Upload human_games/game_20260325_001249_5.json with huggingface_hub

human_games/game_20260325_001249_5.json

@@ -0,0 +1,2351 @@
+{
+ "game_number": 5,
+ "timestamp": "2026-03-25T00:12:49.955354+00:00",
+ "checkpoint": "checkpoints/r42_800M.pkl",
+ "architecture": "simba_aux",
+ "model_checkpoint": "r42_800M.pkl",
+ "model_architecture": "simba_aux",
+ "result": "model_win",
+ "final_scores": [
+  0,
+  22
+ ],
+ "total_turns": 16,
+ "actions": [
+  {
+   "turn": 0,
+   "player": -1,
+   "phase": "draw",
+   "action": -1,
+   "action_desc": "Initial deal",
+   "card_drawn": null,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     51,
+     5,
+     15,
+     9,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     42,
+     45,
+     7,
+     43,
+     21,
+     36,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23
+   ],
+   "discard_size": 1,
+   "stock_remaining": 31,
+   "deadwood": [
+    56,
+    69
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 1,
+   "player": 0,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Human drew from stock",
+   "card_drawn": 48,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     51,
+     5,
+     15,
+     9,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     42,
+     45,
+     7,
+     43,
+     21,
+     36,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23
+   ],
+   "discard_size": 1,
+   "stock_remaining": 31,
+   "deadwood": [
+    56,
+    69
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 2,
+   "player": 0,
+   "phase": "discard",
+   "action": 5,
+   "action_desc": "Human discarded K\u2663",
+   "card_drawn": null,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     51,
+     5,
+     15,
+     9,
+     27,
+     30,
+     13,
+     48
+    ],
+    [
+     2,
+     29,
+     8,
+     42,
+     45,
+     7,
+     43,
+     21,
+     36,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    23
+   ],
+   "discard_size": 1,
+   "stock_remaining": 30,
+   "deadwood": [
+    66,
+    69
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 3,
+   "player": 1,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Model drew from stock",
+   "card_drawn": 11,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     48,
+     5,
+     15,
+     9,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     42,
+     45,
+     7,
+     43,
+     21,
+     36,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51
+   ],
+   "discard_size": 2,
+   "stock_remaining": 30,
+   "deadwood": [
+    56,
+    69
+   ],
+   "model_logits": [
+    0.44646427035331726,
+    -0.44516491889953613,
+    2.005288600921631,
+    -0.7088584303855896,
+    -2.6995675563812256,
+    -1.8335438966751099,
+    1.838926076889038,
+    -4.08890962600708,
+    -0.399880051612854,
+    -1.8007315397262573,
+    2.0132405757904053,
+    -0.1954866349697113,
+    2.959669351577759,
+    -1.5346155166625977,
+    -0.060077957808971405,
+    15.1032133102417
+   ],
+   "model_value": 0.19617769122123718,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 4,
+   "player": 1,
+   "phase": "discard",
+   "action": 6,
+   "action_desc": "Model discarded 7\u2663",
+   "card_drawn": null,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     48,
+     5,
+     15,
+     9,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     42,
+     45,
+     7,
+     43,
+     21,
+     36,
+     12,
+     11
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    23,
+    51
+   ],
+   "discard_size": 2,
+   "stock_remaining": 29,
+   "deadwood": [
+    56,
+    79
+   ],
+   "model_logits": [
+    0.22540131211280823,
+    -0.22753995656967163,
+    2.407101631164551,
+    0.6800909638404846,
+    -2.173002243041992,
+    -0.08242562413215637,
+    2.898866891860962,
+    -1.2171683311462402,
+    0.9923494458198547,
+    -1.960150122642517,
+    -0.17256639897823334,
+    -3.667513847351074,
+    -1.1051957607269287,
+    2.7059309482574463,
+    -4.0940327644348145,
+    13.52048397064209
+   ],
+   "model_value": 0.3150976300239563,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 5,
+   "player": 0,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Human drew from stock",
+   "card_drawn": 17,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     48,
+     5,
+     15,
+     9,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     42,
+     11,
+     7,
+     43,
+     21,
