Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Completion mask fix #4140

Open
pluesclues wants to merge 2 commits intounslothai:mainfrom
pluesclues:completion_mask_fix
Open

Completion mask fix #4140
pluesclues wants to merge 2 commits intounslothai:mainfrom
pluesclues:completion_mask_fix

Conversation

@pluesclues
Copy link
Collaborator

@pluesclues pluesclues commented Mar 2, 2026

Should fix this issue: #4081 essentially we changed the completion mask the compute loss function and change its length relative to the logprob tensors. Relies on: unslothai/unsloth-zoo#528.

@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello, 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 resolves a critical issue in the reinforcement learning loss computation by ensuring the completion mask is properly returned and utilized. The fix specifically adjusts how the completion mask is unpacked from helper functions, aligning its length with logprob tensors and preventing incorrect loss calculations.

Highlights

  • Completion Mask Handling: The compute_loss function in rl_replacements.py has been updated to correctly handle the completion_mask. This involves modifying the unpacking of return values from grpo_compute_loss_slow and grpo_accumulated_loss to include the completion_mask.
  • Bug Fix: This change addresses a reported issue ([Bug] The size of tensor a (828) must match the size of tensor b (824) at non-singleton dimension 1 #4081) where the completion mask's length was incorrect relative to logprob tensors during loss computation.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The 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 /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

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 .gemini/ folder in the base of the repository. Detailed instructions can be found here.

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

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

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

Code Review

The pull request addresses issue #4081 by modifying the compute_loss function to correctly capture the completion_mask returned by grpo_compute_loss_slow and grpo_accumulated_loss. This change ensures that the updated completion_mask, whose length is adjusted relative to the logprob tensors, is used in subsequent calculations within compute_loss. The modification is consistently applied across all relevant calls to these loss computation functions.

flat_is_ratio,
coef_1,
completion_mask,
) = grpo_compute_loss_slow(
Copy link
Collaborator

@Datta0 Datta0 Mar 3, 2026

Choose a reason for hiding this comment

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

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants