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 26008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4b6965ee3c8fe9f288af5656c77196c7e86837303dc705239465706b719e92d
|
3 |
size 26008
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 68874
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:646344145be2ff711dad8f94e513f264eb66c7dd17b593493b449da9387d4a8e
|
3 |
size 68874
|
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:d44d335247c68c299d5cb17ae000a9368d28c39c4f813ee6bfbc93fb640cf891
|
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:c5d2a6c6aafc669cea03b9634666f204de949a3d45ce2f48a07e7e3eaf18c715
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 11.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch": 0.
|
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": 161.815,
|
382 |
"eval_steps_per_second": 22.654,
|
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": 11.921051025390625,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.4672897196261682,
|
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": 161.815,
|
382 |
"eval_steps_per_second": 22.654,
|
383 |
"step": 50
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.2383177570093458,
|
387 |
+
"grad_norm": 0.0555480420589447,
|
388 |
+
"learning_rate": 0.0002668315918143169,
|
389 |
+
"loss": 11.9239,
|
390 |
+
"step": 51
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.24299065420560748,
|
394 |
+
"grad_norm": 0.03427752107381821,
|
395 |
+
"learning_rate": 0.00026526016662852886,
|
396 |
+
"loss": 11.9273,
|
397 |
+
"step": 52
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 0.24766355140186916,
|
401 |
+
"grad_norm": 0.051935601979494095,
|
402 |
+
"learning_rate": 0.00026365723046405023,
|
403 |
+
"loss": 11.9254,
|
404 |
+
"step": 53
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.2523364485981308,
|
408 |
+
"grad_norm": 0.05068502947688103,
|
409 |
+
"learning_rate": 0.0002620232215476231,
|
410 |
+
"loss": 11.9243,
|
411 |
+
"step": 54
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.2570093457943925,
|
415 |
+
"grad_norm": 0.042215969413518906,
|
416 |
+
"learning_rate": 0.0002603585866009697,
|
417 |
+
"loss": 11.9256,
|
418 |
+
"step": 55
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 0.2616822429906542,
|
422 |
+
"grad_norm": 0.03927940875291824,
|
423 |
+
"learning_rate": 0.00025866378071866334,
|
424 |
+
"loss": 11.9255,
|
425 |
+
"step": 56
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.26635514018691586,
|
429 |
+
"grad_norm": 0.041530344635248184,
|
430 |
+
"learning_rate": 0.00025693926724370956,
|
431 |
+
"loss": 11.9267,
|
432 |
+
"step": 57
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 0.27102803738317754,
|
436 |
+
"grad_norm": 0.05640103295445442,
|
437 |
+
"learning_rate": 0.00025518551764087326,
|
438 |
+
"loss": 11.9244,
|
439 |
+
"step": 58
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 0.2757009345794392,
|
443 |
+
"grad_norm": 0.039908554404973984,
|
444 |
+
"learning_rate": 0.00025340301136778483,
|
445 |
+
"loss": 11.9261,
|
446 |
+
"step": 59
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.2803738317757009,
|
450 |
+
"grad_norm": 0.03271481394767761,
|
451 |
+
"learning_rate": 0.00025159223574386114,
|
452 |
+
"loss": 11.9258,
|
453 |
+
"step": 60
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.2850467289719626,
|
457 |
+
"grad_norm": 0.0314725823700428,
|
458 |
+
"learning_rate": 0.0002497536858170772,
|
459 |
+
"loss": 11.9223,
|
460 |
+
"step": 61
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 0.2897196261682243,
|
464 |
+
"grad_norm": 0.03497527167201042,
|
465 |
+
"learning_rate": 0.00024788786422862526,
|
466 |
+
"loss": 11.9226,
|
467 |
+
"step": 62
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.29439252336448596,
|
471 |
+
"grad_norm": 0.03343958035111427,
|
472 |
+
"learning_rate": 0.00024599528107549745,
|
473 |
+
"loss": 11.9246,
|
474 |
+
"step": 63
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.29906542056074764,
|
478 |
+
"grad_norm": 0.03223850205540657,
|
479 |
+
"learning_rate": 0.00024407645377103054,
|
480 |
+
"loss": 11.9208,
|
481 |
+
"step": 64
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.3037383177570093,
