Commit
·
b9a11b7
1
Parent(s):
c05bcc5
update
Browse files- pytorch_model.bin +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- trainer_state.json +587 -785
- training_args.bin +1 -1
- vocab.txt +0 -0
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95185ea87bb32530ed79219bebf3aca2d8cc305d6d0e6d42c65a8ac154fec4c0
|
| 3 |
+
size 435660145
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"do_lower_case":
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_type": "bert", "special_tokens_map_file": null, "name_or_path": "/lus/theta-fs0/projects/SolarWindowsADSP/shu/models/best_models/bert/batteryonlybert-uncased/", "tokenizer_class": "BertTokenizer"}
|
trainer_state.json
CHANGED
|
@@ -1,1180 +1,982 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
-
"epoch": 0.
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss": 0.
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0.
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch": 0.
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 2500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 3000
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0
|
| 48 |
-
"
|
| 49 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
"step": 3500
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch":
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 0.
|
| 56 |
"step": 4000
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"epoch":
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss": 0.
|
| 62 |
"step": 4500
|
| 63 |
},
|
| 64 |
{
|
| 65 |
-
"epoch":
|
| 66 |
-
"learning_rate":
|
| 67 |
-
"loss": 0.
|
| 68 |
"step": 5000
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch":
|
| 72 |
-
"learning_rate":
|
| 73 |
-
"loss": 0.
|
| 74 |
"step": 5500
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch":
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 6000
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch":
|
| 84 |
-
"eval_accuracy": 0.
|
| 85 |
-
"eval_f1": 0.
|
| 86 |
-
"eval_loss": 0.
|
| 87 |
-
"eval_precision": 0.
|
| 88 |
-
"eval_recall": 0.
|
| 89 |
-
"eval_runtime":
|
| 90 |
-
"eval_samples_per_second":
|
| 91 |
-
"eval_steps_per_second":
|
| 92 |
-
"step":
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch":
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss": 0.
|
| 98 |
"step": 6500
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch":
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss": 0.
|
| 104 |
"step": 7000
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch":
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss": 0.
|
| 110 |
"step": 7500
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"epoch":
|
| 114 |
-
"learning_rate":
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 8000
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch":
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss": 0.
|
| 122 |
"step": 8500
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch":
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 9000
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch":
|
| 132 |
-
"learning_rate":
|
| 133 |
-
"loss": 0.
|
| 134 |
"step": 9500
|
| 135 |
},
|
| 136 |
{
|
| 137 |
-
"epoch":
|
| 138 |
-
"
|
| 139 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 140 |
"step": 10000
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"epoch":
|
| 144 |
-
"learning_rate":
|
| 145 |
-
"loss": 0.
|
| 146 |
"step": 10500
|
| 147 |
},
|
| 148 |
{
|
| 149 |
-
"epoch":
|
| 150 |
-
"learning_rate":
|
| 151 |
-
"loss": 0.
|
| 152 |
"step": 11000
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"epoch":
|
| 156 |
-
"learning_rate":
|
| 157 |
-
"loss": 0.
|
| 158 |
"step": 11500
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"epoch":
|
| 162 |
-
"learning_rate":
|
| 163 |
-
"loss": 0.
|
| 164 |
"step": 12000
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"epoch":
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 12500
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch":
|
| 174 |
-
"eval_accuracy": 0.
|
| 175 |
-
"eval_f1": 0.
|
| 176 |
-
"eval_loss": 0.
|
| 177 |
-
"eval_precision": 0.
|
| 178 |
-
"eval_recall": 0.
|
| 179 |
-
"eval_runtime":
|
| 180 |
-
"eval_samples_per_second":
|
| 181 |
-
"eval_steps_per_second":
|
| 182 |
-
"step":
|
| 183 |
},
|
| 184 |
{
|
| 185 |
-
"epoch":
|
| 186 |
-
"learning_rate":
|
| 187 |
-
"loss": 0.
|
| 188 |
"step": 13000
|
| 189 |
},
|
| 190 |
{
|
| 191 |
-
"epoch":
|
| 192 |
-
"learning_rate":
|
| 193 |
-
"loss": 0.
|
| 194 |
"step": 13500
|
| 195 |
},
|
| 196 |
{
|
| 197 |
-
"epoch":
|
| 198 |
-
"learning_rate":
|
| 199 |
-
"loss": 0.
|
| 200 |
"step": 14000
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"epoch":
|
| 204 |
-
"learning_rate":
|
| 205 |
-
"loss": 0.
|
| 206 |
"step": 14500
|
| 207 |
},
|
| 208 |
{
|
| 209 |
-
"epoch":
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 15000
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch":
|
| 216 |
-
"learning_rate":
|
| 217 |
-
"loss": 0.
|
| 218 |
"step": 15500
|
| 219 |
},
|
| 220 |
{
|
| 221 |
-
"epoch":
|
| 222 |
-
"learning_rate":
|
| 223 |
-
"loss": 0.
|
| 224 |
"step": 16000
|
| 225 |
},
|
| 226 |
{
|
| 227 |
-
"epoch":
|
| 228 |
-
"
|
| 229 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 230 |
"step": 16500
|
| 231 |
},
|
| 232 |
{
|
| 233 |
-
"epoch":
|
| 234 |
-
"learning_rate":
|
| 235 |
-
"loss": 0.
|
| 236 |
"step": 17000
|
| 237 |
},
|
| 238 |
{
|
| 239 |
-
"epoch":
|
| 240 |
-
"learning_rate":
|
| 241 |
-
"loss": 0.
|
| 242 |
"step": 17500
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"epoch":
|
| 246 |
-
"learning_rate":
|
| 247 |
-
"loss": 0.
|
| 248 |
"step": 18000
|
| 249 |
},
|
| 250 |
{
|
| 251 |
-
"epoch":
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 18500
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch":
|
| 258 |
-
"learning_rate":
|
| 259 |
-
"loss": 0.
|
| 260 |
"step": 19000
|
| 261 |
},
|
| 262 |
{
|
| 263 |
-
"epoch":
|
| 264 |
-
"eval_accuracy": 0.
|
| 265 |
-
"eval_f1": 0.
|
| 266 |
-
"eval_loss": 0.
|
| 267 |
-
"eval_precision": 0.
|
| 268 |
-
"eval_recall": 0.
|
| 269 |
-
"eval_runtime":
|
| 270 |
-
"eval_samples_per_second":
|
| 271 |
-
"eval_steps_per_second":
|
| 272 |
-
"step":
|
| 273 |
},
|
| 274 |
{
|
| 275 |
-
"epoch":
|
| 276 |
-
"learning_rate":
|
| 277 |
-
"loss": 0.
|
| 278 |
"step": 19500
|
| 279 |
},
|
| 280 |
{
|
| 281 |
-
"epoch":
|
| 282 |
-
"learning_rate":
|
| 283 |
-
"loss": 0.
|
| 284 |
"step": 20000
|
| 285 |
},
|
| 286 |
{
|
| 287 |
-
"epoch":
|
| 288 |
-
"learning_rate":
|
| 289 |
-
"loss": 0.
|
| 290 |
"step": 20500
|
| 291 |
},
|
| 292 |
{
|
| 293 |
-
"epoch":
|
| 294 |
-
"learning_rate":
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 21000
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"epoch":
|
| 300 |
-
"learning_rate":
|
| 301 |
-
"loss": 0.
|
| 302 |
"step": 21500
|
| 303 |
},
|
| 304 |
{
|
| 305 |
-
"epoch":
|
| 306 |
-
"learning_rate": 1.
|
| 307 |
-
"loss": 0.
|
| 308 |
"step": 22000
|
| 309 |
},
|
| 310 |
{
|
| 311 |
-
"epoch":
|
| 312 |
-
"learning_rate": 1.
|
| 313 |
-
"loss": 0.
|
| 314 |
"step": 22500
|
| 315 |
},
|
| 316 |
{
|
| 317 |
-
"epoch":
|
| 318 |
-
"
|
| 319 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 320 |
"step": 23000
|
| 321 |
},
|
| 322 |
{
|
| 323 |
-
"epoch":
|
| 324 |
-
"learning_rate": 1.
|
| 325 |
-
"loss": 0.
|
| 326 |
"step": 23500
|
| 327 |
},
|
| 328 |
{
|
| 329 |
-
"epoch":
|
| 330 |
-
"learning_rate": 1.
|
| 331 |
-
"loss": 0.
|
| 332 |
"step": 24000
|
| 333 |
},
|
| 334 |
{
|
| 335 |
-
"epoch":
|
| 336 |
-
"learning_rate": 1.
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 24500
|
| 339 |
},
|
| 340 |
{
|
| 341 |
-
"epoch":
|
| 342 |
-
"learning_rate": 1.
|
| 343 |
-
"loss": 0.
|
| 344 |
"step": 25000
|
| 345 |
},
|
| 346 |
{
|
| 347 |
-
"epoch":
|
| 348 |
-
"learning_rate": 1.
|
| 349 |
-
"loss": 0.
|
| 350 |
"step": 25500
|
| 351 |
},
|
| 352 |
{
|
| 353 |
-
"epoch":
|
| 354 |
-
"eval_accuracy": 0.
|
| 355 |
-
"eval_f1": 0.
|
| 356 |
-
"eval_loss": 0.
|
| 357 |
-
"eval_precision": 0.
|
| 358 |
-
"eval_recall": 0.
|
| 359 |
-
"eval_runtime":
|
| 360 |
-
"eval_samples_per_second":
|
| 361 |
-
"eval_steps_per_second":
|
| 362 |
-
"step":
|
| 363 |
},
|
| 364 |
{
|
| 365 |
-
"epoch":
|
| 366 |
-
"learning_rate": 1.
|
| 367 |
-
"loss": 0.
|
| 368 |
"step": 26000
|
| 369 |
},
|
| 370 |
{
|
| 371 |
-
"epoch":
|
| 372 |
-
"learning_rate": 1.
|
| 373 |
-
"loss": 0.
|
| 374 |
"step": 26500
|
| 375 |
},
|
| 376 |
{
|
| 377 |
-
"epoch":
|
| 378 |
-
"learning_rate": 1.
|
| 379 |
-
"loss": 0.
|
| 380 |
"step": 27000
|
| 381 |
},
|
| 382 |
{
|
| 383 |
-
"epoch":
|
| 384 |
-
"learning_rate": 1.
|
| 385 |
-
"loss": 0.
|
| 386 |
"step": 27500
|
| 387 |
},
|
| 388 |
{
|
| 389 |
-
"epoch":
|
| 390 |
-
"learning_rate": 1.
|
| 391 |
-
"loss": 0.
|
| 392 |
"step": 28000
|
| 393 |
},
|
| 394 |
{
|
| 395 |
-
"epoch":
|
| 396 |
-
"learning_rate": 1.
