Training in progress, step 100, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 50503544
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96ce0314173a36001be124e563371f4dbf4d67976065e79dc74b46b9058e4b66
|
3 |
size 50503544
|
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 sha256:933ac0599e4a17791df367dfcc44b69fd177609c60ab919468e026dbc222e401
|
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:e4109ea023d2b4f1eda8dd9fb89823ed8490a56a4d4c7bbc4f8d7162970b5133
|
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:dcdf921ba93c40432f46569609c07042f6599be99ba80522cb2d9b52ee37d8be
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -381,6 +381,372 @@
|
|
381 |
"eval_samples_per_second": 19.716,
|
382 |
"eval_steps_per_second": 2.76,
|
383 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
384 |
}
|
385 |
],
|
386 |
"logging_steps": 1,
|
@@ -409,7 +775,7 @@
|
|
409 |
"attributes": {}
|
410 |
}
|
411 |
},
|
412 |
-
"total_flos":
|
413 |
"train_batch_size": 8,
|
414 |
"trial_name": null,
|
415 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.5009154081344604,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 1.1424501424501425,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
381 |
"eval_samples_per_second": 19.716,
|
382 |
"eval_steps_per_second": 2.76,
|
383 |
"step": 50
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.5811965811965812,
|
387 |
+
"grad_norm": 1.0719735622406006,
|
388 |
+
"learning_rate": 0.0002570649169030708,
|
389 |
+
"loss": 1.8955,
|
390 |
+
"step": 51
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.5925925925925926,
|
394 |
+
"grad_norm": 1.078503966331482,
|
395 |
+
"learning_rate": 0.0002550576202307026,
|
396 |
+
"loss": 1.5589,
|
397 |
+
"step": 52
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 0.603988603988604,
|
401 |
+
"grad_norm": 1.1071960926055908,
|
402 |
+
"learning_rate": 0.00025301269668202516,
|
403 |
+
"loss": 1.546,
|
404 |
+
"step": 53
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.6153846153846154,
|
408 |
+
"grad_norm": 1.0681451559066772,
|
409 |
+
"learning_rate": 0.0002509308786559378,
|
410 |
+
"loss": 1.5604,
|
411 |
+
"step": 54
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.6267806267806267,
|
415 |
+
"grad_norm": 1.173900842666626,
|
416 |
+
"learning_rate": 0.00024881291176526903,
|
417 |
+
"loss": 1.4711,
|
418 |
+
"step": 55
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 0.6381766381766382,
|
422 |
+
"grad_norm": 1.070963740348816,
|
423 |
+
"learning_rate": 0.00024665955456973154,
|
424 |
+
"loss": 1.3633,
|
425 |
+
"step": 56
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.6495726495726496,
|
429 |
+
"grad_norm": 1.2699030637741089,
|
430 |
+
"learning_rate": 0.00024447157830424066,
|
431 |
+
"loss": 1.4303,
|
432 |
+
"step": 57
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 0.6609686609686609,
|
436 |
+
"grad_norm": 5.538363933563232,
|
437 |
+
"learning_rate": 0.00024224976660269302,
|
438 |
+
"loss": 1.7974,
|
439 |
+
"step": 58
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 0.6723646723646723,
|
443 |
+
"grad_norm": 1.8669769763946533,
|
444 |
+
"learning_rate": 0.0002399949152173043,
|
445 |
+
"loss": 1.3754,
|
446 |
+
"step": 59
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.6837606837606838,
|
450 |
+
"grad_norm": 1.68172287940979,
|
451 |
+
"learning_rate": 0.00023770783173360704,
|
452 |
+
"loss": 1.3149,
|
453 |
+
"step": 60
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.6951566951566952,
|
457 |
+
"grad_norm": 1.3897011280059814,
|
458 |
+
"learning_rate": 0.00023538933528120988,
|
459 |
+
"loss": 1.0742,
|
460 |
+
"step": 61
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 0.7065527065527065,
|
464 |
+
"grad_norm": 1.9569456577301025,
|
465 |
+
"learning_rate": 0.00023304025624042263,
|
466 |
+
"loss": 1.2155,
|
467 |
+
"step": 62
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.717948717948718,
|
471 |
+
"grad_norm": 3.3312759399414062,
|
472 |
+
"learning_rate": 0.00023066143594485178,
|
473 |
+
"loss": 2.1298,
|
474 |
+
"step": 63
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.7293447293447294,
|
478 |
+
"grad_norm": 1.547868013381958,
|
479 |
+
"learning_rate": 0.00022825372638007267,
