Commit
•
d71bd83
1
Parent(s):
a5ea3ed
Training in progress, step 700
Browse files- {checkpoint-400 → checkpoint-700}/config.json +0 -0
- {checkpoint-400 → checkpoint-700}/optimizer.pt +1 -1
- {checkpoint-400 → checkpoint-700}/preprocessor_config.json +0 -0
- {checkpoint-400 → checkpoint-700}/pytorch_model.bin +1 -1
- {checkpoint-400 → checkpoint-700}/rng_state.pth +1 -1
- {checkpoint-400 → checkpoint-700}/scaler.pt +1 -1
- {checkpoint-400 → checkpoint-700}/scheduler.pt +1 -1
- {checkpoint-400 → checkpoint-700}/trainer_state.json +210 -3
- {checkpoint-400 → checkpoint-700}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-400 → checkpoint-700}/config.json
RENAMED
|
File without changes
|
{checkpoint-400 → checkpoint-700}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2490346001
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:069822e7cb50437bf3b0c3c681ba2097aca5275abda255e4fc6af68096387a0f
|
| 3 |
size 2490346001
|
{checkpoint-400 → checkpoint-700}/preprocessor_config.json
RENAMED
|
File without changes
|
{checkpoint-400 → checkpoint-700}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262067185
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f82fd4ef9d1ee16be752146f67271d9079ee4c70b3fc0deb5e49afca834a8366
|
| 3 |
size 1262067185
|
{checkpoint-400 → checkpoint-700}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14567
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87ff61a351af84ca56c488c49a3cc628f0fcf141b18f2d6a7cc51cc4bc0d60cf
|
| 3 |
size 14567
|
{checkpoint-400 → checkpoint-700}/scaler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f78925f079cf346f5de839091ad9ea905df589af85f400d7d4ba825eb420db33
|
| 3 |
size 559
|
{checkpoint-400 → checkpoint-700}/scheduler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8642bc4d6c53b743cbfe106c9335222647650f89ec52d95e575d8e1f87f4f2be
|
| 3 |
size 623
|
{checkpoint-400 → checkpoint-700}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -282,11 +282,218 @@
|
|
| 282 |
"eval_steps_per_second": 1.115,
|
| 283 |
"eval_wer": 1.0,
|
| 284 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 285 |
}
|
| 286 |
],
|
| 287 |
"max_steps": 6501,
|
| 288 |
"num_train_epochs": 3,
|
| 289 |
-
"total_flos":
|
| 290 |
"trial_name": null,
|
| 291 |
"trial_params": null
|
| 292 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.3229527104959631,
|
| 5 |
+
"global_step": 700,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 282 |
"eval_steps_per_second": 1.115,
|
| 283 |
"eval_wer": 1.0,
|
| 284 |
"step": 400
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.19,
|
| 288 |
+
"learning_rate": 7.183281004709575e-05,
|
| 289 |
+
"loss": 3.0018,
|
| 290 |
+
"step": 410
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.19,
|
| 294 |
+
"learning_rate": 7.171507064364207e-05,
|
| 295 |
+
"loss": 2.9947,
|
| 296 |
+
"step": 420
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.2,
|
| 300 |
+
"learning_rate": 7.159733124018838e-05,
|
| 301 |
+
"loss": 2.9935,
|
| 302 |
+
"step": 430
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.2,
|
| 306 |
+
"learning_rate": 7.147959183673469e-05,
|
| 307 |
+
"loss": 3.0818,
|
| 308 |
+
"step": 440
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.21,
|
| 312 |
+
"learning_rate": 7.137362637362637e-05,
|
| 313 |
+
"loss": 3.3386,
|
| 314 |
+
"step": 450
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.21,
|
| 318 |
+
"learning_rate": 7.125588697017268e-05,
|
| 319 |
+
"loss": 3.0803,
|
| 320 |
+
"step": 460
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.22,
|
| 324 |
+
"learning_rate": 7.1138147566719e-05,
|
| 325 |
+
"loss": 3.1655,
|
| 326 |
+
"step": 470
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.22,
|
| 330 |
+
"learning_rate": 7.10204081632653e-05,
|
| 331 |
+
"loss": 3.0899,
|
| 332 |
+
"step": 480
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.23,
|
| 336 |
+
"learning_rate": 7.090266875981161e-05,
|
| 337 |
+
"loss": 3.1638,
|
| 338 |
+
"step": 490
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.23,
|
| 342 |
+
"learning_rate": 7.079670329670328e-05,
|
| 343 |
+
"loss": 3.3518,
|
| 344 |
+
"step": 500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.23,
|
| 348 |
+
"eval_loss": 2.9412434101104736,
|
| 349 |
+
"eval_runtime": 130.1575,
|
| 350 |
+
"eval_samples_per_second": 35.495,
|
| 351 |
+
"eval_steps_per_second": 1.114,
|
