Apr 25

1. 08:25

   feat: implement Unsloth GRPO training script with diverse reward functions and logging

   adityss
   d2449aa
2. 07:30

   fix: update training script with seed variation, fix reward normalization, regenerate training curves showing 0.52->0.67 improvement

   adityss
   bdc9954
3. 05:33

   fix: training reward uses 8-step rollout + /grade for genuine episode-level signal

   adityss
   c70e17d
4. 05:16

   feat: add baseline evaluation tools and demo scripts for RL performance comparison

   adityss
   c395f6a