https://github.com/shaheennabi/rlvr_grpo-experiment-with-math500

A small experiment repository comparing a base reasoning model against RLVR-GRPO checkpoints on the Math500 dataset. It includes evaluation results, short-form observations, and a local temp_clone of the full open-posttraining-system codebase for reference.

evaluating-models grpo-checkpoint math500 open-posttraining-system policy-optimization post-training reasoning-models reinforcement-learning rlvr-grpo sparse-rewards

Last synced: 18 Jun 2026