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 478211024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56c6bf8c7c5ae516931386d3855704d96843a49e5e62de680ed94b30d3398bb4
|
3 |
size 478211024
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 956679634
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:875eef51819bf03f1a1a252f3d10facdf21cdc96229b31b3790107466f06c35f
|
3 |
size 956679634
|
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 sha256:333fb34de7627d3f9e97a4a74f0cc7987acea26fb643cbc10a4a40a965099bd3
|
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 sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
|
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": 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": 17.987,
|
374 |
"eval_steps_per_second": 9.029,
|
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": 1.0880825519561768,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.6611570247933884,
|
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": 17.987,
|
374 |
"eval_steps_per_second": 9.029,
|
375 |
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.3371900826446281,
|
379 |
+
"grad_norm": 0.9313036203384399,
|
380 |
+
"learning_rate": 9.285836503510562e-05,
|
381 |
+
"loss": 4.8954,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.343801652892562,
|
386 |
+
"grad_norm": 0.8967971205711365,
|
387 |
+
"learning_rate": 9.24024048078213e-05,
|
388 |
+
"loss": 4.2944,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.3504132231404959,
|
393 |
+
"grad_norm": 0.9805819392204285,
|
394 |
+
"learning_rate": 9.193352839727121e-05,
|
395 |
+
"loss": 5.1855,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.35702479338842974,
|
400 |
+
"grad_norm": 1.110192060470581,
|
401 |
+
"learning_rate": 9.145187862775209e-05,
|
402 |
+
"loss": 5.0659,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.36363636363636365,
|
407 |
+
"grad_norm": 1.0864770412445068,
|
408 |
+
"learning_rate": 9.09576022144496e-05,
|
409 |
+
"loss": 4.6465,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.3702479338842975,
|
414 |
+
"grad_norm": 1.6741044521331787,
|
415 |
+
"learning_rate": 9.045084971874738e-05,
|
416 |
+
"loss": 4.5788,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.3768595041322314,
|
421 |
+
"grad_norm": 1.2498528957366943,
|
422 |
+
"learning_rate": 8.993177550236464e-05,
|
423 |
+
"loss": 4.8934,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.3834710743801653,
|
428 |
+
"grad_norm": 1.2537343502044678,
|
429 |
+
"learning_rate": 8.940053768033609e-05,
|
430 |
+
"loss": 4.7502,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.39008264462809916,
|
435 |
+
"grad_norm": 1.2770891189575195,
|
436 |
+
"learning_rate": 8.885729807284856e-05,
|
437 |
+
"loss": 4.8936,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.39669421487603307,
|
442 |
+
"grad_norm": 1.4430948495864868,
|
443 |
+
"learning_rate": 8.83022221559489e-05,
|
444 |
+
"loss": 4.8503,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.4033057851239669,
|
449 |
+
"grad_norm": 1.5071772336959839,
|
450 |
+
"learning_rate": 8.773547901113862e-05,
|
451 |
+
"loss": 5.3403,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.4099173553719008,
|
456 |
+
"grad_norm": 1.624732494354248,
|
457 |
+
"learning_rate": 8.715724127386972e-05,
|
458 |
+
"loss": 5.3317,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.41652892561983473,
|
463 |
+
"grad_norm": 1.6274948120117188,
|
464 |
+
"learning_rate": 8.656768508095853e-05,
|
465 |
+
"loss": 4.4587,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.4231404958677686,
|
470 |
+
"grad_norm": 1.6330101490020752,
|
471 |
+
"learning_rate": 8.596699001693255e-05,
|
472 |
+
"loss": 4.1029,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.4297520661157025,
|
477 |
+
"grad_norm": 1.6284996271133423,
|
478 |
+
"learning_rate": 8.535533905932738e-05,
|
479 |
+
"loss": 5.1398,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.43636363636363634,
|
484 |
+
"grad_norm": 1.741026520729065,
|
485 |
+
"learning_rate": 8.473291852294987e-05,
|
486 |
+
"loss": 5.2479,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.44297520661157025,
|
491 |
+
"grad_norm": 1.8886727094650269,
|
492 |
+
"learning_rate": 8.409991800312493e-05,
|
493 |
+
"loss": 5.6305,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.44958677685950416,
|
498 |
+
"grad_norm": 1.9955488443374634,
|
499 |
+
"learning_rate": 8.345653031794292e-05,
|
500 |
+
"loss": 5.6926,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.456198347107438,
|
505 |
+
"grad_norm": 2.239786386489868,
|
506 |
+
"learning_rate": 8.280295144952536e-05,
|
507 |
+
"loss": 5.9947,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.4628099173553719,
|
512 |
+
"grad_norm": 2.239755630493164,
|
513 |
+
"learning_rate": 8.213938048432697e-05,
|
514 |
+
"loss": 4.4617,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.46942148760330576,
|
519 |
+
"grad_norm": 2.663750648498535,
|
520 |
+
"learning_rate": 8.146601955249188e-05,
|
521 |
+
"loss": 4.2143,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.47603305785123967,
|
526 |
+
"grad_norm": 2.472973108291626,
|
527 |
+
"learning_rate": 8.07830737662829e-05,
|
528 |
+
"loss": 4.8717,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.4826446280991736,
|
533 |
+
"grad_norm": 3.02223801612854,
|
534 |
+
"learning_rate": 8.009075115760243e-05,
|
535 |
+
"loss": 5.2497,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.48925619834710743,
|
540 |
+
