Files
qwen2.5-1.5b-24game-grpo/results/countdown_zeroshot_sample16_summary.json
ModelHub XC a0f3248e4a 初始化项目,由ModelHub XC社区提供模型
Model: lxazjk/qwen2.5-1.5b-24game-grpo
Source: Original Platform
2026-08-22 12:19:16 +08:00

604 lines
23 KiB
JSON

{
"count": 100,
"solved": 11,
"solved_rate": 0.11,
"solved_at_n_count": 11,
"solved_at_n_rate": 0.11,
"pass_at_1_count": 0,
"pass_at_1_rate": 0.0,
"candidate_count_total": 1600,
"candidate_count_mean_per_problem": 16,
"num_samples_max": 16,
"num_samples_min": 16,
"reason_counts": {
"numbers are not used exactly once": 615,
"numbers must be positive integers": 32,
"empty expression": 20,
"ok": 19,
"contains disallowed characters": 13,
"value is 222, expected 88": 10,
"value is 88, expected 26": 10,
"unsupported expression node: UnaryOp": 9,
"value is 61, expected 75": 8,
"value is 32, expected 36": 8,
"value is 1664, expected 96": 7,
"value is 350, expected 26": 7,
"value is 840, expected 62": 7,
"value is 727, expected 87": 7,
"value is 99, expected 30": 6,
"value is 715, expected 78": 6,
"value is 225, expected 50": 6,
"value is 120, expected 32": 6,
"value is 992, expected 60": 6,
"value is 36, expected 20": 5,
"value is 483, expected 62": 5,
"value is 30, expected 26": 5,
"value is 895, expected 75": 5,
"value is 16.2608695652, expected 33": 5,
"value is 56, expected 22": 5,
"value is 4.5, expected 14": 5,
"value is 496, expected 100": 5,
"value is 310, expected 41": 5,
"value is 390, expected 43": 5,
"value is 192.705882353, expected 53": 5,
"value is 19.4520547945, expected 44": 4,
"value is 26.5, expected 76": 4,
"value is 270, expected 90": 4,
"value is 981, expected 17": 4,
"value is 228, expected 28": 4,
"value is 156, expected 98": 4,
"value is 960, expected 80": 4,
"value is 18.5454545455, expected 38": 4,
"value is 129, expected 65": 4,
"value is 102, expected 37": 4,
"value is 1600, expected 100": 4,
"value is 437, expected 45": 4,
"value is 1.14893617021, expected 15": 4,
"value is 324, expected 36": 4,
"value is 144, expected 14": 4,
"value is 722, expected 57": 4,
"value is 777, expected 59": 4,
"value is 830, expected 77": 3,
"value is 272, expected 17": 3,
"value is 3956, expected 76": 3,
"value is -260, expected 55": 3,
"value is 11.1538461538, expected 90": 3,
"value is 505, expected 100": 3,
"value is 72.8, expected 100": 3,
"value is 79, expected 17": 3,
"value is 279, expected 96": 3,
"value is 229.210526316, expected 92": 3,
"value is 624, expected 83": 3,
"value is -700, expected 53": 3,
"value is 1190, expected 53": 3,
"value is 819, expected 50": 3,
"value is 99, expected 80": 3,
"value is 27.7894736842, expected 90": 3,
"value is 218.75, expected 61": 3,
"value is 29.4444444444, expected 36": 3,
"value is 501, expected 83": 3,
"value is 183, expected 47": 3,
"value is 392, expected 45": 3,
"value is 798, expected 43": 3,
"value is 782, expected 11": 3,
"value is 143, expected 35": 3,
"value is 48, expected 35": 3,
"value is 15, expected 66": 3,
"value is 440, expected 15": 3,
"value is 154, expected 29": 3,
"value is 40.25, expected 22": 3,
"value is 1900, expected 51": 3,
"value is 17.2307692308, expected 77": 2,
"value is 40, expected 44": 2,
"value is 5394, expected 96": 2,
"value is 40.5517241379, expected 96": 2,
"value is 99.8979591837, expected 96": 2,
"value is 4704.21428571, expected 96": 2,
"value is 139, expected 28": 2,
"value is 590, expected 76": 2,
"value is 50.92, expected 24": 2,
"value is 155.52, expected 24": 2,
"value is -1098, expected 90": 2,
