[DPO] average_log_prob when loss is IPO#1265
Merged
kashif merged 2 commits intohuggingface:mainfrom Jan 24, 2024
Merged
Conversation
|
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. |
edbeeching
approved these changes
Jan 24, 2024
Collaborator
edbeeching
left a comment
edbeeching
left a comment
There was a problem hiding this comment.
Thanks for the fix. LGTM!
Closed
lapp0
pushed a commit
to lapp0/trl
that referenced
this pull request
May 10, 2024
* average_log_prob when loss is IPO * updated docs with the fix
yxliu-TAMU
pushed a commit
to mincheolseong/ECEN743-GRPO-Project-Proposal
that referenced
this pull request
Apr 20, 2025
* average_log_prob when loss is IPO * updated docs with the fix
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
so that the beta is not dependent on the sequence length with IPO