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 sha256:76c654ad27de6088d16ec1bd4ea3cc4519cb635a2b7ef006586c122050ffcf11
|
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 1342555602
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc6ae9cde05c62da705e9b95de3b9ea52cb9d23f7013f203239c9554fb46f0cd
|
3 |
size 1342555602
|
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 sha256:702c45c0237a22bb5ce4069004750502f3877aa025892f667028bf6137107874
|
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": 6.
|
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": 11.298,
|
374 |
"eval_steps_per_second": 5.649,
|
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": 6.02884578704834,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.04357298474945534,
|
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": 11.298,
|
374 |
"eval_steps_per_second": 5.649,
|
375 |
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.022222222222222223,
|
379 |
+
"grad_norm": 35.10013961791992,
|
380 |
+
"learning_rate": 9.285836503510562e-05,
|
381 |
+
"loss": 5.0736,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.022657952069716776,
|
386 |
+
"grad_norm": 9.756641387939453,
|
387 |
+
"learning_rate": 9.24024048078213e-05,
|
388 |
+
"loss": 5.1805,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.02309368191721133,
|
393 |
+
"grad_norm": 5.467214584350586,
|
394 |
+
"learning_rate": 9.193352839727121e-05,
|
395 |
+
"loss": 4.7327,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.023529411764705882,
|
400 |
+
"grad_norm": 5.6564483642578125,
|
401 |
+
"learning_rate": 9.145187862775209e-05,
|
402 |
+
"loss": 4.4293,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.023965141612200435,
|
407 |
+
"grad_norm": 3.8603763580322266,
|
408 |
+
"learning_rate": 9.09576022144496e-05,
|
409 |
+
"loss": 4.2583,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.024400871459694988,
|
414 |
+
"grad_norm": 3.4143786430358887,
|
415 |
+
"learning_rate": 9.045084971874738e-05,
|
416 |
+
"loss": 4.0873,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.02483660130718954,
|
421 |
+
"grad_norm": 3.591214179992676,
|
422 |
+
"learning_rate": 8.993177550236464e-05,
|
423 |
+
"loss": 4.1065,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.025272331154684097,
|
428 |
+
"grad_norm": 3.990115165710449,
|
429 |
+
"learning_rate": 8.940053768033609e-05,
|
430 |
+
"loss": 3.9787,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.02570806100217865,
|
435 |
+
"grad_norm": 3.732379674911499,
|
436 |
+
"learning_rate": 8.885729807284856e-05,
|
437 |
+
"loss": 3.9912,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.026143790849673203,
|
442 |
+
"grad_norm": 4.2087016105651855,
|
443 |
+
"learning_rate": 8.83022221559489e-05,
|
444 |
+
"loss": 3.9105,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.026579520697167756,
|
449 |
+
"grad_norm": 3.774808645248413,
|
450 |
+
"learning_rate": 8.773547901113862e-05,
|
451 |
+
"loss": 3.7629,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.02701525054466231,
|
456 |
+
"grad_norm": 3.8952903747558594,
|
457 |
+
"learning_rate": 8.715724127386972e-05,
|
458 |
+
"loss": 3.9626,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.027450980392156862,
|
463 |
+
"grad_norm": 4.1821160316467285,
|
464 |
+
"learning_rate": 8.656768508095853e-05,
|
465 |
+
"loss": 3.7911,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.027886710239651415,
|
470 |
+
"grad_norm": 4.013959884643555,
|
471 |
+
"learning_rate": 8.596699001693255e-05,
|
472 |
+
"loss": 4.0033,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.02832244008714597,
|
477 |
+
"grad_norm": 4.394720554351807,
|
478 |
+
"learning_rate": 8.535533905932738e-05,
|
479 |
+
"loss": 3.7035,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.02875816993464052,
|
484 |
+
"grad_norm": 4.393320083618164,
|
485 |
+
"learning_rate": 8.473291852294987e-05,
|
486 |
+
"loss": 3.6583,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.029193899782135078,
|
491 |
+
"grad_norm": 5.116196632385254,
|
492 |
+
"learning_rate": 8.409991800312493e-05,
|
493 |
+
"loss": 3.4642,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.02962962962962963,
|
498 |
+
"grad_norm": 5.922344207763672,
|
499 |
+
"learning_rate": 8.345653031794292e-05,
|
500 |
+
"loss": 2.4069,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.030065359477124184,
|
505 |
+
"grad_norm": 5.2199482917785645,
|
506 |
+
"learning_rate": 8.280295144952536e-05,
|
507 |
+
"loss": 2.8334,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.030501089324618737,
|
512 |
+
"grad_norm": 5.466800212860107,
|
513 |
+
"learning_rate": 8.213938048432697e-05,
|
514 |
+
"loss": 2.7829,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.03093681917211329,
|
519 |
+
"grad_norm": 5.415471076965332,
|
520 |
+
"learning_rate": 8.146601955249188e-05,
|
521 |
+
"loss": 2.926,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.03137254901960784,
|
526 |
+
"grad_norm": 5.683098316192627,
|
527 |
+
"learning_rate": 8.07830737662829e-05,
|
528 |
+
"loss": 3.3565,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.0318082788671024,
|
533 |
+
"grad_norm": 7.391642093658447,
|
534 |
+
"learning_rate": 8.009075115760243e-05,
|
535 |
+
"loss": 4.1612,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.03224400871459695,
|
540 |
+
"grad_norm": 7.878474712371826,
|
541 |
+
"learning_rate": 7.938926261462366e-05,
|
542 |
