instruct/no_revision_available/PIQA.json b/results/text-embedding-3-small-instruct/no_revision_available/PIQA.json new file mode 100644 index 000000000..cc006e882 --- /dev/null +++ b/results/text-embedding-3-small-instruct/no_revision_available/PIQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.29586, + "ndcg_at_1": 0.14146, + "ndcg_at_3": 0.24153, + "ndcg_at_5": 0.26911, + "ndcg_at_10": 0.29586, + "ndcg_at_100": 0.34062, + "ndcg_at_1000": 0.35936, + "map_at_1": 0.14146, + "map_at_3": 0.21772, + "map_at_5": 0.23303, + "map_at_10": 0.24397, + "map_at_100": 0.25246, + "map_at_1000": 0.25305, + "recall_at_1": 0.14146, + "recall_at_3": 0.31012, + "recall_at_5": 0.37704, + "recall_at_10": 0.46028, + "recall_at_100": 0.67791, + "recall_at_1000": 0.83188, + "precision_at_1": 0.14146, + "precision_at_3": 0.10337, + "precision_at_5": 0.07541, + "precision_at_10": 0.04603, + "precision_at_100": 0.00678, + "precision_at_1000": 0.00083 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/text-embedding-3-small-instruct/no_revision_available/Quail.json b/results/text-embedding-3-small-instruct/no_revision_available/Quail.json new file mode 100644 index 000000000..4de4d15a1 --- /dev/null +++ b/results/text-embedding-3-small-instruct/no_revision_available/Quail.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.06638, + "ndcg_at_1": 0.02647, + "ndcg_at_3": 0.04481, + "ndcg_at_5": 0.05333, + "ndcg_at_10": 0.06638, + "ndcg_at_100": 0.10567, + "ndcg_at_1000": 0.13683, + "map_at_1": 0.02647, + "map_at_3": 0.04001, + "map_at_5": 0.04475, + "map_at_10": 0.05007, + "map_at_100": 0.05726, + "map_at_1000": 0.05819, + "recall_at_1": 0.02647, + "recall_at_3": 0.05882, + "recall_at_5": 0.07941, + "recall_at_10": 0.12022, + "recall_at_100": 0.31434, + "recall_at_1000": 0.57426, + "precision_at_1": 0.02647, + "precision_at_3": 0.01961, + "precision_at_5": 0.01588, + "precision_at_10": 0.01202, + "precision_at_100": 0.00314, + "precision_at_1000": 0.00057 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/text-embedding-3-small-instruct/no_revision_available/RARbCode.json b/results/text-embedding-3-small-instruct/no_revision_available/RARbCode.json new file mode 100644 index 000000000..da96cb42f --- /dev/null +++ b/results/text-embedding-3-small-instruct/no_revision_available/RARbCode.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.72141, + "ndcg_at_1": 0.56806, + "ndcg_at_3": 0.67068, + "ndcg_at_5": 0.69959, + "ndcg_at_10": 0.72141, + "ndcg_at_100": 0.74374, + "ndcg_at_1000": 0.74578, + "map_at_1": 0.56806, + "map_at_3": 0.64578, + "map_at_5": 0.66185, + "map_at_10": 0.67099, + "map_at_100": 0.67598, + "map_at_1000": 0.67605, + "recall_at_1": 0.56806, + "recall_at_3": 0.74259, + "recall_at_5": 0.81267, + "recall_at_10": 0.87938, + "recall_at_100": 0.97978, + "recall_at_1000": 0.99663, + "precision_at_1": 0.56806, + "precision_at_3": 0.24753, + "precision_at_5": 0.16253, + "precision_at_10": 0.08794, + "precision_at_100": 0.0098, + "precision_at_1000": 0.001 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/text-embedding-3-small-instruct/no_revision_available/RARbMath.json b/results/text-embedding-3-small-instruct/no_revision_available/RARbMath.json new file mode 100644 index 000000000..5e157ee44 --- /dev/null +++ b/results/text-embedding-3-small-instruct/no_revision_available/RARbMath.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.6431, + "ndcg_at_1": 0.57652, + "ndcg_at_3": 0.61708, + "ndcg_at_5": 0.62954, + "ndcg_at_10": 0.6431, + "ndcg_at_100": 0.67705, + "ndcg_at_1000": 0.68883, + "map_at_1": 0.57652, + "map_at_3": 0.60719, + "map_at_5": 0.61407, + "map_at_10": 0.61963, + "map_at_100": 0.62597, + "map_at_1000": 0.62639, + "recall_at_1": 0.57652, + "recall_at_3": 0.64567, + "recall_at_5": 0.67606, + "recall_at_10": 0.71815, + "recall_at_100": 0.88384, + "recall_at_1000": 0.97784, + "precision_at_1": 0.57652, + "precision_at_3": 0.21522, + "precision_at_5": 0.13521, + "precision_at_10": 0.07182, + "precision_at_100": 0.00884, + "precision_at_1000": 0.00098 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/text-embedding-3-small-instruct/no_revision_available/SIQA.json b/results/text-embedding-3-small-instruct/no_revision_available/SIQA.json new file mode 100644 index 000000000..662eb5bbd --- /dev/null +++ b/results/text-embedding-3-small-instruct/no_revision_available/SIQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02977, + "ndcg_at_1": 0.01535, + "ndcg_at_3": 0.02308, + "ndcg_at_5": 0.02557, + "ndcg_at_10": 0.02977, + "ndcg_at_100": 0.04556, + "ndcg_at_1000": 0.07767, + "map_at_1": 0.01535, + "map_at_3": 0.02115, + "map_at_5": 0.02251, + "map_at_10": 0.02419, + "map_at_100": 0.02688, + "map_at_1000": 0.02771, + "recall_at_1": 0.01535, + "recall_at_3": 0.02866, + "recall_at_5": 0.0348, + "recall_at_10": 0.04811, + "recall_at_100": 0.12845, + "recall_at_1000": 0.40379, + "precision_at_1": 0.01535, + "precision_at_3": 0.00955, + "precision_at_5": 0.00696, + "precision_at_10": 0.00481, + "precision_at_100": 0.00128, + "precision_at_1000": 0.0004 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/text-embedding-3-small-instruct/no_revision_available/SpartQA.json b/results/text-embedding-3-small-instruct/no_revision_available/SpartQA.json new file mode 100644 index 000000000..415eeef89 --- /dev/null +++ b/results/text-embedding-3-small-instruct/no_revision_available/SpartQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.03582, + "ndcg_at_1": 0.00473, + "ndcg_at_3": 0.01235, + "ndcg_at_5": 0.02099, + "ndcg_at_10": 0.03582, + "ndcg_at_100": 0.08339, + "ndcg_at_1000": 0.10546, + "map_at_1": 0.00343, + "map_at_3": 0.00897, + "map_at_5": 0.01352, + "map_at_10": 0.01932, + "map_at_100": 0.0281, + "map_at_1000": 0.02862, + "recall_at_1": 0.00343, + "recall_at_3": 0.01827, + "recall_at_5": 0.03756, + "recall_at_10": 0.07939, + "recall_at_100": 0.28659, + "recall_at_1000": 0.45307, + "precision_at_1": 0.00473, + "precision_at_3": 0.00881, + "precision_at_5": 0.01096, + "precision_at_10": 0.01191, + "precision_at_100": 0.00438, + "precision_at_1000": 0.00074 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/text-embedding-3-small-instruct/no_revision_available/TempReasonL1.json b/results/text-embedding-3-small-instruct/no_revision_available/TempReasonL1.json new file mode 100644 index 000000000..f0a94810a --- /dev/null +++ b/results/text-embedding-3-small-instruct/no_revision_available/TempReasonL1.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02285, + "ndcg_at_1": 0.003, + "ndcg_at_3": 0.01035, + "ndcg_at_5": 0.01439, + "ndcg_at_10": 0.02285, + "ndcg_at_100": 0.05631, + "ndcg_at_1000": 0.10659, + "map_at_1": 0.003, + "map_at_3": 0.00842, + "map_at_5": 0.01062, + "map_at_10": 0.01404, + "map_at_100": 0.01931, + "map_at_1000": 0.02078, + "recall_at_1": 0.003, + "recall_at_3": 0.016, + "recall_at_5": 0.026, + "recall_at_10": 0.0525, + "recall_at_100": 0.228, + "recall_at_1000": 0.649, + "precision_at_1": 0.003, + "precision_at_3": 0.00533, + "precision_at_5": 0.0052, + "precision_at_10": 0.00525, + "precision_at_100": 0.00228, + "precision_at_1000": 0.00065 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/text-embedding-3-small-instruct/no_revision_available/TempReasonL2Fact.json b/results/text-embedding-3-small-instruct/no_revision_available/TempReasonL2Fact.json new file mode 100644 index 000000000..5f03e5a35 --- /dev/null +++ b/results/text-embedding-3-small-instruct/no_revision_available/TempReasonL2Fact.