End of training
Browse files- README.md +8 -6
- all_results.json +12 -12
- eval_results.json +8 -8
- train_results.json +4 -4
- trainer_state.json +431 -431
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: facebook/dinov2-base-imagenet1k-1-layer
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
|
@@ -18,13 +20,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# dinov2-base-imagenet1k-1-layer-finetuned-galaxy_mnist
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [facebook/dinov2-base-imagenet1k-1-layer](https://huggingface.co/facebook/dinov2-base-imagenet1k-1-layer) on
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
-
- Accuracy: 0.
|
| 25 |
-
- Precision: 0.
|
| 26 |
-
- Recall: 0.
|
| 27 |
-
- F1: 0.
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: facebook/dinov2-base-imagenet1k-1-layer
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- vision
|
| 7 |
- generated_from_trainer
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
|
|
|
| 20 |
|
| 21 |
# dinov2-base-imagenet1k-1-layer-finetuned-galaxy_mnist
|
| 22 |
|
| 23 |
+
This model is a fine-tuned version of [facebook/dinov2-base-imagenet1k-1-layer](https://huggingface.co/facebook/dinov2-base-imagenet1k-1-layer) on the matthieulel/galaxy_mnist dataset.
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
+
- Loss: 0.1875
|
| 26 |
+
- Accuracy: 0.9365
|
| 27 |
+
- Precision: 0.9367
|
| 28 |
+
- Recall: 0.9365
|
| 29 |
+
- F1: 0.9365
|
| 30 |
|
| 31 |
## Model description
|
| 32 |
|
all_results.json
CHANGED
|
@@ -1,15 +1,15 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 29.76,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime":
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second":
|
| 11 |
-
"train_loss": 0.
|
| 12 |
-
"train_runtime":
|
| 13 |
-
"train_samples_per_second":
|
| 14 |
-
"train_steps_per_second": 0.
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 29.76,
|
| 3 |
+
"eval_accuracy": 0.9365,
|
| 4 |
+
"eval_f1": 0.9365419334555197,
|
| 5 |
+
"eval_loss": 0.18749217689037323,
|
| 6 |
+
"eval_precision": 0.9367142468929726,
|
| 7 |
+
"eval_recall": 0.9365,
|
| 8 |
+
"eval_runtime": 15.7828,
|
| 9 |
+
"eval_samples_per_second": 126.72,
|
| 10 |
+
"eval_steps_per_second": 2.028,
|
| 11 |
+
"train_loss": 0.2331973833422507,
|
| 12 |
+
"train_runtime": 4457.686,
|
| 13 |
+
"train_samples_per_second": 53.84,
|
| 14 |
+
"train_steps_per_second": 0.209
|
| 15 |
}
|
eval_results.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 29.76,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime":
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second":
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 29.76,
|
| 3 |
+
"eval_accuracy": 0.9365,
|
| 4 |
+
"eval_f1": 0.9365419334555197,
|
| 5 |
+
"eval_loss": 0.18749217689037323,
|
| 6 |
+
"eval_precision": 0.9367142468929726,
|
| 7 |
+
"eval_recall": 0.9365,
|
| 8 |
+
"eval_runtime": 15.7828,
|
| 9 |
+
"eval_samples_per_second": 126.72,
|
| 10 |
+
"eval_steps_per_second": 2.028
|
| 11 |
}
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 29.76,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second": 0.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 29.76,
|
| 3 |
+
"train_loss": 0.2331973833422507,
|
| 4 |
+
"train_runtime": 4457.686,
|
| 5 |
+
"train_samples_per_second": 53.84,
|
| 6 |
+
"train_steps_per_second": 0.209
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "dinov2-base-imagenet1k-1-layer-finetuned-galaxy_mnist/checkpoint-
|
| 4 |
"epoch": 29.76,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 930,
|
|
@@ -10,930 +10,930 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.32,
|
| 13 |
-
"learning_rate": 5.376344086021506e-
|
| 14 |
-
"loss": 1.
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.64,
|
| 19 |
-
"learning_rate": 1.
|
| 20 |
-
"loss":
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.96,
|
| 25 |
-
"learning_rate": 1.
|
| 26 |
-
"loss": 0.
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.99,
|
| 31 |
-
"eval_accuracy": 0.
|
| 32 |
-
"eval_f1": 0.
|
| 33 |
-
"eval_loss": 0.
|
| 34 |
-
"eval_precision": 0.
|
| 35 |
-
"eval_recall": 0.
|
| 36 |
-
"eval_runtime":
|
| 37 |
-
"eval_samples_per_second":
|
| 38 |
-
"eval_steps_per_second": 1.
|
| 39 |
"step": 31
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 1.28,
|
| 43 |
-
"learning_rate": 2.
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 40
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 1.6,
|
| 49 |
-
"learning_rate": 2.
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 50
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 1.92,
|
| 55 |
-
"learning_rate": 3.
|
| 56 |
-
"loss": 0.
|
| 57 |
"step": 60
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 1.98,
|
| 61 |
-
"eval_accuracy": 0.
|
| 62 |
-
"eval_f1": 0.
|
| 63 |
-
"eval_loss": 0.
|
| 64 |
-
"eval_precision": 0.
|
| 65 |
-
"eval_recall": 0.
|
| 66 |
-
"eval_runtime":
|
| 67 |
-
"eval_samples_per_second":
|
| 68 |
-
"eval_steps_per_second": 1.
|
| 69 |
"step": 62
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 2.24,
|
| 73 |
-
"learning_rate": 3.763440860215054e-
|
| 74 |
-
"loss": 0.
|
| 75 |
"step": 70
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 2.56,
|
| 79 |
-
"learning_rate": 4.
|
| 80 |
-
"loss": 0.
|
| 81 |
"step": 80
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 2.88,
|
| 85 |
-
"learning_rate": 4.
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 90
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 2.98,
|
| 91 |
-
"eval_accuracy": 0.
|
| 92 |
-
"eval_f1": 0.
|
| 93 |
-
"eval_loss": 0.
|
| 94 |
-
"eval_precision": 0.
|
| 95 |
-
"eval_recall": 0.
|
| 96 |
-
"eval_runtime":
|
| 97 |
-
"eval_samples_per_second":
|
| 98 |
-
"eval_steps_per_second": 1.
|
| 99 |
"step": 93
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 3.2,
|
| 103 |
-
"learning_rate": 4.9581839904420555e-
|
| 104 |
-
"loss": 0.
|
| 105 |
"step": 100
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 3.52,
|
| 109 |
-
"learning_rate": 4.898446833930705e-
|
| 110 |
-
"loss": 0.
|
| 111 |
"step": 110
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 3.84,
|
| 115 |
-
"learning_rate": 4.
|
| 116 |
-
"loss": 0.
|
| 117 |
"step": 120
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 4.0,
|
| 121 |
-
"eval_accuracy": 0.
|
| 122 |
-
"eval_f1": 0.
|
| 123 |
-
"eval_loss": 0.
|
| 124 |
-
"eval_precision": 0.
|
| 125 |
-
"eval_recall": 0.
|
| 126 |
-
"eval_runtime":
|
| 127 |
-
"eval_samples_per_second":
|
| 128 |
-
"eval_steps_per_second": 1.
|
| 129 |
"step": 125
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 4.16,
|
| 133 |
-
"learning_rate": 4.
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 130
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 4.48,
|
| 139 |
-
"learning_rate": 4.
|
| 140 |
-
"loss": 0.
|
| 141 |
"step": 140
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 4.8,
|
| 145 |
-
"learning_rate": 4.659498207885305e-
|
| 146 |
-
"loss": 0.
|
| 147 |
"step": 150
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 4.99,
|
| 151 |
-
"eval_accuracy": 0.
|
| 152 |
-
"eval_f1": 0.
|
| 153 |
-
"eval_loss": 0.
|
| 154 |
-
"eval_precision": 0.
|
| 155 |
-
"eval_recall": 0.
|
| 156 |
-
"eval_runtime":
|
| 157 |
-
"eval_samples_per_second":
|
| 158 |
-
"eval_steps_per_second": 1.
|
| 159 |
"step": 156
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 5.12,
|
| 163 |
-
"learning_rate": 4.
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 160
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 5.44,
|
| 169 |
-
"learning_rate": 4.
|
| 170 |
-
"loss": 0.
|
| 171 |
"step": 170
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 5.76,
|
| 175 |
-
"learning_rate": 4.
