orgOS / training /grpo_orgos.ipynb

Commit History

fix: stable GRPO notebook — pin TRL<=0.24, multi-step reward, Drive checkpoints every 30 steps
5ebb26b

muskan singh Claude Opus 4.7 commited on

training notebook with training logs
e22f664

muskan singh commited on

training notebook
9e29238

muskan singh commited on

added minimal ui and all 4 apps+workflows
2305b9f

Taniieeee83 commited on