Upload human_games/game_20260325_141856_3.json with huggingface_hub

human_games/game_20260325_141856_3.json

@@ -0,0 +1,917 @@
+{
+ "game_number": 3,
+ "timestamp": "2026-03-25T14:18:56.604934+00:00",
+ "checkpoint": "checkpoints/r42_1500M.pkl",
+ "architecture": "simba_aux",
+ "model_checkpoint": "r42_1500M.pkl",
+ "model_architecture": "simba_aux",
+ "result": "human_win",
+ "final_scores": [
+  38,
+  0
+ ],
+ "total_turns": 6,
+ "actions": [
+  {
+   "turn": 0,
+   "player": -1,
+   "phase": "draw",
+   "action": -1,
+   "action_desc": "Initial deal",
+   "card_drawn": null,
+   "hands": [
+    [
+     51,
+     8,
+     6,
+     5,
+     15,
+     1,
+     40,
+     20,
+     41,
+     0
+    ],
+    [
+     50,
+     31,
+     35,
+     23,
+     26,
+     10,
+     34,
+     38,
+     13,
+     11
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    14
+   ],
+   "discard_size": 1,
+   "stock_remaining": 31,
+   "deadwood": [
+    51,
+    77
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 1,
+   "player": 1,
+   "phase": "draw",
+   "action": 1,
+   "action_desc": "Model drew 2\u2665 from discard",
+   "card_drawn": 14,
+   "hands": [
+    [
+     51,
+     8,
+     6,
+     5,
+     15,
+     1,
+     40,
+     20,
+     41,
+     0
+    ],
+    [
+     50,
+     31,
+     35,
+     23,
+     26,
+     10,
+     34,
+     38,
+     13,
+     11
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    14
+   ],
+   "discard_size": 1,
+   "stock_remaining": 31,
+   "deadwood": [
+    51,
+    77
+   ],
+   "model_logits": [
+    -2.179316759109497,
+    2.1689205169677734,
+    -0.7507094740867615,
+    2.689263105392456,
+    -1.6090465784072876,
+    -2.3403196334838867,
+    1.2583497762680054,
+    -11.310918807983398,
+    0.023658961057662964,
+    3.2385363578796387,
+    3.1845920085906982,
+    -5.17340612411499,
+    2.6762375831604004,
+    0.8319200873374939,
+    -2.242178440093994,
+    12.762957572937012
+   ],
+   "model_value": 0.3390149772167206,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 2,
+   "player": 1,
+   "phase": "discard",
+   "action": 9,
+   "action_desc": "Model discarded K\u2666",
+   "card_drawn": null,
+   "hands": [
+    [
+     51,
+     8,
+     6,
+     5,
+     15,
+     1,
+     40,
+     20,
+     41,
+     0
+    ],
+    [
+     50,
+     31,
+     35,
+     23,
+     26,
+     10,
+     34,
+     38,
+     13,
+     11,
+     14
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [],
+   "discard_size": 0,
+   "stock_remaining": 31,
+   "deadwood": [
+    51,
+    79
+   ],
+   "model_logits": [
+    -0.5086246132850647,
+    0.4933563470840454,
+    -4.677019119262695,
+    3.740961790084839,
+    -1.706278920173645,
+    -0.89510577917099,
+    0.7171502709388733,
+    -8.997886657714844,
+    -0.5313340425491333,
+    2.589456558227539,
+    1.413824439048767,
+    -8.039081573486328,
+    8.278109550476074,
+    3.3399972915649414,
+    -4.720890045166016,
+    11.930136680603027
+   ],
+   "model_value": 0.4126838445663452,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 3,
+   "player": 0,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Human drew from stock",
+   "card_drawn": 7,
+   "hands": [
+    [
+     51,
+     8,
+     6,
+     5,
+     15,
+     1,
+     40,
+     20,
+     41,
+     0
+    ],
+    [
+     50,
+     31,
+     35,
+     23,
+     26,
+     10,
+     34,
+     14,
+     13,
+     11
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    38
+   ],
+   "discard_size": 1,
+   "stock_remaining": 31,
+   "deadwood": [
+    51,
+    69
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 4,
+   "player": 0,
+   "phase": "discard",
+   "action": 2,
+   "action_desc": "Human discarded K\u2663",
+   "card_drawn": null,
+   "hands": [
+    [
+     51,
+     8,
+     6,
+     5,
+     15,
+     1,
+     40,
+     20,
+     41,
+     0,
+     7
+    ],
+    [
+     50,
+     31,
+     35,
+     23,
+     26,
+     10,
+     34,
+     14,
