The N Implementation Details of RLHF with PPO
RLHF / ChatGPT has been a popular research topic these days. In our quest to research more on RLHF, this blog post attempts to do a reproduction of OpenAI’s 2019 original RLHF codebase at openai/lm-human-preferences. Despite its “tensorflow-1.x-ness,” OpenAI’s original codebase is very well-evaluated and benchmarked, making it a good place to study RLHF implementation engineering details. We aim to: This work is just for educational / learning purposes. For advanced users requiring more features, such as running larger models with PEFT, huggingface/trl would be a great choice. Here are the important links: Our main contribution is to reproduce OAI’s results in stylistic tasks, such as sentiment and descriptiveness. As shown in the figure below, our codebase (orange curves) can produce nearly identical learning curves as OAI’s codebase (blue curves). To make a direct comparison, we ran the original RLHF code at openai/lm-human-preferences, which will offer valuable metrics to help valid
RLHF / ChatGPT has been a popular research topic these days. In our quest to research more on RLHF, this blog post attempts to do a reproduction of OpenAI’s 2019 original RLHF codebase at openai/lm-human-preferences. Despite its “tensorflow-1.x-ness,” OpenAI’s original codebase is very well-evaluated and benchmarked, making it a good place to study RLHF implementation engineering details. We aim to: reproduce OAI’s results in stylistic tasks and match the learning curves of openai/lm-human-preferences. present a checklist of implementation details, similar to the spirit of The 37…
related reading
- The N Implementation Details of RLHF with PPO | ICLR Blogposts 2024iclr-blogposts.github.io
- RLHF: Reinforcement Learning from Human Feedbackhuyenchip.com
- RLHF & Post-Training Course by Nathan Lambertrlhfbook.com
- A vision researcher’s guide to some RL stuff: PPO & GRPO - Yuge (Jimmy) Shiyugeten.github.io
- State of RL for reasoning LLMs | A. Weersaweers.de
- The 37 Implementation Details of Proximal Policy Optimization · The ICLR Blog Trackiclr-blog-track.github.io
- RLHF | John Lambertjohnwlambert.github.io
- rlhfbook.com/book.pdfrlhfbook.com
- GitHub - ash80/RLHF_in_notebooks: RLHF (Supervised fine-tuning, reward model, and PPO) step-by-step in 3 Jupyter notebooksgithub.com
- Introduction | RLHF and Post-Training Book by Nathan Lambertrlhfbook.com
- [2402.14740] Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMsarxiv.org
- Thoughts on the impact of RLHF research — LessWronglesswrong.com