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 216151256
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08444859cc6aabcdab2170f1dca404853335b0df6aaff8db1c0e4ff32d4743d4
|
3 |
size 216151256
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 110412612
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4df4b1a5025c7cef65da468c76f116bbeff1a8d73dbd59d1e5cd323a8b6aa42
|
3 |
size 110412612
|
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 sha256:43b6dc63b5d230acc41c1b09ff6e1e1178849f2514a59abb1639f1f060b8588f
|
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":
|
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": 4.245,
|
382 |
"eval_steps_per_second": 4.245,
|
383 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
384 |
}
|
385 |
],
|
386 |
"logging_steps": 1,
|
@@ -409,7 +775,7 @@
|
|
409 |
"attributes": {}
|
410 |
}
|
411 |
},
|
412 |
-
"total_flos":
|
413 |
"train_batch_size": 1,
|
414 |
"trial_name": null,
|
415 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.1003895029425621,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.734113328745125,
|
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": 4.245,
|
382 |
"eval_steps_per_second": 4.245,
|
383 |
"step": 50
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.37439779766001374,
|
387 |
+
"grad_norm": 1.1293262243270874,
|
388 |
+
"learning_rate": 0.0002668315918143169,
|
389 |
+
"loss": 1.1617,
|
390 |
+
"step": 51
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.381738930947465,
|
394 |
+
"grad_norm": 1.1484521627426147,
|
395 |
+
"learning_rate": 0.00026526016662852886,
|
396 |
+
"loss": 1.2379,
|
397 |
+
"step": 52
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 0.38908006423491626,
|
401 |
+
"grad_norm": 1.064557671546936,
|
402 |
+
"learning_rate": 0.00026365723046405023,
|
403 |
+
"loss": 1.1066,
|
404 |
+
"step": 53
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.39642119752236754,
|
408 |
+
"grad_norm": 0.9905532002449036,
|
409 |
+
"learning_rate": 0.0002620232215476231,
|
410 |
+
"loss": 1.1669,
|
411 |
+
"step": 54
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.40376233080981877,
|
415 |
+
"grad_norm": 1.251165509223938,
|
416 |
+
"learning_rate": 0.0002603585866009697,
|
417 |
+
"loss": 1.0054,
|
418 |
+
"step": 55
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 0.41110346409727,
|
422 |
+
"grad_norm": 1.0376931428909302,
|
423 |
+
"learning_rate": 0.00025866378071866334,
|
424 |
+
"loss": 1.0141,
|
425 |
+
"step": 56
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.4184445973847213,
|
429 |
+
"grad_norm": 1.1509113311767578,
|
430 |
+
"learning_rate": 0.00025693926724370956,
|
431 |
+
"loss": 0.8967,
|
432 |
+
"step": 57
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 0.4257857306721725,
|
436 |
+
"grad_norm": 1.2194794416427612,
|
437 |
+
"learning_rate": 0.00025518551764087326,
|
438 |
+
"loss": 1.0544,
|
439 |
+
"step": 58
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 0.43312686395962374,
|
443 |
+
"grad_norm": 0.999973475933075,
|
444 |
+
"learning_rate": 0.00025340301136778483,
|
445 |
+
"loss": 0.8905,
|
446 |
+
"step": 59
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.440467997247075,
|
450 |
+
"grad_norm": 1.0643336772918701,
|
451 |
+
"learning_rate": 0.00025159223574386114,
|
452 |
+
"loss": 1.0378,
|
453 |
+
"step": 60
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.44780913053452626,
|
457 |
+
"grad_norm": 1.0134408473968506,
|
458 |
+
"learning_rate": 0.0002497536858170772,
|
459 |
+
"loss": 0.8218,
|
460 |
+
"step": 61
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 0.45515026382197754,
|
464 |
+
"grad_norm": 1.4050616025924683,
|
465 |
+
"learning_rate": 0.00024788786422862526,
|
466 |
+
"loss": 0.8544,
|
467 |
+
"step": 62
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.46249139710942877,
|
471 |
+
"grad_norm": 1.4386414289474487,
|
472 |
+
"learning_rate": 0.00024599528107549745,
|
473 |
+
"loss": 0.8324,
|
474 |
+
"step": 63
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.46983253039688,
|
478 |
+
"grad_norm": 1.1594165563583374,
|
479 |
+
"learning_rate": 0.00024407645377103054,
|
480 |
+
"loss": 0.7453,
|
481 |
+
