Upload human_games/game_20260325_142116_4.json with huggingface_hub

human_games/game_20260325_142116_4.json

@@ -0,0 +1,2550 @@
+{
+ "game_number": 4,
+ "timestamp": "2026-03-25T14:21:16.903291+00:00",
+ "checkpoint": "checkpoints/r42_1500M.pkl",
+ "architecture": "simba_aux",
+ "model_checkpoint": "r42_1500M.pkl",
+ "model_architecture": "simba_aux",
+ "result": "human_win",
+ "final_scores": [
+  8,
+  0
+ ],
+ "total_turns": 18,
+ "actions": [
+  {
+   "turn": 0,
+   "player": -1,
+   "phase": "draw",
+   "action": -1,
+   "action_desc": "Initial deal",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     33,
+     17,
+     37,
+     51,
+     18,
+     25,
+     23
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     7,
+     29,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44
+   ],
+   "discard_size": 1,
+   "stock_remaining": 31,
+   "deadwood": [
+    75,
+    62
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 1,
+   "player": 1,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Model drew from stock",
+   "card_drawn": 4,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     33,
+     17,
+     37,
+     51,
+     18,
+     25,
+     23
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     7,
+     29,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44
+   ],
+   "discard_size": 1,
+   "stock_remaining": 31,
+   "deadwood": [
+    75,
+    62
+   ],
+   "model_logits": [
+    0.09325987845659256,
+    -0.087431900203228,
+    -0.5688839554786682,
+    -0.06865032762289047,
+    -2.5005149841308594,
+    -4.514980316162109,
+    -0.9133586883544922,
+    1.1016803979873657,
+    1.1803399324417114,
+    2.8836007118225098,
+    3.5052731037139893,
+    0.17142173647880554,
+    -4.690744400024414,
+    1.8572735786437988,
+    -3.2495574951171875,
+    14.289706230163574
+   ],
+   "model_value": 0.32534098625183105,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 2,
+   "player": 1,
+   "phase": "discard",
+   "action": 12,
+   "action_desc": "Model discarded 5\u2660",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     33,
+     17,
+     37,
+     51,
+     18,
+     25,
+     23
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     7,
+     29,
+     14,
+     0,
+     4
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    44
+   ],
+   "discard_size": 1,
+   "stock_remaining": 30,
+   "deadwood": [
+    75,
+    67
+   ],
+   "model_logits": [
+    3.417013168334961,
+    -3.4077160358428955,
+    -5.001515865325928,
+    -0.009092236869037151,
+    -2.6918270587921143,
+    -3.870602607727051,
+    -3.5438337326049805,
+    -2.014331579208374,
+    1.7961392402648926,
+    4.180337429046631,
+    4.018463134765625,
+    -1.7526929378509521,
+    4.605531215667725,
+    2.3439955711364746,
+    -3.8578248023986816,
+    13.765121459960938
+   ],
+   "model_value": 0.3130495548248291,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 3,
+   "player": 0,
+   "phase": "draw",
+   "action": 1,
+   "action_desc": "Human drew 5\u2660 from discard",
+   "card_drawn": 4,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     33,
+     17,
+     37,
+     51,
+     18,
+     25,
+     23
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     7,
+     29,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    4
+   ],
+   "discard_size": 2,
+   "stock_remaining": 30,
+   "deadwood": [
+    75,
+    62
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 4,
+   "player": 0,
+   "phase": "discard",
+   "action": 8,
+   "action_desc": "Human discarded K\u2663",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     33,
+     17,
+     37,
+     51,
+     18,
+     25,
+     23,
+     4
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     7,
+     29,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    44
+   ],
+   "discard_size": 1,
+   "stock_remaining": 30,
+   "deadwood": [
+    62,
+    62
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 5,
+   "player": 1,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Model drew from stock",
+   "card_drawn": 36,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     33,
+     17,
+     37,
+     4,
+     18,
+     25,
+     23
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     7,
+     29,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51
+   ],
+   "discard_size": 2,
+   "stock_remaining": 30,
+   "deadwood": [
+    52,
+    62
+   ],
+   "model_logits": [
+    5.197052478790283,
+    -5.18112325668335,
+    -2.769796371459961,
+    -0.8118061423301697,
+    -0.5535638332366943,
+    -7.104782581329346,
+    -2.2658491134643555,
+    0.2758958339691162,