+     36,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45
+   ],
+   "discard_size": 3,
+   "stock_remaining": 29,
+   "deadwood": [
+    56,
+    72
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 6,
+   "player": 0,
+   "phase": "discard",
+   "action": 8,
+   "action_desc": "Human discarded 10\u2660",
+   "card_drawn": null,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     48,
+     5,
+     15,
+     9,
+     27,
+     30,
+     13,
+     17
+    ],
+    [
+     2,
+     29,
+     8,
+     42,
+     11,
+     7,
+     43,
+     21,
+     36,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45
+   ],
+   "discard_size": 3,
+   "stock_remaining": 28,
+   "deadwood": [
+    61,
+    72
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 7,
+   "player": 1,
+   "phase": "draw",
+   "action": 1,
+   "action_desc": "Model drew 10\u2660 from discard",
+   "card_drawn": 9,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     48,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     42,
+     11,
+     7,
+     43,
+     21,
+     36,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    9
+   ],
+   "discard_size": 4,
+   "stock_remaining": 28,
+   "deadwood": [
+    51,
+    72
+   ],
+   "model_logits": [
+    -12.26740837097168,
+    12.26699447631836,
+    1.8883110284805298,
+    -1.626328706741333,
+    -1.6464855670928955,
+    -2.814018726348877,
+    -1.3795942068099976,
+    -2.46687388420105,
+    -1.8701295852661133,
+    -0.34300312399864197,
+    2.6106715202331543,
+    2.051229476928711,
+    -3.2833993434906006,
+    -1.2803606986999512,
+    0.7393525838851929,
+    8.850516319274902
+   ],
+   "model_value": 0.16748379170894623,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 8,
+   "player": 1,
+   "phase": "discard",
+   "action": 10,
+   "action_desc": "Model discarded J\u2666",
+   "card_drawn": null,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     48,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     42,
+     11,
+     7,
+     43,
+     21,
+     36,
+     12,
+     9
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45
+   ],
+   "discard_size": 3,
+   "stock_remaining": 28,
+   "deadwood": [
+    51,
+    55
+   ],
+   "model_logits": [
+    -3.3303606510162354,
+    3.322096824645996,
+    3.56318998336792,
+    -0.1697646826505661,
+    -7.255303382873535,
+    0.6792615056037903,
+    1.5580886602401733,
+    -9.08933162689209,
+    0.20594502985477448,
+    -1.4213473796844482,
+    7.503976345062256,
+    2.17415189743042,
+    -2.7449615001678467,
+    0.8932405114173889,
+    -1.8213993310928345,
+    10.873382568359375
+   ],
+   "model_value": 0.266734778881073,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 9,
+   "player": 0,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Human drew from stock",
+   "card_drawn": 20,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     48,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     42,
+     11,
+     7,
+     43,
+     21,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36
+   ],
+   "discard_size": 4,
+   "stock_remaining": 28,
+   "deadwood": [
+    51,
+    45
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 10,
+   "player": 0,
+   "phase": "discard",
+   "action": 12,
+   "action_desc": "Human discarded 8\u2665",
+   "card_drawn": null,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     48,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13,
+     20
+    ],
+    [
+     2,
+     29,
+     8,
+     42,
+     11,
+     7,
+     43,
+     21,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36
+   ],
+   "discard_size": 4,
+   "stock_remaining": 27,
+   "deadwood": [
+    59,
+    45
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 11,
+   "player": 1,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Model drew from stock",
+   "card_drawn": 10,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     48,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     42,
+     11,
+     7,
+     43,
+     21,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20
+   ],
+   "discard_size": 5,
+   "stock_remaining": 27,
+   "deadwood": [
+    51,
+    45
+   ],
+   "model_logits": [
+    1.8350306749343872,
+    -1.8555736541748047,
+    0.7017938494682312,
+    0.699691653251648,
+    -3.9626903533935547,
+    -1.1517935991287231,
+    2.5774996280670166,