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.26338, + "ndcg_at_1": 0.10765, + "ndcg_at_3": 0.19317, + "ndcg_at_5": 0.22568, + "ndcg_at_10": 0.26338, + "ndcg_at_100": 0.32964, + "ndcg_at_1000": 0.35162, + "map_at_1": 0.10765, + "map_at_3": 0.17152, + "map_at_5": 0.18952, + "map_at_10": 0.20498, + "map_at_100": 0.2177, + "map_at_1000": 0.2185, + "recall_at_1": 0.10765, + "recall_at_3": 0.25607, + "recall_at_5": 0.33519, + "recall_at_10": 0.45229, + "recall_at_100": 0.77247, + "recall_at_1000": 0.94701, + "precision_at_1": 0.10765, + "precision_at_3": 0.08536, + "precision_at_5": 0.06704, + "precision_at_10": 0.04523, + "precision_at_100": 0.00772, + "precision_at_1000": 0.00095 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/text-embedding-3-small-instruct/no_revision_available/TempReasonL2Pure.json b/results/text-embedding-3-small-instruct/no_revision_available/TempReasonL2Pure.json new file mode 100644 index 000000000..27dd75211 --- /dev/null +++ b/results/text-embedding-3-small-instruct/no_revision_available/TempReasonL2Pure.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.03166, + "ndcg_at_1": 0.01001, + "ndcg_at_3": 0.01788, + "ndcg_at_5": 0.02252, + "ndcg_at_10": 0.03166, + "ndcg_at_100": 0.07142, + "ndcg_at_1000": 0.11977, + "map_at_1": 0.01001, + "map_at_3": 0.01581, + "map_at_5": 0.01838, + "map_at_10": 0.0221, + "map_at_100": 0.02838, + "map_at_1000": 0.02989, + "recall_at_1": 0.01001, + "recall_at_3": 0.0239, + "recall_at_5": 0.0352, + "recall_at_10": 0.06374, + "recall_at_100": 0.27182, + "recall_at_1000": 0.67074, + "precision_at_1": 0.01001, + "precision_at_3": 0.00797, + "precision_at_5": 0.00704, + "precision_at_10": 0.00637, + "precision_at_100": 0.00272, + "precision_at_1000": 0.00067 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/text-embedding-3-small-instruct/no_revision_available/TempReasonL3Fact.json b/results/text-embedding-3-small-instruct/no_revision_available/TempReasonL3Fact.json new file mode 100644 index 000000000..e805ecca6 --- /dev/null +++ b/results/text-embedding-3-small-instruct/no_revision_available/TempReasonL3Fact.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.22715, + "ndcg_at_1": 0.06078, + "ndcg_at_3": 0.15237, + "ndcg_at_5": 0.18992, + "ndcg_at_10": 0.22715, + "ndcg_at_100": 0.29406, + "ndcg_at_1000": 0.31842, + "map_at_1": 0.06078, + "map_at_3": 0.12901, + "map_at_5": 0.14982, + "map_at_10": 0.16529, + "map_at_100": 0.17817, + "map_at_1000": 0.17903, + "recall_at_1": 0.06078, + "recall_at_3": 0.22029, + "recall_at_5": 0.31157, + "recall_at_10": 0.42612, + "recall_at_100": 0.74944, + "recall_at_1000": 0.94419, + "precision_at_1": 0.06078, + "precision_at_3": 0.07343, + "precision_at_5": 0.06231, + "precision_at_10": 0.04261, + "precision_at_100": 0.00749, + "precision_at_1000": 0.00094 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/text-embedding-3-small-instruct/no_revision_available/TempReasonL3Pure.json b/results/text-embedding-3-small-instruct/no_revision_available/TempReasonL3Pure.json new file mode 100644 index 000000000..5af9905bf --- /dev/null +++ b/results/text-embedding-3-small-instruct/no_revision_available/TempReasonL3Pure.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.09976, + "ndcg_at_1": 0.00294, + "ndcg_at_3": 0.05572, + "ndcg_at_5": 0.07566, + "ndcg_at_10": 0.09976, + "ndcg_at_100": 0.15336, + "ndcg_at_1000": 0.19476, + "map_at_1": 0.00294, + "map_at_3": 0.04233, + "map_at_5": 0.05334, + "map_at_10": 0.06328, + "map_at_100": 0.07278, + "map_at_1000": 0.07417, + "recall_at_1": 0.00294, + "recall_at_3": 0.09467, + "recall_at_5": 0.14324, + "recall_at_10": 0.2178, + "recall_at_100": 0.48667, + "recall_at_1000": 0.82196, + "precision_at_1": 0.00294, + "precision_at_3": 0.03156, + "precision_at_5": 0.02865, + "precision_at_10": 0.02178, + "precision_at_100": 0.00487, + "precision_at_1000": 0.00082 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/text-embedding-3-small-instruct/no_revision_available/WinoGrande.json b/results/text-embedding-3-small-instruct/no_revision_available/WinoGrande.json new file mode 100644 index 000000000..602c64d91 --- /dev/null +++ b/results/text-embedding-3-small-instruct/no_revision_available/WinoGrande.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.25488, + "ndcg_at_1": 0.10497, + "ndcg_at_3": 0.17965, + "ndcg_at_5": 0.21728, + "ndcg_at_10": 0.25488, + "ndcg_at_100": 0.34646, + "ndcg_at_1000": 0.36133, + "map_at_1": 0.10497, + "map_at_3": 0.16127, + "map_at_5": 0.18211, + "map_at_10": 0.19752, + "map_at_100": 0.21565, + "map_at_1000": 0.21626, + "recall_at_1": 0.10497, + "recall_at_3": 0.23283, + "recall_at_5": 0.32439, + "recall_at_10": 0.4412, + "recall_at_100": 0.87687, + "recall_at_1000": 0.99132, + "precision_at_1": 0.10497, + "precision_at_3": 0.07761, + "precision_at_5": 0.06488, + "precision_at_10": 0.04412, + "precision_at_100": 0.00877, + "precision_at_1000": 0.00099 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/text-embedding-3-small/no_revision_available/ARCChallenge.json b/results/text-embedding-3-small/no_revision_available/ARCChallenge.json new file mode 100644 index 000000000..a7a521b92 --- /dev/null +++ b/results/text-embedding-3-small/no_revision_available/ARCChallenge.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.1463, + "ndcg_at_1": 0.05461, + "ndcg_at_3": 0.10321, + "ndcg_at_5": 0.1245, + "ndcg_at_10": 0.1463, + "ndcg_at_100": 0.20328, + "ndcg_at_1000": 0.24408, + "map_at_1": 0.05461, + "map_at_3": 0.09087, + "map_at_5": 0.1026, + "map_at_10": 0.11144, + "map_at_100": 0.12158, + "map_at_1000": 0.12296, + "recall_at_1": 0.05461, + "recall_at_3": 0.13908, + "recall_at_5": 0.19113, + "recall_at_10": 0.25939, + "recall_at_100": 0.54352, + "recall_at_1000": 0.87372, + "precision_at_1": 0.05461, + "precision_at_3": 0.04636, + "precision_at_5": 0.03823, + "precision_at_10": 0.02594, + "precision_at_100": 0.00544, + "precision_at_1000": 0.00087 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/text-embedding-3-small/no_revision_available/AlphaNLI.json b/results/text-embedding-3-small/no_revision_available/AlphaNLI.json new file mode 100644 index 000000000..7bfa23123 --- /dev/null +++ b/results/text-embedding-3-small/no_revision_available/AlphaNLI.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.30611, + "ndcg_at_1": 0.20104, + "ndcg_at_3": 0.26792, + "ndcg_at_5": 0.28898, + "ndcg_at_10": 0.30611, + "ndcg_at_100": 0.34539, + "ndcg_at_1000": 0.3702, + "map_at_1": 0.20104, + "map_at_3": 0.25174, + "map_at_5": 0.26333, + "map_at_10": 0.27054, + "map_at_100": 0.27745, + "map_at_1000": 0.2783, + "recall_at_1": 0.20104, + "recall_at_3": 0.31462, + "recall_at_5": 0.36619, + "recall_at_10": 0.41841, + "recall_at_100": 0.61554, + "recall_at_1000": 0.81593, + "precision_at_1": 0.20104, + "precision_at_3": 0.10487, + "precision_at_5": 0.07324, + "precision_at_10": 0.04184, + "precision_at_100": 0.00616, + "precision_at_1000": 0.00082 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/text-embedding-3-small/no_revision_available/HellaSwag.json b/results/text-embedding-3-small/no_revision_available/HellaSwag.json new file mode 100644 index 000000000..0326d6ab3 --- /dev/null +++ b/results/text-embedding-3-small/no_revision_available/HellaSwag.