Upload models/real_data_training_summary.json with huggingface_hub
Browse files
models/real_data_training_summary.json
ADDED
|
@@ -0,0 +1,189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"timestamp": "2025-12-02T17:19:38.011582",
|
| 3 |
+
"total_time_sec": 3143.6702983379364,
|
| 4 |
+
"n_helpers": 13,
|
| 5 |
+
"results": {
|
| 6 |
+
"emotional_intelligence": {
|
| 7 |
+
"domain": "emotional_intelligence",
|
| 8 |
+
"dataset": "dair-ai/emotion",
|
| 9 |
+
"description": "Twitter emotions (anger, fear, joy, love, sadness, surprise)",
|
| 10 |
+
"n_samples": 3000,
|
| 11 |
+
"n_features": 110,
|
| 12 |
+
"n_classes": 6,
|
| 13 |
+
"train_accuracy": 0.435,
|
| 14 |
+
"test_accuracy": 0.35833333333333334,
|
| 15 |
+
"train_test_gap": 0.07666666666666666,
|
| 16 |
+
"cv_mean": 0.36875,
|
| 17 |
+
"cv_std": 0.009592387027684456,
|
| 18 |
+
"train_time_sec": 0.816157341003418
|
| 19 |
+
},
|
| 20 |
+
"decision_making": {
|
| 21 |
+
"domain": "decision_making",
|
| 22 |
+
"dataset": "openai/gsm8k",
|
| 23 |
+
"description": "Grade school math - multi-step reasoning",
|
| 24 |
+
"n_samples": 3000,
|
| 25 |
+
"n_features": 110,
|
| 26 |
+
"n_classes": 5,
|
| 27 |
+
"train_accuracy": 0.8420833333333333,
|
| 28 |
+
"test_accuracy": 0.84,
|
| 29 |
+
"train_test_gap": 0.002083333333333326,
|
| 30 |
+
"cv_mean": 0.8404166666666667,
|
| 31 |
+
"cv_std": 0.001020620726159654,
|
| 32 |
+
"train_time_sec": 0.8619897365570068
|
| 33 |
+
},
|
| 34 |
+
"adaptive_learning": {
|
| 35 |
+
"domain": "adaptive_learning",
|
| 36 |
+
"dataset": "rajpurkar/squad",
|
| 37 |
+
"description": "SQuAD reading comprehension",
|
| 38 |
+
"n_samples": 3000,
|
| 39 |
+
"n_features": 110,
|
| 40 |
+
"n_classes": 4,
|
| 41 |
+
"train_accuracy": 0.6195833333333334,
|
| 42 |
+
"test_accuracy": 0.5983333333333334,
|
| 43 |
+
"train_test_gap": 0.02124999999999999,
|
| 44 |
+
"cv_mean": 0.6083333333333334,
|
| 45 |
+
"cv_std": 0.008436856971381926,
|
| 46 |
+
"train_time_sec": 0.33698034286499023
|
| 47 |
+
},
|
| 48 |
+
"logical_reasoning": {
|
| 49 |
+
"domain": "logical_reasoning",
|
| 50 |
+
"dataset": "lucasmccabe/logiqa",
|
| 51 |
+
"description": "Logical reasoning questions",
|
| 52 |
+
"n_samples": 1000,
|
| 53 |
+
"n_features": 110,
|
| 54 |
+
"n_classes": 5,
|
| 55 |
+
"train_accuracy": 1.0,
|
| 56 |
+
"test_accuracy": 0.19,
|
| 57 |
+
"train_test_gap": 0.81,
|
| 58 |
+
"cv_mean": 0.1775,
|
| 59 |
+
"cv_std": 0.020000000000000007,
|
| 60 |
+
"train_time_sec": 0.4216756820678711
|
| 61 |
+
},
|
| 62 |
+
"memory_formation": {
|
| 63 |
+
"domain": "memory_formation",
|
| 64 |
+
"dataset": "mandarjoshi/trivia_qa",
|
| 65 |
+
"description": "TriviaQA fact recall",
|
| 66 |
+
"n_samples": 3000,
|
| 67 |
+
"n_features": 110,
|
| 68 |
+
"n_classes": 4,
|
| 69 |
+
"train_accuracy": 0.7108333333333333,
|
| 70 |
+
"test_accuracy": 0.7133333333333334,
|
| 71 |
+
"train_test_gap": -0.0025000000000000577,
|
| 72 |
+
"cv_mean": 0.69875,
|
| 73 |
+
"cv_std": 0.015172617880027592,
|
| 74 |
+
"train_time_sec": 0.3318939208984375
|
| 75 |
+
},
|
| 76 |
+
"pattern_recognition": {
|
| 77 |
+
"domain": "pattern_recognition",
|
| 78 |
+
"dataset": "allenai/ai2_arc",
|
| 79 |
+
"description": "ARC science reasoning",
|
| 80 |
+
"n_samples": 1119,
|
| 81 |
+
"n_features": 110,
|
| 82 |
+
"n_classes": 8,
|
| 83 |
+
"train_accuracy": 0.5217877094972067,
|
| 84 |
+
"test_accuracy": 0.26785714285714285,
|
| 85 |
+
"train_test_gap": 0.2539305666400638,
|
| 86 |
+
"cv_mean": 0.23016759776536314,
|
| 87 |
+
"cv_std": 0.0227340669825428,
|
| 88 |
+
"train_time_sec": 0.19740653038024902
|
| 89 |
+
},
|
| 90 |
+
"metacognition": {
|
| 91 |
+
"domain": "metacognition",
|
| 92 |
+
"dataset": "tau/commonsense_qa",