+    -6.230175495147705,
+    1.0678907632827759,
+    3.7306838035583496,
+    -5.8910980224609375,
+    6.788896560668945,
+    1.6548861265182495,
+    3.7875125408172607,
+    -5.116235733032227,
+    13.08728313446045
+   ],
+   "model_value": 0.13876299560070038,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 12,
+   "player": 1,
+   "phase": "discard",
+   "action": 9,
+   "action_desc": "Model discarded 9\u2665",
+   "card_drawn": null,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     48,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     42,
+     11,
+     7,
+     43,
+     21,
+     9,
+     12,
+     10
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20
+   ],
+   "discard_size": 5,
+   "stock_remaining": 26,
+   "deadwood": [
+    51,
+    25
+   ],
+   "model_logits": [
+    -2.2246735095977783,
+    2.20810604095459,
+    4.102224349975586,
+    3.0280911922454834,
+    -7.31381368637085,
+    2.561394214630127,
+    -3.572284460067749,
+    -0.1446799784898758,
+    5.87237548828125,
+    9.524531364440918,
+    -11.957315444946289,
+    3.309128522872925,
+    -8.70164966583252,
+    3.2824041843414307,
+    -3.70316219329834,
+    5.874724388122559
+   ],
+   "model_value": 0.303559273481369,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 13,
+   "player": 0,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Human drew from stock",
+   "card_drawn": 6,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     48,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     42,
+     11,
+     7,
+     43,
+     10,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21
+   ],
+   "discard_size": 6,
+   "stock_remaining": 26,
+   "deadwood": [
+    51,
+    16
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 14,
+   "player": 0,
+   "phase": "discard",
+   "action": 5,
+   "action_desc": "Human discarded 10\u2663",
+   "card_drawn": null,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     48,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13,
+     6
+    ],
+    [
+     2,
+     29,
+     8,
+     42,
+     11,
+     7,
+     43,
+     10,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21
+   ],
+   "discard_size": 6,
+   "stock_remaining": 25,
+   "deadwood": [
+    58,
+    16
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 15,
+   "player": 1,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Model drew from stock",
+   "card_drawn": 14,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     42,
+     11,
+     7,
+     43,
+     10,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48
+   ],
+   "discard_size": 7,
+   "stock_remaining": 25,
+   "deadwood": [
+    48,
+    16
+   ],
+   "model_logits": [
+    5.166488170623779,
+    -5.19210958480835,
+    4.5680413246154785,
+    3.404137134552002,
+    0.34513992071151733,
+    4.458003997802734,
+    -4.01824951171875,
+    0.876509964466095,
+    4.626875877380371,
+    -7.867835521697998,
+    -6.73263692855835,
+    2.9618117809295654,
+    -0.6598952412605286,
+    0.059613440185785294,
+    -1.489869236946106,
+    12.89390754699707
+   ],
+   "model_value": 0.37604159116744995,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 16,
+   "player": 1,
+   "phase": "discard",
+   "action": 5,
+   "action_desc": "Model discarded 4\u2663",
+   "card_drawn": null,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     42,
+     11,
+     7,
+     43,
+     10,
+     9,
+     12,
+     14
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48
+   ],
+   "discard_size": 7,
+   "stock_remaining": 24,
+   "deadwood": [
+    48,
+    18
+   ],
+   "model_logits": [
+    2.1318228244781494,
+    -2.164736032485962,
+    5.450942516326904,
+    3.822159767150879,
+    -2.391251802444458,
+    7.0785088539123535,
+    -5.183215618133545,
+    2.5668752193450928,
+    7.5528669357299805,
+    -12.599595069885254,
+    -11.118485450744629,
+    4.190390586853027,
+    0.32790911197662354,
+    -2.6046624183654785,
+    1.5989207029342651,
+    9.116048812866211
+   ],
+   "model_value": 0.45257148146629333,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 17,
+   "player": 0,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Human drew from stock",
+   "card_drawn": 16,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     43,
+     10,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42
+   ],