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 180
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 5.98,
|
| 181 |
-
"eval_accuracy": 0.
|
| 182 |
-
"eval_f1": 0.
|
| 183 |
-
"eval_loss": 0.
|
| 184 |
-
"eval_precision": 0.
|
| 185 |
-
"eval_recall": 0.
|
| 186 |
-
"eval_runtime":
|
| 187 |
-
"eval_samples_per_second":
|
| 188 |
-
"eval_steps_per_second": 1.
|
| 189 |
"step": 187
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 6.08,
|
| 193 |
-
"learning_rate": 4.420549581839905e-
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 190
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 6.4,
|
| 199 |
-
"learning_rate": 4.360812425328555e-
|
| 200 |
-
"loss": 0.
|
| 201 |
"step": 200
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 6.72,
|
| 205 |
-
"learning_rate": 4.
|
| 206 |
-
"loss": 0.
|
| 207 |
"step": 210
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 6.98,
|
| 211 |
-
"eval_accuracy": 0.
|
| 212 |
-
"eval_f1": 0.
|
| 213 |
-
"eval_loss": 0.
|
| 214 |
-
"eval_precision": 0.
|
| 215 |
-
"eval_recall": 0.
|
| 216 |
-
"eval_runtime":
|
| 217 |
-
"eval_samples_per_second":
|
| 218 |
-
"eval_steps_per_second": 1.
|
| 219 |
"step": 218
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 7.04,
|
| 223 |
-
"learning_rate": 4.
|
| 224 |
-
"loss": 0.
|
| 225 |
"step": 220
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 7.36,
|
| 229 |
-
"learning_rate": 4.
|
| 230 |
-
"loss": 0.
|
| 231 |
"step": 230
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 7.68,
|
| 235 |
-
"learning_rate": 4.
|
| 236 |
-
"loss": 0.
|
| 237 |
"step": 240
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 8.0,
|
| 241 |
-
"learning_rate": 4.062126642771804e-
|
| 242 |
-
"loss": 0.
|
| 243 |
"step": 250
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 8.0,
|
| 247 |
-
"eval_accuracy": 0.
|
| 248 |
-
"eval_f1": 0.
|
| 249 |
-
"eval_loss": 0.
|
| 250 |
-
"eval_precision": 0.
|
| 251 |
-
"eval_recall": 0.
|
| 252 |
-
"eval_runtime":
|
| 253 |
-
"eval_samples_per_second":
|
| 254 |
-
"eval_steps_per_second": 1.
|
| 255 |
"step": 250
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 8.32,
|
| 259 |
-
"learning_rate": 4.002389486260454e-
|
| 260 |
-
"loss": 0.
|
| 261 |
"step": 260
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 8.64,
|
| 265 |
-
"learning_rate": 3.
|
| 266 |
-
"loss": 0.
|
| 267 |
"step": 270
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 8.96,
|
| 271 |
-
"learning_rate": 3.882915173237754e-
|
| 272 |
-
"loss": 0.
|
| 273 |
"step": 280
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 8.99,
|
| 277 |
-
"eval_accuracy": 0.
|
| 278 |
-
"eval_f1": 0.
|
| 279 |
-
"eval_loss": 0.
|
| 280 |
-
"eval_precision": 0.
|
| 281 |
-
"eval_recall": 0.
|
| 282 |
-
"eval_runtime":
|
| 283 |
-
"eval_samples_per_second":
|
| 284 |
-
"eval_steps_per_second": 1.
|
| 285 |
"step": 281
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 9.28,
|
| 289 |
-
"learning_rate": 3.
|
| 290 |
-
"loss": 0.
|
| 291 |
"step": 290
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 9.6,
|
| 295 |
-
"learning_rate": 3.763440860215054e-
|
| 296 |
-
"loss": 0.
|
| 297 |
"step": 300
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 9.92,
|
| 301 |
-
"learning_rate": 3.7037037037037037e-
|
| 302 |
-
"loss": 0.
|
| 303 |
"step": 310
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 9.98,
|
| 307 |
-
"eval_accuracy": 0.
|
| 308 |
-
"eval_f1": 0.
|
| 309 |
-
"eval_loss": 0.
|
| 310 |
-
"eval_precision": 0.
|
| 311 |
-
"eval_recall": 0.
|
| 312 |
-
"eval_runtime":
|
| 313 |
-
"eval_samples_per_second":
|
| 314 |
-
"eval_steps_per_second": 1.
|
| 315 |
"step": 312
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 10.24,
|
| 319 |
-
"learning_rate": 3.643966547192354e-
|
| 320 |
-
"loss": 0.
|
| 321 |
"step": 320
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 10.56,
|
| 325 |
-
"learning_rate": 3.
|
| 326 |
-
"loss": 0.
|
| 327 |
"step": 330
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 10.88,
|
| 331 |
-
"learning_rate": 3.
|
| 332 |
-
"loss": 0.
|
| 333 |
"step": 340
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 10.98,
|
| 337 |
-
"eval_accuracy": 0.
|
| 338 |
-
"eval_f1": 0.
|
| 339 |
-
"eval_loss": 0.
|
| 340 |
-
"eval_precision": 0.
|
| 341 |
-
"eval_recall": 0.
|
| 342 |
-
"eval_runtime":
|
| 343 |
-
"eval_samples_per_second":
|
| 344 |
-
"eval_steps_per_second": 1.
|
| 345 |
"step": 343
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 11.2,
|
| 349 |
-
"learning_rate": 3.
|
| 350 |
-
"loss": 0.
|
| 351 |
"step": 350
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 11.52,
|
| 355 |
-
"learning_rate": 3.
|
| 356 |
-
"loss": 0.
|
| 357 |
"step": 360
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"epoch": 11.84,
|
| 361 |
-
"learning_rate": 3.3452807646356034e-
|
| 362 |
-
"loss": 0.
|
| 363 |
"step": 370
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 12.0,
|
| 367 |
-
"eval_accuracy": 0.
|
| 368 |
-
"eval_f1": 0.
|
| 369 |
-
"eval_loss": 0.
|
| 370 |
-
"eval_precision": 0.
|
| 371 |
-
"eval_recall": 0.
|
| 372 |
-
"eval_runtime":
|
| 373 |
-
"eval_samples_per_second":
|
| 374 |
-
"eval_steps_per_second":
|
| 375 |
"step": 375
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 12.16,
|
| 379 |
-
"learning_rate": 3.
|
| 380 |
-
"loss": 0.
|
| 381 |
"step": 380
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 12.48,
|
| 385 |
-
"learning_rate": 3.
|
| 386 |
-
"loss": 0.
|
| 387 |
"step": 390
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 12.8,
|
| 391 |
-
"learning_rate": 3.
|
| 392 |
-
"loss": 0.
|
| 393 |
"step": 400
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 12.99,
|
| 397 |
-
"eval_accuracy": 0.
|
| 398 |
-
"eval_f1": 0.
|
| 399 |
-
"eval_loss": 0.
|
| 400 |
-
"eval_precision": 0.
|
| 401 |
-
"eval_recall": 0.
|
| 402 |
-
"eval_runtime":
|
| 403 |
-
"eval_samples_per_second":
|
| 404 |
-
"eval_steps_per_second": 1.
|
| 405 |
"step": 406
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"epoch": 13.12,
|
| 409 |
-
"learning_rate": 3.
|
| 410 |
-
"loss": 0.
|
| 411 |
"step": 410
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 13.44,
|
| 415 |
-
"learning_rate": 3.
|
| 416 |
-
"loss": 0.
|
| 417 |
"step": 420
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 13.76,
|
| 421 |
-
"learning_rate": 2.
|
| 422 |
-
"loss": 0.
|
| 423 |
"step": 430
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 13.98,
|
| 427 |
-
"eval_accuracy": 0.
|
| 428 |
-
"eval_f1": 0.
|
| 429 |
-
"eval_loss": 0.
|
| 430 |
-
"eval_precision": 0.
|
| 431 |
-
"eval_recall": 0.
|
| 432 |
-
"eval_runtime":
|
| 433 |
-
"eval_samples_per_second":
|
| 434 |
-
"eval_steps_per_second": 1.
|
| 435 |
"step": 437
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 14.08,
|
| 439 |
-
"learning_rate": 2.
|
| 440 |
-
"loss": 0.
|
| 441 |
"step": 440
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 14.4,
|
| 445 |
-
"learning_rate": 2.
|
| 446 |
-
"loss": 0.
|
| 447 |
"step": 450
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 14.72,
|
| 451 |
-
"learning_rate": 2.807646356033453e-
|
| 452 |
-
"loss": 0.
|
| 453 |
"step": 460
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 14.98,
|
| 457 |
-
"eval_accuracy": 0.
|
| 458 |
-
"eval_f1": 0.
|
| 459 |
-
"eval_loss": 0.
|
| 460 |
-
"eval_precision": 0.
|
| 461 |
-
"eval_recall": 0.