|
| 397 |
-
"loss": 0.
|
| 398 |
"step": 28500
|
| 399 |
},
|
| 400 |
{
|
| 401 |
-
"epoch":
|
| 402 |
-
"learning_rate": 1.
|
| 403 |
-
"loss": 0.
|
| 404 |
"step": 29000
|
| 405 |
},
|
| 406 |
{
|
| 407 |
-
"epoch":
|
| 408 |
-
"
|
| 409 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 410 |
"step": 29500
|
| 411 |
},
|
| 412 |
{
|
| 413 |
-
"epoch":
|
| 414 |
-
"learning_rate": 1.
|
| 415 |
-
"loss": 0.
|
| 416 |
"step": 30000
|
| 417 |
},
|
| 418 |
{
|
| 419 |
-
"epoch":
|
| 420 |
-
"learning_rate": 1.
|
| 421 |
-
"loss": 0.
|
| 422 |
"step": 30500
|
| 423 |
},
|
| 424 |
{
|
| 425 |
-
"epoch":
|
| 426 |
-
"learning_rate": 1.
|
| 427 |
-
"loss": 0.
|
| 428 |
"step": 31000
|
| 429 |
},
|
| 430 |
{
|
| 431 |
-
"epoch":
|
| 432 |
-
"learning_rate": 1.
|
| 433 |
-
"loss": 0.
|
| 434 |
"step": 31500
|
| 435 |
},
|
| 436 |
{
|
| 437 |
-
"epoch":
|
| 438 |
-
"learning_rate": 1.
|
| 439 |
-
"loss": 0.
|
| 440 |
"step": 32000
|
| 441 |
},
|
| 442 |
{
|
| 443 |
-
"epoch":
|
| 444 |
-
"eval_accuracy": 0.
|
| 445 |
-
"eval_f1": 0.
|
| 446 |
-
"eval_loss": 0.
|
| 447 |
-
"eval_precision": 0.
|
| 448 |
-
"eval_recall": 0.
|
| 449 |
-
"eval_runtime": 50.
|
| 450 |
-
"eval_samples_per_second":
|
| 451 |
-
"eval_steps_per_second":
|
| 452 |
-
"step":
|
| 453 |
-
},
|
| 454 |
-
{
|
| 455 |
-
"epoch":
|
| 456 |
-
"learning_rate": 1.
|
| 457 |
-
"loss": 0.
|
| 458 |
"step": 32500
|
| 459 |
},
|
| 460 |
{
|
| 461 |
-
"epoch":
|
| 462 |
-
"learning_rate": 1.
|
| 463 |
-
"loss": 0.
|
| 464 |
"step": 33000
|
| 465 |
},
|
| 466 |
{
|
| 467 |
-
"epoch":
|
| 468 |
-
"learning_rate": 1.
|
| 469 |
-
"loss": 0.
|
| 470 |
"step": 33500
|
| 471 |
},
|
| 472 |
{
|
| 473 |
-
"epoch":
|
| 474 |
-
"learning_rate": 1.
|
| 475 |
-
"loss": 0.
|
| 476 |
"step": 34000
|
| 477 |
},
|
| 478 |
{
|
| 479 |
-
"epoch":
|
| 480 |
-
"learning_rate": 1.
|
| 481 |
-
"loss": 0.
|
| 482 |
"step": 34500
|
| 483 |
},
|
| 484 |
{
|
| 485 |
-
"epoch":
|
| 486 |
-
"learning_rate": 1.
|
| 487 |
-
"loss": 0.
|
| 488 |
"step": 35000
|
| 489 |
},
|
| 490 |
{
|
| 491 |
-
"epoch":
|
| 492 |
-
"learning_rate": 1.
|
| 493 |
-
"loss": 0.
|
| 494 |
"step": 35500
|
| 495 |
},
|
| 496 |
{
|
| 497 |
-
"epoch":
|
| 498 |
-
"
|
| 499 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 500 |
"step": 36000
|
| 501 |
},
|
| 502 |
{
|
| 503 |
-
"epoch":
|
| 504 |
-
"learning_rate": 1.
|
| 505 |
-
"loss": 0.
|
| 506 |
"step": 36500
|
| 507 |
},
|
| 508 |
{
|
| 509 |
-
"epoch":
|
| 510 |
-
"learning_rate": 1.
|
| 511 |
-
"loss": 0.
|
| 512 |
"step": 37000
|
| 513 |
},
|
| 514 |
{
|
| 515 |
-
"epoch":
|
| 516 |
-
"learning_rate": 1.
|
| 517 |
-
"loss": 0.
|
| 518 |
"step": 37500
|
| 519 |
},
|
| 520 |
{
|
| 521 |
-
"epoch":
|
| 522 |
-
"learning_rate": 1.
|
| 523 |
-
"loss": 0.
|
| 524 |
"step": 38000
|
| 525 |
},
|
| 526 |
{
|
| 527 |
-
"epoch":
|
| 528 |
-
"learning_rate": 1.
|
| 529 |
-
"loss": 0.
|
| 530 |
"step": 38500
|
| 531 |
},
|
| 532 |
{
|
| 533 |
-
"epoch":
|
| 534 |
-
"eval_accuracy": 0.
|
| 535 |
-
"eval_f1": 0.
|
| 536 |
-
"eval_loss": 0.
|
| 537 |
-
"eval_precision": 0.
|
| 538 |
-
"eval_recall": 0.
|
| 539 |
-
"eval_runtime": 50.
|
| 540 |
-
"eval_samples_per_second":
|
| 541 |
-
"eval_steps_per_second":
|
| 542 |
-
"step":
|
| 543 |
},
|
| 544 |
{
|
| 545 |
-
"epoch":
|
| 546 |
-
"learning_rate": 1.
|
| 547 |
-
"loss": 0.
|
| 548 |
"step": 39000
|
| 549 |
},
|
| 550 |
{
|
| 551 |
-
"epoch":
|
| 552 |
-
"learning_rate": 1.
|
| 553 |
-
"loss": 0.
|
| 554 |
"step": 39500
|
| 555 |
},
|
| 556 |
{
|
| 557 |
-
"epoch":
|
| 558 |
-
"learning_rate": 1.
|
| 559 |
-
"loss": 0.
|
| 560 |
"step": 40000
|
| 561 |
},
|
| 562 |
{
|
| 563 |
-
"epoch":
|
| 564 |
-
"learning_rate": 1.
|
| 565 |
-
"loss": 0.
|
| 566 |
"step": 40500
|
| 567 |
},
|
| 568 |
{
|
| 569 |
-
"epoch":
|
| 570 |
-
"learning_rate": 1.
|
| 571 |
-
"loss": 0.
|
| 572 |
"step": 41000
|
| 573 |
},
|
| 574 |
{
|
| 575 |
-
"epoch":
|
| 576 |
-
"learning_rate": 1.
|
| 577 |
-
"loss": 0.
|
| 578 |
"step": 41500
|
| 579 |
},
|
| 580 |
{
|
| 581 |
-
"epoch":
|
| 582 |
-
"learning_rate": 1.
|
| 583 |
-
"loss": 0.
|
| 584 |
"step": 42000
|
| 585 |
},
|
| 586 |
{
|
| 587 |
-
"epoch":
|
| 588 |
-
"
|
| 589 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 590 |
"step": 42500
|
| 591 |
},
|
| 592 |
{
|
| 593 |
-
"epoch":
|
| 594 |
-
"learning_rate": 1.
|
| 595 |
-
"loss": 0.
|
| 596 |
"step": 43000
|
| 597 |
},
|
| 598 |
{
|
| 599 |
-
"epoch":
|
| 600 |
-
"learning_rate":
|
| 601 |
-
"loss": 0.
|
| 602 |
"step": 43500
|
| 603 |
},
|
| 604 |
{
|
| 605 |
-
"epoch":
|
| 606 |
-
"learning_rate":
|
| 607 |
-
"loss": 0.
|
| 608 |
"step": 44000
|
| 609 |
},
|
| 610 |
{
|
| 611 |
-
"epoch":
|
| 612 |
-
"learning_rate":
|
| 613 |
-
"loss": 0.
|
| 614 |
"step": 44500
|
| 615 |
},
|
| 616 |
{
|
| 617 |
-
"epoch":
|
| 618 |
-
"learning_rate":
|
| 619 |
-
"loss": 0.
|
| 620 |
"step": 45000
|
| 621 |
},
|
| 622 |
{
|
| 623 |
-
"epoch":
|
| 624 |
-
"eval_accuracy": 0.
|
| 625 |
-
"eval_f1": 0.
|
| 626 |
-
"eval_loss": 0.
|
| 627 |
-
"eval_precision": 0.
|
| 628 |
-
"eval_recall": 0.
|
| 629 |
-
"eval_runtime":
|
| 630 |
-
"eval_samples_per_second":
|
| 631 |
-
"eval_steps_per_second":
|
| 632 |
-
"step":
|
| 633 |
-
},
|
| 634 |
-
{
|
| 635 |
-
"epoch":
|
| 636 |
-
"learning_rate":
|
| 637 |
-
"loss": 0.
|
| 638 |
"step": 45500
|
| 639 |
},
|
| 640 |
{
|
| 641 |
-
"epoch":
|
| 642 |
-
"learning_rate":
|
| 643 |
-
"loss": 0.
|
| 644 |
"step": 46000
|
| 645 |
},
|
| 646 |
{
|
| 647 |
-
"epoch":
|
| 648 |
-
"learning_rate":
|
| 649 |
-
"loss": 0.
|
| 650 |
"step": 46500
|
| 651 |
},
|
| 652 |
{
|
| 653 |
-
"epoch":
|
| 654 |
-
"learning_rate":
|
| 655 |
-
"loss": 0.
|
| 656 |
"step": 47000
|
| 657 |
},
|
| 658 |
{
|
| 659 |
-
"epoch":
|
| 660 |
-
"learning_rate":
|
| 661 |
-
"loss": 0.
|
| 662 |
"step": 47500
|
| 663 |
},
|
| 664 |
{
|
| 665 |
-
"epoch":
|
| 666 |
-
"learning_rate":
|
| 667 |
-
"loss": 0.
|
| 668 |
"step": 48000
|
| 669 |
},
|
| 670 |
{
|
| 671 |
-
"epoch":
|
| 672 |
-
"learning_rate":
|
| 673 |
-
"loss": 0.
|
| 674 |
"step": 48500
|
| 675 |
},
|
| 676 |
{
|
| 677 |
-
"epoch":
|
| 678 |
-
"
|
| 679 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 680 |
"step": 49000
|
| 681 |
},
|
| 682 |
{
|
| 683 |
-
"epoch":
|
| 684 |
-
"learning_rate":
|
| 685 |
-
"loss": 0.
|
| 686 |
"step": 49500
|
| 687 |
},
|
| 688 |
{
|
| 689 |
-
"epoch":
|
| 690 |
-
"learning_rate":
|
| 691 |
-
"loss": 0.
|
| 692 |
"step": 50000
|
| 693 |
},
|
| 694 |
{
|
| 695 |
-
"epoch":
|
| 696 |
-
"learning_rate":
|
| 697 |
-
"loss": 0.
|
| 698 |
"step": 50500
|
| 699 |
},
|
| 700 |
{
|
| 701 |
-
"epoch":
|
| 702 |
-
"learning_rate":
|
| 703 |
-
"loss": 0.
|
| 704 |
"step": 51000
|
| 705 |
},
|
| 706 |
{
|
| 707 |
-
"epoch":
|
| 708 |
-
"learning_rate":
|
| 709 |
-
"loss": 0.
|
| 710 |
"step": 51500
|
| 711 |
},
|
| 712 |
{
|
| 713 |
-
"epoch":
|
| 714 |
-
"eval_accuracy": 0.
|
| 715 |
-
"eval_f1": 0.
|
| 716 |
-
"eval_loss": 0.
|
| 717 |
-
"eval_precision": 0.
|
| 718 |
-
"eval_recall": 0.
|
| 719 |
-
"eval_runtime":
|
| 720 |
-
"eval_samples_per_second":
|
| 721 |
-
"eval_steps_per_second":
|
| 722 |
-
"step":
|
| 723 |
},
|
| 724 |
{
|
| 725 |
-
"epoch":
|
| 726 |
-
"learning_rate":
|
| 727 |
-
"loss": 0.
|
| 728 |
"step": 52000
|
| 729 |
},
|
| 730 |
{
|
| 731 |
-
"epoch":
|
| 732 |
-
"learning_rate":
|
| 733 |
-
"loss": 0.
|
| 734 |
"step": 52500
|
| 735 |
},
|
| 736 |
{
|
| 737 |
-
"epoch":
|
| 738 |
-
"learning_rate":
|
| 739 |
-
"loss": 0.
|
| 740 |
"step": 53000
|
| 741 |
},
|
| 742 |
{
|
| 743 |
-
"epoch":
|
| 744 |
-
"learning_rate":
|
| 745 |
-
"loss": 0.
|
| 746 |
"step": 53500
|
| 747 |
},
|
| 748 |
{
|
| 749 |
-
"epoch":
|
| 750 |
-
"learning_rate":
|
| 751 |
-
"loss": 0.
|
| 752 |
"step": 54000
|
| 753 |
},
|
| 754 |
{
|
| 755 |
-
"epoch":
|
| 756 |
-
"learning_rate":
|
| 757 |
-
"loss": 0.
|
| 758 |
"step": 54500
|
| 759 |
},
|
| 760 |
{
|
| 761 |
-
"epoch":
|
| 762 |
-
"learning_rate":
|
| 763 |
-
"loss": 0.0013,
|
| 764 |
-
"step": 55000
|
| 765 |
-
},
|
| 766 |
-
{
|
| 767 |
-
"epoch": 8.55,
|
| 768 |
-
"learning_rate": 8.603111042661328e-06,
|
| 769 |
-
"loss": 0.0013,
|
| 770 |
-
"step": 55500
|
| 771 |
-
},
|
| 772 |
-
{
|
| 773 |
-
"epoch": 8.62,
|
| 774 |
-
"learning_rate": 8.50043636736999e-06,
|
| 775 |
-
"loss": 0.0011,
|
| 776 |
-
"step": 56000
|
| 777 |
-
},
|
| 778 |
-
{
|
| 779 |
-
"epoch": 8.7,
|
| 780 |
-
"learning_rate": 8.39776169207865e-06,
|
| 781 |
-
"loss": 0.0014,
|
| 782 |
-
"step": 56500
|
| 783 |
-
},
|
| 784 |
-
{
|
| 785 |
-
"epoch": 8.78,
|
| 786 |
-
"learning_rate": 8.29508701678731e-06,
|
| 787 |
-
"loss": 0.0016,
|
| 788 |
-
"step": 57000
|
| 789 |
-
},
|
| 790 |
-
{
|
| 791 |
-
"epoch": 8.86,
|
| 792 |
-
"learning_rate": 8.19241234149597e-06,
|
| 793 |
-
"loss": 0.0015,
|
| 794 |
-
"step": 57500
|
| 795 |
-
},
|
| 796 |
-
{
|
| 797 |
-
"epoch": 8.93,
|
| 798 |
-
"learning_rate": 8.089737666204631e-06,
|
| 799 |
-
"loss": 0.0019,
|
| 800 |
-
"step": 58000
|
| 801 |
-
},
|
| 802 |
-
{
|
| 803 |
-
"epoch": 9.0,
|
| 804 |
-
"eval_accuracy": 0.9969735432546178,
|
| 805 |
-
"eval_f1": 0.957957696804553,
|
| 806 |
-
"eval_loss": 0.02377239800989628,
|
| 807 |
-
"eval_precision": 0.9470949005521695,
|
| 808 |
-
"eval_recall": 0.9690725680325305,
|
| 809 |
-
"eval_runtime": 57.1242,
|
| 810 |
-
"eval_samples_per_second": 389.152,
|
| 811 |
-
"eval_steps_per_second": 24.333,
|
| 812 |
-
"step": 58437
|
| 813 |
-
},
|
| 814 |
-
{
|
| 815 |
-
"epoch": 9.01,
|
| 816 |
-
"learning_rate": 7.987062990913292e-06,
|
| 817 |
-
"loss": 0.0014,
|
| 818 |
-
"step": 58500
|
| 819 |
-
},
|
| 820 |
-
{
|
| 821 |
-
"epoch": 9.09,
|
| 822 |
-
"learning_rate": 7.884388315621953e-06,
|
| 823 |
-
"loss": 0.0014,
|
| 824 |
-
"step": 59000
|
| 825 |
-
},
|
| 826 |
-
{
|
| 827 |
-
"epoch": 9.16,
|
| 828 |
-
"learning_rate": 7.781713640330612e-06,
|
| 829 |
-
"loss": 0.0013,
|
| 830 |
-
"step": 59500
|
| 831 |
-
},
|
| 832 |
-
{
|
| 833 |
-
"epoch": 9.24,
|
| 834 |
-
"learning_rate": 7.679038965039273e-06,
|
| 835 |
-
"loss": 0.0013,
|
| 836 |
-
"step": 60000
|
| 837 |
-
},
|
| 838 |
-
{
|
| 839 |
-
"epoch": 9.32,
|
| 840 |
-
"learning_rate": 7.576364289747934e-06,
|
| 841 |
-
"loss": 0.0012,
|
| 842 |
-
"step": 60500
|
| 843 |
-
},
|
| 844 |
-
{
|
| 845 |
-
"epoch": 9.39,
|
| 846 |
-
"learning_rate": 7.473689614456595e-06,
|
| 847 |
-
"loss": 0.0011,
|
| 848 |
-
"step": 61000
|
| 849 |
-
},
|
| 850 |
-
{
|
| 851 |
-
"epoch": 9.47,
|
| 852 |
-
"learning_rate": 7.371014939165256e-06,
|
| 853 |
"loss": 0.001,
|
| 854 |
-
"step":
|
| 855 |
-
},
|
| 856 |
-
{
|
| 857 |
-
"epoch": 9.55,
|
| 858 |
-
"learning_rate": 7.2683402638739165e-06,
|
| 859 |
-
"loss": 0.0014,
|
| 860 |
-
"step": 62000
|
| 861 |
-
},
|
| 862 |
-
{
|
| 863 |
-
"epoch": 9.63,
|
| 864 |
-
"learning_rate": 7.1656655885825765e-06,
|
| 865 |
-
"loss": 0.0011,
|
| 866 |
-
"step": 62500
|
| 867 |
-
},
|
| 868 |
-
{
|
| 869 |
-
"epoch": 9.7,
|
| 870 |
-
"learning_rate": 7.062990913291237e-06,
|
| 871 |
-
"loss": 0.0014,
|
| 872 |
-
"step": 63000
|
| 873 |
-
},
|
| 874 |
-
{
|
| 875 |
-
"epoch": 9.78,
|
| 876 |
-
"learning_rate": 6.960316237999898e-06,
|
| 877 |
-
"loss": 0.0009,
|
| 878 |
-
"step": 63500
|
| 879 |
-
},
|
| 880 |
-
{
|
| 881 |
-
"epoch": 9.86,
|
| 882 |
-
"learning_rate": 6.857641562708558e-06,
|
| 883 |
-
"loss": 0.0011,
|
| 884 |
-
"step": 64000
|
| 885 |
-
},
|
| 886 |
-
{
|
| 887 |
-
"epoch": 9.93,
|
| 888 |
-
"learning_rate": 6.754966887417219e-06,
|
| 889 |
-
"loss": 0.0012,
|
| 890 |
-
"step": 64500
|
| 891 |
-
},
|
| 892 |
-
{
|
| 893 |
-
"epoch": 10.0,
|
| 894 |
-
"eval_accuracy": 0.9970482413055323,
|
| 895 |
-
"eval_f1": 0.9589748568100184,
|
| 896 |
-
"eval_loss": 0.02672559767961502,
|
| 897 |
-
"eval_precision": 0.9524470669906282,
|
| 898 |
-
"eval_recall": 0.9655927431967469,
|
| 899 |
-
"eval_runtime": 50.0835,
|
| 900 |
-
"eval_samples_per_second": 443.858,
|
| 901 |
-
"eval_steps_per_second": 27.754,
|
| 902 |
-
"step": 64930
|
| 903 |
-
},
|
| 904 |
-
{
|
| 905 |
-
"epoch": 10.01,
|
| 906 |
-
"learning_rate": 6.652292212125879e-06,
|
| 907 |
-
"loss": 0.0014,
|
| 908 |
-
"step": 65000
|
| 909 |
-
},
|
| 910 |
-
{
|
| 911 |
-
"epoch": 10.09,
|
| 912 |
-
"learning_rate": 6.54961753683454e-06,
|
| 913 |
-
"loss": 0.001,
|
| 914 |
-
"step": 65500
|
| 915 |
-
},
|
| 916 |
-
{
|
| 917 |
-
"epoch": 10.16,
|
| 918 |
-
"learning_rate": 6.446942861543201e-06,
|
| 919 |
-
"loss": 0.0009,
|
| 920 |
-
"step": 66000
|
| 921 |
-
},
|
| 922 |
-
{
|
| 923 |
-
"epoch": 10.24,
|
| 924 |
-
"learning_rate": 6.344268186251862e-06,
|
| 925 |
-
"loss": 0.0007,
|
| 926 |
-
"step": 66500
|
| 927 |
-
},
|
| 928 |
-
{
|
| 929 |
-
"epoch": 10.32,
|
| 930 |
-
"learning_rate": 6.241593510960522e-06,
|
| 931 |
-
"loss": 0.0009,
|
| 932 |
-
"step": 67000
|
| 933 |
-
},
|
| 934 |
-
{
|
| 935 |
-
"epoch": 10.4,
|
| 936 |
-
"learning_rate": 6.138918835669183e-06,
|
| 937 |
-
"loss": 0.001,
|
| 938 |
-
"step": 67500
|
| 939 |
-
},
|
| 940 |
-
{
|
| 941 |
-
"epoch": 10.47,
|
| 942 |
-
"learning_rate": 6.036244160377844e-06,
|
| 943 |
-
"loss": 0.0011,
|
| 944 |
-
"step": 68000
|
| 945 |
-
},
|
| 946 |
-
{
|
| 947 |
-
"epoch": 10.55,
|
| 948 |
-
"learning_rate": 5.9335694850865045e-06,
|
| 949 |
-
"loss": 0.0011,
|
| 950 |
-
"step": 68500
|
| 951 |
-
},
|
| 952 |
-
{
|
| 953 |
-
"epoch": 10.63,
|
| 954 |
-
"learning_rate": 5.8308948097951645e-06,
|
| 955 |
-
"loss": 0.001,
|
| 956 |
-
"step": 69000
|
| 957 |
-
},
|
| 958 |
-
{
|
| 959 |
-
"epoch": 10.7,
|
| 960 |
-
"learning_rate": 5.7282201345038246e-06,
|
| 961 |
-
"loss": 0.0011,
|
| 962 |
-
"step": 69500
|
| 963 |
-
},
|
| 964 |
-
{
|
| 965 |
-
"epoch": 10.78,
|
| 966 |
-
"learning_rate": 5.6255454592124854e-06,
|
| 967 |
-
"loss": 0.001,
|
| 968 |
-
"step": 70000
|
| 969 |
-
},
|
| 970 |
-
{
|
| 971 |
-
"epoch": 10.86,
|
| 972 |
-
"learning_rate": 5.522870783921146e-06,
|
| 973 |
-
"loss": 0.0007,
|
| 974 |
-
"step": 70500
|
| 975 |
-
},
|
| 976 |
-
{
|
| 977 |
-
"epoch": 10.93,
|
| 978 |
-
"learning_rate": 5.420196108629807e-06,
|
| 979 |
-
"loss": 0.0012,
|
| 980 |
-
"step": 71000
|
| 981 |
},
|
| 982 |
{
|
| 983 |
-
"epoch":
|
| 984 |
-
"eval_accuracy": 0.
|
| 985 |
-
"eval_f1": 0.
|
| 986 |
-
"eval_loss": 0.
|
| 987 |
-
"eval_precision": 0.
|
| 988 |
-
"eval_recall": 0.
|
| 989 |
-
"eval_runtime":
|
| 990 |
-
"eval_samples_per_second":
|
| 991 |
-
"eval_steps_per_second":
|
| 992 |
-
"step":
|
| 993 |
-
},
|
| 994 |
-
{
|
| 995 |
-
"epoch": 11.01,
|
| 996 |
-
"learning_rate": 5.317521433338467e-06,
|
| 997 |
-
"loss": 0.0008,
|
| 998 |
-
"step": 71500
|
| 999 |
},
|
| 1000 |
{
|
| 1001 |
-
"epoch":
|
| 1002 |
-
"learning_rate":
|
| 1003 |
"loss": 0.0008,
|
| 1004 |
-
"step":
|
| 1005 |
},
|
| 1006 |
{
|
| 1007 |
-
"epoch":
|
| 1008 |
-
"learning_rate":
|
| 1009 |
"loss": 0.0008,
|
| 1010 |
-
"step":
|
| 1011 |
-
},
|
| 1012 |
-
{
|
| 1013 |
-
"epoch": 11.24,
|
| 1014 |
-
"learning_rate": 5.00949740746445e-06,
|
| 1015 |
-
"loss": 0.0007,
|
| 1016 |
-
"step": 73000
|
| 1017 |
-
},
|
| 1018 |
-
{
|
| 1019 |
-
"epoch": 11.32,
|
| 1020 |
-
"learning_rate": 4.90682273217311e-06,
|
| 1021 |
-
"loss": 0.0007,
|
| 1022 |
-
"step": 73500
|
| 1023 |
-
},
|
| 1024 |
-
{
|
| 1025 |
-
"epoch": 11.4,
|
| 1026 |
-
"learning_rate": 4.804148056881771e-06,
|
| 1027 |
-
"loss": 0.0007,
|
| 1028 |
-
"step": 74000
|
| 1029 |
-
},
|
| 1030 |
-
{
|
| 1031 |
-
"epoch": 11.47,
|
| 1032 |
-
"learning_rate": 4.701473381590432e-06,
|
| 1033 |
-
"loss": 0.0009,
|
| 1034 |
-
"step": 74500
|
| 1035 |
-
},
|
| 1036 |
-
{
|
| 1037 |
-
"epoch": 11.55,
|
| 1038 |
-
"learning_rate": 4.598798706299092e-06,
|
| 1039 |
-
"loss": 0.0007,
|
| 1040 |
-
"step": 75000
|
| 1041 |
},
|
| 1042 |
{
|
| 1043 |
-
"epoch":
|
| 1044 |
-
"learning_rate":
|
| 1045 |
"loss": 0.0008,
|
| 1046 |
-
"step":
|
| 1047 |
-
},
|
| 1048 |
-
{
|
| 1049 |
-
"epoch": 11.7,
|
| 1050 |
-
"learning_rate": 4.393449355716413e-06,
|
| 1051 |
-
"loss": 0.0007,
|
| 1052 |
-
"step": 76000
|
| 1053 |
-
},
|
| 1054 |
-
{
|
| 1055 |
-
"epoch": 11.78,
|
| 1056 |
-
"learning_rate": 4.2907746804250734e-06,
|
| 1057 |
-
"loss": 0.0007,
|
| 1058 |
-
"step": 76500
|
| 1059 |
-
},
|
| 1060 |
-
{
|
| 1061 |
-
"epoch": 11.86,
|
| 1062 |
-
"learning_rate": 4.188100005133734e-06,
|
| 1063 |
-
"loss": 0.0007,
|
| 1064 |
-
"step": 77000
|
| 1065 |
-
},
|
| 1066 |
-
{
|
| 1067 |
-
"epoch": 11.94,
|
| 1068 |
-
"learning_rate": 4.085425329842394e-06,
|
| 1069 |
-
"loss": 0.0007,
|
| 1070 |
-
"step": 77500
|
| 1071 |
-
},
|
| 1072 |
-
{
|
| 1073 |
-
"epoch": 12.0,
|
| 1074 |
-
"eval_accuracy": 0.9971656239569692,
|
| 1075 |
-
"eval_f1": 0.9604331205247123,
|
| 1076 |
-
"eval_loss": 0.02845791168510914,
|
| 1077 |
-
"eval_precision": 0.953384443502716,
|
| 1078 |
-
"eval_recall": 0.9675868001251173,
|
| 1079 |
-
"eval_runtime": 49.6251,
|
| 1080 |
-
"eval_samples_per_second": 447.959,
|
| 1081 |
-
"eval_steps_per_second": 28.01,
|
| 1082 |
-
"step": 77916
|
| 1083 |
},
|
| 1084 |
{
|
| 1085 |
-
"epoch":
|
| 1086 |
-
"learning_rate": 3.
|
| 1087 |
"loss": 0.0007,
|
| 1088 |
-
"step":
|
| 1089 |
},
|
| 1090 |
{
|
| 1091 |
-
"epoch":
|
| 1092 |
-
"learning_rate": 3.
|
| 1093 |
"loss": 0.0007,
|
| 1094 |
-
"step":
|
| 1095 |
-
},
|
| 1096 |
-
{
|
| 1097 |
-
"epoch": 12.17,
|
| 1098 |
-
"learning_rate": 3.7774013039683766e-06,
|
| 1099 |
-
"loss": 0.0008,
|
| 1100 |
-
"step": 79000
|
| 1101 |
},
|
| 1102 |
{
|
| 1103 |
-
"epoch":
|
| 1104 |
-
"learning_rate": 3.
|
| 1105 |
-
"loss": 0.
|
| 1106 |
-
"step":
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
-
"epoch":
|
| 1110 |
-
"
|
| 1111 |
-
"
|
| 1112 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1113 |
},
|
| 1114 |
{
|
| 1115 |
-
"epoch":
|
| 1116 |
-
"learning_rate":
|
| 1117 |
"loss": 0.0007,
|
| 1118 |
-
"step":
|
| 1119 |
},
|
| 1120 |
{
|
| 1121 |
-
"epoch":
|
| 1122 |
-
"learning_rate":
|
| 1123 |
"loss": 0.0007,
|
| 1124 |
-
"step":
|
| 1125 |
},
|
| 1126 |
{
|
| 1127 |
-
"epoch":
|
| 1128 |
-
"learning_rate":
|
| 1129 |
"loss": 0.0006,
|
| 1130 |
-
"step":
|
| 1131 |
},
|
| 1132 |
{
|
| 1133 |
-
"epoch":
|
| 1134 |
-
"learning_rate":
|
| 1135 |
-
"loss": 0.
|
| 1136 |
-
"step":
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
-
"epoch":
|
| 1140 |
-
"learning_rate":
|
| 1141 |
"loss": 0.0007,
|
| 1142 |
-
"step":
|
| 1143 |
-
},
|
| 1144 |
-
{
|
| 1145 |
-
"epoch": 12.78,
|
| 1146 |
-
"learning_rate": 2.9560039016376615e-06,
|
| 1147 |
-
"loss": 0.0006,
|
| 1148 |
-
"step": 83000
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
-
"epoch":
|
| 1152 |
-
"learning_rate":
|
| 1153 |
-
"loss": 0.
|
| 1154 |
-
"step":
|
| 1155 |
},
|
| 1156 |
{
|
| 1157 |
-
"epoch":
|
| 1158 |
-
"learning_rate":
|
| 1159 |
"loss": 0.0006,
|
| 1160 |
-
"step":
|
| 1161 |
},
|
| 1162 |
{
|
| 1163 |
-
"epoch":
|
| 1164 |
-
"eval_accuracy": 0.
|
| 1165 |
-
"eval_f1": 0.
|
| 1166 |
-
"eval_loss": 0.
|
| 1167 |
-
"eval_precision": 0.
|
| 1168 |
-
"eval_recall": 0.
