File size: 5,698 Bytes
c19ecfe |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 |
{
"best_metric": 0.7838312829525483,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-24/checkpoint-1926",
"epoch": 9.0,
"eval_steps": 500,
"global_step": 1926,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 7.816347122192383,
"learning_rate": 0.0002514027907655722,
"loss": 0.603,
"step": 214
},
{
"epoch": 1.0,
"eval_accuracy": 0.705916813122437,
"eval_f1": 0.4670912951167728,
"eval_loss": 0.5544006824493408,
"eval_mcc": 0.2876964932013613,
"eval_precision": 0.5898123324396782,
"eval_recall": 0.3866432337434095,
"eval_runtime": 3.1616,
"eval_samples_per_second": 539.92,
"eval_steps_per_second": 17.08,
"step": 214
},
{
"epoch": 2.0,
"grad_norm": 2.7939634323120117,
"learning_rate": 0.00021997744191987566,
"loss": 0.531,
"step": 428
},
{
"epoch": 2.0,
"eval_accuracy": 0.7352079671939075,
"eval_f1": 0.5368852459016393,
"eval_loss": 0.5183561444282532,
"eval_mcc": 0.3684302929196794,
"eval_precision": 0.6437346437346437,
"eval_recall": 0.46045694200351495,
"eval_runtime": 3.2232,
"eval_samples_per_second": 529.598,
"eval_steps_per_second": 16.754,
"step": 428
},
{
"epoch": 3.0,
"grad_norm": 2.888092279434204,
"learning_rate": 0.00018855209307417915,
"loss": 0.502,
"step": 642
},
{
"epoch": 3.0,
"eval_accuracy": 0.7451669595782073,
"eval_f1": 0.48520710059171596,
"eval_loss": 0.5155817270278931,
"eval_mcc": 0.3814260429877007,
"eval_precision": 0.7427536231884058,
"eval_recall": 0.3602811950790861,
"eval_runtime": 3.1891,
"eval_samples_per_second": 535.256,
"eval_steps_per_second": 16.933,
"step": 642
},
{
"epoch": 4.0,
"grad_norm": 3.3760223388671875,
"learning_rate": 0.00015712674422848263,
"loss": 0.4897,
"step": 856
},
{
"epoch": 4.0,
"eval_accuracy": 0.7422378441710603,
"eval_f1": 0.45812807881773393,
"eval_loss": 0.5075758695602417,
"eval_mcc": 0.37344089980427997,
"eval_precision": 0.7654320987654321,
"eval_recall": 0.3268892794376098,
"eval_runtime": 3.1359,
"eval_samples_per_second": 544.344,
"eval_steps_per_second": 17.22,
"step": 856
},
{
"epoch": 5.0,
"grad_norm": 11.075637817382812,
"learning_rate": 0.0001257013953827861,
"loss": 0.4761,
"step": 1070
},
{
"epoch": 5.0,
"eval_accuracy": 0.7568834212067955,
"eval_f1": 0.5870646766169154,
"eval_loss": 0.49240508675575256,
"eval_mcc": 0.42649635439740835,
"eval_precision": 0.676605504587156,
"eval_recall": 0.5184534270650264,
"eval_runtime": 3.1156,
"eval_samples_per_second": 547.891,
"eval_steps_per_second": 17.332,
"step": 1070
},
{
"epoch": 6.0,
"grad_norm": 6.270783424377441,
"learning_rate": 9.427604653708957e-05,
"loss": 0.4671,
"step": 1284
},
{
"epoch": 6.0,
"eval_accuracy": 0.7697715289982425,
"eval_f1": 0.6288951841359773,
"eval_loss": 0.48595207929611206,
"eval_mcc": 0.4660789140327505,
"eval_precision": 0.6795918367346939,
"eval_recall": 0.5852372583479789,
"eval_runtime": 3.1299,
"eval_samples_per_second": 545.38,
"eval_steps_per_second": 17.253,
"step": 1284
},
{
"epoch": 7.0,
"grad_norm": 6.990926742553711,
"learning_rate": 6.285069769139304e-05,
"loss": 0.4567,
"step": 1498
},
{
"epoch": 7.0,
"eval_accuracy": 0.7633274751025191,
"eval_f1": 0.5692963752665245,
"eval_loss": 0.48252516984939575,
"eval_mcc": 0.43473790600905954,
"eval_precision": 0.7235772357723578,
"eval_recall": 0.46924428822495606,
"eval_runtime": 3.1545,
"eval_samples_per_second": 541.124,
"eval_steps_per_second": 17.118,
"step": 1498
},
{
"epoch": 8.0,
"grad_norm": 4.125209331512451,
"learning_rate": 3.142534884569652e-05,
"loss": 0.4404,
"step": 1712
},
{
"epoch": 8.0,
"eval_accuracy": 0.7820738137082601,
"eval_f1": 0.6395348837209303,
"eval_loss": 0.4758114218711853,
"eval_mcc": 0.4910151946014594,
"eval_precision": 0.712742980561555,
"eval_recall": 0.5799648506151143,
"eval_runtime": 3.146,
"eval_samples_per_second": 542.597,
"eval_steps_per_second": 17.165,
"step": 1712
},
{
"epoch": 9.0,
"grad_norm": 11.615726470947266,
"learning_rate": 0.0,
"loss": 0.4355,
"step": 1926
},
{
"epoch": 9.0,
"eval_accuracy": 0.7838312829525483,
"eval_f1": 0.654170571696345,
"eval_loss": 0.47215673327445984,
"eval_mcc": 0.5002988732745446,
"eval_precision": 0.7008032128514057,
"eval_recall": 0.6133567662565905,
"eval_runtime": 3.1367,
"eval_samples_per_second": 544.2,
"eval_steps_per_second": 17.215,
"step": 1926
}
],
"logging_steps": 500,
"max_steps": 1926,
"num_input_tokens_seen": 0,
"num_train_epochs": 9,
"save_steps": 500,
"total_flos": 4722980979960.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"alpha": 0.9932022812512611,
"learning_rate": 0.0002828281396112687,
"num_train_epochs": 9,
"temperature": 23
}
}
|