From 153ac08aaa61c6a6834bddd19de9aec2e704f2b8 Mon Sep 17 00:00:00 2001 From: chinainfant <38291328+chinainfant@users.noreply.github.com> Date: Fri, 8 Dec 2023 15:40:11 +0800 Subject: [PATCH] Update README.md Modify the hyperlink path, change 'training' to 'dschat' --- applications/DeepSpeed-Chat/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/applications/DeepSpeed-Chat/README.md b/applications/DeepSpeed-Chat/README.md index ac9f3ab6a..1fbdbcc4d 100644 --- a/applications/DeepSpeed-Chat/README.md +++ b/applications/DeepSpeed-Chat/README.md @@ -251,9 +251,9 @@ bash training_scripts/opt/single_gpu/run_1.3b.sh ### 🐼 Adding and using your own datasets in DeepSpeed-Chat -In addition to the datasets used in our example scripts, you can also add and use your own datasets. To do so, first you need to add a new Class in [training/utils/data/raw_datasets.py](https://github.com/microsoft/DeepSpeedExamples/blob/master/applications/DeepSpeed-Chat/training/utils/data/raw_datasets.py) to define the format when using your data. You need to make sure to follow the APIs and format defined in the PromptRawDataset class to ensure a consistent data format that DeepSpeed-Chat relies on. You can look at the existing classes to learn how to do so. +In addition to the datasets used in our example scripts, you can also add and use your own datasets. To do so, first you need to add a new Class in [dschat/utils/data/raw_datasets.py](https://github.com/microsoft/DeepSpeedExamples/blob/master/applications/DeepSpeed-Chat/dschat/utils/data/raw_datasets.py) to define the format when using your data. You need to make sure to follow the APIs and format defined in the PromptRawDataset class to ensure a consistent data format that DeepSpeed-Chat relies on. You can look at the existing classes to learn how to do so. -Second, you need to add an if condition in function get_raw_dataset in [training/utils/data/data_utils.py](https://github.com/microsoft/DeepSpeedExamples/blob/master/applications/DeepSpeed-Chat/training/utils/data/data_utils.py) corresponding to your new dataset. The dataset_name string in the if condition should be the dataset name you will provide as a arg for the training scripts. Last, you need to add your new dataset's dataset_name into your "--data_path" arg in your training scripts. +Second, you need to add an if condition in function get_raw_dataset in [dschat/utils/data/data_utils.py](https://github.com/microsoft/DeepSpeedExamples/blob/master/applications/DeepSpeed-Chat/dschat/utils/data/data_utils.py) corresponding to your new dataset. The dataset_name string in the if condition should be the dataset name you will provide as a arg for the training scripts. Last, you need to add your new dataset's dataset_name into your "--data_path" arg in your training scripts. If you have downloaded huggingface datasets manually, you can add your local path into "--data_path", such as "--data_path ./relative/Dahoas/rm-static" and "--data_path /absolute/Dahoas/rm-static". Remember you should not make `data/` in your local path, it may cause an exception to `load_dataset`. One thing to note is that some datasets may only have one response instead of two responses. For those datasets, you can only use them in step 1. And in such case, you should add the dataset_name as part of the "--sft_only_data_path" arg instead of the "--data_path" arg. One thing to note is that: If you plan to only do step 1 SFT, adding more single-response datasets is definitely beneficial. However, if you do plan to do steps 2 and 3, then adding too many single-response datasets during SFT could backfire: these data could be different from the data used for steps 2/3, generating different distributions which could cause training instability/worse model quality during step 2/3. That is part of the reason why we focused on trying the datasets with two responses and the preference, and always split a dataset into all 3 steps.