Add sft example #138
Add sft example #138
Conversation
There was a problem hiding this comment.
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 significantly enhances the project's examples by introducing a dedicated Supervised Fine-Tuning (SFT) example. It provides all the necessary configuration files and documentation updates to guide users on how to perform SFT, specifically utilizing the Mixture-of-Thoughts dataset. The primary goal is to offer a robust and easily reproducible SFT use case.
Highlights
- New SFT Example: I've added a complete example for Supervised Fine-Tuning (SFT) specifically tailored for the Mixture-of-Thoughts dataset. This provides a clear, runnable demonstration of SFT within the project.
- Configuration Files: This PR introduces two new YAML configuration files:
sft.yamlfor the main SFT training parameters (including dataset specification and model settings) andtrain_sft.yamlfor detailed trainer-specific configurations, such as FSDP settings and optimization parameters. - Documentation Updates: The existing documentation (
example_dpo.md) has been updated to correctly reference the new SFT example's configuration file path and provide the correct command for running the SFT process. - Example Readme: A new
README.mdhas been added within theexamples/sft_motdirectory to provide an overview of this specific SFT example, its purpose, and pointers to its configuration files and relevant documentation.
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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.
| 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 issue 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 or fill out our survey to provide feedback.
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
-
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. ↩
|
/unittest-module-common |
There was a problem hiding this comment.
Code Review
This pull request introduces a new example for Supervised Fine-Tuning (SFT), including configuration files and updated documentation. The changes are a valuable addition. My review focuses on improving the clarity, usability, and correctness of the new configuration files. I've suggested adding instructional comments for placeholder paths, aligning configuration parameters to prevent unexpected runtime behavior, and cleaning up the training config for better readability.
|
/unittest-module-common |
Summary
Tests
Github Test Reporter by CTRF 💚 |
Description
As the title says.
Checklist
Please check the following items before code is ready to be reviewed.