Skip to content

Add DPO training support <- created by AI agent #329

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
Draft
wants to merge 5 commits into
base: main
Choose a base branch
from
Draft

Add DPO training support <- created by AI agent #329

wants to merge 5 commits into from

Conversation

jialei777
Copy link
Collaborator

Summary

  • implement DPO dataset and trainer
  • register new DPO components in maps
  • provide configs for running llama-3-8b DPO
  • update e2e workflow and benchmarks
  • add unit tests for dataset and trainer
  • add comments and docstrings for DPO code

Testing

  • ruff format
  • ruff check . --fix
  • pytest -q (fails: ModuleNotFoundError: No module named 'torch')

https://chatgpt.com/codex/tasks/task_e_685c358f3274832cb4dc847359814dba

@jialei777 jialei777 marked this pull request as draft June 25, 2025 18:51
@jialei777 jialei777 changed the title Add DPO training support Add DPO training support <- created by AI agent Jun 25, 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
codex
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@jialei777