Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

【Question】Does DPO trainer support with FSDP? #2500

Open
yingtongxiong opened this issue Dec 18, 2024 · 2 comments
Open

【Question】Does DPO trainer support with FSDP? #2500

yingtongxiong opened this issue Dec 18, 2024 · 2 comments

Comments

@yingtongxiong
Copy link

Hello, I'm wondering if the DPO trainer supports FSDP and, if so, how I can use it. I look forward to your reply.

@asparius
Copy link
Contributor

trl uses accelerate which supports FSDP. However there is no recommeded config of FSDP in the repo unlike DeepSpeed, so you could refer to this page for FSDP. All in all, DPO and trl supports FSDP but not for online algo like PPO #1726.

@yingtongxiong
Copy link
Author

trl uses accelerate which supports FSDP. However there is no recommeded config of FSDP in the repo unlike DeepSpeed, so you could refer to this page for FSDP. All in all, DPO and trl supports FSDP but not for online algo like PPO #1726.

@asparius Thank you very much

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants