End of training
Browse files- README.md +5 -5
- all_results.json +12 -12
- eval_results.json +8 -8
- train_results.json +4 -4
- trainer_state.json +633 -633
README.md
CHANGED
|
@@ -23,11 +23,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 23 |
|
| 24 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the medmnist-v2 dataset.
|
| 25 |
It achieves the following results on the evaluation set:
|
| 26 |
-
- Loss: 0.
|
| 27 |
-
- Accuracy: 0.
|
| 28 |
-
- Precision: 0.
|
| 29 |
-
- Recall: 0.
|
| 30 |
-
- F1: 0.
|
| 31 |
|
| 32 |
## Model description
|
| 33 |
|
|
|
|
| 23 |
|
| 24 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the medmnist-v2 dataset.
|
| 25 |
It achieves the following results on the evaluation set:
|
| 26 |
+
- Loss: 0.2714
|
| 27 |
+
- Accuracy: 0.9141
|
| 28 |
+
- Precision: 0.9095
|
| 29 |
+
- Recall: 0.9007
|
| 30 |
+
- F1: 0.9042
|
| 31 |
|
| 32 |
## Model description
|
| 33 |
|
all_results.json
CHANGED
|
@@ -1,16 +1,16 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 9.99,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime": 44.
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second": 11.
|
| 11 |
"total_flos": 1.0133154899356189e+19,
|
| 12 |
-
"train_loss": 0.
|
| 13 |
-
"train_runtime":
|
| 14 |
-
"train_samples_per_second": 83.
|
| 15 |
-
"train_steps_per_second": 1.
|
| 16 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 9.99,
|
| 3 |
+
"eval_accuracy": 0.9141267537493952,
|
| 4 |
+
"eval_f1": 0.9041810830566877,
|
| 5 |
+
"eval_loss": 0.2713584899902344,
|
| 6 |
+
"eval_precision": 0.9094870552968058,
|
| 7 |
+
"eval_recall": 0.9007044159397597,
|
| 8 |
+
"eval_runtime": 44.7123,
|
| 9 |
+
"eval_samples_per_second": 184.915,
|
| 10 |
+
"eval_steps_per_second": 11.563,
|
| 11 |
"total_flos": 1.0133154899356189e+19,
|
| 12 |
+
"train_loss": 0.5615053875692959,
|
| 13 |
+
"train_runtime": 1549.2005,
|
| 14 |
+
"train_samples_per_second": 83.914,
|
| 15 |
+
"train_steps_per_second": 1.31
|
| 16 |
}
|
eval_results.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 9.99,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime": 44.
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second": 11.
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 9.99,
|
| 3 |
+
"eval_accuracy": 0.9141267537493952,
|
| 4 |
+
"eval_f1": 0.9041810830566877,
|
| 5 |
+
"eval_loss": 0.2713584899902344,
|
| 6 |
+
"eval_precision": 0.9094870552968058,
|
| 7 |
+
"eval_recall": 0.9007044159397597,
|
| 8 |
+
"eval_runtime": 44.7123,
|
| 9 |
+
"eval_samples_per_second": 184.915,
|
| 10 |
+
"eval_steps_per_second": 11.563
|
| 11 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 9.99,
|
| 3 |
"total_flos": 1.0133154899356189e+19,
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second": 83.
|
| 7 |
-
"train_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 9.99,
|
| 3 |
"total_flos": 1.0133154899356189e+19,
|
| 4 |
+
"train_loss": 0.5615053875692959,
|
| 5 |
+
"train_runtime": 1549.2005,
|
| 6 |
+
"train_samples_per_second": 83.914,
|
| 7 |
+
"train_steps_per_second": 1.31
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-lora-medmnistv2/checkpoint-
|
| 4 |
"epoch": 9.98769987699877,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 2030,
|
|
@@ -10,1553 +10,1553 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.05,
|
| 13 |
-
"grad_norm": 1.
|
| 14 |
"learning_rate": 0.004975369458128079,
|
| 15 |
-
"loss":
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.1,
|
| 20 |
-
"grad_norm":
|
| 21 |
"learning_rate": 0.004950738916256157,
|
| 22 |
-
"loss":
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.15,
|
| 27 |
-
"grad_norm": 1.
|
| 28 |
-
"learning_rate": 0.
|
| 29 |
-
"loss":
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.2,
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate": 0.
|
| 36 |
-
"loss":
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.25,
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.3,
|
| 48 |
-
"grad_norm": 1.
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.34,
|
| 55 |
-
"grad_norm": 1.
|
| 56 |
-
"learning_rate": 0.
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.39,
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate": 0.
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.44,
|
| 69 |
-
"grad_norm": 1.
|
| 70 |
-
"learning_rate": 0.
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.49,
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate": 0.
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.54,
|
| 83 |
-
"grad_norm":
|
| 84 |
-
"learning_rate": 0.
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.59,
|
| 90 |
-
"grad_norm": 1.
|
| 91 |
-
"learning_rate": 0.
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.64,
|
| 97 |
-
"grad_norm": 1.
|
| 98 |
-
"learning_rate": 0.
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.69,
|
| 104 |
-
"grad_norm": 1.
|
| 105 |
-
"learning_rate": 0.
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.74,
|
| 111 |
-
"grad_norm":
|
| 112 |
"learning_rate": 0.004635467980295567,
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.79,
|
| 118 |
-
"grad_norm":
|
| 119 |
"learning_rate": 0.004610837438423646,
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.84,
|
| 125 |
-
"grad_norm":
|
| 126 |
-
"learning_rate": 0.
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.89,
|
| 132 |
-
"grad_norm": 1.
|
| 133 |
"learning_rate": 0.004564039408866995,
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.93,
|
| 139 |
-
"grad_norm":
|
| 140 |
"learning_rate": 0.004539408866995074,
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 190
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.98,
|
| 146 |
-
"grad_norm":
|
| 147 |
"learning_rate": 0.004514778325123153,
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 200
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 1.0,
|
| 153 |
-
"eval_accuracy": 0.
|
| 154 |
-
"eval_f1": 0.
|
| 155 |
-
"eval_loss": 0.
|
| 156 |
-
"eval_precision": 0.
|
| 157 |
-
"eval_recall": 0.
|
| 158 |
-
"eval_runtime": 12.
|
| 159 |
-
"eval_samples_per_second": 186.
|
| 160 |
-
"eval_steps_per_second": 11.
|
| 161 |
"step": 203
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 1.03,
|
| 165 |
-
"grad_norm": 1.
|
| 166 |
"learning_rate": 0.004490147783251232,
|
| 167 |
-
"loss": 0.
|
| 168 |
"step": 210
|
| 169 |
},
|
| 170 |
{
|
| 171 |
"epoch": 1.08,
|
| 172 |
-
"grad_norm":
|
| 173 |
"learning_rate": 0.00446551724137931,
|
| 174 |
-
"loss": 0.
|
| 175 |
"step": 220
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"epoch": 1.13,
|
| 179 |
-
"grad_norm":
|
| 180 |
"learning_rate": 0.004440886699507389,
|
| 181 |
-
"loss": 0.
|
| 182 |
"step": 230
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 1.18,
|
| 186 |
-
"grad_norm":
|
| 187 |
"learning_rate": 0.004416256157635468,
|
| 188 |
-
"loss": 0.
|
| 189 |
"step": 240
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 1.23,
|
| 193 |
-
"grad_norm":
|
| 194 |
"learning_rate": 0.004391625615763547,
|
| 195 |
-
"loss": 0.
|
| 196 |
"step": 250
|
| 197 |
},
|
| 198 |
{
|
| 199 |
"epoch": 1.28,
|
| 200 |
-
"grad_norm":
|
| 201 |
"learning_rate": 0.004366995073891626,
|
| 202 |
-
"loss": 0.
|
| 203 |
"step": 260
|
| 204 |
},
|
| 205 |
{
|
| 206 |
"epoch": 1.33,
|
| 207 |
-
"grad_norm": 2.
|
| 208 |
"learning_rate": 0.004342364532019705,
|
| 209 |
-
"loss": 0.
|
| 210 |
"step": 270
|
| 211 |
},
|
| 212 |
{
|
| 213 |
"epoch": 1.38,
|
| 214 |
-
"grad_norm": 1.
|
| 215 |
"learning_rate": 0.004317733990147784,
|
| 216 |
-
"loss": 0.
|
| 217 |
"step": 280
|
| 218 |
},
|
| 219 |
{
|
| 220 |
"epoch": 1.43,
|
| 221 |
-
"grad_norm":
|
| 222 |
"learning_rate": 0.004293103448275862,
|
| 223 |
-
"loss": 0.
|
| 224 |
"step": 290
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 1.48,
|
| 228 |
-
"grad_norm": 1.
|
| 229 |
"learning_rate": 0.00426847290640394,
|
| 230 |
-
"loss": 0.
|
| 231 |
"step": 300
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 1.53,
|
| 235 |
-
"grad_norm":
|
| 236 |
"learning_rate": 0.004243842364532019,
|
| 237 |
-
"loss": 0.
|
| 238 |
"step": 310
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"epoch": 1.57,
|
| 242 |
-
"grad_norm":
|
| 243 |
"learning_rate": 0.0042192118226600985,
|
| 244 |
-
"loss": 0.
|
| 245 |
"step": 320
|
| 246 |
},
|
| 247 |
{
|
| 248 |
"epoch": 1.62,
|
| 249 |
-
"grad_norm":
|
| 250 |
"learning_rate": 0.004194581280788178,
|
| 251 |
-
"loss": 0.
|
| 252 |
"step": 330
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 1.67,
|
| 256 |
-
"grad_norm":
|
| 257 |
"learning_rate": 0.004169950738916256,
|
| 258 |
-
"loss": 0.
|
| 259 |
"step": 340
|
| 260 |
},
|
| 261 |
{
|
| 262 |
"epoch": 1.72,
|
| 263 |
-
"grad_norm":
|
| 264 |
"learning_rate": 0.004145320197044335,
|
| 265 |
-
"loss": 0.
|
| 266 |
"step": 350
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 1.77,
|
| 270 |
-
"grad_norm":
|
| 271 |
"learning_rate": 0.004120689655172414,
|
| 272 |
-
"loss": 0.
|
| 273 |
"step": 360
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 1.82,
|
| 277 |
-
"grad_norm":
|
| 278 |
"learning_rate": 0.004096059113300492,
|
| 279 |
-
"loss": 0.
|
| 280 |
"step": 370
|
| 281 |
},
|
| 282 |
{
|
| 283 |
"epoch": 1.87,
|
| 284 |
-
"grad_norm":
|
| 285 |
"learning_rate": 0.004071428571428571,
|
| 286 |
-
"loss": 0.
|
| 287 |
"step": 380
|
| 288 |
},
|
| 289 |
{
|
| 290 |
"epoch": 1.92,
|
| 291 |
-
"grad_norm":
|
| 292 |
"learning_rate": 0.00404679802955665,
|
| 293 |
-
"loss": 0.
|
| 294 |
"step": 390
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 1.97,
|
| 298 |
-
"grad_norm":
|
| 299 |
"learning_rate": 0.0040221674876847295,
|
| 300 |
-
"loss": 0.
|
| 301 |
"step": 400
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"epoch": 2.0,
|
| 305 |
-
"eval_accuracy": 0.
|
| 306 |
-
"eval_f1": 0.
|
| 307 |
-
"eval_loss": 0.
|
| 308 |
-
"eval_precision": 0.
|
| 309 |
-
"eval_recall": 0.
|
| 310 |
-
"eval_runtime": 12.
|
| 311 |
-
"eval_samples_per_second":
|
| 312 |
-
"eval_steps_per_second": 11.
|
| 313 |
"step": 406
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 2.02,
|
| 317 |
-
"grad_norm":
|
| 318 |
"learning_rate": 0.003997536945812808,
|
| 319 |
-
"loss": 0.
|
| 320 |
"step": 410
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 2.07,
|
| 324 |
-
"grad_norm": 3.
|
| 325 |
"learning_rate": 0.003972906403940887,
|
| 326 |
-
"loss":
|
| 327 |
"step": 420
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 2.12,
|
| 331 |
-
"grad_norm":
|
| 332 |
"learning_rate": 0.003948275862068966,
|
| 333 |
-
"loss": 0.
|
| 334 |
"step": 430
|
| 335 |
},
|
| 336 |
{
|
| 337 |
"epoch": 2.16,
|
| 338 |
-
"grad_norm":
|
| 339 |
"learning_rate": 0.003923645320197044,
|
| 340 |
-
"loss": 0.
|
| 341 |
"step": 440
|
| 342 |
},
|
| 343 |
{
|
| 344 |
"epoch": 2.21,
|
| 345 |
-
"grad_norm":
|
| 346 |
"learning_rate": 0.0038990147783251232,
|
| 347 |
-
"loss": 0.
|
| 348 |
"step": 450
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 2.26,
|
| 352 |
-
"grad_norm":
|
| 353 |
"learning_rate": 0.0038743842364532023,
|
| 354 |
-
"loss": 0.
|
| 355 |
"step": 460
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"epoch": 2.31,
|
| 359 |
-
"grad_norm":
|
| 360 |
"learning_rate": 0.003849753694581281,
|
| 361 |
-
"loss": 0.
|
| 362 |
"step": 470
|
| 363 |
},
|
| 364 |
{
|
| 365 |
"epoch": 2.36,
|
| 366 |
-
"grad_norm":
|
| 367 |
"learning_rate": 0.00382512315270936,
|
| 368 |
-
"loss": 0.
|
| 369 |
"step": 480
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 2.41,
|
| 373 |
-
"grad_norm": 2.
|
| 374 |
"learning_rate": 0.0038004926108374383,
|
| 375 |
-
"loss": 0.
|
| 376 |
"step": 490
|
| 377 |
},
|
| 378 |
{
|
| 379 |
"epoch": 2.46,
|
| 380 |
-
"grad_norm":
|
| 381 |
"learning_rate": 0.003775862068965517,
|
| 382 |
-
"loss": 0.
|
| 383 |
"step": 500
|
| 384 |
},
|
| 385 |
{
|
| 386 |
"epoch": 2.51,
|
| 387 |
-
"grad_norm": 3.
|
| 388 |
"learning_rate": 0.003751231527093596,
|
| 389 |
-
"loss": 0.
|
| 390 |
"step": 510
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 2.56,
|
| 394 |
-
"grad_norm":
|
| 395 |
"learning_rate": 0.0037266009852216747,
|
| 396 |
-
"loss": 0.
|
| 397 |
"step": 520
|
| 398 |
},
|
| 399 |
{
|
| 400 |
"epoch": 2.61,
|
| 401 |
-
"grad_norm":
|
| 402 |
"learning_rate": 0.003701970443349754,
|
| 403 |
-
"loss": 0.
|
| 404 |
"step": 530
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 2.66,
|
| 408 |
-
"grad_norm":
|
| 409 |
"learning_rate": 0.0036773399014778324,
|
| 410 |
-
"loss": 0.
|
| 411 |
"step": 540
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 2.71,
|
| 415 |
-
"grad_norm": 1.
|
| 416 |
"learning_rate": 0.0036527093596059115,
|
| 417 |
-
"loss": 0.
|
| 418 |
"step": 550
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"epoch": 2.76,
|
| 422 |
-
"grad_norm":
|
| 423 |
"learning_rate": 0.00362807881773399,
|
| 424 |
-
"loss": 0.
|
| 425 |
"step": 560
|
| 426 |
},
|
| 427 |
{
|
| 428 |
"epoch": 2.8,
|
| 429 |
-
"grad_norm": 1.