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.30941, + "ndcg_at_1": 0.16939, + "ndcg_at_3": 0.25698, + "ndcg_at_5": 0.28467, + "ndcg_at_10": 0.30941, + "ndcg_at_100": 0.35679, + "ndcg_at_1000": 0.37977, + "map_at_1": 0.16939, + "map_at_3": 0.23506, + "map_at_5": 0.25045, + "map_at_10": 0.26069, + "map_at_100": 0.26971, + "map_at_1000": 0.2705, + "recall_at_1": 0.16939, + "recall_at_3": 0.32055, + "recall_at_5": 0.38767, + "recall_at_10": 0.46405, + "recall_at_100": 0.69399, + "recall_at_1000": 0.87911, + "precision_at_1": 0.16939, + "precision_at_3": 0.10685, + "precision_at_5": 0.07753, + "precision_at_10": 0.04641, + "precision_at_100": 0.00694, + "precision_at_1000": 0.00088 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/text-embedding-3-small/no_revision_available/PIQA.json b/results/text-embedding-3-small/no_revision_available/PIQA.json new file mode 100644 index 000000000..38a237e32 --- /dev/null +++ b/results/text-embedding-3-small/no_revision_available/PIQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.33692, + "ndcg_at_1": 0.18281, + "ndcg_at_3": 0.28593, + "ndcg_at_5": 0.31122, + "ndcg_at_10": 0.33692, + "ndcg_at_100": 0.38283, + "ndcg_at_1000": 0.40219, + "map_at_1": 0.18281, + "map_at_3": 0.26097, + "map_at_5": 0.27512, + "map_at_10": 0.28584, + "map_at_100": 0.29474, + "map_at_1000": 0.29539, + "recall_at_1": 0.18281, + "recall_at_3": 0.358, + "recall_at_5": 0.41893, + "recall_at_10": 0.49782, + "recall_at_100": 0.71817, + "recall_at_1000": 0.87541, + "precision_at_1": 0.18281, + "precision_at_3": 0.11933, + "precision_at_5": 0.08379, + "precision_at_10": 0.04978, + "precision_at_100": 0.00718, + "precision_at_1000": 0.00088 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/text-embedding-3-small/no_revision_available/Quail.json b/results/text-embedding-3-small/no_revision_available/Quail.json new file mode 100644 index 000000000..7eadd3e18 --- /dev/null +++ b/results/text-embedding-3-small/no_revision_available/Quail.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.06108, + "ndcg_at_1": 0.02316, + "ndcg_at_3": 0.03988, + "ndcg_at_5": 0.04827, + "ndcg_at_10": 0.06108, + "ndcg_at_100": 0.09651, + "ndcg_at_1000": 0.12607, + "map_at_1": 0.02316, + "map_at_3": 0.03542, + "map_at_5": 0.0401, + "map_at_10": 0.0453, + "map_at_100": 0.05174, + "map_at_1000": 0.05262, + "recall_at_1": 0.02316, + "recall_at_3": 0.05294, + "recall_at_5": 0.07316, + "recall_at_10": 0.11324, + "recall_at_100": 0.2886, + "recall_at_1000": 0.53493, + "precision_at_1": 0.02316, + "precision_at_3": 0.01765, + "precision_at_5": 0.01463, + "precision_at_10": 0.01132, + "precision_at_100": 0.00289, + "precision_at_1000": 0.00053 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/text-embedding-3-small/no_revision_available/RARbCode.json b/results/text-embedding-3-small/no_revision_available/RARbCode.json new file mode 100644 index 000000000..fbff8d27e --- /dev/null +++ b/results/text-embedding-3-small/no_revision_available/RARbCode.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.72027, + "ndcg_at_1": 0.56267, + "ndcg_at_3": 0.67065, + "ndcg_at_5": 0.69825, + "ndcg_at_10": 0.72027, + "ndcg_at_100": 0.74315, + "ndcg_at_1000": 0.74495, + "map_at_1": 0.56267, + "map_at_3": 0.64477, + "map_at_5": 0.66, + "map_at_10": 0.66921, + "map_at_100": 0.67439, + "map_at_1000": 0.67445, + "recall_at_1": 0.56267, + "recall_at_3": 0.74528, + "recall_at_5": 0.81267, + "recall_at_10": 0.88005, + "recall_at_100": 0.98181, + "recall_at_1000": 0.99663, + "precision_at_1": 0.56267, + "precision_at_3": 0.24843, + "precision_at_5": 0.16253, + "precision_at_10": 0.08801, + "precision_at_100": 0.00982, + "precision_at_1000": 0.001 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/text-embedding-3-small/no_revision_available/RARbMath.json b/results/text-embedding-3-small/no_revision_available/RARbMath.json new file mode 100644 index 000000000..3b03dfcd2 --- /dev/null +++ b/results/text-embedding-3-small/no_revision_available/RARbMath.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.7107, + "ndcg_at_1": 0.64441, + "ndcg_at_3": 0.68618, + "ndcg_at_5": 0.69841, + "ndcg_at_10": 0.7107, + "ndcg_at_100": 0.7378, + "ndcg_at_1000": 0.74701, + "map_at_1": 0.64441, + "map_at_3": 0.67595, + "map_at_5": 0.68272, + "map_at_10": 0.68782, + "map_at_100": 0.69297, + "map_at_1000": 0.69331, + "recall_at_1": 0.64441, + "recall_at_3": 0.71578, + "recall_at_5": 0.74553, + "recall_at_10": 0.78335, + "recall_at_100": 0.9147, + "recall_at_1000": 0.9875, + "precision_at_1": 0.64441, + "precision_at_3": 0.23859, + "precision_at_5": 0.14911, + "precision_at_10": 0.07834, + "precision_at_100": 0.00915, + "precision_at_1000": 0.00099 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/text-embedding-3-small/no_revision_available/SIQA.json b/results/text-embedding-3-small/no_revision_available/SIQA.json new file mode 100644 index 000000000..47b020520 --- /dev/null +++ b/results/text-embedding-3-small/no_revision_available/SIQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.03029, + "ndcg_at_1": 0.01535, + "ndcg_at_3": 0.02418, + "ndcg_at_5": 0.02671, + "ndcg_at_10": 0.03029, + "ndcg_at_100": 0.0416, + "ndcg_at_1000": 0.07653, + "map_at_1": 0.01535, + "map_at_3": 0.02209, + "map_at_5": 0.0235, + "map_at_10": 0.02494, + "map_at_100": 0.02669, + "map_at_1000": 0.02756, + "recall_at_1": 0.01535, + "recall_at_3": 0.03019, + "recall_at_5": 0.03634, + "recall_at_10": 0.04759, + "recall_at_100": 0.10696, + "recall_at_1000": 0.4089, + "precision_at_1": 0.01535, + "precision_at_3": 0.01006, + "precision_at_5": 0.00727, + "precision_at_10": 0.00476, + "precision_at_100": 0.00107, + "precision_at_1000": 0.00041 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/text-embedding-3-small/no_revision_available/SpartQA.json b/results/text-embedding-3-small/no_revision_available/SpartQA.json new file mode 100644 index 000000000..516de8229 --- /dev/null +++ b/results/text-embedding-3-small/no_revision_available/SpartQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.06627, + "ndcg_at_1": 0.01336, + "ndcg_at_3": 0.02736, + "ndcg_at_5": 0.0432, + "ndcg_at_10": 0.06627, + "ndcg_at_100": 0.10555, + "ndcg_at_1000": 0.12809, + "map_at_1": 0.00983, + "map_at_3": 0.02153, + "map_at_5": 0.02988, + "map_at_10": 0.03892, + "map_at_100": 0.04665, + "map_at_1000": 0.04708, + "recall_at_1": 0.00983, + "recall_at_3": 0.03664, + "recall_at_5": 0.07197, + "recall_at_10": 0.13652, + "recall_at_100": 0.3018, + "recall_at_1000": 0.47709, + "precision_at_1": 0.01336, + "precision_at_3": 0.01716, + "precision_at_5": 0.02059, + "precision_at_10": 0.02037, + "precision_at_100": 0.00462, + "precision_at_1000": 0.00078 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/text-embedding-3-small/no_revision_available/TempReasonL1.json b/results/text-embedding-3-small/no_revision_available/TempReasonL1.json new file mode 100644 index 000000000..ce74f2bcd --- /dev/null +++ b/results/text-embedding-3-small/no_revision_available/TempReasonL1.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02348, + "ndcg_at_1": 0.0035, + "ndcg_at_3": 0.01082, + "ndcg_at_5": 0.015, + "ndcg_at_10": 0.02348, + "ndcg_at_100": 0.05582, + "ndcg_at_1000": 0.10586, + "map_at_1": 0.0035, + "map_at_3": 0.00896, + "map_at_5": 0.01125, + "map_at_10": 0.01465, + "map_at_100": 0.01968, + "map_at_1000": 0.02109, + "recall_at_1": 0.0035, + "recall_at_3": 0.01625, + "recall_at_5": 0.0265, + "recall_at_10": 0.05325, + "recall_at_100": 0.22325, + "recall_at_1000": 0.64525, + "precision_at_1": 0.0035, + "precision_at_3": 0.00542, + "precision_at_5": 0.0053, + "precision_at_10": 0.00533, + "precision_at_100": 0.00223, + "precision_at_1000": 0.00065 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/text-embedding-3-small/no_revision_available/TempReasonL2Fact.json b/results/text-embedding-3-small/no_revision_available/TempReasonL2Fact.json new file mode 100644 index 000000000..78d23fd2c --- /dev/null +++ b/results/text-embedding-3-small/no_revision_available/TempReasonL2Fact.