Training in progress, epoch 1
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- train_results.json +8 -0
- trainer_state.json +346 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 6.007692537881395e+17,
|
| 4 |
+
"train_loss": 0.08446450429527383,
|
| 5 |
+
"train_runtime": 456.2579,
|
| 6 |
+
"train_samples_per_second": 52.974,
|
| 7 |
+
"train_steps_per_second": 0.416
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 110395310
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddb55cab4e923fd21cd501f4bd4fd7abc6429cc70e608a5cd2ac5d23a87064af
|
| 3 |
size 110395310
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 6.007692537881395e+17,
|
| 4 |
+
"train_loss": 0.08446450429527383,
|
| 5 |
+
"train_runtime": 456.2579,
|
| 6 |
+
"train_samples_per_second": 52.974,
|
| 7 |
+
"train_steps_per_second": 0.416
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9962825278810409,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-fraud_number_classification/checkpoint-57",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 190,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.26,
|
| 13 |
+
"learning_rate": 1.3157894736842106e-05,
|
| 14 |
+
"loss": 0.7418,
|
| 15 |
+
"step": 5
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.53,
|
| 19 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 20 |
+
"loss": 0.6324,
|
| 21 |
+
"step": 10
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.79,
|
| 25 |
+
"learning_rate": 3.9473684210526316e-05,
|
| 26 |
+
"loss": 0.4532,
|
| 27 |
+
"step": 15
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.0,
|
| 31 |
+
"eval_accuracy": 0.9739776951672863,
|
| 32 |
+
"eval_loss": 0.1707221418619156,
|
| 33 |
+
"eval_runtime": 5.6354,
|
| 34 |
+
"eval_samples_per_second": 47.734,
|
| 35 |
+
"eval_steps_per_second": 1.597,
|
| 36 |
+
"step": 19
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.05,
|
| 40 |
+
"learning_rate": 4.970760233918128e-05,
|
| 41 |
+
"loss": 0.2697,
|
| 42 |
+
"step": 20
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.32,
|
| 46 |
+
"learning_rate": 4.824561403508772e-05,
|
| 47 |
+
"loss": 0.12,
|
| 48 |
+
"step": 25
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.58,
|
| 52 |
+
"learning_rate": 4.678362573099415e-05,
|
| 53 |
+
"loss": 0.1068,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.84,
|
| 58 |
+
"learning_rate": 4.5321637426900585e-05,
|
| 59 |
+
"loss": 0.0796,
|
| 60 |
+
"step": 35
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 2.0,
|
| 64 |
+
"eval_accuracy": 0.9851301115241635,
|
| 65 |
+
"eval_loss": 0.04716307297348976,
|
| 66 |
+
"eval_runtime": 2.8574,
|
| 67 |
+
"eval_samples_per_second": 94.14,
|
| 68 |
+
"eval_steps_per_second": 3.15,
|
| 69 |
+
"step": 38
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.11,
|
| 73 |
+
"learning_rate": 4.3859649122807014e-05,
|
| 74 |
+
"loss": 0.061,
|
| 75 |
+
"step": 40
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.37,
|
| 79 |
+
"learning_rate": 4.239766081871345e-05,
|
| 80 |
+
"loss": 0.056,
|
| 81 |
+
"step": 45
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.63,
|
| 85 |
+
"learning_rate": 4.093567251461988e-05,
|
| 86 |
+
"loss": 0.0429,
|
| 87 |
+
"step": 50
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.89,
|
| 91 |
+
"learning_rate": 3.9473684210526316e-05,
|
| 92 |
+
"loss": 0.0487,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.0,
|
| 97 |
+
"eval_accuracy": 0.9962825278810409,
|
| 98 |
+
"eval_loss": 0.01890862174332142,
|
| 99 |
+
"eval_runtime": 2.3569,
|
| 100 |
+
"eval_samples_per_second": 114.131,
|
| 101 |
+
"eval_steps_per_second": 3.819,
|
| 102 |
+
