Upload 9 files
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +2 -2
- scaler.pt +1 -1
- scheduler.pt +1 -1
- trainer_state.json +503 -5
- training_args.bin +1 -1
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1934158597
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4471784c01a9be28fab76646476f5cfb25e90eb4207edcd525c03bd186964c7b
|
| 3 |
size 1934158597
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 967099139
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:703799b9cdce56301c0f09ebd733b5f14e53541aa5fd43f829001a8a849cdad0
|
| 3 |
size 967099139
|
rng_state.pth
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:dcc7df53b6a5c90ce8062891d12cde44dec8976a02f115d37fd6b757cc27aecc
|
| 3 |
+
size 14567
|
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:e9651ab0c530e23e58f4fec0324e98dcbfe386a5c7c7e02abb865cc2445fe00c
|
| 3 |
size 559
|
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 sha256:358d3cc5378fafc026eb4d987f7a358d0f6d6bfc9501f710e91d8952b2fb645b
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "/content/gdrive/MyDrive/Whisper_Checkpoints/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -504,11 +504,509 @@
|
|
| 504 |
"eval_steps_per_second": 0.322,
|
| 505 |
"eval_wer": 20.332876233497352,
|
| 506 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 507 |
}
|
| 508 |
],
|
| 509 |
"max_steps": 4000,
|
| 510 |
"num_train_epochs": 6,
|
| 511 |
-
"total_flos":
|
| 512 |
"trial_name": null,
|
| 513 |
"trial_params": null
|
| 514 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 19.894598155467722,
|
| 3 |
+
"best_model_checkpoint": "/content/gdrive/MyDrive/Whisper_Checkpoints/checkpoint-4000",
|
| 4 |
+
"epoch": 5.174644243208279,
|
| 5 |
+
"global_step": 4000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 504 |
"eval_steps_per_second": 0.322,
|
| 505 |
"eval_wer": 20.332876233497352,
|
| 506 |
"step": 2000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.62,
|
| 510 |
+
"learning_rate": 5.654285714285714e-06,
|
| 511 |
+
"loss": 0.0519,
|
| 512 |
+
"step": 2025
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.65,
|
| 516 |
+
"learning_rate": 5.582857142857143e-06,
|
| 517 |
+
"loss": 0.0507,
|
| 518 |
+
"step": 2050
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.68,
|
| 522 |
+
"learning_rate": 5.511428571428572e-06,
|
| 523 |
+
"loss": 0.0524,
|
| 524 |
+
"step": 2075
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 2.72,
|
| 528 |
+
"learning_rate": 5.4400000000000004e-06,
|
| 529 |
+
"loss": 0.0591,
|
| 530 |
+
"step": 2100
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 2.75,
|
| 534 |
+
"learning_rate": 5.368571428571429e-06,
|
| 535 |
+
"loss": 0.049,
|
| 536 |
+
"step": 2125
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.78,
|
| 540 |
+
"learning_rate": 5.297142857142858e-06,
|
| 541 |
+
"loss": 0.0476,
|
| 542 |
+
"step": 2150
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.81,
|
| 546 |
+
"learning_rate": 5.225714285714286e-06,
|
| 547 |
+
"loss": 0.0448,
|
| 548 |
+
"step": 2175
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.85,
|
| 552 |
+
"learning_rate": 5.154285714285715e-06,
|
| 553 |
+
"loss": 0.0549,
|
| 554 |
+
"step": 2200
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.88,
|
| 558 |
+
"learning_rate": 5.082857142857144e-06,
|
| 559 |
+
"loss": 0.0449,
|
| 560 |
+
"step": 2225
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.91,
|
| 564 |
+
"learning_rate": 5.011428571428571e-06,
|
| 565 |
+
"loss": 0.0512,
|
| 566 |
+
"step": 2250
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.94,
|
| 570 |
+
"learning_rate": 4.94e-06,
|
| 571 |
+
"loss": 0.0499,
|
| 572 |
+
"step": 2275
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.98,
|
| 576 |
+
"learning_rate": 4.868571428571429e-06,
|
| 577 |
+
"loss": 0.0513,
|
| 578 |
+
"step": 2300
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 3.01,
|
| 582 |
+
"learning_rate": 4.797142857142857e-06,
|
| 583 |
+
"loss": 0.0508,
|
| 584 |
+
"step": 2325
