Edison
commited on
Commit
·
ce80dfa
1
Parent(s):
f443e36
End of training
Browse files- all_results.json +18 -0
- eval_results.json +13 -0
- train_results.json +8 -0
- trainer_state.json +196 -0
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9702625751344511,
|
| 4 |
+
"eval_f1": 0.9683927370544722,
|
| 5 |
+
"eval_loss": 0.11914637684822083,
|
| 6 |
+
"eval_precision": 0.9769335142469471,
|
| 7 |
+
"eval_recall": 0.96,
|
| 8 |
+
"eval_roc_auc": 0.9697652016857315,
|
| 9 |
+
"eval_runtime": 9.4949,
|
| 10 |
+
"eval_samples": 6322,
|
| 11 |
+
"eval_samples_per_second": 665.828,
|
| 12 |
+
"eval_steps_per_second": 5.266,
|
| 13 |
+
"train_loss": 0.11545699092274161,
|
| 14 |
+
"train_runtime": 488.0473,
|
| 15 |
+
"train_samples": 25287,
|
| 16 |
+
"train_samples_per_second": 155.438,
|
| 17 |
+
"train_steps_per_second": 1.217
|
| 18 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9702625751344511,
|
| 4 |
+
"eval_f1": 0.9683927370544722,
|
| 5 |
+
"eval_loss": 0.11914637684822083,
|
| 6 |
+
"eval_precision": 0.9769335142469471,
|
| 7 |
+
"eval_recall": 0.96,
|
| 8 |
+
"eval_roc_auc": 0.9697652016857315,
|
| 9 |
+
"eval_runtime": 9.4949,
|
| 10 |
+
"eval_samples": 6322,
|
| 11 |
+
"eval_samples_per_second": 665.828,
|
| 12 |
+
"eval_steps_per_second": 5.266
|
| 13 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.11545699092274161,
|
| 4 |
+
"train_runtime": 488.0473,
|
| 5 |
+
"train_samples": 25287,
|
| 6 |
+
"train_samples_per_second": 155.438,
|
| 7 |
+
"train_steps_per_second": 1.217
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 594,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.33,
|
| 12 |
+
"learning_rate": 8.905723905723906e-05,
|
| 13 |
+
"loss": 0.3716,
|
| 14 |
+
"step": 66
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.33,
|
| 18 |
+
"eval_accuracy": 0.9296108826320785,
|
| 19 |
+
"eval_f1": 0.9248945147679325,
|
| 20 |
+
"eval_loss": 0.20176392793655396,
|
| 21 |
+
"eval_precision": 0.9367521367521368,
|
| 22 |
+
"eval_recall": 0.9133333333333333,
|
| 23 |
+
"eval_roc_auc": 0.9288219947822597,
|
| 24 |
+
"eval_runtime": 9.531,
|
| 25 |
+
"eval_samples_per_second": 663.307,
|
| 26 |
+
"eval_steps_per_second": 5.246,
|
| 27 |
+
"step": 66
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.67,
|
| 31 |
+
"learning_rate": 7.794612794612795e-05,
|
| 32 |
+
"loss": 0.1745,
|
| 33 |
+
"step": 132
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.67,
|
| 37 |
+
"eval_accuracy": 0.9533375514077823,
|
| 38 |
+
"eval_f1": 0.9497530233350365,
|
| 39 |
+
"eval_loss": 0.14681555330753326,
|
| 40 |
+
"eval_precision": 0.9710902124695228,
|
| 41 |
+
"eval_recall": 0.9293333333333333,
|
| 42 |
+
"eval_roc_auc": 0.9521741922536624,
|
| 43 |
+
"eval_runtime": 9.5186,
|
| 44 |
+
"eval_samples_per_second": 664.175,
|
| 45 |
+
"eval_steps_per_second": 5.253,
|
| 46 |
+
"step": 132
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.0,
|
| 50 |
+
"learning_rate": 6.683501683501684e-05,
|
| 51 |
+
"loss": 0.1346,
|
| 52 |
+
"step": 198
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.0,
|
| 56 |
+
"eval_accuracy": 0.9656754191711484,
|
| 57 |
+
"eval_f1": 0.9633631605605266,
|
| 58 |
+
"eval_loss": 0.10907050222158432,
|
| 59 |
+
"eval_precision": 0.976052001368457,
|
| 60 |
+
"eval_recall": 0.951,
|
| 61 |
+
"eval_roc_auc": 0.9649641782059001,
|
| 62 |
+
"eval_runtime": 9.5208,
|
| 63 |
+
"eval_samples_per_second": 664.018,
|
| 64 |
+
"eval_steps_per_second": 5.252,
|
| 65 |
+
"step": 198
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.33,
|
| 69 |
+
"learning_rate": 5.572390572390572e-05,
|
| 70 |
+
"loss": 0.0917,
|
| 71 |
+
"step": 264
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.33,
|
| 75 |
+
"eval_accuracy": 0.9647263524201202,
|
| 76 |
+
"eval_f1": 0.9621969825394135,
|
| 77 |
+
"eval_loss": 0.12939223647117615,
|
| 78 |
+
"eval_precision": 0.9789582614694722,
|
| 79 |
+
"eval_recall": 0.946,
|
| 80 |
+
