🍻 cheers
Browse files- README.md +4 -3
- all_results.json +11 -11
- eval_results.json +6 -6
- train_results.json +6 -6
- trainer_state.json +472 -2380
README.md
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: microsoft/swin-tiny-patch4-window7-224
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
|
@@ -15,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# swin-tiny-patch4-window7-224-finetuned_ASL_Isolated_Swin_dataset2
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
-
- Accuracy: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: microsoft/swin-tiny-patch4-window7-224
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
|
|
|
| 16 |
|
| 17 |
# swin-tiny-patch4-window7-224-finetuned_ASL_Isolated_Swin_dataset2
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the ASL_Isolated_Swin_dataset dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0558
|
| 22 |
+
- Accuracy: 0.9846
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 16.
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 4.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9846153846153847,
|
| 4 |
+
"eval_loss": 0.05584708973765373,
|
| 5 |
+
"eval_runtime": 2.0579,
|
| 6 |
+
"eval_samples_per_second": 126.342,
|
| 7 |
+
"eval_steps_per_second": 16.036,
|
| 8 |
+
"total_flos": 7.30261234607063e+17,
|
| 9 |
+
"train_loss": 0.5342570722103119,
|
| 10 |
+
"train_runtime": 409.3983,
|
| 11 |
+
"train_samples_per_second": 71.715,
|
| 12 |
+
"train_steps_per_second": 4.494
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 16.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9846153846153847,
|
| 4 |
+
"eval_loss": 0.05584708973765373,
|
| 5 |
+
"eval_runtime": 2.0579,
|
| 6 |
+
"eval_samples_per_second": 126.342,
|
| 7 |
+
"eval_steps_per_second": 16.036
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 4.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"total_flos": 7.30261234607063e+17,
|
| 4 |
+
"train_loss": 0.5342570722103119,
|
| 5 |
+
"train_runtime": 409.3983,
|
| 6 |
+
"train_samples_per_second": 71.715,
|
| 7 |
+
"train_steps_per_second": 4.494
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,3202 +1,1294 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned_ASL_Isolated_Swin_dataset2/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.11,
|
| 13 |
-
"learning_rate": 0.
|
| 14 |
-
"loss": 3.
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.22,
|
| 19 |
-
"learning_rate": 0.
|
| 20 |
-
"loss": 3.
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.33,
|
| 25 |
-
"learning_rate": 0.
|
| 26 |
-
"loss": 3.
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.43,
|
| 31 |
-
"learning_rate": 0.
|
| 32 |
-
"loss": 2.
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.54,
|
| 37 |
-
"learning_rate": 0.
|
| 38 |
-
"loss": 2.
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.65,
|
| 43 |
-
"learning_rate": 0.
|
| 44 |
-
"loss": 2.
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.76,
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss":
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.87,
|
| 55 |
-
"learning_rate": 0.
|
| 56 |
-
"loss": 1.
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.98,
|
| 61 |
-
"learning_rate": 0.
|
| 62 |
-
"loss": 1.
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 1.09,
|
| 67 |
-
"learning_rate": 0.
|
| 68 |
-
"loss": 1.
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 1.09,
|
| 73 |
-
"eval_accuracy": 0.
|
| 74 |
-
"eval_loss": 1.
|
| 75 |
-
"eval_runtime":
|
| 76 |
-
"eval_samples_per_second":
|
| 77 |
-
"eval_steps_per_second":
|
| 78 |
"step": 100
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 1.2,
|
| 82 |
-
"learning_rate": 0.
|
| 83 |
-
"loss": 1.
|
| 84 |
"step": 110
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 1.3,
|
| 88 |
-
"learning_rate": 0.
|
| 89 |
-
"loss": 1.
|
| 90 |
"step": 120
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 1.41,
|
| 94 |
-
"learning_rate": 0.
|
| 95 |
-
"loss": 1.
|
| 96 |
"step": 130
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 1.52,
|
| 100 |
-
"learning_rate": 0.
|
| 101 |
-
"loss": 1.
|
| 102 |
"step": 140
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 1.63,
|
| 106 |
-
"learning_rate": 0.
|
| 107 |
-
"loss":
|
| 108 |
"step": 150
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 1.74,
|
| 112 |
-
"learning_rate": 0.
|
| 113 |
-
"loss": 1.
|
| 114 |
"step": 160
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 1.85,
|
| 118 |
-
"learning_rate": 0.
|
| 119 |
-
"loss":
|
| 120 |
"step": 170
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 1.96,
|
| 124 |
-
"learning_rate": 0.
|
| 125 |
-
"loss": 1.
|
| 126 |
"step": 180
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 2.07,
|
| 130 |
-
"learning_rate": 0.
|
| 131 |
-
"loss": 1.
|
| 132 |
"step": 190
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 2.17,
|
| 136 |
-
"learning_rate": 0.
|
| 137 |
-
"loss": 1.
|
| 138 |
"step": 200
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 2.17,
|
| 142 |
-
"eval_accuracy": 0.
|
| 143 |
-
"eval_loss": 0.
|
| 144 |
-
"eval_runtime":
|
| 145 |
-
"eval_samples_per_second":
|
| 146 |
-
"eval_steps_per_second":
|
| 147 |
"step": 200
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 2.28,
|
| 151 |
-
"learning_rate": 0.
|
| 152 |
-
"loss": 0.
|
| 153 |
"step": 210
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 2.39,
|
| 157 |
-
"learning_rate": 0.
|
| 158 |
-
"loss":
|
| 159 |
"step": 220
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 2.5,
|
| 163 |
-
"learning_rate": 0.
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 230
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 2.61,
|
| 169 |
-
"learning_rate": 0.
|
| 170 |
-
"loss":
|
| 171 |
"step": 240
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 2.72,
|
| 175 |
-
"learning_rate": 0.
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 250
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 2.83,
|
| 181 |
-
"learning_rate": 0.
|
| 182 |
-
"loss": 0.
|
| 183 |
"step": 260
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 2.93,
|
| 187 |
-
"learning_rate": 0.
|
| 188 |
-
"loss": 0.
|
| 189 |
"step": 270
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 3.04,
|
| 193 |
-
"learning_rate": 0.
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 280
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 3.15,
|
| 199 |
-
"learning_rate": 0.
|
| 200 |
-
"loss": 0.
|
| 201 |
"step": 290
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 3.26,
|
| 205 |
-
"learning_rate": 0.
|
| 206 |
-
"loss": 0.
|
| 207 |
"step": 300
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 3.26,
|
| 211 |
-
"eval_accuracy": 0.
|
| 212 |
-
"eval_loss": 0.
|
| 213 |
-
"eval_runtime": 2.
|
| 214 |
-
"eval_samples_per_second":
|
| 215 |
-
"eval_steps_per_second":
|
| 216 |
"step": 300
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 3.37,
|
| 220 |
-
"learning_rate": 0.
|
| 221 |
-
"loss": 0.
|
| 222 |
"step": 310
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 3.48,
|
| 226 |
-
"learning_rate": 0.
|
| 227 |
-
"loss": 0.
|
| 228 |
"step": 320
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 3.59,
|
| 232 |
-
"learning_rate": 0.
|
| 233 |
-
"loss": 0.
|
| 234 |
"step": 330
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 3.7,
|
| 238 |
-
"learning_rate": 0.
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 340
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 3.8,
|
| 244 |
-
"learning_rate": 0.
|
| 245 |
-
"loss": 0.
|
| 246 |
"step": 350
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 3.91,
|
| 250 |
-
"learning_rate": 0.
|
| 251 |
-
"loss": 0.
|
| 252 |
"step": 360
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 4.02,
|
| 256 |
-
"learning_rate": 0.
|
| 257 |
-
"loss": 0.
|
| 258 |
"step": 370
|
| 259 |
},
|
| 260 |
{
|
| 261 |
"epoch": 4.13,
|
| 262 |
-
"learning_rate": 0.
|
| 263 |
-
"loss": 0.
|
| 264 |
"step": 380
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 4.24,
|
| 268 |
-
"learning_rate": 0.
|
| 269 |
-
"loss": 0.
|
| 270 |
"step": 390
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 4.35,
|
| 274 |
-
"learning_rate": 0.
|
| 275 |
-
"loss": 0.
|
| 276 |
"step": 400
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 4.35,
|
| 280 |
-
"eval_accuracy": 0.
|
| 281 |
-
"eval_loss": 0.
|
| 282 |
-
"eval_runtime":
|
| 283 |
-
"eval_samples_per_second":
|
| 284 |
-
"eval_steps_per_second":
|
| 285 |
"step": 400
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 4.46,
|
| 289 |
-
"learning_rate": 0.
|
| 290 |
-
"loss": 0.
|
| 291 |
"step": 410
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 4.57,
|
| 295 |
-
"learning_rate": 0.
|
| 296 |
-
"loss": 0.
|
| 297 |
"step": 420
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 4.67,
|
| 301 |
-
"learning_rate": 0.
|
| 302 |
-
"loss": 0.
|
| 303 |
"step": 430
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 4.78,
|
| 307 |
-
"learning_rate": 0.
|
| 308 |
-
"loss": 0.
|
| 309 |
"step": 440
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 4.89,
|
| 313 |
-
"learning_rate": 0.
|
| 314 |
-
"loss": 0.
|
| 315 |
"step": 450
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 5.0,
|
| 319 |
-
"learning_rate": 0.
|
| 320 |
-
"loss": 0.
|
| 321 |
"step": 460
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 5.11,
|
| 325 |
-
"learning_rate": 0.
|
| 326 |
-
"loss": 0.
|
| 327 |
"step": 470
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 5.22,
|
| 331 |
-
"learning_rate": 0.
|
| 332 |
-
"loss": 0.
|
| 333 |
"step": 480
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 5.33,
|
| 337 |
-
"learning_rate": 0.
|
| 338 |
-
"loss": 0.
|
| 339 |
"step": 490
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 5.43,
|
| 343 |
-
"learning_rate": 0.
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 500
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 5.43,
|
| 349 |
-
"eval_accuracy": 0.
|
| 350 |
-
"eval_loss": 0.
|
| 351 |
-
"eval_runtime": 1.
|
| 352 |
-
"eval_samples_per_second":
|
| 353 |
-
"eval_steps_per_second":
|
| 354 |
"step": 500
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 5.54,
|
| 358 |
-
"learning_rate": 0.
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 510
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 5.65,
|
| 364 |
-
"learning_rate": 0.
|
| 365 |
-
"loss": 0.
|
| 366 |
"step": 520
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 5.76,
|
| 370 |
-
"learning_rate": 0.
|
| 371 |
-
"loss": 0.
|
| 372 |
"step": 530
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 5.87,
|
| 376 |
-
"learning_rate": 0.
|
| 377 |
-
"loss": 0.
|
| 378 |
"step": 540
|
| 379 |
},
|
| 380 |
{
|
| 381 |
"epoch": 5.98,
|
| 382 |
-
"learning_rate": 0.
|
| 383 |
-
"loss": 0.
|
| 384 |
"step": 550
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 6.09,
|
| 388 |
-
"learning_rate": 0.
|
| 389 |
-
"loss": 0.
|
| 390 |
"step": 560
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 6.2,
|
| 394 |
-
"learning_rate": 0.
|
| 395 |
-
"loss": 0.
|
| 396 |
"step": 570
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 6.3,
|
| 400 |
-
"learning_rate": 0.
|
| 401 |
-
"loss": 0.
|
| 402 |
"step": 580
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 6.41,
|
| 406 |
-
"learning_rate": 0.
|
| 407 |
-
"loss": 0.
|
| 408 |
"step": 590
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 6.52,
|
| 412 |
-
"learning_rate": 0.
|
| 413 |
-
"loss": 0.
|
| 414 |
"step": 600
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 6.52,
|
| 418 |
-
"eval_accuracy": 0.
|
| 419 |
-
"eval_loss": 0.
|
| 420 |
-
"eval_runtime":
|
| 421 |
-
"eval_samples_per_second":
|
| 422 |
-
"eval_steps_per_second":
|
| 423 |
"step": 600
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 6.63,
|
| 427 |
-
"learning_rate": 0.
|
| 428 |
-
"loss": 0.
|
| 429 |
"step": 610
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 6.74,
|
| 433 |
-
"learning_rate": 0.
|
| 434 |
-
"loss": 0.
|
| 435 |
"step": 620
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 6.85,
|
| 439 |
-
"learning_rate": 0.
|
| 440 |
-
"loss": 0.
|
| 441 |
"step": 630
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 6.96,
|
| 445 |
-
"learning_rate": 0.
|
| 446 |
-
"loss": 0.
|
| 447 |
"step": 640
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 7.07,
|
| 451 |
-
"learning_rate": 0.
|
| 452 |
-
"loss": 0.
|
| 453 |
"step": 650
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 7.17,
|
| 457 |
-
"learning_rate": 0.
|
| 458 |
-
"loss": 0.
|
| 459 |
"step": 660
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 7.28,
|
| 463 |
-
"learning_rate": 0.
|
| 464 |
-
"loss": 0.
|
| 465 |
"step": 670
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 7.39,
|
| 469 |
-
"learning_rate": 0.
|
| 470 |
-
"loss": 0.
|
| 471 |
"step": 680
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 7.5,
|
| 475 |
-
"learning_rate": 0.
|
| 476 |
-
"loss": 0.
|
| 477 |
"step": 690
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 7.61,
|
| 481 |
-
"learning_rate": 0.
|
| 482 |
-
"loss": 0.
|
| 483 |
"step": 700
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 7.61,
|
| 487 |
-
"eval_accuracy": 0.
|
| 488 |
-
"eval_loss": 0.
|
| 489 |
-
"eval_runtime": 1.
|
| 490 |
-
"eval_samples_per_second": 140.
|
| 491 |
-
"eval_steps_per_second": 17.
|
| 492 |
"step": 700
|
| 493 |
},
|
| 494 |
{
|
| 495 |
"epoch": 7.72,
|
| 496 |
-
"learning_rate": 0.
|
| 497 |
-
"loss": 0.
|
| 498 |
"step": 710
|
| 499 |
},
|
| 500 |
{
|
| 501 |
"epoch": 7.83,
|
| 502 |
-
"learning_rate": 0.
|
| 503 |
-
"loss": 0.
|
| 504 |
"step": 720
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 7.93,
|
| 508 |
-
"learning_rate": 0.
|
| 509 |
-
"loss": 0.
|
| 510 |
"step": 730
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 8.04,
|
| 514 |
-
"learning_rate": 0.
|
| 515 |
-
"loss": 0.
|
| 516 |
"step": 740
|
| 517 |
},
|
| 518 |
{
|
| 519 |
"epoch": 8.15,
|
| 520 |
-
"learning_rate": 0.
|
| 521 |
-
"loss": 0.
|
| 522 |
"step": 750
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 8.26,
|
| 526 |
-
"learning_rate": 0.
|
| 527 |
-
"loss": 0.
|
| 528 |
"step": 760
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 8.37,
|
| 532 |
-
"learning_rate": 0.
|
| 533 |
-
"loss": 0.
|
| 534 |
"step": 770
|
| 535 |
},
|
| 536 |
{
|
| 537 |
"epoch": 8.48,
|
| 538 |
-
"learning_rate": 0.
|
| 539 |
-
"loss": 0.
|
| 540 |
"step": 780
|
| 541 |
},
|
| 542 |
{
|
| 543 |
"epoch": 8.59,
|
| 544 |
-
"learning_rate": 0.
|
| 545 |
-
"loss": 0.
|
| 546 |
"step": 790
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 8.7,
|
| 550 |
-
"learning_rate": 0.
|
| 551 |
-
"loss": 0.
|
| 552 |
"step": 800
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"epoch": 8.7,
|
| 556 |
-
"eval_accuracy": 0.
|
| 557 |
-
"eval_loss": 0.
|
| 558 |
-
"eval_runtime": 1.
|
| 559 |
-
"eval_samples_per_second":
|
| 560 |
-
"eval_steps_per_second": 17.
|
| 561 |
"step": 800
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 8.8,
|
| 565 |
-
"learning_rate": 0.
|
| 566 |
-
"loss": 0.
|
| 567 |
"step": 810
|
| 568 |
},
|
| 569 |
{
|
| 570 |
"epoch": 8.91,
|
| 571 |
-
"learning_rate": 0.
|
| 572 |
-
"loss": 0.
|
| 573 |
"step": 820
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 9.02,
|
| 577 |
-
"learning_rate": 0.
|
| 578 |
-
"loss": 0.
|
| 579 |
"step": 830
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 9.13,
|
| 583 |
-
"learning_rate": 0.
|
| 584 |
-
"loss": 0.
|
| 585 |
"step": 840
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 9.24,
|
| 589 |
-
"learning_rate": 0.
|
| 590 |
-
"loss": 0.
|
| 591 |
"step": 850
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 9.35,
|
| 595 |
-
"learning_rate": 0.
|
| 596 |
-
"loss": 0.
|
| 597 |
"step": 860
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 9.46,
|
| 601 |
-
"learning_rate": 0.
|
| 602 |
-
"loss": 0.
|
| 603 |
"step": 870
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 9.57,
|
| 607 |
-
"learning_rate": 0.
|
| 608 |
-
"loss": 0.
|
| 609 |
"step": 880
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 9.67,
|
| 613 |
-
"learning_rate": 0.
|
| 614 |
-
"loss": 0.
|
| 615 |
"step": 890
|
| 616 |
},
|
| 617 |
{
|
| 618 |
"epoch": 9.78,
|
| 619 |
-
"learning_rate": 0.
|
| 620 |
-
"loss": 0.
|
| 621 |
"step": 900
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 9.78,
|
| 625 |
-
"eval_accuracy": 0.
|
| 626 |
-
"eval_loss": 0.
|
| 627 |
-
"eval_runtime":
|
| 628 |
-
"eval_samples_per_second":
|
| 629 |
-
"eval_steps_per_second":
|
| 630 |
"step": 900
|
| 631 |
},
|
| 632 |
{
|
| 633 |
"epoch": 9.89,
|
| 634 |
-
"learning_rate": 0.
|
| 635 |
-
"loss": 0.
|
| 636 |
"step": 910
|
| 637 |
},
|
| 638 |
{
|
| 639 |
"epoch": 10.0,
|
| 640 |
-
"learning_rate": 0.
|
| 641 |
-
"loss": 0.
|
| 642 |
"step": 920
|
| 643 |
},
|
| 644 |
{
|
| 645 |
"epoch": 10.11,
|
| 646 |
-
"learning_rate":
|
| 647 |
-
"loss": 0.
|
| 648 |
"step": 930
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 10.22,
|
| 652 |
-
"learning_rate":
|
| 653 |
-
"loss": 0.
|
| 654 |
"step": 940
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 10.33,
|
| 658 |
-
"learning_rate":
|
| 659 |
-
"loss": 0.
|
| 660 |
"step": 950
|
| 661 |
},
|
| 662 |
{
|
| 663 |
"epoch": 10.43,
|
| 664 |
-
"learning_rate":
|
| 665 |
-
"loss": 0.
|
| 666 |
"step": 960
|
| 667 |
},
|
| 668 |
{
|
| 669 |
"epoch": 10.54,
|
| 670 |
-
"learning_rate":
|
| 671 |
-
"loss": 0.
|
| 672 |
"step": 970
|
| 673 |
},
|
| 674 |
{
|
| 675 |
"epoch": 10.65,
|
| 676 |
-
"learning_rate":
|
| 677 |
-
"loss": 0.
|
| 678 |
"step": 980
|
| 679 |
},
|
| 680 |
{
|
| 681 |
"epoch": 10.76,
|
| 682 |
-
"learning_rate":
|
| 683 |
-
"loss": 0.
|
| 684 |
"step": 990
|
| 685 |
},
|
| 686 |
{
|
| 687 |
"epoch": 10.87,
|
| 688 |
-
"learning_rate":
|
| 689 |
-
"loss": 0.
|
| 690 |
"step": 1000
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 10.87,
|
| 694 |
-
"eval_accuracy": 0.
|
| 695 |
-
"eval_loss": 0.
|
| 696 |
-
"eval_runtime":
|
| 697 |
-
"eval_samples_per_second":
|
| 698 |
-
"eval_steps_per_second":
|
| 699 |
"step": 1000
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 10.98,
|
| 703 |
-
"learning_rate":
|
| 704 |
-
"loss": 0.
|
| 705 |
"step": 1010
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 11.09,
|
| 709 |
-
"learning_rate":
|
| 710 |
-
"loss": 0.
|
| 711 |
"step": 1020
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 11.2,
|
| 715 |
-
"learning_rate":
|
| 716 |
-
"loss": 0.
|
| 717 |
"step": 1030
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 11.3,
|
| 721 |
-
"learning_rate":
|
| 722 |
-
"loss": 0.
|
| 723 |
"step": 1040
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 11.41,
|
| 727 |
-
"learning_rate":
|
| 728 |
-
"loss": 0.
|
| 729 |
"step": 1050
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 11.52,
|
| 733 |
-
"learning_rate":
|
| 734 |
-
"loss": 0.
|
| 735 |
"step": 1060
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 11.63,
|
| 739 |
-
"learning_rate":
|
| 740 |
-
"loss": 0.
|
| 741 |
"step": 1070
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 11.74,
|
| 745 |
-
"learning_rate":
|
| 746 |
-
"loss": 0.
|
| 747 |
"step": 1080
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 11.85,
|
| 751 |
-
"learning_rate":
|
| 752 |
-
"loss": 0.
|
| 753 |
"step": 1090
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 11.96,
|
| 757 |
-
"learning_rate":
|
| 758 |
-
"loss": 0.
|
| 759 |
"step": 1100
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 11.96,
|
| 763 |
-
"eval_accuracy": 0.
|
| 764 |
-
"eval_loss": 0.
|
| 765 |
-
"eval_runtime":
|
| 766 |
-
"eval_samples_per_second":
|
| 767 |
-
"eval_steps_per_second":
|
| 768 |
"step": 1100
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 12.07,
|
| 772 |
-
"learning_rate":
|
| 773 |
-
"loss": 0.
|
| 774 |
"step": 1110
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"epoch": 12.17,
|
| 778 |
-
"learning_rate":
|
| 779 |
-
"loss": 0.
|
| 780 |
"step": 1120
|
| 781 |
},
|
| 782 |
{
|
| 783 |
"epoch": 12.28,
|
| 784 |
-
"learning_rate":
|
| 785 |
-
"loss": 0.
|
| 786 |
"step": 1130
|
| 787 |
},
|
| 788 |
{
|
| 789 |
"epoch": 12.39,
|
| 790 |
-
"learning_rate":
|
| 791 |
-
"loss": 0.
|
| 792 |
"step": 1140
|
| 793 |
},
|
| 794 |
{
|
| 795 |
"epoch": 12.5,
|
| 796 |
-
"learning_rate":
|
| 797 |
-
"loss": 0.
|
| 798 |
"step": 1150
|
| 799 |
},
|
| 800 |
{
|
| 801 |
"epoch": 12.61,
|
| 802 |
-
"learning_rate":
|
| 803 |
-
"loss": 0.
|
| 804 |
"step": 1160
|
| 805 |
},
|
| 806 |
{
|
| 807 |
"epoch": 12.72,
|
| 808 |
-
"learning_rate":
|
| 809 |
-
"loss": 0.
|
| 810 |
"step": 1170
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 12.83,
|
| 814 |
-
"learning_rate":
|
| 815 |
-
"loss": 0.
|
| 816 |
"step": 1180
|
| 817 |
},
|
| 818 |
{
|
| 819 |
"epoch": 12.93,
|
| 820 |
-
"learning_rate":
|
| 821 |
-
"loss": 0.
|
| 822 |
"step": 1190
|
| 823 |
},
|
| 824 |
{
|
| 825 |
"epoch": 13.04,
|
| 826 |
-
"learning_rate":
|
| 827 |
-
"loss": 0.
|
| 828 |
"step": 1200
|
| 829 |
},
|
| 830 |
{
|
| 831 |
"epoch": 13.04,
|
| 832 |
-
"eval_accuracy": 0.
|
| 833 |
-
"eval_loss": 0.
|
| 834 |
-
"eval_runtime":
|
| 835 |
-
"eval_samples_per_second":
|
| 836 |
-
"eval_steps_per_second":
|
| 837 |
"step": 1200
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 13.15,
|
| 841 |
-
"learning_rate":
|
| 842 |
-
"loss": 0.
|
| 843 |
"step": 1210
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 13.26,
|
| 847 |
-
"learning_rate":
|
| 848 |
-
"loss": 0.
|
| 849 |
"step": 1220
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 13.37,
|
| 853 |
-
"learning_rate":
|
| 854 |
-
"loss": 0.
|
| 855 |
"step": 1230
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 13.48,
|
| 859 |
-
"learning_rate":
|
| 860 |
-
"loss": 0.
|
| 861 |
"step": 1240
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 13.59,
|
| 865 |
-
"learning_rate":
|
| 866 |
-
"loss": 0.
|
| 867 |
"step": 1250
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 13.7,
|
| 871 |
-
"learning_rate":
|
| 872 |
-
"loss": 0.
|
| 873 |
"step": 1260
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"epoch": 13.8,
|
| 877 |
-
"learning_rate":
|
| 878 |
-
"loss": 0.
|
| 879 |
"step": 1270
|
| 880 |
},
|
| 881 |
{
|
| 882 |
"epoch": 13.91,
|
| 883 |
-
"learning_rate":
|
| 884 |
-
"loss": 0.
|
| 885 |
"step": 1280
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 14.02,
|
| 889 |
-
"learning_rate":
|
| 890 |
-
"loss": 0.
|
| 891 |
"step": 1290
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"epoch": 14.13,
|
| 895 |
-
"learning_rate":
|
| 896 |
-
"loss": 0.
|
| 897 |
"step": 1300
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 14.13,
|
| 901 |
-
"eval_accuracy": 0.
|
| 902 |
-
"eval_loss": 0.
|
| 903 |
-
"eval_runtime":
|
| 904 |
-
"eval_samples_per_second":
|
| 905 |
-
"eval_steps_per_second":
|
| 906 |
"step": 1300
|
| 907 |
},
|
| 908 |
{
|
| 909 |
"epoch": 14.24,
|
| 910 |
-
"learning_rate":
|
| 911 |
-
"loss": 0.
|
| 912 |
"step": 1310
|
| 913 |
},
|
| 914 |
{
|
| 915 |
"epoch": 14.35,
|
| 916 |
-
"learning_rate":
|
| 917 |
-
"loss": 0.
|
| 918 |
"step": 1320
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"epoch": 14.46,
|
| 922 |
-
"learning_rate":
|
| 923 |
-
"loss": 0.
|
| 924 |
"step": 1330
|
| 925 |
},
|
| 926 |
{
|
| 927 |
"epoch": 14.57,
|
| 928 |
-
"learning_rate":
|
| 929 |
-
"loss": 0.
|
| 930 |
"step": 1340
|
| 931 |
},
|
| 932 |
{
|
| 933 |
"epoch": 14.67,
|
| 934 |
-
"learning_rate":
|
| 935 |
-
"loss": 0.
|
| 936 |
"step": 1350
|
| 937 |
},
|
| 938 |
{
|
| 939 |
"epoch": 14.78,
|
| 940 |
-
"learning_rate":
|
| 941 |
-
"loss": 0.
|
| 942 |
"step": 1360
|
| 943 |
},
|
| 944 |
{
|
| 945 |
"epoch": 14.89,
|
| 946 |
-
"learning_rate":
|
| 947 |
-
"loss": 0.
|
| 948 |
"step": 1370
|
| 949 |
},
|
| 950 |
{
|
| 951 |
"epoch": 15.0,
|
| 952 |
-
"learning_rate":
|
| 953 |
-
"loss": 0.
|
| 954 |
"step": 1380
|
| 955 |
},
|
| 956 |
{
|
| 957 |
"epoch": 15.11,
|
| 958 |
-
"learning_rate":
|
| 959 |
-
"loss": 0.
|
| 960 |
"step": 1390
|
| 961 |
},
|
| 962 |
{
|
| 963 |
"epoch": 15.22,
|
| 964 |
-
"learning_rate":
|
| 965 |
-
"loss": 0.
|
| 966 |
"step": 1400
|
| 967 |
},
|
| 968 |
{
|
| 969 |
"epoch": 15.22,
|
| 970 |
-
"eval_accuracy": 0.
|
| 971 |
-
"eval_loss": 0.
|
| 972 |
-
"eval_runtime":
|
| 973 |
-
"eval_samples_per_second":
|
| 974 |
-
"eval_steps_per_second":
|
| 975 |
"step": 1400
|
| 976 |
},
|
| 977 |
{
|
| 978 |
"epoch": 15.33,
|
| 979 |
-
"learning_rate":
|
| 980 |
-
"loss": 0.
|
| 981 |
"step": 1410
|
| 982 |
},
|
| 983 |
{
|
| 984 |
"epoch": 15.43,
|
| 985 |
-
"learning_rate":
|
| 986 |
-
"loss": 0.
|
| 987 |
"step": 1420
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 15.54,
|
| 991 |
-
"learning_rate":
|
| 992 |
-
"loss": 0.
|
| 993 |
"step": 1430
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"epoch": 15.65,
|
| 997 |
-
"learning_rate":
|
| 998 |
-
"loss": 0.
|
| 999 |
"step": 1440
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 15.76,
|
| 1003 |
-
"learning_rate":
|
| 1004 |
-
"loss": 0.
|
| 1005 |
"step": 1450
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 15.87,
|
| 1009 |
-
"learning_rate":
|
| 1010 |
-
"loss": 0.
|
| 1011 |
"step": 1460
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
"epoch": 15.98,
|
| 1015 |
-
"learning_rate":
|
| 1016 |
-
"loss": 0.
|
| 1017 |
"step": 1470
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
"epoch": 16.09,
|
| 1021 |
-
"learning_rate":
|
| 1022 |
-
"loss": 0.
|
| 1023 |
"step": 1480
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
"epoch": 16.2,
|
| 1027 |
-
"learning_rate":
|
| 1028 |
-
"loss": 0.
|
| 1029 |
"step": 1490
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
"epoch": 16.3,
|
| 1033 |
-
"learning_rate":
|
| 1034 |
-
"loss": 0.
|
| 1035 |
"step": 1500
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
"epoch": 16.3,
|
| 1039 |
-
"eval_accuracy": 0.
|
| 1040 |
-
"eval_loss": 0.
|
| 1041 |
-
"eval_runtime":
|
| 1042 |
-
"eval_samples_per_second":
|
| 1043 |
-
"eval_steps_per_second":
|
| 1044 |
"step": 1500
|
| 1045 |
},
|
| 1046 |
{
|
| 1047 |
"epoch": 16.41,
|
| 1048 |
-
"learning_rate":
|
| 1049 |
-
"loss": 0.
|
| 1050 |
"step": 1510
|
| 1051 |
},
|
| 1052 |
{
|
| 1053 |
"epoch": 16.52,
|
| 1054 |
-
"learning_rate":
|
| 1055 |
-
"loss": 0.
|
| 1056 |
"step": 1520
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
"epoch": 16.63,
|
| 1060 |
-
"learning_rate":
|
| 1061 |
-
"loss": 0.
|
| 1062 |
"step": 1530
|
| 1063 |
},
|
| 1064 |
{
|
| 1065 |
"epoch": 16.74,
|
| 1066 |
-
"learning_rate":
|
| 1067 |
-
"loss": 0.
|
| 1068 |
"step": 1540
|
| 1069 |
},
|
| 1070 |
{
|
| 1071 |
"epoch": 16.85,
|
| 1072 |
-
"learning_rate":
|
| 1073 |
-
"loss": 0.
|
| 1074 |
"step": 1550
|
| 1075 |
},
|
| 1076 |
{
|
| 1077 |
"epoch": 16.96,
|
| 1078 |
-
"learning_rate":
|
| 1079 |
-
"loss": 0.
|
| 1080 |
"step": 1560
|
| 1081 |
},
|
| 1082 |
{
|
| 1083 |
"epoch": 17.07,
|
| 1084 |
-
"learning_rate":
|
| 1085 |
-
"loss": 0.
|
| 1086 |
"step": 1570
|
| 1087 |
},
|
| 1088 |
{
|
| 1089 |
"epoch": 17.17,
|
| 1090 |
-
"learning_rate":
|
| 1091 |
-
"loss": 0.
|
| 1092 |
"step": 1580
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
"epoch": 17.28,
|
| 1096 |
-
"learning_rate":
|
| 1097 |
-
"loss": 0.
|
| 1098 |
"step": 1590
|
| 1099 |
},
|
| 1100 |
{
|
| 1101 |
"epoch": 17.39,
|
| 1102 |
-
"learning_rate":
|
| 1103 |
-
"loss": 0.
|
| 1104 |
"step": 1600
|
| 1105 |
},
|
| 1106 |
{
|
| 1107 |
"epoch": 17.39,
|
| 1108 |
-
"eval_accuracy": 0.
|
| 1109 |
-
"eval_loss": 0.
|
| 1110 |
-
"eval_runtime": 1.
|
| 1111 |
-
"eval_samples_per_second":
|
| 1112 |
-
"eval_steps_per_second":
|
| 1113 |
"step": 1600
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 17.5,
|
| 1117 |
-
"learning_rate":
|
| 1118 |
-
"loss": 0.
|
| 1119 |
"step": 1610
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 17.61,
|
| 1123 |
-
"learning_rate":
|
| 1124 |
-
"loss": 0.
|
| 1125 |
"step": 1620
|
| 1126 |
},
|
| 1127 |
{
|
| 1128 |
"epoch": 17.72,
|
| 1129 |
-
"learning_rate":
|
| 1130 |
-
"loss": 0.
|
| 1131 |
"step": 1630
|
| 1132 |
},
|
| 1133 |
{
|
| 1134 |
"epoch": 17.83,
|
| 1135 |
-
"learning_rate":
|
| 1136 |
-
"loss": 0.
|
| 1137 |
"step": 1640
|
| 1138 |
},
|
| 1139 |
{
|
| 1140 |
"epoch": 17.93,
|
| 1141 |
-
"learning_rate":
|
| 1142 |
-
"loss": 0.
|
| 1143 |
"step": 1650
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 18.04,
|
| 1147 |
-
"learning_rate":
|
| 1148 |
-
"loss": 0.
|
| 1149 |
"step": 1660
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
"epoch": 18.15,
|
| 1153 |
-
"learning_rate":
|
| 1154 |
-
"loss": 0.
|
| 1155 |
"step": 1670
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 18.26,
|
| 1159 |
-
"learning_rate":
|
| 1160 |
-
"loss": 0.
|
| 1161 |
"step": 1680
|
| 1162 |
},
|
| 1163 |
{
|
| 1164 |
"epoch": 18.37,
|
| 1165 |
-
"learning_rate":
|
| 1166 |
-
"loss": 0.
|
| 1167 |
"step": 1690
|
| 1168 |
},
|
| 1169 |
{
|
| 1170 |
"epoch": 18.48,
|
| 1171 |
-
"learning_rate":
|
| 1172 |
-
"loss": 0.
|
| 1173 |
"step": 1700
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
"epoch": 18.48,
|
| 1177 |
-
"eval_accuracy": 0.
|
| 1178 |
-
"eval_loss": 0.
|
| 1179 |
-
"eval_runtime":
|
| 1180 |
-
"eval_samples_per_second":
|
| 1181 |
-
"eval_steps_per_second":
|
| 1182 |
"step": 1700
|
| 1183 |
},
|
| 1184 |
{
|
| 1185 |
"epoch": 18.59,
|
| 1186 |
-
"learning_rate":
|
| 1187 |
-
"loss": 0.
|
| 1188 |
"step": 1710
|
| 1189 |
},
|
| 1190 |
{
|
| 1191 |
"epoch": 18.7,
|
| 1192 |
-
"learning_rate":
|
| 1193 |
-
"loss": 0.
|
| 1194 |
"step": 1720
|
| 1195 |
},
|
| 1196 |
{
|
| 1197 |
"epoch": 18.8,
|
| 1198 |
-
"learning_rate":
|
| 1199 |
-
"loss": 0.
|
| 1200 |
"step": 1730
|
| 1201 |
},
|
| 1202 |
{
|
| 1203 |
"epoch": 18.91,
|
| 1204 |
-
"learning_rate":
|
| 1205 |
-
"loss": 0.
|
| 1206 |
"step": 1740
|
| 1207 |
},
|
| 1208 |
{
|
| 1209 |
"epoch": 19.02,
|
| 1210 |
-
"learning_rate":
|
| 1211 |
-
"loss": 0.
|
| 1212 |
"step": 1750
|
| 1213 |
},
|
| 1214 |
{
|
| 1215 |
"epoch": 19.13,
|
| 1216 |
-
"learning_rate":
|
| 1217 |
-
"loss": 0.
|
| 1218 |
"step": 1760
|
| 1219 |
},
|
| 1220 |
{
|
| 1221 |
"epoch": 19.24,
|
| 1222 |
-
"learning_rate":
|
| 1223 |
-
"loss": 0.
|
| 1224 |
"step": 1770
|
| 1225 |
},
|
| 1226 |
{
|
| 1227 |
"epoch": 19.35,
|
| 1228 |
-
"learning_rate":
|
| 1229 |
-
"loss": 0.
|
| 1230 |
"step": 1780
|
| 1231 |
},
|
| 1232 |
{
|
| 1233 |
"epoch": 19.46,
|
| 1234 |
-
"learning_rate":
|
| 1235 |
-
"loss": 0.
|
| 1236 |
"step": 1790
|
| 1237 |
},
|
| 1238 |
{
|
| 1239 |
"epoch": 19.57,
|
| 1240 |
-
"learning_rate":
|
| 1241 |
-
"loss": 0.
|
| 1242 |
"step": 1800
|
| 1243 |
},
|
| 1244 |
{
|
| 1245 |
"epoch": 19.57,
|
| 1246 |
-
"eval_accuracy": 0.
|
| 1247 |
-
"eval_loss": 0.
|
| 1248 |
-
"eval_runtime": 1.
|
| 1249 |
-
"eval_samples_per_second":
|
| 1250 |
-
"eval_steps_per_second": 17.
|
| 1251 |
"step": 1800
|
| 1252 |
},
|
| 1253 |
{
|
| 1254 |
"epoch": 19.67,
|
| 1255 |
-
"learning_rate":
|
| 1256 |
-
"loss": 0.
|
| 1257 |
"step": 1810
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
"epoch": 19.78,
|
| 1261 |
-
"learning_rate":
|
| 1262 |
-
"loss": 0.
|
| 1263 |
"step": 1820
|
| 1264 |
},
|
| 1265 |
{
|
| 1266 |
"epoch": 19.89,
|
| 1267 |
-
"learning_rate":
|
| 1268 |
-
"loss": 0.
|
| 1269 |
"step": 1830
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
"epoch": 20.0,
|
| 1273 |
-
"learning_rate":
|
| 1274 |
-
"loss": 0.
|
| 1275 |
"step": 1840
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
-
"epoch": 20.