|
| 93 |
+
"description": "CommonsenseQA reasoning",
|
| 94 |
+
"n_samples": 3000,
|
| 95 |
+
"n_features": 110,
|
| 96 |
+
"n_classes": 5,
|
| 97 |
+
"train_accuracy": 0.3595833333333333,
|
| 98 |
+
"test_accuracy": 0.22333333333333333,
|
| 99 |
+
"train_test_gap": 0.13624999999999998,
|
| 100 |
+
"cv_mean": 0.21416666666666667,
|
| 101 |
+
"cv_std": 0.013906932723565526,
|
| 102 |
+
"train_time_sec": 0.23867106437683105
|
| 103 |
+
},
|
| 104 |
+
"self_awareness": {
|
| 105 |
+
"domain": "self_awareness",
|
| 106 |
+
"dataset": "dair-ai/emotion",
|
| 107 |
+
"description": "Self-awareness through emotion recognition",
|
| 108 |
+
"n_samples": 3000,
|
| 109 |
+
"n_features": 110,
|
| 110 |
+
"n_classes": 6,
|
| 111 |
+
"train_accuracy": 0.435,
|
| 112 |
+
"test_accuracy": 0.35833333333333334,
|
| 113 |
+
"train_test_gap": 0.07666666666666666,
|
| 114 |
+
"cv_mean": 0.36875,
|
| 115 |
+
"cv_std": 0.009592387027684456,
|
| 116 |
+
"train_time_sec": 0.24677586555480957
|
| 117 |
+
},
|
| 118 |
+
"social_learning": {
|
| 119 |
+
"domain": "social_learning",
|
| 120 |
+
"dataset": "allenai/social_i_qa",
|
| 121 |
+
"description": "Social intelligence QA",
|
| 122 |
+
"n_samples": 1000,
|
| 123 |
+
"n_features": 110,
|
| 124 |
+
"n_classes": 5,
|
| 125 |
+
"train_accuracy": 1.0,
|
| 126 |
+
"test_accuracy": 0.19,
|
| 127 |
+
"train_test_gap": 0.81,
|
| 128 |
+
"cv_mean": 0.1775,
|
| 129 |
+
"cv_std": 0.020000000000000007,
|
| 130 |
+
"train_time_sec": 0.24502849578857422
|
| 131 |
+
},
|
| 132 |
+
"spatial_reasoning": {
|
| 133 |
+
"domain": "spatial_reasoning",
|
| 134 |
+
"dataset": "ybisk/piqa",
|
| 135 |
+
"description": "Physical intuition QA",
|
| 136 |
+
"n_samples": 1000,
|
| 137 |
+
"n_features": 110,
|
| 138 |
+
"n_classes": 5,
|
| 139 |
+
"train_accuracy": 1.0,
|
| 140 |
+
"test_accuracy": 0.19,
|
| 141 |
+
"train_test_gap": 0.81,
|
| 142 |
+
"cv_mean": 0.1775,
|
| 143 |
+
"cv_std": 0.020000000000000007,
|
| 144 |
+
"train_time_sec": 0.24609684944152832
|
| 145 |
+
},
|
| 146 |
+
"language_processing": {
|
| 147 |
+
"domain": "language_processing",
|
| 148 |
+
"dataset": "nyu-mll/glue",
|
| 149 |
+
"description": "CoLA linguistic acceptability",
|
| 150 |
+
"n_samples": 3000,
|
| 151 |
+
"n_features": 110,
|
| 152 |
+
"n_classes": 2,
|
| 153 |
+
"train_accuracy": 0.7208333333333333,
|
| 154 |
+
"test_accuracy": 0.71,
|
| 155 |
+
"train_test_gap": 0.010833333333333361,
|
| 156 |
+
"cv_mean": 0.7108333333333332,
|
| 157 |
+
"cv_std": 0.004639803635691711,
|
| 158 |
+
"train_time_sec": 0.23175382614135742
|
| 159 |
+
},
|
| 160 |
+
"creative_thinking": {
|
| 161 |
+
"domain": "creative_thinking",
|
| 162 |
+
"dataset": "Abirate/english_quotes",
|
| 163 |
+
"description": "Creative quotes and writing",
|
| 164 |
+
"n_samples": 2508,
|
| 165 |
+
"n_features": 110,
|
| 166 |
+
"n_classes": 3,
|
| 167 |
+
"train_accuracy": 0.8035892323030908,
|
| 168 |
+
"test_accuracy": 0.7051792828685259,
|
| 169 |
+
"train_test_gap": 0.09840994943456483,
|
| 170 |
+
"cv_mean": 0.7437662063746108,
|
| 171 |
+
"cv_std": 0.00565980154039184,
|
| 172 |
+
"train_time_sec": 0.2100505828857422
|
| 173 |
+
},
|
| 174 |
+
"abstract_thinking": {
|
| 175 |
+
"domain": "abstract_thinking",
|
| 176 |
+
"dataset": "lighteval/MATH",
|
| 177 |
+
"description": "Abstract mathematical reasoning",
|
| 178 |
+
"n_samples": 1000,
|
| 179 |
+
"n_features": 110,
|
| 180 |
+
"n_classes": 5,
|
| 181 |
+
"train_accuracy": 1.0,
|
| 182 |
+
"test_accuracy": 0.19,
|
| 183 |
+
"train_test_gap": 0.81,
|
| 184 |
+
"cv_mean": 0.1775,
|
| 185 |
+
"cv_std": 0.020000000000000007,
|
| 186 |
+
"train_time_sec": 0.19356322288513184
|
| 187 |
+
}
|
| 188 |
+
}
|
| 189 |
+
}
|