|
| 462 |
-
"eval_runtime":
|
| 463 |
-
"eval_samples_per_second":
|
| 464 |
-
"eval_steps_per_second": 1.
|
| 465 |
"step": 468
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 15.04,
|
| 469 |
-
"learning_rate": 2.747909199522103e-
|
| 470 |
-
"loss": 0.
|
| 471 |
"step": 470
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 15.36,
|
| 475 |
-
"learning_rate": 2.
|
| 476 |
-
"loss": 0.
|
| 477 |
"step": 480
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 15.68,
|
| 481 |
-
"learning_rate": 2.
|
| 482 |
-
"loss": 0.
|
| 483 |
"step": 490
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 16.0,
|
| 487 |
-
"learning_rate": 2.
|
| 488 |
-
"loss": 0.
|
| 489 |
"step": 500
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 16.0,
|
| 493 |
-
"eval_accuracy": 0.
|
| 494 |
-
"eval_f1": 0.
|
| 495 |
-
"eval_loss": 0.
|
| 496 |
-
"eval_precision": 0.
|
| 497 |
-
"eval_recall": 0.
|
| 498 |
-
"eval_runtime":
|
| 499 |
-
"eval_samples_per_second":
|
| 500 |
-
"eval_steps_per_second": 1.
|
| 501 |
"step": 500
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 16.32,
|
| 505 |
-
"learning_rate": 2.5089605734767026e-
|
| 506 |
-
"loss": 0.
|
| 507 |
"step": 510
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 16.64,
|
| 511 |
-
"learning_rate": 2.4492234169653525e-
|
| 512 |
-
"loss": 0.
|
| 513 |
"step": 520
|
| 514 |
},
|
| 515 |
{
|
| 516 |
"epoch": 16.96,
|
| 517 |
-
"learning_rate": 2.
|
| 518 |
-
"loss": 0.
|
| 519 |
"step": 530
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 16.99,
|
| 523 |
-
"eval_accuracy": 0.
|
| 524 |
-
"eval_f1": 0.
|
| 525 |
-
"eval_loss": 0.
|
| 526 |
-
"eval_precision": 0.
|
| 527 |
-
"eval_recall": 0.
|
| 528 |
-
"eval_runtime":
|
| 529 |
-
"eval_samples_per_second":
|
| 530 |
-
"eval_steps_per_second": 1.
|
| 531 |
"step": 531
|
| 532 |
},
|
| 533 |
{
|
| 534 |
"epoch": 17.28,
|
| 535 |
-
"learning_rate": 2.
|
| 536 |
-
"loss": 0.
|
| 537 |
"step": 540
|
| 538 |
},
|
| 539 |
{
|
| 540 |
"epoch": 17.6,
|
| 541 |
-
"learning_rate": 2.
|
| 542 |
-
"loss": 0.
|
| 543 |
"step": 550
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 17.92,
|
| 547 |
-
"learning_rate": 2.2102747909199524e-
|
| 548 |
-
"loss": 0.
|
| 549 |
"step": 560
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 17.98,
|
| 553 |
-
"eval_accuracy": 0.
|
| 554 |
-
"eval_f1": 0.
|
| 555 |
-
"eval_loss": 0.
|
| 556 |
-
"eval_precision": 0.
|
| 557 |
-
"eval_recall": 0.
|
| 558 |
-
"eval_runtime":
|
| 559 |
-
"eval_samples_per_second":
|
| 560 |
-
"eval_steps_per_second": 1.
|
| 561 |
"step": 562
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 18.24,
|
| 565 |
-
"learning_rate": 2.
|
| 566 |
-
"loss": 0.
|
| 567 |
"step": 570
|
| 568 |
},
|
| 569 |
{
|
| 570 |
"epoch": 18.56,
|
| 571 |
-
"learning_rate": 2.
|
| 572 |
-
"loss": 0.
|
| 573 |
"step": 580
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 18.88,
|
| 577 |
-
"learning_rate": 2.031063321385902e-
|
| 578 |
-
"loss": 0.
|
| 579 |
"step": 590
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 18.98,
|
| 583 |
-
"eval_accuracy": 0.
|
| 584 |
-
"eval_f1": 0.
|
| 585 |
-
"eval_loss": 0.
|
| 586 |
-
"eval_precision": 0.
|
| 587 |
-
"eval_recall": 0.
|
| 588 |
-
"eval_runtime":
|
| 589 |
-
"eval_samples_per_second":
|
| 590 |
-
"eval_steps_per_second": 1.
|
| 591 |
"step": 593
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 19.2,
|
| 595 |
-
"learning_rate": 1.
|
| 596 |
-
"loss": 0.
|
| 597 |
"step": 600
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 19.52,
|
| 601 |
-
"learning_rate": 1.
|
| 602 |
-
"loss": 0.
|
| 603 |
"step": 610
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 19.84,
|
| 607 |
-
"learning_rate": 1.
|
| 608 |
-
"loss": 0.
|
| 609 |
"step": 620
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 20.0,
|
| 613 |
-
"eval_accuracy": 0.
|
| 614 |
-
"eval_f1": 0.
|
| 615 |
-
"eval_loss": 0.
|
| 616 |
-
"eval_precision": 0.
|
| 617 |
-
"eval_recall": 0.
|
| 618 |
-
"eval_runtime":
|
| 619 |
-
"eval_samples_per_second":
|
| 620 |
-
"eval_steps_per_second": 1.
|
| 621 |
"step": 625
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 20.16,
|
| 625 |
-
"learning_rate": 1.
|
| 626 |
-
"loss": 0.
|
| 627 |
"step": 630
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 20.48,
|
| 631 |
-
"learning_rate": 1.7323775388291518e-
|
| 632 |
-
"loss": 0.
|
| 633 |
"step": 640
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 20.8,
|
| 637 |
-
"learning_rate": 1.6726403823178017e-
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 650
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 20.99,
|
| 643 |
-
"eval_accuracy": 0.
|
| 644 |
-
"eval_f1": 0.
|
| 645 |
-
"eval_loss": 0.
|
| 646 |
-
"eval_precision": 0.
|
| 647 |
-
"eval_recall": 0.
|
| 648 |
-
"eval_runtime":
|
| 649 |
-
"eval_samples_per_second":
|
| 650 |
-
"eval_steps_per_second": 1.
|
| 651 |
"step": 656
|
| 652 |
},
|
| 653 |
{
|
| 654 |
"epoch": 21.12,
|
| 655 |
-
"learning_rate": 1.
|
| 656 |
-
"loss": 0.
|
| 657 |
"step": 660
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"epoch": 21.44,
|
| 661 |
-
"learning_rate": 1.
|
| 662 |
-
"loss": 0.
|
| 663 |
"step": 670
|
| 664 |
},
|
| 665 |
{
|
| 666 |
"epoch": 21.76,
|
| 667 |
-
"learning_rate": 1.
|
| 668 |
-
"loss": 0.
|
| 669 |
"step": 680
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 21.98,
|
| 673 |
-
"eval_accuracy": 0.
|
| 674 |
-
"eval_f1": 0.
|
| 675 |
-
"eval_loss": 0.
|
| 676 |
-
"eval_precision": 0.
|
| 677 |
-
"eval_recall": 0.
|
| 678 |
-
"eval_runtime":
|
| 679 |
-
"eval_samples_per_second":
|
| 680 |
-
"eval_steps_per_second": 1.
|
| 681 |
"step": 687
|
| 682 |
},
|
| 683 |
{
|
| 684 |
"epoch": 22.08,
|
| 685 |
-
"learning_rate": 1.4336917562724014e-
|
| 686 |
-
"loss": 0.
|
| 687 |
"step": 690
|
| 688 |
},
|
| 689 |
{
|
| 690 |
"epoch": 22.4,
|
| 691 |
-
"learning_rate": 1.3739545997610515e-
|
| 692 |
-
"loss": 0.
|
| 693 |
"step": 700
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"epoch": 22.72,
|
| 697 |
-
"learning_rate": 1.
|
| 698 |
-
"loss": 0.
|
| 699 |
"step": 710
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 22.98,
|
| 703 |
-
"eval_accuracy": 0.
|
| 704 |
-
"eval_f1": 0.
|
| 705 |
-
"eval_loss": 0.
|
| 706 |
-
"eval_precision": 0.
|
| 707 |
-
"eval_recall": 0.
|
| 708 |
-
"eval_runtime":
|
| 709 |
-
"eval_samples_per_second":
|
| 710 |
-
"eval_steps_per_second": 1.
|
| 711 |
"step": 718
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 23.04,
|
| 715 |
-
"learning_rate": 1.2544802867383513e-
|
| 716 |
-
"loss": 0.