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 3.04,
|
| 588 |
+
"learning_rate": 4.725714285714286e-06,
|
| 589 |
+
"loss": 0.0245,
|
| 590 |
+
"step": 2350
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 3.07,
|
| 594 |
+
"learning_rate": 4.6542857142857145e-06,
|
| 595 |
+
"loss": 0.0221,
|
| 596 |
+
"step": 2375
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 3.1,
|
| 600 |
+
"learning_rate": 4.5828571428571435e-06,
|
| 601 |
+
"loss": 0.0194,
|
| 602 |
+
"step": 2400
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 3.14,
|
| 606 |
+
"learning_rate": 4.511428571428572e-06,
|
| 607 |
+
"loss": 0.0243,
|
| 608 |
+
"step": 2425
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 3.17,
|
| 612 |
+
"learning_rate": 4.440000000000001e-06,
|
| 613 |
+
"loss": 0.0192,
|
| 614 |
+
"step": 2450
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 3.2,
|
| 618 |
+
"learning_rate": 4.368571428571429e-06,
|
| 619 |
+
"loss": 0.0178,
|
| 620 |
+
"step": 2475
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 3.23,
|
| 624 |
+
"learning_rate": 4.297142857142858e-06,
|
| 625 |
+
"loss": 0.0203,
|
| 626 |
+
"step": 2500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 3.27,
|
| 630 |
+
"learning_rate": 4.225714285714286e-06,
|
| 631 |
+
"loss": 0.0268,
|
| 632 |
+
"step": 2525
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.3,
|
| 636 |
+
"learning_rate": 4.154285714285714e-06,
|
| 637 |
+
"loss": 0.022,
|
| 638 |
+
"step": 2550
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 3.33,
|
| 642 |
+
"learning_rate": 4.082857142857143e-06,
|
| 643 |
+
"loss": 0.0201,
|
| 644 |
+
"step": 2575
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 3.36,
|
| 648 |
+
"learning_rate": 4.011428571428571e-06,
|
| 649 |
+
"loss": 0.0232,
|
| 650 |
+
"step": 2600
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 3.4,
|
| 654 |
+
"learning_rate": 3.94e-06,
|
| 655 |
+
"loss": 0.0211,
|
| 656 |
+
"step": 2625
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 3.43,
|
| 660 |
+
"learning_rate": 3.8685714285714286e-06,
|
| 661 |
+
"loss": 0.0191,
|
| 662 |
+
"step": 2650
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 3.46,
|
| 666 |
+
"learning_rate": 3.7971428571428576e-06,
|
| 667 |
+
"loss": 0.0222,
|
| 668 |
+
"step": 2675
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 3.49,
|
| 672 |
+
"learning_rate": 3.7257142857142857e-06,
|
| 673 |
+
"loss": 0.0251,
|
| 674 |
+
"step": 2700
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.53,
|
| 678 |
+
"learning_rate": 3.6542857142857148e-06,
|
| 679 |
+
"loss": 0.0211,
|
| 680 |
+
"step": 2725
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 3.56,
|
| 684 |
+
"learning_rate": 3.582857142857143e-06,
|
| 685 |
+
"loss": 0.02,
|
| 686 |
+
"step": 2750
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 3.59,
|
| 690 |
+
"learning_rate": 3.511428571428572e-06,
|
| 691 |
+
"loss": 0.0214,
|
| 692 |
+
"step": 2775
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 3.62,
|
| 696 |
+
"learning_rate": 3.44e-06,
|
| 697 |
+
"loss": 0.022,
|
| 698 |
+
"step": 2800
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 3.65,
|
| 702 |
+
"learning_rate": 3.3685714285714287e-06,
|
| 703 |
+
"loss": 0.0173,
|
| 704 |
+
"step": 2825
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.69,
|
| 708 |
+
"learning_rate": 3.2971428571428577e-06,
|
| 709 |
+
"loss": 0.021,
|
| 710 |
+
"step": 2850
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 3.72,
|
| 714 |
+
"learning_rate": 3.225714285714286e-06,
|
| 715 |
+
"loss": 0.0203,
|
| 716 |
+
"step": 2875
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 3.75,
|
| 720 |
+
"learning_rate": 3.154285714285715e-06,
|
| 721 |
+
"loss": 0.0205,
|
| 722 |
+
"step": 2900
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 3.78,
|
| 726 |
+
"learning_rate": 3.082857142857143e-06,
|
| 727 |
+
"loss": 0.019,
|
| 728 |
+
"step": 2925
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 3.82,
|
| 732 |
+