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.25678, + "ndcg_at_1": 0.10469, + "ndcg_at_3": 0.18923, + "ndcg_at_5": 0.21993, + "ndcg_at_10": 0.25678, + "ndcg_at_100": 0.32463, + "ndcg_at_1000": 0.34706, + "map_at_1": 0.10469, + "map_at_3": 0.16793, + "map_at_5": 0.1849, + "map_at_10": 0.2001, + "map_at_100": 0.21319, + "map_at_1000": 0.21399, + "recall_at_1": 0.10469, + "recall_at_3": 0.25107, + "recall_at_5": 0.32592, + "recall_at_10": 0.43987, + "recall_at_100": 0.76709, + "recall_at_1000": 0.94553, + "precision_at_1": 0.10469, + "precision_at_3": 0.08369, + "precision_at_5": 0.06518, + "precision_at_10": 0.04399, + "precision_at_100": 0.00767, + "precision_at_1000": 0.00095 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/text-embedding-3-small/no_revision_available/TempReasonL2Pure.json b/results/text-embedding-3-small/no_revision_available/TempReasonL2Pure.json new file mode 100644 index 000000000..a201e8dba --- /dev/null +++ b/results/text-embedding-3-small/no_revision_available/TempReasonL2Pure.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02755, + "ndcg_at_1": 0.00945, + "ndcg_at_3": 0.01613, + "ndcg_at_5": 0.02092, + "ndcg_at_10": 0.02755, + "ndcg_at_100": 0.06417, + "ndcg_at_1000": 0.11254, + "map_at_1": 0.00945, + "map_at_3": 0.0143, + "map_at_5": 0.01695, + "map_at_10": 0.01971, + "map_at_100": 0.02552, + "map_at_1000": 0.02701, + "recall_at_1": 0.00945, + "recall_at_3": 0.02149, + "recall_at_5": 0.03317, + "recall_at_10": 0.05355, + "recall_at_100": 0.24495, + "recall_at_1000": 0.64499, + "precision_at_1": 0.00945, + "precision_at_3": 0.00716, + "precision_at_5": 0.00663, + "precision_at_10": 0.00535, + "precision_at_100": 0.00245, + "precision_at_1000": 0.00064 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/text-embedding-3-small/no_revision_available/TempReasonL3Fact.json b/results/text-embedding-3-small/no_revision_available/TempReasonL3Fact.json new file mode 100644 index 000000000..ae3895fca --- /dev/null +++ b/results/text-embedding-3-small/no_revision_available/TempReasonL3Fact.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.22091, + "ndcg_at_1": 0.05038, + "ndcg_at_3": 0.14666, + "ndcg_at_5": 0.18353, + "ndcg_at_10": 0.22091, + "ndcg_at_100": 0.28519, + "ndcg_at_1000": 0.31073, + "map_at_1": 0.05038, + "map_at_3": 0.12204, + "map_at_5": 0.14251, + "map_at_10": 0.15801, + "map_at_100": 0.17016, + "map_at_1000": 0.17107, + "recall_at_1": 0.05038, + "recall_at_3": 0.21826, + "recall_at_5": 0.30773, + "recall_at_10": 0.42296, + "recall_at_100": 0.73588, + "recall_at_1000": 0.9399, + "precision_at_1": 0.05038, + "precision_at_3": 0.07275, + "precision_at_5": 0.06155, + "precision_at_10": 0.0423, + "precision_at_100": 0.00736, + "precision_at_1000": 0.00094 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/text-embedding-3-small/no_revision_available/TempReasonL3Pure.json b/results/text-embedding-3-small/no_revision_available/TempReasonL3Pure.json new file mode 100644 index 000000000..d86e86fd9 --- /dev/null +++ b/results/text-embedding-3-small/no_revision_available/TempReasonL3Pure.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.09793, + "ndcg_at_1": 0.00249, + "ndcg_at_3": 0.05466, + "ndcg_at_5": 0.0759, + "ndcg_at_10": 0.09793, + "ndcg_at_100": 0.14715, + "ndcg_at_1000": 0.18951, + "map_at_1": 0.00249, + "map_at_3": 0.04116, + "map_at_5": 0.05291, + "map_at_10": 0.06202, + "map_at_100": 0.07062, + "map_at_1000": 0.07199, + "recall_at_1": 0.00249, + "recall_at_3": 0.09399, + "recall_at_5": 0.14573, + "recall_at_10": 0.21374, + "recall_at_100": 0.46204, + "recall_at_1000": 0.80795, + "precision_at_1": 0.00249, + "precision_at_3": 0.03133, + "precision_at_5": 0.02915, + "precision_at_10": 0.02137, + "precision_at_100": 0.00462, + "precision_at_1000": 0.00081 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/text-embedding-3-small/no_revision_available/WinoGrande.json b/results/text-embedding-3-small/no_revision_available/WinoGrande.json new file mode 100644 index 000000000..a33e750e4 --- /dev/null +++ b/results/text-embedding-3-small/no_revision_available/WinoGrande.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.31526, + "ndcg_at_1": 0.13496, + "ndcg_at_3": 0.22646, + "ndcg_at_5": 0.26739, + "ndcg_at_10": 0.31526, + "ndcg_at_100": 0.39715, + "ndcg_at_1000": 0.40717, + "map_at_1": 0.13496, + "map_at_3": 0.2031, + "map_at_5": 0.2258, + "map_at_10": 0.24533, + "map_at_100": 0.26263, + "map_at_1000": 0.26303, + "recall_at_1": 0.13496, + "recall_at_3": 0.2944, + "recall_at_5": 0.39384, + "recall_at_10": 0.54301, + "recall_at_100": 0.92107, + "recall_at_1000": 0.99842, + "precision_at_1": 0.13496, + "precision_at_3": 0.09813, + "precision_at_5": 0.07877, + "precision_at_10": 0.0543, + "precision_at_100": 0.00921, + "precision_at_1000": 0.001 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002-instruct/no_revision_available/ARCChallenge.json b/results/text-embedding-ada-002-instruct/no_revision_available/ARCChallenge.json new file mode 100644 index 000000000..d8a3fef48 --- /dev/null +++ b/results/text-embedding-ada-002-instruct/no_revision_available/ARCChallenge.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.11847, + "ndcg_at_1": 0.03925, + "ndcg_at_3": 0.08164, + "ndcg_at_5": 0.1, + "ndcg_at_10": 0.11847, + "ndcg_at_100": 0.17408, + "ndcg_at_1000": 0.21556, + "map_at_1": 0.03925, + "map_at_3": 0.07096, + "map_at_5": 0.0812, + "map_at_10": 0.08898, + "map_at_100": 0.09863, + "map_at_1000": 0.09998, + "recall_at_1": 0.03925, + "recall_at_3": 0.11263, + "recall_at_5": 0.157, + "recall_at_10": 0.21331, + "recall_at_100": 0.49317, + "recall_at_1000": 0.83106, + "precision_at_1": 0.03925, + "precision_at_3": 0.03754, + "precision_at_5": 0.0314, + "precision_at_10": 0.02133, + "precision_at_100": 0.00493, + "precision_at_1000": 0.00083 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002-instruct/no_revision_available/AlphaNLI.json b/results/text-embedding-ada-002-instruct/no_revision_available/AlphaNLI.json new file mode 100644 index 000000000..67b33cdc2 --- /dev/null +++ b/results/text-embedding-ada-002-instruct/no_revision_available/AlphaNLI.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.10619, + "ndcg_at_1": 0.047, + "ndcg_at_3": 0.07867, + "ndcg_at_5": 0.09266, + "ndcg_at_10": 0.10619, + "ndcg_at_100": 0.14105, + "ndcg_at_1000": 0.17065, + "map_at_1": 0.047, + "map_at_3": 0.0705, + "map_at_5": 0.07826, + "map_at_10": 0.08386, + "map_at_100": 0.08987, + "map_at_1000": 0.09076, + "recall_at_1": 0.047, + "recall_at_3": 0.10248, + "recall_at_5": 0.13642, + "recall_at_10": 0.1782, + "recall_at_100": 0.35444, + "recall_at_1000": 0.59922, + "precision_at_1": 0.047, + "precision_at_3": 0.03416, + "precision_at_5": 0.02728, + "precision_at_10": 0.01782, + "precision_at_100": 0.00354, + "precision_at_1000": 0.0006 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002-instruct/no_revision_available/HellaSwag.json b/results/text-embedding-ada-002-instruct/no_revision_available/HellaSwag.json new file mode 100644 index 000000000..72ebb5da6 --- /dev/null +++ b/results/text-embedding-ada-002-instruct/no_revision_available/HellaSwag.