|
| 717 |
"step": 720
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 23.36,
|
| 721 |
-
"learning_rate": 1.
|
| 722 |
-
"loss": 0.
|
| 723 |
"step": 730
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 23.68,
|
| 727 |
-
"learning_rate": 1.
|
| 728 |
-
"loss": 0.
|
| 729 |
"step": 740
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 24.0,
|
| 733 |
-
"learning_rate": 1.
|
| 734 |
-
"loss": 0.
|
| 735 |
"step": 750
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 24.0,
|
| 739 |
-
"eval_accuracy": 0.
|
| 740 |
-
"eval_f1": 0.
|
| 741 |
-
"eval_loss": 0.
|
| 742 |
-
"eval_precision": 0.
|
| 743 |
-
"eval_recall": 0.
|
| 744 |
-
"eval_runtime":
|
| 745 |
-
"eval_samples_per_second":
|
| 746 |
-
"eval_steps_per_second": 1.
|
| 747 |
"step": 750
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 24.32,
|
| 751 |
-
"learning_rate": 1.015531660692951e-
|
| 752 |
-
"loss": 0.
|
| 753 |
"step": 760
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 24.64,
|
| 757 |
-
"learning_rate": 9.
|
| 758 |
-
"loss": 0.
|
| 759 |
"step": 770
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 24.96,
|
| 763 |
-
"learning_rate": 8.
|
| 764 |
-
"loss": 0.
|
| 765 |
"step": 780
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 24.99,
|
| 769 |
-
"eval_accuracy": 0.
|
| 770 |
-
"eval_f1": 0.
|
| 771 |
-
"eval_loss": 0.
|
| 772 |
-
"eval_precision": 0.
|
| 773 |
-
"eval_recall": 0.
|
| 774 |
-
"eval_runtime":
|
| 775 |
-
"eval_samples_per_second":
|
| 776 |
-
"eval_steps_per_second": 1.
|
| 777 |
"step": 781
|
| 778 |
},
|
| 779 |
{
|
| 780 |
"epoch": 25.28,
|
| 781 |
-
"learning_rate": 8.363201911589009e-
|
| 782 |
-
"loss": 0.
|
| 783 |
"step": 790
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 25.6,
|
| 787 |
-
"learning_rate": 7.765830346475508e-
|
| 788 |
-
"loss": 0.
|
| 789 |
"step": 800
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 25.92,
|
| 793 |
-
"learning_rate": 7.168458781362007e-
|
| 794 |
-
"loss": 0.
|
| 795 |
"step": 810
|
| 796 |
},
|
| 797 |
{
|
| 798 |
"epoch": 25.98,
|
| 799 |
-
"eval_accuracy": 0.
|
| 800 |
-
"eval_f1": 0.
|
| 801 |
-
"eval_loss": 0.
|
| 802 |
-
"eval_precision": 0.
|
| 803 |
-
"eval_recall": 0.
|
| 804 |
-
"eval_runtime":
|
| 805 |
-
"eval_samples_per_second":
|
| 806 |
-
"eval_steps_per_second": 1.
|
| 807 |
"step": 812
|
| 808 |
},
|
| 809 |
{
|
| 810 |
"epoch": 26.24,
|
| 811 |
-
"learning_rate": 6.
|
| 812 |
-
"loss": 0.
|
| 813 |
"step": 820
|
| 814 |
},
|
| 815 |
{
|
| 816 |
"epoch": 26.56,
|
| 817 |
-
"learning_rate": 5.
|
| 818 |
-
"loss": 0.
|
| 819 |
"step": 830
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"epoch": 26.88,
|
| 823 |
-
"learning_rate": 5.376344086021506e-
|
| 824 |
-
"loss": 0.
|
| 825 |
"step": 840
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 26.98,
|
| 829 |
-
"eval_accuracy": 0.
|
| 830 |
-
"eval_f1": 0.
|
| 831 |
-
"eval_loss": 0.
|
| 832 |
-
"eval_precision": 0.
|
| 833 |
-
"eval_recall": 0.
|
| 834 |
-
"eval_runtime":
|
| 835 |
-
"eval_samples_per_second":
|
| 836 |
-
"eval_steps_per_second": 1.
|
| 837 |
"step": 843
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 27.2,
|
| 841 |
-
"learning_rate": 4.
|
| 842 |
-
"loss": 0.
|
| 843 |
"step": 850
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 27.52,
|
| 847 |
-
"learning_rate": 4.
|
| 848 |
-
"loss": 0.
|
| 849 |
"step": 860
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 27.84,
|
| 853 |
-
"learning_rate": 3.
|
| 854 |
-
"loss": 0.
|
| 855 |
"step": 870
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 28.0,
|
| 859 |
-
"eval_accuracy": 0.
|
| 860 |
-
"eval_f1": 0.
|
| 861 |
-
"eval_loss": 0.
|
| 862 |
-
"eval_precision": 0.
|
| 863 |
-
"eval_recall": 0.
|
| 864 |
-
"eval_runtime":
|
| 865 |
-
"eval_samples_per_second":
|
| 866 |
-
"eval_steps_per_second": 1.
|
| 867 |
"step": 875
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 28.16,
|
| 871 |
-
"learning_rate": 2.
|
| 872 |
-
"loss": 0.
|
| 873 |
"step": 880
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"epoch": 28.48,
|
| 877 |
-
"learning_rate": 2.
|
| 878 |
-
"loss": 0.
|
| 879 |
"step": 890
|
| 880 |
},
|
| 881 |
{
|
| 882 |
"epoch": 28.8,
|
| 883 |
-
"learning_rate": 1.
|
| 884 |
-
"loss": 0.
|
| 885 |
"step": 900
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 28.99,
|
| 889 |
-
"eval_accuracy": 0.
|
| 890 |
-
"eval_f1": 0.
|
| 891 |
-
"eval_loss": 0.
|
| 892 |
-
"eval_precision": 0.
|
| 893 |
-
"eval_recall": 0.
|
| 894 |
-
"eval_runtime":
|
| 895 |
-
"eval_samples_per_second":
|
| 896 |
-
"eval_steps_per_second": 1.
|
| 897 |
"step": 906
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 29.12,
|
| 901 |
-
"learning_rate": 1.1947431302270014e-
|
| 902 |
-
"loss": 0.
|
| 903 |
"step": 910
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 29.44,
|
| 907 |
-
"learning_rate": 5.973715651135007e-
|
| 908 |
-
"loss": 0.
|
| 909 |
"step": 920
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 29.76,
|
| 913 |
"learning_rate": 0.0,
|
| 914 |
-
"loss": 0.
|
| 915 |
"step": 930
|
| 916 |
},
|
| 917 |
{
|
| 918 |
"epoch": 29.76,
|
| 919 |
-
"eval_accuracy": 0.
|
| 920 |
-
"eval_f1": 0.
|
| 921 |
-
"eval_loss": 0.
|
| 922 |
-
"eval_precision": 0.
|
| 923 |
-
"eval_recall": 0.
|
| 924 |
-
"eval_runtime":
|
| 925 |
-
"eval_samples_per_second":
|
| 926 |
-
"eval_steps_per_second": 1.
|
| 927 |
"step": 930
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 29.76,
|
| 931 |
"step": 930,
|
| 932 |
"total_flos": 2.4317906065576428e+19,
|
| 933 |
-
"train_loss": 0.
|
| 934 |
-
"train_runtime":
|
| 935 |
-
"train_samples_per_second":
|
| 936 |
-
"train_steps_per_second": 0.
