Do not force set beta to 0 for DAPO

[Datta0]

Addresses #3596
Sample output with/without UNSLOTH_ENABLE_LOGGING

Unsloth: The DAPO paper recommends `mask_truncated_completions = True` - we will set it.
Unsloth: The DAPO paper recommends `epsilon_high = 0.28` - we will set it.
[WARNING] Unsloth: The DAPO paper recommends setting `beta = 0.0` to remove the KL term - You have set it to 0.7.

[gemini-code-assist]

Summary of Changes

Hello @Datta0, 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 handling of the beta parameter within the DAPO (DPO with Adaptive Policy Optimization) implementation. Previously, the system would automatically adjust beta to 0.0 based on a paper's recommendation. This change removes that automatic override, allowing users to explicitly control the beta value. To ensure users are aware of best practices, a warning message is now displayed if beta is set to a value other than 0.0, providing guidance without enforcing the change.

Highlights

• Parameter Control: The system no longer automatically forces the beta parameter to 0.0 when using DAPO, giving users more control over this setting.
• User Notification: Instead of silently overriding the beta value, a warning is now issued if beta is set to a non-zero value, reminding the user of the DAPO paper's recommendation to set it to 0.0 to remove the KL term.

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]

Code Review

This pull request correctly modifies the behavior for DAPO training by no longer forcing the beta parameter to 0.0. Instead, it now issues a warning if the user-provided beta value is not the recommended 0.0, while still allowing the user's value. This provides greater flexibility for experimentation. The change is implemented correctly within the existing code patching mechanism and is consistent with the pull request's stated goal.