Add example of RL training with Axolotl

[andreaskoepf]

Axolotl v0.7.0 is has been released with support for GRPO. See tweet.

Wing shared this GSM-8K example: https://github.com/axolotl-ai-cloud/axolotl-cookbook/blob/main/grpo/gsm8k_grpo.py

The GRPO support in Axolotl is based on trl (afaik) but nevertheless it would be great to have a separate example because Axolotl is a popular training tool which integrates many different techniques (and makes them easily usable).