+   "discard_size": 8,
+   "stock_remaining": 24,
+   "deadwood": [
+    48,
+    14
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 18,
+   "player": 0,
+   "phase": "discard",
+   "action": 2,
+   "action_desc": "Human discarded 9\u2663",
+   "card_drawn": null,
+   "hands": [
+    [
+     47,
+     3,
+     31,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13,
+     16
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     43,
+     10,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42
+   ],
+   "discard_size": 8,
+   "stock_remaining": 23,
+   "deadwood": [
+    40,
+    14
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 19,
+   "player": 1,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Model drew from stock",
+   "card_drawn": 4,
+   "hands": [
+    [
+     16,
+     3,
+     31,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     43,
+     10,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42,
+    47
+   ],
+   "discard_size": 9,
+   "stock_remaining": 23,
+   "deadwood": [
+    31,
+    14
+   ],
+   "model_logits": [
+    4.420629978179932,
+    -4.447947025299072,
+    3.50484037399292,
+    5.919126987457275,
+    -1.6009573936462402,
+    2.61783504486084,
+    -3.265421152114868,
+    1.7501583099365234,
+    6.085115432739258,
+    -8.871217727661133,
+    -7.1262030601501465,
+    3.755293130874634,
+    -1.0539367198944092,
+    -1.6321419477462769,
+    0.30441853404045105,
+    12.216235160827637
+   ],
+   "model_value": 0.4005470275878906,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 20,
+   "player": 1,
+   "phase": "discard",
+   "action": 8,
+   "action_desc": "Model discarded 5\u2663",
+   "card_drawn": null,
+   "hands": [
+    [
+     16,
+     3,
+     31,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     43,
+     10,
+     9,
+     12,
+     4
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42,
+    47
+   ],
+   "discard_size": 9,
+   "stock_remaining": 22,
+   "deadwood": [
+    31,
+    19
+   ],
+   "model_logits": [
+    -1.8081129789352417,
+    1.7736397981643677,
+    2.2659590244293213,
+    6.230957508087158,
+    -4.518009662628174,
+    2.9621570110321045,
+    -4.923310279846191,
+    2.28125262260437,
+    6.971704483032227,
+    -13.012149810791016,
+    -9.59646987915039,
+    4.096042633056641,
+    4.966683387756348,
+    -1.6995298862457275,
+    0.7542835474014282,
+    9.218894004821777
+   ],
+   "model_value": 0.5602080821990967,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 21,
+   "player": 0,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Human drew from stock",
+   "card_drawn": 19,
+   "hands": [
+    [
+     16,
+     3,
+     31,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     4,
+     10,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42,
+    47,
+    43
+   ],
+   "discard_size": 10,
+   "stock_remaining": 22,
+   "deadwood": [
+    31,
+    14
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 22,
+   "player": 0,
+   "phase": "discard",
+   "action": 4,
+   "action_desc": "Human discarded 6\u2666",
+   "card_drawn": null,
+   "hands": [
+    [
+     16,
+     3,
+     31,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13,
+     19
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     4,
+     10,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42,
+    47,
+    43
+   ],
+   "discard_size": 10,
+   "stock_remaining": 21,
+   "deadwood": [
+    38,
+    14
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 23,
+   "player": 1,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Model drew from stock",
+   "card_drawn": 35,
+   "hands": [
+    [
+     16,
+     3,
+     19,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     4,
+     10,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42,
+    47,
+    43,
+    31
+   ],
+   "discard_size": 11,
+   "stock_remaining": 21,
+   "deadwood": [
+    32,
+    14
+   ],
+   "model_logits": [
+    3.981086015701294,
+    -4.012567043304443,
+    1.4224706888198853,
+    5.855846881866455,
+    -0.14530238509178162,
+    3.299467086791992,
+    -4.2381696701049805,
+    2.2106308937072754,
+    8.822104454040527,
+    -11.091350555419922,
+    -7.793320178985596,
+    4.890064716339111,
+    -1.1544140577316284,
+    -1.613085150718689,
+    0.491565078496933,
+    10.63914680480957
+   ],