|
| 430 |
"learning_rate": 0.003603448275862069,
|
| 431 |
-
"loss": 0.
|
| 432 |
"step": 570
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"epoch": 2.85,
|
| 436 |
-
"grad_norm":
|
| 437 |
"learning_rate": 0.003578817733990148,
|
| 438 |
-
"loss": 0.
|
| 439 |
"step": 580
|
| 440 |
},
|
| 441 |
{
|
| 442 |
"epoch": 2.9,
|
| 443 |
-
"grad_norm": 2.
|
| 444 |
"learning_rate": 0.0035541871921182266,
|
| 445 |
-
"loss": 0.
|
| 446 |
"step": 590
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 2.95,
|
| 450 |
-
"grad_norm": 1.
|
| 451 |
"learning_rate": 0.0035295566502463057,
|
| 452 |
-
"loss": 0.
|
| 453 |
"step": 600
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 3.0,
|
| 457 |
-
"eval_accuracy": 0.
|
| 458 |
-
"eval_f1": 0.
|
| 459 |
-
"eval_loss": 0.
|
| 460 |
-
"eval_precision": 0.
|
| 461 |
-
"eval_recall": 0.
|
| 462 |
-
"eval_runtime": 12.
|
| 463 |
-
"eval_samples_per_second":
|
| 464 |
-
"eval_steps_per_second": 11.
|
| 465 |
"step": 609
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 3.0,
|
| 469 |
-
"grad_norm": 1.
|
| 470 |
"learning_rate": 0.0035049261083743843,
|
| 471 |
-
"loss": 0.
|
| 472 |
"step": 610
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"epoch": 3.05,
|
| 476 |
-
"grad_norm":
|
| 477 |
"learning_rate": 0.0034802955665024634,
|
| 478 |
-
"loss": 0.
|
| 479 |
"step": 620
|
| 480 |
},
|
| 481 |
{
|
| 482 |
"epoch": 3.1,
|
| 483 |
-
"grad_norm": 2.
|
| 484 |
"learning_rate": 0.003455665024630542,
|
| 485 |
-
"loss": 0.
|
| 486 |
"step": 630
|
| 487 |
},
|
| 488 |
{
|
| 489 |
"epoch": 3.15,
|
| 490 |
-
"grad_norm":
|
| 491 |
"learning_rate": 0.0034310344827586207,
|
| 492 |
-
"loss": 0.
|
| 493 |
"step": 640
|
| 494 |
},
|
| 495 |
{
|
| 496 |
"epoch": 3.2,
|
| 497 |
-
"grad_norm":
|
| 498 |
"learning_rate": 0.0034064039408867,
|
| 499 |
-
"loss": 0.
|
| 500 |
"step": 650
|
| 501 |
},
|
| 502 |
{
|
| 503 |
"epoch": 3.25,
|
| 504 |
-
"grad_norm":
|
| 505 |
"learning_rate": 0.0033817733990147785,
|
| 506 |
-
"loss": 0.
|
| 507 |
"step": 660
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 3.3,
|
| 511 |
-
"grad_norm":
|
| 512 |
"learning_rate": 0.003357142857142857,
|
| 513 |
-
"loss": 0.
|
| 514 |
"step": 670
|
| 515 |
},
|
| 516 |
{
|
| 517 |
"epoch": 3.35,
|
| 518 |
-
"grad_norm":
|
| 519 |
"learning_rate": 0.003332512315270936,
|
| 520 |
-
"loss": 0.
|
| 521 |
"step": 680
|
| 522 |
},
|
| 523 |
{
|
| 524 |
"epoch": 3.39,
|
| 525 |
-
"grad_norm":
|
| 526 |
"learning_rate": 0.0033078817733990145,
|
| 527 |
-
"loss": 0.
|
| 528 |
"step": 690
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 3.44,
|
| 532 |
-
"grad_norm":
|
| 533 |
"learning_rate": 0.0032832512315270936,
|
| 534 |
-
"loss": 0.
|
| 535 |
"step": 700
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"epoch": 3.49,
|
| 539 |
-
"grad_norm":
|
| 540 |
"learning_rate": 0.003258620689655172,
|
| 541 |
-
"loss": 0.
|
| 542 |
"step": 710
|
| 543 |
},
|
| 544 |
{
|
| 545 |
"epoch": 3.54,
|
| 546 |
-
"grad_norm":
|
| 547 |
"learning_rate": 0.0032339901477832513,
|
| 548 |
-
"loss": 0.
|
| 549 |
"step": 720
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 3.59,
|
| 553 |
-
"grad_norm":
|
| 554 |
"learning_rate": 0.00320935960591133,
|
| 555 |
-
"loss": 0.
|
| 556 |
"step": 730
|
| 557 |
},
|
| 558 |
{
|
| 559 |
"epoch": 3.64,
|
| 560 |
-
"grad_norm":
|
| 561 |
"learning_rate": 0.003184729064039409,
|
| 562 |
-
"loss": 0.
|
| 563 |
"step": 740
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 3.69,
|
| 567 |
-
"grad_norm":
|
| 568 |
"learning_rate": 0.0031600985221674877,
|
| 569 |
-
"loss": 0.
|
| 570 |
"step": 750
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 3.74,
|
| 574 |
-
"grad_norm":
|
| 575 |
-
"learning_rate": 0.
|
| 576 |
-
"loss": 0.
|
| 577 |
"step": 760
|
| 578 |
},
|
| 579 |
{
|
| 580 |
"epoch": 3.79,
|
| 581 |
-
"grad_norm": 2.
|
| 582 |
-
"learning_rate": 0.
|
| 583 |
-
"loss": 0.
|
| 584 |
"step": 770
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"epoch": 3.84,
|
| 588 |
-
"grad_norm":
|
| 589 |
-
"learning_rate": 0.
|
| 590 |
-
"loss": 0.
|
| 591 |
"step": 780
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 3.89,
|
| 595 |
-
"grad_norm":
|
| 596 |
-
"learning_rate": 0.
|
| 597 |
-
"loss": 0.
|
| 598 |
"step": 790
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"epoch": 3.94,
|
| 602 |
-
"grad_norm":
|
| 603 |
-
"learning_rate": 0.
|
| 604 |
-
"loss": 0.
|
| 605 |
"step": 800
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 3.99,
|
| 609 |
-
"grad_norm":
|
| 610 |
-
"learning_rate": 0.
|
| 611 |
-
"loss": 0.
|
| 612 |
"step": 810
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 4.0,
|
| 616 |
-
"eval_accuracy": 0.
|
| 617 |
-
"eval_f1": 0.
|
| 618 |
-
"eval_loss": 0.
|
| 619 |
-
"eval_precision": 0.
|
| 620 |
-
"eval_recall": 0.
|
| 621 |
-
"eval_runtime": 12.
|
| 622 |
-
"eval_samples_per_second":
|
| 623 |
-
"eval_steps_per_second": 11.
|
| 624 |
"step": 813
|
| 625 |
},
|
| 626 |
{
|
| 627 |
"epoch": 4.03,
|
| 628 |
-
"grad_norm":
|
| 629 |
-
"learning_rate": 0.
|
| 630 |
-
"loss": 0.
|
| 631 |
"step": 820
|
| 632 |
},
|
| 633 |
{
|
| 634 |
"epoch": 4.08,
|
| 635 |
-
"grad_norm":
|
| 636 |
-
"learning_rate": 0.
|
| 637 |
-
"loss": 0.
|
| 638 |
"step": 830
|
| 639 |
},
|
| 640 |
{
|
| 641 |
"epoch": 4.13,
|
| 642 |
-
"grad_norm":
|
| 643 |
-
"learning_rate": 0.
|
| 644 |
-
"loss": 0.
|
| 645 |
"step": 840
|
| 646 |
},
|
| 647 |
{
|
| 648 |
"epoch": 4.18,
|
| 649 |
-
"grad_norm":
|
| 650 |
-
"learning_rate": 0.
|
| 651 |
-
"loss": 0.
|
| 652 |
"step": 850
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"epoch": 4.23,
|
| 656 |
-
"grad_norm": 2.
|
| 657 |
-
"learning_rate": 0.
|
| 658 |
-
"loss": 0.
|
| 659 |
"step": 860
|
| 660 |
},
|
| 661 |
{
|
| 662 |
"epoch": 4.28,
|
| 663 |
-
"grad_norm":
|
| 664 |
-
"learning_rate": 0.
|
| 665 |
-
"loss": 0.
|
| 666 |
"step": 870
|
| 667 |
},
|
| 668 |
{
|
| 669 |
"epoch": 4.33,
|
| 670 |
-
"grad_norm": 1.
|
| 671 |
-
"learning_rate": 0.
|
| 672 |
-
"loss": 0.
|
| 673 |
"step": 880
|
| 674 |
},
|
| 675 |
{
|
| 676 |
"epoch": 4.38,
|
| 677 |
-
"grad_norm": 1.
|
| 678 |
-
"learning_rate": 0.
|
| 679 |
-
"loss": 0.
|
| 680 |
"step": 890
|
| 681 |
},
|
| 682 |
{
|
| 683 |
"epoch": 4.43,
|
| 684 |
-
"grad_norm": 1.
|
| 685 |
-
"learning_rate": 0.
|
| 686 |
-
"loss": 0.
|
| 687 |
"step": 900
|
| 688 |
},
|
| 689 |
{
|
| 690 |
"epoch": 4.48,
|
| 691 |
-
"grad_norm": 1.
|
| 692 |
-
"learning_rate": 0.
|
| 693 |
-
"loss": 0.
|
| 694 |
"step": 910
|
| 695 |
},
|
| 696 |
{
|
| 697 |
"epoch": 4.53,
|
| 698 |
-
"grad_norm": 1.
|
| 699 |
-
"learning_rate": 0.
|
| 700 |
-
"loss": 0.
|
| 701 |
"step": 920
|
| 702 |
},
|
| 703 |
{
|
| 704 |
"epoch": 4.58,
|
| 705 |
-
"grad_norm":
|
| 706 |
-
"learning_rate": 0.
|
| 707 |
-
"loss": 0.
|
| 708 |
"step": 930
|
| 709 |
},
|
| 710 |
{
|
| 711 |
"epoch": 4.62,
|
| 712 |
-
"grad_norm":
|
| 713 |
-
"learning_rate": 0.
|
| 714 |
-
"loss": 0.
|
| 715 |
"step": 940
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"epoch": 4.67,
|
| 719 |
-
"grad_norm":
|
| 720 |
-
"learning_rate": 0.
|
| 721 |
-
"loss": 0.
|
| 722 |
"step": 950
|
| 723 |
},
|
| 724 |
{
|
| 725 |
"epoch": 4.72,
|
| 726 |
-
"grad_norm":
|
| 727 |
-
"learning_rate": 0.
|
| 728 |
-
"loss": 0.
|
| 729 |
"step": 960
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 4.77,
|
| 733 |
-
"grad_norm":
|
| 734 |
-
"learning_rate": 0.
|
| 735 |
-
"loss": 0.
|
| 736 |
"step": 970
|
| 737 |
},
|
| 738 |
{
|
| 739 |
"epoch": 4.82,
|
| 740 |
-
"grad_norm":
|
| 741 |
-
"learning_rate": 0.
|
| 742 |
-
"loss": 0.
|
| 743 |
"step": 980
|
| 744 |
},
|
| 745 |
{
|
| 746 |
"epoch": 4.87,
|
| 747 |
-
"grad_norm":
|
| 748 |
-
"learning_rate": 0.
|
| 749 |
-
"loss": 0.
|
| 750 |
"step": 990
|
| 751 |
},
|
| 752 |
{
|
| 753 |
"epoch": 4.92,
|
| 754 |
-
"grad_norm":
|
| 755 |
-
"learning_rate": 0.
|
| 756 |
-
"loss": 0.
|
| 757 |
"step": 1000
|
| 758 |
},
|
| 759 |
{
|
| 760 |
"epoch": 4.97,
|
| 761 |
-
"grad_norm":
|
| 762 |
-
"learning_rate": 0.
|
| 763 |
-
"loss": 0.
|
| 764 |
"step": 1010
|
| 765 |
},
|
| 766 |
{
|
| 767 |
"epoch": 5.0,
|
| 768 |
-
"eval_accuracy": 0.
|
| 769 |
-
"eval_f1": 0.
|
| 770 |
-
"eval_loss": 0.
|
| 771 |
-
"eval_precision": 0.
|
| 772 |
-
"eval_recall": 0.
|
| 773 |
-
"eval_runtime": 12.
|
| 774 |
-
"eval_samples_per_second":
|
| 775 |
-
"eval_steps_per_second": 11.
|
| 776 |
"step": 1016
|
| 777 |
},
|
| 778 |
{
|
| 779 |
"epoch": 5.02,
|
| 780 |
-
"grad_norm":
|
| 781 |
-
"learning_rate": 0.
|
| 782 |
-
"loss": 0.
|
| 783 |
"step": 1020
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 5.07,
|
| 787 |
-
"grad_norm": 1.
|
| 788 |
-
"learning_rate": 0.
|
| 789 |
-
"loss": 0.
|
| 790 |
"step": 1030
|
| 791 |
},
|
| 792 |
{
|
| 793 |
"epoch": 5.12,
|
| 794 |
-
"grad_norm": 1.
|
| 795 |
-
"learning_rate": 0.
|
| 796 |
-
"loss": 0.
|
| 797 |
"step": 1040
|
| 798 |
},
|
| 799 |
{
|
| 800 |
"epoch": 5.17,
|
| 801 |
-
"grad_norm":
|
| 802 |
-
"learning_rate": 0.
|
| 803 |
-
"loss": 0.
|
| 804 |
"step": 1050
|
| 805 |
},
|
| 806 |
{
|
| 807 |
"epoch": 5.22,
|
| 808 |
-
"grad_norm": 1.
|
| 809 |
-
"learning_rate": 0.
|
| 810 |
-
"loss": 0.
|
| 811 |
"step": 1060
|
| 812 |
},
|
| 813 |
{
|
| 814 |
"epoch": 5.26,
|
| 815 |
-
"grad_norm":
|
| 816 |
-
"learning_rate": 0.
|
| 817 |
-
"loss": 0.
|
| 818 |
"step": 1070
|
| 819 |
},
|
| 820 |
{
|
| 821 |
"epoch": 5.31,
|
| 822 |
-
"grad_norm":
|
| 823 |
-
"learning_rate": 0.
|
| 824 |
-
"loss": 0.
|
| 825 |
"step": 1080
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 5.36,
|
| 829 |
-
"grad_norm":
|
| 830 |
-
"learning_rate": 0.
|
| 831 |
-
"loss": 0.
|
| 832 |
"step": 1090
|
| 833 |
},
|
| 834 |
{
|
| 835 |
"epoch": 5.41,
|
| 836 |
-
"grad_norm":
|
| 837 |
-
"learning_rate": 0.
|
| 838 |
-
"loss": 0.
|
| 839 |
"step": 1100
|
| 840 |
},
|
| 841 |
{
|
| 842 |
"epoch": 5.46,
|
| 843 |
-
"grad_norm": 2.
|
| 844 |
-
"learning_rate": 0.
|
| 845 |
-
"loss": 0.
|
| 846 |
"step": 1110
|
| 847 |
},
|
| 848 |
{
|
| 849 |
"epoch": 5.51,
|
| 850 |
-
"grad_norm":
|
| 851 |
-
"learning_rate": 0.
|
| 852 |
-
"loss": 0.
|
| 853 |
"step": 1120
|
| 854 |
},
|
| 855 |
{
|
| 856 |
"epoch": 5.56,
|
| 857 |
-
"grad_norm":
|
| 858 |
-
"learning_rate": 0.