"grad_norm": 4.158394813537598,
|
541 |
+
"learning_rate": 7.938926261462366e-05,
|
542 |
+
"loss": 4.8917,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.49586776859504134,
|
547 |
+
"grad_norm": 1.0667253732681274,
|
548 |
+
"learning_rate": 7.86788218175523e-05,
|
549 |
+
"loss": 3.4973,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.5024793388429752,
|
554 |
+
"grad_norm": 1.0640274286270142,
|
555 |
+
"learning_rate": 7.795964517353735e-05,
|
556 |
+
"loss": 3.6,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.509090909090909,
|
561 |
+
"grad_norm": 0.8343002200126648,
|
562 |
+
"learning_rate": 7.723195175075136e-05,
|
563 |
+
"loss": 3.9431,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.515702479338843,
|
568 |
+
"grad_norm": 0.8102278709411621,
|
569 |
+
"learning_rate": 7.649596321166024e-05,
|
570 |
+
"loss": 4.2592,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.5223140495867769,
|
575 |
+
"grad_norm": 0.7733540534973145,
|
576 |
+
"learning_rate": 7.575190374550272e-05,
|
577 |
+
"loss": 4.4856,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.5289256198347108,
|
582 |
+
"grad_norm": 0.6886125802993774,
|
583 |
+
"learning_rate": 7.500000000000001e-05,
|
584 |
+
"loss": 4.4077,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.5355371900826447,
|
589 |
+
"grad_norm": 0.7023859620094299,
|
590 |
+
"learning_rate": 7.424048101231686e-05,
|
591 |
+
"loss": 4.4471,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.5421487603305785,
|
596 |
+
"grad_norm": 0.733121931552887,
|
597 |
+
"learning_rate": 7.347357813929454e-05,
|
598 |
+
"loss": 4.2295,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.5487603305785124,
|
603 |
+
"grad_norm": 1.4499454498291016,
|
604 |
+
"learning_rate": 7.269952498697734e-05,
|
605 |
+
"loss": 4.4026,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.5553719008264463,
|
610 |
+
"grad_norm": 0.795872151851654,
|
611 |
+
"learning_rate": 7.191855733945387e-05,
|
612 |
+
"loss": 4.5716,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.5619834710743802,
|
617 |
+
"grad_norm": 0.8914481997489929,
|
618 |
+
"learning_rate": 7.113091308703498e-05,
|
619 |
+
"loss": 4.6541,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.5685950413223141,
|
624 |
+
"grad_norm": 0.9090842008590698,
|
625 |
+
"learning_rate": 7.033683215379002e-05,
|
626 |
+
"loss": 4.3894,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.5752066115702479,
|
631 |
+
"grad_norm": 0.9541610479354858,
|
632 |
+
"learning_rate": 6.953655642446368e-05,
|
633 |
+
"loss": 4.1603,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.5818181818181818,
|
638 |
+
"grad_norm": 1.0280675888061523,
|
639 |
+
"learning_rate": 6.873032967079561e-05,
|
640 |
+
"loss": 4.4232,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.5884297520661157,
|
645 |
+
"grad_norm": 1.1509857177734375,
|
646 |
+
"learning_rate": 6.7918397477265e-05,
|
647 |
+
"loss": 4.442,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.5950413223140496,
|
652 |
+
"grad_norm": 1.0895159244537354,
|
653 |
+
"learning_rate": 6.710100716628344e-05,
|
654 |
+
"loss": 4.802,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.6016528925619835,
|
659 |
+
"grad_norm": 1.1312400102615356,
|
660 |
+
"learning_rate": 6.627840772285784e-05,
|
661 |
+
"loss": 4.6077,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.6082644628099173,
|
666 |
+
"grad_norm": 1.2083485126495361,
|
667 |
+
"learning_rate": 6.545084971874738e-05,
|
668 |
+
"loss": 4.686,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.6148760330578512,
|
673 |
+
"grad_norm": 1.1744060516357422,
|
674 |
+
"learning_rate": 6.461858523613684e-05,
|
675 |
+
"loss": 4.7755,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.6214876033057851,
|
680 |
+
"grad_norm": 1.1983288526535034,
|
681 |
+
"learning_rate": 6.378186779084995e-05,
|
682 |
+
"loss": 4.5161,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.628099173553719,
|
687 |
+
"grad_norm": 1.2709901332855225,
|
688 |
+
"learning_rate": 6.294095225512603e-05,
|
689 |
+
"loss": 4.6903,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.6347107438016529,
|
694 |
+
"grad_norm": 1.2853686809539795,
|
695 |
+
"learning_rate": 6.209609477998338e-05,
|
696 |
+
"loss": 4.8628,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.6413223140495867,
|
701 |
+
"grad_norm": 1.4955391883850098,
|
702 |
+
"learning_rate": 6.124755271719325e-05,
|
703 |
+
"loss": 5.4237,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.6479338842975206,
|
708 |
+
"grad_norm": 1.4081076383590698,
|
709 |
+
"learning_rate": 6.0395584540887963e-05,
|
710 |
+
"loss": 5.2527,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.6545454545454545,
|
715 |
+
"grad_norm": 1.5048182010650635,
|
716 |
+
"learning_rate": 5.9540449768827246e-05,
|
717 |
+
"loss": 4.8745,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.6611570247933884,
|
722 |
+
"grad_norm": 1.615033507347107,
|
723 |
+
"learning_rate": 5.868240888334653e-05,
|
724 |
+
"loss": 4.8292,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.6611570247933884,
|
729 |
+
"eval_loss": 1.0880825519561768,
|
730 |
+
"eval_runtime": 14.1578,
|
731 |
+
"eval_samples_per_second": 18.011,
|
732 |
+
"eval_steps_per_second": 9.041,
|
733 |
+
"step": 100
|
734 |
}
|
735 |
],
|
736 |
"logging_steps": 1,
|
|
|
759 |
"attributes": {}
|
760 |
}
|
761 |
},
|
762 |
+
"total_flos": 8.101566995654246e+16,
|
763 |
"train_batch_size": 8,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|