Edison
commited on
Commit
·
56e83bc
1
Parent(s):
ae46e3c
End of training
Browse files- all_results.json +18 -0
- eval_results.json +13 -0
- train_results.json +8 -0
- trainer_state.json +215 -0
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9769967138162595,
|
| 4 |
+
"eval_f1": 0.9777347531461762,
|
| 5 |
+
"eval_loss": 0.17970030009746552,
|
| 6 |
+
"eval_precision": 0.98413140311804,
|
| 7 |
+
"eval_recall": 0.9714207199780159,
|
| 8 |
+
"eval_roc_auc": 0.977228217131865,
|
| 9 |
+
"eval_runtime": 7.2505,
|
| 10 |
+
"eval_samples": 6999,
|
| 11 |
+
"eval_samples_per_second": 965.318,
|
| 12 |
+
"eval_steps_per_second": 7.586,
|
| 13 |
+
"train_loss": 0.040063528825431106,
|
| 14 |
+
"train_runtime": 1111.3299,
|
| 15 |
+
"train_samples": 27992,
|
| 16 |
+
"train_samples_per_second": 251.878,
|
| 17 |
+
"train_steps_per_second": 1.971
|
| 18 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9769967138162595,
|
| 4 |
+
"eval_f1": 0.9777347531461762,
|
| 5 |
+
"eval_loss": 0.17970030009746552,
|
| 6 |
+
"eval_precision": 0.98413140311804,
|
| 7 |
+
"eval_recall": 0.9714207199780159,
|
| 8 |
+
"eval_roc_auc": 0.977228217131865,
|
| 9 |
+
"eval_runtime": 7.2505,
|
| 10 |
+
"eval_samples": 6999,
|
| 11 |
+
"eval_samples_per_second": 965.318,
|
| 12 |
+
"eval_steps_per_second": 7.586
|
| 13 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.040063528825431106,
|
| 4 |
+
"train_runtime": 1111.3299,
|
| 5 |
+
"train_samples": 27992,
|
| 6 |
+
"train_samples_per_second": 251.878,
|
| 7 |
+
"train_steps_per_second": 1.971
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,215 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 2190,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 9.009132420091326e-05,
|
| 13 |
+
"loss": 0.2106,
|
| 14 |
+
"step": 219
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.9639948564080583,
|
| 19 |
+
"eval_f1": 0.9653751030502885,
|
| 20 |
+
"eval_loss": 0.11960607767105103,
|
| 21 |
+
"eval_precision": 0.9653751030502885,
|
| 22 |
+
"eval_recall": 0.9653751030502885,
|
| 23 |
+
"eval_roc_auc": 0.9639375515251443,
|
| 24 |
+
"eval_runtime": 7.2687,
|
| 25 |
+
"eval_samples_per_second": 962.897,
|
| 26 |
+
"eval_steps_per_second": 7.567,
|
| 27 |
+
"step": 219
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.0,
|
| 31 |
+
"learning_rate": 8.009132420091324e-05,
|
| 32 |
+
"loss": 0.086,
|
| 33 |
+
"step": 438
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.0,
|
| 37 |
+
"eval_accuracy": 0.9735676525217888,
|
| 38 |
+
"eval_f1": 0.9742805505352425,
|
| 39 |
+
"eval_loss": 0.08830533176660538,
|
| 40 |
+
"eval_precision": 0.9859313449634215,
|
| 41 |
+
"eval_recall": 0.9629018961253092,
|
| 42 |
+
"eval_roc_auc": 0.9740104718721784,
|
| 43 |
+
"eval_runtime": 7.2659,
|
| 44 |
+
"eval_samples_per_second": 963.269,
|
| 45 |
+
"eval_steps_per_second": 7.57,
|
| 46 |
+
"step": 438
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.0,
|
| 50 |
+
"learning_rate": 7.009132420091324e-05,
|
| 51 |
+
"loss": 0.0477,
|
| 52 |
+
"step": 657
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 3.0,
|
| 56 |
+
"eval_accuracy": 0.9728532647521074,
|
| 57 |
+
"eval_f1": 0.9737931034482759,
|
| 58 |
+
"eval_loss": 0.09442037343978882,
|
| 59 |
+
"eval_precision": 0.977568540570479,
|
| 60 |
+
"eval_recall": 0.9700467161308052,
|
| 61 |
+
"eval_roc_auc": 0.9729697866368312,
|
| 62 |
+
"eval_runtime": 7.2693,
|
| 63 |
+
"eval_samples_per_second": 962.82,
|
| 64 |
+
"eval_steps_per_second": 7.566,
|
| 65 |
+
"step": 657
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 4.0,
|
| 69 |
+
"learning_rate": 6.0091324200913244e-05,
|
| 70 |
+
"loss": 0.0269,
|
| 71 |
+
"step": 876
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 4.0,
|
| 75 |
+
"eval_accuracy": 0.9722817545363623,
|
| 76 |
+
"eval_f1": 0.9734246575342465,
|
| 77 |
+
"eval_loss": 0.12147631496191025,
|
| 78 |
+
"eval_precision": 0.9704998634252936,
|
| 79 |
+
"eval_recall": 0.9763671338279747,
|
| 80 |
+
"eval_roc_auc": 0.9721121383425587,
|
| 81 |
+
"eval_runtime": 7.2591,
|
| 82 |
+
"eval_samples_per_second": 964.173,
|
| 83 |
+
"eval_steps_per_second": 7.577,
|
| 84 |
+
"step": 876
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 5.0,
|
| 88 |
+
"learning_rate": 5.0091324200913245e-05,
|
| 89 |
+
"loss": 0.0146,
|
| 90 |
+
"step": 1095
