{ "repo_id": "yangfy0627/RL-postTrain", "source_run": "20261015-1659_distribution_bc_remote", "models": [ { "task": "ToolHang", "experiment": "tool_hang", "regime": "diverse50", "seed": 1, "epoch": 3000, "status": "completed", "family": "StandardBaseBC", "framework": "jax", "weights": "complete_model_EMA", "horizon": 8, "successes": 6, "episodes": 50, "success_rate": 0.12, "last_10_eval_mean": 0.092, "last_50_eval_mean": 0.1048, "checkpoint_sha256": "19a096005907b1636ab80fd22c29db3a9307ee0734332f1eb31031522c375c3a", "checkpoint_bytes": 96456353, "path": "Robomimic/study1/ToolHang/diverse50/seed_1", "plan_hash": "e1adf0b00a0b6829d9587db48628479a796dc3a85d706c2fd78af3d318865b81", "plan_file_sha256": "f7f759458e780c08c40cd40e7a2ab8aa31ae50fdcc3a728fd264432c0b7095af", "identity_hash": "09541bb765419769b428eca807a8bf7c98741ffd3818563bde24aea286c9f0c6", "source_run": "20261015-1659_distribution_bc_remote", "data_split": { "training": 45, "validation": 5 } }, { "task": "ToolHang", "experiment": "tool_hang", "regime": "focused50", "seed": 1, "epoch": 3000, "status": "completed", "family": "StandardBaseBC", "framework": "jax", "weights": "complete_model_EMA", "horizon": 8, "successes": 6, "episodes": 50, "success_rate": 0.12, "last_10_eval_mean": 0.11399999999999999, "last_50_eval_mean": 0.1108, "checkpoint_sha256": "a6fd78e1aea4e2897aeddb0b085c0312b95f2bb44ec7703967a3fea4dc58a0d7", "checkpoint_bytes": 96460817, "path": "Robomimic/study1/ToolHang/focused50/seed_1", "plan_hash": "e1adf0b00a0b6829d9587db48628479a796dc3a85d706c2fd78af3d318865b81", "plan_file_sha256": "f7f759458e780c08c40cd40e7a2ab8aa31ae50fdcc3a728fd264432c0b7095af", "identity_hash": "d19054118da34a35727167cb9ce35cf6f0b434840266eb3dce92f8907c92ecbe", "source_run": "20261015-1659_distribution_bc_remote", "data_split": { "training": 45, "validation": 5 } }, { "task": "ToolHang", "experiment": "tool_hang", "regime": "mixed50", "seed": 1, "epoch": 3000, "status": "completed", "family": "StandardBaseBC", "framework": "jax", "weights": "complete_model_EMA", "horizon": 8, "successes": 5, "episodes": 50, "success_rate": 0.1, "last_10_eval_mean": 0.174, "last_50_eval_mean": 0.1548, "checkpoint_sha256": "db9b15280cd3f2147793cf8bf818e0d4eb6f5df52154f73e0858b9db97d41777", "checkpoint_bytes": 96455648, "path": "Robomimic/study1/ToolHang/mixed50/seed_1", "plan_hash": "e1adf0b00a0b6829d9587db48628479a796dc3a85d706c2fd78af3d318865b81", "plan_file_sha256": "f7f759458e780c08c40cd40e7a2ab8aa31ae50fdcc3a728fd264432c0b7095af", "identity_hash": "600cc3f958c4bf4e1c470c047ca3c76db264929522e907741944580f7d807683", "source_run": "20261015-1659_distribution_bc_remote", "data_split": { "training": 45, "validation": 5 } }, { "task": "Transport", "experiment": "transport_8", "regime": "diverse50", "seed": 1, "epoch": 3000, "status": "completed", "family": "StandardBaseBC", "framework": "jax", "weights": "complete_model_EMA", "horizon": 8, "successes": 30, "episodes": 50, "success_rate": 0.6, "last_10_eval_mean": 0.568, "last_50_eval_mean": 0.5492, "checkpoint_sha256": "b82b0c433a011cd236f7071cf7d169f297f77ee51ba490f305b0b25754cd747c", "checkpoint_bytes": 180483199, "path": "Robomimic/study1/Transport/diverse50/seed_1", "plan_hash": "e1adf0b00a0b6829d9587db48628479a796dc3a85d706c2fd78af3d318865b81", "plan_file_sha256": "f7f759458e780c08c40cd40e7a2ab8aa31ae50fdcc3a728fd264432c0b7095af", "identity_hash": "a7ca306b68faecea4728cff6ad1fb1fa5e16006117c013c4b3095f61ac934ecf", "source_run": "20261015-1659_distribution_bc_remote", "data_split": { "training": 45, "validation": 5 } }, { "task": "Transport", "experiment": "transport_8", "regime": "focused50", "seed": 1, "epoch": 3000, "status": "completed", "family": "StandardBaseBC", "framework": "jax", "weights": "complete_model_EMA", "horizon": 8, "successes": 32, "episodes": 50, "success_rate": 0.64, "last_10_eval_mean": 0.564, "last_50_eval_mean": 0.5676, "checkpoint_sha256": "c27da77bf528fe9689f40a298ba9629a0cf3a9588f36be3e286c82ed1027b6b0", "checkpoint_bytes": 180496738, "path": "Robomimic/study1/Transport/focused50/seed_1", "plan_hash": "e1adf0b00a0b6829d9587db48628479a796dc3a85d706c2fd78af3d318865b81", "plan_file_sha256": "f7f759458e780c08c40cd40e7a2ab8aa31ae50fdcc3a728fd264432c0b7095af", "identity_hash": "c2570f4d7331f9bd4bd6aa0af988019a3a5b3c3cee347f155c6f9cba5aa42486", "source_run": "20261015-1659_distribution_bc_remote", "data_split": { "training": 45, "validation": 5 } }, { "task": "Transport", "experiment": "transport_8", "regime": "mixed50", "seed": 1, "epoch": 3000, "status": "completed", "family": "StandardBaseBC", "framework": "jax", "weights": "complete_model_EMA", "horizon": 8, "successes": 22, "episodes": 50, "success_rate": 0.44, "last_10_eval_mean": 0.524, "last_50_eval_mean": 0.5496, "checkpoint_sha256": "254c5ab1b1af96faf2b86373fc05cd5dc4995ae1048ffdbc896a74d9756bb9b5", "checkpoint_bytes": 180484982, "path": "Robomimic/study1/Transport/mixed50/seed_1", "plan_hash": "e1adf0b00a0b6829d9587db48628479a796dc3a85d706c2fd78af3d318865b81", "plan_file_sha256": "f7f759458e780c08c40cd40e7a2ab8aa31ae50fdcc3a728fd264432c0b7095af", "identity_hash": "6d9565e4580af95f5874d988c99c694d9a077a389b583fb203f14b8b1577f833", "source_run": "20261015-1659_distribution_bc_remote", "data_split": { "training": 45, "validation": 5 } } ] }