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.248, + "ndcg_at_1": 0.12995, + "ndcg_at_3": 0.2015, + "ndcg_at_5": 0.22556, + "ndcg_at_10": 0.248, + "ndcg_at_100": 0.2939, + "ndcg_at_1000": 0.31983, + "map_at_1": 0.12995, + "map_at_3": 0.18366, + "map_at_5": 0.197, + "map_at_10": 0.20633, + "map_at_100": 0.21485, + "map_at_1000": 0.21571, + "recall_at_1": 0.12995, + "recall_at_3": 0.25324, + "recall_at_5": 0.31169, + "recall_at_10": 0.3807, + "recall_at_100": 0.60615, + "recall_at_1000": 0.81667, + "precision_at_1": 0.12995, + "precision_at_3": 0.08441, + "precision_at_5": 0.06234, + "precision_at_10": 0.03807, + "precision_at_100": 0.00606, + "precision_at_1000": 0.00082 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002-instruct/no_revision_available/PIQA.json b/results/text-embedding-ada-002-instruct/no_revision_available/PIQA.json new file mode 100644 index 000000000..f25676b1e --- /dev/null +++ b/results/text-embedding-ada-002-instruct/no_revision_available/PIQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.2387, + "ndcg_at_1": 0.11099, + "ndcg_at_3": 0.19119, + "ndcg_at_5": 0.21421, + "ndcg_at_10": 0.2387, + "ndcg_at_100": 0.28582, + "ndcg_at_1000": 0.31129, + "map_at_1": 0.11099, + "map_at_3": 0.17202, + "map_at_5": 0.18475, + "map_at_10": 0.19498, + "map_at_100": 0.20406, + "map_at_1000": 0.20489, + "recall_at_1": 0.11099, + "recall_at_3": 0.24646, + "recall_at_5": 0.3025, + "recall_at_10": 0.37758, + "recall_at_100": 0.60501, + "recall_at_1000": 0.81338, + "precision_at_1": 0.11099, + "precision_at_3": 0.08215, + "precision_at_5": 0.0605, + "precision_at_10": 0.03776, + "precision_at_100": 0.00605, + "precision_at_1000": 0.00081 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002-instruct/no_revision_available/Quail.json b/results/text-embedding-ada-002-instruct/no_revision_available/Quail.json new file mode 100644 index 000000000..1a08fef0f --- /dev/null +++ b/results/text-embedding-ada-002-instruct/no_revision_available/Quail.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.05791, + "ndcg_at_1": 0.02169, + "ndcg_at_3": 0.03628, + "ndcg_at_5": 0.04628, + "ndcg_at_10": 0.05791, + "ndcg_at_100": 0.09159, + "ndcg_at_1000": 0.12062, + "map_at_1": 0.02169, + "map_at_3": 0.03235, + "map_at_5": 0.0379, + "map_at_10": 0.04262, + "map_at_100": 0.04873, + "map_at_1000": 0.04963, + "recall_at_1": 0.02169, + "recall_at_3": 0.04779, + "recall_at_5": 0.07206, + "recall_at_10": 0.10846, + "recall_at_100": 0.27537, + "recall_at_1000": 0.51507, + "precision_at_1": 0.02169, + "precision_at_3": 0.01593, + "precision_at_5": 0.01441, + "precision_at_10": 0.01085, + "precision_at_100": 0.00275, + "precision_at_1000": 0.00052 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002-instruct/no_revision_available/RARbCode.json b/results/text-embedding-ada-002-instruct/no_revision_available/RARbCode.json new file mode 100644 index 000000000..e0efd7852 --- /dev/null +++ b/results/text-embedding-ada-002-instruct/no_revision_available/RARbCode.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.82356, + "ndcg_at_1": 0.73652, + "ndcg_at_3": 0.80304, + "ndcg_at_5": 0.81644, + "ndcg_at_10": 0.82356, + "ndcg_at_100": 0.83335, + "ndcg_at_1000": 0.83686, + "map_at_1": 0.73652, + "map_at_3": 0.78729, + "map_at_5": 0.79477, + "map_at_10": 0.79767, + "map_at_100": 0.79974, + "map_at_1000": 0.79987, + "recall_at_1": 0.73652, + "recall_at_3": 0.84838, + "recall_at_5": 0.88073, + "recall_at_10": 0.90296, + "recall_at_100": 0.94811, + "recall_at_1000": 0.97642, + "precision_at_1": 0.73652, + "precision_at_3": 0.28279, + "precision_at_5": 0.17615, + "precision_at_10": 0.0903, + "precision_at_100": 0.00948, + "precision_at_1000": 0.00098 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002-instruct/no_revision_available/RARbMath.json b/results/text-embedding-ada-002-instruct/no_revision_available/RARbMath.json new file mode 100644 index 000000000..5e808f95c --- /dev/null +++ b/results/text-embedding-ada-002-instruct/no_revision_available/RARbMath.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.6726, + "ndcg_at_1": 0.59899, + "ndcg_at_3": 0.64433, + "ndcg_at_5": 0.65798, + "ndcg_at_10": 0.6726, + "ndcg_at_100": 0.70565, + "ndcg_at_1000": 0.71435, + "map_at_1": 0.59899, + "map_at_3": 0.63301, + "map_at_5": 0.64056, + "map_at_10": 0.64655, + "map_at_100": 0.65281, + "map_at_1000": 0.65314, + "recall_at_1": 0.59899, + "recall_at_3": 0.67716, + "recall_at_5": 0.7104, + "recall_at_10": 0.75582, + "recall_at_100": 0.9166, + "recall_at_1000": 0.98512, + "precision_at_1": 0.59899, + "precision_at_3": 0.22572, + "precision_at_5": 0.14208, + "precision_at_10": 0.07558, + "precision_at_100": 0.00917, + "precision_at_1000": 0.00099 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002-instruct/no_revision_available/SIQA.json b/results/text-embedding-ada-002-instruct/no_revision_available/SIQA.json new file mode 100644 index 000000000..404d95332 --- /dev/null +++ b/results/text-embedding-ada-002-instruct/no_revision_available/SIQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02641, + "ndcg_at_1": 0.01279, + "ndcg_at_3": 0.01864, + "ndcg_at_5": 0.02075, + "ndcg_at_10": 0.02641, + "ndcg_at_100": 0.04155, + "ndcg_at_1000": 0.07039, + "map_at_1": 0.01279, + "map_at_3": 0.01697, + "map_at_5": 0.01815, + "map_at_10": 0.0205, + "map_at_100": 0.02306, + "map_at_1000": 0.02387, + "recall_at_1": 0.01279, + "recall_at_3": 0.02354, + "recall_at_5": 0.02866, + "recall_at_10": 0.04606, + "recall_at_100": 0.12385, + "recall_at_1000": 0.36694, + "precision_at_1": 0.01279, + "precision_at_3": 0.00785, + "precision_at_5": 0.00573, + "precision_at_10": 0.00461, + "precision_at_100": 0.00124, + "precision_at_1000": 0.00037 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002-instruct/no_revision_available/SpartQA.json b/results/text-embedding-ada-002-instruct/no_revision_available/SpartQA.json new file mode 100644 index 000000000..c6f136c14 --- /dev/null +++ b/results/text-embedding-ada-002-instruct/no_revision_available/SpartQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.04751, + "ndcg_at_1": 0.00974, + "ndcg_at_3": 0.02173, + "ndcg_at_5": 0.03313, + "ndcg_at_10": 0.04751, + "ndcg_at_100": 0.08131, + "ndcg_at_1000": 0.10968, + "map_at_1": 0.00659, + "map_at_3": 0.01651, + "map_at_5": 0.02227, + "map_at_10": 0.02773, + "map_at_100": 0.03346, + "map_at_1000": 0.03418, + "recall_at_1": 0.00659, + "recall_at_3": 0.02931, + "recall_at_5": 0.05435, + "recall_at_10": 0.09423, + "recall_at_100": 0.2468, + "recall_at_1000": 0.46123, + "precision_at_1": 0.00974, + "precision_at_3": 0.01465, + "precision_at_5": 0.01636, + "precision_at_10": 0.01458, + "precision_at_100": 0.00384, + "precision_at_1000": 0.00076 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL1.json b/results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL1.json new file mode 100644 index 000000000..b16272893 --- /dev/null +++ b/results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL1.