+    2.0152428150177,
+    3.033750057220459,
+    2.8243067264556885,
+    0.27645158767700195,
+    3.9991893768310547,
+    0.7301002740859985,
+    -2.4215526580810547,
+    15.506138801574707
+   ],
+   "model_value": 0.165588840842247,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 6,
+   "player": 1,
+   "phase": "discard",
+   "action": 8,
+   "action_desc": "Model discarded 8\u2660",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     33,
+     17,
+     37,
+     4,
+     18,
+     25,
+     23
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     7,
+     29,
+     14,
+     0,
+     36
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    44,
+    51
+   ],
+   "discard_size": 2,
+   "stock_remaining": 29,
+   "deadwood": [
+    52,
+    72
+   ],
+   "model_logits": [
+    -0.32122141122817993,
+    0.3406141698360443,
+    -5.724595546722412,
+    -4.194174289703369,
+    -3.1780011653900146,
+    -2.937650680541992,
+    -0.8163458704948425,
+    1.94199538230896,
+    3.5510947704315186,
+    4.117539882659912,
+    1.6936264038085938,
+    -1.9613864421844482,
+    1.4538295269012451,
+    5.999101638793945,
+    -7.209649085998535,
+    11.982159614562988
+   ],
+   "model_value": 0.3117015063762665,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 7,
+   "player": 0,
+   "phase": "draw",
+   "action": 1,
+   "action_desc": "Human drew 8\u2660 from discard",
+   "card_drawn": 7,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     33,
+     17,
+     37,
+     4,
+     18,
+     25,
+     23
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     36,
+     29,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    7
+   ],
+   "discard_size": 3,
+   "stock_remaining": 29,
+   "deadwood": [
+    52,
+    64
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 8,
+   "player": 0,
+   "phase": "discard",
+   "action": 7,
+   "action_desc": "Human discarded Q\u2666",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     33,
+     17,
+     37,
+     4,
+     18,
+     25,
+     23,
+     7
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     36,
+     29,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51
+   ],
+   "discard_size": 2,
+   "stock_remaining": 29,
+   "deadwood": [
+    52,
+    64
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 9,
+   "player": 1,
+   "phase": "draw",
+   "action": 1,
+   "action_desc": "Model drew Q\u2666 from discard",
+   "card_drawn": 37,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     33,
+     17,
+     7,
+     4,
+     18,
+     25,
+     23
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     36,
+     29,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    37
+   ],
+   "discard_size": 3,
+   "stock_remaining": 29,
+   "deadwood": [
+    42,
+    64
+   ],
+   "model_logits": [
+    -24.1959228515625,
+    24.210447311401367,
+    -1.0009433031082153,
+    -2.5308589935302734,
+    1.8285845518112183,
+    -2.4441871643066406,
+    -0.4872193932533264,
+    -2.541861057281494,
+    1.9330122470855713,
+    -0.7277585864067078,
+    0.5597188472747803,
+    0.2730743885040283,
+    -9.375678062438965,
+    -1.695233702659607,
+    2.0203540325164795,
+    2.025934934616089
+   ],
+   "model_value": 0.186870738863945,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 10,
+   "player": 1,
+   "phase": "discard",
+   "action": 9,
+   "action_desc": "Model discarded 4\u2666",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     33,
+     17,
+     7,
+     4,
+     18,
+     25,
+     23
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     36,
+     29,
+     14,
+     0,
+     37
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    44,
+    51
+   ],
+   "discard_size": 2,
+   "stock_remaining": 29,
+   "deadwood": [
+    42,
+    44
+   ],
+   "model_logits": [
+    -3.7748053073883057,
+    3.7913267612457275,
+    2.5602798461914062,
+    3.7133896350860596,
+    -12.48697566986084,
+    3.3832638263702393,
+    3.0778608322143555,
+    4.574680328369141,
+    -17.03318214416504,
+    6.318802356719971,
+    7.165841102600098,
+    2.709026575088501,
+    -11.156314849853516,
+    1.7774165868759155,
+    -2.1440062522888184,
+    6.494228363037109
+   ],
+   "model_value": 0.31523439288139343,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 11,
+   "player": 0,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Human drew from stock",
+   "card_drawn": 49,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     33,
+     17,
+     7,
+     4,
+     18,
+     25,
+     23
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29
+   ],