|
| 859 |
-
"loss": 0.
|
| 860 |
"step": 1130
|
| 861 |
},
|
| 862 |
{
|
| 863 |
"epoch": 5.61,
|
| 864 |
-
"grad_norm": 1.
|
| 865 |
-
"learning_rate": 0.
|
| 866 |
-
"loss": 0.
|
| 867 |
"step": 1140
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 5.66,
|
| 871 |
-
"grad_norm":
|
| 872 |
-
"learning_rate": 0.
|
| 873 |
-
"loss": 0.
|
| 874 |
"step": 1150
|
| 875 |
},
|
| 876 |
{
|
| 877 |
"epoch": 5.71,
|
| 878 |
-
"grad_norm":
|
| 879 |
-
"learning_rate": 0.
|
| 880 |
-
"loss": 0.
|
| 881 |
"step": 1160
|
| 882 |
},
|
| 883 |
{
|
| 884 |
"epoch": 5.76,
|
| 885 |
-
"grad_norm":
|
| 886 |
-
"learning_rate": 0.
|
| 887 |
-
"loss": 0.
|
| 888 |
"step": 1170
|
| 889 |
},
|
| 890 |
{
|
| 891 |
"epoch": 5.81,
|
| 892 |
-
"grad_norm":
|
| 893 |
-
"learning_rate": 0.
|
| 894 |
-
"loss": 0.
|
| 895 |
"step": 1180
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"epoch": 5.85,
|
| 899 |
-
"grad_norm":
|
| 900 |
-
"learning_rate": 0.
|
| 901 |
-
"loss": 0.
|
| 902 |
"step": 1190
|
| 903 |
},
|
| 904 |
{
|
| 905 |
"epoch": 5.9,
|
| 906 |
-
"grad_norm":
|
| 907 |
-
"learning_rate": 0.
|
| 908 |
-
"loss": 0.
|
| 909 |
"step": 1200
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 5.95,
|
| 913 |
-
"grad_norm":
|
| 914 |
-
"learning_rate": 0.
|
| 915 |
-
"loss": 0.
|
| 916 |
"step": 1210
|
| 917 |
},
|
| 918 |
{
|
| 919 |
"epoch": 6.0,
|
| 920 |
-
"eval_accuracy": 0.
|
| 921 |
-
"eval_f1": 0.
|
| 922 |
-
"eval_loss": 0.
|
| 923 |
-
"eval_precision": 0.
|
| 924 |
-
"eval_recall": 0.
|
| 925 |
-
"eval_runtime": 12.
|
| 926 |
-
"eval_samples_per_second":
|
| 927 |
-
"eval_steps_per_second": 11.
|
| 928 |
"step": 1219
|
| 929 |
},
|
| 930 |
{
|
| 931 |
"epoch": 6.0,
|
| 932 |
-
"grad_norm":
|
| 933 |
-
"learning_rate": 0.
|
| 934 |
-
"loss": 0.
|
| 935 |
"step": 1220
|
| 936 |
},
|
| 937 |
{
|
| 938 |
"epoch": 6.05,
|
| 939 |
-
"grad_norm": 1.
|
| 940 |
-
"learning_rate": 0.
|
| 941 |
-
"loss": 0.
|
| 942 |
"step": 1230
|
| 943 |
},
|
| 944 |
{
|
| 945 |
"epoch": 6.1,
|
| 946 |
-
"grad_norm":
|
| 947 |
-
"learning_rate": 0.
|
| 948 |
-
"loss": 0.
|
| 949 |
"step": 1240
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"epoch": 6.15,
|
| 953 |
-
"grad_norm":
|
| 954 |
-
"learning_rate": 0.
|
| 955 |
-
"loss": 0.
|
| 956 |
"step": 1250
|
| 957 |
},
|
| 958 |
{
|
| 959 |
"epoch": 6.2,
|
| 960 |
-
"grad_norm":
|
| 961 |
-
"learning_rate": 0.
|
| 962 |
-
"loss": 0.
|
| 963 |
"step": 1260
|
| 964 |
},
|
| 965 |
{
|
| 966 |
"epoch": 6.25,
|
| 967 |
-
"grad_norm":
|
| 968 |
-
"learning_rate": 0.
|
| 969 |
-
"loss": 0.
|
| 970 |
"step": 1270
|
| 971 |
},
|
| 972 |
{
|
| 973 |
"epoch": 6.3,
|
| 974 |
-
"grad_norm":
|
| 975 |
-
"learning_rate": 0.
|
| 976 |
-
"loss": 0.
|
| 977 |
"step": 1280
|
| 978 |
},
|
| 979 |
{
|
| 980 |
"epoch": 6.35,
|
| 981 |
-
"grad_norm":
|
| 982 |
-
"learning_rate": 0.
|
| 983 |
-
"loss": 0.
|
| 984 |
"step": 1290
|
| 985 |
},
|
| 986 |
{
|
| 987 |
"epoch": 6.4,
|
| 988 |
-
"grad_norm":
|
| 989 |
-
"learning_rate": 0.
|
| 990 |
-
"loss": 0.
|
| 991 |
"step": 1300
|
| 992 |
},
|
| 993 |
{
|
| 994 |
"epoch": 6.45,
|
| 995 |
-
"grad_norm":
|
| 996 |
-
"learning_rate": 0.
|
| 997 |
-
"loss": 0.
|
| 998 |
"step": 1310
|
| 999 |
},
|
| 1000 |
{
|
| 1001 |
"epoch": 6.49,
|
| 1002 |
-
"grad_norm":
|
| 1003 |
-
"learning_rate": 0.
|
| 1004 |
-
"loss": 0.
|
| 1005 |
"step": 1320
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 6.54,
|
| 1009 |
-
"grad_norm":
|
| 1010 |
-
"learning_rate": 0.
|
| 1011 |
-
"loss": 0.
|
| 1012 |
"step": 1330
|
| 1013 |
},
|
| 1014 |
{
|
| 1015 |
"epoch": 6.59,
|
| 1016 |
-
"grad_norm":
|
| 1017 |
-
"learning_rate": 0.
|
| 1018 |
-
"loss": 0.
|
| 1019 |
"step": 1340
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
"epoch": 6.64,
|
| 1023 |
-
"grad_norm":
|
| 1024 |
-
"learning_rate": 0.
|
| 1025 |
-
"loss": 0.
|
| 1026 |
"step": 1350
|
| 1027 |
},
|
| 1028 |
{
|
| 1029 |
"epoch": 6.69,
|
| 1030 |
-
"grad_norm":
|
| 1031 |
-
"learning_rate": 0.
|
| 1032 |
-
"loss": 0.
|
| 1033 |
"step": 1360
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
"epoch": 6.74,
|
| 1037 |
-
"grad_norm": 1.
|
| 1038 |
-
"learning_rate": 0.
|
| 1039 |
-
"loss": 0.
|
| 1040 |
"step": 1370
|
| 1041 |
},
|
| 1042 |
{
|
| 1043 |
"epoch": 6.79,
|
| 1044 |
-
"grad_norm": 1.
|
| 1045 |
-
"learning_rate": 0.
|
| 1046 |
-
"loss": 0.
|
| 1047 |
"step": 1380
|
| 1048 |
},
|
| 1049 |
{
|
| 1050 |
"epoch": 6.84,
|
| 1051 |
-
"grad_norm":
|
| 1052 |
-
"learning_rate": 0.
|
| 1053 |
-
"loss": 0.
|
| 1054 |
"step": 1390
|
| 1055 |
},
|
| 1056 |
{
|
| 1057 |
"epoch": 6.89,
|
| 1058 |
-
"grad_norm":
|
| 1059 |
-
"learning_rate": 0.
|
| 1060 |
-
"loss": 0.
|
| 1061 |
"step": 1400
|
| 1062 |
},
|
| 1063 |
{
|
| 1064 |
"epoch": 6.94,
|
| 1065 |
-
"grad_norm": 1.
|
| 1066 |
-
"learning_rate": 0.
|
| 1067 |
-
"loss": 0.
|
| 1068 |
"step": 1410
|
| 1069 |
},
|
| 1070 |
{
|
| 1071 |
"epoch": 6.99,
|
| 1072 |
-
"grad_norm":
|
| 1073 |
-
"learning_rate": 0.
|
| 1074 |
-
"loss": 0.
|
| 1075 |
"step": 1420
|
| 1076 |
},
|
| 1077 |
{
|
| 1078 |
"epoch": 7.0,
|
| 1079 |
-
"eval_accuracy": 0.
|
| 1080 |
-
"eval_f1": 0.
|
| 1081 |
-
"eval_loss": 0.
|
| 1082 |
-
"eval_precision": 0.
|
| 1083 |
-
"eval_recall": 0.
|
| 1084 |
-
"eval_runtime": 12.
|
| 1085 |
-
"eval_samples_per_second":
|
| 1086 |
-
"eval_steps_per_second": 11.
|
| 1087 |
"step": 1422
|
| 1088 |
},
|
| 1089 |
{
|
| 1090 |
"epoch": 7.04,
|
| 1091 |
-
"grad_norm": 0.
|
| 1092 |
-
"learning_rate": 0.
|
| 1093 |
-
"loss": 0.
|
| 1094 |
"step": 1430
|
| 1095 |
},
|
| 1096 |
{
|
| 1097 |
"epoch": 7.08,
|
| 1098 |
-
"grad_norm":
|
| 1099 |
-
"learning_rate": 0.
|
| 1100 |
-
"loss": 0.
|
| 1101 |
"step": 1440
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
"epoch": 7.13,
|
| 1105 |
-
"grad_norm": 1.
|
| 1106 |
-
"learning_rate": 0.
|
| 1107 |
-
"loss": 0.
|
| 1108 |
"step": 1450
|
| 1109 |
},
|
| 1110 |
{
|
| 1111 |
"epoch": 7.18,
|
| 1112 |
-
"grad_norm": 1.
|
| 1113 |
-
"learning_rate": 0.
|
| 1114 |
-
"loss": 0.
|
| 1115 |
"step": 1460
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
"epoch": 7.23,
|
| 1119 |
-
"grad_norm":
|
| 1120 |
-
"learning_rate": 0.
|
| 1121 |
-
"loss": 0.
|
| 1122 |
"step": 1470
|
| 1123 |
},
|
| 1124 |
{
|
| 1125 |
"epoch": 7.28,
|
| 1126 |
-
"grad_norm":
|
| 1127 |
-
"learning_rate": 0.
|
| 1128 |
-
"loss": 0.
|
| 1129 |
"step": 1480
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
"epoch": 7.33,
|
| 1133 |
-
"grad_norm":
|
| 1134 |
-
"learning_rate": 0.
|
| 1135 |
-
"loss": 0.
|
| 1136 |
"step": 1490
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
"epoch": 7.38,
|
| 1140 |
-
"grad_norm":
|
| 1141 |
-
"learning_rate": 0.
|
| 1142 |
-
"loss": 0.
|
| 1143 |
"step": 1500
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 7.43,
|
| 1147 |
-
"grad_norm":
|
| 1148 |
-
"learning_rate": 0.
|
| 1149 |
-
"loss": 0.
|
| 1150 |
"step": 1510
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
"epoch": 7.48,
|
| 1154 |
-
"grad_norm":
|
| 1155 |
-
"learning_rate": 0.
|
| 1156 |
-
"loss": 0.
|
| 1157 |
"step": 1520
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
"epoch": 7.53,
|
| 1161 |
-
"grad_norm":
|
| 1162 |
-
"learning_rate": 0.
|
| 1163 |
-
"loss": 0.
|
| 1164 |
"step": 1530
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
"epoch": 7.58,
|
| 1168 |
-
"grad_norm":
|
| 1169 |
-
"learning_rate": 0.
|
| 1170 |
-
"loss": 0.
|
| 1171 |
"step": 1540
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
"epoch": 7.63,
|
| 1175 |
-
"grad_norm": 1.
|
| 1176 |
-
"learning_rate": 0.
|
| 1177 |
-
"loss": 0.
|
| 1178 |
"step": 1550
|
| 1179 |
},
|
| 1180 |
{
|
| 1181 |
"epoch": 7.68,
|
| 1182 |
-
"grad_norm": 1.
|
| 1183 |
-
"learning_rate": 0.
|
| 1184 |
-
"loss": 0.
|
| 1185 |
"step": 1560
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"epoch": 7.72,
|
| 1189 |
-
"grad_norm":
|
| 1190 |
-
"learning_rate": 0.
|
| 1191 |
-
"loss": 0.
|
| 1192 |
"step": 1570
|
| 1193 |
},
|
| 1194 |
{
|
| 1195 |
"epoch": 7.77,
|
| 1196 |
-
"grad_norm":
|
| 1197 |
-
"learning_rate": 0.
|
| 1198 |
-
"loss": 0.
|
| 1199 |
"step": 1580
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
"epoch": 7.82,
|
| 1203 |
-
"grad_norm":
|
| 1204 |
-
"learning_rate": 0.
|
| 1205 |
-
"loss": 0.
|
| 1206 |
"step": 1590
|
| 1207 |
},
|
| 1208 |
{
|
| 1209 |
"epoch": 7.87,
|
| 1210 |
-
"grad_norm":
|
| 1211 |
-
"learning_rate": 0.
|
| 1212 |
-
"loss": 0.
|
| 1213 |
"step": 1600
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
"epoch": 7.92,
|
| 1217 |
-
"grad_norm": 1.
|
| 1218 |
-
"learning_rate": 0.
|
| 1219 |
-
"loss": 0.
|
| 1220 |
"step": 1610
|
| 1221 |
},
|
| 1222 |
{
|
| 1223 |
"epoch": 7.97,
|
| 1224 |
-
"grad_norm":
|
| 1225 |
-
"learning_rate": 0.
|
| 1226 |
-
"loss": 0.
|
| 1227 |
"step": 1620
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
"epoch": 8.0,
|
| 1231 |
-
"eval_accuracy": 0.
|
| 1232 |
-
"eval_f1": 0.
|
| 1233 |
-
"eval_loss": 0.
|
| 1234 |
-
"eval_precision": 0.
|
| 1235 |
-
"eval_recall": 0.
|
| 1236 |
-
"eval_runtime": 12.
|
| 1237 |
-
"eval_samples_per_second": 185.
|
| 1238 |
-
"eval_steps_per_second": 11.
|
| 1239 |
"step": 1626
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
"epoch": 8.02,
|
| 1243 |
-
"grad_norm":
|
| 1244 |
-
"learning_rate": 0.
|
| 1245 |
-
"loss": 0.
|
| 1246 |
"step": 1630
|
| 1247 |
},
|
| 1248 |
{
|
| 1249 |
"epoch": 8.07,
|
| 1250 |
-
"grad_norm":
|
| 1251 |
-
"learning_rate": 0.
|
| 1252 |
-
"loss": 0.
|
| 1253 |
"step": 1640
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
"epoch": 8.12,
|
| 1257 |
-
"grad_norm":
|
| 1258 |
-
"learning_rate": 0.
|
| 1259 |
-
"loss": 0.
|
| 1260 |
"step": 1650
|
| 1261 |
},
|
| 1262 |
{
|
| 1263 |
"epoch": 8.17,
|
| 1264 |
-
"grad_norm": 1.
|
| 1265 |
-
"learning_rate": 0.
|
| 1266 |
-
"loss": 0.
|
| 1267 |
"step": 1660
|
| 1268 |
},
|
| 1269 |
{
|
| 1270 |
"epoch": 8.22,
|
| 1271 |
-
"grad_norm":
|
| 1272 |
-
"learning_rate": 0.
|
| 1273 |
-
"loss": 0.