|
| 1169 |
-
"eval_runtime":
|
| 1170 |
-
"eval_samples_per_second":
|
| 1171 |
-
"eval_steps_per_second":
|
| 1172 |
-
"step":
|
| 1173 |
}
|
| 1174 |
],
|
| 1175 |
-
"max_steps":
|
| 1176 |
-
"num_train_epochs":
|
| 1177 |
-
"total_flos":
|
| 1178 |
"trial_name": null,
|
| 1179 |
"trial_params": null
|
| 1180 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.0,
|
| 5 |
+
"global_step": 61693,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.15,
|
| 12 |
+
"learning_rate": 2.9769017554665847e-05,
|
| 13 |
+
"loss": 0.0666,
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.31,
|
| 18 |
+
"learning_rate": 2.953803510933169e-05,
|
| 19 |
+
"loss": 0.0447,
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.46,
|
| 24 |
+
"learning_rate": 2.9307052663997538e-05,
|
| 25 |
+
"loss": 0.0411,
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.62,
|
| 30 |
+
"learning_rate": 2.9076070218663384e-05,
|
| 31 |
+
"loss": 0.038,
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.77,
|
| 36 |
+
"learning_rate": 2.8845087773329226e-05,
|
| 37 |
+
"loss": 0.0346,
|
| 38 |
"step": 2500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.92,
|
| 42 |
+
"learning_rate": 2.8614105327995072e-05,
|
| 43 |
+
"loss": 0.0332,
|
| 44 |
"step": 3000
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_accuracy": 0.9877246731440231,
|
| 49 |
+
"eval_f1": 0.889670288672294,
|
| 50 |
+
"eval_loss": 0.03370480611920357,
|
| 51 |
+
"eval_precision": 0.8513566583363085,
|
| 52 |
+
"eval_recall": 0.9315948823127258,
|
| 53 |
+
"eval_runtime": 50.7022,
|
| 54 |
+
"eval_samples_per_second": 438.443,
|
| 55 |
+
"eval_steps_per_second": 13.708,
|
| 56 |
+
"step": 3247
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.08,
|
| 60 |
+
"learning_rate": 2.8383122882660918e-05,
|
| 61 |
+
"loss": 0.0291,
|
| 62 |
"step": 3500
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 1.23,
|
| 66 |
+
"learning_rate": 2.8152140437326767e-05,
|
| 67 |
+
"loss": 0.0226,
|
| 68 |
"step": 4000
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 1.39,
|
| 72 |
+
"learning_rate": 2.792115799199261e-05,
|
| 73 |
+
"loss": 0.023,
|
| 74 |
"step": 4500
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 1.54,
|
| 78 |
+
"learning_rate": 2.7690175546658455e-05,
|
| 79 |
+
"loss": 0.0235,
|
| 80 |
"step": 5000
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 1.69,
|
| 84 |
+
"learning_rate": 2.74591931013243e-05,
|
| 85 |
+
"loss": 0.023,
|
| 86 |
"step": 5500
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 1.85,
|
| 90 |
+
"learning_rate": 2.7228210655990143e-05,
|
| 91 |
+
"loss": 0.0218,
|
| 92 |
"step": 6000
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 2.0,
|
| 96 |
+
"eval_accuracy": 0.9908514749994501,
|
| 97 |
+
"eval_f1": 0.9142371280113368,
|
| 98 |
+
"eval_loss": 0.0262825395911932,
|
| 99 |
+
"eval_precision": 0.8852986917939805,
|
| 100 |
+
"eval_recall": 0.9451313604844223,
|
| 101 |
+
"eval_runtime": 50.2363,
|
| 102 |
+
"eval_samples_per_second": 442.508,
|
| 103 |
+
"eval_steps_per_second": 13.835,
|
| 104 |
+
"step": 6494
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 2.0,
|
| 108 |
+
"learning_rate": 2.6997228210655992e-05,
|
| 109 |
+
"loss": 0.0228,
|
| 110 |
"step": 6500
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"epoch": 2.16,
|
| 114 |
+
"learning_rate": 2.6766245765321838e-05,
|
| 115 |
+
"loss": 0.014,
|
| 116 |
"step": 7000
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 2.31,
|
| 120 |
+
"learning_rate": 2.653526331998768e-05,
|
| 121 |
+
"loss": 0.0143,
|
| 122 |
"step": 7500
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 2.46,
|
| 126 |
+
"learning_rate": 2.6304280874653526e-05,
|
| 127 |
+
"loss": 0.0158,
|
| 128 |
"step": 8000
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 2.62,
|
| 132 |
+
"learning_rate": 2.6073298429319372e-05,
|
| 133 |
+
"loss": 0.015,
|
| 134 |
"step": 8500
|
| 135 |
},
|
| 136 |
{
|
| 137 |
+
"epoch": 2.77,
|
| 138 |
+
"learning_rate": 2.5842315983985218e-05,
|
| 139 |
+
"loss": 0.0142,
|
| 140 |
"step": 9000
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"epoch": 2.93,
|
| 144 |
+
"learning_rate": 2.5611333538651064e-05,
|
| 145 |
+
"loss": 0.0147,
|
| 146 |
"step": 9500
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"epoch": 3.0,
|
| 150 |
+
"eval_accuracy": 0.9930254150662127,
|
| 151 |
+
"eval_f1": 0.9280089446645269,
|
| 152 |
+
"eval_loss": 0.024331996217370033,
|
| 153 |
+
"eval_precision": 0.9160101990333752,
|
| 154 |
+
"eval_recall": 0.9403262037308331,
|
| 155 |
+
"eval_runtime": 50.2727,
|
| 156 |
+
"eval_samples_per_second": 442.188,
|
| 157 |
+
"eval_steps_per_second": 13.825,
|
| 158 |
+
"step": 9741
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.08,
|
| 162 |
+
"learning_rate": 2.538035109331691e-05,
|
| 163 |
+
"loss": 0.0122,
|
| 164 |
"step": 10000
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 3.23,
|
| 168 |
+
"learning_rate": 2.5149368647982755e-05,
|
| 169 |
+
"loss": 0.0103,
|
| 170 |
"step": 10500
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 3.39,
|
| 174 |
+
"learning_rate": 2.4918386202648598e-05,
|
| 175 |
+
"loss": 0.0095,
|
| 176 |
"step": 11000
|
| 177 |
},
|
| 178 |
{
|
| 179 |
+
"epoch": 3.54,
|
| 180 |
+
"learning_rate": 2.4687403757314447e-05,
|
| 181 |
+
"loss": 0.0111,
|
| 182 |
"step": 11500
|
| 183 |
},
|
| 184 |
{
|
| 185 |
+
"epoch": 3.7,
|
| 186 |
+
"learning_rate": 2.4456421311980292e-05,
|
| 187 |
+
"loss": 0.0099,
|
| 188 |
"step": 12000
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 3.85,
|
| 192 |
+
"learning_rate": 2.4225438866646135e-05,
|
| 193 |
+
"loss": 0.0097,
|
| 194 |
"step": 12500
|
| 195 |
},
|
| 196 |
{
|
| 197 |
+
"epoch": 4.0,
|
| 198 |
+
"eval_accuracy": 0.9936326074754469,
|
| 199 |
+
"eval_f1": 0.9362323294406885,
|
| 200 |
+
"eval_loss": 0.027174057438969612,
|
| 201 |
+
"eval_precision": 0.920862222054295,
|
| 202 |
+
"eval_recall": 0.9521242308819221,
|
| 203 |
+
"eval_runtime": 50.3309,
|
| 204 |
+
"eval_samples_per_second": 441.677,
|
| 205 |
+
"eval_steps_per_second": 13.809,
|
| 206 |
+
"step": 12988
|
| 207 |
},
|
| 208 |
{
|
| 209 |
+
"epoch": 4.0,
|
| 210 |
+
"learning_rate": 2.399445642131198e-05,
|
| 211 |
+
"loss": 0.0102,
|
| 212 |
"step": 13000
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 4.16,
|
| 216 |
+
"learning_rate": 2.3763473975977826e-05,
|
| 217 |
+
"loss": 0.0076,
|
| 218 |
"step": 13500
|
| 219 |
},
|
| 220 |
{
|
| 221 |
+
"epoch": 4.31,
|
| 222 |
+
"learning_rate": 2.3532491530643672e-05,
|
| 223 |
+
"loss": 0.007,
|
| 224 |
"step": 14000
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 4.47,
|
| 228 |
+
"learning_rate": 2.3301509085309518e-05,
|
| 229 |
+
"loss": 0.007,
|
| 230 |
"step": 14500
|
| 231 |
},
|
| 232 |
{
|
| 233 |
+
"epoch": 4.62,
|
| 234 |
+
"learning_rate": 2.3070526639975364e-05,
|
| 235 |
+
"loss": 0.0082,
|
| 236 |
"step": 15000
|
| 237 |
},
|
| 238 |
{
|
| 239 |
+
"epoch": 4.77,
|
| 240 |
+
"learning_rate": 2.2839544194641206e-05,
|
| 241 |
+
"loss": 0.0079,
|
| 242 |
"step": 15500
|
| 243 |
},
|
| 244 |
{
|
| 245 |
+
"epoch": 4.93,
|
| 246 |
+
"learning_rate": 2.2608561749307052e-05,
|
| 247 |
+
"loss": 0.0077,
|
| 248 |
"step": 16000
|
| 249 |
},
|
| 250 |
{
|
| 251 |
+