| 352 |
+
"eval_wer": 1.0,
|
| 353 |
+
"step": 500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.24,
|
| 357 |
+
"learning_rate": 7.06789638932496e-05,
|
| 358 |
+
"loss": 2.9352,
|
| 359 |
+
"step": 510
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.24,
|
| 363 |
+
"learning_rate": 7.056122448979591e-05,
|
| 364 |
+
"loss": 2.9405,
|
| 365 |
+
"step": 520
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.24,
|
| 369 |
+
"learning_rate": 7.044348508634222e-05,
|
| 370 |
+
"loss": 2.9125,
|
| 371 |
+
"step": 530
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.25,
|
| 375 |
+
"learning_rate": 7.032574568288854e-05,
|
| 376 |
+
"loss": 2.9401,
|
| 377 |
+
"step": 540
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.25,
|
| 381 |
+
"learning_rate": 7.021978021978021e-05,
|
| 382 |
+
"loss": 3.1443,
|
| 383 |
+
"step": 550
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.26,
|
| 387 |
+
"learning_rate": 7.010204081632653e-05,
|
| 388 |
+
"loss": 2.7692,
|
| 389 |
+
"step": 560
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.26,
|
| 393 |
+
"learning_rate": 6.998430141287284e-05,
|
| 394 |
+
"loss": 2.7574,
|
| 395 |
+
"step": 570
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.27,
|
| 399 |
+
"learning_rate": 6.986656200941914e-05,
|
| 400 |
+
"loss": 2.706,
|
| 401 |
+
"step": 580
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.27,
|
| 405 |
+
"learning_rate": 6.974882260596545e-05,
|
| 406 |
+
"loss": 2.7155,
|
| 407 |
+
"step": 590
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.28,
|
| 411 |
+
"learning_rate": 6.964285714285713e-05,
|
| 412 |
+
"loss": 2.8747,
|
| 413 |
+
"step": 600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.28,
|
| 417 |
+
"eval_loss": 2.5006003379821777,
|
| 418 |
+
"eval_runtime": 129.3111,
|
| 419 |
+
"eval_samples_per_second": 35.728,
|
| 420 |
+
"eval_steps_per_second": 1.121,
|
| 421 |
+
"eval_wer": 1.0,
|
| 422 |
+
"step": 600
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.28,
|
| 426 |
+
"learning_rate": 6.952511773940345e-05,
|
| 427 |
+
"loss": 2.5368,
|
| 428 |
+
"step": 610
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.29,
|
| 432 |
+
"learning_rate": 6.940737833594976e-05,
|
| 433 |
+
"loss": 2.5942,
|
| 434 |
+
"step": 620
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.29,
|
| 438 |
+
"learning_rate": 6.928963893249607e-05,
|
| 439 |
+
"loss": 2.4907,
|
| 440 |
+
"step": 630
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.3,
|
| 444 |
+
"learning_rate": 6.917189952904238e-05,
|
| 445 |
+
"loss": 2.472,
|
| 446 |
+
"step": 640
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.3,
|
| 450 |
+
"learning_rate": 6.907770800627943e-05,
|
| 451 |
+
"loss": 2.6826,
|
| 452 |
+
"step": 650
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.3,
|
| 456 |
+
"learning_rate": 6.895996860282574e-05,
|
| 457 |
+
"loss": 2.3167,
|
| 458 |
+
"step": 660
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.31,
|
| 462 |
+
"learning_rate": 6.884222919937205e-05,
|
| 463 |
+
"loss": 2.3457,
|
| 464 |
+
"step": 670
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.31,
|
| 468 |
+
"learning_rate": 6.872448979591836e-05,
|
| 469 |
+
"loss": 2.3532,
|
| 470 |
+
"step": 680
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.32,
|
| 474 |
+
"learning_rate": 6.860675039246468e-05,
|
| 475 |
+
"loss": 2.4822,
|
| 476 |
+
"step": 690
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.32,
|
| 480 |
+
"learning_rate": 6.850078492935636e-05,
|
| 481 |
+
"loss": 3.1002,
|
| 482 |
+
"step": 700
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.32,
|
| 486 |
+
"eval_loss": 2.819200277328491,
|
| 487 |
+
"eval_runtime": 129.5044,
|
| 488 |
+
"eval_samples_per_second": 35.674,
|
| 489 |
+
"eval_steps_per_second": 1.12,
|
| 490 |
+
"eval_wer": 0.9999694058618369,
|
| 491 |
+
"step": 700
|
| 492 |
}
|
| 493 |
],
|
| 494 |
"max_steps": 6501,
|
| 495 |
"num_train_epochs": 3,
|
| 496 |
+
"total_flos": 1.3228060515474647e+19,
|
| 497 |
"trial_name": null,
|
| 498 |
"trial_params": null
|
| 499 |
}
|
{checkpoint-400 → checkpoint-700}/training_args.bin
RENAMED
|
File without changes
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262067185
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f82fd4ef9d1ee16be752146f67271d9079ee4c70b3fc0deb5e49afca834a8366
|
| 3 |
size 1262067185
|