"step": 64
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.4771736636843313,
|
485 |
+
"grad_norm": 1.2135729789733887,
|
486 |
+
"learning_rate": 0.00024213190690345018,
|
487 |
+
"loss": 0.8184,
|
488 |
+
"step": 65
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.4845147969717825,
|
492 |
+
"grad_norm": 0.9763234257698059,
|
493 |
+
"learning_rate": 0.00024016217209245374,
|
494 |
+
"loss": 0.596,
|
495 |
+
"step": 66
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.49185593025923374,
|
499 |
+
"grad_norm": 1.1825246810913086,
|
500 |
+
"learning_rate": 0.00023816778784387094,
|
501 |
+
"loss": 0.6871,
|
502 |
+
"step": 67
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 0.499197063546685,
|
506 |
+
"grad_norm": 1.0060195922851562,
|
507 |
+
"learning_rate": 0.0002361492994024415,
|
508 |
+
"loss": 0.658,
|
509 |
+
"step": 68
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 0.5065381968341363,
|
513 |
+
"grad_norm": 1.87339186668396,
|
514 |
+
"learning_rate": 0.0002341072586027509,
|
515 |
+
"loss": 0.7342,
|
516 |
+
"step": 69
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 0.5138793301215875,
|
520 |
+
"grad_norm": 1.2143769264221191,
|
521 |
+
"learning_rate": 0.00023204222371836405,
|
522 |
+
"loss": 0.6153,
|
523 |
+
"step": 70
|
524 |
+
},
|
525 |
+
{
|
526 |
+
"epoch": 0.5212204634090388,
|
527 |
+
"grad_norm": 1.0467982292175293,
|
528 |
+
"learning_rate": 0.00022995475930919905,
|
529 |
+
"loss": 0.5277,
|
530 |
+
"step": 71
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.52856159669649,
|
534 |
+
"grad_norm": 1.0355846881866455,
|
535 |
+
"learning_rate": 0.00022784543606718227,
|
536 |
+
"loss": 0.5707,
|
537 |
+
"step": 72
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.5359027299839413,
|
541 |
+
"grad_norm": 0.8927159905433655,
|
542 |
+
"learning_rate": 0.00022571483066022657,
|
543 |
+
"loss": 0.3879,
|
544 |
+
"step": 73
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 0.5432438632713925,
|
548 |
+
"grad_norm": 1.427565097808838,
|
549 |
+
"learning_rate": 0.0002235635255745762,
|
550 |
+
"loss": 0.6126,
|
551 |
+
"step": 74
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.5505849965588437,
|
555 |
+
"grad_norm": 1.1537415981292725,
|
556 |
+
"learning_rate": 0.00022139210895556104,
|
557 |
+
"loss": 0.5787,
|
558 |
+
"step": 75
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 0.5505849965588437,
|
562 |
+
"eval_loss": 0.3803807497024536,
|
563 |
+
"eval_runtime": 11.7561,
|
564 |
+
"eval_samples_per_second": 4.253,
|
565 |
+
"eval_steps_per_second": 4.253,
|
566 |
+
"step": 75
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.557926129846295,
|
570 |
+
"grad_norm": 0.9431911706924438,
|
571 |
+
"learning_rate": 0.00021920117444680317,
|
572 |
+
"loss": 0.3773,
|
573 |
+
"step": 76
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.5652672631337463,
|
577 |
+
"grad_norm": 0.9953020215034485,
|
578 |
+
"learning_rate": 0.00021699132102792097,
|
579 |
+
"loss": 0.3676,
|
580 |
+
"step": 77
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 0.5726083964211975,
|
584 |
+
"grad_norm": 0.98787921667099,
|
585 |
+
"learning_rate": 0.0002147631528507739,
|
586 |
+
"loss": 0.3079,
|
587 |
+
"step": 78
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.5799495297086488,
|
591 |
+
"grad_norm": 1.191606879234314,
|
592 |
+
"learning_rate": 0.00021251727907429355,
|
593 |
+
"loss": 0.3129,
|
594 |
+
"step": 79
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.5872906629961,
|
598 |
+
"grad_norm": 1.0935895442962646,
|
599 |
+
"learning_rate": 0.0002102543136979454,
|
600 |
+
"loss": 0.3122,
|
601 |
+
"step": 80
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 0.5946317962835512,
|
605 |
+
"grad_norm": 1.4533487558364868,
|
606 |
+
"learning_rate": 0.0002079748753938678,
|
607 |
+
"loss": 0.5123,
|
608 |
+
"step": 81
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.6019729295710026,
|
612 |
+
"grad_norm": 1.176979422569275,
|
613 |
+
"learning_rate": 0.0002056795873377331,
|
614 |
+
"loss": 0.3833,
|
615 |
+
"step": 82
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.6093140628584538,
|
619 |
+
"grad_norm": 1.027469277381897,
|
620 |
+
