justrl-simple-recipe

【数据与研究】Demonstrate that simple single-stage RL with fixed hyperparameters matches complex multi-stage approaches for training small LLMs on mathematical reasoning. Use basic setup: GRPO algorithm, rule-based verification, 16K token context, standard training data without difficulty filtering. Train two 1.5B models to competitive performance using 2× less co…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准