+   "discard_size": 3,
+   "stock_remaining": 29,
+   "deadwood": [
+    42,
+    40
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 12,
+   "player": 0,
+   "phase": "discard",
+   "action": 12,
+   "action_desc": "Human discarded J\u2663",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     33,
+     17,
+     7,
+     4,
+     18,
+     25,
+     23,
+     49
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29
+   ],
+   "discard_size": 3,
+   "stock_remaining": 28,
+   "deadwood": [
+    52,
+    40
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 13,
+   "player": 1,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Model drew from stock",
+   "card_drawn": 3,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     33,
+     17,
+     7,
+     4,
+     18,
+     25,
+     23
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49
+   ],
+   "discard_size": 4,
+   "stock_remaining": 28,
+   "deadwood": [
+    42,
+    40
+   ],
+   "model_logits": [
+    5.435916423797607,
+    -5.450207233428955,
+    3.107023000717163,
+    2.9311065673828125,
+    -7.157114505767822,
+    -0.09724774211645126,
+    4.413162708282471,
+    1.8900127410888672,
+    -9.952603340148926,
+    -8.317371368408203,
+    3.3269364833831787,
+    2.0887064933776855,
+    4.783175945281982,
+    2.314573049545288,
+    -3.9845399856567383,
+    14.989801406860352
+   ],
+   "model_value": 0.2417949140071869,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 14,
+   "player": 1,
+   "phase": "discard",
+   "action": 12,
+   "action_desc": "Model discarded 4\u2660",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     33,
+     17,
+     7,
+     4,
+     18,
+     25,
+     23
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0,
+     3
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49
+   ],
+   "discard_size": 4,
+   "stock_remaining": 27,
+   "deadwood": [
+    42,
+    44
+   ],
+   "model_logits": [
+    1.3572660684585571,
+    -1.3808159828186035,
+    2.8994479179382324,
+    1.6390485763549805,
+    -11.19175910949707,
+    2.5846855640411377,
+    2.7333574295043945,
+    1.3355464935302734,
+    -15.045228004455566,
+    -12.471461296081543,
+    2.690511465072632,
+    2.2058544158935547,
+    16.3038272857666,
+    1.5606690645217896,
+    -2.86368989944458,
+    11.665703773498535
+   ],
+   "model_value": 0.2911173105239868,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 15,
+   "player": 0,
+   "phase": "draw",
+   "action": 1,
+   "action_desc": "Human drew 4\u2660 from discard",
+   "card_drawn": 3,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     33,
+     17,
+     7,
+     4,
+     18,
+     25,
+     23
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    3
+   ],
+   "discard_size": 5,
+   "stock_remaining": 27,
+   "deadwood": [
+    42,
+    40
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 16,
+   "player": 0,
+   "phase": "discard",
+   "action": 5,
+   "action_desc": "Human discarded 8\u2666",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     33,
+     17,
+     7,
+     4,
+     18,
+     25,
+     23,
+     3
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49
+   ],
+   "discard_size": 4,
+   "stock_remaining": 27,
+   "deadwood": [
+    39,
+    40
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 17,
+   "player": 1,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Model drew from stock",
+   "card_drawn": 13,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     25,
+     23
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33
+   ],
+   "discard_size": 5,
+   "stock_remaining": 27,
+   "deadwood": [
+    31,
+    40
+   ],
+   "model_logits": [
+    8.066147804260254,
+    -8.0846529006958,
+    9.601375579833984,
+    6.709384441375732,
+    -6.27523946762085,
+    4.711665153503418,
+    5.822248935699463,
+    0.8416484594345093,
+    -11.963319778442383,
+    -9.035999298095703,
+    -0.22975727915763855,
+    -0.3294707238674164,
+    1.2679355144500732,
+    2.0494441986083984,
+    -3.489938735961914,
+    12.807523727416992
+   ],
+   "model_value": 0.16435781121253967,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 18,
+   "player": 1,
+   "phase": "discard",
+   "action": 2,
+   "action_desc": "Model discarded 9\u2665",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     25,
+     23
+    ],
+    [
+     21,
+     19,
+     38,
+     47,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0,
+     13
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33
+   ],
+   "discard_size": 5,
+   "stock_remaining": 26,
+   "deadwood": [
+    31,
+    41
+   ],
+   "model_logits": [
