[PPO] fix corner cases with PPO batch size and forward_batch_size#563
Merged
younesbelkada merged 3 commits intomainfrom Jul 28, 2023
Merged
[PPO] fix corner cases with PPO batch size and forward_batch_size#563younesbelkada merged 3 commits intomainfrom
PPO] fix corner cases with PPO batch size and forward_batch_size#563younesbelkada merged 3 commits intomainfrom
Conversation
|
The documentation is not available anymore as the PR was closed or merged. |
lvwerra
reviewed
Jul 25, 2023
lvwerra
approved these changes
Jul 28, 2023
yxliu-TAMU
pushed a commit
to mincheolseong/ECEN743-GRPO-Project-Proposal
that referenced
this pull request
Apr 20, 2025
…uggingface#563) * fix corner cases PPO * forward contrib credits from initial contribution * forward contrib credits from initial discussions --------- Co-authored-by: 1485840691-eng <1485840691-eng@users.noreply.github.com> Co-authored-by: shubhlohiya <shubhlohiya@users.noreply.github.com>
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
5 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes: #553
When users uses different combinations of batch size and forward batch size it might lead to breaking behaviours as explained on the attached issue.
This PR fixes it by adding the suggestion proposed by one of the user which is perfectly backward compatible
cc @lvwerra