|
| 1279 |
-
"
|
| 1280 |
-
"
|
| 1281 |
-
"
|
| 1282 |
-
|
| 1283 |
-
|
| 1284 |
-
"
|
| 1285 |
-
"learning_rate": 0.0001192608695652174,
|
| 1286 |
-
"loss": 0.2989,
|
| 1287 |
-
"step": 1860
|
| 1288 |
-
},
|
| 1289 |
-
{
|
| 1290 |
-
"epoch": 20.33,
|
| 1291 |
-
"learning_rate": 0.00011882608695652175,
|
| 1292 |
-
"loss": 0.4813,
|
| 1293 |
-
"step": 1870
|
| 1294 |
-
},
|
| 1295 |
-
{
|
| 1296 |
-
"epoch": 20.43,
|
| 1297 |
-
"learning_rate": 0.00011839130434782609,
|
| 1298 |
-
"loss": 0.0967,
|
| 1299 |
-
"step": 1880
|
| 1300 |
-
},
|
| 1301 |
-
{
|
| 1302 |
-
"epoch": 20.54,
|
| 1303 |
-
"learning_rate": 0.00011795652173913044,
|
| 1304 |
-
"loss": 0.2902,
|
| 1305 |
-
"step": 1890
|
| 1306 |
-
},
|
| 1307 |
-
{
|
| 1308 |
-
"epoch": 20.65,
|
| 1309 |
-
"learning_rate": 0.00011752173913043478,
|
| 1310 |
-
"loss": 0.2769,
|
| 1311 |
-
"step": 1900
|
| 1312 |
-
},
|
| 1313 |
-
{
|
| 1314 |
-
"epoch": 20.65,
|
| 1315 |
-
"eval_accuracy": 0.95,
|
| 1316 |
-
"eval_loss": 0.1938965767621994,
|
| 1317 |
-
"eval_runtime": 2.5866,
|
| 1318 |
-
"eval_samples_per_second": 100.519,
|
| 1319 |
-
"eval_steps_per_second": 12.758,
|
| 1320 |
-
"step": 1900
|
| 1321 |
-
},
|
| 1322 |
-
{
|
| 1323 |
-
"epoch": 20.76,
|
| 1324 |
-
"learning_rate": 0.00011708695652173913,
|
| 1325 |
-
"loss": 0.443,
|
| 1326 |
-
"step": 1910
|
| 1327 |
-
},
|
| 1328 |
-
{
|
| 1329 |
-
"epoch": 20.87,
|
| 1330 |
-
"learning_rate": 0.00011665217391304348,
|
| 1331 |
-
"loss": 0.2882,
|
| 1332 |
-
"step": 1920
|
| 1333 |
-
},
|
| 1334 |
-
{
|
| 1335 |
-
"epoch": 20.98,
|
| 1336 |
-
"learning_rate": 0.00011621739130434783,
|
| 1337 |
-
"loss": 0.3616,
|
| 1338 |
-
"step": 1930
|
| 1339 |
-
},
|
| 1340 |
-
{
|
| 1341 |
-
"epoch": 21.09,
|
| 1342 |
-
"learning_rate": 0.00011578260869565219,
|
| 1343 |
-
"loss": 0.2436,
|
| 1344 |
-
"step": 1940
|
| 1345 |
-
},
|
| 1346 |
-
{
|
| 1347 |
-
"epoch": 21.2,
|
| 1348 |
-
"learning_rate": 0.00011534782608695654,
|
| 1349 |
-
"loss": 0.3428,
|
| 1350 |
-
"step": 1950
|
| 1351 |
-
},
|
| 1352 |
-
{
|
| 1353 |
-
"epoch": 21.3,
|
| 1354 |
-
"learning_rate": 0.00011491304347826088,
|
| 1355 |
-
"loss": 0.2317,
|
| 1356 |
-
"step": 1960
|
| 1357 |
-
},
|
| 1358 |
-
{
|
| 1359 |
-
"epoch": 21.41,
|
| 1360 |
-
"learning_rate": 0.00011447826086956522,
|
| 1361 |
-
"loss": 0.1838,
|
| 1362 |
-
"step": 1970
|
| 1363 |
-
},
|
| 1364 |
-
{
|
| 1365 |
-
"epoch": 21.52,
|
| 1366 |
-
"learning_rate": 0.00011404347826086957,
|
| 1367 |
-
"loss": 0.3383,
|
| 1368 |
-
"step": 1980
|
| 1369 |
-
},
|
| 1370 |
-
{
|
| 1371 |
-
"epoch": 21.63,
|
| 1372 |
-
"learning_rate": 0.00011360869565217391,
|
| 1373 |
-
"loss": 0.3384,
|
| 1374 |
-
"step": 1990
|
| 1375 |
-
},
|
| 1376 |
-
{
|
| 1377 |
-
"epoch": 21.74,
|
| 1378 |
-
"learning_rate": 0.00011317391304347826,
|
| 1379 |
-
"loss": 0.2471,
|
| 1380 |
-
"step": 2000
|
| 1381 |
-
},
|
| 1382 |
-
{
|
| 1383 |
-
"epoch": 21.74,
|
| 1384 |
-
"eval_accuracy": 0.95,
|
| 1385 |
-
"eval_loss": 0.17909857630729675,
|
| 1386 |
-
"eval_runtime": 1.8343,
|
| 1387 |
-
"eval_samples_per_second": 141.746,
|
| 1388 |
-
"eval_steps_per_second": 17.991,
|
| 1389 |
-
"step": 2000
|
| 1390 |
-
},
|
| 1391 |
-
{
|
| 1392 |
-
"epoch": 21.85,
|
| 1393 |
-
"learning_rate": 0.00011273913043478261,
|
| 1394 |
-
"loss": 0.2243,
|
| 1395 |
-
"step": 2010
|
| 1396 |
-
},
|
| 1397 |
-
{
|
| 1398 |
-
"epoch": 21.96,
|
| 1399 |
-
"learning_rate": 0.00011230434782608696,
|
| 1400 |
-
"loss": 0.2756,
|
| 1401 |
-
"step": 2020
|
| 1402 |
-
},
|
| 1403 |
-
{
|
| 1404 |
-
"epoch": 22.07,
|
| 1405 |
-
"learning_rate": 0.00011186956521739132,
|
| 1406 |
-
"loss": 0.2575,
|
| 1407 |
-
"step": 2030
|
| 1408 |
-
},
|
| 1409 |
-
{
|
| 1410 |
-
"epoch": 22.17,
|
| 1411 |
-
"learning_rate": 0.00011143478260869567,
|
| 1412 |
-
"loss": 0.3987,
|
| 1413 |
-
"step": 2040
|
| 1414 |
-
},
|
| 1415 |
-
{
|
| 1416 |
-
"epoch": 22.28,
|
| 1417 |
-
"learning_rate": 0.00011100000000000001,
|
| 1418 |
-
"loss": 0.2974,
|
| 1419 |
-
"step": 2050
|
| 1420 |
-
},
|
| 1421 |
-
{
|
| 1422 |
-
"epoch": 22.39,
|
| 1423 |
-
"learning_rate": 0.00011056521739130435,
|
| 1424 |
-
"loss": 0.2818,
|
| 1425 |
-
"step": 2060
|
| 1426 |
-
},
|
| 1427 |
-
{
|
| 1428 |
-
"epoch": 22.5,
|
| 1429 |
-
"learning_rate": 0.0001101304347826087,
|
| 1430 |
-
"loss": 0.1453,
|
| 1431 |
-
"step": 2070
|
| 1432 |
-
},
|
| 1433 |
-
{
|
| 1434 |
-
"epoch": 22.61,
|
| 1435 |
-
"learning_rate": 0.00010969565217391304,
|
| 1436 |
-
"loss": 0.2972,
|
| 1437 |
-
"step": 2080
|
| 1438 |
-
},
|
| 1439 |
-
{
|
| 1440 |
-
"epoch": 22.72,
|
| 1441 |
-
"learning_rate": 0.00010926086956521739,
|
| 1442 |
-
"loss": 0.1785,
|
| 1443 |
-
"step": 2090
|
| 1444 |
-
},
|
| 1445 |
-
{
|
| 1446 |
-
"epoch": 22.83,
|
| 1447 |
-
"learning_rate": 0.00010882608695652174,
|
| 1448 |
-
"loss": 0.3054,
|
| 1449 |
-
"step": 2100
|
| 1450 |
-
},
|
| 1451 |
-
{
|
| 1452 |
-
"epoch": 22.83,
|
| 1453 |
-
"eval_accuracy": 0.9615384615384616,
|
| 1454 |
-
"eval_loss": 0.18149061501026154,
|
| 1455 |
-
"eval_runtime": 2.3493,
|
| 1456 |
-
"eval_samples_per_second": 110.67,
|
| 1457 |
-
"eval_steps_per_second": 14.047,
|
| 1458 |
-
"step": 2100
|
| 1459 |
-
},
|
| 1460 |
-
{
|
| 1461 |
-
"epoch": 22.93,
|
| 1462 |
-
"learning_rate": 0.00010839130434782609,
|
| 1463 |
-
"loss": 0.2999,
|
| 1464 |
-
"step": 2110
|
| 1465 |
-
},
|
| 1466 |
-
{
|
| 1467 |
-
"epoch": 23.04,
|
| 1468 |
-
"learning_rate": 0.00010795652173913045,
|
| 1469 |
-
"loss": 0.1633,
|
| 1470 |
-
"step": 2120
|
| 1471 |
-
},
|
| 1472 |
-
{
|
| 1473 |
-
"epoch": 23.15,
|
| 1474 |
-
"learning_rate": 0.0001075217391304348,
|
| 1475 |
-
"loss": 0.3255,
|
| 1476 |
-
"step": 2130
|
| 1477 |
-
},
|
| 1478 |
-
{
|
| 1479 |
-
"epoch": 23.26,
|
| 1480 |
-
"learning_rate": 0.00010708695652173915,
|
| 1481 |
-
"loss": 0.2453,
|
| 1482 |
-
"step": 2140
|
| 1483 |
-
},
|
| 1484 |
-
{
|
| 1485 |
-
"epoch": 23.37,
|
| 1486 |
-
"learning_rate": 0.00010665217391304348,
|
| 1487 |
-
"loss": 0.4836,
|
| 1488 |
-
"step": 2150
|
| 1489 |
-
},
|
| 1490 |
-
{
|
| 1491 |
-
"epoch": 23.48,
|
| 1492 |
-
"learning_rate": 0.00010621739130434783,
|
| 1493 |
-
"loss": 0.1796,
|
| 1494 |
-
"step": 2160
|
| 1495 |
-
},
|
| 1496 |
-
{
|
| 1497 |
-
"epoch": 23.59,
|
| 1498 |
-
"learning_rate": 0.00010578260869565218,
|
| 1499 |
-
"loss": 0.1229,
|
| 1500 |
-
"step": 2170
|
| 1501 |
-
},
|
| 1502 |
-
{
|
| 1503 |
-
"epoch": 23.7,
|
| 1504 |
-
"learning_rate": 0.00010534782608695652,
|
| 1505 |
-
"loss": 0.4153,
|
| 1506 |
-
"step": 2180
|
| 1507 |
-
},
|
| 1508 |
-
{
|
| 1509 |
-
"epoch": 23.8,
|
| 1510 |
-
"learning_rate": 0.00010491304347826087,
|
| 1511 |
-
"loss": 0.2937,
|
| 1512 |
-
"step": 2190
|
| 1513 |
-
},
|
| 1514 |
-
{
|
| 1515 |
-
"epoch": 23.91,
|
| 1516 |
-
"learning_rate": 0.00010447826086956522,
|
| 1517 |
-
"loss": 0.4803,
|
| 1518 |
-
"step": 2200
|
| 1519 |
-
},
|
| 1520 |
-
{
|
| 1521 |
-
"epoch": 23.91,
|
| 1522 |
-
"eval_accuracy": 0.95,
|
| 1523 |
-
"eval_loss": 0.23987938463687897,
|
| 1524 |
-
"eval_runtime": 1.8204,
|
| 1525 |
-
"eval_samples_per_second": 142.824,
|
| 1526 |
-
"eval_steps_per_second": 18.128,
|
| 1527 |
-
"step": 2200
|
| 1528 |
-
},
|
| 1529 |
-
{
|
| 1530 |
-
"epoch": 24.02,
|
| 1531 |
-
"learning_rate": 0.00010404347826086958,
|
| 1532 |
-
"loss": 0.1835,
|
| 1533 |
-
"step": 2210
|
| 1534 |
-
},
|
| 1535 |
-
{
|
| 1536 |
-
"epoch": 24.13,
|
| 1537 |
-
"learning_rate": 0.00010360869565217393,
|
| 1538 |
-
"loss": 0.2622,
|
| 1539 |
-
"step": 2220
|
| 1540 |
-
},
|
| 1541 |
-
{
|
| 1542 |
-
"epoch": 24.24,
|
| 1543 |
-
"learning_rate": 0.00010317391304347828,
|
| 1544 |
-
"loss": 0.2113,
|
| 1545 |
-
"step": 2230
|
| 1546 |
-
},
|
| 1547 |
-
{
|
| 1548 |
-
"epoch": 24.35,
|
| 1549 |
-
"learning_rate": 0.00010273913043478261,
|
| 1550 |
-
"loss": 0.1929,
|
| 1551 |
-
"step": 2240
|
| 1552 |
-
},
|
| 1553 |
-
{
|
| 1554 |
-
"epoch": 24.46,
|
| 1555 |
-
"learning_rate": 0.00010230434782608696,
|
| 1556 |
-
"loss": 0.483,
|
| 1557 |
-
"step": 2250
|
| 1558 |
-
},
|
| 1559 |
-
{
|
| 1560 |
-
"epoch": 24.57,
|
| 1561 |
-
"learning_rate": 0.0001018695652173913,
|
| 1562 |
-
"loss": 0.1994,
|
| 1563 |
-
"step": 2260
|
| 1564 |
-
},
|
| 1565 |
-
{
|
| 1566 |
-
"epoch": 24.67,
|
| 1567 |
-
"learning_rate": 0.00010143478260869565,
|
| 1568 |
-
"loss": 0.3179,
|
| 1569 |
-
"step": 2270
|
| 1570 |
-
},
|
| 1571 |
-
{
|
| 1572 |
-
"epoch": 24.78,
|
| 1573 |
-
"learning_rate": 0.000101,
|
| 1574 |
-
"loss": 0.2537,
|
| 1575 |
-
"step": 2280
|
| 1576 |
-
},
|
| 1577 |
-
{
|
| 1578 |
-
"epoch": 24.89,
|
| 1579 |
-
"learning_rate": 0.00010056521739130435,
|
| 1580 |
-
"loss": 0.3047,
|
| 1581 |
-
"step": 2290
|
| 1582 |
-
},
|
| 1583 |
-
{
|
| 1584 |
-
"epoch": 25.0,
|
| 1585 |
-
"learning_rate": 0.00010013043478260871,
|
| 1586 |
-
"loss": 0.218,
|
| 1587 |
-
"step": 2300
|
| 1588 |
-
},
|
| 1589 |
-
{
|
| 1590 |
-
"epoch": 25.0,
|
| 1591 |
-
"eval_accuracy": 0.9461538461538461,
|
| 1592 |
-
"eval_loss": 0.28188276290893555,
|
| 1593 |
-
"eval_runtime": 2.2046,
|
| 1594 |
-
"eval_samples_per_second": 117.936,
|
| 1595 |
-
"eval_steps_per_second": 14.969,
|
| 1596 |
-
"step": 2300
|
| 1597 |
-
},
|
| 1598 |
-
{
|
| 1599 |
-
"epoch": 25.11,
|
| 1600 |
-
"learning_rate": 9.969565217391305e-05,
|
| 1601 |
-
"loss": 0.1038,
|
| 1602 |
-
"step": 2310
|
| 1603 |
-
},
|
| 1604 |
-
{
|
| 1605 |
-
"epoch": 25.22,
|
| 1606 |
-
"learning_rate": 9.92608695652174e-05,
|
| 1607 |
-
"loss": 0.2629,
|
| 1608 |
-
"step": 2320
|
| 1609 |
-
},
|
| 1610 |
-
{
|
| 1611 |
-
"epoch": 25.33,
|
| 1612 |
-
"learning_rate": 9.882608695652174e-05,
|
| 1613 |
-
"loss": 0.2938,
|
| 1614 |
-
"step": 2330
|
| 1615 |
-
},
|
| 1616 |
-
{
|
| 1617 |
-
"epoch": 25.43,
|
| 1618 |
-
"learning_rate": 9.83913043478261e-05,
|
| 1619 |
-
"loss": 0.2453,
|
| 1620 |
-
"step": 2340
|
| 1621 |
-
},
|
| 1622 |
-
{
|
| 1623 |
-
"epoch": 25.54,
|
| 1624 |
-
"learning_rate": 9.795652173913044e-05,
|
| 1625 |
-
"loss": 0.2449,
|
| 1626 |
-
"step": 2350
|
| 1627 |
-
},
|
| 1628 |
-
{
|
| 1629 |
-
"epoch": 25.65,
|
| 1630 |
-
"learning_rate": 9.752173913043478e-05,
|
| 1631 |
-
"loss": 0.355,
|
| 1632 |
-
"step": 2360
|
| 1633 |
-
},
|
| 1634 |
-
{
|
| 1635 |
-
"epoch": 25.76,
|
| 1636 |
-
"learning_rate": 9.708695652173913e-05,
|
| 1637 |
-
"loss": 0.199,
|
| 1638 |
-
"step": 2370
|
| 1639 |
-
},
|
| 1640 |
-
{
|
| 1641 |
-
"epoch": 25.87,
|
| 1642 |
-
"learning_rate": 9.665217391304348e-05,
|
| 1643 |
-
"loss": 0.3433,
|
| 1644 |
-
"step": 2380
|
| 1645 |
-
},
|
| 1646 |
-
{
|
| 1647 |
-
"epoch": 25.98,
|
| 1648 |
-
"learning_rate": 9.621739130434783e-05,
|
| 1649 |
-
"loss": 0.2047,
|
| 1650 |
-
"step": 2390
|
| 1651 |
-
},
|
| 1652 |
-
{
|
| 1653 |
-
"epoch": 26.09,
|
| 1654 |
-
"learning_rate": 9.578260869565218e-05,
|
| 1655 |
-
"loss": 0.1858,
|
| 1656 |
-
"step": 2400
|
| 1657 |
-
},
|
| 1658 |
-
{
|
| 1659 |
-
"epoch": 26.09,
|
| 1660 |
-
"eval_accuracy": 0.9769230769230769,
|
| 1661 |
-
"eval_loss": 0.20682699978351593,
|
| 1662 |
-
"eval_runtime": 1.9198,
|
| 1663 |
-
"eval_samples_per_second": 135.43,
|
| 1664 |
-
"eval_steps_per_second": 17.189,
|
| 1665 |
-
"step": 2400
|
| 1666 |
-
},
|
| 1667 |
-
{
|
| 1668 |
-
"epoch": 26.2,
|
| 1669 |
-
"learning_rate": 9.534782608695652e-05,
|
| 1670 |
-
"loss": 0.2261,
|
| 1671 |
-
"step": 2410
|
| 1672 |
-
},
|
| 1673 |
-
{
|
| 1674 |
-
"epoch": 26.3,
|
| 1675 |
-
"learning_rate": 9.491304347826087e-05,
|
| 1676 |
-
"loss": 0.2663,
|
| 1677 |
-
"step": 2420
|
| 1678 |
-
},
|
| 1679 |
-
{
|
| 1680 |
-
"epoch": 26.41,
|
| 1681 |
-
"learning_rate": 9.447826086956523e-05,
|
| 1682 |
-
"loss": 0.209,
|
| 1683 |
-
"step": 2430
|
| 1684 |
-
},
|
| 1685 |
-
{
|
| 1686 |
-
"epoch": 26.52,
|
| 1687 |
-
"learning_rate": 9.404347826086957e-05,
|
| 1688 |
-
"loss": 0.1664,
|
| 1689 |
-
"step": 2440
|
| 1690 |
-
},
|
| 1691 |
-
{
|
| 1692 |
-
"epoch": 26.63,
|
| 1693 |
-
"learning_rate": 9.360869565217392e-05,
|
| 1694 |
-
"loss": 0.2993,
|
| 1695 |
-
"step": 2450
|
| 1696 |
-
},
|
| 1697 |
-
{
|
| 1698 |
-
"epoch": 26.74,
|
| 1699 |
-
"learning_rate": 9.317391304347826e-05,
|
| 1700 |
-
"loss": 0.1812,
|
| 1701 |
-
"step": 2460
|
| 1702 |
-
},
|
| 1703 |
-
{
|
| 1704 |
-
"epoch": 26.85,
|
| 1705 |
-
"learning_rate": 9.273913043478261e-05,
|
| 1706 |
-
"loss": 0.3832,
|
| 1707 |
-
"step": 2470
|
| 1708 |
-
},
|
| 1709 |
-
{
|
| 1710 |
-
"epoch": 26.96,
|
| 1711 |
-
"learning_rate": 9.230434782608696e-05,
|
| 1712 |
-
"loss": 0.2746,
|
| 1713 |
-
"step": 2480
|
| 1714 |
-
},
|
| 1715 |
-
{
|
| 1716 |
-
"epoch": 27.07,
|
| 1717 |
-
"learning_rate": 9.186956521739131e-05,
|
| 1718 |
-
"loss": 0.2398,
|
| 1719 |
-
"step": 2490
|
| 1720 |
-
},
|
| 1721 |
-
{
|
| 1722 |
-
"epoch": 27.17,
|
| 1723 |
-
"learning_rate": 9.143478260869566e-05,
|
| 1724 |
-
"loss": 0.214,
|
| 1725 |
-
"step": 2500
|
| 1726 |
-
},
|
| 1727 |
-
{
|
| 1728 |
-
"epoch": 27.17,
|
| 1729 |
-
"eval_accuracy": 0.9461538461538461,
|
| 1730 |
-
"eval_loss": 0.2683180868625641,
|
| 1731 |
-
"eval_runtime": 1.97,
|
| 1732 |
-
"eval_samples_per_second": 131.981,
|
| 1733 |
-
"eval_steps_per_second": 16.751,
|
| 1734 |
-
"step": 2500
|
| 1735 |
-
},
|
| 1736 |
-
{
|
| 1737 |
-
"epoch": 27.28,
|
| 1738 |
-
"learning_rate": 9.1e-05,
|
| 1739 |
-
"loss": 0.3322,
|
| 1740 |
-
"step": 2510
|
| 1741 |
-
},
|
| 1742 |
-
{
|
| 1743 |
-
"epoch": 27.39,
|
| 1744 |
-
"learning_rate": 9.056521739130435e-05,
|
| 1745 |
-
"loss": 0.1819,
|
| 1746 |
-
"step": 2520
|
| 1747 |
-
},
|
| 1748 |
-
{
|
| 1749 |
-
"epoch": 27.5,
|
| 1750 |
-
"learning_rate": 9.01304347826087e-05,
|
| 1751 |
-
"loss": 0.358,
|
| 1752 |
-
"step": 2530
|
| 1753 |
-
},
|
| 1754 |
-
{
|
| 1755 |
-
"epoch": 27.61,
|
| 1756 |
-
"learning_rate": 8.969565217391305e-05,
|
| 1757 |
-
"loss": 0.1992,
|
| 1758 |
-
"step": 2540
|
| 1759 |
-
},
|
| 1760 |
-
{
|
| 1761 |
-
"epoch": 27.72,
|
| 1762 |
-
"learning_rate": 8.92608695652174e-05,
|
| 1763 |
-
"loss": 0.2446,
|
| 1764 |
-
"step": 2550
|
| 1765 |
-
},
|
| 1766 |
-
{
|
| 1767 |
-
"epoch": 27.83,
|
| 1768 |
-
"learning_rate": 8.882608695652174e-05,
|
| 1769 |
-
"loss": 0.2713,
|
| 1770 |
-
"step": 2560
|
| 1771 |
-
},
|
| 1772 |
-
{
|
| 1773 |
-
"epoch": 27.93,
|
| 1774 |
-
"learning_rate": 8.839130434782609e-05,
|
| 1775 |
-
"loss": 0.1827,
|
| 1776 |
-
"step": 2570
|
| 1777 |
-
},
|
| 1778 |
-
{
|
| 1779 |
-
"epoch": 28.04,
|
| 1780 |
-
"learning_rate": 8.795652173913044e-05,
|
| 1781 |
-
"loss": 0.3405,
|
| 1782 |
-
"step": 2580
|
| 1783 |
-
},
|
| 1784 |
-
{
|
| 1785 |
-
"epoch": 28.15,
|
| 1786 |
-
"learning_rate": 8.752173913043479e-05,
|
| 1787 |
-
"loss": 0.3026,
|
| 1788 |
-
"step": 2590
|
| 1789 |
-
},
|
| 1790 |
-
{
|
| 1791 |
-
"epoch": 28.26,
|
| 1792 |
-
"learning_rate": 8.708695652173913e-05,
|
| 1793 |
-
"loss": 0.2532,
|
| 1794 |
-
"step": 2600
|
| 1795 |
-
},
|
| 1796 |
-
{
|
| 1797 |
-
"epoch": 28.26,
|
| 1798 |
-
"eval_accuracy": 0.9615384615384616,
|
| 1799 |
-
"eval_loss": 0.13641561567783356,
|
| 1800 |
-
"eval_runtime": 1.8692,
|
| 1801 |
-
"eval_samples_per_second": 139.096,
|
| 1802 |
-
"eval_steps_per_second": 17.654,
|
| 1803 |
-
"step": 2600
|
| 1804 |
-
},
|
| 1805 |
-
{
|
| 1806 |
-
"epoch": 28.37,
|
| 1807 |
-
"learning_rate": 8.665217391304348e-05,
