Skip to content

Fix sft warmup yaml #435

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
Merged
pan-x-c merged 2 commits into from
Dec 11, 2025
Merged

Fix sft warmup yaml #435

pan-x-c merged 2 commits into from
Dec 11, 2025

Conversation

@hiyuchang
Copy link
Collaborator

@hiyuchang hiyuchang commented Dec 11, 2025

Description

[Please describe the background, purpose, changes made, and how to test this PR]

Checklist

Please check the following items before code is ready to be reviewed.

  • Code has passed all tests
  • Docstrings have been added/updated in Google Style
  • Documentation has been updated
  • Code is ready for review

@gemini-code-assist
Copy link
Contributor

gemini-code-assist bot commented Dec 11, 2025

Summary of Changes

Hello @hiyuchang, 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 refines the configuration for SFT (Supervised Fine-Tuning) warmup and related training parameters within benchmark templates. It adjusts sampling strategies and loss aggregation modes to align with updated defaults. Furthermore, it enhances documentation by clarifying the release status of a specific SFT dataset and provides clearer, commented-out examples for integrating SFT warmup into existing training pipelines.

Highlights

  • Configuration Updates: The sample_strategy in alfworld-template.yaml and gsm8k-template.yaml has been changed from warmup to default. Additionally, loss_agg_mode in alfworld-template.yaml was updated from seq-mean-token-sum to token-mean.
  • Documentation Clarification: The alfworld.md report was updated to clarify that the SFT dataset mentioned will be released soon.
  • SFT Warmup Examples: Commented-out sections demonstrating how to enable SFT warmup before RFT stages have been added to alfworld.yaml and gsm8k.yaml example configurations, including a fix for the storage_type in gsm8k.yaml.
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. ↩

gemini-code-assist[bot]
gemini-code-assist bot reviewed Dec 11, 2025
View reviewed changes
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

This pull request correctly updates configuration files to replace the deprecated warmup sample strategy with default. It also introduces commented-out examples for SFT warmup stages in alfworld.yaml and gsm8k.yaml. While these changes are a good step, I've identified a couple of areas for improvement in the example configurations to enhance their clarity and ensure they are complete and functional for users who choose to enable them.

@pan-x-c pan-x-c merged commit 0a72680 into modelscope:main Dec 11, 2025
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@pan-x-c pan-x-c pan-x-c approved these changes

+1 more reviewer

@gemini-code-assist gemini-code-assist[bot] gemini-code-assist[bot] left review comments

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@hiyuchang @pan-x-c