|
480 |
+
"loss": 2.2686,
|
481 |
+
"step": 64
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.7407407407407407,
|
485 |
+
"grad_norm": 1.5944535732269287,
|
486 |
+
"learning_rate": 0.0002258179898784871,
|
487 |
+
"loss": 2.1082,
|
488 |
+
"step": 65
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.7521367521367521,
|
492 |
+
"grad_norm": 1.5516560077667236,
|
493 |
+
"learning_rate": 0.00022335509881047497,
|
494 |
+
"loss": 2.0809,
|
495 |
+
"step": 66
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.7635327635327636,
|
499 |
+
"grad_norm": 1.4995073080062866,
|
500 |
+
"learning_rate": 0.00022086593527195062,
|
501 |
+
"loss": 2.0216,
|
502 |
+
"step": 67
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 0.7749287749287749,
|
506 |
+
"grad_norm": 1.274309754371643,
|
507 |
+
"learning_rate": 0.00021835139076843623,
|
508 |
+
"loss": 1.8188,
|
509 |
+
"step": 68
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 0.7863247863247863,
|
513 |
+
"grad_norm": 0.9307559132575989,
|
514 |
+
"learning_rate": 0.00021581236589576476,
|
515 |
+
"loss": 1.6062,
|
516 |
+
"step": 69
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 0.7977207977207977,
|
520 |
+
"grad_norm": 1.0454336404800415,
|
521 |
+
"learning_rate": 0.00021324977001752757,
|
522 |
+
"loss": 1.5165,
|
523 |
+
"step": 70
|
524 |
+
},
|
525 |
+
{
|
526 |
+
"epoch": 0.8091168091168092,
|
527 |
+
"grad_norm": 0.9848281145095825,
|
528 |
+
"learning_rate": 0.00021066452093938153,
|
529 |
+
"loss": 1.5541,
|
530 |
+
"step": 71
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.8205128205128205,
|
534 |
+
"grad_norm": 1.0764801502227783,
|
535 |
+
"learning_rate": 0.0002080575445803326,
|
536 |
+
"loss": 1.511,
|
537 |
+
"step": 72
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.8319088319088319,
|
541 |
+
"grad_norm": 1.072153091430664,
|
542 |
+
"learning_rate": 0.00020542977464111352,
|
543 |
+
"loss": 1.6469,
|
544 |
+
"step": 73
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 0.8433048433048433,
|
548 |
+
"grad_norm": 1.0326112508773804,
|
549 |
+
"learning_rate": 0.00020278215226977493,
|
550 |
+
"loss": 1.5988,
|
551 |
+
"step": 74
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.8547008547008547,
|
555 |
+
"grad_norm": 1.093682050704956,
|
556 |
+
"learning_rate": 0.0002001156257246085,
|
557 |
+
"loss": 1.5237,
|
558 |
+
"step": 75
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 0.8547008547008547,
|
562 |
+
"eval_loss": 1.6302566528320312,
|
563 |
+
"eval_runtime": 2.5336,
|
564 |
+
"eval_samples_per_second": 19.735,
|
565 |
+
"eval_steps_per_second": 2.763,
|
566 |
+
"step": 75
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.8660968660968661,
|
570 |
+
"grad_norm": 1.018373727798462,
|
571 |
+
"learning_rate": 0.00019743115003452357,
|
572 |
+
"loss": 1.3891,
|
573 |
+
"step": 76
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.8774928774928775,
|
577 |
+
"grad_norm": 1.1713063716888428,
|
578 |
+
"learning_rate": 0.0001947296866569998,
|
579 |
+
"loss": 1.0838,
|
580 |
+
"step": 77
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 0.8888888888888888,
|
584 |
+
"grad_norm": 1.148584246635437,
|
585 |
+
"learning_rate": 0.00019201220313373607,
|
586 |
+
"loss": 1.4356,
|
587 |
+
"step": 78
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.9002849002849003,
|
591 |
+
"grad_norm": 1.1051701307296753,
|
592 |
+
"learning_rate": 0.00018927967274412098,
|
593 |
+
"loss": 1.1822,
|
594 |
+
"step": 79
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.9116809116809117,
|
598 |
+
"grad_norm": 1.3948734998703003,
|
599 |
+
"learning_rate": 0.00018653307415664877,
|
600 |
+
"loss": 1.2418,
|
601 |
+
"step": 80
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 0.9230769230769231,
|
605 |
+
"grad_norm": 1.060866355895996,
|
606 |
+
"learning_rate": 0.00018377339107840412,
|
607 |
+
"loss": 0.9866,
|
608 |
+
"step": 81
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.9344729344729344,
|
612 |
+
"grad_norm": 1.3267959356307983,
|
613 |
+
"learning_rate": 0.0001810016119027429,
|
614 |
+
"loss": 1.2331,
|
615 |
+
"step": 82
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.9458689458689459,
|
619 |
+