+   "model_value": 0.2749723792076111,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 24,
+   "player": 1,
+   "phase": "discard",
+   "action": 12,
+   "action_desc": "Model discarded 10\u2666",
+   "card_drawn": null,
+   "hands": [
+    [
+     16,
+     3,
+     19,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     4,
+     10,
+     9,
+     12,
+     35
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42,
+    47,
+    43,
+    31
+   ],
+   "discard_size": 11,
+   "stock_remaining": 20,
+   "deadwood": [
+    32,
+    24
+   ],
+   "model_logits": [
+    3.9433114528656006,
+    -3.976815700531006,
+    0.3868432343006134,
+    3.749077796936035,
+    -1.3430635929107666,
+    2.311318874359131,
+    -5.866939067840576,
+    1.3649365901947021,
+    4.520620822906494,
+    -10.834098815917969,
+    -9.302236557006836,
+    2.196981191635132,
+    13.273894309997559,
+    3.1547605991363525,
+    -4.482095718383789,
+    10.480803489685059
+   ],
+   "model_value": 0.33236491680145264,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 25,
+   "player": 0,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Human drew from stock",
+   "card_drawn": 37,
+   "hands": [
+    [
+     16,
+     3,
+     19,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     4,
+     10,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42,
+    47,
+    43,
+    31,
+    35
+   ],
+   "discard_size": 12,
+   "stock_remaining": 20,
+   "deadwood": [
+    32,
+    14
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 26,
+   "player": 0,
+   "phase": "discard",
+   "action": 12,
+   "action_desc": "Human discarded Q\u2666",
+   "card_drawn": null,
+   "hands": [
+    [
+     16,
+     3,
+     19,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13,
+     37
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     4,
+     10,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42,
+    47,
+    43,
+    31,
+    35
+   ],
+   "discard_size": 12,
+   "stock_remaining": 19,
+   "deadwood": [
+    42,
+    14
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 27,
+   "player": 1,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Model drew from stock",
+   "card_drawn": 44,
+   "hands": [
+    [
+     16,
+     3,
+     19,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     4,
+     10,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42,
+    47,
+    43,
+    31,
+    35,
+    37
+   ],
+   "discard_size": 13,
+   "stock_remaining": 19,
+   "deadwood": [
+    32,
+    14
+   ],
+   "model_logits": [
+    4.104899883270264,
+    -4.123440742492676,
+    1.151823878288269,
+    6.2424845695495605,
+    -0.7818430662155151,
+    1.3664721250534058,
+    -3.36592698097229,
+    1.64742112159729,
+    8.030861854553223,
+    -9.514984130859375,
+    -7.078109264373779,
+    4.604839324951172,
+    -0.653775155544281,
+    -0.8946107029914856,
+    -0.35482338070869446,
+    11.643874168395996
+   ],
+   "model_value": 0.33271682262420654,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 28,
+   "player": 1,
+   "phase": "discard",
+   "action": 12,
+   "action_desc": "Model discarded 6\u2663",
+   "card_drawn": null,
+   "hands": [
+    [
+     16,
+     3,
+     19,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     4,
+     10,
+     9,
+     12,
+     44
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42,
+    47,
+    43,
+    31,
+    35,
+    37
+   ],
+   "discard_size": 13,
+   "stock_remaining": 18,
+   "deadwood": [
+    32,
+    20
+   ],
+   "model_logits": [
+    3.6289353370666504,
+    -3.651562452316284,
+    0.8955609798431396,
+    5.640666484832764,
+    -1.6406002044677734,
+    1.7489086389541626,
+    -4.630945205688477,
+    1.221543788909912,
+    5.193866729736328,
+    -12.430208206176758,
+    -8.844193458557129,
+    3.4088165760040283,
+    9.342318534851074,
+    2.644631862640381,
+    -3.967137098312378,
+    10.869965553283691
+   ],
+   "model_value": 0.4112440049648285,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 29,
+   "player": 0,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Human drew from stock",
+   "card_drawn": 50,
+   "hands": [
+    [
+     16,
+     3,
+     19,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     4,
+     10,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42,
+    47,
+    43,
+    31,
+    35,
+    37,
+    44
+   ],
+   "discard_size": 14,