|
| 1808 |
-
"loss": 0.298,
|
| 1809 |
-
"step": 2610
|
| 1810 |
-
},
|
| 1811 |
-
{
|
| 1812 |
-
"epoch": 28.48,
|
| 1813 |
-
"learning_rate": 8.621739130434783e-05,
|
| 1814 |
-
"loss": 0.1697,
|
| 1815 |
-
"step": 2620
|
| 1816 |
-
},
|
| 1817 |
-
{
|
| 1818 |
-
"epoch": 28.59,
|
| 1819 |
-
"learning_rate": 8.578260869565218e-05,
|
| 1820 |
-
"loss": 0.1527,
|
| 1821 |
-
"step": 2630
|
| 1822 |
-
},
|
| 1823 |
-
{
|
| 1824 |
-
"epoch": 28.7,
|
| 1825 |
-
"learning_rate": 8.534782608695653e-05,
|
| 1826 |
-
"loss": 0.1777,
|
| 1827 |
-
"step": 2640
|
| 1828 |
-
},
|
| 1829 |
-
{
|
| 1830 |
-
"epoch": 28.8,
|
| 1831 |
-
"learning_rate": 8.491304347826087e-05,
|
| 1832 |
-
"loss": 0.212,
|
| 1833 |
-
"step": 2650
|
| 1834 |
-
},
|
| 1835 |
-
{
|
| 1836 |
-
"epoch": 28.91,
|
| 1837 |
-
"learning_rate": 8.447826086956522e-05,
|
| 1838 |
-
"loss": 0.3394,
|
| 1839 |
-
"step": 2660
|
| 1840 |
-
},
|
| 1841 |
-
{
|
| 1842 |
-
"epoch": 29.02,
|
| 1843 |
-
"learning_rate": 8.404347826086957e-05,
|
| 1844 |
-
"loss": 0.1577,
|
| 1845 |
-
"step": 2670
|
| 1846 |
-
},
|
| 1847 |
-
{
|
| 1848 |
-
"epoch": 29.13,
|
| 1849 |
-
"learning_rate": 8.360869565217392e-05,
|
| 1850 |
-
"loss": 0.2502,
|
| 1851 |
-
"step": 2680
|
| 1852 |
-
},
|
| 1853 |
-
{
|
| 1854 |
-
"epoch": 29.24,
|
| 1855 |
-
"learning_rate": 8.317391304347826e-05,
|
| 1856 |
-
"loss": 0.2463,
|
| 1857 |
-
"step": 2690
|
| 1858 |
-
},
|
| 1859 |
-
{
|
| 1860 |
-
"epoch": 29.35,
|
| 1861 |
-
"learning_rate": 8.273913043478261e-05,
|
| 1862 |
-
"loss": 0.2021,
|
| 1863 |
-
"step": 2700
|
| 1864 |
-
},
|
| 1865 |
-
{
|
| 1866 |
-
"epoch": 29.35,
|
| 1867 |
-
"eval_accuracy": 0.9692307692307692,
|
| 1868 |
-
"eval_loss": 0.15067297220230103,
|
| 1869 |
-
"eval_runtime": 1.8314,
|
| 1870 |
-
"eval_samples_per_second": 141.965,
|
| 1871 |
-
"eval_steps_per_second": 18.019,
|
| 1872 |
-
"step": 2700
|
| 1873 |
-
},
|
| 1874 |
-
{
|
| 1875 |
-
"epoch": 29.46,
|
| 1876 |
-
"learning_rate": 8.230434782608696e-05,
|
| 1877 |
-
"loss": 0.204,
|
| 1878 |
-
"step": 2710
|
| 1879 |
-
},
|
| 1880 |
-
{
|
| 1881 |
-
"epoch": 29.57,
|
| 1882 |
-
"learning_rate": 8.186956521739131e-05,
|
| 1883 |
-
"loss": 0.2408,
|
| 1884 |
-
"step": 2720
|
| 1885 |
-
},
|
| 1886 |
-
{
|
| 1887 |
-
"epoch": 29.67,
|
| 1888 |
-
"learning_rate": 8.143478260869566e-05,
|
| 1889 |
-
"loss": 0.1918,
|
| 1890 |
-
"step": 2730
|
| 1891 |
-
},
|
| 1892 |
-
{
|
| 1893 |
-
"epoch": 29.78,
|
| 1894 |
-
"learning_rate": 8.1e-05,
|
| 1895 |
-
"loss": 0.1922,
|
| 1896 |
-
"step": 2740
|
| 1897 |
-
},
|
| 1898 |
-
{
|
| 1899 |
-
"epoch": 29.89,
|
| 1900 |
-
"learning_rate": 8.056521739130435e-05,
|
| 1901 |
-
"loss": 0.1565,
|
| 1902 |
-
"step": 2750
|
| 1903 |
-
},
|
| 1904 |
-
{
|
| 1905 |
-
"epoch": 30.0,
|
| 1906 |
-
"learning_rate": 8.01304347826087e-05,
|
| 1907 |
-
"loss": 0.1015,
|
| 1908 |
-
"step": 2760
|
| 1909 |
-
},
|
| 1910 |
-
{
|
| 1911 |
-
"epoch": 30.11,
|
| 1912 |
-
"learning_rate": 7.969565217391305e-05,
|
| 1913 |
-
"loss": 0.267,
|
| 1914 |
-
"step": 2770
|
| 1915 |
-
},
|
| 1916 |
-
{
|
| 1917 |
-
"epoch": 30.22,
|
| 1918 |
-
"learning_rate": 7.92608695652174e-05,
|
| 1919 |
-
"loss": 0.1925,
|
| 1920 |
-
"step": 2780
|
| 1921 |
-
},
|
| 1922 |
-
{
|
| 1923 |
-
"epoch": 30.33,
|
| 1924 |
-
"learning_rate": 7.882608695652174e-05,
|
| 1925 |
-
"loss": 0.189,
|
| 1926 |
-
"step": 2790
|
| 1927 |
-
},
|
| 1928 |
-
{
|
| 1929 |
-
"epoch": 30.43,
|
| 1930 |
-
"learning_rate": 7.839130434782609e-05,
|
| 1931 |
-
"loss": 0.1794,
|
| 1932 |
-
"step": 2800
|
| 1933 |
-
},
|
| 1934 |
-
{
|
| 1935 |
-
"epoch": 30.43,
|
| 1936 |
-
"eval_accuracy": 0.9692307692307692,
|
| 1937 |
-
"eval_loss": 0.14496548473834991,
|
| 1938 |
-
"eval_runtime": 1.8418,
|
| 1939 |
-
"eval_samples_per_second": 141.168,
|
| 1940 |
-
"eval_steps_per_second": 17.917,
|
| 1941 |
-
"step": 2800
|
| 1942 |
-
},
|
| 1943 |
-
{
|
| 1944 |
-
"epoch": 30.54,
|
| 1945 |
-
"learning_rate": 7.795652173913044e-05,
|
| 1946 |
-
"loss": 0.2747,
|
| 1947 |
-
"step": 2810
|
| 1948 |
-
},
|
| 1949 |
-
{
|
| 1950 |
-
"epoch": 30.65,
|
| 1951 |
-
"learning_rate": 7.752173913043479e-05,
|
| 1952 |
-
"loss": 0.2668,
|
| 1953 |
-
"step": 2820
|
| 1954 |
-
},
|
| 1955 |
-
{
|
| 1956 |
-
"epoch": 30.76,
|
| 1957 |
-
"learning_rate": 7.708695652173913e-05,
|
| 1958 |
-
"loss": 0.4758,
|
| 1959 |
-
"step": 2830
|
| 1960 |
-
},
|
| 1961 |
-
{
|
| 1962 |
-
"epoch": 30.87,
|
| 1963 |
-
"learning_rate": 7.665217391304348e-05,
|
| 1964 |
-
"loss": 0.1839,
|
| 1965 |
-
"step": 2840
|
| 1966 |
-
},
|
| 1967 |
-
{
|
| 1968 |
-
"epoch": 30.98,
|
| 1969 |
-
"learning_rate": 7.621739130434783e-05,
|
| 1970 |
-
"loss": 0.3076,
|
| 1971 |
-
"step": 2850
|
| 1972 |
-
},
|
| 1973 |
-
{
|
| 1974 |
-
"epoch": 31.09,
|
| 1975 |
-
"learning_rate": 7.578260869565218e-05,
|
| 1976 |
-
"loss": 0.1099,
|
| 1977 |
-
"step": 2860
|
| 1978 |
-
},
|
| 1979 |
-
{
|
| 1980 |
-
"epoch": 31.2,
|
| 1981 |
-
"learning_rate": 7.534782608695653e-05,
|
| 1982 |
-
"loss": 0.2545,
|
| 1983 |
-
"step": 2870
|
| 1984 |
-
},
|
| 1985 |
-
{
|
| 1986 |
-
"epoch": 31.3,
|
| 1987 |
-
"learning_rate": 7.491304347826087e-05,
|
| 1988 |
-
"loss": 0.2875,
|
| 1989 |
-
"step": 2880
|
| 1990 |
-
},
|
| 1991 |
-
{
|
| 1992 |
-
"epoch": 31.41,
|
| 1993 |
-
"learning_rate": 7.447826086956522e-05,
|
| 1994 |
-
"loss": 0.183,
|
| 1995 |
-
"step": 2890
|
| 1996 |
-
},
|
| 1997 |
-
{
|
| 1998 |
-
"epoch": 31.52,
|
| 1999 |
-
"learning_rate": 7.404347826086957e-05,
|
| 2000 |
-
"loss": 0.1263,
|
| 2001 |
-
"step": 2900
|
| 2002 |
-
},
|
| 2003 |
-
{
|
| 2004 |
-
"epoch": 31.52,
|
| 2005 |
-
"eval_accuracy": 0.9692307692307692,
|
| 2006 |
-
"eval_loss": 0.15624746680259705,
|
| 2007 |
-
"eval_runtime": 1.8016,
|
| 2008 |
-
"eval_samples_per_second": 144.316,
|
| 2009 |
-
"eval_steps_per_second": 18.317,
|
| 2010 |
-
"step": 2900
|
| 2011 |
-
},
|
| 2012 |
-
{
|
| 2013 |
-
"epoch": 31.63,
|
| 2014 |
-
"learning_rate": 7.360869565217392e-05,
|
| 2015 |
-
"loss": 0.2734,
|
| 2016 |
-
"step": 2910
|
| 2017 |
-
},
|
| 2018 |
-
{
|
| 2019 |
-
"epoch": 31.74,
|
| 2020 |
-
"learning_rate": 7.317391304347827e-05,
|
| 2021 |
-
"loss": 0.2466,
|
| 2022 |
-
"step": 2920
|
| 2023 |
-
},
|
| 2024 |
-
{
|
| 2025 |
-
"epoch": 31.85,
|
| 2026 |
-
"learning_rate": 7.273913043478261e-05,
|
| 2027 |
-
"loss": 0.2409,
|
| 2028 |
-
"step": 2930
|
| 2029 |
-
},
|
| 2030 |
-
{
|
| 2031 |
-
"epoch": 31.96,
|
| 2032 |
-
"learning_rate": 7.230434782608696e-05,
|
| 2033 |
-
"loss": 0.1569,
|
| 2034 |
-
"step": 2940
|
| 2035 |
-
},
|
| 2036 |
-
{
|
| 2037 |
-
"epoch": 32.07,
|
| 2038 |
-
"learning_rate": 7.186956521739131e-05,
|
| 2039 |
-
"loss": 0.1666,
|
| 2040 |
-
"step": 2950
|
| 2041 |
-
},
|
| 2042 |
-
{
|
| 2043 |
-
"epoch": 32.17,
|
| 2044 |
-
"learning_rate": 7.143478260869566e-05,
|
| 2045 |
-
"loss": 0.1791,
|
| 2046 |
-
"step": 2960
|
| 2047 |
-
},
|
| 2048 |
-
{
|
| 2049 |
-
"epoch": 32.28,
|
| 2050 |
-
"learning_rate": 7.1e-05,
|
| 2051 |
-
"loss": 0.2163,
|
| 2052 |
-
"step": 2970
|
| 2053 |
-
},
|
| 2054 |
-
{
|
| 2055 |
-
"epoch": 32.39,
|
| 2056 |
-
"learning_rate": 7.056521739130435e-05,
|
| 2057 |
-
"loss": 0.1386,
|
| 2058 |
-
"step": 2980
|
| 2059 |
-
},
|
| 2060 |
-
{
|
| 2061 |
-
"epoch": 32.5,
|
| 2062 |
-
"learning_rate": 7.01304347826087e-05,
|
| 2063 |
-
"loss": 0.2482,
|
| 2064 |
-
"step": 2990
|
| 2065 |
-
},
|
| 2066 |
-
{
|
| 2067 |
-
"epoch": 32.61,
|
| 2068 |
-
"learning_rate": 6.969565217391305e-05,
|
| 2069 |
-
"loss": 0.1298,
|
| 2070 |
-
"step": 3000
|
| 2071 |
-
},
|
| 2072 |
-
{
|
| 2073 |
-
"epoch": 32.61,
|
| 2074 |
-
"eval_accuracy": 0.9807692307692307,
|
| 2075 |
-
"eval_loss": 0.10777488350868225,
|
| 2076 |
-
"eval_runtime": 1.8606,
|
| 2077 |
-
"eval_samples_per_second": 139.737,
|
| 2078 |
-
"eval_steps_per_second": 17.736,
|
| 2079 |
-
"step": 3000
|
| 2080 |
-
},
|
| 2081 |
-
{
|
| 2082 |
-
"epoch": 32.72,
|
| 2083 |
-
"learning_rate": 6.92608695652174e-05,
|
| 2084 |
-
"loss": 0.191,
|
| 2085 |
-
"step": 3010
|
| 2086 |
-
},
|
| 2087 |
-
{
|
| 2088 |
-
"epoch": 32.83,
|
| 2089 |
-
"learning_rate": 6.882608695652174e-05,
|
| 2090 |
-
"loss": 0.1915,
|
| 2091 |
-
"step": 3020
|
| 2092 |
-
},
|
| 2093 |
-
{
|
| 2094 |
-
"epoch": 32.93,
|
| 2095 |
-
"learning_rate": 6.839130434782609e-05,
|
| 2096 |
-
"loss": 0.3359,
|
| 2097 |
-
"step": 3030
|
| 2098 |
-
},
|
| 2099 |
-
{
|
| 2100 |
-
"epoch": 33.04,
|
| 2101 |
-
"learning_rate": 6.795652173913044e-05,
|
| 2102 |
-
"loss": 0.0779,
|
| 2103 |
-
"step": 3040
|
| 2104 |
-
},
|
| 2105 |
-
{
|
| 2106 |
-
"epoch": 33.15,
|
| 2107 |
-
"learning_rate": 6.752173913043479e-05,
|
| 2108 |
-
"loss": 0.2502,
|
| 2109 |
-
"step": 3050
|
| 2110 |
-
},
|
| 2111 |
-
{
|
| 2112 |
-
"epoch": 33.26,
|
| 2113 |
-
"learning_rate": 6.708695652173914e-05,
|
| 2114 |
-
"loss": 0.2406,
|
| 2115 |
-
"step": 3060
|
| 2116 |
-
},
|
| 2117 |
-
{
|
| 2118 |
-
"epoch": 33.37,
|
| 2119 |
-
"learning_rate": 6.665217391304348e-05,
|
| 2120 |
-
"loss": 0.2338,
|
| 2121 |
-
"step": 3070
|
| 2122 |
-
},
|
| 2123 |
-
{
|
| 2124 |
-
"epoch": 33.48,
|
| 2125 |
-
"learning_rate": 6.621739130434783e-05,
|
| 2126 |
-
"loss": 0.1917,
|
| 2127 |
-
"step": 3080
|
| 2128 |
-
},
|
| 2129 |
-
{
|
| 2130 |
-
"epoch": 33.59,
|
| 2131 |
-
"learning_rate": 6.578260869565218e-05,
|
| 2132 |
-
"loss": 0.2137,
|
| 2133 |
-
"step": 3090
|
| 2134 |
-
},
|
| 2135 |
-
{
|
| 2136 |
-
"epoch": 33.7,
|
| 2137 |
-
"learning_rate": 6.534782608695653e-05,
|
| 2138 |
-
"loss": 0.1883,
|
| 2139 |
-
"step": 3100
|
| 2140 |
-
},
|
| 2141 |
-
{
|
| 2142 |
-
"epoch": 33.7,
|
| 2143 |
-
"eval_accuracy": 0.9846153846153847,
|
| 2144 |
-
"eval_loss": 0.07627514749765396,
|
| 2145 |
-
"eval_runtime": 1.8071,
|
| 2146 |
-
"eval_samples_per_second": 143.881,
|
| 2147 |
-
"eval_steps_per_second": 18.262,
|
| 2148 |
-
"step": 3100
|
| 2149 |
-
},
|
| 2150 |
-
{
|
| 2151 |
-
"epoch": 33.8,
|
| 2152 |
-
"learning_rate": 6.491304347826087e-05,
|
| 2153 |
-
"loss": 0.1658,
|
| 2154 |
-
"step": 3110
|
| 2155 |
-
},
|
| 2156 |
-
{
|
| 2157 |
-
"epoch": 33.91,
|
| 2158 |
-
"learning_rate": 6.447826086956522e-05,
|
| 2159 |
-
"loss": 0.1709,
|
| 2160 |
-
"step": 3120
|
| 2161 |
-
},
|
| 2162 |
-
{
|
| 2163 |
-
"epoch": 34.02,
|
| 2164 |
-
"learning_rate": 6.404347826086957e-05,
|
| 2165 |
-
"loss": 0.1934,
|
| 2166 |
-
"step": 3130
|
| 2167 |
-
},
|
| 2168 |
-
{
|
| 2169 |
-
"epoch": 34.13,
|
| 2170 |
-
"learning_rate": 6.36086956521739e-05,
|
| 2171 |
-
"loss": 0.1042,
|
| 2172 |
-
"step": 3140
|
| 2173 |
-
},
|
| 2174 |
-
{
|
| 2175 |
-
"epoch": 34.24,
|
| 2176 |
-
"learning_rate": 6.317391304347827e-05,
|
| 2177 |
-
"loss": 0.1438,
|
| 2178 |
-
"step": 3150
|
| 2179 |
-
},
|
| 2180 |
-
{
|
| 2181 |
-
"epoch": 34.35,
|
| 2182 |
-
"learning_rate": 6.273913043478261e-05,
|
| 2183 |
-
"loss": 0.1592,
|
| 2184 |
-
"step": 3160
|
| 2185 |
-
},
|
| 2186 |
-
{
|
| 2187 |
-
"epoch": 34.46,
|
| 2188 |
-
"learning_rate": 6.230434782608696e-05,
|
| 2189 |
-
"loss": 0.3535,
|
| 2190 |
-
"step": 3170
|
| 2191 |
-
},
|
| 2192 |
-
{
|
| 2193 |
-
"epoch": 34.57,
|
| 2194 |
-
"learning_rate": 6.186956521739131e-05,
|
| 2195 |
-
"loss": 0.1521,
|
| 2196 |
-
"step": 3180
|
| 2197 |
-
},
|
| 2198 |
-
{
|
| 2199 |
-
"epoch": 34.67,
|
| 2200 |
-
"learning_rate": 6.143478260869566e-05,
|
| 2201 |
-
"loss": 0.2928,
|
| 2202 |
-
"step": 3190
|
| 2203 |
-
},
|
| 2204 |
-
{
|
| 2205 |
-
"epoch": 34.78,
|
| 2206 |
-
"learning_rate": 6.1e-05,
|
| 2207 |
-
"loss": 0.1773,
|
| 2208 |
-
"step": 3200
|
| 2209 |
-
},
|
| 2210 |
-
{
|
| 2211 |
-
"epoch": 34.78,
|
| 2212 |
-
"eval_accuracy": 0.9846153846153847,
|
| 2213 |
-
"eval_loss": 0.07703894376754761,
|
| 2214 |
-
"eval_runtime": 1.8178,
|
| 2215 |
-
"eval_samples_per_second": 143.029,
|
| 2216 |
-
"eval_steps_per_second": 18.154,
|
| 2217 |
-
"step": 3200
|
| 2218 |
-
},
|
| 2219 |
-
{
|
| 2220 |
-
"epoch": 34.89,
|
| 2221 |
-
"learning_rate": 6.056521739130435e-05,
|
| 2222 |
-
"loss": 0.1186,
|
| 2223 |
-
"step": 3210
|
| 2224 |
-
},
|
| 2225 |
-
{
|
| 2226 |
-
"epoch": 35.0,
|
| 2227 |
-
"learning_rate": 6.01304347826087e-05,
|
| 2228 |
-
"loss": 0.1795,
|
| 2229 |
-
"step": 3220
|
| 2230 |
-
},
|
| 2231 |
-
{
|
| 2232 |
-
"epoch": 35.11,
|
| 2233 |
-
"learning_rate": 5.969565217391304e-05,
|
| 2234 |
-
"loss": 0.1586,
|
| 2235 |
-
"step": 3230
|
| 2236 |
-
},
|
| 2237 |
-
{
|
| 2238 |
-
"epoch": 35.22,
|
| 2239 |
-
"learning_rate": 5.926086956521739e-05,
|
| 2240 |
-
"loss": 0.2032,
|
| 2241 |
-
"step": 3240
|
| 2242 |
-
},
|
| 2243 |
-
{
|
| 2244 |
-
"epoch": 35.33,
|
| 2245 |
-
"learning_rate": 5.8826086956521745e-05,
|
| 2246 |
-
"loss": 0.1276,
|
| 2247 |
-
"step": 3250
|
| 2248 |
-
},
|
| 2249 |
-
{
|
| 2250 |
-
"epoch": 35.43,
|
| 2251 |
-
"learning_rate": 5.839130434782609e-05,
|
| 2252 |
-
"loss": 0.1245,
|
| 2253 |
-
"step": 3260
|
| 2254 |
-
},
|
| 2255 |
-
{
|
| 2256 |
-
"epoch": 35.54,
|
| 2257 |
-
"learning_rate": 5.795652173913044e-05,
|
| 2258 |
-
"loss": 0.1988,
|
| 2259 |
-
"step": 3270
|
| 2260 |
-
},
|
| 2261 |
-
{
|
| 2262 |
-
"epoch": 35.65,
|
| 2263 |
-
"learning_rate": 5.752173913043478e-05,
|
| 2264 |
-
"loss": 0.0685,
|
| 2265 |
-
"step": 3280
|
| 2266 |
-
},
|
| 2267 |
-
{
|
| 2268 |
-
"epoch": 35.76,
|
| 2269 |
-
"learning_rate": 5.708695652173913e-05,
|
| 2270 |
-
"loss": 0.2522,
|
| 2271 |
-
"step": 3290
|
| 2272 |
-
},
|
| 2273 |
-
{
|
| 2274 |
-
"epoch": 35.87,
|
| 2275 |
-
"learning_rate": 5.6652173913043484e-05,
|
| 2276 |
-
"loss": 0.1491,
|
| 2277 |
-
"step": 3300
|
| 2278 |
-
},
|
| 2279 |
-
{
|
| 2280 |
-
"epoch": 35.87,
|
| 2281 |
-
"eval_accuracy": 0.9846153846153847,
|
| 2282 |
-
"eval_loss": 0.09560323506593704,
|
| 2283 |
-
"eval_runtime": 1.8328,
|
| 2284 |
-
"eval_samples_per_second": 141.861,
|
| 2285 |
-
"eval_steps_per_second": 18.005,
|
| 2286 |
-
"step": 3300
|
| 2287 |
-
},
|
| 2288 |
-
{
|
| 2289 |
-
"epoch": 35.98,
|
| 2290 |
-
"learning_rate": 5.621739130434783e-05,
|
| 2291 |
-
"loss": 0.1288,
|
| 2292 |
-
"step": 3310
|
| 2293 |
-
},
|
| 2294 |
-
{
|
| 2295 |
-
"epoch": 36.09,
|
| 2296 |
-
"learning_rate": 5.578260869565217e-05,
|
| 2297 |
-
"loss": 0.2158,
|
| 2298 |
-
"step": 3320
|
| 2299 |
-
},
|
| 2300 |
-
{
|
| 2301 |
-
"epoch": 36.2,
|
| 2302 |
-
"learning_rate": 5.534782608695652e-05,
|
| 2303 |
-
"loss": 0.2777,
|
| 2304 |
-
"step": 3330
|
| 2305 |
-
},
|
| 2306 |
-
{
|
| 2307 |
-
"epoch": 36.3,
|
| 2308 |
-
"learning_rate": 5.495652173913044e-05,
|
| 2309 |
-
"loss": 0.1669,
|
| 2310 |
-
"step": 3340
|
| 2311 |
-
},
|
| 2312 |
-
{
|
| 2313 |
-
"epoch": 36.41,
|
| 2314 |
-
"learning_rate": 5.452173913043479e-05,
|
| 2315 |
-
"loss": 0.1559,
|
| 2316 |
-
"step": 3350
|
| 2317 |
-
},
|
| 2318 |
-
{
|
| 2319 |
-
"epoch": 36.52,
|
| 2320 |
-
"learning_rate": 5.408695652173913e-05,
|
| 2321 |
-
"loss": 0.3045,
|
| 2322 |
-
"step": 3360
|
| 2323 |
-
},
|
| 2324 |
-
{
|
| 2325 |
-
"epoch": 36.63,
|
| 2326 |
-
"learning_rate": 5.365217391304348e-05,
|
| 2327 |
-
"loss": 0.1495,
|
| 2328 |
-
"step": 3370
|
| 2329 |
-
},
|
| 2330 |
-
{
|
| 2331 |
-
"epoch": 36.74,
|
| 2332 |
-
"learning_rate": 5.321739130434783e-05,
|
| 2333 |
-
"loss": 0.0966,
|
| 2334 |
-
"step": 3380
|
| 2335 |
-
},
|
| 2336 |
-
{
|
| 2337 |
-
"epoch": 36.85,
|
