Training Gemma-3 for Structured Mathematical Reasoning with Tunix GRPO, LoRA Adapters, and GSM8K Rewards

In this tutorial, we build an end-to-end GRPO training workflow that teaches Gemma-3 to reason through GSM8K math problems using Tunix, JAX, LoRA, and custom reward functions. We start by preparing the environment, authenticating with Hugging Face, loading the Gemma-3 model, and wrapping GSM8K examples into a prompt format that requires both structured reasoning and a final numeric answer. We then define reward functions that assess format adherence and mathematical correctness, attach LoRA adapters to keep training lightweight, evaluate the baseline model, and run GRPO to improve the policy via group-sampled generations. It provides a reinforcement learning tutorial in which we train only the adapter weights while keeping the workflow compact enough for a single-accelerator setup. Installing Tunix and Configuring GRPO Training Copy CodeCopiedUse a different Browserimport importlib. util, os, shutil as _sh if importlib. find_spec("tunix") is None: print("Installing Tunix + JAX ecosystem — this takes ~5-8 min。 ") %pip install -q ipywidgets tensorboardX transformers grain nest_asyncio %pip install -q datasets huggingface_hub "numpy>2" %pip install -q tensorflow tensorflow_datasets %pip install -q git+https://github. com/jax-ml/jax %pip install -q git+https://github.