{ "condition": "raw_shared", "config": { "action_dim": 7, "context_gain": 1.0, "hidden_layers": 4, "input_dim": 3964, "learning_rate": 0.03, "mission_dim": 23, "momentum": 0.9, "reciprocal_learning_rate": 0.03, "weight_decay": 0.0001, "width": 256 }, "data": { "color_cardinality": 6, "elapsed_seconds": 81.82925486564636, "env_id": "BabyAI-PickupLoc-v0", "minigrid_version": "3.1.0", "object_cardinality": 11, "protocol": "babyai_shared_feedback_b0", "rollout_episodes": 500, "rollout_seed_start": 200000, "state_cardinality": 3, "train_episodes": 20000, "train_steps": 121467, "validation_episodes": 2000, "validation_steps": 12347, "vocabulary": [ "", "a", "ball", "behind", "blue", "box", "front", "green", "grey", "in", "key", "left", "of", "on", "pick", "purple", "red", "right", "the", "up", "yellow", "you", "your" ] }, "epoch_history": [ { "epoch": 1, "train_loss": 1.3772296137558786 }, { "epoch": 2, "train_loss": 1.7021908586903622 }, { "epoch": 3, "train_loss": 1.4057510167674014 }, { "epoch": 4, "train_loss": 1.3790689074365716 }, { "epoch": 5, "train_loss": 1.4092068611948114 }, { "epoch": 6, "train_loss": 1.4024050559495624 }, { "epoch": 7, "train_loss": 1.448081522489849 }, { "epoch": 8, "train_loss": 1.3555105929625662 }, { "epoch": 9, "train_loss": 1.314540177897403 }, { "epoch": 10, "train_loss": 1.3105172322925769 }, { "epoch": 11, "train_loss": 1.3240358893494857 }, { "epoch": 12, "train_loss": 1.108769882478212 }, { "epoch": 13, "train_loss": 0.9759558450548272 }, { "epoch": 14, "train_loss": 1.1254934888137014 }, { "epoch": 15, "train_loss": 1.3993210215317575 }, { "epoch": 16, "train_loss": 1.473675866628948 }, { "epoch": 17, "train_loss": 1.4721564543874641 }, { "epoch": 18, "train_loss": 1.4467827192105744 }, { "epoch": 19, "train_loss": 1.3536395237320349 }, { "epoch": 20, "train_loss": 1.494690821170807 }, { "epoch": 21, "train_loss": 1.6195249751994485 }, { "epoch": 22, "train_loss": 1.3495978566219933 }, { "epoch": 23, "train_loss": 1.562763890969126 }, { "epoch": 24, "train_loss": 1.3056548786163331 }, { "epoch": 25, "train_loss": 1.510417148188541 }, { "epoch": 26, "train_loss": 1.2385981110522621 }, { "epoch": 27, "train_loss": 1.416951956372512 }, { "epoch": 28, "train_loss": 1.324134414321498 }, { "epoch": 29, "train_loss": 1.6655939639242072 }, { "epoch": 30, "train_loss": 1.3269542169570923 }, { "epoch": 31, "train_loss": 1.198546481634441 }, { "epoch": 32, "train_loss": 1.6666638913907503 }, { "epoch": 33, "train_loss": 1.427612681388855 }, { "epoch": 34, "train_loss": 1.2676852522398296 }, { "epoch": 35, "train_loss": 1.4735501365912589 }, { "epoch": 36, "train_loss": 1.1051569257284466 }, { "epoch": 37, "train_loss": 1.2862973846887287 }, { "epoch": 38, "train_loss": 1.035027784046374 }, { "epoch": 39, "train_loss": 1.1972457239502354 }, { "epoch": 40, "train_loss": 1.2982738676824068 } ], "epochs_completed": 40, "finite": true, "first_nonfinite_epoch": null, "mission_lesion_rollout": { "episodes": 500, "mean_length": 64.0, "mean_return": 0.0, "success": 0.0 }, "mission_lesion_validation": { "accuracy": 0.49890661699198185, "loss": 1.3048100115036958 }, "predictor": [], "provenance": { "cuda_device_name": "NVIDIA GeForce GTX 1080", "cuda_peak_allocated_bytes": 130029568, "cuda_visible_devices": "2", "device": "cuda:0", "git_commit": "7b7d7a08a5e78c3379397f01f0c9af97d5d84fbd", "git_dirty_tracked": false, "minigrid_version": "3.1.0", "torch_version": "2.3.1+cu118" }, "rollout": { "episodes": 500, "mean_length": 64.0, "mean_return": 0.0, "success": 0.0 }, "stage": "babyai_pickup_p2", "training": { "batch_size": 256, "history_steps": 4, "model_seed": 4101, "neutral_examples_per_epoch": 0, "parameter_count_including_reciprocal_context_predictor": 1438215, "shuffle_seed": 4101, "total_wall_seconds_including_rollouts": 349.1060309410095, "training_wall_seconds": 327.87563133239746 }, "validation": { "accuracy": 0.49890661699198185, "loss": 1.304808247974742 } }