Fix problem in math_mix config #196
Conversation
There was a problem hiding this comment.
Summary of Changes
Hello @garyzhang99, 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 addresses a minor configuration issue within the mix_math.yaml file. The changes involve removing an unnecessary parameter from the algorithm configuration and adjusting the number of training epochs for both the main buffer and the SFT warmup dataset. These adjustments aim to correct the configuration and potentially improve the training process.
Highlights
- Algorithm Configuration Adjustment: The
repeat_timesparameter has been removed from thealgorithmsection, streamlining the configuration. - Training Epochs Update: The
total_epochssetting for the main buffer has been increased from 1 to 10, likely to allow for more extensive training. - SFT Warmup Dataset Epochs: The
sft_warmup_datasetconfiguration now explicitly setstotal_epochsto 10, aligning its training duration with the main buffer.
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. 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
-
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. ↩
There was a problem hiding this comment.
Code Review
This pull request fixes a configuration issue in the mix_math example. It correctly removes an invalid repeat_times parameter from policy_loss_fn_args and adjusts the number of training epochs. A key change is adding a total_epochs setting specifically for the SFT warmup dataset.
My review focuses on this new total_epochs parameter. While it may be functionally necessary, it introduces potential redundancy with the top-level buffer.total_epochs and creates an inconsistency with the configuration generator UI, which could lead to issues for other users. I have provided a comment suggesting an update to the config generator to maintain consistency.
|
/unittest-module-common |
Summary
Tests
Github Test Reporter by CTRF 💚 |
Description
As the title says.
Minor fix in math mix config.
Checklist
Please check the following items before code is ready to be reviewed.