"epoch": 5.0,
|
| 252 |
+
"eval_accuracy": 0.9943201214002335,
|
| 253 |
+
"eval_f1": 0.9403489135049596,
|
| 254 |
+
"eval_loss": 0.023451806977391243,
|
| 255 |
+
"eval_precision": 0.929177551915486,
|
| 256 |
+
"eval_recall": 0.9517921672038285,
|
| 257 |
+
"eval_runtime": 50.2007,
|
| 258 |
+
"eval_samples_per_second": 442.822,
|
| 259 |
+
"eval_steps_per_second": 13.844,
|
| 260 |
+
"step": 16235
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 5.08,
|
| 264 |
+
"learning_rate": 2.2377579303972898e-05,
|
| 265 |
+
"loss": 0.0064,
|
| 266 |
"step": 16500
|
| 267 |
},
|
| 268 |
{
|
| 269 |
+
"epoch": 5.24,
|
| 270 |
+
"learning_rate": 2.2146596858638743e-05,
|
| 271 |
+
"loss": 0.0052,
|
| 272 |
"step": 17000
|
| 273 |
},
|
| 274 |
{
|
| 275 |
+
"epoch": 5.39,
|
| 276 |
+
"learning_rate": 2.191561441330459e-05,
|
| 277 |
+
"loss": 0.0055,
|
| 278 |
"step": 17500
|
| 279 |
},
|
| 280 |
{
|
| 281 |
+
"epoch": 5.54,
|
| 282 |
+
"learning_rate": 2.1684631967970435e-05,
|
| 283 |
+
"loss": 0.0061,
|
| 284 |
"step": 18000
|
| 285 |
},
|
| 286 |
{
|
| 287 |
+
"epoch": 5.7,
|
| 288 |
+
"learning_rate": 2.145364952263628e-05,
|
| 289 |
+
"loss": 0.0056,
|
| 290 |
"step": 18500
|
| 291 |
},
|
| 292 |
{
|
| 293 |
+
"epoch": 5.85,
|
| 294 |
+
"learning_rate": 2.1222667077302123e-05,
|
| 295 |
+
"loss": 0.0054,
|
| 296 |
"step": 19000
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 6.0,
|
| 300 |
+
"eval_accuracy": 0.994450643863006,
|
| 301 |
+
"eval_f1": 0.9450084195333173,
|
| 302 |
+
"eval_loss": 0.0263934638351202,
|
| 303 |
+
"eval_precision": 0.9312535558505595,
|
| 304 |
+
"eval_recall": 0.9591757007520265,
|
| 305 |
+
"eval_runtime": 50.2902,
|
| 306 |
+
"eval_samples_per_second": 442.035,
|
| 307 |
+
"eval_steps_per_second": 13.82,
|
| 308 |
+
"step": 19482
|
| 309 |
},
|
| 310 |
{
|
| 311 |
+
"epoch": 6.01,
|
| 312 |
+
"learning_rate": 2.0991684631967972e-05,
|
| 313 |
+
"loss": 0.0062,
|
| 314 |
"step": 19500
|
| 315 |
},
|
| 316 |
{
|
| 317 |
+
"epoch": 6.16,
|
| 318 |
+
"learning_rate": 2.0760702186633818e-05,
|
| 319 |
+
"loss": 0.0033,
|
| 320 |
"step": 20000
|
| 321 |
},
|
| 322 |
{
|
| 323 |
+
"epoch": 6.31,
|
| 324 |
+
"learning_rate": 2.052971974129966e-05,
|
| 325 |
+
"loss": 0.0042,
|
| 326 |
"step": 20500
|
| 327 |
},
|
| 328 |
{
|
| 329 |
+
"epoch": 6.47,
|
| 330 |
+
"learning_rate": 2.0298737295965506e-05,
|
| 331 |
+
"loss": 0.0042,
|
| 332 |
"step": 21000
|
| 333 |
},
|
| 334 |
{
|
| 335 |
+
"epoch": 6.62,
|
| 336 |
+
"learning_rate": 2.0067754850631352e-05,
|
| 337 |
+
"loss": 0.0045,
|
| 338 |
"step": 21500
|
| 339 |
},
|
| 340 |
{
|
| 341 |
+
"epoch": 6.78,
|
| 342 |
+
"learning_rate": 1.9836772405297198e-05,
|
| 343 |
+
"loss": 0.0039,
|
| 344 |
"step": 22000
|
| 345 |
},
|
| 346 |
{
|
| 347 |
+
"epoch": 6.93,
|
| 348 |
+
"learning_rate": 1.9605789959963044e-05,
|
| 349 |
+
"loss": 0.0043,
|
| 350 |
"step": 22500
|
| 351 |
},
|
| 352 |
{
|
| 353 |
+
"epoch": 7.0,
|
| 354 |
+
"eval_accuracy": 0.9948756785494699,
|
| 355 |
+
"eval_f1": 0.9503865101154663,
|
| 356 |
+
"eval_loss": 0.026261983439326286,
|
| 357 |
+
"eval_precision": 0.9473980473223471,
|
| 358 |
+
"eval_recall": 0.9533938861216916,
|
| 359 |
+
"eval_runtime": 50.3703,
|
| 360 |
+
"eval_samples_per_second": 441.332,
|
| 361 |
+
"eval_steps_per_second": 13.798,
|
| 362 |
+
"step": 22729
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 7.08,
|
| 366 |
+
"learning_rate": 1.937480751462889e-05,
|
| 367 |
+
"loss": 0.004,
|
| 368 |
"step": 23000
|
| 369 |
},
|
| 370 |
{
|
| 371 |
+
"epoch": 7.24,
|
| 372 |
+
"learning_rate": 1.914382506929473e-05,
|
| 373 |
+
"loss": 0.0029,
|
| 374 |
"step": 23500
|
| 375 |
},
|
| 376 |
{
|
| 377 |
+
"epoch": 7.39,
|
| 378 |
+
"learning_rate": 1.8912842623960577e-05,
|
| 379 |
+
"loss": 0.0031,
|
| 380 |
"step": 24000
|
| 381 |
},
|
| 382 |
{
|
| 383 |
+
"epoch": 7.55,
|
| 384 |
+
"learning_rate": 1.8681860178626427e-05,
|
| 385 |
+
"loss": 0.0034,
|
| 386 |
"step": 24500
|
| 387 |
},
|
| 388 |
{
|
| 389 |
+
"epoch": 7.7,
|
| 390 |
+
"learning_rate": 1.8450877733292272e-05,
|
| 391 |
+
"loss": 0.0037,
|
| 392 |
"step": 25000
|
| 393 |
},
|
| 394 |
{
|
| 395 |
+
"epoch": 7.85,
|
| 396 |
+
"learning_rate": 1.8219895287958115e-05,
|
| 397 |
+
"loss": 0.0036,
|
| 398 |
"step": 25500
|
| 399 |
},
|
| 400 |
{
|
| 401 |
+
"epoch": 8.0,
|
| 402 |
+
"eval_accuracy": 0.994658141111516,
|
| 403 |
+
"eval_f1": 0.9494068997650896,
|
| 404 |
+
"eval_loss": 0.02981843240559101,
|
| 405 |
+
"eval_precision": 0.943654361962835,
|
| 406 |
+
"eval_recall": 0.9552300029299736,
|
| 407 |
+
"eval_runtime": 50.1982,
|
| 408 |
+
"eval_samples_per_second": 442.845,
|
| 409 |
+
"eval_steps_per_second": 13.845,
|
| 410 |
+
"step": 25976
|
| 411 |
},
|
| 412 |
{
|
| 413 |
+
"epoch": 8.01,
|
| 414 |
+
"learning_rate": 1.798891284262396e-05,
|
| 415 |
+
"loss": 0.0036,
|
| 416 |
"step": 26000
|
| 417 |
},
|
| 418 |
{
|
| 419 |
+
"epoch": 8.16,
|
| 420 |
+
"learning_rate": 1.7757930397289806e-05,
|
| 421 |
+
"loss": 0.0027,
|
| 422 |
"step": 26500
|
| 423 |
},
|
| 424 |
{
|
| 425 |
+
"epoch": 8.32,
|
| 426 |
+
"learning_rate": 1.7526947951955652e-05,
|
| 427 |
+
"loss": 0.0026,
|
| 428 |
"step": 27000
|
| 429 |
},
|
| 430 |
{
|
| 431 |
+
"epoch": 8.47,
|
| 432 |
+
"learning_rate": 1.7295965506621498e-05,
|
| 433 |
+
"loss": 0.0029,
|
| 434 |
"step": 27500
|
| 435 |
},
|
| 436 |
{
|
| 437 |
+
"epoch": 8.62,
|
| 438 |
+
"learning_rate": 1.7064983061287344e-05,
|
| 439 |
+
"loss": 0.0028,
|
| 440 |
"step": 28000
|
| 441 |
},
|
| 442 |
{
|
| 443 |
+
"epoch": 8.78,
|
| 444 |
+
"learning_rate": 1.6834000615953186e-05,
|
| 445 |
+
"loss": 0.0029,
|
| 446 |
"step": 28500
|
| 447 |
},
|
| 448 |
{
|
| 449 |
+
"epoch": 8.93,
|
| 450 |
+
"learning_rate": 1.6603018170619032e-05,
|
| 451 |
+
"loss": 0.0027,
|
| 452 |
"step": 29000
|
| 453 |
},
|
| 454 |
{
|
| 455 |
+
"epoch": 9.0,
|
| 456 |
+
"eval_accuracy": 0.9942837854765313,
|
| 457 |
+
"eval_f1": 0.9483075157773954,
|
| 458 |
+
"eval_loss": 0.03117133490741253,
|
| 459 |
+
"eval_precision": 0.9288564203427929,
|
| 460 |
+
"eval_recall": 0.9685906826838558,
|
| 461 |
+
"eval_runtime": 50.2531,
|
| 462 |
+
"eval_samples_per_second": 442.361,
|
| 463 |
+
"eval_steps_per_second": 13.83,
|
| 464 |
+
"step": 29223
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 9.09,
|
| 468 |
+
"learning_rate": 1.637203572528488e-05,
|
| 469 |
+
"loss": 0.0028,
|
| 470 |
"step": 29500
|
| 471 |
},
|
| 472 |
{
|
| 473 |
+
"epoch": 9.24,
|
| 474 |
+
"learning_rate": 1.6141053279950723e-05,
|
| 475 |
+
"loss": 0.0019,
|
| 476 |
"step": 30000
|
| 477 |
},
|
| 478 |
{
|
| 479 |
+
"epoch": 9.39,
|
| 480 |
+
"learning_rate": 1.591007083461657e-05,
|
| 481 |
+
"loss": 0.0022,
|
| 482 |
"step": 30500
|
| 483 |
},
|
| 484 |
{
|
| 485 |
+
"epoch": 9.55,
|
| 486 |
+
"learning_rate": 1.5679088389282415e-05,
|
| 487 |
+
"loss": 0.0024,
|
| 488 |
"step": 31000
|
| 489 |
},
|
| 490 |
{
|
| 491 |
+
"epoch": 9.7,
|
| 492 |
+
"learning_rate": 1.544810594394826e-05,
|
| 493 |
+
"loss": 0.0024,
|
| 494 |
"step": 31500
|
| 495 |
},
|
| 496 |
{
|
| 497 |
+
"epoch": 9.86,
|
| 498 |
+
"learning_rate": 1.5217123498614105e-05,
|
| 499 |
+
"loss": 0.0023,
|
| 500 |
"step": 32000
|
| 501 |
},
|
| 502 |
{
|
| 503 |
+
"epoch": 10.0,
