File size: 5,256 Bytes
d678fc6 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 |
{
"best_metric": 0.052102286368608475,
"best_model_checkpoint": "autotrain-pbt7y-rt1dv/checkpoint-450",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 450,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.16666666666666666,
"grad_norm": 4.162468433380127,
"learning_rate": 2.6666666666666667e-05,
"loss": 0.6911,
"step": 25
},
{
"epoch": 0.3333333333333333,
"grad_norm": 14.043020248413086,
"learning_rate": 4.950617283950618e-05,
"loss": 0.5826,
"step": 50
},
{
"epoch": 0.5,
"grad_norm": 12.165104866027832,
"learning_rate": 4.654320987654321e-05,
"loss": 0.421,
"step": 75
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.5717558264732361,
"learning_rate": 4.345679012345679e-05,
"loss": 0.2736,
"step": 100
},
{
"epoch": 0.8333333333333334,
"grad_norm": 0.27614304423332214,
"learning_rate": 4.0370370370370374e-05,
"loss": 0.4425,
"step": 125
},
{
"epoch": 1.0,
"grad_norm": 10.753256797790527,
"learning_rate": 3.7283950617283955e-05,
"loss": 0.232,
"step": 150
},
{
"epoch": 1.0,
"eval_accuracy": 0.9607679465776294,
"eval_auc": 0.9811715189608797,
"eval_f1": 0.9595872742906277,
"eval_loss": 0.15245321393013,
"eval_precision": 0.9789473684210527,
"eval_recall": 0.9409780775716695,
"eval_runtime": 0.5784,
"eval_samples_per_second": 2071.084,
"eval_steps_per_second": 32.847,
"step": 150
},
{
"epoch": 1.1666666666666667,
"grad_norm": 0.11041617393493652,
"learning_rate": 3.419753086419753e-05,
"loss": 0.2218,
"step": 175
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.048719145357608795,
"learning_rate": 3.123456790123457e-05,
"loss": 0.1994,
"step": 200
},
{
"epoch": 1.5,
"grad_norm": 0.0485817976295948,
"learning_rate": 2.814814814814815e-05,
"loss": 0.1059,
"step": 225
},
{
"epoch": 1.6666666666666665,
"grad_norm": 17.67010498046875,
"learning_rate": 2.5061728395061727e-05,
"loss": 0.1323,
"step": 250
},
{
"epoch": 1.8333333333333335,
"grad_norm": 0.08793912082910538,
"learning_rate": 2.1975308641975308e-05,
"loss": 0.0836,
"step": 275
},
{
"epoch": 2.0,
"grad_norm": 57.188568115234375,
"learning_rate": 1.901234567901235e-05,
"loss": 0.1419,
"step": 300
},
{
"epoch": 2.0,
"eval_accuracy": 0.9841402337228714,
"eval_auc": 0.9959527824620573,
"eval_f1": 0.9840201850294366,
"eval_loss": 0.08388863503932953,
"eval_precision": 0.9815436241610739,
"eval_recall": 0.9865092748735245,
"eval_runtime": 0.5767,
"eval_samples_per_second": 2077.214,
"eval_steps_per_second": 32.944,
"step": 300
},
{
"epoch": 2.1666666666666665,
"grad_norm": 0.05389270931482315,
"learning_rate": 1.5925925925925926e-05,
"loss": 0.0871,
"step": 325
},
{
"epoch": 2.3333333333333335,
"grad_norm": 0.06370247155427933,
"learning_rate": 1.2839506172839508e-05,
"loss": 0.1008,
"step": 350
},
{
"epoch": 2.5,
"grad_norm": 0.0631629005074501,
"learning_rate": 9.753086419753086e-06,
"loss": 0.1163,
"step": 375
},
{
"epoch": 2.6666666666666665,
"grad_norm": 0.053911201655864716,
"learning_rate": 6.666666666666667e-06,
"loss": 0.0639,
"step": 400
},
{
"epoch": 2.8333333333333335,
"grad_norm": 4.950315952301025,
"learning_rate": 3.580246913580247e-06,
"loss": 0.0894,
"step": 425
},
{
"epoch": 3.0,
"grad_norm": 0.06562542915344238,
"learning_rate": 4.938271604938272e-07,
"loss": 0.0789,
"step": 450
},
{
"epoch": 3.0,
"eval_accuracy": 0.988313856427379,
"eval_auc": 0.9985157415020973,
"eval_f1": 0.9881756756756757,
"eval_loss": 0.052102286368608475,
"eval_precision": 0.9898477157360406,
"eval_recall": 0.9865092748735245,
"eval_runtime": 0.5865,
"eval_samples_per_second": 2042.526,
"eval_steps_per_second": 32.394,
"step": 450
}
],
"logging_steps": 25,
"max_steps": 450,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 947199814926336.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|