|
| 937 |
}
|
| 938 |
],
|
| 939 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9365,
|
| 3 |
+
"best_model_checkpoint": "dinov2-base-imagenet1k-1-layer-finetuned-galaxy_mnist/checkpoint-593",
|
| 4 |
"epoch": 29.76,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 930,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.32,
|
| 13 |
+
"learning_rate": 5.376344086021506e-07,
|
| 14 |
+
"loss": 1.6159,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.64,
|
| 19 |
+
"learning_rate": 1.0752688172043011e-06,
|
| 20 |
+
"loss": 1.2128,
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.96,
|
| 25 |
+
"learning_rate": 1.6129032258064516e-06,
|
| 26 |
+
"loss": 0.8401,
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.99,
|
| 31 |
+
"eval_accuracy": 0.7605,
|
| 32 |
+
"eval_f1": 0.7542683716303844,
|
| 33 |
+
"eval_loss": 0.6220366358757019,
|
| 34 |
+
"eval_precision": 0.7579355479379479,
|
| 35 |
+
"eval_recall": 0.7605,
|
| 36 |
+
"eval_runtime": 17.2083,
|
| 37 |
+
"eval_samples_per_second": 116.223,
|
| 38 |
+
"eval_steps_per_second": 1.86,
|
| 39 |
"step": 31
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 1.28,
|
| 43 |
+
"learning_rate": 2.1505376344086023e-06,
|
| 44 |
+
"loss": 0.5859,
|
| 45 |
"step": 40
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 1.6,
|
| 49 |
+
"learning_rate": 2.688172043010753e-06,
|
| 50 |
+
"loss": 0.4302,
|
| 51 |
"step": 50
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 1.92,
|
| 55 |
+
"learning_rate": 3.225806451612903e-06,
|
| 56 |
+
"loss": 0.3857,
|
| 57 |
"step": 60
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 1.98,
|
| 61 |
+
"eval_accuracy": 0.8875,
|
| 62 |
+
"eval_f1": 0.8876656285967213,
|
| 63 |
+
"eval_loss": 0.26959437131881714,
|
| 64 |
+
"eval_precision": 0.8880762262738604,
|
| 65 |
+
"eval_recall": 0.8875,
|
| 66 |
+
"eval_runtime": 17.6301,
|
| 67 |
+
"eval_samples_per_second": 113.442,
|
| 68 |
+
"eval_steps_per_second": 1.815,
|
| 69 |
"step": 62
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 2.24,
|
| 73 |
+
"learning_rate": 3.763440860215054e-06,
|
| 74 |
+
"loss": 0.3494,
|
| 75 |
"step": 70
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 2.56,
|
| 79 |
+
"learning_rate": 4.3010752688172045e-06,
|
| 80 |
+
"loss": 0.3157,
|
| 81 |
"step": 80
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 2.88,
|
| 85 |
+
"learning_rate": 4.838709677419355e-06,
|
| 86 |
+
"loss": 0.3144,
|
| 87 |
"step": 90
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 2.98,
|
| 91 |
+
"eval_accuracy": 0.9015,
|
| 92 |
+
"eval_f1": 0.9010338577553875,
|
| 93 |
+
"eval_loss": 0.24912068247795105,
|
| 94 |
+
"eval_precision": 0.9028059173186274,
|
| 95 |
+
"eval_recall": 0.9015,
|
| 96 |
+
"eval_runtime": 17.2327,
|
| 97 |
+
"eval_samples_per_second": 116.059,
|
| 98 |
+
"eval_steps_per_second": 1.857,
|
| 99 |
"step": 93
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 3.2,
|
| 103 |
+
"learning_rate": 4.9581839904420555e-06,
|
| 104 |
+
"loss": 0.33,
|
| 105 |
"step": 100
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 3.52,
|
| 109 |
+
"learning_rate": 4.898446833930705e-06,
|
| 110 |
+
"loss": 0.2905,
|
| 111 |
"step": 110
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 3.84,
|
| 115 |
+
"learning_rate": 4.838709677419355e-06,
|
| 116 |
+
"loss": 0.2769,
|
| 117 |
"step": 120
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 4.0,
|
| 121 |
+
"eval_accuracy": 0.913,
|
| 122 |
+
"eval_f1": 0.9128412870419806,
|
| 123 |
+
"eval_loss": 0.21787521243095398,
|
| 124 |
+
"eval_precision": 0.9129249597927858,
|
| 125 |
+
"eval_recall": 0.913,
|
| 126 |
+
"eval_runtime": 17.4445,
|
| 127 |
+
"eval_samples_per_second": 114.649,
|
| 128 |
+
"eval_steps_per_second": 1.834,
|
| 129 |
"step": 125
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 4.16,
|
| 133 |
+
"learning_rate": 4.7789725209080055e-06,
|
| 134 |
+
"loss": 0.2902,
|
| 135 |
"step": 130
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 4.48,
|
| 139 |
+
"learning_rate": 4.719235364396655e-06,
|
| 140 |
+
"loss": 0.2569,
|
| 141 |
"step": 140
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 4.8,
|
| 145 |
+
"learning_rate": 4.659498207885305e-06,
|
| 146 |
+
"loss": 0.2858,
|
| 147 |
"step": 150
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 4.99,
|
| 151 |
+
"eval_accuracy": 0.9025,
|
| 152 |
+
"eval_f1": 0.9020162725126999,
|
| 153 |
+
"eval_loss": 0.2454933226108551,
|
| 154 |
+
"eval_precision": 0.9069644594388034,
|
| 155 |
+
"eval_recall": 0.9025,
|
| 156 |
+
"eval_runtime": 17.3381,
|
| 157 |
+
"eval_samples_per_second": 115.353,
|
| 158 |
+
"eval_steps_per_second": 1.846,
|
| 159 |
"step": 156
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 5.12,
|
| 163 |
+
"learning_rate": 4.599761051373955e-06,
|
| 164 |
+
"loss": 0.2735,
|
| 165 |
"step": 160
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 5.44,
|
| 169 |
+
"learning_rate": 4.540023894862605e-06,
|
| 170 |
+
"loss": 0.2562,
|
| 171 |
"step": 170
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 5.76,
|
| 175 |
+
"learning_rate": 4.480286738351255e-06,
|
| 176 |
+
"loss": 0.2704,
|
| 177 |
"step": 180
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 5.98,
|
| 181 |
+
"eval_accuracy": 0.9155,
|
| 182 |
+
"eval_f1": 0.9155929734022,
|
| 183 |
+
"eval_loss": 0.21211333572864532,
|
| 184 |
+
"eval_precision": 0.9233801924802966,
|
| 185 |
+
"eval_recall": 0.9155,
|
| 186 |
+
"eval_runtime": 16.9571,
|
| 187 |
+
"eval_samples_per_second": 117.945,
|
| 188 |
+
"eval_steps_per_second": 1.887,
|
| 189 |
"step": 187
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 6.08,
|
| 193 |
+
"learning_rate": 4.420549581839905e-06,
|
| 194 |
+
"loss": 0.2634,
|
| 195 |
"step": 190
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 6.4,
|
| 199 |
+
"learning_rate": 4.360812425328555e-06,
|
| 200 |
+
"loss": 0.2351,
|
| 201 |
"step": 200
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 6.72,
|
| 205 |
+
"learning_rate": 4.3010752688172045e-06,
|
| 206 |
+
"loss": 0.2557,
|
| 207 |
"step": 210
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 6.98,
|
| 211 |
+
"eval_accuracy": 0.9155,
|
| 212 |
+
"eval_f1": 0.9152474970088074,
|
| 213 |
+
"eval_loss": 0.2177189141511917,
|
| 214 |
+
"eval_precision": 0.9189605750516177,
|
| 215 |
+
"eval_recall": 0.9155,
|
| 216 |
+
"eval_runtime": 16.5188,
|
| 217 |
+
"eval_samples_per_second": 121.074,
|
| 218 |
+
"eval_steps_per_second": 1.937,
|
| 219 |
"step": 218
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 7.04,
|
| 223 |
+
"learning_rate": 4.241338112305855e-06,
|
| 224 |
+
"loss": 0.2624,
|
| 225 |
"step": 220
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 7.36,
|
| 229 |
+
"learning_rate": 4.181600955794505e-06,
|
| 230 |
+
"loss": 0.2364,
|
| 231 |
"step": 230
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 7.68,
|
| 235 |
+
"learning_rate": 4.121863799283155e-06,
|
| 236 |
+
"loss": 0.2416,
|
| 237 |
"step": 240
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 8.0,
|
| 241 |
