Refactor rl_train and add unit test for prompt filtering

[igorts-git]

Description

Split the rl_train() function to extract the dataset construction logic into a separate function.
Add unit tests to the long sequence filtering logic.

FIXES: b/490410764

Tests

Added unit tests to the new logic.
CI.

Checklist

Before submitting this PR, please make sure (put X in square brackets):

• I have performed a self-review of my code. For an optional AI review, add the gemini-review label.
• I have necessary comments in my code, particularly in hard-to-understand areas.
• I have run end-to-end tests tests and provided workload links above if applicable.
• I have made or will make corresponding changes to the doc if needed, including adding new documentation pages to the relevant Table of Contents (toctree directive) as explained in our documentation.

[codecov]

Codecov Report

❌ Patch coverage is 12.50000% with 21 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
src/maxtext/trainers/post_train/rl/train_rl.py	12.50%	21 Missing ⚠️

📢 Thoughts on this report? Let us know!