Addresults

results/Alibaba-NLP__gte-Qwen2-7B-instruct/e26182b2122f4435e8b3ebecbf363990f409b45b/TopiOCQAHardNegatives.json

@@ -0,0 +1,158 @@
+{
+  "dataset_revision": "b4cc09fb8bb3a9e0ce0f94dc69c96397a2a47c18",
+  "evaluation_time": 1372.583566904068,
+  "kg_co2_emissions": 0.8386569017336079,
+  "mteb_version": "1.18.0",
+  "scores": {
+    "validation": [
+      {
+        "hf_subset": "default",
+        "languages": [
+          "eng-Latn"
+        ],
+        "main_score": 0.21379,
+        "map_at_1": 0.101,
+        "map_at_10": 0.16999,
+        "map_at_100": 0.18447,
+        "map_at_1000": 0.1857,
+        "map_at_20": 0.17815,
+        "map_at_3": 0.1445,
+        "map_at_5": 0.15685,
+        "mrr_at_1": 0.101,
+        "mrr_at_10": 0.16999285714285714,
+        "mrr_at_100": 0.1844746515014581,
+        "mrr_at_1000": 0.18570487360712473,
+        "mrr_at_20": 0.17815270115161763,
+        "mrr_at_3": 0.1444999999999999,
+        "mrr_at_5": 0.15684999999999996,
+        "nauc_map_at_1000_diff1": 0.13945748323445184,
+        "nauc_map_at_1000_max": 0.180274903790705,
+        "nauc_map_at_1000_std": 0.06709372815594669,
+        "nauc_map_at_100_diff1": 0.13919785917177155,
+        "nauc_map_at_100_max": 0.18042107824349934,
+        "nauc_map_at_100_std": 0.06717059926787362,
+        "nauc_map_at_10_diff1": 0.14261175175203336,
+        "nauc_map_at_10_max": 0.17927760124979583,
+        "nauc_map_at_10_std": 0.06629638707545342,
+        "nauc_map_at_1_diff1": 0.15905716654183333,
+        "nauc_map_at_1_max": 0.2242468020908022,
+        "nauc_map_at_1_std": 0.09479778338713164,
+        "nauc_map_at_20_diff1": 0.139220636105314,
+        "nauc_map_at_20_max": 0.17848699783493913,
+        "nauc_map_at_20_std": 0.06518309842275453,
+        "nauc_map_at_3_diff1": 0.13727914503491365,
+        "nauc_map_at_3_max": 0.18229014733987836,
+        "nauc_map_at_3_std": 0.07237713804423689,
+        "nauc_map_at_5_diff1": 0.13722921086137477,
+        "nauc_map_at_5_max": 0.17343924186979326,
+        "nauc_map_at_5_std": 0.06662998675824422,
+        "nauc_mrr_at_1000_diff1": 0.13945748323445184,
+        "nauc_mrr_at_1000_max": 0.180274903790705,
+        "nauc_mrr_at_1000_std": 0.06709372815594669,
+        "nauc_mrr_at_100_diff1": 0.13919785917177155,
+        "nauc_mrr_at_100_max": 0.18042107824349934,
+        "nauc_mrr_at_100_std": 0.06717059926787362,
+        "nauc_mrr_at_10_diff1": 0.14261175175203336,
+        "nauc_mrr_at_10_max": 0.17927760124979583,
+        "nauc_mrr_at_10_std": 0.06629638707545342,
+        "nauc_mrr_at_1_diff1": 0.15905716654183333,
+        "nauc_mrr_at_1_max": 0.2242468020908022,
+        "nauc_mrr_at_1_std": 0.09479778338713164,
+        "nauc_mrr_at_20_diff1": 0.139220636105314,
+        "nauc_mrr_at_20_max": 0.17848699783493913,
+        "nauc_mrr_at_20_std": 0.06518309842275453,
+        "nauc_mrr_at_3_diff1": 0.13727914503491365,
+        "nauc_mrr_at_3_max": 0.18229014733987836,
+        "nauc_mrr_at_3_std": 0.07237713804423689,
+        "nauc_mrr_at_5_diff1": 0.13722921086137477,
+        "nauc_mrr_at_5_max": 0.17343924186979326,
+        "nauc_mrr_at_5_std": 0.06662998675824422,
+        "nauc_ndcg_at_1000_diff1": 0.13462695630731858,
+        "nauc_ndcg_at_1000_max": 0.17755443691247924,
+        "nauc_ndcg_at_1000_std": 0.06519254409553903,
+        "nauc_ndcg_at_100_diff1": 0.12945694978383163,
+        "nauc_ndcg_at_100_max": 0.18146541998404866,
+        "nauc_ndcg_at_100_std": 0.06437218294937233,
+        "nauc_ndcg_at_10_diff1": 0.14492910077258592,
+        "nauc_ndcg_at_10_max": 0.17155360648651682,
+        "nauc_ndcg_at_10_std": 0.056013456686342916,