| 2338 |
-
"learning_rate": 5.278260869565218e-05,
|
| 2339 |
-
"loss": 0.1606,
|
| 2340 |
-
"step": 3390
|
| 2341 |
-
},
|
| 2342 |
-
{
|
| 2343 |
-
"epoch": 36.96,
|
| 2344 |
-
"learning_rate": 5.234782608695652e-05,
|
| 2345 |
-
"loss": 0.1866,
|
| 2346 |
-
"step": 3400
|
| 2347 |
-
},
|
| 2348 |
-
{
|
| 2349 |
-
"epoch": 36.96,
|
| 2350 |
-
"eval_accuracy": 0.9846153846153847,
|
| 2351 |
-
"eval_loss": 0.11623835563659668,
|
| 2352 |
-
"eval_runtime": 1.8358,
|
| 2353 |
-
"eval_samples_per_second": 141.631,
|
| 2354 |
-
"eval_steps_per_second": 17.976,
|
| 2355 |
-
"step": 3400
|
| 2356 |
-
},
|
| 2357 |
-
{
|
| 2358 |
-
"epoch": 37.07,
|
| 2359 |
-
"learning_rate": 5.191304347826087e-05,
|
| 2360 |
-
"loss": 0.1166,
|
| 2361 |
-
"step": 3410
|
| 2362 |
-
},
|
| 2363 |
-
{
|
| 2364 |
-
"epoch": 37.17,
|
| 2365 |
-
"learning_rate": 5.147826086956522e-05,
|
| 2366 |
-
"loss": 0.1632,
|
| 2367 |
-
"step": 3420
|
| 2368 |
-
},
|
| 2369 |
-
{
|
| 2370 |
-
"epoch": 37.28,
|
| 2371 |
-
"learning_rate": 5.104347826086957e-05,
|
| 2372 |
-
"loss": 0.3038,
|
| 2373 |
-
"step": 3430
|
| 2374 |
-
},
|
| 2375 |
-
{
|
| 2376 |
-
"epoch": 37.39,
|
| 2377 |
-
"learning_rate": 5.060869565217392e-05,
|
| 2378 |
-
"loss": 0.1259,
|
| 2379 |
-
"step": 3440
|
| 2380 |
-
},
|
| 2381 |
-
{
|
| 2382 |
-
"epoch": 37.5,
|
| 2383 |
-
"learning_rate": 5.017391304347826e-05,
|
| 2384 |
-
"loss": 0.1906,
|
| 2385 |
-
"step": 3450
|
| 2386 |
-
},
|
| 2387 |
-
{
|
| 2388 |
-
"epoch": 37.61,
|
| 2389 |
-
"learning_rate": 4.973913043478261e-05,
|
| 2390 |
-
"loss": 0.1809,
|
| 2391 |
-
"step": 3460
|
| 2392 |
-
},
|
| 2393 |
-
{
|
| 2394 |
-
"epoch": 37.72,
|
| 2395 |
-
"learning_rate": 4.930434782608696e-05,
|
| 2396 |
-
"loss": 0.1133,
|
| 2397 |
-
"step": 3470
|
| 2398 |
-
},
|
| 2399 |
-
{
|
| 2400 |
-
"epoch": 37.83,
|
| 2401 |
-
"learning_rate": 4.8869565217391305e-05,
|
| 2402 |
-
"loss": 0.2476,
|
| 2403 |
-
"step": 3480
|
| 2404 |
-
},
|
| 2405 |
-
{
|
| 2406 |
-
"epoch": 37.93,
|
| 2407 |
-
"learning_rate": 4.843478260869565e-05,
|
| 2408 |
-
"loss": 0.2042,
|
| 2409 |
-
"step": 3490
|
| 2410 |
-
},
|
| 2411 |
-
{
|
| 2412 |
-
"epoch": 38.04,
|
| 2413 |
-
"learning_rate": 4.8e-05,
|
| 2414 |
-
"loss": 0.1269,
|
| 2415 |
-
"step": 3500
|
| 2416 |
-
},
|
| 2417 |
-
{
|
| 2418 |
-
"epoch": 38.04,
|
| 2419 |
-
"eval_accuracy": 0.9769230769230769,
|
| 2420 |
-
"eval_loss": 0.13658243417739868,
|
| 2421 |
-
"eval_runtime": 1.8465,
|
| 2422 |
-
"eval_samples_per_second": 140.804,
|
| 2423 |
-
"eval_steps_per_second": 17.871,
|
| 2424 |
-
"step": 3500
|
| 2425 |
-
},
|
| 2426 |
-
{
|
| 2427 |
-
"epoch": 38.15,
|
| 2428 |
-
"learning_rate": 4.756521739130435e-05,
|
| 2429 |
-
"loss": 0.244,
|
| 2430 |
-
"step": 3510
|
| 2431 |
-
},
|
| 2432 |
-
{
|
| 2433 |
-
"epoch": 38.26,
|
| 2434 |
-
"learning_rate": 4.71304347826087e-05,
|
| 2435 |
-
"loss": 0.1274,
|
| 2436 |
-
"step": 3520
|
| 2437 |
-
},
|
| 2438 |
-
{
|
| 2439 |
-
"epoch": 38.37,
|
| 2440 |
-
"learning_rate": 4.6695652173913045e-05,
|
| 2441 |
-
"loss": 0.175,
|
| 2442 |
-
"step": 3530
|
| 2443 |
-
},
|
| 2444 |
-
{
|
| 2445 |
-
"epoch": 38.48,
|
| 2446 |
-
"learning_rate": 4.62608695652174e-05,
|
| 2447 |
-
"loss": 0.2629,
|
| 2448 |
-
"step": 3540
|
| 2449 |
-
},
|
| 2450 |
-
{
|
| 2451 |
-
"epoch": 38.59,
|
| 2452 |
-
"learning_rate": 4.582608695652174e-05,
|
| 2453 |
-
"loss": 0.1863,
|
| 2454 |
-
"step": 3550
|
| 2455 |
-
},
|
| 2456 |
-
{
|
| 2457 |
-
"epoch": 38.7,
|
| 2458 |
-
"learning_rate": 4.539130434782609e-05,
|
| 2459 |
-
"loss": 0.1337,
|
| 2460 |
-
"step": 3560
|
| 2461 |
-
},
|
| 2462 |
-
{
|
| 2463 |
-
"epoch": 38.8,
|
| 2464 |
-
"learning_rate": 4.4956521739130436e-05,
|
| 2465 |
-
"loss": 0.1694,
|
| 2466 |
-
"step": 3570
|
| 2467 |
-
},
|
| 2468 |
-
{
|
| 2469 |
-
"epoch": 38.91,
|
| 2470 |
-
"learning_rate": 4.4521739130434784e-05,
|
| 2471 |
-
"loss": 0.1895,
|
| 2472 |
-
"step": 3580
|
| 2473 |
-
},
|
| 2474 |
-
{
|
| 2475 |
-
"epoch": 39.02,
|
| 2476 |
-
"learning_rate": 4.408695652173913e-05,
|
| 2477 |
-
"loss": 0.1817,
|
| 2478 |
-
"step": 3590
|
| 2479 |
-
},
|
| 2480 |
-
{
|
| 2481 |
-
"epoch": 39.13,
|
| 2482 |
-
"learning_rate": 4.365217391304348e-05,
|
| 2483 |
-
"loss": 0.1498,
|
| 2484 |
-
"step": 3600
|
| 2485 |
-
},
|
| 2486 |
-
{
|
| 2487 |
-
"epoch": 39.13,
|
| 2488 |
-
"eval_accuracy": 0.9884615384615385,
|
| 2489 |
-
"eval_loss": 0.12455728650093079,
|
| 2490 |
-
"eval_runtime": 1.8064,
|
| 2491 |
-
"eval_samples_per_second": 143.932,
|
| 2492 |
-
"eval_steps_per_second": 18.268,
|
| 2493 |
-
"step": 3600
|
| 2494 |
-
},
|
| 2495 |
-
{
|
| 2496 |
-
"epoch": 39.24,
|
| 2497 |
-
"learning_rate": 4.321739130434783e-05,
|
| 2498 |
-
"loss": 0.1889,
|
| 2499 |
-
"step": 3610
|
| 2500 |
-
},
|
| 2501 |
-
{
|
| 2502 |
-
"epoch": 39.35,
|
| 2503 |
-
"learning_rate": 4.2782608695652176e-05,
|
| 2504 |
-
"loss": 0.2648,
|
| 2505 |
-
"step": 3620
|
| 2506 |
-
},
|
| 2507 |
-
{
|
| 2508 |
-
"epoch": 39.46,
|
| 2509 |
-
"learning_rate": 4.2347826086956523e-05,
|
| 2510 |
-
"loss": 0.1157,
|
| 2511 |
-
"step": 3630
|
| 2512 |
-
},
|
| 2513 |
-
{
|
| 2514 |
-
"epoch": 39.57,
|
| 2515 |
-
"learning_rate": 4.191304347826087e-05,
|
| 2516 |
-
"loss": 0.2186,
|
| 2517 |
-
"step": 3640
|
| 2518 |
-
},
|
| 2519 |
-
{
|
| 2520 |
-
"epoch": 39.67,
|
| 2521 |
-
"learning_rate": 4.147826086956522e-05,
|
| 2522 |
-
"loss": 0.1046,
|
| 2523 |
-
"step": 3650
|
| 2524 |
-
},
|
| 2525 |
-
{
|
| 2526 |
-
"epoch": 39.78,
|
| 2527 |
-
"learning_rate": 4.104347826086957e-05,
|
| 2528 |
-
"loss": 0.0709,
|
| 2529 |
-
"step": 3660
|
| 2530 |
-
},
|
| 2531 |
-
{
|
| 2532 |
-
"epoch": 39.89,
|
| 2533 |
-
"learning_rate": 4.0608695652173915e-05,
|
| 2534 |
-
"loss": 0.1139,
|
| 2535 |
-
"step": 3670
|
| 2536 |
-
},
|
| 2537 |
-
{
|
| 2538 |
-
"epoch": 40.0,
|
| 2539 |
-
"learning_rate": 4.017391304347826e-05,
|
| 2540 |
-
"loss": 0.114,
|
| 2541 |
-
"step": 3680
|
| 2542 |
-
},
|
| 2543 |
-
{
|
| 2544 |
-
"epoch": 40.11,
|
| 2545 |
-
"learning_rate": 3.973913043478261e-05,
|
| 2546 |
-
"loss": 0.2728,
|
| 2547 |
-
"step": 3690
|
| 2548 |
-
},
|
| 2549 |
-
{
|
| 2550 |
-
"epoch": 40.22,
|
| 2551 |
-
"learning_rate": 3.930434782608696e-05,
|
| 2552 |
-
"loss": 0.1981,
|
| 2553 |
-
"step": 3700
|
| 2554 |
-
},
|
| 2555 |
-
{
|
| 2556 |
-
"epoch": 40.22,
|
| 2557 |
-
"eval_accuracy": 0.9807692307692307,
|
| 2558 |
-
"eval_loss": 0.09199390560388565,
|
| 2559 |
-
"eval_runtime": 1.826,
|
| 2560 |
-
"eval_samples_per_second": 142.387,
|
| 2561 |
-
"eval_steps_per_second": 18.072,
|
| 2562 |
-
"step": 3700
|
| 2563 |
-
},
|
| 2564 |
-
{
|
| 2565 |
-
"epoch": 40.33,
|
| 2566 |
-
"learning_rate": 3.8869565217391306e-05,
|
| 2567 |
-
"loss": 0.2243,
|
| 2568 |
-
"step": 3710
|
| 2569 |
-
},
|
| 2570 |
-
{
|
| 2571 |
-
"epoch": 40.43,
|
| 2572 |
-
"learning_rate": 3.8434782608695654e-05,
|
| 2573 |
-
"loss": 0.1076,
|
| 2574 |
-
"step": 3720
|
| 2575 |
-
},
|
| 2576 |
-
{
|
| 2577 |
-
"epoch": 40.54,
|
| 2578 |
-
"learning_rate": 3.8e-05,
|
| 2579 |
-
"loss": 0.1188,
|
| 2580 |
-
"step": 3730
|
| 2581 |
-
},
|
| 2582 |
-
{
|
| 2583 |
-
"epoch": 40.65,
|
| 2584 |
-
"learning_rate": 3.756521739130435e-05,
|
| 2585 |
-
"loss": 0.1285,
|
| 2586 |
-
"step": 3740
|
| 2587 |
-
},
|
| 2588 |
-
{
|
| 2589 |
-
"epoch": 40.76,
|
| 2590 |
-
"learning_rate": 3.71304347826087e-05,
|
| 2591 |
-
"loss": 0.1592,
|
| 2592 |
-
"step": 3750
|
| 2593 |
-
},
|
| 2594 |
-
{
|
| 2595 |
-
"epoch": 40.87,
|
| 2596 |
-
"learning_rate": 3.6695652173913046e-05,
|
| 2597 |
-
"loss": 0.0863,
|
| 2598 |
-
"step": 3760
|
| 2599 |
-
},
|
| 2600 |
-
{
|
| 2601 |
-
"epoch": 40.98,
|
| 2602 |
-
"learning_rate": 3.6260869565217394e-05,
|
| 2603 |
-
"loss": 0.1847,
|
| 2604 |
-
"step": 3770
|
| 2605 |
-
},
|
| 2606 |
-
{
|
| 2607 |
-
"epoch": 41.09,
|
| 2608 |
-
"learning_rate": 3.582608695652174e-05,
|
| 2609 |
-
"loss": 0.1492,
|
| 2610 |
-
"step": 3780
|
| 2611 |
-
},
|
| 2612 |
-
{
|
| 2613 |
-
"epoch": 41.2,
|
| 2614 |
-
"learning_rate": 3.539130434782609e-05,
|
| 2615 |
-
"loss": 0.2077,
|
| 2616 |
-
"step": 3790
|
| 2617 |
-
},
|
| 2618 |
-
{
|
| 2619 |
-
"epoch": 41.3,
|
| 2620 |
-
"learning_rate": 3.495652173913044e-05,
|
| 2621 |
-
"loss": 0.1421,
|
| 2622 |
-
"step": 3800
|
| 2623 |
-
},
|
| 2624 |
-
{
|
| 2625 |
-
"epoch": 41.3,
|
| 2626 |
-
"eval_accuracy": 0.9807692307692307,
|
| 2627 |
-
"eval_loss": 0.09830256551504135,
|
| 2628 |
-
"eval_runtime": 1.8855,
|
| 2629 |
-
"eval_samples_per_second": 137.894,
|
| 2630 |
-
"eval_steps_per_second": 17.502,
|
| 2631 |
-
"step": 3800
|
| 2632 |
-
},
|
| 2633 |
-
{
|
| 2634 |
-
"epoch": 41.41,
|
| 2635 |
-
"learning_rate": 3.4521739130434785e-05,
|
| 2636 |
-
"loss": 0.1659,
|
| 2637 |
-
"step": 3810
|
| 2638 |
-
},
|
| 2639 |
-
{
|
| 2640 |
-
"epoch": 41.52,
|
| 2641 |
-
"learning_rate": 3.408695652173913e-05,
|
| 2642 |
-
"loss": 0.1637,
|
| 2643 |
-
"step": 3820
|
| 2644 |
-
},
|
| 2645 |
-
{
|
| 2646 |
-
"epoch": 41.63,
|
| 2647 |
-
"learning_rate": 3.365217391304348e-05,
|
| 2648 |
-
"loss": 0.1876,
|
| 2649 |
-
"step": 3830
|
| 2650 |
-
},
|
| 2651 |
-
{
|
| 2652 |
-
"epoch": 41.74,
|
| 2653 |
-
"learning_rate": 3.321739130434783e-05,
|
| 2654 |
-
"loss": 0.2014,
|
| 2655 |
-
"step": 3840
|
| 2656 |
-
},
|
| 2657 |
-
{
|
| 2658 |
-
"epoch": 41.85,
|
| 2659 |
-
"learning_rate": 3.278260869565217e-05,
|
| 2660 |
-
"loss": 0.2616,
|
| 2661 |
-
"step": 3850
|
| 2662 |
-
},
|
| 2663 |
-
{
|
| 2664 |
-
"epoch": 41.96,
|
| 2665 |
-
"learning_rate": 3.2347826086956524e-05,
|
| 2666 |
-
"loss": 0.2388,
|
| 2667 |
-
"step": 3860
|
| 2668 |
-
},
|
| 2669 |
-
{
|
| 2670 |
-
"epoch": 42.07,
|
| 2671 |
-
"learning_rate": 3.191304347826087e-05,
|
| 2672 |
-
"loss": 0.1195,
|
| 2673 |
-
"step": 3870
|
| 2674 |
-
},
|
| 2675 |
-
{
|
| 2676 |
-
"epoch": 42.17,
|
| 2677 |
-
"learning_rate": 3.147826086956522e-05,
|
| 2678 |
-
"loss": 0.0911,
|
| 2679 |
-
"step": 3880
|
| 2680 |
-
},
|
| 2681 |
-
{
|
| 2682 |
-
"epoch": 42.28,
|
| 2683 |
-
"learning_rate": 3.104347826086957e-05,
|
| 2684 |
-
"loss": 0.1069,
|
| 2685 |
-
"step": 3890
|
| 2686 |
-
},
|
| 2687 |
-
{
|
| 2688 |
-
"epoch": 42.39,
|
| 2689 |
-
"learning_rate": 3.0608695652173916e-05,
|
| 2690 |
-
"loss": 0.1936,
|
| 2691 |
-
"step": 3900
|
| 2692 |
-
},
|
| 2693 |
-
{
|
| 2694 |
-
"epoch": 42.39,
|
| 2695 |
-
"eval_accuracy": 0.9769230769230769,
|
| 2696 |
-
"eval_loss": 0.11225084215402603,
|
| 2697 |
-
"eval_runtime": 1.8302,
|
| 2698 |
-
"eval_samples_per_second": 142.059,
|
| 2699 |
-
"eval_steps_per_second": 18.031,
|
| 2700 |
-
"step": 3900
|
| 2701 |
-
},
|
| 2702 |
-
{
|
| 2703 |
-
"epoch": 42.5,
|
| 2704 |
-
"learning_rate": 3.0173913043478264e-05,
|
| 2705 |
-
"loss": 0.1685,
|
| 2706 |
-
"step": 3910
|
| 2707 |
-
},
|
| 2708 |
-
{
|
| 2709 |
-
"epoch": 42.61,
|
| 2710 |
-
"learning_rate": 2.9739130434782608e-05,
|
| 2711 |
-
"loss": 0.0714,
|
| 2712 |
-
"step": 3920
|
| 2713 |
-
},
|
| 2714 |
-
{
|
| 2715 |
-
"epoch": 42.72,
|
| 2716 |
-
"learning_rate": 2.930434782608696e-05,
|
| 2717 |
-
"loss": 0.1757,
|
| 2718 |
-
"step": 3930
|
| 2719 |
-
},
|
| 2720 |
-
{
|
| 2721 |
-
"epoch": 42.83,
|
| 2722 |
-
"learning_rate": 2.8869565217391304e-05,
|
| 2723 |
-
"loss": 0.1768,
|
| 2724 |
-
"step": 3940
|
| 2725 |
-
},
|
| 2726 |
-
{
|
| 2727 |
-
"epoch": 42.93,
|
| 2728 |
-
"learning_rate": 2.8434782608695655e-05,
|
| 2729 |
-
"loss": 0.1389,
|
| 2730 |
-
"step": 3950
|
| 2731 |
-
},
|
| 2732 |
-
{
|
| 2733 |
-
"epoch": 43.04,
|
| 2734 |
-
"learning_rate": 2.8000000000000003e-05,
|
| 2735 |
-
"loss": 0.1236,
|
| 2736 |
-
"step": 3960
|
| 2737 |
-
},
|
| 2738 |
-
{
|
| 2739 |
-
"epoch": 43.15,
|
| 2740 |
-
"learning_rate": 2.7565217391304347e-05,
|
| 2741 |
-
"loss": 0.1475,
|
| 2742 |
-
"step": 3970
|
| 2743 |
-
},
|
| 2744 |
-
{
|
| 2745 |
-
"epoch": 43.26,
|
| 2746 |
-
"learning_rate": 2.71304347826087e-05,
|
| 2747 |
-
"loss": 0.0922,
|
| 2748 |
-
"step": 3980
|
| 2749 |
-
},
|
| 2750 |
-
{
|
| 2751 |
-
"epoch": 43.37,
|
| 2752 |
-
"learning_rate": 2.6695652173913043e-05,
|
| 2753 |
-
"loss": 0.1054,
|
| 2754 |
-
"step": 3990
|
| 2755 |
-
},
|
| 2756 |
-
{
|
| 2757 |
-
"epoch": 43.48,
|
| 2758 |
-
"learning_rate": 2.6260869565217394e-05,
|
| 2759 |
-
"loss": 0.097,
|
| 2760 |
-
"step": 4000
|
| 2761 |
-
},
|
| 2762 |
-
{
|
| 2763 |
-
"epoch": 43.48,
|
| 2764 |
-
"eval_accuracy": 0.9769230769230769,
|
| 2765 |
-
"eval_loss": 0.15064960718154907,
|
| 2766 |
-
"eval_runtime": 1.9877,
|
| 2767 |
-
"eval_samples_per_second": 130.807,
|
| 2768 |
-
"eval_steps_per_second": 16.602,
|
| 2769 |
-
"step": 4000
|
| 2770 |
-
},
|
| 2771 |
-
{
|
| 2772 |
-
"epoch": 43.59,
|
| 2773 |
-
"learning_rate": 2.582608695652174e-05,
|
| 2774 |
-
"loss": 0.1154,
|
| 2775 |
-
"step": 4010
|
| 2776 |
-
},
|
| 2777 |
-
{
|
| 2778 |
-
"epoch": 43.7,
|
| 2779 |
-
"learning_rate": 2.539130434782609e-05,
|
| 2780 |
-
"loss": 0.1719,
|
| 2781 |
-
"step": 4020
|
| 2782 |
-
},
|
| 2783 |
-
{
|
| 2784 |
-
"epoch": 43.8,
|
| 2785 |
-
"learning_rate": 2.4956521739130438e-05,
|
| 2786 |
-
"loss": 0.0627,
|
| 2787 |
-
"step": 4030
|
| 2788 |
-
},
|
| 2789 |
-
{
|
| 2790 |
-
"epoch": 43.91,
|
| 2791 |
-
"learning_rate": 2.4521739130434786e-05,
|
| 2792 |
-
"loss": 0.1385,
|
| 2793 |
-
"step": 4040
|
| 2794 |
-
},
|
| 2795 |
-
{
|
| 2796 |
-
"epoch": 44.02,
|
| 2797 |
-
"learning_rate": 2.408695652173913e-05,
|
| 2798 |
-
"loss": 0.1673,
|
| 2799 |
-
"step": 4050
|
| 2800 |
-
},
|
| 2801 |
-
{
|
| 2802 |
-
"epoch": 44.13,
|
| 2803 |
-
"learning_rate": 2.3652173913043478e-05,
|
| 2804 |
-
"loss": 0.1678,
|
| 2805 |
-
"step": 4060
|
| 2806 |
-
},
|
| 2807 |
-
{
|
| 2808 |
-
"epoch": 44.24,
|
| 2809 |
-
"learning_rate": 2.3217391304347826e-05,
|
| 2810 |
-
"loss": 0.1634,
|
| 2811 |
-
"step": 4070
|
| 2812 |
-
},
|
| 2813 |
-
{
|
| 2814 |
-
"epoch": 44.35,
|
| 2815 |
-
"learning_rate": 2.2782608695652174e-05,
|
| 2816 |
-
"loss": 0.0712,
|
| 2817 |
-
"step": 4080
|
| 2818 |
-
},
|
| 2819 |
-
{
|
| 2820 |
-
"epoch": 44.46,
|
| 2821 |
-
"learning_rate": 2.2347826086956522e-05,
|
| 2822 |
-
"loss": 0.1366,
|
| 2823 |
-
"step": 4090
|
| 2824 |
-
},
|
| 2825 |
-
{
|
| 2826 |
-
"epoch": 44.57,
|
| 2827 |
-
"learning_rate": 2.191304347826087e-05,
|
| 2828 |
-
"loss": 0.0791,
|
| 2829 |
-
"step": 4100
|
| 2830 |
-
},
|
| 2831 |
-
{
|
| 2832 |
-
"epoch": 44.57,
|
| 2833 |
-
"eval_accuracy": 0.9769230769230769,
|
| 2834 |
-
"eval_loss": 0.14431653916835785,
|
| 2835 |
-
"eval_runtime": 1.8767,
|
| 2836 |
-
"eval_samples_per_second": 138.543,
|
| 2837 |
-
"eval_steps_per_second": 17.584,
|
| 2838 |
-
"step": 4100
|
| 2839 |
-
},
|
| 2840 |
-
{
|
| 2841 |
-
"epoch": 44.67,
|
| 2842 |
-
"learning_rate": 2.1478260869565218e-05,
|
| 2843 |
-
"loss": 0.0557,
|
| 2844 |
-
"step": 4110
|
| 2845 |
-
},
|
| 2846 |
-
{
|
| 2847 |
-
"epoch": 44.78,
|
| 2848 |
-
"learning_rate": 2.104347826086957e-05,
|
| 2849 |
-
"loss": 0.1431,
|
| 2850 |
-
"step": 4120
|
| 2851 |
-
},
|
| 2852 |
-
{
|
| 2853 |
-
"epoch": 44.89,
|
| 2854 |
-
"learning_rate": 2.0608695652173913e-05,
|
| 2855 |
-
"loss": 0.1888,
|
| 2856 |
-
"step": 4130
|
| 2857 |
-
},
|
| 2858 |
-
{
|
| 2859 |
-
"epoch": 45.0,
|
| 2860 |
-
"learning_rate": 2.017391304347826e-05,
|
| 2861 |
-
"loss": 0.0463,
|
| 2862 |
-