|
| 1274 |
"step": 1670
|
| 1275 |
},
|
| 1276 |
{
|
| 1277 |
"epoch": 8.27,
|
| 1278 |
-
"grad_norm": 1.
|
| 1279 |
-
"learning_rate": 0.
|
| 1280 |
-
"loss": 0.
|
| 1281 |
"step": 1680
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 8.31,
|
| 1285 |
-
"grad_norm":
|
| 1286 |
-
"learning_rate": 0.
|
| 1287 |
-
"loss": 0.
|
| 1288 |
"step": 1690
|
| 1289 |
},
|
| 1290 |
{
|
| 1291 |
"epoch": 8.36,
|
| 1292 |
-
"grad_norm":
|
| 1293 |
-
"learning_rate": 0.
|
| 1294 |
-
"loss": 0.
|
| 1295 |
"step": 1700
|
| 1296 |
},
|
| 1297 |
{
|
| 1298 |
"epoch": 8.41,
|
| 1299 |
-
"grad_norm":
|
| 1300 |
-
"learning_rate": 0.
|
| 1301 |
-
"loss": 0.
|
| 1302 |
"step": 1710
|
| 1303 |
},
|
| 1304 |
{
|
| 1305 |
"epoch": 8.46,
|
| 1306 |
-
"grad_norm":
|
| 1307 |
-
"learning_rate": 0.
|
| 1308 |
-
"loss": 0.
|
| 1309 |
"step": 1720
|
| 1310 |
},
|
| 1311 |
{
|
| 1312 |
"epoch": 8.51,
|
| 1313 |
-
"grad_norm":
|
| 1314 |
-
"learning_rate": 0.
|
| 1315 |
-
"loss": 0.
|
| 1316 |
"step": 1730
|
| 1317 |
},
|
| 1318 |
{
|
| 1319 |
"epoch": 8.56,
|
| 1320 |
-
"grad_norm":
|
| 1321 |
-
"learning_rate": 0.
|
| 1322 |
-
"loss": 0.
|
| 1323 |
"step": 1740
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
"epoch": 8.61,
|
| 1327 |
-
"grad_norm":
|
| 1328 |
-
"learning_rate": 0.
|
| 1329 |
-
"loss": 0.
|
| 1330 |
"step": 1750
|
| 1331 |
},
|
| 1332 |
{
|
| 1333 |
"epoch": 8.66,
|
| 1334 |
-
"grad_norm":
|
| 1335 |
-
"learning_rate": 0.
|
| 1336 |
-
"loss": 0.
|
| 1337 |
"step": 1760
|
| 1338 |
},
|
| 1339 |
{
|
| 1340 |
"epoch": 8.71,
|
| 1341 |
-
"grad_norm":
|
| 1342 |
-
"learning_rate": 0.
|
| 1343 |
-
"loss": 0.
|
| 1344 |
"step": 1770
|
| 1345 |
},
|
| 1346 |
{
|
| 1347 |
"epoch": 8.76,
|
| 1348 |
-
"grad_norm":
|
| 1349 |
-
"learning_rate": 0.
|
| 1350 |
-
"loss": 0.
|
| 1351 |
"step": 1780
|
| 1352 |
},
|
| 1353 |
{
|
| 1354 |
"epoch": 8.81,
|
| 1355 |
-
"grad_norm":
|
| 1356 |
-
"learning_rate": 0.
|
| 1357 |
-
"loss": 0.
|
| 1358 |
"step": 1790
|
| 1359 |
},
|
| 1360 |
{
|
| 1361 |
"epoch": 8.86,
|
| 1362 |
-
"grad_norm":
|
| 1363 |
-
"learning_rate": 0.
|
| 1364 |
-
"loss": 0.
|
| 1365 |
"step": 1800
|
| 1366 |
},
|
| 1367 |
{
|
| 1368 |
"epoch": 8.91,
|
| 1369 |
-
"grad_norm":
|
| 1370 |
-
"learning_rate": 0.
|
| 1371 |
-
"loss": 0.
|
| 1372 |
"step": 1810
|
| 1373 |
},
|
| 1374 |
{
|
| 1375 |
"epoch": 8.95,
|
| 1376 |
-
"grad_norm": 0.
|
| 1377 |
-
"learning_rate": 0.
|
| 1378 |
-
"loss": 0.
|
| 1379 |
"step": 1820
|
| 1380 |
},
|
| 1381 |
{
|
| 1382 |
"epoch": 9.0,
|
| 1383 |
-
"eval_accuracy": 0.
|
| 1384 |
-
"eval_f1": 0.
|
| 1385 |
-
"eval_loss": 0.
|
| 1386 |
-
"eval_precision": 0.
|
| 1387 |
-
"eval_recall": 0.
|
| 1388 |
-
"eval_runtime": 12.
|
| 1389 |
-
"eval_samples_per_second":
|
| 1390 |
-
"eval_steps_per_second": 11.
|
| 1391 |
"step": 1829
|
| 1392 |
},
|
| 1393 |
{
|
| 1394 |
"epoch": 9.0,
|
| 1395 |
-
"grad_norm":
|
| 1396 |
-
"learning_rate": 0.
|
| 1397 |
-
"loss": 0.
|
| 1398 |
"step": 1830
|
| 1399 |
},
|
| 1400 |
{
|
| 1401 |
"epoch": 9.05,
|
| 1402 |
-
"grad_norm":
|
| 1403 |
-
"learning_rate": 0.
|
| 1404 |
-
"loss": 0.
|
| 1405 |
"step": 1840
|
| 1406 |
},
|
| 1407 |
{
|
| 1408 |
"epoch": 9.1,
|
| 1409 |
-
"grad_norm":
|
| 1410 |
-
"learning_rate": 0.
|
| 1411 |
-
"loss": 0.
|
| 1412 |
"step": 1850
|
| 1413 |
},
|
| 1414 |
{
|
| 1415 |
"epoch": 9.15,
|
| 1416 |
-
"grad_norm":
|
| 1417 |
-
"learning_rate": 0.
|
| 1418 |
-
"loss": 0.
|
| 1419 |
"step": 1860
|
| 1420 |
},
|
| 1421 |
{
|
| 1422 |
"epoch": 9.2,
|
| 1423 |
-
"grad_norm":
|
| 1424 |
-
"learning_rate": 0.
|
| 1425 |
-
"loss": 0.
|
| 1426 |
"step": 1870
|
| 1427 |
},
|
| 1428 |
{
|
| 1429 |
"epoch": 9.25,
|
| 1430 |
-
"grad_norm":
|
| 1431 |
-
"learning_rate": 0.
|
| 1432 |
-
"loss": 0.
|
| 1433 |
"step": 1880
|
| 1434 |
},
|
| 1435 |
{
|
| 1436 |
"epoch": 9.3,
|
| 1437 |
-
"grad_norm": 1.
|
| 1438 |
-
"learning_rate": 0.
|
| 1439 |
-
"loss": 0.
|
| 1440 |
"step": 1890
|
| 1441 |
},
|
| 1442 |
{
|
| 1443 |
"epoch": 9.35,
|
| 1444 |
-
"grad_norm":
|
| 1445 |
-
"learning_rate": 0.
|
| 1446 |
-
"loss": 0.
|
| 1447 |
"step": 1900
|
| 1448 |
},
|
| 1449 |
{
|
| 1450 |
"epoch": 9.4,
|
| 1451 |
-
"grad_norm":
|
| 1452 |
-
"learning_rate": 0.
|
| 1453 |
-
"loss": 0.
|
| 1454 |
"step": 1910
|
| 1455 |
},
|
| 1456 |
{
|
| 1457 |
"epoch": 9.45,
|
| 1458 |
-
"grad_norm":
|
| 1459 |
-
"learning_rate": 0.
|
| 1460 |
-
"loss": 0.
|
| 1461 |
"step": 1920
|
| 1462 |
},
|
| 1463 |
{
|
| 1464 |
"epoch": 9.5,
|
| 1465 |
-
"grad_norm":
|
| 1466 |
-
"learning_rate": 0.
|
| 1467 |
-
"loss": 0.
|
| 1468 |
"step": 1930
|
| 1469 |
},
|
| 1470 |
{
|
| 1471 |
"epoch": 9.54,
|
| 1472 |
-
"grad_norm": 0.
|
| 1473 |
-
"learning_rate": 0.
|
| 1474 |
-
"loss": 0.
|
| 1475 |
"step": 1940
|
| 1476 |
},
|
| 1477 |
{
|
| 1478 |
"epoch": 9.59,
|
| 1479 |
-
"grad_norm":
|
| 1480 |
-
"learning_rate": 0.
|
| 1481 |
-
"loss": 0.
|
| 1482 |
"step": 1950
|
| 1483 |
},
|
| 1484 |
{
|
| 1485 |
"epoch": 9.64,
|
| 1486 |
-
"grad_norm": 1.
|
| 1487 |
-
"learning_rate": 0.
|
| 1488 |
-
"loss": 0.
|
| 1489 |
"step": 1960
|
| 1490 |
},
|
| 1491 |
{
|
| 1492 |
"epoch": 9.69,
|
| 1493 |
-
"grad_norm":
|
| 1494 |
-
"learning_rate": 0.
|
| 1495 |
-
"loss": 0.
|
| 1496 |
"step": 1970
|
| 1497 |
},
|
| 1498 |
{
|
| 1499 |
"epoch": 9.74,
|
| 1500 |
-
"grad_norm":
|
| 1501 |
-
"learning_rate": 0.
|
| 1502 |
-
"loss": 0.
|
| 1503 |
"step": 1980
|
| 1504 |
},
|
| 1505 |
{
|
| 1506 |
"epoch": 9.79,
|
| 1507 |
-
"grad_norm":
|
| 1508 |
-
"learning_rate": 0.
|
| 1509 |
-
"loss": 0.
|
| 1510 |
"step": 1990
|
| 1511 |
},
|
| 1512 |
{
|
| 1513 |
"epoch": 9.84,
|
| 1514 |
-
"grad_norm":
|
| 1515 |
-
"learning_rate": 8.
|
| 1516 |
-
"loss": 0.
|
| 1517 |
"step": 2000
|
| 1518 |
},
|
| 1519 |
{
|
| 1520 |
"epoch": 9.89,
|
| 1521 |
-
"grad_norm": 0.
|
| 1522 |
-
"learning_rate": 5.
|
| 1523 |
-
"loss": 0.
|
| 1524 |
"step": 2010
|
| 1525 |
},
|
| 1526 |
{
|
| 1527 |
"epoch": 9.94,
|
| 1528 |
-
"grad_norm":
|
| 1529 |
-
"learning_rate": 3.
|
| 1530 |
-
"loss": 0.
|
| 1531 |
"step": 2020
|
| 1532 |
},
|
| 1533 |
{
|
| 1534 |
"epoch": 9.99,
|
| 1535 |
-
"grad_norm": 1.
|
| 1536 |
-
"learning_rate":
|
| 1537 |
-
"loss": 0.
|
| 1538 |
"step": 2030
|
| 1539 |
},
|
| 1540 |
{
|
| 1541 |
"epoch": 9.99,
|
| 1542 |
-
"eval_accuracy": 0.
|
| 1543 |
-
"eval_f1": 0.
|
| 1544 |
-
"eval_loss": 0.
|
| 1545 |
-
"eval_precision": 0.
|
| 1546 |
-
"eval_recall": 0.
|
| 1547 |
-
"eval_runtime": 12.
|
| 1548 |
-
"eval_samples_per_second": 186.
|
| 1549 |
-
"eval_steps_per_second": 11.
|
| 1550 |
"step": 2030
|
| 1551 |
},
|
| 1552 |
{
|
| 1553 |
"epoch": 9.99,
|
| 1554 |
"step": 2030,
|
| 1555 |
"total_flos": 1.0133154899356189e+19,
|
| 1556 |
-
"train_loss": 0.
|
| 1557 |
-
"train_runtime":
|
| 1558 |
-
"train_samples_per_second": 83.
|
| 1559 |
-
"train_steps_per_second": 1.