|
485 |
+
"grad_norm": 0.03138720244169235,
|
486 |
+
"learning_rate": 0.00024213190690345018,
|
487 |
+
"loss": 11.9224,
|
488 |
+
"step": 65
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.308411214953271,
|
492 |
+
"grad_norm": 0.02842772752046585,
|
493 |
+
"learning_rate": 0.00024016217209245374,
|
494 |
+
"loss": 11.9213,
|
495 |
+
"step": 66
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.3130841121495327,
|
499 |
+
"grad_norm": 0.033133890479803085,
|
500 |
+
"learning_rate": 0.00023816778784387094,
|
501 |
+
"loss": 11.9225,
|
502 |
+
"step": 67
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 0.3177570093457944,
|
506 |
+
"grad_norm": 0.032245416194200516,
|
507 |
+
"learning_rate": 0.0002361492994024415,
|
508 |
+
"loss": 11.9209,
|
509 |
+
"step": 68
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 0.32242990654205606,
|
513 |
+
"grad_norm": 0.026734715327620506,
|
514 |
+
"learning_rate": 0.0002341072586027509,
|
515 |
+
"loss": 11.925,
|
516 |
+
"step": 69
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 0.32710280373831774,
|
520 |
+
"grad_norm": 0.025514936074614525,
|
521 |
+
"learning_rate": 0.00023204222371836405,
|
522 |
+
"loss": 11.9217,
|
523 |
+
"step": 70
|
524 |
+
},
|
525 |
+
{
|
526 |
+
"epoch": 0.3317757009345794,
|
527 |
+
"grad_norm": 0.018397009000182152,
|
528 |
+
"learning_rate": 0.00022995475930919905,
|
529 |
+
"loss": 11.9264,
|
530 |
+
"step": 71
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.3364485981308411,
|
534 |
+
"grad_norm": 0.017135081812739372,
|
535 |
+
"learning_rate": 0.00022784543606718227,
|
536 |
+
"loss": 11.9244,
|
537 |
+
"step": 72
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.3411214953271028,
|
541 |
+
"grad_norm": 0.02699720673263073,
|
542 |
+
"learning_rate": 0.00022571483066022657,
|
543 |
+
"loss": 11.9216,
|
544 |
+
"step": 73
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 0.34579439252336447,
|
548 |
+
"grad_norm": 0.024376867339015007,
|
549 |
+
"learning_rate": 0.0002235635255745762,
|
550 |
+
"loss": 11.9232,
|
551 |
+
"step": 74
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.35046728971962615,
|
555 |
+
"grad_norm": 0.023777619004249573,
|
556 |
+
"learning_rate": 0.00022139210895556104,
|
557 |
+
"loss": 11.9243,
|
558 |
+
"step": 75
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 0.35046728971962615,
|
562 |
+
"eval_loss": 11.921453475952148,
|
563 |
+
"eval_runtime": 0.3108,
|
564 |
+
"eval_samples_per_second": 160.851,
|
565 |
+
"eval_steps_per_second": 22.519,
|
566 |
+
"step": 75
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.35514018691588783,
|
570 |
+
"grad_norm": 0.02467428147792816,
|
571 |
+
"learning_rate": 0.00021920117444680317,
|
572 |
+
"loss": 11.9218,
|
573 |
+
"step": 76
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.3598130841121495,
|
577 |
+
"grad_norm": 0.014774040319025517,
|
578 |
+
"learning_rate": 0.00021699132102792097,
|
579 |
+
"loss": 11.9219,
|
580 |
+
"step": 77
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 0.3644859813084112,
|
584 |
+
"grad_norm": 0.01568908616900444,
|
585 |
+
"learning_rate": 0.0002147631528507739,
|
586 |
+
"loss": 11.9206,
|
587 |
+
"step": 78
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.3691588785046729,
|
591 |
+
"grad_norm": 0.021154990419745445,
|
592 |
+
"learning_rate": 0.00021251727907429355,
|
593 |
+
"loss": 11.9222,
|
594 |
+
"step": 79
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.37383177570093457,
|
598 |
+
"grad_norm": 0.01931612752377987,
|
599 |
+
"learning_rate": 0.0002102543136979454,
|
600 |
+
"loss": 11.9229,
|
601 |
+
"step": 80
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 0.37850467289719625,
|
605 |
+
"grad_norm": 0.02147780731320381,
|
606 |
+
"learning_rate": 0.0002079748753938678,
|
607 |
+
"loss": 11.923,
|
608 |
+
"step": 81
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.38317757009345793,
|
612 |
+
"grad_norm": 0.01698346436023712,
|
613 |
+
"learning_rate": 0.0002056795873377331,
|
614 |
+
"loss": 11.9215,
|
615 |
+
"step": 82
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.3878504672897196,
|
619 |
+
"grad_norm": 0.021959029138088226,
|
620 |
+
"learning_rate": 0.00020336907703837748,
