Training in progress, step 75, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 101184122
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:004fb050f555ccea670fb1e303937e5bfa204f036a379dfde6af4b55eaac593e
|
3 |
size 101184122
|
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 sha256:9c1d644a4a39d949387b662bdefaee2232811c755c916d4547d1e6e803c86cf5
|
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:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 9,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -405,6 +405,205 @@
|
|
405 |
"learning_rate": 5.868240888334653e-05,
|
406 |
"loss": 0.0,
|
407 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
408 |
}
|
409 |
],
|
410 |
"logging_steps": 1,
|
@@ -424,7 +623,7 @@
|
|
424 |
"attributes": {}
|
425 |
}
|
426 |
},
|
427 |
-
"total_flos":
|
428 |
"train_batch_size": 8,
|
429 |
"trial_name": null,
|
430 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.027563395810363836,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 75,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
405 |
"learning_rate": 5.868240888334653e-05,
|
406 |
"loss": 0.0,
|
407 |
"step": 50
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 0.018743109151047408,
|
411 |
+
"grad_norm": NaN,
|
412 |
+
"learning_rate": 5.695865504800327e-05,
|
413 |
+
"loss": 0.0,
|
414 |
+
"step": 51
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.019110621095185593,
|
418 |
+
"grad_norm": NaN,
|
419 |
+
"learning_rate": 5.522642316338268e-05,
|
420 |
+
"loss": 0.0,
|
421 |
+
"step": 52
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 0.01947813303932378,
|
425 |
+
"grad_norm": NaN,
|
426 |
+
"learning_rate": 5.348782368720626e-05,
|
427 |
+
"loss": 0.0,
|
428 |
+
"step": 53
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.019845644983461964,
|
432 |
+
"grad_norm": NaN,
|
433 |
+
"learning_rate": 5.174497483512506e-05,
|
434 |
+
"loss": 0.0,
|
435 |
+
"step": 54
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.019845644983461964,
|
439 |
+
"eval_loss": NaN,
|
440 |
+
"eval_runtime": 66.1727,
|
441 |
+
"eval_samples_per_second": 34.622,
|
442 |
+
"eval_steps_per_second": 4.337,
|
443 |
+
"step": 54
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.020213156927600145,
|
447 |
+
"grad_norm": NaN,
|
448 |
+
"learning_rate": 5e-05,
|
449 |
+
"loss": 0.0,
|
450 |
+
"step": 55
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.02058066887173833,
|
454 |
+
"grad_norm": NaN,
|
455 |
+
"learning_rate": 4.825502516487497e-05,
|
456 |
+
"loss": 0.0,
|
457 |
+
"step": 56
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.020948180815876516,
|
461 |
+
"grad_norm": NaN,
|
462 |
+
"learning_rate": 4.6512176312793736e-05,
|
463 |
+
"loss": 0.0,
|
464 |
+
"step": 57
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.0213156927600147,
|
468 |
+
"grad_norm": NaN,
|
469 |
+
"learning_rate": 4.477357683661734e-05,
|
470 |
+
"loss": 0.0,
|
471 |
+
"step": 58
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.021683204704152886,
|
475 |
+
"grad_norm": NaN,
|
476 |
+
"learning_rate": 4.3041344951996746e-05,
|
477 |
+
"loss": 0.0,
|
478 |
+
"step": 59
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.022050716648291068,
|
482 |
+
"grad_norm": NaN,
|
483 |
+
"learning_rate": 4.131759111665349e-05,
|
484 |
+
"loss": 0.0,
|
485 |
+
"step": 60
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.022418228592429253,
|
489 |
+
"grad_norm": NaN,
|
490 |
+
"learning_rate": 3.960441545911204e-05,
|
491 |