+    -2.77071213722229,
+    2.749574661254883,
+    12.901314735412598,
+    10.536663055419922,
+    -10.191338539123535,
+    10.192569732666016,
+    9.449311256408691,
+    0.58781898021698,
+    -16.14435577392578,
+    -12.884576797485352,
+    -3.6686058044433594,
+    -2.897615909576416,
+    -3.726410150527954,
+    1.92379629611969,
+    -2.3426313400268555,
+    5.508289813995361
+   ],
+   "model_value": 0.1654054969549179,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 19,
+   "player": 0,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Human drew from stock",
+   "card_drawn": 31,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     25,
+     23
+    ],
+    [
+     13,
+     19,
+     38,
+     47,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21
+   ],
+   "discard_size": 6,
+   "stock_remaining": 26,
+   "deadwood": [
+    31,
+    32
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 20,
+   "player": 0,
+   "phase": "discard",
+   "action": 10,
+   "action_desc": "Human discarded K\u2665",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     25,
+     23,
+     31
+    ],
+    [
+     13,
+     19,
+     38,
+     47,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21
+   ],
+   "discard_size": 6,
+   "stock_remaining": 25,
+   "deadwood": [
+    37,
+    32
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 21,
+   "player": 1,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Model drew from stock",
+   "card_drawn": 1,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     23
+    ],
+    [
+     13,
+     19,
+     38,
+     47,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25
+   ],
+   "discard_size": 7,
+   "stock_remaining": 25,
+   "deadwood": [
+    27,
+    32
+   ],
+   "model_logits": [
+    6.26929235458374,
+    -6.2877702713012695,
+    -0.0012273131869733334,
+    5.2356743812561035,
+    -5.459696292877197,
+    11.210075378417969,
+    6.015535831451416,
+    2.988128185272217,
+    -12.3079252243042,
+    -7.972535610198975,
+    -0.8080845475196838,
+    -0.3211536407470703,
+    0.16582894325256348,
+    0.542965292930603,
+    -1.9980934858322144,
+    13.446394920349121
+   ],
+   "model_value": 0.1807677000761032,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 22,
+   "player": 1,
+   "phase": "discard",
+   "action": 5,
+   "action_desc": "Model discarded 9\u2663",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     23
+    ],
+    [
+     13,
+     19,
+     38,
+     47,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0,
+     1
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25
+   ],
+   "discard_size": 7,
+   "stock_remaining": 24,
+   "deadwood": [
+    27,
+    34
+   ],
+   "model_logits": [
+    -4.491512775421143,
+    4.460123062133789,
+    -2.2431042194366455,
+    9.859258651733398,
+    -9.673826217651367,
+    19.081336975097656,
+    7.023276329040527,
+    4.194875240325928,
+    -17.16871452331543,
+    -10.632189750671387,
+    -2.711754560470581,
+    -4.07654333114624,
+    -1.7465616464614868,
+    0.35864073038101196,
+    -0.7489283680915833,
+    5.912528038024902
+   ],
+   "model_value": 0.25027400255203247,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 23,
+   "player": 0,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Human drew from stock",
+   "card_drawn": 46,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     23
+    ],
+    [
+     13,
+     19,
+     38,
+     1,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25,
+    47
+   ],
+   "discard_size": 8,
+   "stock_remaining": 24,
+   "deadwood": [
+    27,
+    25
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 24,
+   "player": 0,
+   "phase": "discard",
+   "action": 11,
+   "action_desc": "Human discarded J\u2665",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     23,
+     46
+    ],
+    [
+     13,
+     19,
+     38,
+     1,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25,
+    47
+   ],
+   "discard_size": 8,
+   "stock_remaining": 23,
+   "deadwood": [
+    35,
+    25
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 25,
+   "player": 1,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Model drew from stock",
+   "card_drawn": 11,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     46
+    ],
+    [
+     13,
+     19,
+     38,
+     1,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25,
+    47,
+    23
+   ],
+   "discard_size": 9,
+   "stock_remaining": 23,
+   "deadwood": [
+    25,
+    25
+   ],
+   "model_logits": [
+    10.157042503356934,
+    -10.170555114746094,
+    0.7261695265769958,
+    7.496785640716553,