+        "nauc_ndcg_at_1_diff1": 0.15905716654183333,
+        "nauc_ndcg_at_1_max": 0.2242468020908022,
+        "nauc_ndcg_at_1_std": 0.09479778338713164,
+        "nauc_ndcg_at_20_diff1": 0.13448532388570655,
+        "nauc_ndcg_at_20_max": 0.1687675913840615,
+        "nauc_ndcg_at_20_std": 0.05200988337607004,
+        "nauc_ndcg_at_3_diff1": 0.13268386072320917,
+        "nauc_ndcg_at_3_max": 0.17132134501845353,
+        "nauc_ndcg_at_3_std": 0.06657030830595347,
+        "nauc_ndcg_at_5_diff1": 0.13229564249040088,
+        "nauc_ndcg_at_5_max": 0.15705178443583584,
+        "nauc_ndcg_at_5_std": 0.0576524931823522,
+        "nauc_precision_at_1000_diff1": -0.07584994782226347,
+        "nauc_precision_at_1000_max": 0.23235568737298928,
+        "nauc_precision_at_1000_std": 0.34585598945459417,
+        "nauc_precision_at_100_diff1": 0.0789506575749579,
+        "nauc_precision_at_100_max": 0.21343758245726152,
+        "nauc_precision_at_100_std": 0.07469908679513332,
+        "nauc_precision_at_10_diff1": 0.1533995866069045,
+        "nauc_precision_at_10_max": 0.15985540439857587,
+        "nauc_precision_at_10_std": 0.03396892850244202,
+        "nauc_precision_at_1_diff1": 0.15905716654183333,
+        "nauc_precision_at_1_max": 0.2242468020908022,
+        "nauc_precision_at_1_std": 0.09479778338713164,
+        "nauc_precision_at_20_diff1": 0.12327729240061686,
+        "nauc_precision_at_20_max": 0.15111780475474534,
+        "nauc_precision_at_20_std": 0.02148096425427092,
+        "nauc_precision_at_3_diff1": 0.12252699360258856,
+        "nauc_precision_at_3_max": 0.14647466927409164,
+        "nauc_precision_at_3_std": 0.05342916048850624,
+        "nauc_precision_at_5_diff1": 0.12177288818501525,
+        "nauc_precision_at_5_max": 0.12089951556932252,
+        "nauc_precision_at_5_std": 0.037959685120059615,
+        "nauc_recall_at_1000_diff1": -0.07584994782226935,
+        "nauc_recall_at_1000_max": 0.23235568737298334,
+        "nauc_recall_at_1000_std": 0.34585598945460877,
+        "nauc_recall_at_100_diff1": 0.07895065757495787,
+        "nauc_recall_at_100_max": 0.21343758245726166,
+        "nauc_recall_at_100_std": 0.07469908679513311,
+        "nauc_recall_at_10_diff1": 0.15339958660690484,
+        "nauc_recall_at_10_max": 0.15985540439857632,
+        "nauc_recall_at_10_std": 0.033968928502442236,
+        "nauc_recall_at_1_diff1": 0.15905716654183333,
+        "nauc_recall_at_1_max": 0.2242468020908022,
+        "nauc_recall_at_1_std": 0.09479778338713164,
+        "nauc_recall_at_20_diff1": 0.12327729240061752,
+        "nauc_recall_at_20_max": 0.15111780475474582,
+        "nauc_recall_at_20_std": 0.02148096425427147,
+        "nauc_recall_at_3_diff1": 0.12252699360258854,
+        "nauc_recall_at_3_max": 0.1464746692740916,
+        "nauc_recall_at_3_std": 0.05342916048850615,
+        "nauc_recall_at_5_diff1": 0.12177288818501512,
+        "nauc_recall_at_5_max": 0.1208995155693223,
+        "nauc_recall_at_5_std": 0.037959685120059594,
+        "ndcg_at_1": 0.101,
+        "ndcg_at_10": 0.21379,
+        "ndcg_at_100": 0.29074,
+        "ndcg_at_1000": 0.32281,
+        "ndcg_at_20": 0.24325,
+        "ndcg_at_3": 0.15922,
+        "ndcg_at_5": 0.18147,
+        "precision_at_1": 0.101,
+        "precision_at_10": 0.0357,
+        "precision_at_100": 0.00733,
+        "precision_at_1000": 0.00098,
+        "precision_at_20": 0.02365,
+        "precision_at_3": 0.06733,
+        "precision_at_5": 0.0512,
+        "recall_at_1": 0.101,
+        "recall_at_10": 0.357,
+        "recall_at_100": 0.733,
+        "recall_at_1000": 0.983,
+        "recall_at_20": 0.473,
+        "recall_at_3": 0.202,