+
"loss": 4.0754,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.032679738562091505,
|
547 |
+
"grad_norm": 7.959073066711426,
|
548 |
+
"learning_rate": 7.86788218175523e-05,
|
549 |
+
"loss": 3.7957,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.033115468409586055,
|
554 |
+
"grad_norm": 9.686983108520508,
|
555 |
+
"learning_rate": 7.795964517353735e-05,
|
556 |
+
"loss": 3.7651,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.03355119825708061,
|
561 |
+
"grad_norm": 8.671168327331543,
|
562 |
+
"learning_rate": 7.723195175075136e-05,
|
563 |
+
"loss": 3.4634,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.03398692810457516,
|
568 |
+
"grad_norm": 7.247128486633301,
|
569 |
+
"learning_rate": 7.649596321166024e-05,
|
570 |
+
"loss": 3.139,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.03442265795206972,
|
575 |
+
"grad_norm": 8.371869087219238,
|
576 |
+
"learning_rate": 7.575190374550272e-05,
|
577 |
+
"loss": 3.1679,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.034858387799564274,
|
582 |
+
"grad_norm": 7.804739952087402,
|
583 |
+
"learning_rate": 7.500000000000001e-05,
|
584 |
+
"loss": 3.082,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.03529411764705882,
|
589 |
+
"grad_norm": 7.40488862991333,
|
590 |
+
"learning_rate": 7.424048101231686e-05,
|
591 |
+
"loss": 3.0061,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.03572984749455338,
|
596 |
+
"grad_norm": 9.724720001220703,
|
597 |
+
"learning_rate": 7.347357813929454e-05,
|
598 |
+
"loss": 3.3592,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.03616557734204793,
|
603 |
+
"grad_norm": 8.739630699157715,
|
604 |
+
"learning_rate": 7.269952498697734e-05,
|
605 |
+
"loss": 3.1958,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.036601307189542485,
|
610 |
+
"grad_norm": 13.883004188537598,
|
611 |
+
"learning_rate": 7.191855733945387e-05,
|
612 |
+
"loss": 3.6667,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.037037037037037035,
|
617 |
+
"grad_norm": 8.60599136352539,
|
618 |
+
"learning_rate": 7.113091308703498e-05,
|
619 |
+
"loss": 2.9883,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.03747276688453159,
|
624 |
+
"grad_norm": 9.525105476379395,
|
625 |
+
"learning_rate": 7.033683215379002e-05,
|
626 |
+
"loss": 3.3996,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.03790849673202614,
|
631 |
+
"grad_norm": 8.75131607055664,
|
632 |
+
"learning_rate": 6.953655642446368e-05,
|
633 |
+
"loss": 3.193,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.0383442265795207,
|
638 |
+
"grad_norm": 7.756675720214844,
|
639 |
+
"learning_rate": 6.873032967079561e-05,
|
640 |
+
"loss": 3.2385,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.038779956427015254,
|
645 |
+
"grad_norm": 8.15986442565918,
|
646 |
+
"learning_rate": 6.7918397477265e-05,
|
647 |
+
"loss": 3.0469,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.0392156862745098,
|
652 |
+
"grad_norm": 9.440335273742676,
|
653 |
+
"learning_rate": 6.710100716628344e-05,
|
654 |
+
"loss": 3.2547,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.03965141612200436,
|
659 |
+
"grad_norm": 7.82032585144043,
|
660 |
+
"learning_rate": 6.627840772285784e-05,
|
661 |
+
"loss": 3.0536,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.04008714596949891,
|
666 |
+
"grad_norm": 8.337102890014648,
|
667 |
+
"learning_rate": 6.545084971874738e-05,
|
668 |
+
"loss": 3.3388,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.040522875816993466,
|
673 |
+
"grad_norm": 9.669166564941406,
|
674 |
+
"learning_rate": 6.461858523613684e-05,
|
675 |
+
"loss": 3.6829,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.040958605664488015,
|
680 |
+
"grad_norm": 8.827813148498535,
|
681 |
+
"learning_rate": 6.378186779084995e-05,
|
682 |
+
"loss": 3.2636,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.04139433551198257,
|
687 |
+
"grad_norm": 7.568974018096924,
|
688 |
+
"learning_rate": 6.294095225512603e-05,
|
689 |
+
"loss": 3.064,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.04183006535947712,
|
694 |
+
"grad_norm": 10.151366233825684,
|
695 |
+
"learning_rate": 6.209609477998338e-05,
|
696 |
+
"loss": 3.0729,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.04226579520697168,
|
701 |
+
"grad_norm": 15.141189575195312,
|
702 |
+
"learning_rate": 6.124755271719325e-05,
|
703 |
+
"loss": 3.407,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.042701525054466234,
|
708 |
+
"grad_norm": 12.019047737121582,
|
709 |
+
"learning_rate": 6.0395584540887963e-05,
|
710 |
+
"loss": 3.1992,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.043137254901960784,
|
715 |
+
"grad_norm": 18.79649543762207,
|
716 |
+
"learning_rate": 5.9540449768827246e-05,
|
717 |
+
"loss": 3.5933,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.04357298474945534,
|
722 |
+
"grad_norm": 13.088361740112305,
|
723 |
+
"learning_rate": 5.868240888334653e-05,
|
724 |
+
"loss": 4.619,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.04357298474945534,
|
729 |
+
"eval_loss": 6.02884578704834,
|
730 |
+
"eval_runtime": 342.2855,
|
731 |
+
"eval_samples_per_second": 11.295,
|
732 |
+
"eval_steps_per_second": 5.647,
|
733 |
+
"step": 100
|
734 |
}
|
735 |
],
|
736 |
"logging_steps": 1,
|
|
|
759 |
"attributes": {}
|
760 |
}
|
761 |
},
|
762 |
+
"total_flos": 1.4762717692821504e+17,
|
763 |
"train_batch_size": 8,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|