+    -7.870490074157715,
+    0.6724360585212708,
+    11.823999404907227,
+    3.638632297515869,
+    -10.330878257751465,
+    -8.757818222045898,
+    -0.029917217791080475,
+    1.5304876565933228,
+    2.7648935317993164,
+    1.7297470569610596,
+    -3.4055967330932617,
+    13.965205192565918
+   ],
+   "model_value": 0.2112925946712494,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 26,
+   "player": 1,
+   "phase": "discard",
+   "action": 12,
+   "action_desc": "Model discarded Q\u2660",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     46
+    ],
+    [
+     13,
+     19,
+     38,
+     1,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0,
+     11
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25,
+    47,
+    23
+   ],
+   "discard_size": 9,
+   "stock_remaining": 22,
+   "deadwood": [
+    25,
+    35
+   ],
+   "model_logits": [
+    4.846325874328613,
+    -4.868699550628662,
+    -0.11475139111280441,
+    8.090211868286133,
+    -11.844910621643066,
+    -1.5905108451843262,
+    10.211276054382324,
+    2.7191364765167236,
+    -13.504241943359375,
+    -11.84048080444336,
+    -2.415240526199341,
+    -1.146047592163086,
+    18.196413040161133,
+    8.024925231933594,
+    -9.367064476013184,
+    10.640433311462402
+   ],
+   "model_value": 0.3169029951095581,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 27,
+   "player": 0,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Human drew from stock",
+   "card_drawn": 10,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     46
+    ],
+    [
+     13,
+     19,
+     38,
+     1,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25,
+    47,
+    23,
+    11
+   ],
+   "discard_size": 10,
+   "stock_remaining": 22,
+   "deadwood": [
+    25,
+    25
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 28,
+   "player": 0,
+   "phase": "discard",
+   "action": 12,
+   "action_desc": "Human discarded J\u2660",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     46,
+     10
+    ],
+    [
+     13,
+     19,
+     38,
+     1,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25,
+    47,
+    23,
+    11
+   ],
+   "discard_size": 10,
+   "stock_remaining": 21,
+   "deadwood": [
+    35,
+    25
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 29,
+   "player": 1,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Model drew from stock",
+   "card_drawn": 34,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     46
+    ],
+    [
+     13,
+     19,
+     38,
+     1,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25,
+    47,
+    23,
+    11,
+    10
+   ],
+   "discard_size": 11,
+   "stock_remaining": 21,
+   "deadwood": [
+    25,
+    25
+   ],
+   "model_logits": [
+    8.433442115783691,
+    -8.445843696594238,
+    0.2269468605518341,
+    8.16739273071289,
+    -8.541677474975586,
+    0.7132872939109802,
+    11.54711627960205,
+    3.1492228507995605,
+    -9.632174491882324,
+    -8.679957389831543,
+    -0.501717209815979,
+    1.9759103059768677,
+    2.1433303356170654,
+    1.842934489250183,
+    -3.460728645324707,
+    13.90916919708252
+   ],
+   "model_value": 0.226350337266922,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 30,
+   "player": 1,
+   "phase": "discard",
+   "action": 12,
+   "action_desc": "Model discarded 9\u2666",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     46
+    ],
+    [
+     13,
+     19,
+     38,
+     1,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0,
+     34
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25,
+    47,
+    23,
+    11,
+    10
+   ],
+   "discard_size": 11,
+   "stock_remaining": 20,
+   "deadwood": [
+    25,
+    34
+   ],
+   "model_logits": [
+    5.0039753913879395,
+    -5.023728370666504,
+    -1.5188764333724976,
+    8.051513671875,
+    -12.160207748413086,
+    -1.6672836542129517,
+    8.416703224182129,
+    0.8420174717903137,
+    -11.68520450592041,
+    -11.156301498413086,
+    -1.8939532041549683,
+    -1.459132194519043,
+    20.891910552978516,
+    8.046717643737793,
+    -9.465716361999512,
+    11.172394752502441
+   ],
+   "model_value": 0.3114898204803467,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 31,
+   "player": 0,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Human drew from stock",
+   "card_drawn": 24,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     46
+    ],
+    [
+     13,
+     19,
+     38,
+     1,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25,
+    47,
+    23,
+    11,
+    10,
+    34
+   ],
+   "discard_size": 12,
+   "stock_remaining": 20,
+   "deadwood": [
+    25,
+    25
