|
--- |
|
library_name: transformers |
|
tags: [] |
|
--- |
|
|
|
This is the SFT checkpoint used for the project [RLHFlow/Online-RLHF](https://github.com/RLHFlow/Online-RLHF) |
|
|
|
* **Paper**: [RLHF Workflow: From Reward Modeling to Online RLHF](https://arxiv.org/pdf/2405.07863) (Published in TMLR, 2024) |
|
* **Authors**: Hanze Dong*, Wei Xiong*, Bo Pang*, Haoxiang Wang*, Han Zhao, Yingbo Zhou, Nan Jiang, Doyen Sahoo, Caiming Xiong, Tong Zhang |
|
* **Code**: https://github.com/RLHFlow/Online-RLHF |
|
|
|
The model is trained from [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on [RLHFlow/RLHFlow-SFT-Dataset-ver2](https://huggingface.co/datasets/RLHFlow/RLHFlow-SFT-Dataset-ver2) for 1 epoch. We use a global batch size of 128 and a learning rate of 2e-5, where we pack the samples and split them into chunks of 8192 token. See more training details at https://github.com/RLHFlow/Online-RLHF/blob/main/sft/llama3-8b-it.yaml . |
|
|
|
|
|
|
|
|
|
## Citation |
|
Please cite our techical report if you find our model is useful for your research or product. |
|
``` |
|
@misc{dong2024rlhf, |
|
title={RLHF Workflow: From Reward Modeling to Online RLHF}, |
|
author={Hanze Dong and Wei Xiong and Bo Pang and Haoxiang Wang and Han Zhao and Yingbo Zhou and Nan Jiang and Doyen Sahoo and Caiming Xiong and Tong Zhang}, |
|
year={2024}, |
|
eprint={2405.07863}, |
|
archivePrefix={arXiv}, |
|
primaryClass={cs.LG} |
|
} |
|
|
|
``` |