Request for TOPR Training Examples or Configs on GSM8k/MATH

First of all, thank you very much for your great work. I would like to experiment with training LLMs using TOPR on datasets like GSM8k or MATH. May I ask if you could provide any runnable examples or YAML configuration files for such a setup, similar to those available in the [verl](https://github.com/volcengine/verl/tree/main/examples) repository? Any guidance would be greatly appreciated!

Start by reviewing the repository's TOPR training entry points and compare them with the linked verl examples for GSM8k and MATH. Done means providing a runnable training example or YAML configuration for at least one of those datasets, with enough guidance to run it.

Written by the indexing model from the issue text.