"learning_rate": 3.0114285714285716e-06,
|
| 733 |
+
"loss": 0.0206,
|
| 734 |
+
"step": 2950
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.85,
|
| 738 |
+
"learning_rate": 2.9400000000000002e-06,
|
| 739 |
+
"loss": 0.0164,
|
| 740 |
+
"step": 2975
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 3.88,
|
| 744 |
+
"learning_rate": 2.868571428571429e-06,
|
| 745 |
+
"loss": 0.0174,
|
| 746 |
+
"step": 3000
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 3.88,
|
| 750 |
+
"eval_loss": 0.30105218291282654,
|
| 751 |
+
"eval_runtime": 2038.4412,
|
| 752 |
+
"eval_samples_per_second": 2.487,
|
| 753 |
+
"eval_steps_per_second": 0.311,
|
| 754 |
+
"eval_wer": 19.994084590357883,
|
| 755 |
+
"step": 3000
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 3.91,
|
| 759 |
+
"learning_rate": 2.797142857142857e-06,
|
| 760 |
+
"loss": 0.019,
|
| 761 |
+
"step": 3025
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 3.95,
|
| 765 |
+
"learning_rate": 2.725714285714286e-06,
|
| 766 |
+
"loss": 0.019,
|
| 767 |
+
"step": 3050
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 3.98,
|
| 771 |
+
"learning_rate": 2.654285714285714e-06,
|
| 772 |
+
"loss": 0.0194,
|
| 773 |
+
"step": 3075
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 4.01,
|
| 777 |
+
"learning_rate": 2.582857142857143e-06,
|
| 778 |
+
"loss": 0.0166,
|
| 779 |
+
"step": 3100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 4.04,
|
| 783 |
+
"learning_rate": 2.5114285714285718e-06,
|
| 784 |
+
"loss": 0.0078,
|
| 785 |
+
"step": 3125
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 4.08,
|
| 789 |
+
"learning_rate": 2.4400000000000004e-06,
|
| 790 |
+
"loss": 0.008,
|
| 791 |
+
"step": 3150
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 4.11,
|
| 795 |
+
"learning_rate": 2.3685714285714285e-06,
|
| 796 |
+
"loss": 0.0088,
|
| 797 |
+
"step": 3175
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 4.14,
|
| 801 |
+
"learning_rate": 2.297142857142857e-06,
|
| 802 |
+
"loss": 0.0086,
|
| 803 |
+
"step": 3200
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 4.17,
|
| 807 |
+
"learning_rate": 2.2257142857142857e-06,
|
| 808 |
+
"loss": 0.0093,
|
| 809 |
+
"step": 3225
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 4.2,
|
| 813 |
+
"learning_rate": 2.1542857142857147e-06,
|
| 814 |
+
"loss": 0.0086,
|
| 815 |
+
"step": 3250
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 4.24,
|
| 819 |
+
"learning_rate": 2.0828571428571433e-06,
|
| 820 |
+
"loss": 0.0083,
|
| 821 |
+
"step": 3275
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 4.27,
|
| 825 |
+
"learning_rate": 2.0114285714285715e-06,
|
| 826 |
+
"loss": 0.0083,
|
| 827 |
+
"step": 3300
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 4.3,
|
| 831 |
+
"learning_rate": 1.94e-06,
|
| 832 |
+
"loss": 0.0072,
|
| 833 |
+
"step": 3325
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 4.33,
|
| 837 |
+
"learning_rate": 1.8685714285714289e-06,
|
| 838 |
+
"loss": 0.0073,
|
| 839 |
+
"step": 3350
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 4.37,
|
| 843 |
+
"learning_rate": 1.7971428571428572e-06,
|
| 844 |
+
"loss": 0.007,
|
| 845 |
+
"step": 3375
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 4.4,
|
| 849 |
+
"learning_rate": 1.7257142857142858e-06,
|
| 850 |
+
"loss": 0.0086,
|
| 851 |
+
"step": 3400
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 4.43,
|
| 855 |
+
"learning_rate": 1.6542857142857144e-06,
|
| 856 |
+
"loss": 0.007,
|
| 857 |
+
"step": 3425
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 4.46,
|
| 861 |
+
"learning_rate": 1.582857142857143e-06,
|
| 862 |
+
"loss": 0.0066,
|
| 863 |
+
"step": 3450
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 4.5,
|
| 867 |
+
"learning_rate": 1.5114285714285714e-06,
|
| 868 |
+
"loss": 0.0089,
|
| 869 |
+
"step": 3475
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 4.53,
|
| 873 |
+
"learning_rate": 1.44e-06,
|
| 874 |
+
"loss": 0.0083,
|
| 875 |
+
"step": 3500