+   "stock_remaining": 18,
+   "deadwood": [
+    32,
+    14
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 30,
+   "player": 0,
+   "phase": "discard",
+   "action": 12,
+   "action_desc": "Human discarded Q\u2663",
+   "card_drawn": null,
+   "hands": [
+    [
+     16,
+     3,
+     19,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13,
+     50
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     4,
+     10,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42,
+    47,
+    43,
+    31,
+    35,
+    37,
+    44
+   ],
+   "discard_size": 14,
+   "stock_remaining": 17,
+   "deadwood": [
+    42,
+    14
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 31,
+   "player": 1,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Model drew from stock",
+   "card_drawn": 26,
+   "hands": [
+    [
+     16,
+     3,
+     19,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     4,
+     10,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42,
+    47,
+    43,
+    31,
+    35,
+    37,
+    44,
+    50
+   ],
+   "discard_size": 15,
+   "stock_remaining": 17,
+   "deadwood": [
+    32,
+    14
+   ],
+   "model_logits": [
+    4.819906711578369,
+    -4.840890407562256,
+    1.950372576713562,
+    4.808573246002197,
+    -1.167507290840149,
+    3.1777474880218506,
+    -2.1616132259368896,
+    1.547547459602356,
+    7.936022758483887,
+    -8.644107818603516,
+    -7.364597797393799,
+    3.904141664505005,
+    -1.6801589727401733,
+    -1.2845038175582886,
+    0.061372943222522736,
+    11.340662956237793
+   ],
+   "model_value": 0.32115638256073,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 32,
+   "player": 1,
+   "phase": "discard",
+   "action": 8,
+   "action_desc": "Model discarded 5\u2660",
+   "card_drawn": null,
+   "hands": [
+    [
+     16,
+     3,
+     19,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     4,
+     10,
+     9,
+     12,
+     26
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42,
+    47,
+    43,
+    31,
+    35,
+    37,
+    44,
+    50
+   ],
+   "discard_size": 15,
+   "stock_remaining": 16,
+   "deadwood": [
+    32,
+    15
+   ],
+   "model_logits": [
+    1.896209716796875,
+    -1.92103910446167,
+    4.436880111694336,
+    7.893919944763184,
+    -3.3175177574157715,
+    5.695739269256592,
+    -3.99066162109375,
+    2.0932838916778564,
+    11.61303997039795,
+    -14.227922439575195,
+    -11.156967163085938,
+    4.792416095733643,
+    -3.593684673309326,
+    -2.819870710372925,
+    2.2497639656066895,
+    5.461748123168945
+   ],
+   "model_value": 0.4467967748641968,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 33,
+   "player": 1,
+   "phase": "knock_decision",
+   "action": 14,
+   "action_desc": "Model knocked",
+   "card_drawn": null,
+   "hands": [
+    [
+     16,
+     3,
+     19,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     26,
+     10,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42,
+    47,
+    43,
+    31,
+    35,
+    37,
+    44,
+    50,
+    4
+   ],
+   "discard_size": 16,
+   "stock_remaining": 16,
+   "deadwood": [
+    32,
+    10
+   ],
+   "model_logits": [
+    3.515892505645752,
+    -3.549199104309082,
+    4.966958999633789,
+    6.365931034088135,
+    -2.8421521186828613,
+    1.4564769268035889,
+    -2.213350772857666,
+    1.7686691284179688,
+    4.953024387359619,
+    -8.77511978149414,
+    -8.378056526184082,
+    5.679566383361816,
+    -0.9104614853858948,
+    -7.4730939865112305,
+    6.40046501159668,
+    9.804292678833008
+   ],
+   "model_value": 0.2832145392894745,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 34,
+   "player": -1,
+   "phase": "game_over",
+   "action": -1,
+   "action_desc": "Game over.",
+   "card_drawn": null,
+   "hands": [
+    [
+     16,
+     3,
+     19,
+     6,
+     5,
+     15,
+     17,
+     27,
+     30,
+     13
+    ],
+    [
+     2,
+     29,
+     8,
+     14,
+     11,
+     7,
+     26,
+     10,
+     9,
+     12
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    23,
+    51,
+    45,
+    36,
+    20,
+    21,
+    48,
+    42,
+    47,
+    43,
+    31,
+    35,
+    37,
+    44,
+    50,
+    4
+   ],
+   "discard_size": 16,
+   "stock_remaining": 16,
+   "deadwood": [
+    32,
+    10
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_800M.pkl",
+   "model_architecture": "simba_aux"
+  }
+ ]
+}