"step": 4140
|
| 2863 |
-
},
|
| 2864 |
-
{
|
| 2865 |
-
"epoch": 45.11,
|
| 2866 |
-
"learning_rate": 1.973913043478261e-05,
|
| 2867 |
-
"loss": 0.1608,
|
| 2868 |
-
"step": 4150
|
| 2869 |
-
},
|
| 2870 |
-
{
|
| 2871 |
-
"epoch": 45.22,
|
| 2872 |
-
"learning_rate": 1.9304347826086957e-05,
|
| 2873 |
-
"loss": 0.1379,
|
| 2874 |
-
"step": 4160
|
| 2875 |
-
},
|
| 2876 |
-
{
|
| 2877 |
-
"epoch": 45.33,
|
| 2878 |
-
"learning_rate": 1.8869565217391305e-05,
|
| 2879 |
-
"loss": 0.2226,
|
| 2880 |
-
"step": 4170
|
| 2881 |
-
},
|
| 2882 |
-
{
|
| 2883 |
-
"epoch": 45.43,
|
| 2884 |
-
"learning_rate": 1.8434782608695653e-05,
|
| 2885 |
-
"loss": 0.1258,
|
| 2886 |
-
"step": 4180
|
| 2887 |
-
},
|
| 2888 |
-
{
|
| 2889 |
-
"epoch": 45.54,
|
| 2890 |
-
"learning_rate": 1.8e-05,
|
| 2891 |
-
"loss": 0.1235,
|
| 2892 |
-
"step": 4190
|
| 2893 |
-
},
|
| 2894 |
-
{
|
| 2895 |
-
"epoch": 45.65,
|
| 2896 |
-
"learning_rate": 1.756521739130435e-05,
|
| 2897 |
-
"loss": 0.0935,
|
| 2898 |
-
"step": 4200
|
| 2899 |
-
},
|
| 2900 |
-
{
|
| 2901 |
-
"epoch": 45.65,
|
| 2902 |
-
"eval_accuracy": 0.9807692307692307,
|
| 2903 |
-
"eval_loss": 0.1689443737268448,
|
| 2904 |
-
"eval_runtime": 2.3394,
|
| 2905 |
-
"eval_samples_per_second": 111.142,
|
| 2906 |
-
"eval_steps_per_second": 14.106,
|
| 2907 |
-
"step": 4200
|
| 2908 |
-
},
|
| 2909 |
-
{
|
| 2910 |
-
"epoch": 45.76,
|
| 2911 |
-
"learning_rate": 1.7130434782608696e-05,
|
| 2912 |
-
"loss": 0.0753,
|
| 2913 |
-
"step": 4210
|
| 2914 |
-
},
|
| 2915 |
-
{
|
| 2916 |
-
"epoch": 45.87,
|
| 2917 |
-
"learning_rate": 1.6695652173913044e-05,
|
| 2918 |
-
"loss": 0.1414,
|
| 2919 |
-
"step": 4220
|
| 2920 |
-
},
|
| 2921 |
-
{
|
| 2922 |
-
"epoch": 45.98,
|
| 2923 |
-
"learning_rate": 1.6260869565217392e-05,
|
| 2924 |
-
"loss": 0.131,
|
| 2925 |
-
"step": 4230
|
| 2926 |
-
},
|
| 2927 |
-
{
|
| 2928 |
-
"epoch": 46.09,
|
| 2929 |
-
"learning_rate": 1.582608695652174e-05,
|
| 2930 |
-
"loss": 0.2012,
|
| 2931 |
-
"step": 4240
|
| 2932 |
-
},
|
| 2933 |
-
{
|
| 2934 |
-
"epoch": 46.2,
|
| 2935 |
-
"learning_rate": 1.5434782608695654e-05,
|
| 2936 |
-
"loss": 0.1882,
|
| 2937 |
-
"step": 4250
|
| 2938 |
-
},
|
| 2939 |
-
{
|
| 2940 |
-
"epoch": 46.3,
|
| 2941 |
-
"learning_rate": 1.5e-05,
|
| 2942 |
-
"loss": 0.1026,
|
| 2943 |
-
"step": 4260
|
| 2944 |
-
},
|
| 2945 |
-
{
|
| 2946 |
-
"epoch": 46.41,
|
| 2947 |
-
"learning_rate": 1.4565217391304348e-05,
|
| 2948 |
-
"loss": 0.0967,
|
| 2949 |
-
"step": 4270
|
| 2950 |
-
},
|
| 2951 |
-
{
|
| 2952 |
-
"epoch": 46.52,
|
| 2953 |
-
"learning_rate": 1.4130434782608694e-05,
|
| 2954 |
-
"loss": 0.2006,
|
| 2955 |
-
"step": 4280
|
| 2956 |
-
},
|
| 2957 |
-
{
|
| 2958 |
-
"epoch": 46.63,
|
| 2959 |
-
"learning_rate": 1.3695652173913042e-05,
|
| 2960 |
-
"loss": 0.1477,
|
| 2961 |
-
"step": 4290
|
| 2962 |
-
},
|
| 2963 |
-
{
|
| 2964 |
-
"epoch": 46.74,
|
| 2965 |
-
"learning_rate": 1.3260869565217394e-05,
|
| 2966 |
-
"loss": 0.1061,
|
| 2967 |
-
"step": 4300
|
| 2968 |
-
},
|
| 2969 |
-
{
|
| 2970 |
-
"epoch": 46.74,
|
| 2971 |
-
"eval_accuracy": 0.9807692307692307,
|
| 2972 |
-
"eval_loss": 0.13794825971126556,
|
| 2973 |
-
"eval_runtime": 1.8376,
|
| 2974 |
-
"eval_samples_per_second": 141.486,
|
| 2975 |
-
"eval_steps_per_second": 17.958,
|
| 2976 |
-
"step": 4300
|
| 2977 |
-
},
|
| 2978 |
-
{
|
| 2979 |
-
"epoch": 46.85,
|
| 2980 |
-
"learning_rate": 1.2826086956521741e-05,
|
| 2981 |
-
"loss": 0.1748,
|
| 2982 |
-
"step": 4310
|
| 2983 |
-
},
|
| 2984 |
-
{
|
| 2985 |
-
"epoch": 46.96,
|
| 2986 |
-
"learning_rate": 1.2391304347826088e-05,
|
| 2987 |
-
"loss": 0.0196,
|
| 2988 |
-
"step": 4320
|
| 2989 |
-
},
|
| 2990 |
-
{
|
| 2991 |
-
"epoch": 47.07,
|
| 2992 |
-
"learning_rate": 1.1956521739130435e-05,
|
| 2993 |
-
"loss": 0.076,
|
| 2994 |
-
"step": 4330
|
| 2995 |
-
},
|
| 2996 |
-
{
|
| 2997 |
-
"epoch": 47.17,
|
| 2998 |
-
"learning_rate": 1.1521739130434783e-05,
|
| 2999 |
-
"loss": 0.1635,
|
| 3000 |
-
"step": 4340
|
| 3001 |
-
},
|
| 3002 |
-
{
|
| 3003 |
-
"epoch": 47.28,
|
| 3004 |
-
"learning_rate": 1.1086956521739131e-05,
|
| 3005 |
-
"loss": 0.1393,
|
| 3006 |
-
"step": 4350
|
| 3007 |
-
},
|
| 3008 |
-
{
|
| 3009 |
-
"epoch": 47.39,
|
| 3010 |
-
"learning_rate": 1.0652173913043479e-05,
|
| 3011 |
-
"loss": 0.0914,
|
| 3012 |
-
"step": 4360
|
| 3013 |
-
},
|
| 3014 |
-
{
|
| 3015 |
-
"epoch": 47.5,
|
| 3016 |
-
"learning_rate": 1.0217391304347827e-05,
|
| 3017 |
-
"loss": 0.0768,
|
| 3018 |
-
"step": 4370
|
| 3019 |
-
},
|
| 3020 |
-
{
|
| 3021 |
-
"epoch": 47.61,
|
| 3022 |
-
"learning_rate": 9.782608695652175e-06,
|
| 3023 |
-
"loss": 0.1176,
|
| 3024 |
-
"step": 4380
|
| 3025 |
-
},
|
| 3026 |
-
{
|
| 3027 |
-
"epoch": 47.72,
|
| 3028 |
-
"learning_rate": 9.347826086956523e-06,
|
| 3029 |
-
"loss": 0.0986,
|
| 3030 |
-
"step": 4390
|
| 3031 |
-
},
|
| 3032 |
-
{
|
| 3033 |
-
"epoch": 47.83,
|
| 3034 |
-
"learning_rate": 8.91304347826087e-06,
|
| 3035 |
-
"loss": 0.2041,
|
| 3036 |
-
"step": 4400
|
| 3037 |
-
},
|
| 3038 |
-
{
|
| 3039 |
-
"epoch": 47.83,
|
| 3040 |
-
"eval_accuracy": 0.9769230769230769,
|
| 3041 |
-
"eval_loss": 0.1391335427761078,
|
| 3042 |
-
"eval_runtime": 2.4421,
|
| 3043 |
-
"eval_samples_per_second": 106.467,
|
| 3044 |
-
"eval_steps_per_second": 13.513,
|
| 3045 |
-
"step": 4400
|
| 3046 |
-
},
|
| 3047 |
-
{
|
| 3048 |
-
"epoch": 47.93,
|
| 3049 |
-
"learning_rate": 8.478260869565217e-06,
|
| 3050 |
-
"loss": 0.0854,
|
| 3051 |
-
"step": 4410
|
| 3052 |
-
},
|
| 3053 |
-
{
|
| 3054 |
-
"epoch": 48.04,
|
| 3055 |
-
"learning_rate": 8.043478260869565e-06,
|
| 3056 |
-
"loss": 0.1058,
|
| 3057 |
-
"step": 4420
|
| 3058 |
-
},
|
| 3059 |
-
{
|
| 3060 |
-
"epoch": 48.15,
|
| 3061 |
-
"learning_rate": 7.608695652173914e-06,
|
| 3062 |
-
"loss": 0.1268,
|
| 3063 |
-
"step": 4430
|
| 3064 |
-
},
|
| 3065 |
-
{
|
| 3066 |
-
"epoch": 48.26,
|
| 3067 |
-
"learning_rate": 7.173913043478261e-06,
|
| 3068 |
-
"loss": 0.0727,
|
| 3069 |
-
"step": 4440
|
| 3070 |
-
},
|
| 3071 |
-
{
|
| 3072 |
-
"epoch": 48.37,
|
| 3073 |
-
"learning_rate": 6.739130434782609e-06,
|
| 3074 |
-
"loss": 0.0944,
|
| 3075 |
-
"step": 4450
|
| 3076 |
-
},
|
| 3077 |
-
{
|
| 3078 |
-
"epoch": 48.48,
|
| 3079 |
-
"learning_rate": 6.304347826086957e-06,
|
| 3080 |
-
"loss": 0.1517,
|
| 3081 |
-
"step": 4460
|
| 3082 |
-
},
|
| 3083 |
-
{
|
| 3084 |
-
"epoch": 48.59,
|
| 3085 |
-
"learning_rate": 5.869565217391305e-06,
|
| 3086 |
-
"loss": 0.1887,
|
| 3087 |
-
"step": 4470
|
| 3088 |
-
},
|
| 3089 |
-
{
|
| 3090 |
-
"epoch": 48.7,
|
| 3091 |
-
"learning_rate": 5.4347826086956525e-06,
|
| 3092 |
-
"loss": 0.1824,
|
| 3093 |
-
"step": 4480
|
| 3094 |
-
},
|
| 3095 |
-
{
|
| 3096 |
-
"epoch": 48.8,
|
| 3097 |
-
"learning_rate": 5e-06,
|
| 3098 |
-
"loss": 0.1564,
|
| 3099 |
-
"step": 4490
|
| 3100 |
-
},
|
| 3101 |
-
{
|
| 3102 |
-
"epoch": 48.91,
|
| 3103 |
-
"learning_rate": 4.565217391304348e-06,
|
| 3104 |
-
"loss": 0.0262,
|
| 3105 |
-
"step": 4500
|
| 3106 |
-
},
|
| 3107 |
-
{
|
| 3108 |
-
"epoch": 48.91,
|
| 3109 |
-
"eval_accuracy": 0.9769230769230769,
|
| 3110 |
-
"eval_loss": 0.135969340801239,
|
| 3111 |
-
"eval_runtime": 1.8658,
|
| 3112 |
-
"eval_samples_per_second": 139.349,
|
| 3113 |
-
"eval_steps_per_second": 17.687,
|
| 3114 |
-
"step": 4500
|
| 3115 |
-
},
|
| 3116 |
-
{
|
| 3117 |
-
"epoch": 49.02,
|
| 3118 |
-
"learning_rate": 4.130434782608695e-06,
|
| 3119 |
-
"loss": 0.1187,
|
| 3120 |
-
"step": 4510
|
| 3121 |
-
},
|
| 3122 |
-
{
|
| 3123 |
-
"epoch": 49.13,
|
| 3124 |
-
"learning_rate": 3.695652173913044e-06,
|
| 3125 |
-
"loss": 0.0973,
|
| 3126 |
-
"step": 4520
|
| 3127 |
-
},
|
| 3128 |
-
{
|
| 3129 |
-
"epoch": 49.24,
|
| 3130 |
-
"learning_rate": 3.2608695652173914e-06,
|
| 3131 |
-
"loss": 0.1082,
|
| 3132 |
-
"step": 4530
|
| 3133 |
-
},
|
| 3134 |
-
{
|
| 3135 |
-
"epoch": 49.35,
|
| 3136 |
-
"learning_rate": 2.8260869565217393e-06,
|
| 3137 |
-
"loss": 0.1439,
|
| 3138 |
-
"step": 4540
|
| 3139 |
-
},
|
| 3140 |
-
{
|
| 3141 |
-
"epoch": 49.46,
|
| 3142 |
-
"learning_rate": 2.391304347826087e-06,
|
| 3143 |
-
"loss": 0.1052,
|
| 3144 |
-
"step": 4550
|
| 3145 |
-
},
|
| 3146 |
-
{
|
| 3147 |
-
"epoch": 49.57,
|
| 3148 |
-
"learning_rate": 1.956521739130435e-06,
|
| 3149 |
-
"loss": 0.1465,
|
| 3150 |
-
"step": 4560
|
| 3151 |
-
},
|
| 3152 |
-
{
|
| 3153 |
-
"epoch": 49.67,
|
| 3154 |
-
"learning_rate": 1.5217391304347827e-06,
|
| 3155 |
-
"loss": 0.1092,
|
| 3156 |
-
"step": 4570
|
| 3157 |
-
},
|
| 3158 |
-
{
|
| 3159 |
-
"epoch": 49.78,
|
| 3160 |
-
"learning_rate": 1.0869565217391306e-06,
|
| 3161 |
-
"loss": 0.1454,
|
| 3162 |
-
"step": 4580
|
| 3163 |
-
},
|
| 3164 |
-
{
|
| 3165 |
-
"epoch": 49.89,
|
| 3166 |
-
"learning_rate": 6.521739130434782e-07,
|
| 3167 |
-
"loss": 0.1703,
|
| 3168 |
-
"step": 4590
|
| 3169 |
-
},
|
| 3170 |
-
{
|
| 3171 |
-
"epoch": 50.0,
|
| 3172 |
-
"learning_rate": 2.173913043478261e-07,
|
| 3173 |
-
"loss": 0.1274,
|
| 3174 |
-
"step": 4600
|
| 3175 |
-
},
|
| 3176 |
-
{
|
| 3177 |
-
"epoch": 50.0,
|
| 3178 |
-
"eval_accuracy": 0.9769230769230769,
|
| 3179 |
-
"eval_loss": 0.13699783384799957,
|
| 3180 |
-
"eval_runtime": 2.6653,
|
| 3181 |
-
"eval_samples_per_second": 97.548,
|
| 3182 |
-
"eval_steps_per_second": 12.381,
|
| 3183 |
-
"step": 4600
|
| 3184 |
-
},
|
| 3185 |
-
{
|
| 3186 |
-
"epoch": 50.0,
|
| 3187 |
-
"step": 4600,
|
| 3188 |
-
"total_flos": 1.8256530865176576e+18,
|
| 3189 |
-
"train_loss": 0.3526626825786155,
|
| 3190 |
-
"train_runtime": 995.2393,
|
| 3191 |
-
"train_samples_per_second": 73.751,
|
| 3192 |
-
"train_steps_per_second": 4.622
|
| 3193 |
}
|
| 3194 |
],
|
| 3195 |
"logging_steps": 10,
|
| 3196 |
-
"max_steps":
|
| 3197 |
-
"num_train_epochs":
|
| 3198 |
"save_steps": 100,
|
| 3199 |
-
"total_flos":
|
| 3200 |
"trial_name": null,
|
| 3201 |
"trial_params": null
|
| 3202 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9846153846153847,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned_ASL_Isolated_Swin_dataset2/checkpoint-1700",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 1840,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.11,
|
| 13 |
+
"learning_rate": 0.00019891304347826087,
|
| 14 |
+
"loss": 3.3365,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.22,
|
| 19 |
+
"learning_rate": 0.00019782608695652175,
|
| 20 |
+
"loss": 3.2188,
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.33,
|
| 25 |
+
"learning_rate": 0.00019673913043478263,
|
| 26 |
+
"loss": 3.1756,
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.43,
|
| 31 |
+
"learning_rate": 0.0001956521739130435,
|
| 32 |
+
"loss": 2.9023,
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.54,
|
| 37 |
+
"learning_rate": 0.00019467391304347825,
|
| 38 |
+
"loss": 2.5517,
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.65,
|
| 43 |
+
"learning_rate": 0.00019358695652173916,
|
| 44 |
+
"loss": 2.4131,
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.76,
|
| 49 |
+
"learning_rate": 0.00019250000000000002,
|
| 50 |
+
"loss": 2.0957,
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.87,
|
| 55 |
+
"learning_rate": 0.00019141304347826087,
|
| 56 |
+
"loss": 1.8856,
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.98,
|
| 61 |
+
"learning_rate": 0.00019032608695652176,
|
| 62 |
+
"loss": 1.7217,
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 1.09,
|
| 67 |
+
"learning_rate": 0.0001892391304347826,
|
| 68 |
+
"loss": 1.6758,
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 1.09,
|
| 73 |
+
"eval_accuracy": 0.5769230769230769,
|
| 74 |
+
"eval_loss": 1.320558786392212,
|
| 75 |
+
"eval_runtime": 2.846,
|
| 76 |
+
"eval_samples_per_second": 91.356,
|
| 77 |
+
"eval_steps_per_second": 11.595,
|
| 78 |
"step": 100
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 1.2,
|
| 82 |
+
"learning_rate": 0.0001881521739130435,
|
| 83 |
+
"loss": 1.4695,
|
| 84 |
"step": 110
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 1.3,
|
| 88 |
+
"learning_rate": 0.00018706521739130435,
|
| 89 |
+
"loss": 1.311,
|
| 90 |
"step": 120
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 1.41,
|
| 94 |
+
"learning_rate": 0.00018597826086956523,
|
| 95 |
+
"loss": 1.2741,
|
| 96 |
"step": 130
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 1.52,
|
| 100 |
+
"learning_rate": 0.0001848913043478261,
|
| 101 |
+
"loss": 1.3444,
|
| 102 |
"step": 140
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 1.63,
|
| 106 |
+
"learning_rate": 0.00018380434782608697,
|
| 107 |
+
"loss": 1.0445,
|
| 108 |
"step": 150
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 1.74,
|
| 112 |
+
"learning_rate": 0.00018282608695652174,
|
| 113 |
+
"loss": 1.0316,
|
| 114 |
"step": 160
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 1.85,
|
| 118 |
+
"learning_rate": 0.00018173913043478262,
|
| 119 |
+
"loss": 1.0877,
|
| 120 |
"step": 170
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 1.96,
|
| 124 |
+
"learning_rate": 0.00018065217391304348,
|
| 125 |
+
"loss": 1.1561,
|
| 126 |
"step": 180
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 2.07,
|
| 130 |
+
"learning_rate": 0.00017956521739130436,
|
| 131 |
+
"loss": 1.0726,
|
| 132 |
"step": 190
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 2.17,
|
| 136 |
+
"learning_rate": 0.00017847826086956522,
|
| 137 |
+
"loss": 1.0717,
|
| 138 |
"step": 200
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 2.17,
|
| 142 |
+
"eval_accuracy": 0.8153846153846154,
|
| 143 |
+
"eval_loss": 0.6482219696044922,
|
| 144 |
+
"eval_runtime": 1.825,
|
| 145 |
+
"eval_samples_per_second": 142.465,
|
| 146 |
+
"eval_steps_per_second": 18.082,
|
| 147 |
"step": 200
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 2.28,
|
| 151 |
+
"learning_rate": 0.0001773913043478261,
|
| 152 |
+
"loss": 0.744,
|
| 153 |
"step": 210
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 2.39,
|
| 157 |
+
"learning_rate": 0.00017630434782608695,
|
| 158 |
+
"loss": 0.9959,
|
| 159 |
"step": 220
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 2.5,
|
| 163 |
+
"learning_rate": 0.00017521739130434784,
|
| 164 |
+
"loss": 0.9342,
|
| 165 |
"step": 230
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 2.61,
|
| 169 |
+
"learning_rate": 0.00017413043478260872,
|
| 170 |
+
"loss": 0.8275,
|
| 171 |
"step": 240
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 2.72,
|
| 175 |
+
"learning_rate": 0.00017304347826086958,
|
| 176 |
+
"loss": 0.8388,
|
| 177 |
"step": 250
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 2.83,
|
| 181 |
+
"learning_rate": 0.00017195652173913043,
|
| 182 |
+
"loss": 0.8996,
|
| 183 |
"step": 260
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 2.93,
|
| 187 |
+
"learning_rate": 0.00017086956521739132,
|
| 188 |
+
"loss": 0.6616,
|
| 189 |
"step": 270
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 3.04,
|
| 193 |
+
"learning_rate": 0.0001697826086956522,
|
| 194 |
+
"loss": 0.7714,
|
| 195 |
"step": 280
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 3.15,
|
| 199 |
+
"learning_rate": 0.00016869565217391306,
|
| 200 |
+
"loss": 0.7296,
|
| 201 |
"step": 290
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 3.26,
|
| 205 |
+
