Commit
β’
bc5c400
1
Parent(s):
d71bd83
Training in progress, step 800
Browse files- {checkpoint-500 β checkpoint-800}/config.json +0 -0
- {checkpoint-500 β checkpoint-800}/optimizer.pt +1 -1
- {checkpoint-500 β checkpoint-800}/preprocessor_config.json +0 -0
- {checkpoint-500 β checkpoint-800}/pytorch_model.bin +1 -1
- {checkpoint-500 β checkpoint-800}/rng_state.pth +2 -2
- {checkpoint-500 β checkpoint-800}/scaler.pt +1 -1
- {checkpoint-500 β checkpoint-800}/scheduler.pt +1 -1
- {checkpoint-500 β checkpoint-800}/trainer_state.json +210 -3
- {checkpoint-500 β checkpoint-800}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-500 β checkpoint-800}/config.json
RENAMED
File without changes
|
{checkpoint-500 β checkpoint-800}/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:ad7ea02ec7c343ab141220559f7cfc2e88de82783306133f00b7a0f427c9391a
|
3 |
size 2490346001
|
{checkpoint-500 β checkpoint-800}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-500 β checkpoint-800}/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:aa43bdbed16b5fc10ebee537908dcf5e5f5e67381037463baf9a181a9926057d
|
3 |
size 1262067185
|
{checkpoint-500 β checkpoint-800}/rng_state.pth
RENAMED
@@ -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:b18fc220a6ff2583766eb993c583889da7a20bad4aad048832b1c72e10236be1
|
3 |
+
size 14631
|
{checkpoint-500 β checkpoint-800}/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:bea98ff9335db6568bd2c2133c9e5febb1265494530eb77d55ae8ee8b21d5e4e
|
3 |
size 559
|
{checkpoint-500 β checkpoint-800}/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 sha256:66bd4c9006c0fa0d3e816d59ca98b89719c7ee4d17d76fad0d1502cc27f1f6a6
|
3 |
size 623
|
{checkpoint-500 β checkpoint-800}/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,
|
@@ -351,11 +351,218 @@
|
|
351 |
"eval_steps_per_second": 1.114,
|
352 |
"eval_wer": 1.0,
|
353 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
354 |
}
|
355 |
],
|
356 |
"max_steps": 6501,
|
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": 0.3690888119953864,
|
5 |
+
"global_step": 800,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
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 |
+
"epoch": 0.33,
|
495 |
+
"learning_rate": 6.838304552590267e-05,
|
496 |
+
"loss": 2.9139,
|
497 |
+
"step": 710
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 0.33,
|
501 |
+
"learning_rate": 6.826530612244897e-05,
|
502 |
+
"loss": 2.9957,
|
503 |
+
"step": 720
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 0.34,
|
507 |
+
"learning_rate": 6.814756671899528e-05,
|
508 |
+
"loss": 2.9842,
|
509 |
+
"step": 730
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 0.34,
|
513 |
+
"learning_rate": 6.802982731554159e-05,
|
514 |
+
"loss": 3.2804,
|
515 |
+
"step": 740
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.35,
|
519 |
+
"learning_rate": 6.792386185243327e-05,
|
520 |
+
"loss": 3.4944,
|
521 |
+
"step": 750
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.35,
|
525 |
+
"learning_rate": 6.780612244897958e-05,
|
526 |
+
"loss": 2.9905,
|
527 |
+
"step": 760
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.36,
|
531 |
+
"learning_rate": 6.768838304552589e-05,
|
532 |
+
"loss": 2.9692,
|
533 |
+
"step": 770
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 0.36,
|
537 |
+
"learning_rate": 6.757064364207221e-05,
|
538 |
+
"loss": 2.9747,
|
539 |
+
"step": 780
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 0.36,
|
543 |
+
"learning_rate": 6.745290423861852e-05,
|
544 |
+
"loss": 3.294,
|
545 |
+
"step": 790
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 0.37,
|
549 |
+
"learning_rate": 6.73469387755102e-05,
|
550 |
+
"loss": 3.5998,
|
551 |
+
"step": 800
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.37,
|
555 |
+
"eval_loss": 3.059178590774536,
|
556 |
+
"eval_runtime": 129.2337,
|
557 |
+
"eval_samples_per_second": 35.749,
|
558 |
+
"eval_steps_per_second": 1.122,
|
559 |
+
"eval_wer": 1.0,
|
560 |
+
"step": 800
|
561 |
}
|
562 |
],
|
563 |
"max_steps": 6501,
|
564 |
"num_train_epochs": 3,
|
565 |
+
"total_flos": 1.5122477119825152e+19,
|
566 |
"trial_name": null,
|
567 |
"trial_params": null
|
568 |
}
|
{checkpoint-500 β checkpoint-800}/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:aa43bdbed16b5fc10ebee537908dcf5e5f5e67381037463baf9a181a9926057d
|
3 |
size 1262067185
|