|
621 |
+
"loss": 11.9202,
|
622 |
+
"step": 83
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 0.3925233644859813,
|
626 |
+
"grad_norm": 0.018221363425254822,
|
627 |
+
"learning_rate": 0.00020104397616624645,
|
628 |
+
"loss": 11.9213,
|
629 |
+
"step": 84
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 0.397196261682243,
|
633 |
+
"grad_norm": 0.014806934632360935,
|
634 |
+
"learning_rate": 0.00019870492038070252,
|
635 |
+
"loss": 11.921,
|
636 |
+
"step": 85
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 0.40186915887850466,
|
640 |
+
"grad_norm": 0.019513826817274094,
|
641 |
+
"learning_rate": 0.0001963525491562421,
|
642 |
+
"loss": 11.9189,
|
643 |
+
"step": 86
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 0.40654205607476634,
|
647 |
+
"grad_norm": 0.01412623468786478,
|
648 |
+
"learning_rate": 0.0001939875056076697,
|
649 |
+
"loss": 11.9225,
|
650 |
+
"step": 87
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.411214953271028,
|
654 |
+
"grad_norm": 0.01801372691988945,
|
655 |
+
"learning_rate": 0.00019161043631427666,
|
656 |
+
"loss": 11.9201,
|
657 |
+
"step": 88
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.4158878504672897,
|
661 |
+
"grad_norm": 0.019024653360247612,
|
662 |
+
"learning_rate": 0.00018922199114307294,
|
663 |
+
"loss": 11.9205,
|
664 |
+
"step": 89
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 0.4205607476635514,
|
668 |
+
"grad_norm": 0.021895864978432655,
|
669 |
+
"learning_rate": 0.00018682282307111987,
|
670 |
+
"loss": 11.9216,
|
671 |
+
"step": 90
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 0.4252336448598131,
|
675 |
+
"grad_norm": 0.025304431095719337,
|
676 |
+
"learning_rate": 0.00018441358800701273,
|
677 |
+
"loss": 11.9214,
|
678 |
+
"step": 91
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 0.42990654205607476,
|
682 |
+
"grad_norm": 0.0259839054197073,
|
683 |
+
"learning_rate": 0.00018199494461156203,
|
684 |
+
"loss": 11.9253,
|
685 |
+
"step": 92
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.43457943925233644,
|
689 |
+
"grad_norm": 0.04013689234852791,
|
690 |
+
"learning_rate": 0.000179567554117722,
|
691 |
+
"loss": 11.9211,
|
692 |
+
"step": 93
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.4392523364485981,
|
696 |
+
"grad_norm": 0.032571107149124146,
|
697 |
+
"learning_rate": 0.00017713208014981648,
|
698 |
+
"loss": 11.9246,
|
699 |
+
"step": 94
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.4439252336448598,
|
703 |
+
"grad_norm": 0.04223785176873207,
|
704 |
+
"learning_rate": 0.00017468918854211007,
|
705 |
+
"loss": 11.9277,
|
706 |
+
"step": 95
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 0.4485981308411215,
|
710 |
+
"grad_norm": 0.01614546775817871,
|
711 |
+
"learning_rate": 0.00017223954715677627,
|
712 |
+
"loss": 11.9202,
|
713 |
+
"step": 96
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 0.4532710280373832,
|
717 |
+
"grad_norm": 0.05689317733049393,
|
718 |
+
"learning_rate": 0.00016978382570131034,
|
719 |
+
"loss": 11.9215,
|
720 |
+
"step": 97
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 0.45794392523364486,
|
724 |
+
"grad_norm": 0.04419248178601265,
|
725 |
+
"learning_rate": 0.00016732269554543794,
|
726 |
+
"loss": 11.9244,
|
727 |
+
"step": 98
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 0.46261682242990654,
|
731 |
+
"grad_norm": 0.05944395065307617,
|
732 |
+
"learning_rate": 0.00016485682953756942,
|
733 |
+
"loss": 11.9218,
|
734 |
+
"step": 99
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.4672897196261682,
|
738 |
+
"grad_norm": 0.05680546537041664,
|
739 |
+
"learning_rate": 0.00016238690182084986,
|
740 |
+
"loss": 11.9257,
|
741 |
+
"step": 100
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.4672897196261682,
|
745 |
+
"eval_loss": 11.921051025390625,
|
746 |
+
"eval_runtime": 0.3127,
|
747 |
+
"eval_samples_per_second": 159.909,
|
748 |
+
"eval_steps_per_second": 22.387,
|
749 |
+
"step": 100
|
750 |
}
|
751 |
],
|
752 |
"logging_steps": 1,
|
|
|
775 |
"attributes": {}
|
776 |
}
|
777 |
},
|
778 |
+
"total_flos": 159262310400.0,
|
779 |
"train_batch_size": 8,
|
780 |
"trial_name": null,
|
781 |
"trial_params": null
|