Skip to content

Refactor and Improve ReinforceLoss implementation #583

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.

Sign up for GitHub

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

Jump to bottom
Open
wants to merge 7 commits into
base: main
Choose a base branch
from
Open

Refactor and Improve ReinforceLoss implementation #583

wants to merge 7 commits into from
+15 −21

Conversation

@bohdan-nd
Copy link

@bohdan-nd bohdan-nd commented Nov 17, 2025

Summary

Refactors ReinforceLoss to improve code clarity and correctness.

Specifically:

  • Renamed variables to follow standard RL terminology
  • Fixed normalization: normalize by sequence length instead of total batch tokens
  • Cleaned the code
  • Made importance sampling optional and moved configuration to the constructor
  • Reorder func parameters to match SimpleGRPOLoss

@meta-cla meta-cla bot added the CLA Signed This label is managed by the Meta Open Source bot. label Nov 17, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

CLA Signed This label is managed by the Meta Open Source bot.

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@bohdan-nd