Align Colab: disable curriculum gating to match train.py 8fa8b84 verified Pathikreet commited on Apr 26
Fix colab: format reward +-0.15, temp=0.7, kl_coeff=0.1 33c50da verified Pathikreet commited on Apr 26
Update Colab training notebook to use HF Space URL for pipeline test 205b667 Pathikreet Claude Sonnet 4.6 commited on Apr 23