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

Moved old_per_token_logps acquisition from torch.inference_mode to torch.no_grad #7

Merged
merged 1 commit into from
Feb 27, 2025

Conversation

jamesbraza
Copy link

Resolving huggingface#2953

@jamesbraza jamesbraza added the enhancement New feature or request label Feb 27, 2025
@jamesbraza jamesbraza self-assigned this Feb 27, 2025
@jamesbraza jamesbraza merged commit f6ce392 into working-grpo-2025-02-27 Feb 27, 2025
1 of 4 checks passed
@jamesbraza jamesbraza deleted the no-grad-fix branch February 27, 2025 19:24
@sidnarayanan
Copy link
Collaborator

Curious why the TRL folks can't reproduce this - wonder if it's a distributed problem

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

Successfully merging this pull request may close these issues.

2 participants