fix cookbook

[tastelikefeet]

PR type

• Bug Fix
• New Feature
• Document Updates
• More Models or Datasets Support

PR information

Write the detail information belongs to this PR.

Experiment results

Paste your experiment result here(if needed).

[gemini-code-assist]

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 refines the cookbook examples and their accompanying documentation by simplifying the training configuration and updating key components. It removes a redundant Megatron-related flag, ensuring consistent application of the linear learning rate scheduler. Additionally, the optimizer is updated to AdamW, and model references and team names are refreshed across both English and Chinese documentation to align with current practices and model versions.

Highlights

• Megatron Configuration Streamlined: The use_megatron flag and its associated conditional logic for applying the linear learning rate scheduler have been removed from the example code and documentation. This simplifies the training setup, ensuring the linear LR scheduler is always active.
• Optimizer Updated to AdamW: The optimizer used in the training examples within both the Python script and the documentation has been updated from Adam to AdamW.
• Model and Documentation References Refreshed: The base model reference in the examples has been updated to Qwen/Qwen3.5-4B. Correspondingly, documentation titles and SelfCognitionProcessor arguments have been adjusted to reflect these changes and remove the '-4B' suffix from 'Qwen3.5' in titles.

🧠 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.

Changelog

• cookbook/client/twinkle/self_congnition.py
  • Removed the use_megatron variable and its conditional usage for the learning rate scheduler.
• docs/source_en/Usage Guide/Introduction-with-Qwen3.5.md
  • Updated the document title to 'Qwen3.5 Training Best Practices'.
  • Removed an unused os import statement.
  • Eliminated the use_megatron variable and its conditional logic for the learning rate scheduler.
  • Changed the optimizer from Adam to AdamW.
  • Updated the base_model reference and SelfCognitionProcessor arguments.
• docs/source_zh/使用指引/Qwen3.5最佳实践.md
  • Updated the document title to 'Qwen3.5 训练最佳实践'.
  • Removed an unused os import statement.
  • Eliminated the use_megatron variable and its conditional logic for the learning rate scheduler.
  • Changed the optimizer from Adam to AdamW.
  • Updated the base_model reference and SelfCognitionProcessor arguments.

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 refactors the cookbook examples by removing the use_megatron flag and its associated conditional logic. This simplifies the code, making the learning rate scheduler application unconditional. The documentation in both English and Chinese has been updated accordingly, also switching the example model to Qwen3.5-4B and the optimizer from Adam to the more modern AdamW. The changes are consistent and improve the clarity of the examples. I have one minor suggestion to update a comment that became misleading after the refactoring.