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 671149168
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f3c4011f0987305230c352646a67ad265f43828ca34cbeaa598f97397e2ca6f
|
3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 341314196
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6916d1cc2ea8807663a2d3d0fabd4aeeafa5d5f46a35aa578e3038933648b66c
|
3 |
size 341314196
|
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 sha256:3277f4179992063ae69b64f3f3f72420a2b2f4f8004d93816659e01f3fd91a95
|
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 sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 50,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -373,6 +373,364 @@
|
|
373 |
"eval_samples_per_second": 8.833,
|
374 |
"eval_steps_per_second": 2.219,
|
375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
376 |
}
|
377 |
],
|
378 |
"logging_steps": 1,
|
@@ -401,7 +759,7 @@
|
|
401 |
"attributes": {}
|
402 |
}
|
403 |
},
|
404 |
-
"total_flos":
|
405 |
"train_batch_size": 8,
|
406 |
"trial_name": null,
|
407 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.004985797218978405,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.43149946062567424,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
373 |
"eval_samples_per_second": 8.833,
|
374 |
"eval_steps_per_second": 2.219,
|
375 |
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.22006472491909385,
|
379 |
+
"grad_norm": 1.976332187652588,
|
380 |
+
"learning_rate": 8.894386393810563e-05,
|
381 |
+
"loss": 0.0361,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.2243797195253506,
|
386 |
+
"grad_norm": 0.2932753264904022,
|
387 |
+
"learning_rate": 8.842005554284296e-05,
|
388 |
+
"loss": 0.0171,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.22869471413160733,
|
393 |
+
"grad_norm": 0.31595897674560547,
|
394 |
+
"learning_rate": 8.788574348801675e-05,
|
395 |
+
"loss": 0.0195,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.23300970873786409,
|
400 |
+
"grad_norm": 1.3101752996444702,
|
401 |
+
"learning_rate": 8.73410738492077e-05,
|
402 |
+
"loss": 0.0292,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.2373247033441208,
|
407 |
+
"grad_norm": 0.7268949747085571,
|
408 |
+
"learning_rate": 8.678619553365659e-05,
|
409 |
+
"loss": 0.0143,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.24163969795037757,
|
414 |
+
"grad_norm": 4.275149822235107,
|
415 |
+
"learning_rate": 8.622126023955446e-05,
|
416 |
+
"loss": 0.0417,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.2459546925566343,
|
421 |
+
"grad_norm": 0.3323039710521698,
|
422 |
+
"learning_rate": 8.564642241456986e-05,
|
423 |
+
"loss": 0.0145,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.25026968716289105,
|
428 |
+
"grad_norm": 0.3134349584579468,
|
429 |
+
"learning_rate": 8.506183921362443e-05,
|
430 |
+
"loss": 0.0159,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.2545846817691478,
|
435 |
+
"grad_norm": 1.0623679161071777,
|
436 |
+
"learning_rate": 8.44676704559283e-05,
|
437 |
+
"loss": 0.0273,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.2588996763754045,
|
442 |
+
"grad_norm": 1.1334818601608276,
|
443 |
+
"learning_rate": 8.386407858128706e-05,
|
444 |
+
"loss": 0.019,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.2632146709816613,
|
449 |
+
"grad_norm": 0.45052817463874817,
|
450 |
+
"learning_rate": 8.32512286056924e-05,
|
451 |
+
"loss": 0.0226,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.267529665587918,
|
456 |
+
"grad_norm": 0.6137033104896545,
|
457 |
+
"learning_rate": 8.262928807620843e-05,
|
458 |
+
"loss": 0.0212,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.27184466019417475,
|
463 |
+
"grad_norm": 0.7195796370506287,
|
464 |
+
"learning_rate": 8.199842702516583e-05,