"value is 23.6888888889, expected 90": 2,
"value is 90.8117647059, expected 48": 2,
"value is 924, expected 48": 2,
"value is 95.2409638554, expected 48": 2,
"value is 3572, expected 97": 2,
"value is 19.3968253968, expected 44": 2,
"value is 20.8387096774, expected 44": 2,
"value is 23.0322580645, expected 44": 2,
"value is 50.2597402597, expected 52": 2,
"value is 119, expected 52": 2,
"value is -210, expected 28": 2,
"value is 186, expected 28": 2,
"value is -8, expected 92": 2,
"value is 73, expected 92": 2,
"value is 241, expected 94": 2,
"value is 133, expected 94": 2,
"value is 546, expected 94": 2,
"value is 63, expected 28": 2,
"value is 294, expected 28": 2,
"value is 2714, expected 33": 2,
"value is 12.1764705882, expected 33": 2,
"value is 1080, expected 78": 2,
"value is 675, expected 83": 2,
"value is 1680, expected 83": 2,
"value is 138, expected 53": 2,
"value is 23, expected 65": 2,
"value is 1700, expected 65": 2,
"value is 26.3157894737, expected 14": 2,
"value is 75, expected 38": 2,
"value is 65.0833333333, expected 38": 2,
"value is 21, expected 38": 2,
"value is 456, expected 19": 2,
"value is 1650, expected 61": 2,
"value is 20.52, expected 61": 2,
"value is 3766.5, expected 65": 2,
"value is -1110, expected 65": 2,
"value is 49.5, expected 65": 2,
"value is 308, expected 58": 2,
"value is 26.6666666667, expected 58": 2,
"value is 1088, expected 58": 2,
"value is 36, expected 37": 2,
"value is -36, expected 37": 2,
"value is 701, expected 37": 2,
"value is 168, expected 91": 2,
"value is 1426, expected 100": 2,
"value is 2790, expected 36": 2,
"value is -2.4, expected 36": 2,
"value is -2660, expected 36": 2,
"value is 64, expected 47": 2,
"value is 736, expected 100": 2,
"value is 99, expected 59": 2,
"value is 2451, expected 96": 2,
"value is 1584, expected 15": 2,
"value is 80.1382978723, expected 15": 2,
"value is 34, expected 71": 2,
"value is 851, expected 29": 2,
"value is 40, expected 14": 2,
"value is 86, expected 14": 2,
"value is 359, expected 14": 2,
"value is -722, expected 57": 2,
"value is 27.3962264151, expected 30": 2,
"value is 451, expected 30": 2,
"value is 83.4339622642, expected 30": 2,
"value is 9.35, expected 24": 2,
"value is -21.0526315789, expected 24": 2,
"value is 1045, expected 26": 2,
"value is 52.1276595745, expected 26": 2,
"value is 28.085106383, expected 26": 2,
"value is -560, expected 26": 2,
"value is 71, expected 35": 2,
"value is 2494, expected 66": 2,
"value is 154, expected 66": 2,
"value is 46, expected 60": 2,
"value is 71.875, expected 22": 2,
"value is 1710, expected 83": 2,
"value is 3118, expected 83": 2,
"value is 153, expected 53": 2,
"value is 31.5714285714, expected 53": 2,
"value is 2568, expected 53": 2,
"value is -212, expected 78": 2,
"value is 96, expected 78": 2,
"value is 300, expected 87": 2,
"value is 17.902173913, expected 58": 2,
"value is 12.253164557, expected 51": 2,
"value is 5.61224489796, expected 51": 2,
"value is 452, expected 51": 2,
"value is 3454, expected 51": 2,
"value is 15, expected 92": 2,
"value is 252, expected 92": 2,
"value is 324, expected 92": 2,
"value is 32, expected 88": 1,
"value is 1290, expected 72": 1,
"value is 67, expected 71": 1,
"value is 1276, expected 77": 1,
"value is 47.8571428571, expected 77": 1,
"value is 4154, expected 77": 1,
"value is 204, expected 77": 1,
"value is 964, expected 77": 1,
"value is 8.35714285714, expected 77": 1,
"value is 93.8, expected 77": 1,
"value is 83, expected 77": 1,
"value is -74, expected 44": 1,