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 5.0,
|
| 94 |
+
"eval_accuracy": 0.9742820402914703,
|
| 95 |
+
"eval_f1": 0.9750069425159679,
|
| 96 |
+
"eval_loss": 0.12991154193878174,
|
| 97 |
+
"eval_precision": 0.9854055571147909,
|
| 98 |
+
"eval_recall": 0.9648255015114042,
|
| 99 |
+
"eval_roc_auc": 0.9746746555176069,
|
| 100 |
+
"eval_runtime": 7.2686,
|
| 101 |
+
"eval_samples_per_second": 962.904,
|
| 102 |
+
"eval_steps_per_second": 7.567,
|
| 103 |
+
"step": 1095
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 6.0,
|
| 107 |
+
"learning_rate": 4.0091324200913246e-05,
|
| 108 |
+
"loss": 0.0069,
|
| 109 |
+
"step": 1314
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 6.0,
|
| 113 |
+
"eval_accuracy": 0.9749964280611516,
|
| 114 |
+
"eval_f1": 0.9758187094099765,
|
| 115 |
+
"eval_loss": 0.15036572515964508,
|
| 116 |
+
"eval_precision": 0.9813785436353529,
|
| 117 |
+
"eval_recall": 0.9703215169002474,
|
| 118 |
+
"eval_roc_auc": 0.9751905203548855,
|
| 119 |
+
"eval_runtime": 7.2605,
|
| 120 |
+
"eval_samples_per_second": 963.989,
|
| 121 |
+
"eval_steps_per_second": 7.575,
|
| 122 |
+
"step": 1314
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 7.0,
|
| 126 |
+
"learning_rate": 3.0091324200913247e-05,
|
| 127 |
+
"loss": 0.0044,
|
| 128 |
+
"step": 1533
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 7.0,
|
| 132 |
+
"eval_accuracy": 0.9742820402914703,
|
| 133 |
+
"eval_f1": 0.9751997795535962,
|
| 134 |
+
"eval_loss": 0.16526658833026886,
|
| 135 |
+
"eval_precision": 0.9778944459795523,
|
| 136 |
+
"eval_recall": 0.9725199230557846,
|
| 137 |
+
"eval_roc_auc": 0.9743551996231304,
|
| 138 |
+
"eval_runtime": 7.2696,
|
| 139 |
+
"eval_samples_per_second": 962.776,
|
| 140 |
+
"eval_steps_per_second": 7.566,
|
| 141 |
+
"step": 1533
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 8.0,
|
| 145 |
+
"learning_rate": 2.009132420091324e-05,
|
| 146 |
+
"loss": 0.0019,
|
| 147 |
+
"step": 1752
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 8.0,
|
| 151 |
+
"eval_accuracy": 0.9755679382768967,
|
| 152 |
+
"eval_f1": 0.9763779527559054,
|
| 153 |
+
"eval_loss": 0.18039505183696747,
|
| 154 |
+
"eval_precision": 0.9816666666666667,
|
| 155 |
+
"eval_recall": 0.9711459192085737,
|
| 156 |
+
"eval_roc_auc": 0.9757515310328582,
|
| 157 |
+
"eval_runtime": 7.2685,
|
| 158 |
+
"eval_samples_per_second": 962.918,
|
| 159 |
+
"eval_steps_per_second": 7.567,
|
| 160 |
+
"step": 1752
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 9.0,
|
| 164 |
+
"learning_rate": 1.0091324200913242e-05,
|
| 165 |
+
"loss": 0.0008,
|
| 166 |
+
"step": 1971
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 9.0,
|
| 170 |
+
"eval_accuracy": 0.9767109587083869,
|
| 171 |
+
"eval_f1": 0.9774581662287374,
|
| 172 |
+
"eval_loss": 0.18273666501045227,
|
| 173 |
+
"eval_precision": 0.9838530066815144,
|
| 174 |
+
"eval_recall": 0.9711459192085737,
|
| 175 |
+
"eval_roc_auc": 0.9769420072233344,
|
| 176 |
+
"eval_runtime": 7.2614,
|
| 177 |
+
"eval_samples_per_second": 963.859,
|
| 178 |
+
"eval_steps_per_second": 7.574,
|
| 179 |
+
"step": 1971
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 10.0,
|
| 183 |
+
"learning_rate": 9.132420091324201e-08,
|
| 184 |
+
"loss": 0.0008,
|
| 185 |
+
"step": 2190
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 10.0,
|
| 189 |
+
"eval_accuracy": 0.9769967138162595,
|
| 190 |
+
"eval_f1": 0.9777347531461762,
|
| 191 |
+
"eval_loss": 0.17970030009746552,
|
| 192 |
+
"eval_precision": 0.98413140311804,
|
| 193 |
+
"eval_recall": 0.9714207199780159,
|
| 194 |
+
"eval_roc_auc": 0.977228217131865,
|
| 195 |
+
"eval_runtime": 7.262,
|
| 196 |
+
"eval_samples_per_second": 963.777,
|
| 197 |
+
"eval_steps_per_second": 7.574,
|
| 198 |
+
"step": 2190
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 10.0,
|
| 202 |
+
"step": 2190,
|
| 203 |
+
"total_flos": 3.68250233081856e+16,
|
| 204 |
+
"train_loss": 0.040063528825431106,
|
| 205 |
+
"train_runtime": 1111.3299,
|
| 206 |
+
"train_samples_per_second": 251.878,
|
| 207 |
+
"train_steps_per_second": 1.971
|
| 208 |
+
}
|
| 209 |
+
],
|
| 210 |
+
"max_steps": 2190,
|
| 211 |
+
"num_train_epochs": 10,
|
| 212 |
+
"total_flos": 3.68250233081856e+16,
|
| 213 |
+
"trial_name": null,
|
| 214 |
+
"trial_params": null
|
| 215 |
+
}
|