Training in progress, step 10000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +348 -3
- pytorch_model.bin +1 -1
- runs/Apr19_22-38-31_9bb1d09d1b50/events.out.tfevents.1650407940.9bb1d09d1b50.39.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2217183175
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69df7b41162843d3066d511ff7e454b174a4296f035488ece7a03ebd7da15aef
|
| 3 |
size 2217183175
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1110986025
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77912d0e17b40469aa7bdb635e77b5ed25c78dd7b2e1af6263fb95572303bb76
|
| 3 |
size 1110986025
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1138e5e81505c6ff611f6e95829a5854ad3acd60d1e5975aa99a4b42e0f7266
|
| 3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -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 sha256:339fe610f593263fbda15028f0adf454993faebcdfef05cd5d15467b2d37e371
|
| 3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -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 sha256:765a68bdbb7550b6850d344347078b30cb0b00208e2e89de6624323f4ca4cb0a
|
| 3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 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,
|
|
@@ -351,11 +351,356 @@
|
|
| 351 |
"eval_samples_per_second": 15.641,
|
| 352 |
"eval_steps_per_second": 3.913,
|
| 353 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 354 |
}
|
| 355 |
],
|
| 356 |
"max_steps": 10146,
|
| 357 |
"num_train_epochs": 3,
|
| 358 |
-
"total_flos":
|
| 359 |
"trial_name": null,
|
| 360 |
"trial_params": null
|
| 361 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9568302779420463,
|
| 5 |
+
"global_step": 10000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 351 |
"eval_samples_per_second": 15.641,
|
| 352 |
"eval_steps_per_second": 3.913,
|
| 353 |
"step": 5000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.51,
|
| 357 |
+
"learning_rate": 2.4906367041198502e-05,
|
| 358 |
+
"loss": 0.4557,
|
| 359 |
+
"step": 5100
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.54,
|
| 363 |
+
"learning_rate": 2.441356199487483e-05,
|
| 364 |
+
"loss": 0.445,
|
| 365 |
+
"step": 5200
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.57,
|
| 369 |
+
"learning_rate": 2.3920756948551153e-05,
|
| 370 |
+
"loss": 0.4523,
|
| 371 |
+
"step": 5300
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.6,
|
| 375 |
+
"learning_rate": 2.342795190222748e-05,
|
| 376 |
+
"loss": 0.3584,
|
| 377 |
+
"step": 5400
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.63,
|
| 381 |
+
"learning_rate": 2.2935146855903804e-05,
|
| 382 |
+
"loss": 0.4356,
|
| 383 |
+
"step": 5500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.66,
|
| 387 |
+
"learning_rate": 2.244234180958013e-05,
|
| 388 |
+
"loss": 0.3989,
|
| 389 |
+
"step": 5600
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.69,
|
| 393 |
+
"learning_rate": 2.1949536763256458e-05,
|
| 394 |
+
"loss": 0.333,
|
| 395 |
+
"step": 5700
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.71,
|
| 399 |
+
"learning_rate": 2.145673171693278e-05,
|
| 400 |
+
"loss": 0.3701,
|
| 401 |
+
"step": 5800
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.74,
|
| 405 |
+
"learning_rate": 2.096392667060911e-05,
|
| 406 |
+
"loss": 0.4125,
|
| 407 |
+
"step": 5900
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.77,
|
| 411 |
+
"learning_rate": 2.0471121624285432e-05,
|
| 412 |
+
"loss": 0.3393,
|
| 413 |
+
"step": 6000
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.77,
|
| 417 |
+
"eval_cer": 0.12192614849371393,
|
| 418 |
+
"eval_loss": 0.2698688209056854,
|
| 419 |
+
"eval_runtime": 95.6778,
|
| 420 |
+
"eval_samples_per_second": 15.709,
|
| 421 |
+
"eval_steps_per_second": 3.93,
|
| 422 |
+
"step": 6000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.8,
|
| 426 |
+
"learning_rate": 1.997831657796176e-05,
|
| 427 |
+
"loss": 0.2519,
|
| 428 |
+
"step": 6100
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.83,
|
| 432 |
+
"learning_rate": 1.9485511531638083e-05,
|
| 433 |
+