"value is 1203.33333333, expected 44": 1,
"value is 80.1666666667, expected 44": 1,
"value is 17.4025974026, expected 44": 1,
"value is 10, expected 44": 1,
"value is 4.12987012987, expected 44": 1,
"value is 72, expected 17": 1,
"value is 64, expected 17": 1,
"value is -13, expected 17": 1,
"value is 236.833333333, expected 96": 1,
"value is 44.9770114943, expected 96": 1,
"value is 146.274725275, expected 96": 1,
"value is 3826, expected 96": 1,
"value is 1606, expected 96": 1,
"value is 172, expected 96": 1,
"value is 2814, expected 96": 1,
"value is 1890, expected 66": 1,
"value is 23.2222222222, expected 66": 1,
"value is 79.9259259259, expected 28": 1,
"value is 27.7209302326, expected 76": 1,
"value is 313, expected 76": 1,
"value is 44.5, expected 76": 1,
"value is 504, expected 76": 1,
"value is 1689, expected 76": 1,
"value is 73.8873239437, expected 76": 1,
"value is 3358.77777778, expected 76": 1,
"value is 163, expected 55": 1,
"value is 225, expected 55": 1,
"value is 243, expected 55": 1,
"value is 36, expected 55": 1,
"value is 144, expected 55": 1,
"value is 632.888888889, expected 55": 1,
"value is 4895, expected 55": 1,
"value is 10, expected 24": 1,
"value is 93.4375, expected 24": 1,
"value is 26.5625, expected 24": 1,
"value is 111.4375, expected 24": 1,
"value is 825, expected 24": 1,
"value is 18.2153846154, expected 24": 1,
"value is 15.32, expected 24": 1,
"value is 3078.4, expected 24": 1,
"value is 1127, expected 24": 1,
"value is 94.08, expected 24": 1,
"value is 12.3076923077, expected 24": 1,
"value is 990, expected 90": 1,
"value is 12.4590163934, expected 90": 1,
"value is 1184.75555556, expected 90": 1,
"value is 47.2131147541, expected 90": 1,
"value is 74, expected 48": 1,
"value is 14774, expected 48": 1,
"value is 96, expected 48": 1,
"value is 746, expected 48": 1,
"value is 91, expected 48": 1,
"value is 747, expected 48": 1,
"value is 935, expected 48": 1,
"value is 186, expected 48": 1,
"value is 14960, expected 48": 1,
"value is 856, expected 100": 1,
"value is 2413.45238095, expected 100": 1,
"value is 595, expected 100": 1,
"value is 8736, expected 100": 1,
"value is 20.8928571429, expected 100": 1,
"value is 3631, expected 100": 1,
"value is 132, expected 97": 1,
"value is 703, expected 97": 1,
"value is 88, expected 17": 1,
"value is 2356, expected 17": 1,
"value is 90, expected 17": 1,
"value is 1216, expected 17": 1,
"value is 126, expected 17": 1,
"value is 128.710526316, expected 17": 1,
"value is 3.68421052632, expected 17": 1,
"value is 61, expected 17": 1,
"value is 297, expected 17": 1,
"value is 1932, expected 41": 1,
"value is 6.95652173913, expected 41": 1,
"value is 631, expected 44": 1,
"value is 196.269230769, expected 44": 1,
"value is 84, expected 44": 1,
"value is 3040, expected 44": 1,
"value is 88.734375, expected 44": 1,
"value is 28.1842105263, expected 44": 1,
"value is 196.923076923, expected 44": 1,
"value is 416, expected 44": 1,
"value is 104, expected 26": 1,
"value is -176, expected 26": 1,
"value is 14, expected 26": 1,
"value is 15.2307692308, expected 26": 1,
"value is 192, expected 44": 1,
"value is 86, expected 44": 1,
"value is 15.6470588235, expected 44": 1,
"value is 24, expected 44": 1,
"value is 438, expected 44": 1,
"value is 550.263157895, expected 44": 1,
"value is 1102, expected 44": 1,
"value is 58.6774193548, expected 44": 1,
"value is 99, expected 44": 1,
"value is -119, expected 44": 1,
"value is 403.939393939, expected 52": 1,
"value is 54, expected 52": 1,