"learning_rate": 0.00020336907703837748,
|
621 |
+
"loss": 0.2685,
|
622 |
+
"step": 83
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 0.616655196145905,
|
626 |
+
"grad_norm": 0.9938647747039795,
|
627 |
+
"learning_rate": 0.00020104397616624645,
|
628 |
+
"loss": 0.2836,
|
629 |
+
"step": 84
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 0.6239963294333563,
|
633 |
+
"grad_norm": 0.8680717349052429,
|
634 |
+
"learning_rate": 0.00019870492038070252,
|
635 |
+
"loss": 0.2036,
|
636 |
+
"step": 85
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 0.6313374627208075,
|
640 |
+
"grad_norm": 1.1820261478424072,
|
641 |
+
"learning_rate": 0.0001963525491562421,
|
642 |
+
"loss": 0.3018,
|
643 |
+
"step": 86
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 0.6386785960082588,
|
647 |
+
"grad_norm": 0.9207668900489807,
|
648 |
+
"learning_rate": 0.0001939875056076697,
|
649 |
+
"loss": 0.1357,
|
650 |
+
"step": 87
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.64601972929571,
|
654 |
+
"grad_norm": 0.6974514126777649,
|
655 |
+
"learning_rate": 0.00019161043631427666,
|
656 |
+
"loss": 0.1046,
|
657 |
+
"step": 88
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.6533608625831613,
|
661 |
+
"grad_norm": 1.2946507930755615,
|
662 |
+
"learning_rate": 0.00018922199114307294,
|
663 |
+
"loss": 0.2132,
|
664 |
+
"step": 89
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 0.6607019958706125,
|
668 |
+
"grad_norm": 0.9494311213493347,
|
669 |
+
"learning_rate": 0.00018682282307111987,
|
670 |
+
"loss": 0.1881,
|
671 |
+
"step": 90
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 0.6680431291580637,
|
675 |
+
"grad_norm": 0.921244204044342,
|
676 |
+
"learning_rate": 0.00018441358800701273,
|
677 |
+
"loss": 0.26,
|
678 |
+
"step": 91
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 0.675384262445515,
|
682 |
+
"grad_norm": 0.8400191068649292,
|
683 |
+
"learning_rate": 0.00018199494461156203,
|
684 |
+
"loss": 0.153,
|
685 |
+
"step": 92
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.6827253957329663,
|
689 |
+
"grad_norm": 0.7949177622795105,
|
690 |
+
"learning_rate": 0.000179567554117722,
|
691 |
+
"loss": 0.1471,
|
692 |
+
"step": 93
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.6900665290204175,
|
696 |
+
"grad_norm": 0.9048661589622498,
|
697 |
+
"learning_rate": 0.00017713208014981648,
|
698 |
+
"loss": 0.126,
|
699 |
+
"step": 94
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.6974076623078688,
|
703 |
+
"grad_norm": 0.8785199522972107,
|
704 |
+
"learning_rate": 0.00017468918854211007,
|
705 |
+
"loss": 0.1536,
|
706 |
+
"step": 95
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 0.70474879559532,
|
710 |
+
"grad_norm": 0.6925604939460754,
|
711 |
+
"learning_rate": 0.00017223954715677627,
|
712 |
+
"loss": 0.1041,
|
713 |
+
"step": 96
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 0.7120899288827712,
|
717 |
+
"grad_norm": 0.7400240898132324,
|
718 |
+
"learning_rate": 0.00016978382570131034,
|
719 |
+
"loss": 0.0924,
|
720 |
+
"step": 97
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 0.7194310621702226,
|
724 |
+
"grad_norm": 0.6650524139404297,
|
725 |
+
"learning_rate": 0.00016732269554543794,
|
726 |
+
"loss": 0.0788,
|
727 |
+
"step": 98
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 0.7267721954576738,
|
731 |
+
"grad_norm": 0.5950520038604736,
|
732 |
+
"learning_rate": 0.00016485682953756942,
|
733 |
+
"loss": 0.066,
|
734 |
+
"step": 99
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.734113328745125,
|
738 |
+
"grad_norm": 0.6176964640617371,
|
739 |
+
"learning_rate": 0.00016238690182084986,
|
740 |
+
"loss": 0.0628,
|
741 |
+
"step": 100
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.734113328745125,
|
745 |
+
"eval_loss": 0.1003895029425621,
|
746 |
+
"eval_runtime": 11.7465,
|
747 |
+
"eval_samples_per_second": 4.257,
|
748 |
+
"eval_steps_per_second": 4.257,
|
749 |
+
"step": 100
|
750 |
}
|
751 |
],
|
752 |
"logging_steps": 1,
|
|
|
775 |
"attributes": {}
|
776 |
}
|
777 |
},
|
778 |
+
"total_flos": 1.75127051221205e+17,
|
779 |
"train_batch_size": 1,
|
780 |
"trial_name": null,
|
781 |
"trial_params": null
|