Training in progress, step 2000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 290403936
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9823ac5309a0121bbf68af5c301f793de92bd5383b19486c5693e3292544ae2
|
3 |
size 290403936
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 574811514
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c79e864eb767de59929633bcbe6ca5222d062c56994cdbfb20401cd8c361bea7
|
3 |
size 574811514
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9dbbba60e72aa1d9209f2713e04111ddbf0bbbba59dd22bae5b72fb8174ffea8
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efe70d33f3fbb9c10a2f188c0a23f007fecdb7a03f5a154054e5c79c6735f222
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint": "./whisper-base-ha/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -457,6 +457,156 @@
|
|
457 |
"eval_wer": 112.41617168039855,
|
458 |
"eval_wer_ortho": 113.9453125,
|
459 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
460 |
}
|
461 |
],
|
462 |
"logging_steps": 25,
|
@@ -476,7 +626,7 @@
|
|
476 |
"attributes": {}
|
477 |
}
|
478 |
},
|
479 |
-
"total_flos":
|
480 |
"train_batch_size": 16,
|
481 |
"trial_name": null,
|
482 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 104.92431500287411,
|
3 |
+
"best_model_checkpoint": "./whisper-base-ha/checkpoint-2000",
|
4 |
+
"epoch": 12.738853503184714,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
457 |
"eval_wer": 112.41617168039855,
|
458 |
"eval_wer_ortho": 113.9453125,
|
459 |
"step": 1500
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 9.713375796178344,
|
463 |
+
"grad_norm": 4.020846366882324,
|
464 |
+
"learning_rate": 1e-05,
|
465 |
+
"loss": 0.0466,
|
466 |
+
"step": 1525
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 9.872611464968152,
|
470 |
+
"grad_norm": 5.376700401306152,
|
471 |
+
"learning_rate": 1e-05,
|
472 |
+
"loss": 0.0441,
|
473 |
+
"step": 1550
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 10.031847133757962,
|
477 |
+
"grad_norm": 1.6738530397415161,
|
478 |
+
"learning_rate": 1e-05,
|
479 |
+
"loss": 0.0453,
|
480 |
+
"step": 1575
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 10.19108280254777,
|
484 |
+
"grad_norm": 1.8049341440200806,
|
485 |
+
"learning_rate": 1e-05,
|
486 |
+
"loss": 0.0276,
|
487 |
+
"step": 1600
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 10.35031847133758,
|
491 |
+
"grad_norm": 2.4481654167175293,
|
492 |
+
"learning_rate": 1e-05,
|
493 |
+
"loss": 0.0272,
|
494 |
+
"step": 1625
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 10.509554140127388,
|
498 |
+
"grad_norm": 1.8371031284332275,
|
499 |
+
"learning_rate": 1e-05,
|
500 |
+
"loss": 0.0231,
|
501 |
+
"step": 1650
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 10.668789808917197,
|
505 |
+
"grad_norm": 4.078380107879639,
|
506 |
+
"learning_rate": 1e-05,
|
507 |
+
"loss": 0.025,
|
508 |
+
"step": 1675
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 10.828025477707007,
|
512 |
+
"grad_norm": 3.8198206424713135,
|
513 |
+
"learning_rate": 1e-05,
|
514 |
+
"loss": 0.0324,
|
515 |
+
"step": 1700
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 10.987261146496815,
|
519 |
+
"grad_norm": 1.7313209772109985,
|
520 |
+
"learning_rate": 1e-05,
|
521 |
+
"loss": 0.0276,
|
522 |
+
"step": 1725
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 11.146496815286625,
|
526 |
+
"grad_norm": 4.576403617858887,
|
527 |
+
"learning_rate": 1e-05,
|
528 |
+
"loss": 0.0187,
|
529 |
+
"step": 1750
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 11.305732484076433,
|
533 |
+
"grad_norm": 1.7391539812088013,
|
534 |
+
"learning_rate": 1e-05,
|
535 |
+
"loss": 0.0163,
|
536 |
+
"step": 1775
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 11.464968152866241,
|
540 |
+
"grad_norm": 1.6256043910980225,
|
541 |
+
"learning_rate": 1e-05,
|
542 |
+
"loss": 0.0181,
|
543 |
+
"step": 1800
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 11.624203821656051,
|
547 |
+
"grad_norm": 1.2041560411453247,
|
548 |
+
"learning_rate": 1e-05,
|
549 |
+
"loss": 0.0177,
|
550 |
+
"step": 1825
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 11.78343949044586,
|
554 |
+
"grad_norm": 1.2015411853790283,
|
555 |
+
"learning_rate": 1e-05,
|
556 |
+
"loss": 0.0185,
|
557 |
+
"step": 1850
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 11.94267515923567,
|
561 |
+
"grad_norm": 1.7597877979278564,
|
562 |
+
"learning_rate": 1e-05,
|
563 |
+
"loss": 0.0185,
|
564 |
+
"step": 1875
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 12.101910828025478,
|
568 |
+
"grad_norm": 1.2829164266586304,
|
569 |
+
"learning_rate": 1e-05,
|
570 |
+
"loss": 0.014,
|
571 |
+
"step": 1900
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 12.261146496815286,
|
575 |
+
"grad_norm": 1.5107444524765015,
|
576 |
+
"learning_rate": 1e-05,
|
577 |
+
"loss": 0.0115,
|
578 |
+
"step": 1925
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 12.420382165605096,
|
582 |
+
"grad_norm": 1.1438385248184204,
|
583 |
+
"learning_rate": 1e-05,
|
584 |
+
"loss": 0.0118,
|
585 |
+
"step": 1950
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 12.579617834394904,
|
589 |
+
"grad_norm": 2.5098214149475098,
|
590 |
+
"learning_rate": 1e-05,
|
591 |
+
"loss": 0.0113,
|
592 |
+
"step": 1975
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 12.738853503184714,
|
596 |
+
"grad_norm": 0.9226982593536377,
|
597 |
+
"learning_rate": 1e-05,
|
598 |
+
"loss": 0.0134,
|
599 |
+
"step": 2000
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 12.738853503184714,
|
603 |
+
"eval_loss": 2.5008862018585205,
|
604 |
+
"eval_runtime": 168.7552,
|
605 |
+
"eval_samples_per_second": 3.911,
|
606 |
+
"eval_steps_per_second": 0.249,
|
607 |
+
"eval_wer": 104.92431500287411,
|
608 |
+
"eval_wer_ortho": 106.28906250000001,
|
609 |
+
"step": 2000
|
610 |
}
|
611 |
],
|
612 |
"logging_steps": 25,
|
|
|
626 |
"attributes": {}
|
627 |
}
|
628 |
},
|
629 |
+
"total_flos": 2.07240659730432e+18,
|
630 |
"train_batch_size": 16,
|
631 |
"trial_name": null,
|
632 |
"trial_params": null
|