|
| 1560 |
}
|
| 1561 |
],
|
| 1562 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9807692307692307,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-lora-medmnistv2/checkpoint-2030",
|
| 4 |
"epoch": 9.98769987699877,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 2030,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.05,
|
| 13 |
+
"grad_norm": 1.854022741317749,
|
| 14 |
"learning_rate": 0.004975369458128079,
|
| 15 |
+
"loss": 0.5157,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.1,
|
| 20 |
+
"grad_norm": 2.006150245666504,
|
| 21 |
"learning_rate": 0.004950738916256157,
|
| 22 |
+
"loss": 0.645,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.15,
|
| 27 |
+
"grad_norm": 1.8034334182739258,
|
| 28 |
+
"learning_rate": 0.0049261083743842365,
|
| 29 |
+
"loss": 0.5907,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.2,
|
| 34 |
+
"grad_norm": 1.7398325204849243,
|
| 35 |
+
"learning_rate": 0.004903940886699507,
|
| 36 |
+
"loss": 0.6186,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.25,
|
| 41 |
+
"grad_norm": 1.3694934844970703,
|
| 42 |
+
"learning_rate": 0.004879310344827586,
|
| 43 |
+
"loss": 0.5955,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.3,
|
| 48 |
+
"grad_norm": 1.134981632232666,
|
| 49 |
+
"learning_rate": 0.004854679802955665,
|
| 50 |
+
"loss": 0.5948,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.34,
|
| 55 |
+
"grad_norm": 1.2749730348587036,
|
| 56 |
+
"learning_rate": 0.0048300492610837435,
|
| 57 |
+
"loss": 0.598,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.39,
|
| 62 |
+
"grad_norm": 2.5001230239868164,
|
| 63 |
+
"learning_rate": 0.004805418719211823,
|
| 64 |
+
"loss": 0.6648,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.44,
|
| 69 |
+
"grad_norm": 1.3467851877212524,
|
| 70 |
+
"learning_rate": 0.004780788177339902,
|
| 71 |
+
"loss": 0.6488,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.49,
|
| 76 |
+
"grad_norm": 1.319006323814392,
|
| 77 |
+
"learning_rate": 0.00475615763546798,
|
| 78 |
+
"loss": 0.6469,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.54,
|
| 83 |
+
"grad_norm": 1.564982295036316,
|
| 84 |
+
"learning_rate": 0.004731527093596059,
|
| 85 |
+
"loss": 0.5583,
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.59,
|
| 90 |
+
"grad_norm": 1.2751026153564453,
|
| 91 |
+
"learning_rate": 0.004706896551724138,
|
| 92 |
+
"loss": 0.5683,
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.64,
|
| 97 |
+
"grad_norm": 1.8151675462722778,
|
| 98 |
+
"learning_rate": 0.004682266009852217,
|
| 99 |
+
"loss": 0.6268,
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.69,
|
| 104 |
+
"grad_norm": 1.337044358253479,
|
| 105 |
+
"learning_rate": 0.004657635467980295,
|
| 106 |
+
"loss": 0.6423,
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.74,
|
| 111 |
+
"grad_norm": 1.5720871686935425,
|
| 112 |
"learning_rate": 0.004635467980295567,
|
| 113 |
+
"loss": 0.6581,
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.79,
|
| 118 |
+
"grad_norm": 1.5531283617019653,
|
| 119 |
"learning_rate": 0.004610837438423646,
|
| 120 |
+
"loss": 0.6095,
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.84,
|
| 125 |
+
"grad_norm": 3.048377513885498,
|
| 126 |
+
"learning_rate": 0.004586206896551724,
|
| 127 |
+
"loss": 0.661,
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.89,
|
| 132 |
+
"grad_norm": 1.9743188619613647,
|
| 133 |
"learning_rate": 0.004564039408866995,
|
| 134 |
+
"loss": 0.6506,
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.93,
|
| 139 |
+
"grad_norm": 1.9349859952926636,
|
| 140 |
"learning_rate": 0.004539408866995074,
|
| 141 |
+
"loss": 0.6681,
|
| 142 |
"step": 190
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.98,
|
| 146 |
+
"grad_norm": 1.7585110664367676,
|
| 147 |
"learning_rate": 0.004514778325123153,
|
| 148 |
+
"loss": 0.6525,
|
| 149 |
"step": 200
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 1.0,
|
| 153 |
+
"eval_accuracy": 0.9326923076923077,
|
| 154 |
+
"eval_f1": 0.9090572948739559,
|
| 155 |
+
"eval_loss": 0.20250679552555084,
|
| 156 |
+
"eval_precision": 0.9259619040327134,
|
| 157 |
+
"eval_recall": 0.9130050125624415,
|
| 158 |
+
"eval_runtime": 12.8179,
|
| 159 |
+
"eval_samples_per_second": 186.614,
|
| 160 |
+
"eval_steps_per_second": 11.702,
|
| 161 |
"step": 203
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 1.03,
|
| 165 |
+
"grad_norm": 1.5931968688964844,
|
| 166 |
"learning_rate": 0.004490147783251232,
|
| 167 |
+
"loss": 0.7042,
|
| 168 |
"step": 210
|
| 169 |
},
|
| 170 |
{
|
| 171 |
"epoch": 1.08,
|
| 172 |
+
"grad_norm": 4.101116180419922,
|
| 173 |
"learning_rate": 0.00446551724137931,
|
| 174 |
+
"loss": 0.4773,
|
| 175 |
"step": 220
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"epoch": 1.13,
|
| 179 |
+
"grad_norm": 3.1857903003692627,
|
| 180 |
"learning_rate": 0.004440886699507389,
|
| 181 |
+
"loss": 0.5874,
|
| 182 |
"step": 230
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 1.18,
|
| 186 |
+
"grad_norm": 1.9867714643478394,
|
| 187 |
"learning_rate": 0.004416256157635468,
|
| 188 |
+
"loss": 0.6094,
|
| 189 |
"step": 240
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 1.23,
|
| 193 |
+
"grad_norm": 2.3485002517700195,
|
| 194 |
"learning_rate": 0.004391625615763547,
|
| 195 |
+
"loss": 0.589,
|
| 196 |
"step": 250
|
| 197 |
},
|
| 198 |
{
|
| 199 |
"epoch": 1.28,
|
| 200 |
+
"grad_norm": 2.4279944896698,
|
| 201 |
"learning_rate": 0.004366995073891626,
|
| 202 |
+
"loss": 0.6718,
|
| 203 |
"step": 260
|
| 204 |
},
|
| 205 |
{
|
| 206 |
"epoch": 1.33,
|
| 207 |
+
"grad_norm": 2.5905745029449463,
|
| 208 |
"learning_rate": 0.004342364532019705,
|
| 209 |
+
"loss": 0.6379,
|
| 210 |
"step": 270
|
| 211 |
},
|
| 212 |
{
|
| 213 |
"epoch": 1.38,
|
| 214 |
+
"grad_norm": 1.4976040124893188,
|
| 215 |
"learning_rate": 0.004317733990147784,
|
| 216 |
+
"loss": 0.6386,
|
| 217 |
"step": 280
|
| 218 |
},
|
| 219 |
{
|
| 220 |
"epoch": 1.43,
|
| 221 |
+
"grad_norm": 2.4124257564544678,
|
| 222 |
"learning_rate": 0.004293103448275862,
|
| 223 |
+
"loss": 0.6483,
|
| 224 |
"step": 290
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 1.48,
|
| 228 |
+
"grad_norm": 1.5323392152786255,
|
| 229 |
"learning_rate": 0.00426847290640394,
|
| 230 |
+
"loss": 0.639,
|
| 231 |
"step": 300
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 1.53,
|
| 235 |
+
"grad_norm": 2.58333683013916,
|
| 236 |
"learning_rate": 0.004243842364532019,
|
| 237 |
+
"loss": 0.5527,
|
| 238 |
"step": 310
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"epoch": 1.57,
|
| 242 |
+
"grad_norm": 2.3336663246154785,
|
| 243 |
"learning_rate": 0.0042192118226600985,
|
| 244 |
+
"loss": 0.7489,
|
| 245 |
"step": 320
|
| 246 |
},
|
| 247 |
{
|
| 248 |
"epoch": 1.62,
|
| 249 |
+
"grad_norm": 3.3794748783111572,
|
| 250 |
"learning_rate": 0.004194581280788178,
|
| 251 |
+
"loss": 0.6175,
|
| 252 |
"step": 330
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 1.67,
|
| 256 |
+
"grad_norm": 2.078139543533325,
|
| 257 |
"learning_rate": 0.004169950738916256,
|
| 258 |
+
"loss": 0.6445,
|
| 259 |
"step": 340
|
| 260 |
},
|
| 261 |
{
|
| 262 |
"epoch": 1.72,
|
| 263 |
+
"grad_norm": 3.8369834423065186,
|
| 264 |
"learning_rate": 0.004145320197044335,
|
| 265 |
+
"loss": 0.7733,
|
| 266 |
"step": 350
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 1.77,
|
| 270 |
+
"grad_norm": 5.295024871826172,
|
| 271 |
"learning_rate": 0.004120689655172414,
|
| 272 |
+
"loss": 0.8105,
|
| 273 |
"step": 360
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 1.82,
|
| 277 |
+
"grad_norm": 6.0653181076049805,
|
| 278 |
"learning_rate": 0.004096059113300492,
|
| 279 |
+
"loss": 0.8405,
|
| 280 |
"step": 370
|
| 281 |
},
|
| 282 |
{
|
| 283 |
"epoch": 1.87,
|
| 284 |
+
"grad_norm": 3.94065260887146,
|
| 285 |
"learning_rate": 0.004071428571428571,
|
| 286 |
+
"loss": 0.8379,
|
| 287 |
"step": 380
|
| 288 |
},
|
| 289 |
{
|
| 290 |
"epoch": 1.92,
|
| 291 |
+
"grad_norm": 4.302937030792236,
|
| 292 |
"learning_rate": 0.00404679802955665,
|
| 293 |
+
"loss": 0.8095,
|
| 294 |
"step": 390
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 1.97,
|
| 298 |
+
"grad_norm": 4.810948371887207,
|
| 299 |
"learning_rate": 0.0040221674876847295,
|
| 300 |
+
"loss": 0.765,
|
| 301 |
"step": 400
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"epoch": 2.0,
|
| 305 |
+
"eval_accuracy": 0.9377090301003345,
|
| 306 |
+
"eval_f1": 0.9344003800244746,
|
| 307 |
+
"eval_loss": 0.2109694927930832,
|
| 308 |
+
"eval_precision": 0.9440505095684633,
|
| 309 |
+
"eval_recall": 0.9288923374288455,
|
| 310 |
+
"eval_runtime": 12.7867,
|
| 311 |
+
"eval_samples_per_second": 187.069,
|
| 312 |
+
"eval_steps_per_second": 11.731,
|
| 313 |
"step": 406
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 2.02,
|
| 317 |
+
"grad_norm": 9.29123306274414,
|
| 318 |
"learning_rate": 0.003997536945812808,
|
| 319 |
+
"loss": 0.8761,
|
| 320 |
"step": 410
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 2.07,
|
| 324 |
+
"grad_norm": 3.074866533279419,
|
| 325 |
"learning_rate": 0.003972906403940887,
|
| 326 |
+
"loss": 1.0319,
|
| 327 |
"step": 420
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 2.12,
|
| 331 |
+
"grad_norm": 1.6303837299346924,
|
| 332 |
"learning_rate": 0.003948275862068966,
|
| 333 |
+
"loss": 0.7979,
|
| 334 |
"step": 430
|
| 335 |
},
|
| 336 |
{
|
| 337 |
"epoch": 2.16,
|
| 338 |
+
"grad_norm": 1.928175687789917,
|
| 339 |
"learning_rate": 0.003923645320197044,
|
| 340 |
+
"loss": 0.7132,
|
| 341 |
"step": 440
|
| 342 |
},
|
| 343 |
{
|
| 344 |
"epoch": 2.21,
|
| 345 |
+
"grad_norm": 4.943911552429199,
|
| 346 |
"learning_rate": 0.0038990147783251232,
|
| 347 |
+
"loss": 0.7863,
|
| 348 |
"step": 450
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 2.26,
|
| 352 |
+
"grad_norm": 2.6557776927948,
|
| 353 |
"learning_rate": 0.0038743842364532023,
|
| 354 |
+
"loss": 0.6522,
|
| 355 |
"step": 460
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"epoch": 2.31,
|
| 359 |
+
"grad_norm": 15.654020309448242,
|
| 360 |
"learning_rate": 0.003849753694581281,
|
| 361 |
+
"loss": 0.8122,
|
| 362 |
"step": 470
|
| 363 |
},
|
| 364 |
{
|
| 365 |
"epoch": 2.36,
|
| 366 |
+
"grad_norm": 4.983061790466309,
|
| 367 |
"learning_rate": 0.00382512315270936,
|
| 368 |
+
"loss": 0.757,
|
| 369 |
"step": 480
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 2.41,
|
| 373 |
+
"grad_norm": 2.0351402759552,
|
| 374 |
"learning_rate": 0.0038004926108374383,
|
| 375 |
+
"loss": 0.5953,
|
| 376 |
"step": 490
|
| 377 |
},
|
| 378 |
{
|
| 379 |
"epoch": 2.46,
|
| 380 |
+
"grad_norm": 4.033576488494873,
|
| 381 |
"learning_rate": 0.003775862068965517,
|
| 382 |
+
"loss": 0.6497,
|
| 383 |
"step": 500
|
| 384 |
},
|
| 385 |
{
|
| 386 |
"epoch": 2.51,
|
| 387 |
+
"grad_norm": 3.6152243614196777,
|
| 388 |
"learning_rate": 0.003751231527093596,
|
| 389 |
+
"loss": 0.6615,
|
| 390 |
"step": 510
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 2.56,
|
| 394 |
+
"grad_norm": 3.6705260276794434,
|
| 395 |
"learning_rate": 0.0037266009852216747,
|
| 396 |
+
"loss": 0.6813,
|
| 397 |
"step": 520
|
| 398 |
},
|
| 399 |
{
|
| 400 |
"epoch": 2.61,
|
| 401 |
+
"grad_norm": 4.159302234649658,
|
| 402 |
"learning_rate": 0.003701970443349754,
|
| 403 |
+
"loss": 0.6579,
|
| 404 |
"step": 530
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 2.66,
|
| 408 |
+
"grad_norm": 2.04949951171875,