+
"learning_rate": 4.062126642771804e-06,
|
| 242 |
+
"loss": 0.2069,
|
| 243 |
"step": 250
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 8.0,
|
| 247 |
+
"eval_accuracy": 0.9255,
|
| 248 |
+
"eval_f1": 0.9254810632455276,
|
| 249 |
+
"eval_loss": 0.18643927574157715,
|
| 250 |
+
"eval_precision": 0.9256381458578058,
|
| 251 |
+
"eval_recall": 0.9255,
|
| 252 |
+
"eval_runtime": 16.5437,
|
| 253 |
+
"eval_samples_per_second": 120.892,
|
| 254 |
+
"eval_steps_per_second": 1.934,
|
| 255 |
"step": 250
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 8.32,
|
| 259 |
+
"learning_rate": 4.002389486260454e-06,
|
| 260 |
+
"loss": 0.2402,
|
| 261 |
"step": 260
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 8.64,
|
| 265 |
+
"learning_rate": 3.942652329749105e-06,
|
| 266 |
+
"loss": 0.2509,
|
| 267 |
"step": 270
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 8.96,
|
| 271 |
+
"learning_rate": 3.882915173237754e-06,
|
| 272 |
+
"loss": 0.2344,
|
| 273 |
"step": 280
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 8.99,
|
| 277 |
+
"eval_accuracy": 0.923,
|
| 278 |
+
"eval_f1": 0.9230031822087664,
|
| 279 |
+
"eval_loss": 0.1893594115972519,
|
| 280 |
+
"eval_precision": 0.9236882399086506,
|
| 281 |
+
"eval_recall": 0.923,
|
| 282 |
+
"eval_runtime": 17.2256,
|
| 283 |
+
"eval_samples_per_second": 116.106,
|
| 284 |
+
"eval_steps_per_second": 1.858,
|
| 285 |
"step": 281
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 9.28,
|
| 289 |
+
"learning_rate": 3.823178016726404e-06,
|
| 290 |
+
"loss": 0.2187,
|
| 291 |
"step": 290
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 9.6,
|
| 295 |
+
"learning_rate": 3.763440860215054e-06,
|
| 296 |
+
"loss": 0.208,
|
| 297 |
"step": 300
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 9.92,
|
| 301 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 302 |
+
"loss": 0.1996,
|
| 303 |
"step": 310
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 9.98,
|
| 307 |
+
"eval_accuracy": 0.9235,
|
| 308 |
+
"eval_f1": 0.9233698349343116,
|
| 309 |
+
"eval_loss": 0.19926807284355164,
|
| 310 |
+
"eval_precision": 0.9259814793932657,
|
| 311 |
+
"eval_recall": 0.9235,
|
| 312 |
+
"eval_runtime": 17.2364,
|
| 313 |
+
"eval_samples_per_second": 116.033,
|
| 314 |
+
"eval_steps_per_second": 1.857,
|
| 315 |
"step": 312
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 10.24,
|
| 319 |
+
"learning_rate": 3.643966547192354e-06,
|
| 320 |
+
"loss": 0.2049,
|
| 321 |
"step": 320
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 10.56,
|
| 325 |
+
"learning_rate": 3.584229390681004e-06,
|
| 326 |
+
"loss": 0.2089,
|
| 327 |
"step": 330
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 10.88,
|
| 331 |
+
"learning_rate": 3.5244922341696534e-06,
|
| 332 |
+
"loss": 0.2011,
|
| 333 |
"step": 340
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 10.98,
|
| 337 |
+
"eval_accuracy": 0.928,
|
| 338 |
+
"eval_f1": 0.9279233986678691,
|
| 339 |
+
"eval_loss": 0.18277481198310852,
|
| 340 |
+
"eval_precision": 0.9279656529071406,
|
| 341 |
+
"eval_recall": 0.928,
|
| 342 |
+
"eval_runtime": 16.5403,
|
| 343 |
+
"eval_samples_per_second": 120.917,
|
| 344 |
+
"eval_steps_per_second": 1.935,
|
| 345 |
"step": 343
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 11.2,
|
| 349 |
+
"learning_rate": 3.4647550776583037e-06,
|
| 350 |
+
"loss": 0.1899,
|
| 351 |
"step": 350
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 11.52,
|
| 355 |
+
"learning_rate": 3.4050179211469536e-06,
|
| 356 |
+
"loss": 0.1961,
|
| 357 |
"step": 360
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"epoch": 11.84,
|
| 361 |
+
"learning_rate": 3.3452807646356034e-06,
|
| 362 |
+
"loss": 0.2229,
|
| 363 |
"step": 370
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 12.0,
|
| 367 |
+
"eval_accuracy": 0.9155,
|
| 368 |
+
"eval_f1": 0.9145163167356054,
|
| 369 |
+
"eval_loss": 0.23575706779956818,
|
| 370 |
+
"eval_precision": 0.9233304225050336,
|
| 371 |
+
"eval_recall": 0.9155,
|
| 372 |
+
"eval_runtime": 15.8252,
|
| 373 |
+
"eval_samples_per_second": 126.38,
|
| 374 |
+
"eval_steps_per_second": 2.022,
|
| 375 |
"step": 375
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 12.16,
|
| 379 |
+
"learning_rate": 3.2855436081242537e-06,
|
| 380 |
+
"loss": 0.1956,
|
| 381 |
"step": 380
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 12.48,
|
| 385 |
+
"learning_rate": 3.225806451612903e-06,
|
| 386 |
+
"loss": 0.2398,
|
| 387 |
"step": 390
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 12.8,
|
| 391 |
+
"learning_rate": 3.1660692951015535e-06,
|
| 392 |
+
"loss": 0.1792,
|
| 393 |
"step": 400
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 12.99,
|
| 397 |
+
"eval_accuracy": 0.9205,
|
| 398 |
+
"eval_f1": 0.9205455092354193,
|
| 399 |
+
"eval_loss": 0.18970580399036407,
|
| 400 |
+
"eval_precision": 0.9214418149774888,
|
| 401 |
+
"eval_recall": 0.9205,
|
| 402 |
+
"eval_runtime": 16.2468,
|
| 403 |
+
"eval_samples_per_second": 123.101,
|
| 404 |
+
"eval_steps_per_second": 1.97,
|
| 405 |
"step": 406
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"epoch": 13.12,
|
| 409 |
+
"learning_rate": 3.1063321385902034e-06,
|
| 410 |
+
"loss": 0.2103,
|
| 411 |
"step": 410
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 13.44,
|
| 415 |
+
"learning_rate": 3.0465949820788532e-06,
|
| 416 |
+
"loss": 0.1909,
|
| 417 |
"step": 420
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 13.76,
|
| 421 |
+
"learning_rate": 2.9868578255675035e-06,
|
| 422 |
+
"loss": 0.1898,
|
| 423 |
"step": 430
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 13.98,
|
| 427 |
+
"eval_accuracy": 0.921,
|
| 428 |
+
"eval_f1": 0.9208312467941863,
|
| 429 |
+
"eval_loss": 0.20168715715408325,
|
| 430 |
+
"eval_precision": 0.9216542515530398,
|
| 431 |
+
"eval_recall": 0.921,
|
| 432 |
+
"eval_runtime": 16.1466,
|
| 433 |
+
"eval_samples_per_second": 123.865,
|
| 434 |
+
"eval_steps_per_second": 1.982,
|
| 435 |
"step": 437
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 14.08,
|
| 439 |
+
"learning_rate": 2.9271206690561534e-06,
|
| 440 |
+
"loss": 0.1804,
|
| 441 |
"step": 440
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 14.4,
|
| 445 |
+
"learning_rate": 2.867383512544803e-06,
|
| 446 |
+
"loss": 0.2052,
|
| 447 |
"step": 450
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 14.72,
|
| 451 |
+
"learning_rate": 2.807646356033453e-06,
|
| 452 |
+
"loss": 0.1735,
|
| 453 |
"step": 460
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 14.98,
|
| 457 |
+
"eval_accuracy": 0.927,
|
| 458 |
+
"eval_f1": 0.9269426239594731,
|
| 459 |
+
"eval_loss": 0.1954416185617447,
|
| 460 |
+
"eval_precision": 0.9269718249595981,
|
| 461 |
+
"eval_recall": 0.927,
|
| 462 |
+
"eval_runtime": 16.9373,
|
| 463 |
+
"eval_samples_per_second": 118.083,
|
| 464 |
+
"eval_steps_per_second": 1.889,
|
| 465 |
"step": 468
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 15.04,
|
| 469 |
+
"learning_rate": 2.747909199522103e-06,
|
| 470 |
+
"loss": 0.1933,
