## How GRPO Trains Small Language Models with Verifiable Rewards The mechanics behind local reasoning experiments with Unsloth and why the reward function matters as much as the model. A language model can write "let me double-check that" and still get the multiplication wrong. It can even write "wait, let me reconsider," and land on a different wrong answer. Neither sentence is evidence of thinking. If the goal is solving the problem, only the number at the end counts. DeepSeek’s R1-Zero brought considerable attention to reinforcement learning without a preliminary supervised fine-tuning…