"loss": 0.2175,
|
| 434 |
+
"step": 6200
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.86,
|
| 438 |
+
"learning_rate": 1.899270648531441e-05,
|
| 439 |
+
"loss": 0.2418,
|
| 440 |
+
"step": 6300
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.89,
|
| 444 |
+
"learning_rate": 1.8499901438990734e-05,
|
| 445 |
+
"loss": 0.2157,
|
| 446 |
+
"step": 6400
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.92,
|
| 450 |
+
"learning_rate": 1.800709639266706e-05,
|
| 451 |
+
"loss": 0.2653,
|
| 452 |
+
"step": 6500
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.95,
|
| 456 |
+
"learning_rate": 1.7514291346343388e-05,
|
| 457 |
+
"loss": 0.2321,
|
| 458 |
+
"step": 6600
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.98,
|
| 462 |
+
"learning_rate": 1.702148630001971e-05,
|
| 463 |
+
"loss": 0.1881,
|
| 464 |
+
"step": 6700
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.01,
|
| 468 |
+
"learning_rate": 1.652868125369604e-05,
|
| 469 |
+
"loss": 0.1818,
|
| 470 |
+
"step": 6800
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.04,
|
| 474 |
+
"learning_rate": 1.6035876207372362e-05,
|
| 475 |
+
"loss": 0.1204,
|
| 476 |
+
"step": 6900
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.07,
|
| 480 |
+
"learning_rate": 1.554307116104869e-05,
|
| 481 |
+
"loss": 0.1077,
|
| 482 |
+
"step": 7000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.07,
|
| 486 |
+
"eval_cer": 0.09330275954771883,
|
| 487 |
+
"eval_loss": 0.17944632470607758,
|
| 488 |
+
"eval_runtime": 96.1807,
|
| 489 |
+
"eval_samples_per_second": 15.627,
|
| 490 |
+
"eval_steps_per_second": 3.909,
|
| 491 |
+
"step": 7000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 2.1,
|
| 495 |
+
"learning_rate": 1.5050266114725015e-05,
|
| 496 |
+
"loss": 0.174,
|
| 497 |
+
"step": 7100
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.13,
|
| 501 |
+
"learning_rate": 1.455746106840134e-05,
|
| 502 |
+
"loss": 0.1222,
|
| 503 |
+
"step": 7200
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.16,
|
| 507 |
+
"learning_rate": 1.4064656022077665e-05,
|
| 508 |
+
"loss": 0.0985,
|
| 509 |
+
"step": 7300
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.19,
|
| 513 |
+
"learning_rate": 1.357185097575399e-05,
|
| 514 |
+
"loss": 0.0946,
|
| 515 |
+
"step": 7400
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.22,
|
| 519 |
+
"learning_rate": 1.3079045929430316e-05,
|
| 520 |
+
"loss": 0.0832,
|
| 521 |
+
"step": 7500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.25,
|
| 525 |
+
"learning_rate": 1.2586240883106643e-05,
|
| 526 |
+
"loss": 0.074,
|
| 527 |
+
"step": 7600
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.28,
|
| 531 |
+
"learning_rate": 1.209343583678297e-05,
|
| 532 |
+
"loss": 0.0768,
|
| 533 |
+
"step": 7700
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.31,
|
| 537 |
+
"learning_rate": 1.1600630790459296e-05,
|
| 538 |
+
"loss": 0.1018,
|
| 539 |
+
"step": 7800
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.34,
|
| 543 |
+
"learning_rate": 1.1107825744135621e-05,
|
| 544 |
+
"loss": 0.0668,
|
| 545 |
+
"step": 7900
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.37,
|
| 549 |
+
"learning_rate": 1.0615020697811946e-05,
|
| 550 |
+
"loss": 0.063,
|
| 551 |
+
"step": 8000
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 2.37,
|
| 555 |
+
"eval_cer": 0.06167470546374634,
|
| 556 |
+
"eval_loss": 0.13426831364631653,
|
| 557 |
+
"eval_runtime": 95.5453,
|
| 558 |
+
"eval_samples_per_second": 15.731,
|
| 559 |
+
"eval_steps_per_second": 3.935,
|
| 560 |
+
"step": 8000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.4,
|
| 564 |
+
"learning_rate": 1.0122215651488272e-05,
|
| 565 |
+
"loss": 0.0742,
|
| 566 |
+
"step": 8100
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.42,
|
| 570 |
+
"learning_rate": 9.629410605164597e-06,
|
| 571 |
+
"loss": 0.0679,
|
| 572 |
+
"step": 8200
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.45,
|
| 576 |
+
"learning_rate": 9.136605558840922e-06,
|
| 577 |
+
"loss": 0.0818,