"value is 2753.1025641, expected 52": 1,
"value is 53, expected 52": 1,
"value is 70.2857142857, expected 52": 1,
"value is 39.9069767442, expected 52": 1,
"value is 375, expected 52": 1,
"value is 6418.72727273, expected 52": 1,
"value is 352, expected 52": 1,
"value is 3.42857142857, expected 52": 1,
"value is 48.5128205128, expected 52": 1,
"value is 7505, expected 75": 1,
"value is 64.8, expected 75": 1,
"value is 899, expected 75": 1,
"value is 124, expected 28": 1,
"value is -366, expected 28": 1,
"value is 192, expected 28": 1,
"value is 495, expected 28": 1,
"value is -38, expected 96": 1,
"value is 70, expected 36": 1,
"value is 44, expected 98": 1,
"value is 60, expected 98": 1,
"value is 56, expected 98": 1,
"value is 147, expected 98": 1,
"value is 77, expected 98": 1,
"value is 82.3777777778, expected 63": 1,
"value is 2822, expected 63": 1,
"value is 133.392857143, expected 63": 1,
"value is 117, expected 63": 1,
"value is 888, expected 13": 1,
"value is -1340, expected 92": 1,
"value is 402, expected 92": 1,
"value is -6963, expected 92": 1,
"value is 1320, expected 92": 1,
"value is 1328.25, expected 92": 1,
"value is 1802, expected 92": 1,
"value is 293, expected 92": 1,
"value is 97, expected 94": 1,
"value is 2255, expected 94": 1,
"value is 81.4285714286, expected 94": 1,
"value is 11.1428571429, expected 94": 1,
"value is 85, expected 94": 1,
"value is 17.1219512195, expected 94": 1,
"value is 9.07317073171, expected 94": 1,
"value is 5.33333333333, expected 94": 1,
"value is 1632, expected 94": 1,
"value is -75.5714285714, expected 28": 1,
"value is -294, expected 28": 1,
"value is -63, expected 28": 1,
"value is 31.6909090909, expected 28": 1,
"value is 235.571428571, expected 28": 1,
"value is 8.87628865979, expected 28": 1,
"value is 652, expected 28": 1,
"value is 189.380952381, expected 28": 1,
"value is 3070.84057971, expected 33": 1,
"value is 3634, expected 33": 1,
"value is 102.492753623, expected 33": 1,
"value is 7.44117647059, expected 33": 1,
"value is 125.52173913, expected 33": 1,
"value is 2622, expected 33": 1,
"value is 101.076923077, expected 78": 1,
"value is 68, expected 78": 1,
"value is 217, expected 24": 1,
"value is 2.12903225806, expected 24": 1,
"value is 650, expected 83": 1,
"value is -1680, expected 83": 1,
"value is -1764, expected 83": 1,
"value is 2592, expected 83": 1,
"value is 4355, expected 83": 1,
"value is 1088, expected 83": 1,
"value is 21.32, expected 53": 1,
"value is 117.6, expected 53": 1,
"value is 4482, expected 53": 1,
"value is 87, expected 53": 1,
"value is 808, expected 53": 1,
"value is 182.6, expected 53": 1,
"value is 123.636363636, expected 65": 1,
"value is 2624, expected 65": 1,
"value is 25, expected 26": 1,
"value is 45, expected 26": 1,
"value is -225, expected 50": 1,
"value is 76, expected 50": 1,
"value is 2255, expected 14": 1,
"value is 58.6666666667, expected 14": 1,
"value is 131.2, expected 14": 1,
"value is 456.25, expected 14": 1,
"value is -15.2, expected 14": 1,
"value is 8, expected 14": 1,
"value is 675, expected 90": 1,
"value is 39.1875, expected 90": 1,
"value is 874.736842105, expected 90": 1,
"value is 149.925925926, expected 38": 1,
"value is 1140, expected 38": 1,
"value is 700, expected 38": 1,
"value is 69.9259259259, expected 38": 1,
"value is -124.235294118, expected 38": 1,
"value is 1857.77777778, expected 38": 1,
"value is 626.24, expected 61": 1,
"value is 738, expected 61": 1,
"value is 282, expected 61": 1,
"value is 158.333333333, expected 61": 1,
