Skip to content

GSPO parameters update from v2 #3798

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

Merged
merged 6 commits into from
Jul 31, 2025
Merged

Conversation

BounharAbdelaziz
Copy link
Contributor

What does this PR do?

This PR updates thetraining_args of GSPO in docs/source/paper_index.md to align with the hyperparameters described in the GSPO v2 paper and documented in trl/trainer/grpo_config.py.

Before submitting

  • [ x] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • [x ] Did you read the contributor guideline,
    Pull Request section?
  • Was this discussed/approved via a GitHub issue? Please add a link
    to it if that's the case.
  • Did you make sure to update the documentation with your changes?
  • Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@qgallouedec

beta=0.0, # GSPO set kl regularization to zero: https://github.com/volcengine/verl/pull/2775#issuecomment-3131807306
epsilon=3e-4, # GSPO paper (v2), section 5.1
epsilon_high=4e-4, # GSPO paper (v2), section 5.1
gradient_accumulation_steps=4, # partition rollout batch into 4 mini-batches. GSPO paper (v2), section 5.1
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
gradient_accumulation_steps=4, # partition rollout batch into 4 mini-batches. GSPO paper (v2), section 5.1
steps_per_generation=4, # partition rollout batch into 4 mini-batches. GSPO paper (v2), section 5.1

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can you also add somewhere that this value steps_per_generation should be 4x gradient_accumulation_steps

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

you are right! done. thanks.

@qgallouedec
Copy link
Member

Oops, I missed yours, closing #3802 thanks!

@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

Copy link
Collaborator

@LeonEricsson LeonEricsson left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@qgallouedec qgallouedec merged commit 79c5797 into huggingface:main Jul 31, 2025
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

Successfully merging this pull request may close these issues.

4 participants