Skip to content
/ sdft Public

[ACL 2024] The official codebase for the paper "Self-Distillation Bridges Distribution Gap in Language Model Fine-tuning".

Notifications You must be signed in to change notification settings

sail-sg/sdft

Repository files navigation

Implementation for Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning

Here is the code for our work Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning.

Update

Introduction

Fine-tuning LLMs for downstream tasks frequently leads to catastrophic forgetting, negatively affecting models' perfromance on other tasks and alignment. To address the problem, we introduce Self-Distillation Fine-Tuning (SDFT), a novel approach that bridges the distribution gap by guiding fine-tuning with a distilled dataset generated by the model itself to match its original distribution. The workflow of SDFT is shown in the following figure:

Workflow if SDFT

To ensure the quality of distilled responses, we employ simple heuristics. For responses that are not qualified, we preserve original response.

This selection process is implementd in eval/gen_distilled_data.py. Initially, we exclude responses containing specific words, which typically signify irrelevant repetitions rather than meaningful replies. Subsequently, for datasets pertaining to downstream tasks, we isolate the final answer and remove any that are inconsistent.

To facilitate the self-distillation process, a minor modification was implemented in the source code of LLaMA-Factory, as detailed in this commit.

Setup

Clone the repo with submodules:

git clone --recurse-submodules https://github.com/sail-sg/sdft.git

Install all dependencies via:

pip install -r requirements.txt
pip install -e LLaMA-Factory
pip install -e bigcode-evaluation-harness

Our experiments are based on Llama-2-chat-7b-hf model, so it is necessary to obtain the appropriate grant.

Usage

All required bash scripts for replicating the experimental results are located in the scripts directory. Prior to execution, ensure that the model_path argument is accurately configured. This argument denotes the identifier on Hugging Face or the local path containing the weights of the language model intended for fine-tuning.

To evaluate the seed language model, execute the following command: bash scripts/test_seed_LM.sh

For vanilla fine-tuning on a specific task dataset, use: bash scripts/[dataset]/sft.sh

For instance, to fine-tune on the Alpaca dataset, the command is: bash scripts/alpaca/sft.sh

Similarly, to perform Self-Distillation Fine (SDFT), the corresponding command is: bash scripts/[dataset]/sdft.sh

The main branch has been subjected to refactoring, potentially introducing minor discrepancies. For precise replication of the results presented in the paper, it is recommended to utilize the reproduce branch. Results of a latest run on reproduce branch can be found here.

⚠️ Employing multiple GPU cards for inference can result in garbled output; thus, we recommend the utilization of a single card.

Structure

The data directory houses the datasets utilized for fine-tuning and evaluation. After SDFT, corresponding distilled dataset will be created, denoted by a filename beginning with distilled.

The eval directory encompasses Python files that are used for evaluation purposes.

The checkpoints directory stores the LoRA checkpoints, which are generated subsequent to the fine-tuning process.

Within the predictions directory, one can find the outputs generated for each benchmark following the evaluation phase.

Lastly, the results directory contains logs of the evaluation results.

Acknowledgement

Our implementation is based on LLaMA-Factory, for which we are thankful for the exceptional work. For evaluation purposes, we employ tools including AlpacaEval, lm-evaluation-harness, and bigcode-evaluation-harness. Both AlpacaEval and lm-evaluation-harness are included as dependencies in requirements.txt, while LLaMA-Factory and bigcode-evaluation-harness have been integrated as a Git submodule.

To facilitate the self-distillation process, we created a fork of LLaMA-Factory at this repository, incorporating a modification to a single line of code.

Citation

If you find our paper or codebase helpful, consider citing us via:

@inproceedings{yang-etal-2024-self,
    title = "Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning",
    author = "Yang, Zhaorui  and
      Pang, Tianyu  and
      Feng, Haozhe  and
      Wang, Han  and
      Chen, Wei  and
      Zhu, Minfeng  and
      Liu, Qian",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.acl-long.58",
    pages = "1028--1043",
}

Star History

Star History Chart

About

[ACL 2024] The official codebase for the paper "Self-Distillation Bridges Distribution Gap in Language Model Fine-tuning".

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published