|
| 409 |
"learning_rate": 0.0036773399014778324,
|
| 410 |
+
"loss": 0.6976,
|
| 411 |
"step": 540
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 2.71,
|
| 415 |
+
"grad_norm": 1.9712501764297485,
|
| 416 |
"learning_rate": 0.0036527093596059115,
|
| 417 |
+
"loss": 0.6729,
|
| 418 |
"step": 550
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"epoch": 2.76,
|
| 422 |
+
"grad_norm": 2.4759750366210938,
|
| 423 |
"learning_rate": 0.00362807881773399,
|
| 424 |
+
"loss": 0.7195,
|
| 425 |
"step": 560
|
| 426 |
},
|
| 427 |
{
|
| 428 |
"epoch": 2.8,
|
| 429 |
+
"grad_norm": 1.463779091835022,
|
| 430 |
"learning_rate": 0.003603448275862069,
|
| 431 |
+
"loss": 0.7682,
|
| 432 |
"step": 570
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"epoch": 2.85,
|
| 436 |
+
"grad_norm": 3.0022284984588623,
|
| 437 |
"learning_rate": 0.003578817733990148,
|
| 438 |
+
"loss": 0.5556,
|
| 439 |
"step": 580
|
| 440 |
},
|
| 441 |
{
|
| 442 |
"epoch": 2.9,
|
| 443 |
+
"grad_norm": 2.585496187210083,
|
| 444 |
"learning_rate": 0.0035541871921182266,
|
| 445 |
+
"loss": 0.7779,
|
| 446 |
"step": 590
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 2.95,
|
| 450 |
+
"grad_norm": 1.619903326034546,
|
| 451 |
"learning_rate": 0.0035295566502463057,
|
| 452 |
+
"loss": 0.6514,
|
| 453 |
"step": 600
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 3.0,
|
| 457 |
+
"eval_accuracy": 0.9489966555183946,
|
| 458 |
+
"eval_f1": 0.9427879032940832,
|
| 459 |
+
"eval_loss": 0.20264820754528046,
|
| 460 |
+
"eval_precision": 0.9456850153895534,
|
| 461 |
+
"eval_recall": 0.9442313976349834,
|
| 462 |
+
"eval_runtime": 12.7657,
|
| 463 |
+
"eval_samples_per_second": 187.377,
|
| 464 |
+
"eval_steps_per_second": 11.75,
|
| 465 |
"step": 609
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 3.0,
|
| 469 |
+
"grad_norm": 1.8233991861343384,
|
| 470 |
"learning_rate": 0.0035049261083743843,
|
| 471 |
+
"loss": 0.7235,
|
| 472 |
"step": 610
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"epoch": 3.05,
|
| 476 |
+
"grad_norm": 2.941433906555176,
|
| 477 |
"learning_rate": 0.0034802955665024634,
|
| 478 |
+
"loss": 0.8571,
|
| 479 |
"step": 620
|
| 480 |
},
|
| 481 |
{
|
| 482 |
"epoch": 3.1,
|
| 483 |
+
"grad_norm": 2.526165723800659,
|
| 484 |
"learning_rate": 0.003455665024630542,
|
| 485 |
+
"loss": 0.7949,
|
| 486 |
"step": 630
|
| 487 |
},
|
| 488 |
{
|
| 489 |
"epoch": 3.15,
|
| 490 |
+
"grad_norm": 2.683561086654663,
|
| 491 |
"learning_rate": 0.0034310344827586207,
|
| 492 |
+
"loss": 0.811,
|
| 493 |
"step": 640
|
| 494 |
},
|
| 495 |
{
|
| 496 |
"epoch": 3.2,
|
| 497 |
+
"grad_norm": 4.099231243133545,
|
| 498 |
"learning_rate": 0.0034064039408867,
|
| 499 |
+
"loss": 0.694,
|
| 500 |
"step": 650
|
| 501 |
},
|
| 502 |
{
|
| 503 |
"epoch": 3.25,
|
| 504 |
+
"grad_norm": 7.0789289474487305,
|
| 505 |
"learning_rate": 0.0033817733990147785,
|
| 506 |
+
"loss": 0.6623,
|
| 507 |
"step": 660
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 3.3,
|
| 511 |
+
"grad_norm": 4.69476842880249,
|
| 512 |
"learning_rate": 0.003357142857142857,
|
| 513 |
+
"loss": 0.6777,
|
| 514 |
"step": 670
|
| 515 |
},
|
| 516 |
{
|
| 517 |
"epoch": 3.35,
|
| 518 |
+
"grad_norm": 3.9503209590911865,
|
| 519 |
"learning_rate": 0.003332512315270936,
|
| 520 |
+
"loss": 0.6973,
|
| 521 |
"step": 680
|
| 522 |
},
|
| 523 |
{
|
| 524 |
"epoch": 3.39,
|
| 525 |
+
"grad_norm": 2.756246328353882,
|
| 526 |
"learning_rate": 0.0033078817733990145,
|
| 527 |
+
"loss": 0.6769,
|
| 528 |
"step": 690
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 3.44,
|
| 532 |
+
"grad_norm": 2.2053091526031494,
|
| 533 |
"learning_rate": 0.0032832512315270936,
|
| 534 |
+
"loss": 0.694,
|
| 535 |
"step": 700
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"epoch": 3.49,
|
| 539 |
+
"grad_norm": 2.942899465560913,
|
| 540 |
"learning_rate": 0.003258620689655172,
|
| 541 |
+
"loss": 0.6559,
|
| 542 |
"step": 710
|
| 543 |
},
|
| 544 |
{
|
| 545 |
"epoch": 3.54,
|
| 546 |
+
"grad_norm": 3.347179651260376,
|
| 547 |
"learning_rate": 0.0032339901477832513,
|
| 548 |
+
"loss": 0.7284,
|
| 549 |
"step": 720
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 3.59,
|
| 553 |
+
"grad_norm": 3.367220163345337,
|
| 554 |
"learning_rate": 0.00320935960591133,
|
| 555 |
+
"loss": 0.6454,
|
| 556 |
"step": 730
|
| 557 |
},
|
| 558 |
{
|
| 559 |
"epoch": 3.64,
|
| 560 |
+
"grad_norm": 3.6450581550598145,
|
| 561 |
"learning_rate": 0.003184729064039409,
|
| 562 |
+
"loss": 0.6734,
|
| 563 |
"step": 740
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 3.69,
|
| 567 |
+
"grad_norm": 2.7060301303863525,
|
| 568 |
"learning_rate": 0.0031600985221674877,
|
| 569 |
+
"loss": 0.682,
|
| 570 |
"step": 750
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 3.74,
|
| 574 |
+
"grad_norm": 2.4949233531951904,
|
| 575 |
+
"learning_rate": 0.0031354679802955664,
|
| 576 |
+
"loss": 0.6368,
|
| 577 |
"step": 760
|
| 578 |
},
|
| 579 |
{
|
| 580 |
"epoch": 3.79,
|
| 581 |
+
"grad_norm": 2.195974826812744,
|
| 582 |
+
"learning_rate": 0.0031108374384236455,
|
| 583 |
+
"loss": 0.5631,
|
| 584 |
"step": 770
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"epoch": 3.84,
|
| 588 |
+
"grad_norm": 2.8718490600585938,
|
| 589 |
+
"learning_rate": 0.003086206896551724,
|
| 590 |
+
"loss": 0.6699,
|
| 591 |
"step": 780
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 3.89,
|
| 595 |
+
"grad_norm": 2.896594524383545,
|
| 596 |
+
"learning_rate": 0.003061576354679803,
|
| 597 |
+
"loss": 0.6374,
|
| 598 |
"step": 790
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"epoch": 3.94,
|
| 602 |
+
"grad_norm": 2.3888590335845947,
|
| 603 |
+
"learning_rate": 0.003036945812807882,
|
| 604 |
+
"loss": 0.6104,
|
| 605 |
"step": 800
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 3.99,
|
| 609 |
+
"grad_norm": 3.1360650062561035,
|
| 610 |
+
"learning_rate": 0.003012315270935961,
|
| 611 |
+
"loss": 0.6405,
|
| 612 |
"step": 810
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 4.0,
|
| 616 |
+
"eval_accuracy": 0.9289297658862876,
|
| 617 |
+
"eval_f1": 0.9267094039271597,
|
| 618 |
+
"eval_loss": 0.20555561780929565,
|
| 619 |
+
"eval_precision": 0.9480713468179534,
|
| 620 |
+
"eval_recall": 0.9174817160045543,
|
| 621 |
+
"eval_runtime": 12.7217,
|
| 622 |
+
"eval_samples_per_second": 188.025,
|
| 623 |
+
"eval_steps_per_second": 11.791,
|
| 624 |
"step": 813
|
| 625 |
},
|
| 626 |
{
|
| 627 |
"epoch": 4.03,
|
| 628 |
+
"grad_norm": 2.944392681121826,
|
| 629 |
+
"learning_rate": 0.0029876847290640396,
|
| 630 |
+
"loss": 0.6386,
|
| 631 |
"step": 820
|
| 632 |
},
|
| 633 |
{
|
| 634 |
"epoch": 4.08,
|
| 635 |
+
"grad_norm": 2.1877291202545166,
|
| 636 |
+
"learning_rate": 0.0029630541871921187,
|
| 637 |
+
"loss": 0.554,
|
| 638 |
"step": 830
|
| 639 |
},
|
| 640 |
{
|
| 641 |
"epoch": 4.13,
|
| 642 |
+
"grad_norm": 2.3481550216674805,
|
| 643 |
+
"learning_rate": 0.0029384236453201974,
|
| 644 |
+
"loss": 0.6096,
|
| 645 |
"step": 840
|
| 646 |
},
|
| 647 |
{
|
| 648 |
"epoch": 4.18,
|
| 649 |
+
"grad_norm": 1.2819880247116089,
|
| 650 |
+
"learning_rate": 0.002913793103448276,
|
| 651 |
+
"loss": 0.6056,
|
| 652 |
"step": 850
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"epoch": 4.23,
|
| 656 |
+
"grad_norm": 2.8151116371154785,
|
| 657 |
+
"learning_rate": 0.0028891625615763547,
|
| 658 |
+
"loss": 0.529,
|
| 659 |
"step": 860
|
| 660 |
},
|
| 661 |
{
|
| 662 |
"epoch": 4.28,
|
| 663 |
+
"grad_norm": 1.4771710634231567,
|
| 664 |
+
"learning_rate": 0.0028645320197044333,
|
| 665 |
+
"loss": 0.6179,
|
| 666 |
"step": 870
|
| 667 |
},
|
| 668 |
{
|
| 669 |
"epoch": 4.33,
|
| 670 |
+
"grad_norm": 1.6470296382904053,
|
| 671 |
+
"learning_rate": 0.002839901477832512,
|
| 672 |
+
"loss": 0.5378,
|
| 673 |
"step": 880
|
| 674 |
},
|
| 675 |
{
|
| 676 |
"epoch": 4.38,
|
| 677 |
+
"grad_norm": 1.7947298288345337,
|
| 678 |
+
"learning_rate": 0.002815270935960591,
|
| 679 |
+
"loss": 0.6106,
|
| 680 |
"step": 890
|
| 681 |
},
|
| 682 |
{
|
| 683 |
"epoch": 4.43,
|
| 684 |
+
"grad_norm": 1.3656386137008667,
|
| 685 |
+
"learning_rate": 0.0027906403940886697,
|
| 686 |
+
"loss": 0.559,
|
| 687 |
"step": 900
|
| 688 |
},
|
| 689 |
{
|
| 690 |
"epoch": 4.48,
|
| 691 |
+
"grad_norm": 1.5877206325531006,
|
| 692 |
+
"learning_rate": 0.002766009852216749,
|
| 693 |
+
"loss": 0.6011,
|
| 694 |
"step": 910
|
| 695 |
},
|
| 696 |
{
|
| 697 |
"epoch": 4.53,
|
| 698 |
+
"grad_norm": 1.7223550081253052,
|
| 699 |
+
"learning_rate": 0.0027413793103448275,
|
| 700 |
+
"loss": 0.569,
|
| 701 |
"step": 920
|
| 702 |
},
|
| 703 |
{
|
| 704 |
"epoch": 4.58,
|
| 705 |
+
"grad_norm": 3.068004608154297,
|
| 706 |
+
"learning_rate": 0.0027167487684729066,
|
| 707 |
+
"loss": 0.579,
|
| 708 |
"step": 930
|
| 709 |
},
|
| 710 |
{
|
| 711 |
"epoch": 4.62,
|
| 712 |
+
"grad_norm": 2.741926908493042,
|
| 713 |
+
"learning_rate": 0.0026921182266009852,
|
| 714 |
+
"loss": 0.632,
|
| 715 |
"step": 940
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"epoch": 4.67,
|
| 719 |
+
"grad_norm": 2.4220759868621826,
|
| 720 |
+
"learning_rate": 0.0026674876847290643,
|
| 721 |
+
"loss": 0.676,
|
| 722 |
"step": 950
|
| 723 |
},
|
| 724 |
{
|
| 725 |
"epoch": 4.72,
|
| 726 |
+
"grad_norm": 2.406053066253662,
|
| 727 |
+
"learning_rate": 0.002642857142857143,
|
| 728 |
+
"loss": 0.6331,
|
| 729 |
"step": 960
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 4.77,
|
| 733 |
+
"grad_norm": 3.668957471847534,
|
| 734 |
+
"learning_rate": 0.0026182266009852216,
|
| 735 |
+
"loss": 0.5617,
|
| 736 |
"step": 970
|
| 737 |
},
|
| 738 |
{
|
| 739 |
"epoch": 4.82,
|
| 740 |
+
"grad_norm": 2.904611825942993,
|
| 741 |
+
"learning_rate": 0.0025935960591133007,
|
| 742 |
+
"loss": 0.5911,
|
| 743 |
"step": 980
|
| 744 |
},
|
| 745 |
{
|
| 746 |
"epoch": 4.87,
|
| 747 |
+
"grad_norm": 2.3104119300842285,
|
| 748 |
+
"learning_rate": 0.0025689655172413794,
|
| 749 |
+
"loss": 0.6124,
|
| 750 |
"step": 990
|
| 751 |
},
|
| 752 |
{
|
| 753 |
"epoch": 4.92,
|
| 754 |
+
"grad_norm": 3.4378082752227783,
|
| 755 |
+
"learning_rate": 0.0025443349753694585,
|
| 756 |
+
"loss": 0.6497,
|
| 757 |
"step": 1000
|
| 758 |
},
|
| 759 |
{
|
| 760 |
"epoch": 4.97,
|
| 761 |
+
"grad_norm": 3.1942694187164307,
|
| 762 |
+
"learning_rate": 0.002519704433497537,
|
| 763 |
+
"loss": 0.6514,
|
| 764 |
"step": 1010
|
| 765 |
},
|
| 766 |
{
|
| 767 |
"epoch": 5.0,
|
| 768 |
+
"eval_accuracy": 0.9523411371237458,
|
| 769 |
+
"eval_f1": 0.9382471321690677,
|
| 770 |
+
"eval_loss": 0.1361980438232422,
|
| 771 |
+
"eval_precision": 0.9459238480466342,
|
| 772 |
+
"eval_recall": 0.9385166217680354,
|
| 773 |
+
"eval_runtime": 12.797,
|
| 774 |
+
"eval_samples_per_second": 186.918,
|
| 775 |
+
"eval_steps_per_second": 11.721,
|
| 776 |
"step": 1016
|
| 777 |
},
|
| 778 |
{
|
| 779 |
"epoch": 5.02,
|
| 780 |
+
"grad_norm": 2.186038017272949,
|
| 781 |
+
"learning_rate": 0.002495073891625616,
|
| 782 |
+
"loss": 0.6427,
|
| 783 |
"step": 1020
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 5.07,
|
| 787 |
+
"grad_norm": 1.6945507526397705,
|
| 788 |
+
"learning_rate": 0.0024704433497536944,
|
| 789 |
+
"loss": 0.6153,
|
| 790 |
"step": 1030
|
| 791 |
},
|
| 792 |
{
|
| 793 |
"epoch": 5.12,
|
| 794 |
+
"grad_norm": 1.6330933570861816,
|
| 795 |
+
"learning_rate": 0.0024458128078817735,
|
| 796 |
+
"loss": 0.5831,
|
| 797 |
"step": 1040
|
| 798 |
},
|
| 799 |
