File size: 5,632 Bytes
9d52bf6 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"global_step": 220,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 9.090909090909092e-05,
"loss": 0.6837,
"step": 22
},
{
"epoch": 1.0,
"eval_accuracy": 0.5897435897435898,
"eval_f1": 0.6666666666666666,
"eval_loss": 0.6039571166038513,
"eval_precision": 0.5161290322580645,
"eval_recall": 0.9411764705882353,
"eval_roc_auc": 0.6296791443850267,
"eval_runtime": 0.069,
"eval_samples_per_second": 565.227,
"eval_steps_per_second": 43.479,
"step": 22
},
{
"epoch": 2.0,
"learning_rate": 8.090909090909092e-05,
"loss": 0.3852,
"step": 44
},
{
"epoch": 2.0,
"eval_accuracy": 0.9230769230769231,
"eval_f1": 0.9189189189189189,
"eval_loss": 0.28810474276542664,
"eval_precision": 0.85,
"eval_recall": 1.0,
"eval_roc_auc": 0.9318181818181819,
"eval_runtime": 0.064,
"eval_samples_per_second": 609.374,
"eval_steps_per_second": 46.875,
"step": 44
},
{
"epoch": 3.0,
"learning_rate": 7.090909090909092e-05,
"loss": 0.2148,
"step": 66
},
{
"epoch": 3.0,
"eval_accuracy": 0.9230769230769231,
"eval_f1": 0.9189189189189189,
"eval_loss": 0.38069406151771545,
"eval_precision": 0.85,
"eval_recall": 1.0,
"eval_roc_auc": 0.9318181818181819,
"eval_runtime": 0.065,
"eval_samples_per_second": 600.004,
"eval_steps_per_second": 46.154,
"step": 66
},
{
"epoch": 4.0,
"learning_rate": 6.090909090909091e-05,
"loss": 0.0701,
"step": 88
},
{
"epoch": 4.0,
"eval_accuracy": 0.8717948717948718,
"eval_f1": 0.8717948717948718,
"eval_loss": 0.4933823347091675,
"eval_precision": 0.7727272727272727,
"eval_recall": 1.0,
"eval_roc_auc": 0.8863636363636364,
"eval_runtime": 0.071,
"eval_samples_per_second": 549.297,
"eval_steps_per_second": 42.254,
"step": 88
},
{
"epoch": 5.0,
"learning_rate": 5.090909090909091e-05,
"loss": 0.0164,
"step": 110
},
{
"epoch": 5.0,
"eval_accuracy": 0.8974358974358975,
"eval_f1": 0.8947368421052632,
"eval_loss": 0.4892081320285797,
"eval_precision": 0.8095238095238095,
"eval_recall": 1.0,
"eval_roc_auc": 0.9090909090909091,
"eval_runtime": 0.064,
"eval_samples_per_second": 609.381,
"eval_steps_per_second": 46.875,
"step": 110
},
{
"epoch": 6.0,
"learning_rate": 4.0909090909090915e-05,
"loss": 0.0039,
"step": 132
},
{
"epoch": 6.0,
"eval_accuracy": 0.8974358974358975,
"eval_f1": 0.8947368421052632,
"eval_loss": 0.49288177490234375,
"eval_precision": 0.8095238095238095,
"eval_recall": 1.0,
"eval_roc_auc": 0.9090909090909091,
"eval_runtime": 0.058,
"eval_samples_per_second": 672.418,
"eval_steps_per_second": 51.724,
"step": 132
},
{
"epoch": 7.0,
"learning_rate": 3.090909090909091e-05,
"loss": 0.0012,
"step": 154
},
{
"epoch": 7.0,
"eval_accuracy": 0.9230769230769231,
"eval_f1": 0.9189189189189189,
"eval_loss": 0.4065372943878174,
"eval_precision": 0.85,
"eval_recall": 1.0,
"eval_roc_auc": 0.9318181818181819,
"eval_runtime": 0.063,
"eval_samples_per_second": 619.043,
"eval_steps_per_second": 47.619,
"step": 154
},
{
"epoch": 8.0,
"learning_rate": 2.090909090909091e-05,
"loss": 0.0008,
"step": 176
},
{
"epoch": 8.0,
"eval_accuracy": 0.9230769230769231,
"eval_f1": 0.9189189189189189,
"eval_loss": 0.48369330167770386,
"eval_precision": 0.85,
"eval_recall": 1.0,
"eval_roc_auc": 0.9318181818181819,
"eval_runtime": 0.059,
"eval_samples_per_second": 661.03,
"eval_steps_per_second": 50.848,
"step": 176
},
{
"epoch": 9.0,
"learning_rate": 1.0909090909090909e-05,
"loss": 0.0007,
"step": 198
},
{
"epoch": 9.0,
"eval_accuracy": 0.9230769230769231,
"eval_f1": 0.9189189189189189,
"eval_loss": 0.4999829828739166,
"eval_precision": 0.85,
"eval_recall": 1.0,
"eval_roc_auc": 0.9318181818181819,
"eval_runtime": 0.061,
"eval_samples_per_second": 639.321,
"eval_steps_per_second": 49.179,
"step": 198
},
{
"epoch": 10.0,
"learning_rate": 9.09090909090909e-07,
"loss": 0.0006,
"step": 220
},
{
"epoch": 10.0,
"eval_accuracy": 0.9230769230769231,
"eval_f1": 0.9189189189189189,
"eval_loss": 0.5037449598312378,
"eval_precision": 0.85,
"eval_recall": 1.0,
"eval_roc_auc": 0.9318181818181819,
"eval_runtime": 0.058,
"eval_samples_per_second": 672.418,
"eval_steps_per_second": 51.724,
"step": 220
},
{
"epoch": 10.0,
"step": 220,
"total_flos": 197738122089864.0,
"train_loss": 0.1377350079192018,
"train_runtime": 17.676,
"train_samples_per_second": 194.048,
"train_steps_per_second": 12.446
}
],
"max_steps": 220,
"num_train_epochs": 10,
"total_flos": 197738122089864.0,
"trial_name": null,
"trial_params": null
}
|