|
| 471 |
"step": 470
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 15.36,
|
| 475 |
+
"learning_rate": 2.688172043010753e-06,
|
| 476 |
+
"loss": 0.1727,
|
| 477 |
"step": 480
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 15.68,
|
| 481 |
+
"learning_rate": 2.6284348864994032e-06,
|
| 482 |
+
"loss": 0.1835,
|
| 483 |
"step": 490
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 16.0,
|
| 487 |
+
"learning_rate": 2.5686977299880527e-06,
|
| 488 |
+
"loss": 0.1751,
|
| 489 |
"step": 500
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 16.0,
|
| 493 |
+
"eval_accuracy": 0.9295,
|
| 494 |
+
"eval_f1": 0.9294043091590938,
|
| 495 |
+
"eval_loss": 0.19178292155265808,
|
| 496 |
+
"eval_precision": 0.9299108071265199,
|
| 497 |
+
"eval_recall": 0.9295,
|
| 498 |
+
"eval_runtime": 17.2166,
|
| 499 |
+
"eval_samples_per_second": 116.167,
|
| 500 |
+
"eval_steps_per_second": 1.859,
|
| 501 |
"step": 500
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 16.32,
|
| 505 |
+
"learning_rate": 2.5089605734767026e-06,
|
| 506 |
+
"loss": 0.1912,
|
| 507 |
"step": 510
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 16.64,
|
| 511 |
+
"learning_rate": 2.4492234169653525e-06,
|
| 512 |
+
"loss": 0.1815,
|
| 513 |
"step": 520
|
| 514 |
},
|
| 515 |
{
|
| 516 |
"epoch": 16.96,
|
| 517 |
+
"learning_rate": 2.3894862604540028e-06,
|
| 518 |
+
"loss": 0.1732,
|
| 519 |
"step": 530
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 16.99,
|
| 523 |
+
"eval_accuracy": 0.922,
|
| 524 |
+
"eval_f1": 0.9218903176887637,
|
| 525 |
+
"eval_loss": 0.190641850233078,
|
| 526 |
+
"eval_precision": 0.9224739140720933,
|
| 527 |
+
"eval_recall": 0.922,
|
| 528 |
+
"eval_runtime": 17.563,
|
| 529 |
+
"eval_samples_per_second": 113.876,
|
| 530 |
+
"eval_steps_per_second": 1.822,
|
| 531 |
"step": 531
|
| 532 |
},
|
| 533 |
{
|
| 534 |
"epoch": 17.28,
|
| 535 |
+
"learning_rate": 2.3297491039426526e-06,
|
| 536 |
+
"loss": 0.1725,
|
| 537 |
"step": 540
|
| 538 |
},
|
| 539 |
{
|
| 540 |
"epoch": 17.6,
|
| 541 |
+
"learning_rate": 2.2700119474313025e-06,
|
| 542 |
+
"loss": 0.1766,
|
| 543 |
"step": 550
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 17.92,
|
| 547 |
+
"learning_rate": 2.2102747909199524e-06,
|
| 548 |
+
"loss": 0.1738,
|
| 549 |
"step": 560
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 17.98,
|
| 553 |
+
"eval_accuracy": 0.931,
|
| 554 |
+
"eval_f1": 0.9309560007388311,
|
| 555 |
+
"eval_loss": 0.18456581234931946,
|
| 556 |
+
"eval_precision": 0.9316696136336309,
|
| 557 |
+
"eval_recall": 0.931,
|
| 558 |
+
"eval_runtime": 17.21,
|
| 559 |
+
"eval_samples_per_second": 116.212,
|
| 560 |
+
"eval_steps_per_second": 1.859,
|
| 561 |
"step": 562
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 18.24,
|
| 565 |
+
"learning_rate": 2.1505376344086023e-06,
|
| 566 |
+
"loss": 0.1638,
|
| 567 |
"step": 570
|
| 568 |
},
|
| 569 |
{
|
| 570 |
"epoch": 18.56,
|
| 571 |
+
"learning_rate": 2.0908004778972526e-06,
|
| 572 |
+
"loss": 0.1695,
|
| 573 |
"step": 580
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 18.88,
|
| 577 |
+
"learning_rate": 2.031063321385902e-06,
|
| 578 |
+
"loss": 0.1694,
|
| 579 |
"step": 590
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 18.98,
|
| 583 |
+
"eval_accuracy": 0.9365,
|
| 584 |
+
"eval_f1": 0.9365419334555197,
|
| 585 |
+
"eval_loss": 0.18749217689037323,
|
| 586 |
+
"eval_precision": 0.9367142468929726,
|
| 587 |
+
"eval_recall": 0.9365,
|
| 588 |
+
"eval_runtime": 17.245,
|
| 589 |
+
"eval_samples_per_second": 115.976,
|
| 590 |
+
"eval_steps_per_second": 1.856,
|
| 591 |
"step": 593
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 19.2,
|
| 595 |
+
"learning_rate": 1.9713261648745523e-06,
|
| 596 |
+
"loss": 0.1627,
|
| 597 |
"step": 600
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 19.52,
|
| 601 |
+
"learning_rate": 1.911589008363202e-06,
|
| 602 |
+
"loss": 0.156,
|
| 603 |
"step": 610
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 19.84,
|
| 607 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 608 |
+
"loss": 0.1723,
|
| 609 |
"step": 620
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 20.0,
|
| 613 |
+
"eval_accuracy": 0.9285,
|
| 614 |
+
"eval_f1": 0.9283564470960457,
|
| 615 |
+
"eval_loss": 0.19414418935775757,
|
| 616 |
+
"eval_precision": 0.9293172724622787,
|
| 617 |
+
"eval_recall": 0.9285,
|
| 618 |
+
"eval_runtime": 17.3836,
|
| 619 |
+
"eval_samples_per_second": 115.051,
|
| 620 |
+
"eval_steps_per_second": 1.841,
|
| 621 |
"step": 625
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 20.16,
|
| 625 |
+
"learning_rate": 1.792114695340502e-06,
|
| 626 |
+
"loss": 0.1604,
|
| 627 |
"step": 630
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 20.48,
|
| 631 |
+
"learning_rate": 1.7323775388291518e-06,
|
| 632 |
+
"loss": 0.1688,
|
| 633 |
"step": 640
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 20.8,
|
| 637 |
+
"learning_rate": 1.6726403823178017e-06,
|
| 638 |
+
"loss": 0.1574,
|
| 639 |
"step": 650
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 20.99,
|
| 643 |
+
"eval_accuracy": 0.9335,
|
| 644 |
+
"eval_f1": 0.933604382541505,
|
| 645 |
+
"eval_loss": 0.19053442776203156,
|
| 646 |
+
"eval_precision": 0.933748843513901,
|
| 647 |
+
"eval_recall": 0.9335,
|
| 648 |
+
"eval_runtime": 17.3493,
|
| 649 |
+
"eval_samples_per_second": 115.278,
|
| 650 |
+
"eval_steps_per_second": 1.844,
|
| 651 |
"step": 656
|
| 652 |
},
|
| 653 |
{
|
| 654 |
"epoch": 21.12,
|
| 655 |
+
"learning_rate": 1.6129032258064516e-06,
|
| 656 |
+
"loss": 0.1514,
|
| 657 |
"step": 660
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"epoch": 21.44,
|
| 661 |
+
"learning_rate": 1.5531660692951017e-06,
|
| 662 |
+
"loss": 0.1396,
|
| 663 |
"step": 670
|
| 664 |
},
|
| 665 |
{
|
| 666 |
"epoch": 21.76,
|
| 667 |
+
"learning_rate": 1.4934289127837518e-06,
|
| 668 |
+
"loss": 0.1485,
|
| 669 |
"step": 680
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 21.98,
|
| 673 |
+
"eval_accuracy": 0.9315,
|
| 674 |
+
"eval_f1": 0.9314167545216125,
|
| 675 |
+
"eval_loss": 0.18693630397319794,
|
| 676 |
+
"eval_precision": 0.9313446931532684,
|
| 677 |
+
"eval_recall": 0.9315,
|
| 678 |
+
"eval_runtime": 20.8097,
|
| 679 |
+
"eval_samples_per_second": 96.109,
|
| 680 |
+
"eval_steps_per_second": 1.538,
|
| 681 |
"step": 687
|
| 682 |
},
|
| 683 |
{
|
| 684 |
"epoch": 22.08,
|
| 685 |
+
"learning_rate": 1.4336917562724014e-06,
|
| 686 |
+
"loss": 0.1316,
|
| 687 |
"step": 690
|
| 688 |
},
|
| 689 |
{
|
| 690 |
"epoch": 22.4,
|
| 691 |
+
"learning_rate": 1.3739545997610515e-06,
|
| 692 |
+
"loss": 0.1435,
|
| 693 |
"step": 700
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"epoch": 22.72,
|
| 697 |
+
"learning_rate": 1.3142174432497016e-06,
|
| 698 |
+
"loss": 0.1537,
|
| 699 |
"step": 710
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 22.98,
|
| 703 |
+
"eval_accuracy": 0.936,
|
| 704 |
+
"eval_f1": 0.9359520842741622,
|
| 705 |
+
"eval_loss": 0.18298617005348206,
|
| 706 |
+
