Rename data scripts for examples and refine toolcall example readme

[garyzhang99]

Description

As the title says.

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]

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 primarily focuses on improving the project's structure and documentation. I've reorganized data preparation scripts by moving them into their corresponding example directories, ensuring better modularity and discoverability. Additionally, I've substantially enhanced the toolcall example's README, providing crucial insights into preventing reward hacking and offering practical guidance for users.

Highlights

• Script Reorganization: I've moved several data preparation scripts (e.g., get_alfworld_data.py, get_sciworld_data.py, get_webshop_data.py) from the general scripts/data_prepare/ directory into their respective example directories under examples/grpo_*/. This improves the locality and organization of example-specific data utilities.
• Path Updates: Following the script reorganization, I've updated all relevant references to these scripts and their generated data paths across documentation (docs/sphinx_doc/source/tutorial/example_multi_turn.md), configuration files (.yaml files within examples/grpo_*/), and internal code comments (trinity/common/workflows/envs/alfworld/alfworld_workflow.py) to reflect their new locations.
• Toolcall Example Documentation Enhancement: I've significantly refined the examples/grpo_toolcall/README.md. This includes updating the data preprocessing command and adding a comprehensive new section on 'Preventing reward hacking' in the ToolAce workflow. This section explains the issue, provides code snippets for the proposed compute_score_v0 function modifications, and includes new images illustrating reward and response length curves. I also added instructions for inspecting model outputs via sqlite3.

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

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 renames and moves data preparation scripts to be co-located with their respective examples, updating references in documentation and configs. The README for grpo_toolcall is enhanced with a detailed explanation of a reward hacking issue and its solution. The review focuses on improving code quality in the data preparation scripts by suggesting best practices for path construction and enhancing the clarity and correctness of the new documentation.