{
|
| 800 |
"epoch": 5.17,
|
| 801 |
+
"grad_norm": 5.190056800842285,
|
| 802 |
+
"learning_rate": 0.002421182266009852,
|
| 803 |
+
"loss": 0.5627,
|
| 804 |
"step": 1050
|
| 805 |
},
|
| 806 |
{
|
| 807 |
"epoch": 5.22,
|
| 808 |
+
"grad_norm": 1.9557955265045166,
|
| 809 |
+
"learning_rate": 0.0023965517241379313,
|
| 810 |
+
"loss": 0.6279,
|
| 811 |
"step": 1060
|
| 812 |
},
|
| 813 |
{
|
| 814 |
"epoch": 5.26,
|
| 815 |
+
"grad_norm": 2.5824782848358154,
|
| 816 |
+
"learning_rate": 0.00237192118226601,
|
| 817 |
+
"loss": 0.6097,
|
| 818 |
"step": 1070
|
| 819 |
},
|
| 820 |
{
|
| 821 |
"epoch": 5.31,
|
| 822 |
+
"grad_norm": 2.0462582111358643,
|
| 823 |
+
"learning_rate": 0.002347290640394089,
|
| 824 |
+
"loss": 0.6527,
|
| 825 |
"step": 1080
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 5.36,
|
| 829 |
+
"grad_norm": 2.071093797683716,
|
| 830 |
+
"learning_rate": 0.0023226600985221672,
|
| 831 |
+
"loss": 0.6164,
|
| 832 |
"step": 1090
|
| 833 |
},
|
| 834 |
{
|
| 835 |
"epoch": 5.41,
|
| 836 |
+
"grad_norm": 2.4309191703796387,
|
| 837 |
+
"learning_rate": 0.0022980295566502463,
|
| 838 |
+
"loss": 0.5927,
|
| 839 |
"step": 1100
|
| 840 |
},
|
| 841 |
{
|
| 842 |
"epoch": 5.46,
|
| 843 |
+
"grad_norm": 2.204646110534668,
|
| 844 |
+
"learning_rate": 0.002273399014778325,
|
| 845 |
+
"loss": 0.5524,
|
| 846 |
"step": 1110
|
| 847 |
},
|
| 848 |
{
|
| 849 |
"epoch": 5.51,
|
| 850 |
+
"grad_norm": 2.399622917175293,
|
| 851 |
+
"learning_rate": 0.002248768472906404,
|
| 852 |
+
"loss": 0.493,
|
| 853 |
"step": 1120
|
| 854 |
},
|
| 855 |
{
|
| 856 |
"epoch": 5.56,
|
| 857 |
+
"grad_norm": 2.0351855754852295,
|
| 858 |
+
"learning_rate": 0.0022241379310344827,
|
| 859 |
+
"loss": 0.4818,
|
| 860 |
"step": 1130
|
| 861 |
},
|
| 862 |
{
|
| 863 |
"epoch": 5.61,
|
| 864 |
+
"grad_norm": 1.677395224571228,
|
| 865 |
+
"learning_rate": 0.002199507389162562,
|
| 866 |
+
"loss": 0.523,
|
| 867 |
"step": 1140
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 5.66,
|
| 871 |
+
"grad_norm": 3.4297292232513428,
|
| 872 |
+
"learning_rate": 0.0021748768472906405,
|
| 873 |
+
"loss": 0.5055,
|
| 874 |
"step": 1150
|
| 875 |
},
|
| 876 |
{
|
| 877 |
"epoch": 5.71,
|
| 878 |
+
"grad_norm": 1.9771558046340942,
|
| 879 |
+
"learning_rate": 0.002150246305418719,
|
| 880 |
+
"loss": 0.5898,
|
| 881 |
"step": 1160
|
| 882 |
},
|
| 883 |
{
|
| 884 |
"epoch": 5.76,
|
| 885 |
+
"grad_norm": 1.6579110622406006,
|
| 886 |
+
"learning_rate": 0.0021256157635467982,
|
| 887 |
+
"loss": 0.5073,
|
| 888 |
"step": 1170
|
| 889 |
},
|
| 890 |
{
|
| 891 |
"epoch": 5.81,
|
| 892 |
+
"grad_norm": 2.7034878730773926,
|
| 893 |
+
"learning_rate": 0.002100985221674877,
|
| 894 |
+
"loss": 0.6095,
|
| 895 |
"step": 1180
|
| 896 |
},
|
| 897 |
{
|
| 898 |
"epoch": 5.85,
|
| 899 |
+
"grad_norm": 2.2419373989105225,
|
| 900 |
+
"learning_rate": 0.0020763546798029556,
|
| 901 |
+
"loss": 0.5336,
|
| 902 |
"step": 1190
|
| 903 |
},
|
| 904 |
{
|
| 905 |
"epoch": 5.9,
|
| 906 |
+
"grad_norm": 5.060290813446045,
|
| 907 |
+
"learning_rate": 0.0020517241379310346,
|
| 908 |
+
"loss": 0.5068,
|
| 909 |
"step": 1200
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 5.95,
|
| 913 |
+
"grad_norm": 2.3167221546173096,
|
| 914 |
+
"learning_rate": 0.0020270935960591133,
|
| 915 |
+
"loss": 0.5778,
|
| 916 |
"step": 1210
|
| 917 |
},
|
| 918 |
{
|
| 919 |
"epoch": 6.0,
|
| 920 |
+
"eval_accuracy": 0.9770066889632107,
|
| 921 |
+
"eval_f1": 0.9737037280009198,
|
| 922 |
+
"eval_loss": 0.07868464291095734,
|
| 923 |
+
"eval_precision": 0.9739305124429692,
|
| 924 |
+
"eval_recall": 0.9746007095898861,
|
| 925 |
+
"eval_runtime": 12.8063,
|
| 926 |
+
"eval_samples_per_second": 186.783,
|
| 927 |
+
"eval_steps_per_second": 11.713,
|
| 928 |
"step": 1219
|
| 929 |
},
|
| 930 |
{
|
| 931 |
"epoch": 6.0,
|
| 932 |
+
"grad_norm": 2.2392728328704834,
|
| 933 |
+
"learning_rate": 0.002002463054187192,
|
| 934 |
+
"loss": 0.4562,
|
| 935 |
"step": 1220
|
| 936 |
},
|
| 937 |
{
|
| 938 |
"epoch": 6.05,
|
| 939 |
+
"grad_norm": 1.9161555767059326,
|
| 940 |
+
"learning_rate": 0.001977832512315271,
|
| 941 |
+
"loss": 0.5549,
|
| 942 |
"step": 1230
|
| 943 |
},
|
| 944 |
{
|
| 945 |
"epoch": 6.1,
|
| 946 |
+
"grad_norm": 3.461010694503784,
|
| 947 |
+
"learning_rate": 0.0019532019704433497,
|
| 948 |
+
"loss": 0.4686,
|
| 949 |
"step": 1240
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"epoch": 6.15,
|
| 953 |
+
"grad_norm": 2.4330320358276367,
|
| 954 |
+
"learning_rate": 0.0019285714285714288,
|
| 955 |
+
"loss": 0.5092,
|
| 956 |
"step": 1250
|
| 957 |
},
|
| 958 |
{
|
| 959 |
"epoch": 6.2,
|
| 960 |
+
"grad_norm": 3.475228786468506,
|
| 961 |
+
"learning_rate": 0.0019039408866995075,
|
| 962 |
+
"loss": 0.5897,
|
| 963 |
"step": 1260
|
| 964 |
},
|
| 965 |
{
|
| 966 |
"epoch": 6.25,
|
| 967 |
+
"grad_norm": 2.0373263359069824,
|
| 968 |
+
"learning_rate": 0.0018793103448275861,
|
| 969 |
+
"loss": 0.488,
|
| 970 |
"step": 1270
|
| 971 |
},
|
| 972 |
{
|
| 973 |
"epoch": 6.3,
|
| 974 |
+
"grad_norm": 2.285243272781372,
|
| 975 |
+
"learning_rate": 0.001854679802955665,
|
| 976 |
+
"loss": 0.5263,
|
| 977 |
"step": 1280
|
| 978 |
},
|
| 979 |
{
|
| 980 |
"epoch": 6.35,
|
| 981 |
+
"grad_norm": 2.0365989208221436,
|
| 982 |
+
"learning_rate": 0.0018300492610837439,
|
| 983 |
+
"loss": 0.4668,
|
| 984 |
"step": 1290
|
| 985 |
},
|
| 986 |
{
|
| 987 |
"epoch": 6.4,
|
| 988 |
+
"grad_norm": 1.457801103591919,
|
| 989 |
+
"learning_rate": 0.0018054187192118227,
|
| 990 |
+
"loss": 0.4518,
|
| 991 |
"step": 1300
|
| 992 |
},
|
| 993 |
{
|
| 994 |
"epoch": 6.45,
|
| 995 |
+
"grad_norm": 1.9687854051589966,
|
| 996 |
+
"learning_rate": 0.0017807881773399016,
|
| 997 |
+
"loss": 0.4986,
|
| 998 |
"step": 1310
|
| 999 |
},
|
| 1000 |
{
|
| 1001 |
"epoch": 6.49,
|
| 1002 |
+
"grad_norm": 3.3556230068206787,
|
| 1003 |
+
"learning_rate": 0.0017561576354679803,
|
| 1004 |
+
"loss": 0.4955,
|
| 1005 |
"step": 1320
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 6.54,
|
| 1009 |
+
"grad_norm": 2.372751474380493,
|
| 1010 |
+
"learning_rate": 0.0017315270935960591,
|
| 1011 |
+
"loss": 0.542,
|
| 1012 |
"step": 1330
|
| 1013 |
},
|
| 1014 |
{
|
| 1015 |
"epoch": 6.59,
|
| 1016 |
+
"grad_norm": 2.2720744609832764,
|
| 1017 |
+
"learning_rate": 0.001706896551724138,
|
| 1018 |
+
"loss": 0.4917,
|
| 1019 |
"step": 1340
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
"epoch": 6.64,
|
| 1023 |
+
"grad_norm": 1.2895252704620361,
|
| 1024 |
+
"learning_rate": 0.0016822660098522169,
|
| 1025 |
+
"loss": 0.5833,
|
| 1026 |
"step": 1350
|
| 1027 |
},
|
| 1028 |
{
|
| 1029 |
"epoch": 6.69,
|
| 1030 |
+
"grad_norm": 2.9902422428131104,
|
| 1031 |
+
"learning_rate": 0.0016576354679802955,
|
| 1032 |
+
"loss": 0.5227,
|
| 1033 |
"step": 1360
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
"epoch": 6.74,
|
| 1037 |
+
"grad_norm": 1.3934229612350464,
|
| 1038 |
+
"learning_rate": 0.0016330049261083744,
|
| 1039 |
+
"loss": 0.503,
|
| 1040 |
"step": 1370
|
| 1041 |
},
|
| 1042 |
{
|
| 1043 |
"epoch": 6.79,
|
| 1044 |
+
"grad_norm": 1.479251503944397,
|
| 1045 |
+
"learning_rate": 0.001608374384236453,
|
| 1046 |
+
"loss": 0.506,
|
| 1047 |
"step": 1380
|
| 1048 |
},
|
| 1049 |
{
|
| 1050 |
"epoch": 6.84,
|
| 1051 |
+
"grad_norm": 2.6870193481445312,
|
| 1052 |
+
"learning_rate": 0.001583743842364532,
|
| 1053 |
+
"loss": 0.4654,
|
| 1054 |
"step": 1390
|
| 1055 |
},
|
| 1056 |
{
|
| 1057 |
"epoch": 6.89,
|
| 1058 |
+
"grad_norm": 1.2971521615982056,
|
| 1059 |
+
"learning_rate": 0.0015591133004926108,
|
| 1060 |
+
"loss": 0.4906,
|
| 1061 |
"step": 1400
|
| 1062 |
},
|
| 1063 |
{
|
| 1064 |
"epoch": 6.94,
|
| 1065 |
+
"grad_norm": 1.7734407186508179,
|
| 1066 |
+
"learning_rate": 0.0015344827586206897,
|
| 1067 |
+
"loss": 0.4829,
|
| 1068 |
"step": 1410
|
| 1069 |
},
|
| 1070 |
{
|
| 1071 |
"epoch": 6.99,
|
| 1072 |
+
"grad_norm": 1.2960278987884521,
|
| 1073 |
+
"learning_rate": 0.0015098522167487686,
|
| 1074 |
+
"loss": 0.4759,
|
| 1075 |
"step": 1420
|
| 1076 |
},
|
| 1077 |
{
|
| 1078 |
"epoch": 7.0,
|
| 1079 |
+
"eval_accuracy": 0.9724080267558528,
|
| 1080 |
+
"eval_f1": 0.9714127059477171,
|
| 1081 |
+
"eval_loss": 0.09588505327701569,
|
| 1082 |
+
"eval_precision": 0.9743979044505011,
|
| 1083 |
+
"eval_recall": 0.9692755583510763,
|
| 1084 |
+
"eval_runtime": 12.8496,
|
| 1085 |
+
"eval_samples_per_second": 186.154,
|
| 1086 |
+
"eval_steps_per_second": 11.674,
|
| 1087 |
"step": 1422
|
| 1088 |
},
|
| 1089 |
{
|
| 1090 |
"epoch": 7.04,
|
| 1091 |
+
"grad_norm": 0.9376949071884155,
|
| 1092 |
+
"learning_rate": 0.0014852216748768474,
|
| 1093 |
+
"loss": 0.3886,
|
| 1094 |
"step": 1430
|
| 1095 |
},
|
| 1096 |
{
|
| 1097 |
"epoch": 7.08,
|
| 1098 |
+
"grad_norm": 1.449591040611267,
|
| 1099 |
+
"learning_rate": 0.0014605911330049263,
|
| 1100 |
+
"loss": 0.4327,
|
| 1101 |
"step": 1440
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
"epoch": 7.13,
|
| 1105 |
+
"grad_norm": 1.4483599662780762,
|
| 1106 |
+
"learning_rate": 0.0014359605911330052,
|
| 1107 |
+
"loss": 0.4035,
|
| 1108 |
"step": 1450
|
| 1109 |
},
|
| 1110 |
{
|
| 1111 |
"epoch": 7.18,
|
| 1112 |
+
"grad_norm": 1.8822619915008545,
|
| 1113 |
+
"learning_rate": 0.0014113300492610836,
|
| 1114 |
+
"loss": 0.4234,
|
| 1115 |
"step": 1460
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
"epoch": 7.23,
|
| 1119 |
+
"grad_norm": 2.542346239089966,
|
| 1120 |
+
"learning_rate": 0.0013866995073891625,
|
| 1121 |
+
"loss": 0.4178,
|
| 1122 |
"step": 1470
|
| 1123 |
},
|
| 1124 |
{
|
| 1125 |
"epoch": 7.28,
|
| 1126 |
+
"grad_norm": 2.098578929901123,
|
| 1127 |
+
"learning_rate": 0.0013620689655172414,
|
| 1128 |
+
"loss": 0.4904,
|
| 1129 |
"step": 1480
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
"epoch": 7.33,
|
| 1133 |
+
"grad_norm": 2.8648364543914795,
|
| 1134 |
+
"learning_rate": 0.0013374384236453203,
|
| 1135 |
+
"loss": 0.4314,
|
| 1136 |
"step": 1490
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
"epoch": 7.38,
|
| 1140 |
+
"grad_norm": 2.2441766262054443,
|
| 1141 |
+
"learning_rate": 0.0013128078817733991,
|
| 1142 |
+
"loss": 0.4915,
|
| 1143 |
"step": 1500
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 7.43,
|
| 1147 |
+
"grad_norm": 2.867161989212036,
|
| 1148 |
+
"learning_rate": 0.001288177339901478,
|
| 1149 |
+
"loss": 0.4285,
|
| 1150 |
"step": 1510
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
"epoch": 7.48,
|
| 1154 |
+
"grad_norm": 2.074552297592163,
|
| 1155 |
+
"learning_rate": 0.0012635467980295567,
|
| 1156 |
+
"loss": 0.4875,
|
| 1157 |
"step": 1520
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
"epoch": 7.53,
|
| 1161 |
+
"grad_norm": 1.6760947704315186,
|
| 1162 |
+
"learning_rate": 0.0012389162561576355,
|
| 1163 |
+
"loss": 0.4438,
|
| 1164 |
"step": 1530
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
"epoch": 7.58,
|
| 1168 |
+
"grad_norm": 3.0626227855682373,
|
| 1169 |
+
"learning_rate": 0.0012142857142857144,
|
| 1170 |
+
"loss": 0.4202,
|
| 1171 |
"step": 1540
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
"epoch": 7.63,
|
| 1175 |
+
"grad_norm": 1.759521722793579,
|
| 1176 |
+
"learning_rate": 0.001189655172413793,
|
| 1177 |
+
"loss": 0.6058,
|
| 1178 |
"step": 1550
|
| 1179 |
},
|
| 1180 |
{
|
| 1181 |
"epoch": 7.68,
|
| 1182 |
+
"grad_norm": 1.6488869190216064,
|
| 1183 |
+
"learning_rate": 0.001165024630541872,
|
| 1184 |
