feat: 5 training plots (reward±std, KL/loss, completion stats) + Drive backup in Cell 8 ff63792 Jaswanth1210 Claude Sonnet 4.6 commited on 14 days ago
fix: plots gitignore, trainer_state fallback for reward curve, Cell 8 --trainer-state arg 2fe5366 Jaswanth1210 Claude Sonnet 4.6 commited on 15 days ago
Phase 7/8: full README, video script, make_plots.py, Cell 8 implementation 5244e53 Jaswanth1210 Claude Opus 4.7 commited on 15 days ago