"step": 57
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 3.16,
|
| 106 |
+
"learning_rate": 3.8011695906432746e-05,
|
| 107 |
+
"loss": 0.0352,
|
| 108 |
+
"step": 60
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 3.42,
|
| 112 |
+
"learning_rate": 3.654970760233918e-05,
|
| 113 |
+
"loss": 0.0282,
|
| 114 |
+
"step": 65
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.68,
|
| 118 |
+
"learning_rate": 3.508771929824561e-05,
|
| 119 |
+
"loss": 0.0471,
|
| 120 |
+
"step": 70
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.95,
|
| 124 |
+
"learning_rate": 3.362573099415205e-05,
|
| 125 |
+
"loss": 0.0314,
|
| 126 |
+
"step": 75
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 4.0,
|
| 130 |
+
"eval_accuracy": 0.9925650557620818,
|
| 131 |
+
"eval_loss": 0.03749678283929825,
|
| 132 |
+
"eval_runtime": 2.3771,
|
| 133 |
+
"eval_samples_per_second": 113.161,
|
| 134 |
+
"eval_steps_per_second": 3.786,
|
| 135 |
+
"step": 76
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.21,
|
| 139 |
+
"learning_rate": 3.216374269005848e-05,
|
| 140 |
+
"loss": 0.0231,
|
| 141 |
+
"step": 80
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 4.47,
|
| 145 |
+
"learning_rate": 3.0701754385964913e-05,
|
| 146 |
+
"loss": 0.0274,
|
| 147 |
+
"step": 85
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 4.74,
|
| 151 |
+
"learning_rate": 2.9239766081871346e-05,
|
| 152 |
+
"loss": 0.0407,
|
| 153 |
+
"step": 90
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 5.0,
|
| 157 |
+
"learning_rate": 2.777777777777778e-05,
|
| 158 |
+
"loss": 0.0318,
|
| 159 |
+
"step": 95
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 5.0,
|
| 163 |
+
"eval_accuracy": 0.9925650557620818,
|
| 164 |
+
"eval_loss": 0.034306034445762634,
|
| 165 |
+
"eval_runtime": 2.3276,
|
| 166 |
+
"eval_samples_per_second": 115.57,
|
| 167 |
+
"eval_steps_per_second": 3.867,
|
| 168 |
+
"step": 95
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 5.26,
|
| 172 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 173 |
+
"loss": 0.0197,
|
| 174 |
+
"step": 100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 5.53,
|
| 178 |
+
"learning_rate": 2.485380116959064e-05,
|
| 179 |
+
"loss": 0.0201,
|
| 180 |
+
"step": 105
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 5.79,
|
| 184 |
+
"learning_rate": 2.3391812865497074e-05,
|
| 185 |
+
"loss": 0.0153,
|
| 186 |
+
"step": 110
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 6.0,
|
| 190 |
+
"eval_accuracy": 0.9776951672862454,
|
| 191 |
+
"eval_loss": 0.07378215342760086,
|
| 192 |
+
"eval_runtime": 2.2757,
|
| 193 |
+
"eval_samples_per_second": 118.205,
|
| 194 |
+
"eval_steps_per_second": 3.955,
|
| 195 |
+
"step": 114
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 6.05,
|
| 199 |
+
"learning_rate": 2.1929824561403507e-05,
|
| 200 |
+
"loss": 0.0304,
|
| 201 |
+
"step": 115
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 6.32,
|
| 205 |
+
"learning_rate": 2.046783625730994e-05,
|
| 206 |
+
"loss": 0.0161,
|
| 207 |
+
"step": 120
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 6.58,
|
| 211 |
+
"learning_rate": 1.9005847953216373e-05,
|
| 212 |
+
"loss": 0.0182,
|
| 213 |
+
"step": 125
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 6.84,
|
| 217 |
+
"learning_rate": 1.7543859649122806e-05,
|
| 218 |
+
"loss": 0.0145,
|
| 219 |
+
"step": 130
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.0,
|
| 223 |
+
"eval_accuracy": 0.9925650557620818,
|
| 224 |
+
"eval_loss": 0.02636624686419964,
|
| 225 |
+
"eval_runtime": 2.4304,
|
| 226 |
+
"eval_samples_per_second": 110.682,
|
| 227 |
+