+
"loss": 0.4106,
|
| 1185 |
"step": 1560
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"epoch": 7.72,
|
| 1189 |
+
"grad_norm": 1.598101019859314,
|
| 1190 |
+
"learning_rate": 0.0011403940886699508,
|
| 1191 |
+
"loss": 0.3934,
|
| 1192 |
"step": 1570
|
| 1193 |
},
|
| 1194 |
{
|
| 1195 |
"epoch": 7.77,
|
| 1196 |
+
"grad_norm": 1.9214413166046143,
|
| 1197 |
+
"learning_rate": 0.0011157635467980295,
|
| 1198 |
+
"loss": 0.4484,
|
| 1199 |
"step": 1580
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
"epoch": 7.82,
|
| 1203 |
+
"grad_norm": 1.8111754655838013,
|
| 1204 |
+
"learning_rate": 0.0010911330049261083,
|
| 1205 |
+
"loss": 0.4292,
|
| 1206 |
"step": 1590
|
| 1207 |
},
|
| 1208 |
{
|
| 1209 |
"epoch": 7.87,
|
| 1210 |
+
"grad_norm": 1.7007110118865967,
|
| 1211 |
+
"learning_rate": 0.0010665024630541872,
|
| 1212 |
+
"loss": 0.3767,
|
| 1213 |
"step": 1600
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
"epoch": 7.92,
|
| 1217 |
+
"grad_norm": 1.5511890649795532,
|
| 1218 |
+
"learning_rate": 0.001041871921182266,
|
| 1219 |
+
"loss": 0.4394,
|
| 1220 |
"step": 1610
|
| 1221 |
},
|
| 1222 |
{
|
| 1223 |
"epoch": 7.97,
|
| 1224 |
+
"grad_norm": 1.2566757202148438,
|
| 1225 |
+
"learning_rate": 0.0010172413793103447,
|
| 1226 |
+
"loss": 0.482,
|
| 1227 |
"step": 1620
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
"epoch": 8.0,
|
| 1231 |
+
"eval_accuracy": 0.9761705685618729,
|
| 1232 |
+
"eval_f1": 0.9732825494984669,
|
| 1233 |
+
"eval_loss": 0.07430998235940933,
|
| 1234 |
+
"eval_precision": 0.9737460251788703,
|
| 1235 |
+
"eval_recall": 0.9737015525572723,
|
| 1236 |
+
"eval_runtime": 12.8992,
|
| 1237 |
+
"eval_samples_per_second": 185.438,
|
| 1238 |
+
"eval_steps_per_second": 11.629,
|
| 1239 |
"step": 1626
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
"epoch": 8.02,
|
| 1243 |
+
"grad_norm": 2.213076114654541,
|
| 1244 |
+
"learning_rate": 0.0009926108374384236,
|
| 1245 |
+
"loss": 0.3732,
|
| 1246 |
"step": 1630
|
| 1247 |
},
|
| 1248 |
{
|
| 1249 |
"epoch": 8.07,
|
| 1250 |
+
"grad_norm": 1.5906304121017456,
|
| 1251 |
+
"learning_rate": 0.0009679802955665025,
|
| 1252 |
+
"loss": 0.4375,
|
| 1253 |
"step": 1640
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
"epoch": 8.12,
|
| 1257 |
+
"grad_norm": 1.559348464012146,
|
| 1258 |
+
"learning_rate": 0.0009433497536945814,
|
| 1259 |
+
"loss": 0.4711,
|
| 1260 |
"step": 1650
|
| 1261 |
},
|
| 1262 |
{
|
| 1263 |
"epoch": 8.17,
|
| 1264 |
+
"grad_norm": 1.3519264459609985,
|
| 1265 |
+
"learning_rate": 0.00091871921182266,
|
| 1266 |
+
"loss": 0.4236,
|
| 1267 |
"step": 1660
|
| 1268 |
},
|
| 1269 |
{
|
| 1270 |
"epoch": 8.22,
|
| 1271 |
+
"grad_norm": 1.181723952293396,
|
| 1272 |
+
"learning_rate": 0.0008940886699507389,
|
| 1273 |
+
"loss": 0.3528,
|
| 1274 |
"step": 1670
|
| 1275 |
},
|
| 1276 |
{
|
| 1277 |
"epoch": 8.27,
|
| 1278 |
+
"grad_norm": 1.1211256980895996,
|
| 1279 |
+
"learning_rate": 0.0008694581280788178,
|
| 1280 |
+
"loss": 0.4419,
|
| 1281 |
"step": 1680
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 8.31,
|
| 1285 |
+
"grad_norm": 1.1640053987503052,
|
| 1286 |
+
"learning_rate": 0.0008448275862068966,
|
| 1287 |
+
"loss": 0.3888,
|
| 1288 |
"step": 1690
|
| 1289 |
},
|
| 1290 |
{
|
| 1291 |
"epoch": 8.36,
|
| 1292 |
+
"grad_norm": 2.279167652130127,
|
| 1293 |
+
"learning_rate": 0.0008201970443349754,
|
| 1294 |
+
"loss": 0.4163,
|
| 1295 |
"step": 1700
|
| 1296 |
},
|
| 1297 |
{
|
| 1298 |
"epoch": 8.41,
|
| 1299 |
+
"grad_norm": 1.6173532009124756,
|
| 1300 |
+
"learning_rate": 0.0007955665024630542,
|
| 1301 |
+
"loss": 0.4028,
|
| 1302 |
"step": 1710
|
| 1303 |
},
|
| 1304 |
{
|
| 1305 |
"epoch": 8.46,
|
| 1306 |
+
"grad_norm": 2.8598406314849854,
|
| 1307 |
+
"learning_rate": 0.000770935960591133,
|
| 1308 |
+
"loss": 0.4218,
|
| 1309 |
"step": 1720
|
| 1310 |
},
|
| 1311 |
{
|
| 1312 |
"epoch": 8.51,
|
| 1313 |
+
"grad_norm": 1.727655053138733,
|
| 1314 |
+
"learning_rate": 0.0007463054187192118,
|
| 1315 |
+
"loss": 0.4014,
|
| 1316 |
"step": 1730
|
| 1317 |
},
|
| 1318 |
{
|
| 1319 |
"epoch": 8.56,
|
| 1320 |
+
"grad_norm": 6.330834865570068,
|
| 1321 |
+
"learning_rate": 0.0007216748768472907,
|
| 1322 |
+
"loss": 0.3819,
|
| 1323 |
"step": 1740
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
"epoch": 8.61,
|
| 1327 |
+
"grad_norm": 2.008993625640869,
|
| 1328 |
+
"learning_rate": 0.0006970443349753696,
|
| 1329 |
+
"loss": 0.4146,
|
| 1330 |
"step": 1750
|
| 1331 |
},
|
| 1332 |
{
|
| 1333 |
"epoch": 8.66,
|
| 1334 |
+
"grad_norm": 1.3601949214935303,
|
| 1335 |
+
"learning_rate": 0.0006724137931034482,
|
| 1336 |
+
"loss": 0.4091,
|
| 1337 |
"step": 1760
|
| 1338 |
},
|
| 1339 |
{
|
| 1340 |
"epoch": 8.71,
|
| 1341 |
+
"grad_norm": 1.5751508474349976,
|
| 1342 |
+
"learning_rate": 0.0006477832512315271,
|
| 1343 |
+
"loss": 0.4721,
|
| 1344 |
"step": 1770
|
| 1345 |
},
|
| 1346 |
{
|
| 1347 |
"epoch": 8.76,
|
| 1348 |
+
"grad_norm": 2.352508544921875,
|
| 1349 |
+
"learning_rate": 0.000623152709359606,
|
| 1350 |
+
"loss": 0.4087,
|
| 1351 |
"step": 1780
|
| 1352 |
},
|
| 1353 |
{
|
| 1354 |
"epoch": 8.81,
|
| 1355 |
+
"grad_norm": 1.4975714683532715,
|
| 1356 |
+
"learning_rate": 0.0005985221674876847,
|
| 1357 |
+
"loss": 0.3899,
|
| 1358 |
"step": 1790
|
| 1359 |
},
|
| 1360 |
{
|
| 1361 |
"epoch": 8.86,
|
| 1362 |
+
"grad_norm": 1.4178757667541504,
|
| 1363 |
+
"learning_rate": 0.0005738916256157636,
|
| 1364 |
+
"loss": 0.3813,
|
| 1365 |
"step": 1800
|
| 1366 |
},
|
| 1367 |
{
|
| 1368 |
"epoch": 8.91,
|
| 1369 |
+
"grad_norm": 2.137474536895752,
|
| 1370 |
+
"learning_rate": 0.0005492610837438424,
|
| 1371 |
+
"loss": 0.4743,
|
| 1372 |
"step": 1810
|
| 1373 |
},
|
| 1374 |
{
|
| 1375 |
"epoch": 8.95,
|
| 1376 |
+
"grad_norm": 0.9968273639678955,
|
| 1377 |
+
"learning_rate": 0.0005246305418719212,
|
| 1378 |
+
"loss": 0.3729,
|
| 1379 |
"step": 1820
|
| 1380 |
},
|
| 1381 |
{
|
| 1382 |
"epoch": 9.0,
|
| 1383 |
+
"eval_accuracy": 0.975752508361204,
|
| 1384 |
+
"eval_f1": 0.9761552417357652,
|
| 1385 |
+
"eval_loss": 0.090341717004776,
|
| 1386 |
+
"eval_precision": 0.9777538442850773,
|
| 1387 |
+
"eval_recall": 0.9753874426406991,
|
| 1388 |
+
"eval_runtime": 12.9146,
|
| 1389 |
+
"eval_samples_per_second": 185.217,
|
| 1390 |
+
"eval_steps_per_second": 11.615,
|
| 1391 |
"step": 1829
|
| 1392 |
},
|
| 1393 |
{
|
| 1394 |
"epoch": 9.0,
|
| 1395 |
+
"grad_norm": 1.4125550985336304,
|
| 1396 |
+
"learning_rate": 0.0005,
|
| 1397 |
+
"loss": 0.4285,
|
| 1398 |
"step": 1830
|
| 1399 |
},
|
| 1400 |
{
|
| 1401 |
"epoch": 9.05,
|
| 1402 |
+
"grad_norm": 1.411934494972229,
|
| 1403 |
+
"learning_rate": 0.00047536945812807883,
|
| 1404 |
+
"loss": 0.4119,
|
| 1405 |
"step": 1840
|
| 1406 |
},
|
| 1407 |
{
|
| 1408 |
"epoch": 9.1,
|
| 1409 |
+
"grad_norm": 1.0983872413635254,
|
| 1410 |
+
"learning_rate": 0.00045073891625615765,
|
| 1411 |
+
"loss": 0.4449,
|
| 1412 |
"step": 1850
|
| 1413 |
},
|
| 1414 |
{
|
| 1415 |
"epoch": 9.15,
|
| 1416 |
+
"grad_norm": 1.1691962480545044,
|
| 1417 |
+
"learning_rate": 0.0004261083743842364,
|
| 1418 |
+
"loss": 0.4178,
|
| 1419 |
"step": 1860
|
| 1420 |
},
|
| 1421 |
{
|
| 1422 |
"epoch": 9.2,
|
| 1423 |
+
"grad_norm": 1.168599247932434,
|
| 1424 |
+
"learning_rate": 0.0004014778325123153,
|
| 1425 |
+
"loss": 0.356,
|
| 1426 |
"step": 1870
|
| 1427 |
},
|
| 1428 |
{
|
| 1429 |
"epoch": 9.25,
|
| 1430 |
+
"grad_norm": 2.360109329223633,
|
| 1431 |
+
"learning_rate": 0.00037684729064039405,
|
| 1432 |
+
"loss": 0.3666,
|
| 1433 |
"step": 1880
|
| 1434 |
},
|
| 1435 |
{
|
| 1436 |
"epoch": 9.3,
|
| 1437 |
+
"grad_norm": 1.499463438987732,
|
| 1438 |
+
"learning_rate": 0.00035221674876847293,
|
| 1439 |
+
"loss": 0.3928,
|
| 1440 |
"step": 1890
|
| 1441 |
},
|
| 1442 |
{
|
| 1443 |
"epoch": 9.35,
|
| 1444 |
+
"grad_norm": 1.5823447704315186,
|
| 1445 |
+
"learning_rate": 0.00032758620689655175,
|
| 1446 |
+
"loss": 0.3461,
|
| 1447 |
"step": 1900
|
| 1448 |
},
|
| 1449 |
{
|
| 1450 |
"epoch": 9.4,
|
| 1451 |
+
"grad_norm": 1.3279311656951904,
|
| 1452 |
+
"learning_rate": 0.0003029556650246305,
|
| 1453 |
+
"loss": 0.4023,
|
| 1454 |
"step": 1910
|
| 1455 |
},
|
| 1456 |
{
|
| 1457 |
"epoch": 9.45,
|
| 1458 |
+
"grad_norm": 1.4666024446487427,
|
| 1459 |
+
"learning_rate": 0.00027832512315270933,
|
| 1460 |
+
"loss": 0.3929,
|
| 1461 |
"step": 1920
|
| 1462 |
},
|
| 1463 |
{
|
| 1464 |
"epoch": 9.5,
|
| 1465 |
+
"grad_norm": 1.5968170166015625,
|
| 1466 |
+
"learning_rate": 0.0002536945812807882,
|
| 1467 |
+
"loss": 0.3738,
|
| 1468 |
"step": 1930
|
| 1469 |
},
|
| 1470 |
{
|
| 1471 |
"epoch": 9.54,
|
| 1472 |
+
"grad_norm": 0.8691931962966919,
|
| 1473 |
+
"learning_rate": 0.000229064039408867,
|
| 1474 |
+
"loss": 0.3323,
|
| 1475 |
"step": 1940
|
| 1476 |
},
|
| 1477 |
{
|
| 1478 |
"epoch": 9.59,
|
| 1479 |
+
"grad_norm": 1.582350254058838,
|
| 1480 |
+
"learning_rate": 0.00020443349753694582,
|
| 1481 |
+
"loss": 0.327,
|
| 1482 |
"step": 1950
|
| 1483 |
},
|
| 1484 |
{
|
| 1485 |
"epoch": 9.64,
|
| 1486 |
+
"grad_norm": 1.616529107093811,
|
| 1487 |
+
"learning_rate": 0.00017980295566502464,
|
| 1488 |
+
"loss": 0.3701,
|
| 1489 |
"step": 1960
|
| 1490 |
},
|
| 1491 |
{
|
| 1492 |
"epoch": 9.69,
|
| 1493 |
+
"grad_norm": 2.23984432220459,
|
| 1494 |
+
"learning_rate": 0.00015517241379310346,
|
| 1495 |
+
"loss": 0.3796,
|
| 1496 |
"step": 1970
|
| 1497 |
},
|
| 1498 |
{
|
| 1499 |
"epoch": 9.74,
|
| 1500 |
+
"grad_norm": 1.5370508432388306,
|
| 1501 |
+
"learning_rate": 0.00013054187192118225,
|
| 1502 |
+
"loss": 0.405,
|
| 1503 |
"step": 1980
|
| 1504 |
},
|
| 1505 |
{
|
| 1506 |
"epoch": 9.79,
|
| 1507 |
+
"grad_norm": 2.253962755203247,
|
| 1508 |
+
"learning_rate": 0.0001059113300492611,
|
| 1509 |
+
"loss": 0.3793,
|
| 1510 |
"step": 1990
|
| 1511 |
},
|
| 1512 |
{
|
| 1513 |
"epoch": 9.84,
|
| 1514 |
+
"grad_norm": 1.1481009721755981,
|
| 1515 |
+
"learning_rate": 8.12807881773399e-05,
|
| 1516 |
+
"loss": 0.3496,
|
| 1517 |
"step": 2000
|
| 1518 |
},
|
| 1519 |
{
|
| 1520 |
"epoch": 9.89,
|
| 1521 |
+
"grad_norm": 0.9593034982681274,
|
| 1522 |
+
"learning_rate": 5.6650246305418716e-05,
|
| 1523 |
+
"loss": 0.3418,
|
| 1524 |
"step": 2010
|
| 1525 |
},
|
| 1526 |
{
|
| 1527 |
"epoch": 9.94,
|
| 1528 |
+
"grad_norm": 1.4056353569030762,
|
| 1529 |
+
"learning_rate": 3.2019704433497536e-05,
|
| 1530 |
+
"loss": 0.3796,
|
| 1531 |
"step": 2020
|
| 1532 |
},
|
| 1533 |
{
|
| 1534 |
"epoch": 9.99,
|
| 1535 |
+
"grad_norm": 1.489027500152588,
|
| 1536 |
+
"learning_rate": 7.3891625615763555e-06,
|
| 1537 |
+
"loss": 0.3705,
|
| 1538 |
"step": 2030
|
| 1539 |
},
|
| 1540 |
{
|
| 1541 |
"epoch": 9.99,
|
| 1542 |
+
"eval_accuracy": 0.9807692307692307,
|
| 1543 |
+
"eval_f1": 0.9825245324491525,
|
| 1544 |
+
"eval_loss": 0.07319223880767822,
|
| 1545 |
+
"eval_precision": 0.9829956117956687,
|
| 1546 |
+
"eval_recall": 0.9825747689517654,
|
| 1547 |
+
"eval_runtime": 12.8452,
|
| 1548 |
+
"eval_samples_per_second": 186.217,
|
| 1549 |
+
"eval_steps_per_second": 11.677,
|
| 1550 |
"step": 2030
|
| 1551 |
},
|
| 1552 |
{
|
| 1553 |
"epoch": 9.99,
|
| 1554 |
"step": 2030,
|
| 1555 |
"total_flos": 1.0133154899356189e+19,
|
| 1556 |
+
"train_loss": 0.5615053875692959,
|
| 1557 |
+
"train_runtime": 1549.2005,
|
| 1558 |
+
"train_samples_per_second": 83.914,
|
| 1559 |
+
"train_steps_per_second": 1.31
|
| 1560 |
}
|
| 1561 |
],
|
| 1562 |
"logging_steps": 10,
|