"value is 107.666666667, expected 61": 1,
"value is 336, expected 65": 1,
"value is 78, expected 65": 1,
"value is 84.1538461538, expected 65": 1,
"value is 91, expected 65": 1,
"value is 89, expected 65": 1,
"value is 396, expected 58": 1,
"value is 260, expected 58": 1,
"value is 41.6666666667, expected 58": 1,
"value is 71.15, expected 37": 1,
"value is 12.5094339623, expected 37": 1,
"value is 663, expected 37": 1,
"value is 110, expected 37": 1,
"value is 88, expected 100": 1,
"value is 40.7058823529, expected 100": 1,
"value is -760, expected 36": 1,
"value is 54.3396226415, expected 36": 1,
"value is 103.055555556, expected 36": 1,
"value is 123.2, expected 36": 1,
"value is 20.4, expected 83": 1,
"value is 519, expected 83": 1,
"value is 671.333333333, expected 83": 1,
"value is 246.666666667, expected 83": 1,
"value is 99.6666666667, expected 83": 1,
"value is 12, expected 83": 1,
"value is 380, expected 83": 1,
"value is 26.3157894737, expected 83": 1,
"value is 69, expected 47": 1,
"value is 259, expected 47": 1,
"value is 84, expected 47": 1,
"value is 175, expected 47": 1,
"value is 42, expected 45": 1,
"value is -12, expected 32": 1,
"value is 84, expected 100": 1,
"value is 177, expected 59": 1,
"value is 59, expected 43": 1,
"value is 408, expected 43": 1,
"value is 100, expected 96": 1,
"value is 111, expected 15": 1,
"value is -5.74074074074, expected 15": 1,
"value is 214.5, expected 15": 1,
"value is 419, expected 15": 1,
"value is 2256, expected 15": 1,
"value is 1800, expected 15": 1,
"value is 42.9545454545, expected 71": 1,
"value is 28.5185185185, expected 71": 1,
"value is 511, expected 71": 1,
"value is 29.5540540541, expected 71": 1,
"value is -28.5185185185, expected 71": 1,
"value is 1917, expected 71": 1,
"value is 37.4594594595, expected 71": 1,
"value is 5880, expected 71": 1,
"value is 114.932432432, expected 71": 1,
"value is 17, expected 14": 1,
"value is 5041, expected 36": 1,
"value is 54.8648648649, expected 29": 1,
"value is 195, expected 14": 1,
"value is 500, expected 14": 1,
"value is 87, expected 14": 1,
"value is 13, expected 14": 1,
"value is 131, expected 14": 1,
"value is 24.0652173913, expected 14": 1,
"value is 4332, expected 57": 1,
"value is 133, expected 57": 1,
"value is 545.416666667, expected 30": 1,
"value is 53.5471698113, expected 30": 1,
"value is 59.5833333333, expected 30": 1,
"value is 34.1666666667, expected 30": 1,
"value is 49.2, expected 30": 1,
"value is 2.83636363636, expected 30": 1,
"value is 78, expected 30": 1,
"value is 76, expected 30": 1,
"value is 141, expected 11": 1,
"value is 58.1176470588, expected 24": 1,
"value is -2590, expected 24": 1,
"value is 74.25, expected 24": 1,
"value is -32.1481481481, expected 24": 1,
"value is 960, expected 24": 1,
"value is 3468, expected 24": 1,
"value is -2860, expected 24": 1,
"value is 16, expected 24": 1,
"value is 2052, expected 24": 1,
"value is -25.6296296296, expected 24": 1,
"value is 265, expected 26": 1,
"value is 2184, expected 26": 1,
"value is 32.6666666667, expected 26": 1,
"value is 560, expected 26": 1,
"value is 35.3571428571, expected 26": 1,
"value is 680, expected 26": 1,
"value is 1584, expected 35": 1,
"value is 88, expected 35": 1,
"value is 1972, expected 35": 1,
"value is 1989, expected 35": 1,
"value is 129, expected 35": 1,
"value is 61, expected 35": 1,
"value is 116, expected 35": 1,
"value is 58, expected 59": 1,
"value is -17, expected 59": 1,
"value is 390, expected 66": 1,
"value is 234.846153846, expected 66": 1,