|
| 504 |
+
"eval_accuracy": 0.9948642040472482,
|
| 505 |
+
"eval_f1": 0.9512794425354655,
|
| 506 |
+
"eval_loss": 0.036810312420129776,
|
| 507 |
+
"eval_precision": 0.935158800551037,
|
| 508 |
+
"eval_recall": 0.9679656216427386,
|
| 509 |
+
"eval_runtime": 50.4106,
|
| 510 |
+
"eval_samples_per_second": 440.978,
|
| 511 |
+
"eval_steps_per_second": 13.787,
|
| 512 |
+
"step": 32470
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 10.01,
|
| 516 |
+
"learning_rate": 1.4986141053279952e-05,
|
| 517 |
+
"loss": 0.0024,
|
| 518 |
"step": 32500
|
| 519 |
},
|
| 520 |
{
|
| 521 |
+
"epoch": 10.16,
|
| 522 |
+
"learning_rate": 1.4755158607945796e-05,
|
| 523 |
+
"loss": 0.0018,
|
| 524 |
"step": 33000
|
| 525 |
},
|
| 526 |
{
|
| 527 |
+
"epoch": 10.32,
|
| 528 |
+
"learning_rate": 1.4524176162611642e-05,
|
| 529 |
+
"loss": 0.0018,
|
| 530 |
"step": 33500
|
| 531 |
},
|
| 532 |
{
|
| 533 |
+
"epoch": 10.47,
|
| 534 |
+
"learning_rate": 1.4293193717277488e-05,
|
| 535 |
+
"loss": 0.002,
|
| 536 |
"step": 34000
|
| 537 |
},
|
| 538 |
{
|
| 539 |
+
"epoch": 10.63,
|
| 540 |
+
"learning_rate": 1.4062211271943332e-05,
|
| 541 |
+
"loss": 0.0024,
|
| 542 |
"step": 34500
|
| 543 |
},
|
| 544 |
{
|
| 545 |
+
"epoch": 10.78,
|
| 546 |
+
"learning_rate": 1.383122882660918e-05,
|
| 547 |
+
"loss": 0.002,
|
| 548 |
"step": 35000
|
| 549 |
},
|
| 550 |
{
|
| 551 |
+
"epoch": 10.93,
|
| 552 |
+
"learning_rate": 1.3600246381275023e-05,
|
| 553 |
+
"loss": 0.0019,
|
| 554 |
"step": 35500
|
| 555 |
},
|
| 556 |
{
|
| 557 |
+
"epoch": 11.0,
|
| 558 |
+
"eval_accuracy": 0.9952223041374186,
|
| 559 |
+
"eval_f1": 0.9571868114802629,
|
| 560 |
+
"eval_loss": 0.034278471022844315,
|
| 561 |
+
"eval_precision": 0.9512868001697727,
|
| 562 |
+
"eval_recall": 0.9631604648891493,
|
| 563 |
+
"eval_runtime": 50.1571,
|
| 564 |
+
"eval_samples_per_second": 443.208,
|
| 565 |
+
"eval_steps_per_second": 13.856,
|
| 566 |
+
"step": 35717
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 11.09,
|
| 570 |
+
"learning_rate": 1.3369263935940867e-05,
|
| 571 |
+
"loss": 0.0018,
|
| 572 |
"step": 36000
|
| 573 |
},
|
| 574 |
{
|
| 575 |
+
"epoch": 11.24,
|
| 576 |
+
"learning_rate": 1.3138281490606715e-05,
|
| 577 |
+
"loss": 0.0014,
|
| 578 |
"step": 36500
|
| 579 |
},
|
| 580 |
{
|
| 581 |
+
"epoch": 11.4,
|
| 582 |
+
"learning_rate": 1.2907299045272559e-05,
|
| 583 |
+
"loss": 0.0016,
|
| 584 |
"step": 37000
|
| 585 |
},
|
| 586 |
{
|
| 587 |
+
"epoch": 11.55,
|
| 588 |
+
"learning_rate": 1.2676316599938406e-05,
|
| 589 |
+
"loss": 0.0016,
|
| 590 |
"step": 37500
|
| 591 |
},
|
| 592 |
{
|
| 593 |
+
"epoch": 11.7,
|
| 594 |
+
"learning_rate": 1.244533415460425e-05,
|
| 595 |
+
"loss": 0.0014,
|
| 596 |
"step": 38000
|
| 597 |
},
|
| 598 |
{
|
| 599 |
+
"epoch": 11.86,
|
| 600 |
+
"learning_rate": 1.2214351709270095e-05,
|
| 601 |
+
"loss": 0.0018,
|
| 602 |
"step": 38500
|
| 603 |
},
|
| 604 |
{
|
| 605 |
+
"epoch": 12.0,
|
| 606 |
+
"eval_accuracy": 0.9950344091635375,
|
| 607 |
+
"eval_f1": 0.9542591914950985,
|
| 608 |
+
"eval_loss": 0.03573078662157059,
|
| 609 |
+
"eval_precision": 0.941064747108317,
|
| 610 |
+
"eval_recall": 0.9678288895399941,
|
| 611 |
+
"eval_runtime": 50.2611,
|
| 612 |
+
"eval_samples_per_second": 442.291,
|
| 613 |
+
"eval_steps_per_second": 13.828,
|
| 614 |
+
"step": 38964
|
| 615 |
},
|
| 616 |
{
|
| 617 |
+
"epoch": 12.01,
|
| 618 |
+
"learning_rate": 1.1983369263935942e-05,
|
| 619 |
+
"loss": 0.0015,
|
| 620 |
"step": 39000
|
| 621 |
},
|
| 622 |
{
|
| 623 |
+
"epoch": 12.17,
|
| 624 |
+
"learning_rate": 1.1752386818601786e-05,
|
| 625 |
+
"loss": 0.0014,
|
| 626 |
"step": 39500
|
| 627 |
},
|
| 628 |
{
|
| 629 |
+
"epoch": 12.32,
|
| 630 |
+
"learning_rate": 1.1521404373267632e-05,
|
| 631 |
+
"loss": 0.0016,
|
| 632 |
"step": 40000
|
| 633 |
},
|
| 634 |
{
|
| 635 |
+
"epoch": 12.47,
|
| 636 |
+
"learning_rate": 1.1290421927933478e-05,
|
| 637 |
+
"loss": 0.0017,
|
| 638 |
"step": 40500
|
| 639 |
},
|
| 640 |
{
|
| 641 |
+
"epoch": 12.63,
|
| 642 |
+
"learning_rate": 1.1059439482599322e-05,
|
| 643 |
+
"loss": 0.0011,
|
| 644 |
"step": 41000
|
| 645 |
},
|
| 646 |
{
|
| 647 |
+
"epoch": 12.78,
|
| 648 |
+
"learning_rate": 1.082845703726517e-05,
|
| 649 |
+
"loss": 0.0014,
|
| 650 |
"step": 41500
|
| 651 |
},
|
| 652 |
{
|
| 653 |
+
"epoch": 12.94,
|
| 654 |
+
"learning_rate": 1.0597474591931013e-05,
|
| 655 |
+
"loss": 0.0014,
|
| 656 |
"step": 42000
|
| 657 |
},
|
| 658 |
{
|
| 659 |
+
"epoch": 13.0,
|
| 660 |
+
"eval_accuracy": 0.9954953016694444,
|
| 661 |
+
"eval_f1": 0.9582205552548141,
|
| 662 |
+
"eval_loss": 0.034824222326278687,
|
| 663 |
+
"eval_precision": 0.9485197022180545,
|
| 664 |
+
"eval_recall": 0.9681218869030179,
|
| 665 |
+
"eval_runtime": 50.5254,
|
| 666 |
+
"eval_samples_per_second": 439.977,
|
| 667 |
+
"eval_steps_per_second": 13.755,
|
| 668 |
+
"step": 42211
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 13.09,
|
| 672 |
+
"learning_rate": 1.0366492146596857e-05,
|
| 673 |
+
"loss": 0.0013,
|
| 674 |
"step": 42500
|
| 675 |
},
|
| 676 |
{
|
| 677 |
+
"epoch": 13.24,
|
| 678 |
+
"learning_rate": 1.0135509701262705e-05,
|
| 679 |
+
"loss": 0.001,
|
| 680 |
"step": 43000
|
| 681 |
},
|
| 682 |
{
|
| 683 |
+
"epoch": 13.4,
|
| 684 |
+
"learning_rate": 9.904527255928549e-06,
|
| 685 |
+
"loss": 0.0011,
|
| 686 |
"step": 43500
|
| 687 |
},
|
| 688 |
{
|
| 689 |
+
"epoch": 13.55,
|
| 690 |
+
"learning_rate": 9.673544810594396e-06,
|
| 691 |
+
"loss": 0.0012,
|
| 692 |
"step": 44000
|
| 693 |
},
|
| 694 |
{
|
| 695 |
+
"epoch": 13.7,
|
| 696 |
+
"learning_rate": 9.44256236526024e-06,
|
| 697 |
+
"loss": 0.0013,
|
| 698 |
"step": 44500
|
| 699 |
},
|
| 700 |
{
|
| 701 |
+
"epoch": 13.86,
|
| 702 |
+
"learning_rate": 9.211579919926085e-06,
|
| 703 |
+
"loss": 0.0012,
|
| 704 |
"step": 45000
|
| 705 |
},
|
| 706 |
{
|
| 707 |
+
"epoch": 14.0,
|
| 708 |
+
"eval_accuracy": 0.99525290281001,
|
| 709 |
+
"eval_f1": 0.9559630182389084,
|
| 710 |
+
"eval_loss": 0.03898163139820099,
|
| 711 |
+
"eval_precision": 0.9486449577811544,
|
| 712 |
+
"eval_recall": 0.9633948627795683,
|
| 713 |
+
"eval_runtime": 50.2226,
|
| 714 |
+
"eval_samples_per_second": 442.629,
|
| 715 |
+
"eval_steps_per_second": 13.838,
|
| 716 |
+
"step": 45458
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 14.01,
|
| 720 |
+
"learning_rate": 8.980597474591932e-06,
|
| 721 |
+
"loss": 0.0012,
|
| 722 |
"step": 45500
|
| 723 |
},
|
| 724 |
{
|
| 725 |
+
"epoch": 14.17,
|
| 726 |
+
"learning_rate": 8.749615029257776e-06,
|
| 727 |
+
"loss": 0.0007,
|
| 728 |
"step": 46000
|
| 729 |
},
|
| 730 |
{
|
| 731 |
+
"epoch": 14.32,
|
| 732 |
+
"learning_rate": 8.518632583923622e-06,
|
| 733 |
+
"loss": 0.0009,
|
| 734 |
"step": 46500
|
| 735 |
},
|
| 736 |
{
|
| 737 |
+
"epoch": 14.47,
|
| 738 |
+
"learning_rate": 8.287650138589468e-06,
|
| 739 |
+
"loss": 0.0013,
|
| 740 |
"step": 47000
|
| 741 |
},
|
| 742 |
{
|
| 743 |
+
"epoch": 14.63,
|
| 744 |
+
"learning_rate": 8.056667693255312e-06,
|
| 745 |
+
"loss": 0.0012,
|
| 746 |
"step": 47500
|
| 747 |
},
|
| 748 |
{
|
| 749 |
+
"epoch": 14.78,
|
| 750 |
+
"learning_rate": 7.82568524792116e-06,
|
| 751 |
+
"loss": 0.001,
|
| 752 |
"step": 48000
|
| 753 |
},
|
| 754 |