"eval_steps_per_second": 3.703,
|
| 228 |
+
"step": 133
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 7.11,
|
| 232 |
+
"learning_rate": 1.608187134502924e-05,
|
| 233 |
+
"loss": 0.0347,
|
| 234 |
+
"step": 135
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 7.37,
|
| 238 |
+
"learning_rate": 1.4619883040935673e-05,
|
| 239 |
+
"loss": 0.0278,
|
| 240 |
+
"step": 140
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 7.63,
|
| 244 |
+
"learning_rate": 1.3157894736842106e-05,
|
| 245 |
+
"loss": 0.0124,
|
| 246 |
+
"step": 145
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 7.89,
|
| 250 |
+
"learning_rate": 1.1695906432748537e-05,
|
| 251 |
+
"loss": 0.01,
|
| 252 |
+
"step": 150
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 8.0,
|
| 256 |
+
"eval_accuracy": 0.9888475836431226,
|
| 257 |
+
"eval_loss": 0.0280575193464756,
|
| 258 |
+
"eval_runtime": 2.9148,
|
| 259 |
+
"eval_samples_per_second": 92.287,
|
| 260 |
+
"eval_steps_per_second": 3.088,
|
| 261 |
+
"step": 152
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 8.16,
|
| 265 |
+
"learning_rate": 1.023391812865497e-05,
|
| 266 |
+
"loss": 0.0136,
|
| 267 |
+
"step": 155
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 8.42,
|
| 271 |
+
"learning_rate": 8.771929824561403e-06,
|
| 272 |
+
"loss": 0.0118,
|
| 273 |
+
"step": 160
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 8.68,
|
| 277 |
+
"learning_rate": 7.3099415204678366e-06,
|
| 278 |
+
"loss": 0.0158,
|
| 279 |
+
"step": 165
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 8.95,
|
| 283 |
+
"learning_rate": 5.8479532163742686e-06,
|
| 284 |
+
"loss": 0.015,
|
| 285 |
+
"step": 170
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 9.0,
|
| 289 |
+
"eval_accuracy": 0.9888475836431226,
|
| 290 |
+
"eval_loss": 0.0480315163731575,
|
| 291 |
+
"eval_runtime": 2.7854,
|
| 292 |
+
"eval_samples_per_second": 96.574,
|
| 293 |
+
"eval_steps_per_second": 3.231,
|
| 294 |
+
"step": 171
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 9.21,
|
| 298 |
+
"learning_rate": 4.3859649122807014e-06,
|
| 299 |
+
"loss": 0.0076,
|
| 300 |
+
"step": 175
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 9.47,
|
| 304 |
+
"learning_rate": 2.9239766081871343e-06,
|
| 305 |
+
"loss": 0.0124,
|
| 306 |
+
"step": 180
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 9.74,
|
| 310 |
+
"learning_rate": 1.4619883040935671e-06,
|
| 311 |
+
"loss": 0.0132,
|
| 312 |
+
"step": 185
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 10.0,
|
| 316 |
+
"learning_rate": 0.0,
|
| 317 |
+
"loss": 0.0241,
|
| 318 |
+
"step": 190
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 10.0,
|
| 322 |
+
"eval_accuracy": 0.9888475836431226,
|
| 323 |
+
"eval_loss": 0.030204007402062416,
|
| 324 |
+
"eval_runtime": 2.2938,
|
| 325 |
+
"eval_samples_per_second": 117.271,
|
| 326 |
+
"eval_steps_per_second": 3.924,
|
| 327 |
+
"step": 190
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 10.0,
|
| 331 |
+
"step": 190,
|
| 332 |
+
"total_flos": 6.007692537881395e+17,
|
| 333 |
+
"train_loss": 0.08446450429527383,
|
| 334 |
+
"train_runtime": 456.2579,
|
| 335 |
+
"train_samples_per_second": 52.974,
|
| 336 |
+
"train_steps_per_second": 0.416
|
| 337 |
+
}
|
| 338 |
+
],
|
| 339 |
+
"logging_steps": 5,
|
| 340 |
+
"max_steps": 190,
|
| 341 |
+
"num_train_epochs": 10,
|
| 342 |
+
"save_steps": 500,
|
| 343 |
+
"total_flos": 6.007692537881395e+17,
|
| 344 |
+
"trial_name": null,
|
| 345 |
+
"trial_params": null
|
| 346 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:322de159de53868a66f22620b710025b03178196327a431952cfd5be14b565aa
|
| 3 |
size 4600
|