|
465 |
+
"loss": 0.0213,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.2761596548004315,
|
470 |
+
"grad_norm": 0.5169023871421814,
|
471 |
+
"learning_rate": 8.135881792367686e-05,
|
472 |
+
"loss": 0.0222,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.28047464940668826,
|
477 |
+
"grad_norm": 0.36940544843673706,
|
478 |
+
"learning_rate": 8.07106356344834e-05,
|
479 |
+
"loss": 0.0206,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.284789644012945,
|
484 |
+
"grad_norm": 0.6449036598205566,
|
485 |
+
"learning_rate": 8.005405736415126e-05,
|
486 |
+
"loss": 0.0438,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.2891046386192017,
|
491 |
+
"grad_norm": 1.0550373792648315,
|
492 |
+
"learning_rate": 7.938926261462366e-05,
|
493 |
+
"loss": 0.0297,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.29341963322545844,
|
498 |
+
"grad_norm": 0.3580387830734253,
|
499 |
+
"learning_rate": 7.871643313414718e-05,
|
500 |
+
"loss": 0.0208,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.2977346278317152,
|
505 |
+
"grad_norm": 0.4854778051376343,
|
506 |
+
"learning_rate": 7.803575286758364e-05,
|
507 |
+
"loss": 0.0218,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.30204962243797195,
|
512 |
+
"grad_norm": 0.4402463436126709,
|
513 |
+
"learning_rate": 7.734740790612136e-05,
|
514 |
+
"loss": 0.0157,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.3063646170442287,
|
519 |
+
"grad_norm": 0.3080613315105438,
|
520 |
+
"learning_rate": 7.66515864363997e-05,
|
521 |
+
"loss": 0.015,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.3106796116504854,
|
526 |
+
"grad_norm": 0.3834276497364044,
|
527 |
+
"learning_rate": 7.594847868906076e-05,
|
528 |
+
"loss": 0.0122,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.3149946062567422,
|
533 |
+
"grad_norm": 0.9351459741592407,
|
534 |
+
"learning_rate": 7.52382768867422e-05,
|
535 |
+
"loss": 0.0232,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.3193096008629989,
|
540 |
+
"grad_norm": 0.8108393549919128,
|
541 |
+
"learning_rate": 7.452117519152542e-05,
|
542 |
+
"loss": 0.0276,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.32362459546925565,
|
547 |
+
"grad_norm": 0.43026992678642273,
|
548 |
+
"learning_rate": 7.379736965185368e-05,
|
549 |
+
"loss": 0.0136,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.32793959007551243,
|
554 |
+
"grad_norm": 0.4602266550064087,
|
555 |
+
"learning_rate": 7.30670581489344e-05,
|
556 |
+
"loss": 0.0175,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.33225458468176916,
|
561 |
+
"grad_norm": 11.124612808227539,
|
562 |
+
"learning_rate": 7.233044034264034e-05,
|
563 |
+
"loss": 0.0284,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.3365695792880259,
|
568 |
+
"grad_norm": 6.074794769287109,
|
569 |
+
"learning_rate": 7.158771761692464e-05,
|
570 |
+
"loss": 0.028,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.3408845738942826,
|
575 |
+
"grad_norm": 1.4700261354446411,
|
576 |
+
"learning_rate": 7.083909302476453e-05,
|
577 |
+
"loss": 0.0224,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.3451995685005394,
|
582 |
+
"grad_norm": 17.13897132873535,
|
583 |
+
"learning_rate": 7.008477123264848e-05,
|
584 |
+
"loss": 0.0538,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.34951456310679613,
|
589 |
+
"grad_norm": 0.4576086103916168,
|
590 |
+
"learning_rate": 6.932495846462261e-05,
|
591 |
+
"loss": 0.021,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.35382955771305286,
|
596 |
+
"grad_norm": 0.3490538001060486,
|
597 |
+
"learning_rate": 6.855986244591104e-05,
|
598 |
+
"loss": 0.0213,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.3581445523193096,
|
603 |
+
"grad_norm": 7.836808204650879,
|
604 |
+
