| { | |
| "checkpoint_schema_version": 2, | |
| "hidden_reset_policy": "episode_done", | |
| "update": 356, | |
| "stage": 7, | |
| "ent_scale": 1.0695132172294464, | |
| "lr_now": 0.00008014427207031247, | |
| "total_env_steps": 767488, | |
| "recent_wins": [ | |
| 0.0 | |
| ], | |
| "recent_conversions": [], | |
| "best_eval_win": null, | |
| "best_eval_score": null, | |
| "v81_curriculum": true, | |
| "curriculum_schedule": "v8.3", | |
| "reward_profile": "v8.3-closeout-v1", | |
| "return_stats": null, | |
| "stage_env_targets": [ | |
| 24, | |
| 24, | |
| 24, | |
| 24, | |
| 24, | |
| 24, | |
| 16, | |
| 12, | |
| 10, | |
| 12, | |
| 10, | |
| 8, | |
| 8, | |
| 8, | |
| 8 | |
| ], | |
| "envs_per_shard": 12, | |
| "requested_env_target": null | |
| } |