"learning_rate": 0.0001676086956521739,
|
| 206 |
+
"loss": 0.627,
|
| 207 |
"step": 300
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 3.26,
|
| 211 |
+
"eval_accuracy": 0.8653846153846154,
|
| 212 |
+
"eval_loss": 0.4485549330711365,
|
| 213 |
+
"eval_runtime": 2.5537,
|
| 214 |
+
"eval_samples_per_second": 101.814,
|
| 215 |
+
"eval_steps_per_second": 12.923,
|
| 216 |
"step": 300
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 3.37,
|
| 220 |
+
"learning_rate": 0.0001666304347826087,
|
| 221 |
+
"loss": 0.8732,
|
| 222 |
"step": 310
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 3.48,
|
| 226 |
+
"learning_rate": 0.00016554347826086958,
|
| 227 |
+
"loss": 0.8933,
|
| 228 |
"step": 320
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 3.59,
|
| 232 |
+
"learning_rate": 0.00016445652173913044,
|
| 233 |
+
"loss": 0.8468,
|
| 234 |
"step": 330
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 3.7,
|
| 238 |
+
"learning_rate": 0.0001633695652173913,
|
| 239 |
+
"loss": 0.6468,
|
| 240 |
"step": 340
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 3.8,
|
| 244 |
+
"learning_rate": 0.00016228260869565218,
|
| 245 |
+
"loss": 0.7266,
|
| 246 |
"step": 350
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 3.91,
|
| 250 |
+
"learning_rate": 0.00016119565217391306,
|
| 251 |
+
"loss": 0.8522,
|
| 252 |
"step": 360
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 4.02,
|
| 256 |
+
"learning_rate": 0.00016010869565217392,
|
| 257 |
+
"loss": 0.5888,
|
| 258 |
"step": 370
|
| 259 |
},
|
| 260 |
{
|
| 261 |
"epoch": 4.13,
|
| 262 |
+
"learning_rate": 0.00015902173913043478,
|
| 263 |
+
"loss": 0.685,
|
| 264 |
"step": 380
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 4.24,
|
| 268 |
+
"learning_rate": 0.00015793478260869566,
|
| 269 |
+
"loss": 0.6937,
|
| 270 |
"step": 390
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 4.35,
|
| 274 |
+
"learning_rate": 0.00015684782608695654,
|
| 275 |
+
"loss": 0.5397,
|
| 276 |
"step": 400
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 4.35,
|
| 280 |
+
"eval_accuracy": 0.8923076923076924,
|
| 281 |
+
"eval_loss": 0.2977767884731293,
|
| 282 |
+
"eval_runtime": 1.8479,
|
| 283 |
+
"eval_samples_per_second": 140.701,
|
| 284 |
+
"eval_steps_per_second": 17.858,
|
| 285 |
"step": 400
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 4.46,
|
| 289 |
+
"learning_rate": 0.0001557608695652174,
|
| 290 |
+
"loss": 0.6058,
|
| 291 |
"step": 410
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 4.57,
|
| 295 |
+
"learning_rate": 0.00015467391304347828,
|
| 296 |
+
"loss": 0.553,
|
| 297 |
"step": 420
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 4.67,
|
| 301 |
+
"learning_rate": 0.00015358695652173914,
|
| 302 |
+
"loss": 0.4621,
|
| 303 |
"step": 430
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 4.78,
|
| 307 |
+
"learning_rate": 0.0001525,
|
| 308 |
+
"loss": 0.5002,
|
| 309 |
"step": 440
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 4.89,
|
| 313 |
+
"learning_rate": 0.00015141304347826088,
|
| 314 |
+
"loss": 0.4833,
|
| 315 |
"step": 450
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 5.0,
|
| 319 |
+
"learning_rate": 0.00015032608695652176,
|
| 320 |
+
"loss": 0.5952,
|
| 321 |
"step": 460
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 5.11,
|
| 325 |
+
"learning_rate": 0.00014923913043478262,
|
| 326 |
+
"loss": 0.5049,
|
| 327 |
"step": 470
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 5.22,
|
| 331 |
+
"learning_rate": 0.00014815217391304347,
|
| 332 |
+
"loss": 0.5219,
|
| 333 |
"step": 480
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 5.33,
|
| 337 |
+
"learning_rate": 0.00014706521739130436,
|
| 338 |
+
"loss": 0.6222,
|
| 339 |
"step": 490
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 5.43,
|
| 343 |
+
"learning_rate": 0.00014597826086956524,
|
| 344 |
+
"loss": 0.537,
|
| 345 |
"step": 500
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 5.43,
|
| 349 |
+
"eval_accuracy": 0.9423076923076923,
|
| 350 |
+
"eval_loss": 0.151279479265213,
|
| 351 |
+
"eval_runtime": 1.8783,
|
| 352 |
+
"eval_samples_per_second": 138.42,
|
| 353 |
+
"eval_steps_per_second": 17.569,
|
| 354 |
"step": 500
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 5.54,
|
| 358 |
+
"learning_rate": 0.0001448913043478261,
|
| 359 |
+
"loss": 0.498,
|
| 360 |
"step": 510
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 5.65,
|
| 364 |
+
"learning_rate": 0.00014380434782608695,
|
| 365 |
+
"loss": 0.5532,
|
| 366 |
"step": 520
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 5.76,
|
| 370 |
+
"learning_rate": 0.00014271739130434783,
|
| 371 |
+
"loss": 0.5434,
|
| 372 |
"step": 530
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 5.87,
|
| 376 |
+
"learning_rate": 0.00014163043478260872,
|
| 377 |
+
"loss": 0.6535,
|
| 378 |
"step": 540
|
| 379 |
},
|
| 380 |
{
|
| 381 |
"epoch": 5.98,
|
| 382 |
+
"learning_rate": 0.00014054347826086957,
|
| 383 |
+
"loss": 0.4965,
|
| 384 |
"step": 550
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 6.09,
|
| 388 |
+
"learning_rate": 0.00013945652173913043,
|
| 389 |
+
"loss": 0.6712,
|
| 390 |
"step": 560
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 6.2,
|
| 394 |
+
"learning_rate": 0.0001383695652173913,
|
| 395 |
+
"loss": 0.5683,
|
| 396 |
"step": 570
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 6.3,
|
| 400 |
+
"learning_rate": 0.00013728260869565217,
|
| 401 |
+
"loss": 0.3377,
|
| 402 |
"step": 580
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 6.41,
|
| 406 |
+
"learning_rate": 0.00013619565217391305,
|
| 407 |
+
"loss": 0.482,
|
| 408 |
"step": 590
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 6.52,
|
| 412 |
+
"learning_rate": 0.00013510869565217394,
|
| 413 |
+
"loss": 0.3766,
|
| 414 |
"step": 600
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 6.52,
|
| 418 |
+
"eval_accuracy": 0.8846153846153846,
|
| 419 |
+
"eval_loss": 0.4736884534358978,
|
| 420 |
+
"eval_runtime": 1.8513,
|
| 421 |
+
"eval_samples_per_second": 140.44,
|
| 422 |
+
"eval_steps_per_second": 17.825,
|
| 423 |
"step": 600
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 6.63,
|
| 427 |
+
"learning_rate": 0.0001340217391304348,
|
| 428 |
+
"loss": 0.5068,
|
| 429 |
"step": 610
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 6.74,
|
| 433 |
+
"learning_rate": 0.00013293478260869565,
|
| 434 |
+
"loss": 0.3019,
|
| 435 |
"step": 620
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 6.85,
|
| 439 |
+
"learning_rate": 0.00013184782608695653,
|
| 440 |
+
"loss": 0.4852,
|
| 441 |
"step": 630
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 6.96,
|
| 445 |
+
"learning_rate": 0.00013076086956521741,
|
| 446 |
+
"loss": 0.55,
|
| 447 |
"step": 640
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 7.07,
|
| 451 |
+
"learning_rate": 0.00012967391304347827,
|
| 452 |
+
"loss": 0.4122,
|
| 453 |
"step": 650
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 7.17,
|
| 457 |
+
"learning_rate": 0.00012858695652173913,
|
| 458 |
+
"loss": 0.3566,
|
| 459 |
"step": 660
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 7.28,
|
| 463 |
+
"learning_rate": 0.0001275,
|
| 464 |
+
"loss": 0.4279,
|
| 465 |
"step": 670
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 7.39,
|
| 469 |
+
"learning_rate": 0.0001264130434782609,
|
| 470 |
+
"loss": 0.3295,
|
| 471 |
"step": 680
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 7.5,
|
| 475 |
+
"learning_rate": 0.00012532608695652175,
|
| 476 |
+
"loss": 0.5113,
|
| 477 |
"step": 690
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 7.61,
|
| 481 |
+
"learning_rate": 0.0001242391304347826,
|
| 482 |
+
"loss": 0.3994,
|
| 483 |
"step": 700
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 7.61,
|
| 487 |
+
"eval_accuracy": 0.9115384615384615,
|
| 488 |
+
"eval_loss": 0.3060305714607239,
|
| 489 |
+
"eval_runtime": 1.8463,
|
| 490 |
+
"eval_samples_per_second": 140.821,
|
| 491 |
+
"eval_steps_per_second": 17.873,
|
| 492 |
"step": 700
|
| 493 |
},
|
| 494 |
{
|
| 495 |
"epoch": 7.72,
|
| 496 |
+
"learning_rate": 0.0001231521739130435,
|
| 497 |
+
"loss": 0.5572,
|
| 498 |
"step": 710
|
| 499 |
},
|
| 500 |
{
|
| 501 |
"epoch": 7.83,
|
| 502 |
+
"learning_rate": 0.00012206521739130434,
|
| 503 |
+
"loss": 0.2986,
|
| 504 |
"step": 720
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 7.93,
|
| 508 |
+
"learning_rate": 0.00012097826086956523,
|
| 509 |
+
"loss": 0.5146,
|
| 510 |
"step": 730
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 8.04,
|
| 514 |
+
"learning_rate": 0.0001198913043478261,
|
| 515 |
+
"loss": 0.4029,
|
| 516 |
"step": 740
|
| 517 |
},
|
| 518 |
{
|
| 519 |
"epoch": 8.15,
|
| 520 |
+
"learning_rate": 0.00011880434782608695,
|
| 521 |
+
"loss": 0.3901,
|
| 522 |
"step": 750
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 8.26,
|
| 526 |
+
"learning_rate": 0.00011771739130434782,
|
| 527 |
+
"loss": 0.5112,
|
| 528 |
"step": 760
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 8.37,
|
| 532 |
+
"learning_rate": 0.0001166304347826087,
|
| 533 |
+
"loss": 0.2704,
|
| 534 |
"step": 770
|
| 535 |
},
|
| 536 |
{
|
| 537 |
"epoch": 8.48,
|
| 538 |
+
"learning_rate": 0.00011554347826086958,
|
| 539 |
+
"loss": 0.3839,
|
| 540 |
"step": 780
|
| 541 |
},
|
| 542 |
{
|
| 543 |
"epoch": 8.59,
|
| 544 |
+
"learning_rate": 0.00011445652173913045,
|
| 545 |
+
"loss": 0.4988,
|
| 546 |
"step": 790
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 8.7,
|
| 550 |
+
"learning_rate": 0.0001133695652173913,
|
| 551 |
+
"loss": 0.2139,
|
| 552 |
"step": 800
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"epoch": 8.7,
|
| 556 |
+
"eval_accuracy": 0.9576923076923077,
|
| 557 |
+
"eval_loss": 0.13448870182037354,
|
| 558 |
+
"eval_runtime": 1.9169,
|
| 559 |
+
"eval_samples_per_second": 135.638,
|
| 560 |
+
"eval_steps_per_second": 17.216,
|
| 561 |
"step": 800
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 8.8,
|
| 565 |
+
"learning_rate": 0.00011228260869565217,
|
| 566 |
+
"loss": 0.2857,
|
| 567 |
"step": 810
|
| 568 |
},
|
| 569 |
{
|
| 570 |
"epoch": 8.91,
|
| 571 |
+
"learning_rate": 0.00011119565217391305,
|
| 572 |
+
"loss": 0.2416,
|
| 573 |
"step": 820
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 9.02,
|
| 577 |
+
"learning_rate": 0.00011010869565217392,
|
| 578 |
+
"loss": 0.4803,
|
| 579 |
"step": 830
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 9.13,
|
| 583 |
+
"learning_rate": 0.00010902173913043478,
|
| 584 |
+
"loss": 0.4416,
|
| 585 |
"step": 840
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 9.24,
|
| 589 |
+
"learning_rate": 0.00010793478260869565,
|
| 590 |
+
"loss": 0.3271,
|
| 591 |
"step": 850
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 9.35,
|
| 595 |
+
"learning_rate": 0.00010684782608695653,
|
| 596 |
+
"loss": 0.2261,
|
| 597 |
"step": 860
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 9.46,
|
| 601 |
+
"learning_rate": 0.0001057608695652174,
|
| 602 |
+
"loss": 0.2063,
|
| 603 |
"step": 870
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 9.57,
|
| 607 |
+
"learning_rate": 0.00010467391304347827,
|
| 608 |
+
"loss": 0.4865,
|
| 609 |
"step": 880
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 9.67,
|
| 613 |
+
"learning_rate": 0.00010358695652173913,
|
| 614 |
+
"loss": 0.4903,
|
| 615 |
"step": 890
|
| 616 |
},
|
| 617 |
{
|
| 618 |
"epoch": 9.78,
|
| 619 |
+
"learning_rate": 0.0001025,
|
| 620 |
+
"loss": 0.2995,
|
| 621 |
"step": 900
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 9.78,
|
| 625 |
+
"eval_accuracy": 0.95,
|
| 626 |
+
"eval_loss": 0.155814990401268,
|
| 627 |
+
"eval_runtime": 1.8528,
|
| 628 |
+
"eval_samples_per_second": 140.328,
|
| 629 |
+
"eval_steps_per_second": 17.811,
|
| 630 |
"step": 900
|
| 631 |
},
|
| 632 |
{
|
| 633 |
"epoch": 9.89,
|
| 634 |
+
"learning_rate": 0.00010141304347826088,
|
| 635 |
+
"loss": 0.2847,
|
| 636 |
"step": 910
|
| 637 |
},
|
| 638 |
{
|
| 639 |
"epoch": 10.0,
|
| 640 |
+
"learning_rate": 0.00010032608695652175,
|
| 641 |
+
"loss": 0.2913,
|
| 642 |
"step": 920
|
| 643 |
},
|
| 644 |
{
|
| 645 |
"epoch": 10.11,
|
| 646 |
+
"learning_rate": 9.923913043478261e-05,
|
| 647 |
+
"loss": 0.2779,
|
| 648 |
"step": 930
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 10.22,
|
| 652 |
+
"learning_rate": 9.815217391304349e-05,
|
| 653 |
+
"loss": 0.2205,
|
| 654 |
"step": 940
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 10.33,
|
| 658 |
+
"learning_rate": 9.706521739130435e-05,
|
| 659 |
+
"loss": 0.405,
|
| 660 |
"step": 950
|
| 661 |
},
|
| 662 |
{
|
| 663 |
"epoch": 10.43,
|
| 664 |
+
"learning_rate": 9.597826086956522e-05,
|
| 665 |
+
"loss": 0.3613,
|
| 666 |
"step": 960
|
| 667 |
},
|
| 668 |
{
|
| 669 |
"epoch": 10.54,
|
| 670 |
+
"learning_rate": 9.48913043478261e-05,
|
| 671 |
+
"loss": 0.2381,
|
| 672 |
"step": 970
|
| 673 |
},
|
| 674 |
{
|
| 675 |
"epoch": 10.65,
|
| 676 |
+
"learning_rate": 9.380434782608696e-05,
|
| 677 |
+
"loss": 0.224,
|
| 678 |
"step": 980
|
| 679 |
},
|
| 680 |
{
|
| 681 |
"epoch": 10.76,
|
| 682 |
+
"learning_rate": 9.271739130434784e-05,
|
| 683 |
+
"loss": 0.2544,
|
| 684 |
"step": 990
|
| 685 |
},
|
| 686 |
{
|
| 687 |
"epoch": 10.87,
|
| 688 |
+
"learning_rate": 9.16304347826087e-05,
|
| 689 |
+
"loss": 0.2835,
|
| 690 |
"step": 1000
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 10.87,
|
| 694 |
+
"eval_accuracy": 0.9730769230769231,
|
| 695 |
+
"eval_loss": 0.09426813572645187,
|
| 696 |
+
"eval_runtime": 2.2351,
|
| 697 |
+
"eval_samples_per_second": 116.327,
|
| 698 |
+
"eval_steps_per_second": 14.765,
|
| 699 |
"step": 1000
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 10.98,
|
| 703 |
+
"learning_rate": 9.054347826086958e-05,
|
| 704 |
+
"loss": 0.4605,
|
| 705 |
"step": 1010
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 11.09,
|
| 709 |
+
"learning_rate": 8.945652173913043e-05,
|
| 710 |
+
"loss": 0.2259,
|
| 711 |
"step": 1020
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 11.2,
|
| 715 |
+
"learning_rate": 8.83695652173913e-05,
|
| 716 |
+
"loss": 0.2241,
|
| 717 |
"step": 1030
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 11.3,
|
| 721 |
+
"learning_rate": 8.728260869565217e-05,
|
| 722 |
+
"loss": 0.2173,
|
| 723 |
"step": 1040
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 11.41,
|
| 727 |
+
"learning_rate": 8.619565217391304e-05,
|
| 728 |
+
"loss": 0.3629,
|
| 729 |
"step": 1050
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 11.52,
|
| 733 |
+
"learning_rate": 8.510869565217393e-05,
|
| 734 |
+
"loss": 0.6198,
|
| 735 |
"step": 1060
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 11.63,
|
| 739 |
+
"learning_rate": 8.402173913043478e-05,
|
| 740 |
+
"loss": 0.5369,
|
| 741 |
"step": 1070
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 11.74,
|
| 745 |
+
"learning_rate": 8.293478260869567e-05,
|
| 746 |
+
"loss": 0.304,
|
| 747 |
"step": 1080
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 11.85,
|
| 751 |
+
"learning_rate": 8.184782608695652e-05,
|
| 752 |
+
"loss": 0.2756,
|
| 753 |
"step": 1090
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 11.96,