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 4.56,
|
| 879 |
+
"learning_rate": 1.3685714285714286e-06,
|
| 880 |
+
"loss": 0.0084,
|
| 881 |
+
"step": 3525
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 4.59,
|
| 885 |
+
"learning_rate": 1.2971428571428574e-06,
|
| 886 |
+
"loss": 0.008,
|
| 887 |
+
"step": 3550
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 4.62,
|
| 891 |
+
"learning_rate": 1.2257142857142857e-06,
|
| 892 |
+
"loss": 0.0079,
|
| 893 |
+
"step": 3575
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 4.66,
|
| 897 |
+
"learning_rate": 1.1542857142857143e-06,
|
| 898 |
+
"loss": 0.0075,
|
| 899 |
+
"step": 3600
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 4.69,
|
| 903 |
+
"learning_rate": 1.082857142857143e-06,
|
| 904 |
+
"loss": 0.0078,
|
| 905 |
+
"step": 3625
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 4.72,
|
| 909 |
+
"learning_rate": 1.0114285714285715e-06,
|
| 910 |
+
"loss": 0.0077,
|
| 911 |
+
"step": 3650
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 4.75,
|
| 915 |
+
"learning_rate": 9.400000000000001e-07,
|
| 916 |
+
"loss": 0.0079,
|
| 917 |
+
"step": 3675
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 4.79,
|
| 921 |
+
"learning_rate": 8.685714285714286e-07,
|
| 922 |
+
"loss": 0.0066,
|
| 923 |
+
"step": 3700
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 4.82,
|
| 927 |
+
"learning_rate": 7.971428571428572e-07,
|
| 928 |
+
"loss": 0.0079,
|
| 929 |
+
"step": 3725
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 4.85,
|
| 933 |
+
"learning_rate": 7.257142857142857e-07,
|
| 934 |
+
"loss": 0.0078,
|
| 935 |
+
"step": 3750
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 4.88,
|
| 939 |
+
"learning_rate": 6.542857142857144e-07,
|
| 940 |
+
"loss": 0.0072,
|
| 941 |
+
"step": 3775
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 4.92,
|
| 945 |
+
"learning_rate": 5.82857142857143e-07,
|
| 946 |
+
"loss": 0.009,
|
| 947 |
+
"step": 3800
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 4.95,
|
| 951 |
+
"learning_rate": 5.114285714285714e-07,
|
| 952 |
+
"loss": 0.0073,
|
| 953 |
+
"step": 3825
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 4.98,
|
| 957 |
+
"learning_rate": 4.4e-07,
|
| 958 |
+
"loss": 0.0073,
|
| 959 |
+
"step": 3850
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 5.01,
|
| 963 |
+
"learning_rate": 3.685714285714286e-07,
|
| 964 |
+
"loss": 0.0074,
|
| 965 |
+
"step": 3875
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 5.05,
|
| 969 |
+
"learning_rate": 2.9714285714285715e-07,
|
| 970 |
+
"loss": 0.0042,
|
| 971 |
+
"step": 3900
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 5.08,
|
| 975 |
+
"learning_rate": 2.2571428571428574e-07,
|
| 976 |
+
"loss": 0.0053,
|
| 977 |
+
"step": 3925
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 5.11,
|
| 981 |
+
"learning_rate": 1.542857142857143e-07,
|
| 982 |
+
"loss": 0.0048,
|
| 983 |
+
"step": 3950
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 5.14,
|
| 987 |
+
"learning_rate": 8.285714285714285e-08,
|
| 988 |
+
"loss": 0.0046,
|
| 989 |
+
"step": 3975
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 5.17,
|
| 993 |
+
"learning_rate": 1.142857142857143e-08,
|
| 994 |
+
"loss": 0.0039,
|
| 995 |
+
"step": 4000
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 5.17,
|
| 999 |
+
"eval_loss": 0.32625457644462585,
|
| 1000 |
+
"eval_runtime": 2112.7102,
|
| 1001 |
+
"eval_samples_per_second": 2.399,
|
| 1002 |
+
"eval_steps_per_second": 0.3,
|
| 1003 |
+
"eval_wer": 19.894598155467722,
|
| 1004 |
+
"step": 4000
|
| 1005 |
}
|
| 1006 |
],
|
| 1007 |
"max_steps": 4000,
|
| 1008 |
"num_train_epochs": 6,
|
| 1009 |
+
"total_flos": 1.84579222044672e+19,
|
| 1010 |
"trial_name": null,
|
| 1011 |
"trial_params": null
|
| 1012 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3567
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:730c7d9ec62d26c1223ee5e75fd3fdb877acb133e770bcd4e80ba24b21896b24
|
| 3 |
size 3567
|