+     13,
+     11
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    38
+   ],
+   "discard_size": 1,
+   "stock_remaining": 30,
+   "deadwood": [
+    29,
+    69
+   ],
+   "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": 48,
+   "hands": [
+    [
+     7,
+     8,
+     6,
+     5,
+     15,
+     1,
+     40,
+     20,
+     41,
+     0
+    ],
+    [
+     50,
+     31,
+     35,
+     23,
+     26,
+     10,
+     34,
+     14,
+     13,
+     11
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    38,
+    51
+   ],
+   "discard_size": 2,
+   "stock_remaining": 30,
+   "deadwood": [
+    19,
+    69
+   ],
+   "model_logits": [
+    6.998260974884033,
+    -7.001339912414551,
+    -0.564143717288971,
+    2.677340030670166,
+    -2.441758155822754,
+    -1.4348958730697632,
+    1.405638337135315,
+    -10.40619945526123,
+    0.8527387380599976,
+    0.882925808429718,
+    0.8208208084106445,
+    -1.9499595165252686,
+    8.245833396911621,
+    3.7369155883789062,
+    -5.5609917640686035,
+    15.164470672607422
+   ],
+   "model_value": 0.3300398588180542,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 6,
+   "player": 1,
+   "phase": "discard",
+   "action": 3,
+   "action_desc": "Model discarded 6\u2666",
+   "card_drawn": null,
+   "hands": [
+    [
+     7,
+     8,
+     6,
+     5,
+     15,
+     1,
+     40,
+     20,
+     41,
+     0
+    ],
+    [
+     50,
+     31,
+     35,
+     23,
+     26,
+     10,
+     34,
+     14,
+     13,
+     11,
+     48
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    38,
+    51
+   ],
+   "discard_size": 2,
+   "stock_remaining": 29,
+   "deadwood": [
+    19,
+    79
+   ],
+   "model_logits": [
+    -0.9781932830810547,
+    0.9889533519744873,
+    -4.856568813323975,
+    5.682194232940674,
+    -7.957631587982178,
+    0.06896070390939713,
+    0.5953248143196106,
+    -9.917901992797852,
+    5.767940044403076,
+    5.3669209480285645,
+    4.093746185302734,
+    -8.548243522644043,
+    1.2511438131332397,
+    4.427976608276367,
+    -5.39259147644043,
+    9.533227920532227
+   ],
+   "model_value": 0.3848801255226135,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 7,
+   "player": 0,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Human drew from stock",
+   "card_drawn": 30,
+   "hands": [
+    [
+     7,
+     8,
+     6,
+     5,
+     15,
+     1,
+     40,
+     20,
+     41,
+     0
+    ],
+    [
+     50,
+     48,
+     35,
+     23,
+     26,
+     10,
+     34,
+     14,
+     13,
+     11
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    38,
+    51,
+    31
+   ],
+   "discard_size": 3,
+   "stock_remaining": 29,
+   "deadwood": [
+    19,
+    73
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 8,
+   "player": 0,
+   "phase": "discard",
+   "action": 9,
+   "action_desc": "Human discarded 8\u2665",
+   "card_drawn": null,
+   "hands": [
+    [
+     7,
+     8,
+     6,
+     5,
+     15,
+     1,
+     40,
+     20,
+     41,
+     0,
+     30
+    ],
+    [
+     50,
+     48,
+     35,
+     23,
+     26,
+     10,
+     34,
+     14,
+     13,
+     11
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    38,
+    51,
+    31
+   ],
+   "discard_size": 3,
+   "stock_remaining": 28,
+   "deadwood": [
+    24,
+    73
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 9,
+   "player": 1,
+   "phase": "draw",
+   "action": 0,
+   "action_desc": "Model drew from stock",
+   "card_drawn": 33,
+   "hands": [
+    [
+     7,
+     8,
+     6,
+     5,
+     15,
+     1,
+     40,
+     30,
+     41,
+     0
+    ],
+    [
+     50,
+     48,
+     35,
+     23,
+     26,
+     10,
+     34,
+     14,
+     13,
+     11
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    38,
+    51,
+    31,
+    20
+   ],
+   "discard_size": 4,
+   "stock_remaining": 28,
+   "deadwood": [
+    16,
+    73
+   ],
+   "model_logits": [
+    10.287674903869629,
+    -10.301124572753906,
+    4.379702091217041,
