<p>We build an end-to-end GRPO training workflow that teaches Gemma-3 to reason through GSM8K math problems. We prepare the environment, authenticate with Hugging Face, load Gemma-3, and wrap examples into a reasoning-plus-answer prompt format. We define reward functions for format adherence and numeric correctness, then attach LoRA adapters to keep training lightweight. We evaluate a baseline, run GRPO to improve the policy through group-sampled generations, and optionally export the merged mod