Move RL code from src/MaxText/rl/ to src/maxtext/trainers/post_train/rl/

[A9isha]

Description

Migrate RL training code to the new package structure following the same pattern as the SFT (PR #2988) and distillation moves. Old location files are replaced with backward-compatibility shims that delegate to the new modules with deprecation warnings.

Tests

Locally ran RL using the following commands:

## new
python3 -m src.maxtext.trainers.post_train.rl.train_rl src/maxtext/configs/post_train/rl.yml   model_name=llama3.1-8b   t
okenizer_path=meta-llama/Llama-3.1-8B-Instruct   load_parameters_path=/path/to/checkpoint   run_name=maz-8b-$RANDOM   bas
e_output_directory=/path/to/storage   hf_access_token=<HF_TOKEN> dataset_name=gsm8k steps=4


## old
python3 -m src.MaxText.rl.train_rl src/maxtext/configs/post_train/rl.yml   model_name=llama3.1-8b   t
okenizer_path=meta-llama/Llama-3.1-8B-Instruct   load_parameters_path=/path/to/checkpoint   run_name=maz-8b-$RANDOM   bas
e_output_directory=/path/to/storage   hf_access_token=<HF_TOKEN> dataset_name=gsm8k steps=4

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

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

[bvandermoon]

For the manual tests you ran, could you also try with the old commands? Not as critical as the train.py shims since RL is a newer feature, but still good to test them since they are added here

[A9isha]

Done testing with the old command and updated the description - thanks @bvandermoon

[bvandermoon]

Done testing with the old command and updated the description - thanks @bvandermoon

Thanks @A9isha. Just to double check, can you confirm you saw all logs as expected with the old command? For train.py, I needed to set logging.set_verbosity(logging.INFO) to see the standard completed step output logged