"value is 2520, expected 66": 1,
"value is 184, expected 66": 1,
"value is 261.533333333, expected 66": 1,
"value is 9.50704225352, expected 66": 1,
"value is 101, expected 66": 1,
"value is 371, expected 60": 1,
"value is 85, expected 86": 1,
"value is 9, expected 29": 1,
"value is 36, expected 29": 1,
"value is 69.9130434783, expected 22": 1,
"value is 40, expected 22": 1,
"value is 67, expected 22": 1,
"value is 1798, expected 83": 1,
"value is 302.210526316, expected 83": 1,
"value is 212, expected 83": 1,
"value is 638, expected 83": 1,
"value is 1722, expected 83": 1,
"value is 12.4776119403, expected 83": 1,
"value is 2456.32307692, expected 83": 1,
"value is 4158, expected 83": 1,
"value is 48.3731343284, expected 83": 1,
"value is 121.268656716, expected 83": 1,
"value is 40, expected 16": 1,
"value is 3900, expected 53": 1,
"value is -1241, expected 53": 1,
"value is 12.3452380952, expected 53": 1,
"value is 1222, expected 72": 1,
"value is 630, expected 72": 1,
"value is 282, expected 72": 1,
"value is 912, expected 72": 1,
"value is 29.375, expected 72": 1,
"value is 104, expected 78": 1,
"value is 58.4210526316, expected 78": 1,
"value is 103.529411765, expected 78": 1,
"value is 695, expected 78": 1,
"value is -24.7368421053, expected 78": 1,
"value is 175.058823529, expected 78": 1,
"value is -8930, expected 78": 1,
"value is 1051, expected 78": 1,
"value is 2516, expected 78": 1,
"value is 50.7058823529, expected 78": 1,
"value is 190.842105263, expected 78": 1,
"value is 475, expected 78": 1,
"value is -551, expected 87": 1,
"value is 156.85915493, expected 87": 1,
"value is -63, expected 87": 1,
"value is 5531.95061728, expected 87": 1,
"value is 221, expected 87": 1,
"value is 229, expected 87": 1,
"value is 133, expected 77": 1,
"value is 2423, expected 58": 1,
"value is -17.7608695652, expected 58": 1,
"value is 52.4262295082, expected 58": 1,
"value is 16.7450980392, expected 58": 1,
"value is 6396, expected 58": 1,
"value is 1700, expected 58": 1,
"value is 85.5326086957, expected 58": 1,
"value is 32.0392156863, expected 58": 1,
"value is 77.0543478261, expected 58": 1,
"value is 20.2692307692, expected 58": 1,
"value is 128.336956522, expected 58": 1,
"value is 9.42391304348, expected 58": 1,
"value is 21.5306122449, expected 51": 1,
"value is 46.6363636364, expected 51": 1,
"value is 3914.09090909, expected 51": 1,
"value is 608, expected 51": 1,
"value is 76, expected 92": 1,
"value is -988, expected 92": 1,
"value is 426, expected 92": 1,
"value is 828, expected 92": 1,
"value is 7.125, expected 92": 1,
"value is 11.5, expected 92": 1,
"value is 72, expected 92": 1
},
"empty": false,
"first_attempt_count": 100,
"first_attempt_r1_format_rate": 0.97,
"first_attempt_answer_tag_rate": 0.97,
"first_attempt_allowed_chars_rate": 0.96,
"first_attempt_parse_ok_rate": 0.95,
"first_attempt_numbers_ok_rate": 0.58,
"first_attempt_target_ok_rate": 0.01,
"first_attempt_valid_rate": 0.0,
"attempt_count": 1600,
"attempt_r1_format_rate": 0.986875,
"attempt_answer_tag_rate": 0.986875,
"attempt_allowed_chars_rate": 0.979375,
"attempt_parse_ok_rate": 0.95375,
"attempt_numbers_ok_rate": 0.570625,
"attempt_target_ok_rate": 0.015625,
"attempt_valid_rate": 0.011875,
"mean_candidates_until_solution": 7.363636363636363,
"median_candidates_until_solution": 7,
"max_candidates_until_solution": 15,
"solved_at_1_count": 0,
"solved_at_1": 0.0,
"solved_at_4_count": 5,
"solved_at_4": 0.05,
"solved_at_16_count": 11,
"solved_at_16": 0.11,
"num_samples": 16
}