{
  "condition": "bp",
  "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": [
      "<unk>",
      "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": 0.617732492434351
    },
    {
      "epoch": 2,
      "train_loss": 0.4960194272116611
    },
    {
      "epoch": 3,
      "train_loss": 0.46592118231873764
    },
    {
      "epoch": 4,
      "train_loss": 0.4488015041225835
    },
    {
      "epoch": 5,
      "train_loss": 0.43406150341033933
    },
    {
      "epoch": 6,
      "train_loss": 0.40718337021375955
    },
    {
      "epoch": 7,
      "train_loss": 0.3807649670776568
    },
    {
      "epoch": 8,
      "train_loss": 0.3537148001319484
    },
    {
      "epoch": 9,
      "train_loss": 0.32643107909905283
    },
    {
      "epoch": 10,
      "train_loss": 0.3063848673356207
    },
    {
      "epoch": 11,
      "train_loss": 0.28984395764375986
    },
    {
      "epoch": 12,
      "train_loss": 0.2761740297392795
    },
    {
      "epoch": 13,
      "train_loss": 0.2647564570841036
    },
    {
      "epoch": 14,
      "train_loss": 0.25636729594908264
    },
    {
      "epoch": 15,
      "train_loss": 0.24771365335113124
    },
    {
      "epoch": 16,
      "train_loss": 0.2439696610287616
    },
    {
      "epoch": 17,
      "train_loss": 0.2316527129474439
    },
    {
      "epoch": 18,
      "train_loss": 0.22913515367006002
    },
    {
      "epoch": 19,
      "train_loss": 0.21849248581811
    },
    {
      "epoch": 20,
      "train_loss": 0.21554886654803626
    },
    {
      "epoch": 21,
      "train_loss": 0.20946172889910247
    },
    {
      "epoch": 22,
      "train_loss": 0.20310457860168657
    },
    {
      "epoch": 23,
      "train_loss": 0.2004946485946053
    },
    {
      "epoch": 24,
      "train_loss": 0.19238460020015113
    },
    {
      "epoch": 25,
      "train_loss": 0.19454976933567147
    },
    {
      "epoch": 26,
      "train_loss": 0.1896667920915704
    },
    {
      "epoch": 27,
      "train_loss": 0.17798410443883192
    },
    {
      "epoch": 28,
      "train_loss": 0.18044299861318186
    },
    {
      "epoch": 29,
      "train_loss": 0.17217574811295458
    },
    {
      "epoch": 30,
      "train_loss": 0.1684879423128931
    },
    {
      "epoch": 31,
      "train_loss": 0.16110639711743907
    },
    {
      "epoch": 32,
      "train_loss": 0.1620375840914877
    },
    {
      "epoch": 33,
      "train_loss": 0.15719828299785915
    },
    {
      "epoch": 34,
      "train_loss": 0.1522270987222069
    },
    {
      "epoch": 35,
      "train_loss": 0.14935507338297996
    },
    {
      "epoch": 36,
      "train_loss": 0.1444174110889435
    },
    {
      "epoch": 37,
      "train_loss": 0.14394060233705921
    },
    {
      "epoch": 38,
      "train_loss": 0.13934059754798286
    },
    {
      "epoch": 39,
      "train_loss": 0.13100762662918944
    },
    {
      "epoch": 40,
      "train_loss": 0.1349288523667737
    }
  ],
  "epochs_completed": 40,
  "finite": true,
  "first_nonfinite_epoch": null,
  "mission_lesion_rollout": {
    "episodes": 500,
    "mean_length": 41.77,
    "mean_return": 0.36140937500000003,
    "success": 0.488
  },
  "mission_lesion_validation": {
    "accuracy": 0.7446343241273183,
    "loss": 0.9336490147585154
  },
  "predictor": [],
  "provenance": {
    "cuda_device_name": "NVIDIA GeForce GTX 1080",
    "cuda_peak_allocated_bytes": 130533376,
    "cuda_visible_devices": "0",
    "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": 22.676,
    "mean_return": 0.66191875,
    "success": 0.808
  },
  "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": 337.6041464805603,
    "training_wall_seconds": 322.6370050907135
  },
  "validation": {
    "accuracy": 0.878108042439459,
    "loss": 0.3454075009463489
  }
}