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01441, + "ndcg_at_1": 0.00075, + "ndcg_at_3": 0.00659, + "ndcg_at_5": 0.01003, + "ndcg_at_10": 0.01441, + "ndcg_at_100": 0.03917, + "ndcg_at_1000": 0.08979, + "map_at_1": 0.00075, + "map_at_3": 0.005, + "map_at_5": 0.00687, + "map_at_10": 0.00865, + "map_at_100": 0.01271, + "map_at_1000": 0.01407, + "recall_at_1": 0.00075, + "recall_at_3": 0.01125, + "recall_at_5": 0.01975, + "recall_at_10": 0.0335, + "recall_at_100": 0.16125, + "recall_at_1000": 0.592, + "precision_at_1": 0.00075, + "precision_at_3": 0.00375, + "precision_at_5": 0.00395, + "precision_at_10": 0.00335, + "precision_at_100": 0.00161, + "precision_at_1000": 0.00059 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL2Fact.json b/results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL2Fact.json new file mode 100644 index 000000000..914c8bf85 --- /dev/null +++ b/results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL2Fact.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.19382, + "ndcg_at_1": 0.08394, + "ndcg_at_3": 0.13932, + "ndcg_at_5": 0.16438, + "ndcg_at_10": 0.19382, + "ndcg_at_100": 0.25685, + "ndcg_at_1000": 0.28776, + "map_at_1": 0.08394, + "map_at_3": 0.12529, + "map_at_5": 0.13921, + "map_at_10": 0.15134, + "map_at_100": 0.16315, + "map_at_1000": 0.16422, + "recall_at_1": 0.08394, + "recall_at_3": 0.1801, + "recall_at_5": 0.24087, + "recall_at_10": 0.33204, + "recall_at_100": 0.63999, + "recall_at_1000": 0.88864, + "precision_at_1": 0.08394, + "precision_at_3": 0.06003, + "precision_at_5": 0.04817, + "precision_at_10": 0.0332, + "precision_at_100": 0.0064, + "precision_at_1000": 0.00089 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL2Pure.json b/results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL2Pure.json new file mode 100644 index 000000000..adf75ae5f --- /dev/null +++ b/results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL2Pure.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.02428, + "ndcg_at_1": 0.00778, + "ndcg_at_3": 0.01552, + "ndcg_at_5": 0.01974, + "ndcg_at_10": 0.02428, + "ndcg_at_100": 0.05823, + "ndcg_at_1000": 0.10705, + "map_at_1": 0.00778, + "map_at_3": 0.01353, + "map_at_5": 0.01589, + "map_at_10": 0.01772, + "map_at_100": 0.02293, + "map_at_1000": 0.02445, + "recall_at_1": 0.00778, + "recall_at_3": 0.02131, + "recall_at_5": 0.0315, + "recall_at_10": 0.04577, + "recall_at_100": 0.2255, + "recall_at_1000": 0.62905, + "precision_at_1": 0.00778, + "precision_at_3": 0.0071, + "precision_at_5": 0.0063, + "precision_at_10": 0.00458, + "precision_at_100": 0.00225, + "precision_at_1000": 0.00063 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL3Fact.json b/results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL3Fact.json new file mode 100644 index 000000000..7b4c086d6 --- /dev/null +++ b/results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL3Fact.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.1758, + "ndcg_at_1": 0.05355, + "ndcg_at_3": 0.11447, + "ndcg_at_5": 0.14305, + "ndcg_at_10": 0.1758, + "ndcg_at_100": 0.23734, + "ndcg_at_1000": 0.26913, + "map_at_1": 0.05355, + "map_at_3": 0.09911, + "map_at_5": 0.11487, + "map_at_10": 0.12827, + "map_at_100": 0.14, + "map_at_1000": 0.1411, + "recall_at_1": 0.05355, + "recall_at_3": 0.15906, + "recall_at_5": 0.22887, + "recall_at_10": 0.33077, + "recall_at_100": 0.62946, + "recall_at_1000": 0.88522, + "precision_at_1": 0.05355, + "precision_at_3": 0.05302, + "precision_at_5": 0.04577, + "precision_at_10": 0.03308, + "precision_at_100": 0.00629, + "precision_at_1000": 0.00089 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL3Pure.json b/results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL3Pure.json new file mode 100644 index 000000000..5421f45c3 --- /dev/null +++ b/results/text-embedding-ada-002-instruct/no_revision_available/TempReasonL3Pure.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07306, + "ndcg_at_1": 0.007, + "ndcg_at_3": 0.03518, + "ndcg_at_5": 0.05176, + "ndcg_at_10": 0.07306, + "ndcg_at_100": 0.12569, + "ndcg_at_1000": 0.16778, + "map_at_1": 0.007, + "map_at_3": 0.02794, + "map_at_5": 0.03709, + "map_at_10": 0.04595, + "map_at_100": 0.05552, + "map_at_1000": 0.05688, + "recall_at_1": 0.007, + "recall_at_3": 0.05626, + "recall_at_5": 0.0967, + "recall_at_10": 0.16222, + "recall_at_100": 0.42296, + "recall_at_1000": 0.76706, + "precision_at_1": 0.007, + "precision_at_3": 0.01875, + "precision_at_5": 0.01934, + "precision_at_10": 0.01622, + "precision_at_100": 0.00423, + "precision_at_1000": 0.00077 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002-instruct/no_revision_available/WinoGrande.json b/results/text-embedding-ada-002-instruct/no_revision_available/WinoGrande.json new file mode 100644 index 000000000..2fbbf63dd --- /dev/null +++ b/results/text-embedding-ada-002-instruct/no_revision_available/WinoGrande.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.11357, + "ndcg_at_1": 0.05051, + "ndcg_at_3": 0.07831, + "ndcg_at_5": 0.09138, + "ndcg_at_10": 0.11357, + "ndcg_at_100": 0.1832, + "ndcg_at_1000": 0.22757, + "map_at_1": 0.05051, + "map_at_3": 0.0713, + "map_at_5": 0.0786, + "map_at_10": 0.08774, + "map_at_100": 0.09969, + "map_at_1000": 0.10119, + "recall_at_1": 0.05051, + "recall_at_3": 0.09866, + "recall_at_5": 0.13023, + "recall_at_10": 0.1989, + "recall_at_100": 0.5517, + "recall_at_1000": 0.91002, + "precision_at_1": 0.05051, + "precision_at_3": 0.03289, + "precision_at_5": 0.02605, + "precision_at_10": 0.01989, + "precision_at_100": 0.00552, + "precision_at_1000": 0.00091 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002/no_revision_available/ARCChallenge.json b/results/text-embedding-ada-002/no_revision_available/ARCChallenge.json new file mode 100644 index 000000000..a0658f1e9 --- /dev/null +++ b/results/text-embedding-ada-002/no_revision_available/ARCChallenge.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "c481e0da3dcbbad8bce7721dea9085b74320a0a3", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.13298, + "ndcg_at_1": 0.04693, + "ndcg_at_3": 0.09295, + "ndcg_at_5": 0.11256, + "ndcg_at_10": 0.13298, + "ndcg_at_100": 0.19483, + "ndcg_at_1000": 0.23282, + "map_at_1": 0.04693, + "map_at_3": 0.0812, + "map_at_5": 0.09204, + "map_at_10": 0.10047, + "map_at_100": 0.11146, + "map_at_1000": 0.1127, + "recall_at_1": 0.04693, + "recall_at_3": 0.12713, + "recall_at_5": 0.17491, + "recall_at_10": 0.23805, + "recall_at_100": 0.54693, + "recall_at_1000": 0.8558, + "precision_at_1": 0.04693, + "precision_at_3": 0.04238, + "precision_at_5": 0.03498, + "precision_at_10": 0.02381, + "precision_at_100": 0.00547, + "precision_at_1000": 0.00086 + } + ] + }, + "task_name": "ARCChallenge" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002/no_revision_available/AlphaNLI.json b/results/text-embedding-ada-002/no_revision_available/AlphaNLI.json new file mode 100644 index 000000000..e69dded3c --- /dev/null +++ b/results/text-embedding-ada-002/no_revision_available/AlphaNLI.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "303f40ef3d50918d3dc43577d33f2f7344ad72c1", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.25645, + "ndcg_at_1": 0.16449, + "ndcg_at_3": 0.22297, + "ndcg_at_5": 0.24083, + "ndcg_at_10": 0.25645, + "ndcg_at_100": 0.29982, + "ndcg_at_1000": 0.32644, + "map_at_1": 0.16449, + "map_at_3": 0.20866, + "map_at_5": 0.21848, + "map_at_10": 0.22479, + "map_at_100": 0.23259, + "map_at_1000": 0.23349, + "recall_at_1": 0.16449, + "recall_at_3": 0.26436, + "recall_at_5": 0.30809, + "recall_at_10": 0.35705, + "recall_at_100": 0.57311, + "recall_at_1000": 0.78851, + "precision_at_1": 0.16449, + "precision_at_3": 0.08812, + "precision_at_5": 0.06162, + "precision_at_10": 0.0357, + "precision_at_100": 0.00573, + "precision_at_1000": 0.00079 + } + ] + }, + "task_name": "AlphaNLI" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002/no_revision_available/HellaSwag.json b/results/text-embedding-ada-002/no_revision_available/HellaSwag.json new file mode 100644 index 000000000..8bb718982 --- /dev/null +++ b/results/text-embedding-ada-002/no_revision_available/HellaSwag.