"grad_norm": 1.868615984916687,
|
620 |
+
"learning_rate": 0.00017821872935529505,
|
621 |
+
"loss": 1.0533,
|
622 |
+
"step": 83
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 0.9572649572649573,
|
626 |
+
"grad_norm": 3.270871639251709,
|
627 |
+
"learning_rate": 0.0001754257401384145,
|
628 |
+
"loss": 1.6908,
|
629 |
+
"step": 84
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 0.9686609686609686,
|
633 |
+
"grad_norm": 1.1830881834030151,
|
634 |
+
"learning_rate": 0.00017262364457420608,
|
635 |
+
"loss": 1.861,
|
636 |
+
"step": 85
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 0.98005698005698,
|
640 |
+
"grad_norm": 1.3552889823913574,
|
641 |
+
"learning_rate": 0.00016981344624625536,
|
642 |
+
"loss": 1.6788,
|
643 |
+
"step": 86
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 0.9914529914529915,
|
647 |
+
"grad_norm": 1.6340991258621216,
|
648 |
+
"learning_rate": 0.0001669961516401905,
|
649 |
+
"loss": 1.0865,
|
650 |
+
"step": 87
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 1.0056980056980056,
|
654 |
+
"grad_norm": 2.1923134326934814,
|
655 |
+
"learning_rate": 0.00016417276978320468,
|
656 |
+
"loss": 2.0869,
|
657 |
+
"step": 88
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 1.017094017094017,
|
661 |
+
"grad_norm": 1.1427710056304932,
|
662 |
+
"learning_rate": 0.00016134431188266851,
|
663 |
+
"loss": 1.9375,
|
664 |
+
"step": 89
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 1.0284900284900285,
|
668 |
+
"grad_norm": 1.0332353115081787,
|
669 |
+
"learning_rate": 0.00015851179096396112,
|
670 |
+
"loss": 1.8373,
|
671 |
+
"step": 90
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 1.03988603988604,
|
675 |
+
"grad_norm": 1.0836644172668457,
|
676 |
+
"learning_rate": 0.00015567622150765057,
|
677 |
+
"loss": 1.8318,
|
678 |
+
"step": 91
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 1.0512820512820513,
|
682 |
+
"grad_norm": 0.9457873702049255,
|
683 |
+
"learning_rate": 0.00015283861908615284,
|
684 |
+
"loss": 1.4851,
|
685 |
+
"step": 92
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 1.0626780626780628,
|
689 |
+
"grad_norm": 0.8754853010177612,
|
690 |
+
"learning_rate": 0.00015,
|
691 |
+
"loss": 1.3744,
|
692 |
+
"step": 93
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 1.074074074074074,
|
696 |
+
"grad_norm": 0.7847860455513,
|
697 |
+
"learning_rate": 0.00014716138091384716,
|
698 |
+
"loss": 1.3702,
|
699 |
+
"step": 94
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 1.0854700854700854,
|
703 |
+
"grad_norm": 0.8638334274291992,
|
704 |
+
"learning_rate": 0.00014432377849234946,
|
705 |
+
"loss": 1.4673,
|
706 |
+
"step": 95
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 1.0968660968660968,
|
710 |
+
"grad_norm": 0.8940455913543701,
|
711 |
+
"learning_rate": 0.00014148820903603888,
|
712 |
+
"loss": 1.2493,
|
713 |
+
"step": 96
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 1.1082621082621082,
|
717 |
+
"grad_norm": 0.8780096769332886,
|
718 |
+
"learning_rate": 0.00013865568811733151,
|
719 |
+
"loss": 1.3118,
|
720 |
+
"step": 97
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 1.1196581196581197,
|
724 |
+
"grad_norm": 0.9429007172584534,
|
725 |
+
"learning_rate": 0.00013582723021679532,
|
726 |
+
"loss": 1.255,
|
727 |
+
"step": 98
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 1.131054131054131,
|
731 |
+
"grad_norm": 1.0075204372406006,
|
732 |
+
"learning_rate": 0.0001330038483598095,
|
733 |
+
"loss": 1.112,
|
734 |
+
"step": 99
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 1.1424501424501425,
|
738 |
+
"grad_norm": 1.133158564567566,
|
739 |
+
"learning_rate": 0.00013018655375374467,
|
740 |
+
"loss": 1.175,
|
741 |
+
"step": 100
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 1.1424501424501425,
|
745 |
+
"eval_loss": 1.5009154081344604,
|
746 |
+
"eval_runtime": 2.8313,
|
747 |
+
"eval_samples_per_second": 17.66,
|
748 |
+
"eval_steps_per_second": 2.472,
|
749 |
+
"step": 100
|
750 |
}
|
751 |
],
|
752 |
"logging_steps": 1,
|
|
|
775 |
"attributes": {}
|
776 |
}
|
777 |
},
|
778 |
+
"total_flos": 2.4663032422465536e+16,
|
779 |
"train_batch_size": 8,
|
780 |
"trial_name": null,
|
781 |
"trial_params": null
|