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.

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

Fix DPO unit test fail and refactor #554

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Fix DPO unit test fail and refactor #554

wants to merge 3 commits into from

Conversation

Tcc0403
Copy link
Collaborator

@Tcc0403 Tcc0403 commented Feb 1, 2025 •
edited
Loading

Summary

#521 introduced a unit test failure caused by the numerical issue in bf16.

This PR relaxes the atol for chosen_rewards and rejected_rewards only.
Note: It's just a temporary fix for ci.

This PR also removes duplicated calculations on both terms.

Testing Done

  • Hardware Type:
  • run make test to ensure correctness
  • run make checkstyle to ensure code style
  • run make test-convergence to ensure convergence

@kashif
Copy link
Contributor

kashif commented Feb 2, 2025

thanks @Tcc0403

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@austin362667 austin362667 Awaiting requested review from austin362667

@shivam15s shivam15s Awaiting requested review from shivam15s

At least 1 approving review is required to merge this pull request.

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@Tcc0403 @kashif