|
| 757 |
+
"learning_rate": 8.076086956521739e-05,
|
| 758 |
+
"loss": 0.3089,
|
| 759 |
"step": 1100
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 11.96,
|
| 763 |
+
"eval_accuracy": 0.9576923076923077,
|
| 764 |
+
"eval_loss": 0.09128668904304504,
|
| 765 |
+
"eval_runtime": 1.8693,
|
| 766 |
+
"eval_samples_per_second": 139.093,
|
| 767 |
+
"eval_steps_per_second": 17.654,
|
| 768 |
"step": 1100
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 12.07,
|
| 772 |
+
"learning_rate": 7.967391304347826e-05,
|
| 773 |
+
"loss": 0.3491,
|
| 774 |
"step": 1110
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"epoch": 12.17,
|
| 778 |
+
"learning_rate": 7.858695652173913e-05,
|
| 779 |
+
"loss": 0.1677,
|
| 780 |
"step": 1120
|
| 781 |
},
|
| 782 |
{
|
| 783 |
"epoch": 12.28,
|
| 784 |
+
"learning_rate": 7.75e-05,
|
| 785 |
+
"loss": 0.2795,
|
| 786 |
"step": 1130
|
| 787 |
},
|
| 788 |
{
|
| 789 |
"epoch": 12.39,
|
| 790 |
+
"learning_rate": 7.641304347826087e-05,
|
| 791 |
+
"loss": 0.2714,
|
| 792 |
"step": 1140
|
| 793 |
},
|
| 794 |
{
|
| 795 |
"epoch": 12.5,
|
| 796 |
+
"learning_rate": 7.532608695652175e-05,
|
| 797 |
+
"loss": 0.302,
|
| 798 |
"step": 1150
|
| 799 |
},
|
| 800 |
{
|
| 801 |
"epoch": 12.61,
|
| 802 |
+
"learning_rate": 7.423913043478261e-05,
|
| 803 |
+
"loss": 0.3564,
|
| 804 |
"step": 1160
|
| 805 |
},
|
| 806 |
{
|
| 807 |
"epoch": 12.72,
|
| 808 |
+
"learning_rate": 7.32608695652174e-05,
|
| 809 |
+
"loss": 0.3085,
|
| 810 |
"step": 1170
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 12.83,
|
| 814 |
+
"learning_rate": 7.217391304347827e-05,
|
| 815 |
+
"loss": 0.2515,
|
| 816 |
"step": 1180
|
| 817 |
},
|
| 818 |
{
|
| 819 |
"epoch": 12.93,
|
| 820 |
+
"learning_rate": 7.108695652173914e-05,
|
| 821 |
+
"loss": 0.3075,
|
| 822 |
"step": 1190
|
| 823 |
},
|
| 824 |
{
|
| 825 |
"epoch": 13.04,
|
| 826 |
+
"learning_rate": 7e-05,
|
| 827 |
+
"loss": 0.3632,
|
| 828 |
"step": 1200
|
| 829 |
},
|
| 830 |
{
|
| 831 |
"epoch": 13.04,
|
| 832 |
+
"eval_accuracy": 0.9692307692307692,
|
| 833 |
+
"eval_loss": 0.08875690400600433,
|
| 834 |
+
"eval_runtime": 2.7533,
|
| 835 |
+
"eval_samples_per_second": 94.431,
|
| 836 |
+
"eval_steps_per_second": 11.986,
|
| 837 |
"step": 1200
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 13.15,
|
| 841 |
+
"learning_rate": 6.891304347826088e-05,
|
| 842 |
+
"loss": 0.3888,
|
| 843 |
"step": 1210
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 13.26,
|
| 847 |
+
"learning_rate": 6.782608695652173e-05,
|
| 848 |
+
"loss": 0.1683,
|
| 849 |
"step": 1220
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 13.37,
|
| 853 |
+
"learning_rate": 6.673913043478262e-05,
|
| 854 |
+
"loss": 0.3672,
|
| 855 |
"step": 1230
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 13.48,
|
| 859 |
+
"learning_rate": 6.565217391304349e-05,
|
| 860 |
+
"loss": 0.335,
|
| 861 |
"step": 1240
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 13.59,
|
| 865 |
+
"learning_rate": 6.456521739130436e-05,
|
| 866 |
+
"loss": 0.1861,
|
| 867 |
"step": 1250
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 13.7,
|
| 871 |
+
"learning_rate": 6.347826086956523e-05,
|
| 872 |
+
"loss": 0.3386,
|
| 873 |
"step": 1260
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"epoch": 13.8,
|
| 877 |
+
"learning_rate": 6.239130434782608e-05,
|
| 878 |
+
"loss": 0.2222,
|
| 879 |
"step": 1270
|
| 880 |
},
|
| 881 |
{
|
| 882 |
"epoch": 13.91,
|
| 883 |
+
"learning_rate": 6.130434782608696e-05,
|
| 884 |
+
"loss": 0.1714,
|
| 885 |
"step": 1280
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 14.02,
|
| 889 |
+
"learning_rate": 6.021739130434783e-05,
|
| 890 |
+
"loss": 0.2699,
|
| 891 |
"step": 1290
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"epoch": 14.13,
|
| 895 |
+
"learning_rate": 5.9130434782608704e-05,
|
| 896 |
+
"loss": 0.327,
|
| 897 |
"step": 1300
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 14.13,
|
| 901 |
+
"eval_accuracy": 0.9807692307692307,
|
| 902 |
+
"eval_loss": 0.10383553802967072,
|
| 903 |
+
"eval_runtime": 1.9077,
|
| 904 |
+
"eval_samples_per_second": 136.293,
|
| 905 |
+
"eval_steps_per_second": 17.299,
|
| 906 |
"step": 1300
|
| 907 |
},
|
| 908 |
{
|
| 909 |
"epoch": 14.24,
|
| 910 |
+
"learning_rate": 5.804347826086957e-05,
|
| 911 |
+
"loss": 0.224,
|
| 912 |
"step": 1310
|
| 913 |
},
|
| 914 |
{
|
| 915 |
"epoch": 14.35,
|
| 916 |
+
"learning_rate": 5.695652173913044e-05,
|
| 917 |
+
"loss": 0.378,
|
| 918 |
"step": 1320
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"epoch": 14.46,
|
| 922 |
+
"learning_rate": 5.5869565217391306e-05,
|
| 923 |
+
"loss": 0.2503,
|
| 924 |
"step": 1330
|
| 925 |
},
|
| 926 |
{
|
| 927 |
"epoch": 14.57,
|
| 928 |
+
"learning_rate": 5.478260869565217e-05,
|
| 929 |
+
"loss": 0.1633,
|
| 930 |
"step": 1340
|
| 931 |
},
|
| 932 |
{
|
| 933 |
"epoch": 14.67,
|
| 934 |
+
"learning_rate": 5.3695652173913046e-05,
|
| 935 |
+
"loss": 0.2973,
|
| 936 |
"step": 1350
|
| 937 |
},
|
| 938 |
{
|
| 939 |
"epoch": 14.78,
|
| 940 |
+
"learning_rate": 5.260869565217391e-05,
|
| 941 |
+
"loss": 0.1887,
|
| 942 |
"step": 1360
|
| 943 |
},
|
| 944 |
{
|
| 945 |
"epoch": 14.89,
|
| 946 |
+
"learning_rate": 5.1521739130434785e-05,
|
| 947 |
+
"loss": 0.2953,
|
| 948 |
"step": 1370
|
| 949 |
},
|
| 950 |
{
|
| 951 |
"epoch": 15.0,
|
| 952 |
+
"learning_rate": 5.0434782608695655e-05,
|
| 953 |
+
"loss": 0.248,
|
| 954 |
"step": 1380
|
| 955 |
},
|
| 956 |
{
|
| 957 |
"epoch": 15.11,
|
| 958 |
+
"learning_rate": 4.9347826086956524e-05,
|
| 959 |
+
"loss": 0.152,
|
| 960 |
"step": 1390
|
| 961 |
},
|
| 962 |
{
|
| 963 |
"epoch": 15.22,
|
| 964 |
+
"learning_rate": 4.8260869565217394e-05,
|
| 965 |
+
"loss": 0.313,
|
| 966 |
"step": 1400
|
| 967 |
},
|
| 968 |
{
|
| 969 |
"epoch": 15.22,
|
| 970 |
+
"eval_accuracy": 0.9730769230769231,
|
| 971 |
+
"eval_loss": 0.09758734703063965,
|
| 972 |
+
"eval_runtime": 2.57,
|
| 973 |
+
"eval_samples_per_second": 101.167,
|
| 974 |
+
"eval_steps_per_second": 12.84,
|
| 975 |
"step": 1400
|
| 976 |
},
|
| 977 |
{
|
| 978 |
"epoch": 15.33,
|
| 979 |
+
"learning_rate": 4.7173913043478264e-05,
|
| 980 |
+
"loss": 0.2301,
|
| 981 |
"step": 1410
|
| 982 |
},
|
| 983 |
{
|
| 984 |
"epoch": 15.43,
|
| 985 |
+
"learning_rate": 4.608695652173913e-05,
|
| 986 |
+
"loss": 0.1671,
|
| 987 |
"step": 1420
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 15.54,
|
| 991 |
+
"learning_rate": 4.5e-05,
|
| 992 |
+
"loss": 0.2399,
|
| 993 |
"step": 1430
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"epoch": 15.65,
|
| 997 |
+
"learning_rate": 4.391304347826087e-05,
|
| 998 |
+
"loss": 0.278,
|
| 999 |
"step": 1440
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 15.76,
|
| 1003 |
+
"learning_rate": 4.282608695652174e-05,
|
| 1004 |
+
"loss": 0.3062,
|
| 1005 |
"step": 1450
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 15.87,
|
| 1009 |
+
"learning_rate": 4.1739130434782605e-05,
|
| 1010 |
+
"loss": 0.3704,
|
| 1011 |
"step": 1460
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
"epoch": 15.98,
|
| 1015 |
+
"learning_rate": 4.065217391304348e-05,
|
| 1016 |
+
"loss": 0.231,
|
| 1017 |
"step": 1470
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
"epoch": 16.09,
|
| 1021 |
+
"learning_rate": 3.956521739130435e-05,
|
| 1022 |
+
"loss": 0.2339,
|
| 1023 |
"step": 1480
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
"epoch": 16.2,
|
| 1027 |
+
"learning_rate": 3.847826086956522e-05,
|
| 1028 |
+
"loss": 0.2079,
|
| 1029 |
"step": 1490
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
"epoch": 16.3,
|
| 1033 |
+
"learning_rate": 3.739130434782609e-05,
|
| 1034 |
+
"loss": 0.1752,
|
| 1035 |
"step": 1500
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
"epoch": 16.3,
|
| 1039 |
+
"eval_accuracy": 0.9807692307692307,
|
| 1040 |
+
"eval_loss": 0.050352372229099274,
|
| 1041 |
+
"eval_runtime": 1.9714,
|
| 1042 |
+
"eval_samples_per_second": 131.889,
|
| 1043 |
+
"eval_steps_per_second": 16.74,
|
| 1044 |
"step": 1500
|
| 1045 |
},
|
| 1046 |
{
|
| 1047 |
"epoch": 16.41,
|
| 1048 |
+
"learning_rate": 3.630434782608696e-05,
|
| 1049 |
+
"loss": 0.1359,
|
| 1050 |
"step": 1510
|
| 1051 |
},
|
| 1052 |
{
|
| 1053 |
"epoch": 16.52,
|
| 1054 |
+
"learning_rate": 3.521739130434783e-05,
|
| 1055 |
+
"loss": 0.1186,
|
| 1056 |
"step": 1520
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
"epoch": 16.63,
|
| 1060 |
+
"learning_rate": 3.413043478260869e-05,
|
| 1061 |
+
"loss": 0.2223,
|
| 1062 |
"step": 1530
|
| 1063 |
},
|
| 1064 |
{
|
| 1065 |
"epoch": 16.74,
|
| 1066 |
+
"learning_rate": 3.304347826086956e-05,
|
| 1067 |
+
"loss": 0.3185,
|
| 1068 |
"step": 1540
|
| 1069 |
},
|
| 1070 |
{
|
| 1071 |
"epoch": 16.85,
|
| 1072 |
+
"learning_rate": 3.195652173913043e-05,
|
| 1073 |
+
"loss": 0.1554,
|
| 1074 |
"step": 1550
|
| 1075 |
},
|
| 1076 |
{
|
| 1077 |
"epoch": 16.96,
|
| 1078 |
+
"learning_rate": 3.086956521739131e-05,
|
| 1079 |
+
"loss": 0.2177,
|
| 1080 |
"step": 1560
|
| 1081 |
},
|
| 1082 |
{
|
| 1083 |
"epoch": 17.07,
|
| 1084 |
+
"learning_rate": 2.9782608695652175e-05,
|
| 1085 |
+
"loss": 0.167,
|
| 1086 |
"step": 1570
|
| 1087 |
},
|
| 1088 |
{
|
| 1089 |
"epoch": 17.17,
|
| 1090 |
+
"learning_rate": 2.8695652173913044e-05,
|
| 1091 |
+
"loss": 0.216,
|
| 1092 |
"step": 1580
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
"epoch": 17.28,
|
| 1096 |
+
"learning_rate": 2.7608695652173917e-05,
|
| 1097 |
+
"loss": 0.2664,
|
| 1098 |
"step": 1590
|
| 1099 |
},
|
| 1100 |
{
|
| 1101 |
"epoch": 17.39,
|
| 1102 |
+
"learning_rate": 2.6521739130434787e-05,
|
| 1103 |
+
"loss": 0.2397,
|
| 1104 |
"step": 1600
|
| 1105 |
},
|
| 1106 |
{
|
| 1107 |
"epoch": 17.39,
|
| 1108 |
+
"eval_accuracy": 0.9807692307692307,
|
| 1109 |
+
"eval_loss": 0.06116783991456032,
|
| 1110 |
+
"eval_runtime": 1.9643,
|
| 1111 |
+
"eval_samples_per_second": 132.362,
|
| 1112 |
+
"eval_steps_per_second": 16.8,
|
| 1113 |
"step": 1600
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 17.5,
|
| 1117 |
+
"learning_rate": 2.543478260869565e-05,
|
| 1118 |
+
"loss": 0.1432,
|
| 1119 |
"step": 1610
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 17.61,
|
| 1123 |
+
"learning_rate": 2.4347826086956523e-05,
|
| 1124 |
+
"loss": 0.2176,
|
| 1125 |
"step": 1620
|
| 1126 |
},
|
| 1127 |
{
|
| 1128 |
"epoch": 17.72,
|
| 1129 |
+
"learning_rate": 2.3260869565217393e-05,
|
| 1130 |
+
"loss": 0.296,
|
| 1131 |
"step": 1630
|
| 1132 |
},
|
| 1133 |
{
|
| 1134 |
"epoch": 17.83,
|
| 1135 |
+
"learning_rate": 2.2173913043478262e-05,
|
| 1136 |
+
"loss": 0.2308,
|
| 1137 |
"step": 1640
|
| 1138 |
},
|
| 1139 |
{
|
| 1140 |
"epoch": 17.93,
|
| 1141 |
+
"learning_rate": 2.1086956521739132e-05,
|
| 1142 |
+
"loss": 0.1676,
|
| 1143 |
"step": 1650
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 18.04,
|
| 1147 |
+
"learning_rate": 2e-05,
|
| 1148 |
+
"loss": 0.1274,
|
| 1149 |
"step": 1660
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
"epoch": 18.15,
|
| 1153 |
+
"learning_rate": 1.8913043478260868e-05,
|
| 1154 |
+
"loss": 0.179,
|
| 1155 |
"step": 1670
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 18.26,
|
| 1159 |
+
"learning_rate": 1.782608695652174e-05,
|
| 1160 |
+
"loss": 0.1569,
|
| 1161 |
"step": 1680
|
| 1162 |
},
|
| 1163 |
{
|
| 1164 |
"epoch": 18.37,
|
| 1165 |
+
"learning_rate": 1.673913043478261e-05,
|
| 1166 |
+
"loss": 0.1897,
|
| 1167 |
"step": 1690
|
| 1168 |
},
|
| 1169 |
{
|
| 1170 |
"epoch": 18.48,
|
| 1171 |
+
"learning_rate": 1.565217391304348e-05,
|
| 1172 |
+
"loss": 0.1348,
|
| 1173 |
"step": 1700
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
"epoch": 18.48,
|
| 1177 |
+
"eval_accuracy": 0.9846153846153847,
|
| 1178 |
+
"eval_loss": 0.05584708973765373,
|
| 1179 |
+
"eval_runtime": 1.9494,
|
| 1180 |
+
"eval_samples_per_second": 133.373,
|
| 1181 |
+
"eval_steps_per_second": 16.928,
|
| 1182 |
"step": 1700
|
| 1183 |
},
|
| 1184 |
{
|
| 1185 |
"epoch": 18.59,
|
| 1186 |
+
"learning_rate": 1.4565217391304348e-05,
|
| 1187 |
+
"loss": 0.1662,
|
| 1188 |
"step": 1710
|
| 1189 |
},
|
| 1190 |
{
|
| 1191 |
"epoch": 18.7,
|
| 1192 |
+
"learning_rate": 1.3478260869565218e-05,
|
| 1193 |
+
"loss": 0.1644,
|
| 1194 |
"step": 1720
|
| 1195 |
},
|
| 1196 |
{
|
| 1197 |
"epoch": 18.8,
|
| 1198 |
+
"learning_rate": 1.2391304347826088e-05,
|
| 1199 |
+
"loss": 0.2025,
|
| 1200 |
"step": 1730
|
| 1201 |
},
|
| 1202 |
{
|
| 1203 |
"epoch": 18.91,
|
| 1204 |
+
"learning_rate": 1.1304347826086957e-05,
|
| 1205 |
+
"loss": 0.1745,
|
| 1206 |
"step": 1740
|
| 1207 |
},
|
| 1208 |
{
|
| 1209 |
"epoch": 19.02,
|
| 1210 |
+
"learning_rate": 1.0217391304347827e-05,
|
| 1211 |
+
"loss": 0.1786,
|
| 1212 |
"step": 1750
|
| 1213 |
},
|
| 1214 |
{
|
| 1215 |
"epoch": 19.13,
|
| 1216 |
+
"learning_rate": 9.130434782608697e-06,
|
| 1217 |
+
"loss": 0.2791,
|
| 1218 |
"step": 1760
|
| 1219 |
},
|
| 1220 |
{
|
| 1221 |
"epoch": 19.24,
|
| 1222 |
+
"learning_rate": 8.043478260869565e-06,
|
| 1223 |
+
"loss": 0.2056,
|
| 1224 |
"step": 1770
|
| 1225 |
},
|
| 1226 |
{
|
| 1227 |
"epoch": 19.35,
|
| 1228 |
+
"learning_rate": 6.956521739130435e-06,
|
| 1229 |
+
"loss": 0.2616,
|
| 1230 |
"step": 1780
|
| 1231 |
},
|
| 1232 |
{
|
| 1233 |
"epoch": 19.46,
|
| 1234 |
+
"learning_rate": 5.869565217391305e-06,
|
| 1235 |
+
"loss": 0.1488,
|
| 1236 |
"step": 1790
|
| 1237 |
},
|
| 1238 |
{
|
| 1239 |
"epoch": 19.57,
|
| 1240 |
+
"learning_rate": 4.782608695652174e-06,
|
| 1241 |
+
"loss": 0.2842,
|
| 1242 |
"step": 1800
|
| 1243 |
},
|
| 1244 |
{
|
| 1245 |
"epoch": 19.57,
|
| 1246 |
+
"eval_accuracy": 0.9769230769230769,
|
| 1247 |
+
"eval_loss": 0.05035410821437836,
|
| 1248 |
+
"eval_runtime": 1.9009,
|
| 1249 |
+
"eval_samples_per_second": 136.776,
|
| 1250 |
+
"eval_steps_per_second": 17.36,
|
| 1251 |
"step": 1800
|
| 1252 |
},
|
| 1253 |
{
|
| 1254 |
"epoch": 19.67,
|
| 1255 |
+
"learning_rate": 3.695652173913044e-06,
|
| 1256 |
+
"loss": 0.1487,
|
| 1257 |
"step": 1810
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
"epoch": 19.78,
|
| 1261 |
+
"learning_rate": 2.608695652173913e-06,
|
| 1262 |
+
"loss": 0.1818,
|
| 1263 |
"step": 1820
|
| 1264 |
},
|
| 1265 |
{
|
| 1266 |
"epoch": 19.89,
|
| 1267 |
+
"learning_rate": 1.5217391304347827e-06,
|
| 1268 |
+
"loss": 0.1469,
|
| 1269 |
"step": 1830
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
"epoch": 20.0,
|
| 1273 |
+
"learning_rate": 4.347826086956522e-07,
|
| 1274 |
+
"loss": 0.213,
|
| 1275 |
"step": 1840
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
+
"epoch": 20.0,
|
| 1279 |
+
"step": 1840,
|
| 1280 |
+
"total_flos": 7.30261234607063e+17,
|
| 1281 |
+
"train_loss": 0.5342570722103119,
|
| 1282 |
+
"train_runtime": 409.3983,
|
| 1283 |
+
"train_samples_per_second": 71.715,
|
| 1284 |
+
"train_steps_per_second": 4.494
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1285 |
}
|
| 1286 |
],
|
| 1287 |
"logging_steps": 10,
|
| 1288 |
+
"max_steps": 1840,
|
| 1289 |
+
"num_train_epochs": 20,
|
| 1290 |
"save_steps": 100,
|
| 1291 |
+
"total_flos": 7.30261234607063e+17,
|
| 1292 |
"trial_name": null,
|
| 1293 |
"trial_params": null
|
| 1294 |
}
|