linshoufan
commited on
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 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8680dced3930b9abcaa16374ccf16e3e11a09f4bff5b13e99058831dbac7136a
|
3 |
size 966995080
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1925064044
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9cacea682da039c7edf44c59f24360dad4d083c610f2f2574a0c14afe12bff0
|
3 |
size 1925064044
|
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:fba1ca94b44e4e4a1b4f9b82d10d6019eb9437e3c8e0ac1249502acb8cc9bc1b
|
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 sha256:05d76a81ce579e0f1f2bb68af30a2e95dfeadbbfe77f982467ddb98b43e349b1
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint": "./linshoufanfork-whisper-small-nan-tw/checkpoint-
|
4 |
-
"epoch": 0.
|
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,
|
@@ -454,6 +454,155 @@
|
|
454 |
"eval_samples_per_second": 2.465,
|
455 |
"eval_steps_per_second": 0.308,
|
456 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
457 |
}
|
458 |
],
|
459 |
"logging_steps": 25,
|
@@ -461,7 +610,7 @@
|
|
461 |
"num_input_tokens_seen": 0,
|
462 |
"num_train_epochs": 1,
|
463 |
"save_steps": 500,
|
464 |
-
"total_flos":
|
465 |
"train_batch_size": 16,
|
466 |
"trial_name": null,
|
467 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 35.404720629417255,
|
3 |
+
"best_model_checkpoint": "./linshoufanfork-whisper-small-nan-tw/checkpoint-2000",
|
4 |
+
"epoch": 0.6428801028608164,
|
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,
|
|
|
454 |
"eval_samples_per_second": 2.465,
|
455 |
"eval_steps_per_second": 0.308,
|
456 |
"step": 1500
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 0.49,
|
460 |
+
"grad_norm": 9.844304084777832,
|
461 |
+
"learning_rate": 5.267353038857523e-06,
|
462 |
+
"loss": 0.5035,
|
463 |
+
"step": 1525
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 0.5,
|
467 |
+
"grad_norm": 11.165616035461426,
|
468 |
+
"learning_rate": 5.184324144802392e-06,
|
469 |
+
"loss": 0.449,
|
470 |
+
"step": 1550
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.51,
|
474 |
+
"grad_norm": 10.43535327911377,
|
475 |
+
"learning_rate": 5.10129525074726e-06,
|
476 |
+
"loss": 0.4471,
|
477 |
+
"step": 1575
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.51,
|
481 |
+
"grad_norm": 9.737510681152344,
|
482 |
+
"learning_rate": 5.0182663566921295e-06,
|
483 |
+
"loss": 0.4779,
|
484 |
+
"step": 1600
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 0.52,
|
488 |
+
"grad_norm": 10.221022605895996,
|
489 |
+
"learning_rate": 4.935237462636998e-06,
|
490 |
+
"loss": 0.4266,
|
491 |
+
"step": 1625
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 0.53,
|
495 |
+
"grad_norm": 7.031712532043457,
|
496 |
+
"learning_rate": 4.852208568581867e-06,
|
497 |
+
"loss": 0.4355,
|
498 |
+
"step": 1650
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 0.54,
|
502 |
+
"grad_norm": 10.13843822479248,
|
503 |
+
"learning_rate": 4.769179674526736e-06,
|
504 |
+
"loss": 0.4506,
|
505 |
+
"step": 1675
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 0.55,
|
509 |
+
"grad_norm": 14.100777626037598,
|
510 |
+
"learning_rate": 4.686150780471604e-06,
|
511 |
+
"loss": 0.4484,
|
512 |
+
"step": 1700
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.55,
|
516 |
+
"grad_norm": 11.218331336975098,
|
517 |
+
"learning_rate": 4.603121886416473e-06,
|
518 |
+
"loss": 0.4637,
|
519 |
+
"step": 1725
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.56,
|
523 |
+
"grad_norm": 9.891203880310059,
|
524 |
+
"learning_rate": 4.520092992361343e-06,
|
525 |
+
"loss": 0.4142,
|
526 |
+
"step": 1750
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 0.57,
|
530 |
+
"grad_norm": 9.585916519165039,
|
531 |
+
"learning_rate": 4.437064098306211e-06,
|
532 |
+
"loss": 0.4202,
|
533 |
+
"step": 1775
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 0.58,
|
537 |
+
"grad_norm": 10.81905460357666,
|
538 |
+
"learning_rate": 4.35403520425108e-06,
|
539 |
+
"loss": 0.4459,
|
540 |
+
"step": 1800
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 0.59,
|
544 |
+
"grad_norm": 13.257423400878906,
|
545 |
+
"learning_rate": 4.271006310195949e-06,
|
546 |
+
"loss": 0.448,
|
547 |
+
"step": 1825
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 0.59,
|
551 |
+
"grad_norm": 9.057276725769043,
|
552 |
+
"learning_rate": 4.187977416140817e-06,
|
553 |
+
"loss": 0.4043,
|
554 |
+
"step": 1850
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.6,
|
558 |
+
"grad_norm": 11.002601623535156,
|
559 |
+
"learning_rate": 4.104948522085686e-06,
|
560 |
+
"loss": 0.4011,
|
561 |
+
"step": 1875
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.61,
|
565 |
+
"grad_norm": 15.421494483947754,
|
566 |
+
"learning_rate": 4.021919628030555e-06,
|
567 |
+
"loss": 0.4208,
|
568 |
+
"step": 1900
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 0.62,
|
572 |
+
"grad_norm": 12.186066627502441,
|
573 |
+
"learning_rate": 3.938890733975424e-06,
|
574 |
+
"loss": 0.389,
|
575 |
+
"step": 1925
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 0.63,
|
579 |
+
"grad_norm": 8.680899620056152,
|
580 |
+
"learning_rate": 3.855861839920293e-06,
|
581 |
+
"loss": 0.4189,
|
582 |
+
"step": 1950
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 0.63,
|
586 |
+
"grad_norm": 10.597740173339844,
|
587 |
+
"learning_rate": 3.7728329458651612e-06,
|
588 |
+
"loss": 0.3654,
|
589 |
+
"step": 1975
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 0.64,
|
593 |
+
"grad_norm": 10.675308227539062,
|
594 |
+
"learning_rate": 3.6898040518100305e-06,
|
595 |
+
"loss": 0.3512,
|
596 |
+
"step": 2000
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 0.64,
|
600 |
+
"eval_cer": 35.404720629417255,
|
601 |
+
"eval_loss": 0.4709227383136749,
|
602 |
+
"eval_runtime": 1802.3985,
|
603 |
+
"eval_samples_per_second": 2.461,
|
604 |
+
"eval_steps_per_second": 0.308,
|
605 |
+
"step": 2000
|
606 |
}
|
607 |
],
|
608 |
"logging_steps": 25,
|
|
|
610 |
"num_input_tokens_seen": 0,
|
611 |
"num_train_epochs": 1,
|
612 |
"save_steps": 500,
|
613 |
+
"total_flos": 9.23473281024e+18,
|
614 |
"train_batch_size": 16,
|
615 |
"trial_name": null,
|
616 |
"trial_params": null
|