"eval_roc_auc": 0.9638187838651415,
|
| 81 |
+
"eval_runtime": 9.5288,
|
| 82 |
+
"eval_samples_per_second": 663.461,
|
| 83 |
+
"eval_steps_per_second": 5.247,
|
| 84 |
+
"step": 264
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.67,
|
| 88 |
+
"learning_rate": 4.4612794612794616e-05,
|
| 89 |
+
"loss": 0.0877,
|
| 90 |
+
"step": 330
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.67,
|
| 94 |
+
"eval_accuracy": 0.9667826637140146,
|
| 95 |
+
"eval_f1": 0.9651162790697674,
|
| 96 |
+
"eval_loss": 0.10901537537574768,
|
| 97 |
+
"eval_precision": 0.9619205298013245,
|
| 98 |
+
"eval_recall": 0.9683333333333334,
|
| 99 |
+
"eval_roc_auc": 0.9668578165763597,
|
| 100 |
+
"eval_runtime": 9.5197,
|
| 101 |
+
"eval_samples_per_second": 664.094,
|
| 102 |
+
"eval_steps_per_second": 5.252,
|
| 103 |
+
"step": 330
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 2.0,
|
| 107 |
+
"learning_rate": 3.35016835016835e-05,
|
| 108 |
+
"loss": 0.0731,
|
| 109 |
+
"step": 396
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.0,
|
| 113 |
+
"eval_accuracy": 0.9688389750079089,
|
| 114 |
+
"eval_f1": 0.9669074416260709,
|
| 115 |
+
"eval_loss": 0.10423740744590759,
|
| 116 |
+
"eval_precision": 0.9746020995597697,
|
| 117 |
+
"eval_recall": 0.9593333333333334,
|
| 118 |
+
"eval_roc_auc": 0.9683782861729882,
|
| 119 |
+
"eval_runtime": 9.5669,
|
| 120 |
+
"eval_samples_per_second": 660.818,
|
| 121 |
+
"eval_steps_per_second": 5.226,
|
| 122 |
+
"step": 396
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.33,
|
| 126 |
+
"learning_rate": 2.2390572390572393e-05,
|
| 127 |
+
"loss": 0.0342,
|
| 128 |
+
"step": 462
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.33,
|
| 132 |
+
"eval_accuracy": 0.969155330591585,
|
| 133 |
+
"eval_f1": 0.9674620390455532,
|
| 134 |
+
"eval_loss": 0.12906306982040405,
|
| 135 |
+
"eval_precision": 0.9685933845639826,
|
| 136 |
+
"eval_recall": 0.9663333333333334,
|
| 137 |
+
"eval_roc_auc": 0.9690185631145897,
|
| 138 |
+
"eval_runtime": 9.5007,
|
| 139 |
+
"eval_samples_per_second": 665.425,
|
| 140 |
+
"eval_steps_per_second": 5.263,
|
| 141 |
+
"step": 462
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 2.67,
|
| 145 |
+
"learning_rate": 1.127946127946128e-05,
|
| 146 |
+
"loss": 0.0375,
|
| 147 |
+
"step": 528
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 2.67,
|
| 151 |
+
"eval_accuracy": 0.9705789307181272,
|
| 152 |
+
"eval_f1": 0.9687919463087248,
|
| 153 |
+
"eval_loss": 0.12022514641284943,
|
| 154 |
+
"eval_precision": 0.9753378378378378,
|
| 155 |
+
"eval_recall": 0.9623333333333334,
|
| 156 |
+
"eval_roc_auc": 0.9701793096528197,
|
| 157 |
+
"eval_runtime": 9.5237,
|
| 158 |
+
"eval_samples_per_second": 663.816,
|
| 159 |
+
"eval_steps_per_second": 5.25,
|
| 160 |
+
"step": 528
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 3.0,
|
| 164 |
+
"learning_rate": 1.6835016835016834e-07,
|
| 165 |
+
"loss": 0.0342,
|
| 166 |
+
"step": 594
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 3.0,
|
| 170 |
+
"eval_accuracy": 0.9702625751344511,
|
| 171 |
+
"eval_f1": 0.9683927370544722,
|
| 172 |
+
"eval_loss": 0.11914637684822083,
|
| 173 |
+
"eval_precision": 0.9769335142469471,
|
| 174 |
+
"eval_recall": 0.96,
|
| 175 |
+
"eval_roc_auc": 0.9697652016857315,
|
| 176 |
+
"eval_runtime": 9.5437,
|
| 177 |
+
"eval_samples_per_second": 662.428,
|
| 178 |
+
"eval_steps_per_second": 5.239,
|
| 179 |
+
"step": 594
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 3.0,
|
| 183 |
+
"step": 594,
|
| 184 |
+
"total_flos": 9979933885332480.0,
|
| 185 |
+
"train_loss": 0.11545699092274161,
|
| 186 |
+
"train_runtime": 488.0473,
|
| 187 |
+
"train_samples_per_second": 155.438,
|
| 188 |
+
"train_steps_per_second": 1.217
|
| 189 |
+
}
|
| 190 |
+
],
|
| 191 |
+
"max_steps": 594,
|
| 192 |
+
"num_train_epochs": 3,
|
| 193 |
+
"total_flos": 9979933885332480.0,
|
| 194 |
+
"trial_name": null,
|
| 195 |
+
"trial_params": null
|
| 196 |
+
}
|