Add loss_agg_mode for kl and entropy_loss
#388
Merged
Conversation
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
Contributor
Summary of ChangesHello @pan-x-c, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly improves the robustness and configurability of loss calculations within the Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
Contributor
There was a problem hiding this comment.
Code Review
This pull request introduces a configurable loss_agg_mode for KL and entropy losses, allowing for more flexible loss aggregation strategies. It also adds a new low_var_kl KL-divergence calculation method for improved stability. The PPO loss function is enhanced with an additional clipping mechanism for negative advantages, a technique known to improve performance.
The changes are well-implemented across the codebase, with corresponding updates to configurations and tests. I've made a couple of minor suggestions to improve code clarity and maintainability, such as removing a redundant .contiguous() call and improving type safety in the configuration checking logic. Overall, this is a solid contribution that enhances the flexibility and robustness of the training algorithms.
Collaborator
Author
|
/unittest-module-algorithm |
Summary
Tests
Github Test Reporter by CTRF 💚 |
hiyuchang
reviewed
Nov 17, 2025
Collaborator
|
/unittest-all |
Summary
Failed Tests
Skipped
Tests
Github Test Reporter by CTRF 💚 |
Collaborator
Author
|
/unittest-all |
Summary
Skipped
Tests
Github Test Reporter by CTRF 💚 |
hiyuchang
approved these changes
Nov 19, 2025
This was referenced Nov 27, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.
Description
Align with verl 0.5.0
loss_agg_modefor kl and entropy_lossPPOPolicyLossmasked_sumChecklist
Please check the following items before code is ready to be reviewed.