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "a5c990205e017d10761197ccab3000936689c3ae", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.29294, + "ndcg_at_1": 0.15794, + "ndcg_at_3": 0.24303, + "ndcg_at_5": 0.26927, + "ndcg_at_10": 0.29294, + "ndcg_at_100": 0.34026, + "ndcg_at_1000": 0.36373, + "map_at_1": 0.15794, + "map_at_3": 0.22182, + "map_at_5": 0.23644, + "map_at_10": 0.24624, + "map_at_100": 0.25502, + "map_at_1000": 0.25582, + "recall_at_1": 0.15794, + "recall_at_3": 0.30452, + "recall_at_5": 0.36795, + "recall_at_10": 0.44105, + "recall_at_100": 0.67317, + "recall_at_1000": 0.86228, + "precision_at_1": 0.15794, + "precision_at_3": 0.10151, + "precision_at_5": 0.07359, + "precision_at_10": 0.0441, + "precision_at_100": 0.00673, + "precision_at_1000": 0.00086 + } + ] + }, + "task_name": "HellaSwag" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002/no_revision_available/PIQA.json b/results/text-embedding-ada-002/no_revision_available/PIQA.json new file mode 100644 index 000000000..e6d766096 --- /dev/null +++ b/results/text-embedding-ada-002/no_revision_available/PIQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "bb30be7e9184e6b6b1d99bbfe1bb90a3a81842e6", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.31023, + "ndcg_at_1": 0.17138, + "ndcg_at_3": 0.25529, + "ndcg_at_5": 0.28347, + "ndcg_at_10": 0.31023, + "ndcg_at_100": 0.35587, + "ndcg_at_1000": 0.37834, + "map_at_1": 0.17138, + "map_at_3": 0.23531, + "map_at_5": 0.25079, + "map_at_10": 0.26183, + "map_at_100": 0.27033, + "map_at_1000": 0.27109, + "recall_at_1": 0.17138, + "recall_at_3": 0.31284, + "recall_at_5": 0.38194, + "recall_at_10": 0.46464, + "recall_at_100": 0.68825, + "recall_at_1000": 0.86942, + "precision_at_1": 0.17138, + "precision_at_3": 0.10428, + "precision_at_5": 0.07639, + "precision_at_10": 0.04646, + "precision_at_100": 0.00688, + "precision_at_1000": 0.00087 + } + ] + }, + "task_name": "PIQA" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002/no_revision_available/Quail.json b/results/text-embedding-ada-002/no_revision_available/Quail.json new file mode 100644 index 000000000..a65ea26ca --- /dev/null +++ b/results/text-embedding-ada-002/no_revision_available/Quail.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "1851bc536f8bdab29e03e29191c4586b1d8d7c5a", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.05831, + "ndcg_at_1": 0.01949, + "ndcg_at_3": 0.03692, + "ndcg_at_5": 0.04655, + "ndcg_at_10": 0.05831, + "ndcg_at_100": 0.09204, + "ndcg_at_1000": 0.12117, + "map_at_1": 0.01949, + "map_at_3": 0.03254, + "map_at_5": 0.03794, + "map_at_10": 0.04272, + "map_at_100": 0.04882, + "map_at_1000": 0.04975, + "recall_at_1": 0.01949, + "recall_at_3": 0.04963, + "recall_at_5": 0.07279, + "recall_at_10": 0.10956, + "recall_at_100": 0.27684, + "recall_at_1000": 0.51618, + "precision_at_1": 0.01949, + "precision_at_3": 0.01654, + "precision_at_5": 0.01456, + "precision_at_10": 0.01096, + "precision_at_100": 0.00277, + "precision_at_1000": 0.00052 + } + ] + }, + "task_name": "Quail" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002/no_revision_available/RARbCode.json b/results/text-embedding-ada-002/no_revision_available/RARbCode.json new file mode 100644 index 000000000..b77188c74 --- /dev/null +++ b/results/text-embedding-ada-002/no_revision_available/RARbCode.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "25f7d11a7ac12dcbb8d3836eb2de682b98c825e4", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.83393, + "ndcg_at_1": 0.74663, + "ndcg_at_3": 0.81407, + "ndcg_at_5": 0.82582, + "ndcg_at_10": 0.83393, + "ndcg_at_100": 0.84354, + "ndcg_at_1000": 0.84676, + "map_at_1": 0.74663, + "map_at_3": 0.79796, + "map_at_5": 0.80453, + "map_at_10": 0.80778, + "map_at_100": 0.80988, + "map_at_1000": 0.80998, + "recall_at_1": 0.74663, + "recall_at_3": 0.86051, + "recall_at_5": 0.88881, + "recall_at_10": 0.91442, + "recall_at_100": 0.95822, + "recall_at_1000": 0.9845, + "precision_at_1": 0.74663, + "precision_at_3": 0.28684, + "precision_at_5": 0.17776, + "precision_at_10": 0.09144, + "precision_at_100": 0.00958, + "precision_at_1000": 0.00098 + } + ] + }, + "task_name": "RARbCode" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002/no_revision_available/RARbMath.json b/results/text-embedding-ada-002/no_revision_available/RARbMath.json new file mode 100644 index 000000000..088ef45c7 --- /dev/null +++ b/results/text-embedding-ada-002/no_revision_available/RARbMath.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "2393603c0221ff52f448d12dd75f0856103c6cca", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.73206, + "ndcg_at_1": 0.66055, + "ndcg_at_3": 0.70689, + "ndcg_at_5": 0.71881, + "ndcg_at_10": 0.73206, + "ndcg_at_100": 0.7593, + "ndcg_at_1000": 0.76559, + "map_at_1": 0.66055, + "map_at_3": 0.69555, + "map_at_5": 0.70219, + "map_at_10": 0.70772, + "map_at_100": 0.71294, + "map_at_1000": 0.71316, + "recall_at_1": 0.66055, + "recall_at_3": 0.73967, + "recall_at_5": 0.76848, + "recall_at_10": 0.80915, + "recall_at_100": 0.94097, + "recall_at_1000": 0.99098, + "precision_at_1": 0.66055, + "precision_at_3": 0.24656, + "precision_at_5": 0.1537, + "precision_at_10": 0.08091, + "precision_at_100": 0.00941, + "precision_at_1000": 0.00099 + } + ] + }, + "task_name": "RARbMath" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002/no_revision_available/SIQA.json b/results/text-embedding-ada-002/no_revision_available/SIQA.json new file mode 100644 index 000000000..8c22902d4 --- /dev/null +++ b/results/text-embedding-ada-002/no_revision_available/SIQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "4ed8415e9dc24060deefc84be59e2db0aacbadcc", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.03137, + "ndcg_at_1": 0.01535, + "ndcg_at_3": 0.02276, + "ndcg_at_5": 0.02824, + "ndcg_at_10": 0.03137, + "ndcg_at_100": 0.04619, + "ndcg_at_1000": 0.07768, + "map_at_1": 0.01535, + "map_at_3": 0.0209, + "map_at_5": 0.02394, + "map_at_10": 0.02523, + "map_at_100": 0.02774, + "map_at_1000": 0.02865, + "recall_at_1": 0.01535, + "recall_at_3": 0.02815, + "recall_at_5": 0.04145, + "recall_at_10": 0.05118, + "recall_at_100": 0.12692, + "recall_at_1000": 0.39099, + "precision_at_1": 0.01535, + "precision_at_3": 0.00938, + "precision_at_5": 0.00829, + "precision_at_10": 0.00512, + "precision_at_100": 0.00127, + "precision_at_1000": 0.00039 + } + ] + }, + "task_name": "SIQA" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002/no_revision_available/SpartQA.json b/results/text-embedding-ada-002/no_revision_available/SpartQA.json new file mode 100644 index 000000000..67df5551a --- /dev/null +++ b/results/text-embedding-ada-002/no_revision_available/SpartQA.