+    2.5685834884643555,
+    -2.095125913619995,
+    1.1033971309661865,
+    2.508603811264038,
+    -4.717192649841309,
+    -0.3479848802089691,
+    -3.8086419105529785,
+    -1.1612685918807983,
+    -1.1774158477783203,
+    5.276021480560303,
+    4.511486053466797,
+    -6.141311168670654,
+    13.272911071777344
+   ],
+   "model_value": 0.2225799411535263,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 10,
+   "player": 1,
+   "phase": "discard",
+   "action": 2,
+   "action_desc": "Model discarded Q\u2663",
+   "card_drawn": null,
+   "hands": [
+    [
+     7,
+     8,
+     6,
+     5,
+     15,
+     1,
+     40,
+     30,
+     41,
+     0
+    ],
+    [
+     50,
+     48,
+     35,
+     23,
+     26,
+     10,
+     34,
+     14,
+     13,
+     11,
+     33
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    11
+   ],
+   "discard_pile": [
+    38,
+    51,
+    31,
+    20
+   ],
+   "discard_size": 4,
+   "stock_remaining": 27,
+   "deadwood": [
+    16,
+    54
+   ],
+   "model_logits": [
+    -4.684987545013428,
+    4.683658123016357,
+    9.303412437438965,
+    7.45818567276001,
+    -17.655288696289062,
+    8.484724998474121,
+    0.06476521492004395,
+    -0.2480982095003128,
+    -5.369117736816406,
+    -0.9855579137802124,
+    0.8280546069145203,
+    1.8773013353347778,
+    -11.004522323608398,
+    3.2657418251037598,
+    -3.5020692348480225,
+    4.9674763679504395
+   ],
+   "model_value": 0.26370999217033386,
+   "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": 39,
+   "hands": [
+    [
+     7,
+     8,
+     6,
+     5,
+     15,
+     1,
+     40,
+     30,
+     41,
+     0
+    ],
+    [
+     33,
+     48,
+     35,
+     23,
+     26,
+     10,
+     34,
+     14,
+     13,
+     11
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    38,
+    51,
+    31,
+    20,
+    50
+   ],
+   "discard_size": 5,
+   "stock_remaining": 27,
+   "deadwood": [
+    16,
+    44
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 12,
+   "player": 0,
+   "phase": "discard",
+   "action": 9,
+   "action_desc": "Human discarded 5\u2666",
+   "card_drawn": null,
+   "hands": [
+    [
+     7,
+     8,
+     6,
+     5,
+     15,
+     1,
+     40,
+     30,
+     41,
+     0,
+     39
+    ],
+    [
+     33,
+     48,
+     35,
+     23,
+     26,
+     10,
+     34,
+     14,
+     13,
+     11
+    ]
+   ],
+   "hand_sizes": [
+    11,
+    10
+   ],
+   "discard_pile": [
+    38,
+    51,
+    31,
+    20,
+    50
+   ],
+   "discard_size": 5,
+   "stock_remaining": 26,
+   "deadwood": [
+    11,
+    44
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 13,
+   "player": 0,
+   "phase": "knock_decision",
+   "action": 14,
+   "action_desc": "Human knocked",
+   "card_drawn": null,
+   "hands": [
+    [
+     7,
+     8,
+     6,
+     5,
+     15,
+     1,
+     40,
+     39,
+     41,
+     0
+    ],
+    [
+     33,
+     48,
+     35,
+     23,
+     26,
+     10,
+     34,
+     14,
+     13,
+     11
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    38,
+    51,
+    31,
+    20,
+    50,
+    30
+   ],
+   "discard_size": 6,
+   "stock_remaining": 26,
+   "deadwood": [
+    6,
+    44
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  },
+  {
+   "turn": 14,
+   "player": -1,
+   "phase": "game_over",
+   "action": -1,
+   "action_desc": "Game over.",
+   "card_drawn": null,
+   "hands": [
+    [
+     7,
+     8,
+     6,
+     5,
+     15,
+     1,
+     40,
+     39,
+     41,
+     0
+    ],
+    [
+     33,
+     48,
+     35,
+     23,
+     26,
+     10,
+     34,
+     14,
+     13,
+     11
+    ]
+   ],
+   "hand_sizes": [
+    10,
+    10
+   ],
+   "discard_pile": [
+    38,
+    51,
+    31,
+    20,
+    50,
+    30
+   ],
+   "discard_size": 6,
+   "stock_remaining": 26,
+   "deadwood": [
+    6,
+    44
+   ],
+   "model_logits": null,
+   "model_value": null,
+   "model_checkpoint": "r42_1500M.pkl",
+   "model_architecture": "simba_aux"
+  }
+ ]
+}