summaryrefslogtreecommitdiff
path: root/results/babyai_shared/b0/d2_lr0.01_clean_kp.json
blob: c63545b7849cd5f0dd30f108153368f6a2748894 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
{
  "condition": "clean_kp",
  "config": {
    "action_dim": 7,
    "context_gain": 1.0,
    "hidden_layers": 2,
    "input_dim": 984,
    "learning_rate": 0.01,
    "mission_dim": 13,
    "momentum": 0.9,
    "reciprocal_learning_rate": 0.01,
    "weight_decay": 0.0001,
    "width": 256
  },
  "data": {
    "color_cardinality": 6,
    "elapsed_seconds": 37.730633020401,
    "env_id": "BabyAI-GoToObjS6-v1",
    "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": 70159,
    "validation_episodes": 2000,
    "validation_steps": 7019,
    "vocabulary": [
      "<unk>",
      "ball",
      "blue",
      "box",
      "go",
      "green",
      "grey",
      "key",
      "purple",
      "red",
      "the",
      "to",
      "yellow"
    ]
  },
  "epoch_history": [
    {
      "epoch": 1,
      "train_loss": 0.42220023420724
    },
    {
      "epoch": 2,
      "train_loss": 0.042795064787973056
    },
    {
      "epoch": 3,
      "train_loss": 0.01790234833363105
    },
    {
      "epoch": 4,
      "train_loss": 0.014970682340420106
    },
    {
      "epoch": 5,
      "train_loss": 0.014731389162638648
    },
    {
      "epoch": 6,
      "train_loss": 0.012619410693137482
    },
    {
      "epoch": 7,
      "train_loss": 0.013174676087642596
    },
    {
      "epoch": 8,
      "train_loss": 0.012047174987383186
    },
    {
      "epoch": 9,
      "train_loss": 0.011912513411900198
    },
    {
      "epoch": 10,
      "train_loss": 0.011198682525110516
    },
    {
      "epoch": 11,
      "train_loss": 0.010507440414618362
    },
    {
      "epoch": 12,
      "train_loss": 0.011464962014843795
    },
    {
      "epoch": 13,
      "train_loss": 0.011738500667905266
    },
    {
      "epoch": 14,
      "train_loss": 0.010477929167999802
    },
    {
      "epoch": 15,
      "train_loss": 0.010263334540861913
    }
  ],
  "epochs_completed": 15,
  "finite": true,
  "first_nonfinite_epoch": null,
  "mission_lesion_rollout": {
    "episodes": 500,
    "mean_length": 16.362,
    "mean_return": 0.5511499999999999,
    "success": 0.602
  },
  "mission_lesion_validation": {
    "accuracy": 0.7602222538823195,
    "loss": 0.7746106897906575
  },
  "predictor": [],
  "provenance": {
    "cuda_device_name": "NVIDIA GeForce GTX 1080",
    "cuda_peak_allocated_bytes": 39800832,
    "cuda_visible_devices": "1",
    "device": "cuda:0",
    "git_commit": "20fd3577693593e3f62bcc4e1c2565dca5349944",
    "git_dirty_tracked": false,
    "minigrid_version": "3.1.0",
    "torch_version": "2.3.1+cu118"
  },
  "rollout": {
    "episodes": 500,
    "mean_length": 4.29,
    "mean_return": 0.8905500000000001,
    "success": 0.978
  },
  "stage": "babyai_shared_b0",
  "training": {
    "batch_size": 256,
    "model_seed": 4101,
    "neutral_examples_per_epoch": 0,
    "parameter_count_including_reciprocal_context_predictor": 394759,
    "shuffle_seed": 4101,
    "total_wall_seconds_including_rollouts": 72.49147534370422,
    "training_wall_seconds": 68.89583253860474
  },
  "validation": {
    "accuracy": 0.9974355321270836,
    "loss": 0.010123796248337468
  }
}