{
|
| 755 |
+
"epoch": 14.94,
|
| 756 |
+
"learning_rate": 7.594702802587003e-06,
|
| 757 |
+
"loss": 0.001,
|
| 758 |
"step": 48500
|
| 759 |
},
|
| 760 |
{
|
| 761 |
+
"epoch": 15.0,
|
| 762 |
+
"eval_accuracy": 0.9952519466014915,
|
| 763 |
+
"eval_f1": 0.9577630980820753,
|
| 764 |
+
"eval_loss": 0.04225644841790199,
|
| 765 |
+
"eval_precision": 0.9485612475573777,
|
| 766 |
+
"eval_recall": 0.9671452290262721,
|
| 767 |
+
"eval_runtime": 56.1286,
|
| 768 |
+
"eval_samples_per_second": 396.055,
|
| 769 |
+
"eval_steps_per_second": 12.382,
|
| 770 |
+
"step": 48705
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 15.09,
|
| 774 |
+
"learning_rate": 7.363720357252849e-06,
|
| 775 |
+
"loss": 0.0009,
|
| 776 |
"step": 49000
|
| 777 |
},
|
| 778 |
{
|
| 779 |
+
"epoch": 15.24,
|
| 780 |
+
"learning_rate": 7.132737911918695e-06,
|
| 781 |
+
"loss": 0.0008,
|
| 782 |
"step": 49500
|
| 783 |
},
|
| 784 |
{
|
| 785 |
+
"epoch": 15.4,
|
| 786 |
+
"learning_rate": 6.90175546658454e-06,
|
| 787 |
+
"loss": 0.0009,
|
| 788 |
"step": 50000
|
| 789 |
},
|
| 790 |
{
|
| 791 |
+
"epoch": 15.55,
|
| 792 |
+
"learning_rate": 6.6707730212503855e-06,
|
| 793 |
+
"loss": 0.0008,
|
| 794 |
"step": 50500
|
| 795 |
},
|
| 796 |
{
|
| 797 |
+
"epoch": 15.71,
|
| 798 |
+
"learning_rate": 6.43979057591623e-06,
|
| 799 |
+
"loss": 0.0007,
|
| 800 |
"step": 51000
|
| 801 |
},
|
| 802 |
{
|
| 803 |
+
"epoch": 15.86,
|
| 804 |
+
"learning_rate": 6.208808130582076e-06,
|
| 805 |
+
"loss": 0.0008,
|
| 806 |
"step": 51500
|
| 807 |
},
|
| 808 |
{
|
| 809 |
+
"epoch": 16.0,
|
| 810 |
+
"eval_accuracy": 0.9950430150402038,
|
| 811 |
+
"eval_f1": 0.9558787995940656,
|
| 812 |
+
"eval_loss": 0.04262382909655571,
|
| 813 |
+
"eval_precision": 0.9460493590969964,
|
| 814 |
+
"eval_recall": 0.9659146401015725,
|
| 815 |
+
"eval_runtime": 50.4693,
|
| 816 |
+
"eval_samples_per_second": 440.466,
|
| 817 |
+
"eval_steps_per_second": 13.771,
|
| 818 |
+
"step": 51952
|
| 819 |
},
|
| 820 |
{
|
| 821 |
+
"epoch": 16.01,
|
| 822 |
+
"learning_rate": 5.977825685247921e-06,
|
| 823 |
+
"loss": 0.0008,
|
| 824 |
"step": 52000
|
| 825 |
},
|
| 826 |
{
|
| 827 |
+
"epoch": 16.17,
|
| 828 |
+
"learning_rate": 5.746843239913767e-06,
|
| 829 |
+
"loss": 0.0008,
|
| 830 |
"step": 52500
|
| 831 |
},
|
| 832 |
{
|
| 833 |
+
"epoch": 16.32,
|
| 834 |
+
"learning_rate": 5.515860794579612e-06,
|
| 835 |
+
"loss": 0.0008,
|
| 836 |
"step": 53000
|
| 837 |
},
|
| 838 |
{
|
| 839 |
+
"epoch": 16.48,
|
| 840 |
+
"learning_rate": 5.2848783492454576e-06,
|
| 841 |
+
"loss": 0.0009,
|
| 842 |
"step": 53500
|
| 843 |
},
|
| 844 |
{
|
| 845 |
+
"epoch": 16.63,
|
| 846 |
+
"learning_rate": 5.0538959039113025e-06,
|
| 847 |
+
"loss": 0.0008,
|
| 848 |
"step": 54000
|
| 849 |
},
|
| 850 |
{
|
| 851 |
+
"epoch": 16.78,
|
| 852 |
+
"learning_rate": 4.822913458577148e-06,
|
| 853 |
+
"loss": 0.0006,
|
| 854 |
"step": 54500
|
| 855 |
},
|
| 856 |
{
|
| 857 |
+
"epoch": 16.94,
|
| 858 |
+
"learning_rate": 4.591931013242994e-06,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 859 |
"loss": 0.001,
|
| 860 |
+
"step": 55000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 861 |
},
|
| 862 |
{
|
| 863 |
+
"epoch": 17.0,
|
| 864 |
+
"eval_accuracy": 0.9952113077394561,
|
| 865 |
+
"eval_f1": 0.9582838092477171,
|
| 866 |
+
"eval_loss": 0.04263555258512497,
|
| 867 |
+
"eval_precision": 0.9482501434308663,
|
| 868 |
+
"eval_recall": 0.9685320832112511,
|
| 869 |
+
"eval_runtime": 50.1705,
|
| 870 |
+
"eval_samples_per_second": 443.089,
|
| 871 |
+
"eval_steps_per_second": 13.853,
|
| 872 |
+
"step": 55199
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 873 |
},
|
| 874 |
{
|
| 875 |
+
"epoch": 17.09,
|
| 876 |
+
"learning_rate": 4.360948567908839e-06,
|
| 877 |
"loss": 0.0008,
|
| 878 |
+
"step": 55500
|
| 879 |
},
|
| 880 |
{
|
| 881 |
+
"epoch": 17.25,
|
| 882 |
+
"learning_rate": 4.129966122574684e-06,
|
| 883 |
"loss": 0.0008,
|
| 884 |
+
"step": 56000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 885 |
},
|
| 886 |
{
|
| 887 |
+
"epoch": 17.4,
|
| 888 |
+
"learning_rate": 3.89898367724053e-06,
|
| 889 |
"loss": 0.0008,
|
| 890 |
+
"step": 56500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 891 |
},
|
| 892 |
{
|
| 893 |
+
"epoch": 17.55,
|
| 894 |
+
"learning_rate": 3.668001231906375e-06,
|
| 895 |
"loss": 0.0007,
|
| 896 |
+
"step": 57000
|
| 897 |
},
|
| 898 |
{
|
| 899 |
+
"epoch": 17.71,
|
| 900 |
+
"learning_rate": 3.4370187865722208e-06,
|
| 901 |
"loss": 0.0007,
|
| 902 |
+
"step": 57500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 903 |
},
|
| 904 |
{
|
| 905 |
+
"epoch": 17.86,
|
| 906 |
+
"learning_rate": 3.206036341238066e-06,
|
| 907 |
+
"loss": 0.0006,
|
| 908 |
+
"step": 58000
|
| 909 |
},
|
| 910 |
{
|
| 911 |
+
"epoch": 18.0,
|
| 912 |
+
"eval_accuracy": 0.9952199136161224,
|
| 913 |
+
"eval_f1": 0.9574789135649616,
|
| 914 |
+
"eval_loss": 0.045220062136650085,
|
| 915 |
+
"eval_precision": 0.9483607656785913,
|
| 916 |
+
"eval_recall": 0.9667740990331087,
|
| 917 |
+
"eval_runtime": 50.3784,
|
| 918 |
+
"eval_samples_per_second": 441.26,
|
| 919 |
+
"eval_steps_per_second": 13.796,
|
| 920 |
+
"step": 58446
|
| 921 |
},
|
| 922 |
{
|
| 923 |
+
"epoch": 18.02,
|
| 924 |
+
"learning_rate": 2.9750538959039115e-06,
|
| 925 |
"loss": 0.0007,
|
| 926 |
+
"step": 58500
|
| 927 |
},
|
| 928 |
{
|
| 929 |
+
"epoch": 18.17,
|
| 930 |
+
"learning_rate": 2.744071450569757e-06,
|
| 931 |
"loss": 0.0007,
|
| 932 |
+
"step": 59000
|
| 933 |
},
|
| 934 |
{
|
| 935 |
+
"epoch": 18.32,
|
| 936 |
+
"learning_rate": 2.513089005235602e-06,
|
| 937 |
"loss": 0.0006,
|
| 938 |
+
"step": 59500
|
| 939 |
},
|
| 940 |
{
|
| 941 |
+
"epoch": 18.48,
|
| 942 |
+
"learning_rate": 2.2821065599014475e-06,
|
| 943 |
+
"loss": 0.0006,
|
| 944 |
+
"step": 60000
|
| 945 |
},
|
| 946 |
{
|
| 947 |
+
"epoch": 18.63,
|
| 948 |
+
"learning_rate": 2.051124114567293e-06,
|
| 949 |
"loss": 0.0007,
|
| 950 |
+
"step": 60500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 951 |
},
|
| 952 |
{
|
| 953 |
+
"epoch": 18.79,
|
| 954 |
+
"learning_rate": 1.8201416692331382e-06,
|
| 955 |
+
"loss": 0.0007,
|
| 956 |
+
"step": 61000
|
| 957 |
},
|
| 958 |
{
|
| 959 |
+
"epoch": 18.94,
|
| 960 |
+
"learning_rate": 1.5891592238989836e-06,
|
| 961 |
"loss": 0.0006,
|
| 962 |
+
"step": 61500
|
| 963 |
},
|
| 964 |
{
|
| 965 |
+
"epoch": 19.0,
|
| 966 |
+
"eval_accuracy": 0.9954895644183336,
|
| 967 |
+
"eval_f1": 0.959768669851647,
|
| 968 |
+
"eval_loss": 0.046882398426532745,
|
| 969 |
+
"eval_precision": 0.9504664125500412,
|
| 970 |
+
"eval_recall": 0.969254810040043,
|
| 971 |
+
"eval_runtime": 50.5066,
|
| 972 |
+
"eval_samples_per_second": 440.141,
|
| 973 |
+
"eval_steps_per_second": 13.761,
|
| 974 |
+
"step": 61693
|
| 975 |
}
|
| 976 |
],
|
| 977 |
+
"max_steps": 64940,
|
| 978 |
+
"num_train_epochs": 20,
|
| 979 |
+
"total_flos": 5.157312926507336e+17,
|
| 980 |
"trial_name": null,
|
| 981 |
"trial_params": null
|
| 982 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3183
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f0bfa1bfeb2b32964718935395ebbca37b92f93696e7c6e27f07995bf7ef028
|
| 3 |
size 3183
|
vocab.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|