"learning_rate": 6.778969234612584e-05,
|
605 |
+
"loss": 0.0245,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.36245954692556637,
|
610 |
+
"grad_norm": 16.858186721801758,
|
611 |
+
"learning_rate": 6.701465872208216e-05,
|
612 |
+
"loss": 0.2472,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.3667745415318231,
|
617 |
+
"grad_norm": 13.203956604003906,
|
618 |
+
"learning_rate": 6.623497346023418e-05,
|
619 |
+
"loss": 0.0769,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.3710895361380798,
|
624 |
+
"grad_norm": 8.34621810913086,
|
625 |
+
"learning_rate": 6.545084971874738e-05,
|
626 |
+
"loss": 0.057,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.37540453074433655,
|
631 |
+
"grad_norm": 0.9256253242492676,
|
632 |
+
"learning_rate": 6.466250186922325e-05,
|
633 |
+
"loss": 0.0226,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.37971952535059333,
|
638 |
+
"grad_norm": 0.4759206473827362,
|
639 |
+
"learning_rate": 6.387014543809223e-05,
|
640 |
+
"loss": 0.0165,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.38403451995685006,
|
645 |
+
"grad_norm": 0.8075918555259705,
|
646 |
+
"learning_rate": 6.307399704769099e-05,
|
647 |
+
"loss": 0.0152,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.3883495145631068,
|
652 |
+
"grad_norm": 0.435330867767334,
|
653 |
+
"learning_rate": 6.227427435703997e-05,
|
654 |
+
"loss": 0.0122,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.3926645091693635,
|
659 |
+
"grad_norm": 0.4027554988861084,
|
660 |
+
"learning_rate": 6.147119600233758e-05,
|
661 |
+
"loss": 0.0163,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.3969795037756203,
|
666 |
+
"grad_norm": 0.7867634296417236,
|
667 |
+
"learning_rate": 6.066498153718735e-05,
|
668 |
+
"loss": 0.0268,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.40129449838187703,
|
673 |
+
"grad_norm": 0.49145984649658203,
|
674 |
+
"learning_rate": 5.985585137257401e-05,
|
675 |
+
"loss": 0.0255,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.40560949298813376,
|
680 |
+
"grad_norm": 0.4385581612586975,
|
681 |
+
"learning_rate": 5.90440267166055e-05,
|
682 |
+
"loss": 0.0172,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.4099244875943905,
|
687 |
+
"grad_norm": 0.42079663276672363,
|
688 |
+
"learning_rate": 5.8229729514036705e-05,
|
689 |
+
"loss": 0.0172,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.41423948220064727,
|
694 |
+
"grad_norm": 0.37281689047813416,
|
695 |
+
"learning_rate": 5.74131823855921e-05,
|
696 |
+
"loss": 0.0163,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.418554476806904,
|
701 |
+
"grad_norm": 0.5622067451477051,
|
702 |
+
"learning_rate": 5.6594608567103456e-05,
|
703 |
+
"loss": 0.0149,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.4228694714131607,
|
708 |
+
"grad_norm": 0.7449488639831543,
|
709 |
+
"learning_rate": 5.577423184847932e-05,
|
710 |
+
"loss": 0.015,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.42718446601941745,
|
715 |
+
"grad_norm": 0.26745229959487915,
|
716 |
+
"learning_rate": 5.495227651252315e-05,
|
717 |
+
"loss": 0.0088,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.43149946062567424,
|
722 |
+
"grad_norm": 0.23704928159713745,
|
723 |
+
"learning_rate": 5.4128967273616625e-05,
|
724 |
+
"loss": 0.0098,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.43149946062567424,
|
729 |
+
"eval_loss": 0.004985797218978405,
|
730 |
+
"eval_runtime": 44.1566,
|
731 |
+
"eval_samples_per_second": 8.832,
|
732 |
+
"eval_steps_per_second": 2.219,
|
733 |
+
"step": 100
|
734 |
}
|
735 |
],
|
736 |
"logging_steps": 1,
|
|
|
759 |
"attributes": {}
|
760 |
}
|
761 |
},
|
762 |
+
"total_flos": 1.5669428198414746e+17,
|
763 |
"train_batch_size": 8,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|