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

Reward modeling support #836

Merged
merged 7 commits into from
May 27, 2024
Merged

Reward modeling support #836

merged 7 commits into from
May 27, 2024

Conversation

wheresmyhair
Copy link
Collaborator

@wheresmyhair wheresmyhair commented May 20, 2024 •
edited

[Ready for review]
Reward modeling support
Tested on:

  1. Full finetuning
    full

  2. LoRA
    lora

  3. LISA
    lisa

research4pan
research4pan approved these changes May 27, 2024
View reviewed changes
Copy link
Contributor

@research4pan research4pan left a comment

Choose a reason for hiding this comment

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

LGTM 👍 Reward modeling is important for RLHF such as DPO and RAFT, thanks for @wheresmyhair 's contribution!

@research4pan
Copy link
Contributor

research4pan commented May 27, 2024 •
edited

Several additional fixes in this PR:

  • Squash warnings for samplings exceeding maximum lengths during tokenization & grouping.
  • Remove --conversation_template disable

@research4pan research4pan merged commit 0c11ace into main May 27, 2024
3 checks passed
@wheresmyhair wheresmyhair deleted the yizhenjia-rm branch May 28, 2024 16:08
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@research4pan research4pan research4pan approved these changes

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

Successfully merging this pull request may close these issues.

None yet
2 participants
@wheresmyhair @research4pan