"eval_precision": 0.9359672973348017,
|
| 707 |
+
"eval_recall": 0.936,
|
| 708 |
+
"eval_runtime": 17.2379,
|
| 709 |
+
"eval_samples_per_second": 116.023,
|
| 710 |
+
"eval_steps_per_second": 1.856,
|
| 711 |
"step": 718
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 23.04,
|
| 715 |
+
"learning_rate": 1.2544802867383513e-06,
|
| 716 |
+
"loss": 0.1349,
|
| 717 |
"step": 720
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 23.36,
|
| 721 |
+
"learning_rate": 1.1947431302270014e-06,
|
| 722 |
+
"loss": 0.1282,
|
| 723 |
"step": 730
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 23.68,
|
| 727 |
+
"learning_rate": 1.1350059737156513e-06,
|
| 728 |
+
"loss": 0.1408,
|
| 729 |
"step": 740
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 24.0,
|
| 733 |
+
"learning_rate": 1.0752688172043011e-06,
|
| 734 |
+
"loss": 0.1406,
|
| 735 |
"step": 750
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 24.0,
|
| 739 |
+
"eval_accuracy": 0.932,
|
| 740 |
+
"eval_f1": 0.9319845343042348,
|
| 741 |
+
"eval_loss": 0.19753658771514893,
|
| 742 |
+
"eval_precision": 0.9322001623351449,
|
| 743 |
+
"eval_recall": 0.932,
|
| 744 |
+
"eval_runtime": 17.216,
|
| 745 |
+
"eval_samples_per_second": 116.171,
|
| 746 |
+
"eval_steps_per_second": 1.859,
|
| 747 |
"step": 750
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 24.32,
|
| 751 |
+
"learning_rate": 1.015531660692951e-06,
|
| 752 |
+
"loss": 0.1217,
|
| 753 |
"step": 760
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 24.64,
|
| 757 |
+
"learning_rate": 9.55794504181601e-07,
|
| 758 |
+
"loss": 0.1475,
|
| 759 |
"step": 770
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 24.96,
|
| 763 |
+
"learning_rate": 8.96057347670251e-07,
|
| 764 |
+
"loss": 0.1326,
|
| 765 |
"step": 780
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 24.99,
|
| 769 |
+
"eval_accuracy": 0.9315,
|
| 770 |
+
"eval_f1": 0.9315212925629236,
|
| 771 |
+
"eval_loss": 0.1918136179447174,
|
| 772 |
+
"eval_precision": 0.9316398530410831,
|
| 773 |
+
"eval_recall": 0.9315,
|
| 774 |
+
"eval_runtime": 17.2178,
|
| 775 |
+
"eval_samples_per_second": 116.159,
|
| 776 |
+
"eval_steps_per_second": 1.859,
|
| 777 |
"step": 781
|
| 778 |
},
|
| 779 |
{
|
| 780 |
"epoch": 25.28,
|
| 781 |
+
"learning_rate": 8.363201911589009e-07,
|
| 782 |
+
"loss": 0.1423,
|
| 783 |
"step": 790
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 25.6,
|
| 787 |
+
"learning_rate": 7.765830346475508e-07,
|
| 788 |
+
"loss": 0.1462,
|
| 789 |
"step": 800
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 25.92,
|
| 793 |
+
"learning_rate": 7.168458781362007e-07,
|
| 794 |
+
"loss": 0.1238,
|
| 795 |
"step": 810
|
| 796 |
},
|
| 797 |
{
|
| 798 |
"epoch": 25.98,
|
| 799 |
+
"eval_accuracy": 0.9275,
|
| 800 |
+
"eval_f1": 0.9275714852684839,
|
| 801 |
+
"eval_loss": 0.21046194434165955,
|
| 802 |
+
"eval_precision": 0.9287568114219772,
|
| 803 |
+
"eval_recall": 0.9275,
|
| 804 |
+
"eval_runtime": 17.3304,
|
| 805 |
+
"eval_samples_per_second": 115.404,
|
| 806 |
+
"eval_steps_per_second": 1.846,
|
| 807 |
"step": 812
|
| 808 |
},
|
| 809 |
{
|
| 810 |
"epoch": 26.24,
|
| 811 |
+
"learning_rate": 6.571087216248508e-07,
|
| 812 |
+
"loss": 0.1275,
|
| 813 |
"step": 820
|
| 814 |
},
|
| 815 |
{
|
| 816 |
"epoch": 26.56,
|
| 817 |
+
"learning_rate": 5.973715651135007e-07,
|
| 818 |
+
"loss": 0.1417,
|
| 819 |
"step": 830
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"epoch": 26.88,
|
| 823 |
+
"learning_rate": 5.376344086021506e-07,
|
| 824 |
+
"loss": 0.1299,
|
| 825 |
"step": 840
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 26.98,
|
| 829 |
+
"eval_accuracy": 0.9325,
|
| 830 |
+
"eval_f1": 0.932381459503027,
|
| 831 |
+
"eval_loss": 0.20224767923355103,
|
| 832 |
+
"eval_precision": 0.9326921008972977,
|
| 833 |
+
"eval_recall": 0.9325,
|
| 834 |
+
"eval_runtime": 17.2957,
|
| 835 |
+
"eval_samples_per_second": 115.636,
|
| 836 |
+
"eval_steps_per_second": 1.85,
|
| 837 |
"step": 843
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 27.2,
|
| 841 |
+
"learning_rate": 4.778972520908006e-07,
|
| 842 |
+
"loss": 0.1393,
|
| 843 |
"step": 850
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 27.52,
|
| 847 |
+
"learning_rate": 4.1816009557945043e-07,
|
| 848 |
+
"loss": 0.1208,
|
| 849 |
"step": 860
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 27.84,
|
| 853 |
+
"learning_rate": 3.5842293906810036e-07,
|
| 854 |
+
"loss": 0.1387,
|
| 855 |
"step": 870
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 28.0,
|
| 859 |
+
"eval_accuracy": 0.9335,
|
| 860 |
+
"eval_f1": 0.9335696977145349,
|
| 861 |
+
"eval_loss": 0.20111316442489624,
|
| 862 |
+
"eval_precision": 0.9336932043728637,
|
| 863 |
+
"eval_recall": 0.9335,
|
| 864 |
+
"eval_runtime": 16.8699,
|
| 865 |
+
"eval_samples_per_second": 118.555,
|
| 866 |
+
"eval_steps_per_second": 1.897,
|
| 867 |
"step": 875
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 28.16,
|
| 871 |
+
"learning_rate": 2.9868578255675034e-07,
|
| 872 |
+
"loss": 0.1239,
|
| 873 |
"step": 880
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"epoch": 28.48,
|
| 877 |
+
"learning_rate": 2.389486260454003e-07,
|
| 878 |
+
"loss": 0.1357,
|
| 879 |
"step": 890
|
| 880 |
},
|
| 881 |
{
|
| 882 |
"epoch": 28.8,
|
| 883 |
+
"learning_rate": 1.7921146953405018e-07,
|
| 884 |
+
"loss": 0.1279,
|
| 885 |
"step": 900
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 28.99,
|
| 889 |
+
"eval_accuracy": 0.931,
|
| 890 |
+
"eval_f1": 0.9310154849548091,
|
| 891 |
+
"eval_loss": 0.20053213834762573,
|
| 892 |
+
"eval_precision": 0.931047750983443,
|
| 893 |
+
"eval_recall": 0.931,
|
| 894 |
+
"eval_runtime": 17.1937,
|
| 895 |
+
"eval_samples_per_second": 116.322,
|
| 896 |
+
"eval_steps_per_second": 1.861,
|
| 897 |
"step": 906
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 29.12,
|
| 901 |
+
"learning_rate": 1.1947431302270014e-07,
|
| 902 |
+
"loss": 0.1302,
|
| 903 |
"step": 910
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 29.44,
|
| 907 |
+
"learning_rate": 5.973715651135007e-08,
|
| 908 |
+
"loss": 0.1233,
|
| 909 |
"step": 920
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 29.76,
|
| 913 |
"learning_rate": 0.0,
|
| 914 |
+
"loss": 0.1256,
|
| 915 |
"step": 930
|
| 916 |
},
|
| 917 |
{
|
| 918 |
"epoch": 29.76,
|
| 919 |
+
"eval_accuracy": 0.931,
|
| 920 |
+
"eval_f1": 0.9310052979866259,
|
| 921 |
+
"eval_loss": 0.2003646343946457,
|
| 922 |
+
"eval_precision": 0.931012460623901,
|
| 923 |
+
"eval_recall": 0.931,
|
| 924 |
+
"eval_runtime": 17.2043,
|
| 925 |
+
"eval_samples_per_second": 116.25,
|
| 926 |
+
"eval_steps_per_second": 1.86,
|
| 927 |
"step": 930
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 29.76,
|
| 931 |
"step": 930,
|
| 932 |
"total_flos": 2.4317906065576428e+19,
|
| 933 |
+
"train_loss": 0.2331973833422507,
|
| 934 |
+
"train_runtime": 4457.686,
|
| 935 |
+
"train_samples_per_second": 53.84,
|
| 936 |
+
"train_steps_per_second": 0.209
|
| 937 |
}
|
| 938 |
],
|
| 939 |
"logging_steps": 10,
|