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "9ab3ca3ccdd0d43f9cd6d346a363935d127f4f45", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.04227, + "ndcg_at_1": 0.00751, + "ndcg_at_3": 0.01687, + "ndcg_at_5": 0.02823, + "ndcg_at_10": 0.04227, + "ndcg_at_100": 0.07803, + "ndcg_at_1000": 0.10498, + "map_at_1": 0.00529, + "map_at_3": 0.0128, + "map_at_5": 0.01854, + "map_at_10": 0.02393, + "map_at_100": 0.03002, + "map_at_1000": 0.03074, + "recall_at_1": 0.00529, + "recall_at_3": 0.02328, + "recall_at_5": 0.04823, + "recall_at_10": 0.08746, + "recall_at_100": 0.24708, + "recall_at_1000": 0.4501, + "precision_at_1": 0.00751, + "precision_at_3": 0.01122, + "precision_at_5": 0.01436, + "precision_at_10": 0.01322, + "precision_at_100": 0.00386, + "precision_at_1000": 0.00073 + } + ] + }, + "task_name": "SpartQA" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002/no_revision_available/TempReasonL1.json b/results/text-embedding-ada-002/no_revision_available/TempReasonL1.json new file mode 100644 index 000000000..eb06ac435 --- /dev/null +++ b/results/text-embedding-ada-002/no_revision_available/TempReasonL1.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "9097e99aa8c9d827189c65f2e11bfe756af439f6", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.01679, + "ndcg_at_1": 0.00175, + "ndcg_at_3": 0.0069, + "ndcg_at_5": 0.01097, + "ndcg_at_10": 0.01679, + "ndcg_at_100": 0.04296, + "ndcg_at_1000": 0.09303, + "map_at_1": 0.00175, + "map_at_3": 0.00558, + "map_at_5": 0.00781, + "map_at_10": 0.01021, + "map_at_100": 0.01453, + "map_at_1000": 0.01588, + "recall_at_1": 0.00175, + "recall_at_3": 0.01075, + "recall_at_5": 0.02075, + "recall_at_10": 0.03875, + "recall_at_100": 0.17375, + "recall_at_1000": 0.59925, + "precision_at_1": 0.00175, + "precision_at_3": 0.00358, + "precision_at_5": 0.00415, + "precision_at_10": 0.00387, + "precision_at_100": 0.00174, + "precision_at_1000": 0.0006 + } + ] + }, + "task_name": "TempReasonL1" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002/no_revision_available/TempReasonL2Fact.json b/results/text-embedding-ada-002/no_revision_available/TempReasonL2Fact.json new file mode 100644 index 000000000..113df46c1 --- /dev/null +++ b/results/text-embedding-ada-002/no_revision_available/TempReasonL2Fact.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "13758bcf978613b249d0de4d0840f57815122bdf", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.1993, + "ndcg_at_1": 0.08597, + "ndcg_at_3": 0.14448, + "ndcg_at_5": 0.16948, + "ndcg_at_10": 0.1993, + "ndcg_at_100": 0.26229, + "ndcg_at_1000": 0.29287, + "map_at_1": 0.08597, + "map_at_3": 0.12967, + "map_at_5": 0.14352, + "map_at_10": 0.15585, + "map_at_100": 0.16768, + "map_at_1000": 0.16873, + "recall_at_1": 0.08597, + "recall_at_3": 0.18751, + "recall_at_5": 0.24829, + "recall_at_10": 0.34037, + "recall_at_100": 0.64795, + "recall_at_1000": 0.89457, + "precision_at_1": 0.08597, + "precision_at_3": 0.0625, + "precision_at_5": 0.04966, + "precision_at_10": 0.03404, + "precision_at_100": 0.00648, + "precision_at_1000": 0.00089 + } + ] + }, + "task_name": "TempReasonL2Fact" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002/no_revision_available/TempReasonL2Pure.json b/results/text-embedding-ada-002/no_revision_available/TempReasonL2Pure.json new file mode 100644 index 000000000..c709524ce --- /dev/null +++ b/results/text-embedding-ada-002/no_revision_available/TempReasonL2Pure.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "27668949b97bfb178901e0cf047cbee805305dc1", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.026, + "ndcg_at_1": 0.00741, + "ndcg_at_3": 0.0152, + "ndcg_at_5": 0.0198, + "ndcg_at_10": 0.026, + "ndcg_at_100": 0.0611, + "ndcg_at_1000": 0.10696, + "map_at_1": 0.00741, + "map_at_3": 0.01328, + "map_at_5": 0.0158, + "map_at_10": 0.01838, + "map_at_100": 0.02377, + "map_at_1000": 0.02519, + "recall_at_1": 0.00741, + "recall_at_3": 0.02075, + "recall_at_5": 0.03205, + "recall_at_10": 0.05114, + "recall_at_100": 0.23698, + "recall_at_1000": 0.61627, + "precision_at_1": 0.00741, + "precision_at_3": 0.00692, + "precision_at_5": 0.00641, + "precision_at_10": 0.00511, + "precision_at_100": 0.00237, + "precision_at_1000": 0.00062 + } + ] + }, + "task_name": "TempReasonL2Pure" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002/no_revision_available/TempReasonL3Fact.json b/results/text-embedding-ada-002/no_revision_available/TempReasonL3Fact.json new file mode 100644 index 000000000..15e357985 --- /dev/null +++ b/results/text-embedding-ada-002/no_revision_available/TempReasonL3Fact.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "4b70e90197901da24f3cfcd51d27111292878680", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.18021, + "ndcg_at_1": 0.05355, + "ndcg_at_3": 0.11703, + "ndcg_at_5": 0.1477, + "ndcg_at_10": 0.18021, + "ndcg_at_100": 0.24167, + "ndcg_at_1000": 0.27338, + "map_at_1": 0.05355, + "map_at_3": 0.10107, + "map_at_5": 0.11807, + "map_at_10": 0.13143, + "map_at_100": 0.14309, + "map_at_1000": 0.14419, + "recall_at_1": 0.05355, + "recall_at_3": 0.16335, + "recall_at_5": 0.23791, + "recall_at_10": 0.33868, + "recall_at_100": 0.63714, + "recall_at_1000": 0.89245, + "precision_at_1": 0.05355, + "precision_at_3": 0.05445, + "precision_at_5": 0.04758, + "precision_at_10": 0.03387, + "precision_at_100": 0.00637, + "precision_at_1000": 0.00089 + } + ] + }, + "task_name": "TempReasonL3Fact" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002/no_revision_available/TempReasonL3Pure.json b/results/text-embedding-ada-002/no_revision_available/TempReasonL3Pure.json new file mode 100644 index 000000000..2b1857068 --- /dev/null +++ b/results/text-embedding-ada-002/no_revision_available/TempReasonL3Pure.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "68fba138e7e63daccecfbdad0a9d2714e56e34ff", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.07578, + "ndcg_at_1": 0.00633, + "ndcg_at_3": 0.03589, + "ndcg_at_5": 0.05427, + "ndcg_at_10": 0.07578, + "ndcg_at_100": 0.12469, + "ndcg_at_1000": 0.16697, + "map_at_1": 0.00633, + "map_at_3": 0.0282, + "map_at_5": 0.03833, + "map_at_10": 0.04718, + "map_at_100": 0.05594, + "map_at_1000": 0.05731, + "recall_at_1": 0.00633, + "recall_at_3": 0.05829, + "recall_at_5": 0.10325, + "recall_at_10": 0.16991, + "recall_at_100": 0.41392, + "recall_at_1000": 0.75915, + "precision_at_1": 0.00633, + "precision_at_3": 0.01943, + "precision_at_5": 0.02065, + "precision_at_10": 0.01699, + "precision_at_100": 0.00414, + "precision_at_1000": 0.00076 + } + ] + }, + "task_name": "TempReasonL3Pure" +} \ No newline at end of file diff --git a/results/text-embedding-ada-002/no_revision_available/WinoGrande.json b/results/text-embedding-ada-002/no_revision_available/WinoGrande.json new file mode 100644 index 000000000..0a1cd1a9e --- /dev/null +++ b/results/text-embedding-ada-002/no_revision_available/WinoGrande.json @@ -0,0 +1,42 @@ +{ + "dataset_revision": "f74c094f321077cf909ddfb8bccc1b5912a4ac28", + "evaluation_time": 0.0, + "kg_co2_emissions": null, + "mteb_version": "1.12.27", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.19654, + "ndcg_at_1": 0.08524, + "ndcg_at_3": 0.14132, + "ndcg_at_5": 0.15932, + "ndcg_at_10": 0.19654, + "ndcg_at_100": 0.2761, + "ndcg_at_1000": 0.30345, + "map_at_1": 0.08524, + "map_at_3": 0.1272, + "map_at_5": 0.13707, + "map_at_10": 0.15241, + "map_at_100": 0.16746, + "map_at_1000": 0.16842, + "recall_at_1": 0.08524, + "recall_at_3": 0.18232, + "recall_at_5": 0.22652, + "recall_at_10": 0.34175, + "recall_at_100": 0.7277, + "recall_at_1000": 0.94633, + "precision_at_1": 0.08524, + "precision_at_3": 0.06077, + "precision_at_5": 0.0453, + "precision_at_10": 0.03418, + "precision_at_100": 0.00728, + "precision_at_1000": 0.00095 + } + ] + }, + "task_name": "WinoGrande" +} \ No newline at end of file