+        "recall_at_5": 0.256
+      }
+    ]
+  },
+  "task_name": "TopiOCQAHardNegatives"
+}

results/Alibaba-NLP__gte-Qwen2-7B-instruct/e26182b2122f4435e8b3ebecbf363990f409b45b/WebLINXCandidatesReranking.json

@@ -0,0 +1,111 @@
+{
+  "dataset_revision": "ed1c933c2b3617e5700d8a7ebe07f5975969a453",
+  "evaluation_time": 123372.13516354561,
+  "kg_co2_emissions": 11.952502877439517,
+  "mteb_version": "1.18.0",
+  "scores": {
+    "test_cat": [
+      {
+        "hf_subset": "default",
+        "languages": [
+          "eng-Latn"
+        ],
+        "main_score": 0.0976013242375602,
+        "map": 0.11237258520677565,
+        "mrr": 0.0976013242375602,
+        "nAUC_map_diff1": 0.07114335558335581,
+        "nAUC_map_max": 0.18797165030793325,
+        "nAUC_map_std": 0.23018588741459572,
+        "nAUC_mrr_diff1": 0.07350550589163288,
+        "nAUC_mrr_max": 0.17927106844326243,
+        "nAUC_mrr_std": 0.21017440831643888
+      }
+    ],
+    "test_geo": [
+      {
+        "hf_subset": "default",
+        "languages": [
+          "eng-Latn"
+        ],
+        "main_score": 0.11024537628992469,
+        "map": 0.1283388969478226,
+        "mrr": 0.11024537628992469,
+        "nAUC_map_diff1": 0.17659125476015666,
+        "nAUC_map_max": 0.22654802479325403,
+        "nAUC_map_std": 0.14965408976996084,
+        "nAUC_mrr_diff1": 0.1833294351348487,
+        "nAUC_mrr_max": 0.2317049762005828,
+        "nAUC_mrr_std": 0.142763903607862
+      }
+    ],
+    "test_iid": [
+      {
+        "hf_subset": "default",
+        "languages": [
+          "eng-Latn"
+        ],
+        "main_score": 0.14476400203103956,
+        "map": 0.16087191768124767,
+        "mrr": 0.14476400203103956,
+        "nAUC_map_diff1": 0.09435070066744501,
+        "nAUC_map_max": 0.051616909122828326,
+        "nAUC_map_std": 0.03766806115164064,
+        "nAUC_mrr_diff1": 0.09795722670339345,
+        "nAUC_mrr_max": 0.05111781870317291,
+        "nAUC_mrr_std": 0.02954647008403948
+      }
+    ],
+    "test_vis": [
+      {
+        "hf_subset": "default",
+        "languages": [
+          "eng-Latn"
+        ],
+        "main_score": 0.13416690634980558,
+        "map": 0.1506176662817587,
+        "mrr": 0.13416690634980558,
+        "nAUC_map_diff1": 0.14001473527710837,
+        "nAUC_map_max": 0.16101203617005808,
+        "nAUC_map_std": 0.1636794967931306,
+        "nAUC_mrr_diff1": 0.14382866878229997,
+        "nAUC_mrr_max": 0.15824416820535323,
+        "nAUC_mrr_std": 0.14705510573289177
+      }
+    ],
+    "test_web": [
+      {
+        "hf_subset": "default",
+        "languages": [
+          "eng-Latn"
+        ],
+        "main_score": 0.10753450765378245,
+        "map": 0.12185726408995741,
+        "mrr": 0.10753450765378245,
+        "nAUC_map_diff1": 0.1827597942661111,
+        "nAUC_map_max": 0.1319497088529989,
+        "nAUC_map_std": 0.1263163552354218,
+        "nAUC_mrr_diff1": 0.17856124712920643,
+        "nAUC_mrr_max": 0.12874239350387714,
+        "nAUC_mrr_std": 0.11293242307448244
+      }
+    ],
+    "validation": [
+      {
+        "hf_subset": "default",
+        "languages": [
+          "eng-Latn"
+        ],
+        "main_score": 0.15576845649866403,
+        "map": 0.17124390969492517,
+        "mrr": 0.15576845649866403,
+        "nAUC_map_diff1": 0.2281755967894526,
+        "nAUC_map_max": 0.15065079958122887,
+        "nAUC_map_std": 0.007141893298152778,
+        "nAUC_mrr_diff1": 0.2328616941037803,
+        "nAUC_mrr_max": 0.15260088516639617,
+        "nAUC_mrr_std": 0.007862536306838423
+      }
+    ]
+  },
+  "task_name": "WebLINXCandidatesReranking"
+}