+
"loss": 0.0,
|
492 |
+
"step": 61
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.02278574053656744,
|
496 |
+
"grad_norm": NaN,
|
497 |
+
"learning_rate": 3.790390522001662e-05,
|
498 |
+
"loss": 0.0,
|
499 |
+
"step": 62
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.023153252480705624,
|
503 |
+
"grad_norm": NaN,
|
504 |
+
"learning_rate": 3.6218132209150045e-05,
|
505 |
+
"loss": 0.0,
|
506 |
+
"step": 63
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.023153252480705624,
|
510 |
+
"eval_loss": NaN,
|
511 |
+
"eval_runtime": 66.173,
|
512 |
+
"eval_samples_per_second": 34.621,
|
513 |
+
"eval_steps_per_second": 4.337,
|
514 |
+
"step": 63
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.02352076442484381,
|
518 |
+
"grad_norm": NaN,
|
519 |
+
"learning_rate": 3.4549150281252636e-05,
|
520 |
+
"loss": 0.0,
|
521 |
+
"step": 64
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.02388827636898199,
|
525 |
+
"grad_norm": NaN,
|
526 |
+
"learning_rate": 3.289899283371657e-05,
|
527 |
+
"loss": 0.0,
|
528 |
+
"step": 65
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 0.024255788313120176,
|
532 |
+
"grad_norm": NaN,
|
533 |
+
"learning_rate": 3.12696703292044e-05,
|
534 |
+
"loss": 0.0,
|
535 |
+
"step": 66
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.02462330025725836,
|
539 |
+
"grad_norm": NaN,
|
540 |
+
"learning_rate": 2.9663167846209998e-05,
|
541 |
+
"loss": 0.0,
|
542 |
+
"step": 67
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.024990812201396546,
|
546 |
+
"grad_norm": NaN,
|
547 |
+
"learning_rate": 2.8081442660546125e-05,
|
548 |
+
"loss": 0.0,
|
549 |
+
"step": 68
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.025358324145534728,
|
553 |
+
"grad_norm": NaN,
|
554 |
+
"learning_rate": 2.6526421860705473e-05,
|
555 |
+
"loss": 0.0,
|
556 |
+
"step": 69
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.025725836089672913,
|
560 |
+
"grad_norm": NaN,
|
561 |
+
"learning_rate": 2.500000000000001e-05,
|
562 |
+
"loss": 0.0,
|
563 |
+
"step": 70
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.0260933480338111,
|
567 |
+
"grad_norm": NaN,
|
568 |
+
"learning_rate": 2.350403678833976e-05,
|
569 |
+
"loss": 0.0,
|
570 |
+
"step": 71
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.026460859977949284,
|
574 |
+
"grad_norm": NaN,
|
575 |
+
"learning_rate": 2.2040354826462668e-05,
|
576 |
+
"loss": 0.0,
|
577 |
+
"step": 72
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 0.026460859977949284,
|
581 |
+
"eval_loss": NaN,
|
582 |
+
"eval_runtime": 66.082,
|
583 |
+
"eval_samples_per_second": 34.669,
|
584 |
+
"eval_steps_per_second": 4.343,
|
585 |
+
"step": 72
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.02682837192208747,
|
589 |
+
"grad_norm": NaN,
|
590 |
+
"learning_rate": 2.061073738537635e-05,
|
591 |
+
"loss": 0.0,
|
592 |
+
"step": 73
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.02719588386622565,
|
596 |
+
"grad_norm": NaN,
|
597 |
+
"learning_rate": 1.9216926233717085e-05,
|
598 |
+
"loss": 0.0,
|
599 |
+
"step": 74
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.027563395810363836,
|
603 |
+
"grad_norm": NaN,
|
604 |
+
"learning_rate": 1.7860619515673033e-05,
|
605 |
+
"loss": 0.0,
|
606 |
+
"step": 75
|
607 |
}
|
608 |
],
|
609 |
"logging_steps": 1,
|
|
|
623 |
"attributes": {}
|
624 |
}
|
625 |
},
|
626 |
+
"total_flos": 7720265790259200.0,
|
627 |
"train_batch_size": 8,
|
628 |
"trial_name": null,
|
629 |
"trial_params": null
|