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 32,
+   "player": 0,
+   "phase": "discard",
+   "action": 12,
+   "action_desc": "Human discarded Q\u2665",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     46,
+     24
+    ],
+    [
+     13,
+     19,
+     38,
+     1,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25,
+    47,
+    23,
+    11,
+    10,
+    34
+   ],
+   "discard_size": 12,
+   "stock_remaining": 19,
+   "deadwood": [
+    35,
+    25
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 33,
+   "player": 1,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Model drew from stock",
+   "card_drawn": 27,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     46
+    ],
+    [
+     13,
+     19,
+     38,
+     1,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25,
+    47,
+    23,
+    11,
+    10,
+    34,
+    24
+   ],
+   "discard_size": 13,
+   "stock_remaining": 19,
+   "deadwood": [
+    25,
+    25
+   ],
+   "model_logits": [
+    9.665902137756348,
+    -9.677483558654785,
+    0.6676115393638611,
+    7.765767574310303,
+    -7.992070198059082,
+    0.6821295022964478,
+    12.180002212524414,
+    2.483808755874634,
+    -8.4148530960083,
+    -8.724776268005371,
+    -0.7120273113250732,
+    1.5324976444244385,
+    2.654120445251465,
+    1.5488325357437134,
+    -3.1580612659454346,
+    13.590743064880371
+   ],
+   "model_value": 0.19069039821624756,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 34,
+   "player": 1,
+   "phase": "discard",
+   "action": 3,
+   "action_desc": "Model discarded 7\u2665",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     46
+    ],
+    [
+     13,
+     19,
+     38,
+     1,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0,
+     27
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25,
+    47,
+    23,
+    11,
+    10,
+    34,
+    24
+   ],
+   "discard_size": 13,
+   "stock_remaining": 18,
+   "deadwood": [
+    25,
+    21
+   ],
+   "model_logits": [
+    1.4226794242858887,
+    -1.4492957592010498,
+    0.5585522055625916,
+    16.642166137695312,
+    -15.224808692932129,
+    -0.010581095702946186,
+    15.518430709838867,
+    7.496588230133057,
+    -15.361716270446777,
+    -15.838196754455566,
+    -0.8002575039863586,
+    1.2340660095214844,
+    2.604884147644043,
+    0.6524441838264465,
+    -1.1755698919296265,
+    4.939535617828369
+   ],
+   "model_value": 0.3216603994369507,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 35,
+   "player": 0,
+   "phase": "draw",
+   "action": 1,
+   "action_desc": "Human drew 7\u2665 from discard",
+   "card_drawn": 19,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     46
+    ],
+    [
+     13,
+     27,
+     38,
+     1,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25,
+    47,
+    23,
+    11,
+    10,
+    34,
+    24,
+    19
+   ],
+   "discard_size": 14,
+   "stock_remaining": 18,
+   "deadwood": [
+    25,
+    14
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 36,
+   "player": 0,
+   "phase": "discard",
+   "action": 11,
+   "action_desc": "Human discarded 8\u2663",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     46,
+     19
+    ],
+    [
+     13,
+     27,
+     38,
+     1,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25,
+    47,
+    23,
+    11,
+    10,
+    34,
+    24
+   ],
+   "discard_size": 13,
+   "stock_remaining": 18,
+   "deadwood": [
+    14,
+    14
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 37,
+   "player": 0,
+   "phase": "knock_decision",
+   "action": 14,
+   "action_desc": "Human knocked",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     19
+    ],
+    [
+     13,
+     27,
+     38,
+     1,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25,
+    47,
+    23,
+    11,
+    10,
+    34,
+    24,
+    46
+   ],
+   "discard_size": 14,
+   "stock_remaining": 18,
+   "deadwood": [
+    6,
+    14
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 38,
+   "player": -1,
+   "phase": "game_over",
+   "action": -1,
+   "action_desc": "Game over.",
+   "card_drawn": null,
+   "hands": [
+    [
+     5,
+     2,
+     6,
+     3,
+     17,
+     7,
+     4,
+     18,
+     31,
+     19
+    ],
+    [
+     13,
+     27,
+     38,
+     1,
+     45,
+     43,
+     36,
+     37,
+     14,
+     0
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    44,
+    51,
+    29,
+    49,
+    33,
+    21,
+    25,
+    47,
+    23,
+    11,
+    10,
+    34,
+    24,
+    46
+   ],
+   "discard_size": 14,
+   "stock_remaining": 18,
+   "deadwood": [
+    6,
+    14
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  }
+ ]
+}