|
| 578 |
+
"step": 8300
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.48,
|
| 582 |
+
"learning_rate": 8.643800512517248e-06,
|
| 583 |
+
"loss": 0.0704,
|
| 584 |
+
"step": 8400
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.51,
|
| 588 |
+
"learning_rate": 8.150995466193575e-06,
|
| 589 |
+
"loss": 0.0537,
|
| 590 |
+
"step": 8500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.54,
|
| 594 |
+
"learning_rate": 7.6581904198699e-06,
|
| 595 |
+
"loss": 0.0831,
|
| 596 |
+
"step": 8600
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.57,
|
| 600 |
+
"learning_rate": 7.1653853735462255e-06,
|
| 601 |
+
"loss": 0.0547,
|
| 602 |
+
"step": 8700
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.6,
|
| 606 |
+
"learning_rate": 6.672580327222551e-06,
|
| 607 |
+
"loss": 0.0765,
|
| 608 |
+
"step": 8800
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.63,
|
| 612 |
+
"learning_rate": 6.179775280898876e-06,
|
| 613 |
+
"loss": 0.0408,
|
| 614 |
+
"step": 8900
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.66,
|
| 618 |
+
"learning_rate": 5.6869702345752024e-06,
|
| 619 |
+
"loss": 0.0356,
|
| 620 |
+
"step": 9000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.66,
|
| 624 |
+
"eval_cer": 0.06918636830868981,
|
| 625 |
+
"eval_loss": 0.0790172666311264,
|
| 626 |
+
"eval_runtime": 97.3434,
|
| 627 |
+
"eval_samples_per_second": 15.44,
|
| 628 |
+
"eval_steps_per_second": 3.863,
|
| 629 |
+
"step": 9000
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 2.69,
|
| 633 |
+
"learning_rate": 5.194165188251528e-06,
|
| 634 |
+
"loss": 0.059,
|
| 635 |
+
"step": 9100
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 2.72,
|
| 639 |
+
"learning_rate": 4.70628819239109e-06,
|
| 640 |
+
"loss": 0.0775,
|
| 641 |
+
"step": 9200
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.75,
|
| 645 |
+
"learning_rate": 4.213483146067416e-06,
|
| 646 |
+
"loss": 0.058,
|
| 647 |
+
"step": 9300
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.78,
|
| 651 |
+
"learning_rate": 3.7206780997437416e-06,
|
| 652 |
+
"loss": 0.0327,
|
| 653 |
+
"step": 9400
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.81,
|
| 657 |
+
"learning_rate": 3.227873053420067e-06,
|
| 658 |
+
"loss": 0.0378,
|
| 659 |
+
"step": 9500
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 2.84,
|
| 663 |
+
"learning_rate": 2.7350680070963927e-06,
|
| 664 |
+
"loss": 0.0752,
|
| 665 |
+
"step": 9600
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 2.87,
|
| 669 |
+
"learning_rate": 2.2422629607727185e-06,
|
| 670 |
+
"loss": 0.0269,
|
| 671 |
+
"step": 9700
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 2.9,
|
| 675 |
+
"learning_rate": 1.749457914449044e-06,
|
| 676 |
+
"loss": 0.0359,
|
| 677 |
+
"step": 9800
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 2.93,
|
| 681 |
+
"learning_rate": 1.2566528681253697e-06,
|
| 682 |
+
"loss": 0.0345,
|
| 683 |
+
"step": 9900
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.96,
|
| 687 |
+
"learning_rate": 7.638478218016952e-07,
|
| 688 |
+
"loss": 0.0292,
|
| 689 |
+
"step": 10000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.96,
|
| 693 |
+
"eval_cer": 0.044595556258401205,
|
| 694 |
+
"eval_loss": 0.06197139248251915,
|
| 695 |
+
"eval_runtime": 96.6477,
|
| 696 |
+
"eval_samples_per_second": 15.551,
|
| 697 |
+
"eval_steps_per_second": 3.89,
|
| 698 |
+
"step": 10000
|
| 699 |
}
|
| 700 |
],
|
| 701 |
"max_steps": 10146,
|
| 702 |
"num_train_epochs": 3,
|
| 703 |
+
"total_flos": 7.242528907589714e+18,
|
| 704 |
"trial_name": null,
|
| 705 |
"trial_params": null
|
| 706 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1110986025
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77912d0e17b40469aa7bdb635e77b5ed25c78dd7b2e1af6263fb95572303bb76
|
| 3 |
size 1110986025
|
runs/Apr19_22-38-31_9bb1d09d1b50/events.out.tfevents.1650407940.9bb1d09d1b50.39.0
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:efb0e7f076be8579051c89bd5a3dd4cf7dd657db8f2e9ed56c58a2f10987cb26
|
| 3 |
+
size 99555
|