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 54285928
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f58e0bbc94de05d95e3ce989f56420f6d7e91b2e28a74557826722cc8860f8c3
|
3 |
size 54285928
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 108668858
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:357a7cf7981c0b42d6bf0697699d760bc495e502ba6f64837c6084767043652d
|
3 |
size 108668858
|
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 sha256:914695925d14affc0576dbe81559b498ac6fdf69b91949287fb2985e39063e7b
|
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 sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
|
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": 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": 175.286,
|
374 |
"eval_steps_per_second": 22.002,
|
375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
376 |
}
|
377 |
],
|
378 |
"logging_steps": 1,
|
@@ -396,12 +754,12 @@
|
|
396 |
"should_evaluate": false,
|
397 |
"should_log": false,
|
398 |
"should_save": true,
|
399 |
-
"should_training_stop":
|
400 |
},
|
401 |
"attributes": {}
|
402 |
}
|
403 |
},
|
404 |
-
"total_flos":
|
405 |
"train_batch_size": 8,
|
406 |
"trial_name": null,
|
407 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.9553877115249634,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.10020040080160321,
|
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": 175.286,
|
374 |
"eval_steps_per_second": 22.002,
|
375 |
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.05110220440881764,
|
379 |
+
"grad_norm": 5.009476661682129,
|
380 |
+
"learning_rate": 5.695865504800327e-05,
|
381 |
+
"loss": 2.1321,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.052104208416833664,
|
386 |
+
"grad_norm": 3.8039870262145996,
|
387 |
+
"learning_rate": 5.522642316338268e-05,
|
388 |
+
"loss": 2.0542,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.0531062124248497,
|
393 |
+
"grad_norm": 1.9156354665756226,
|
394 |
+
"learning_rate": 5.348782368720626e-05,
|
395 |
+
"loss": 1.8746,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.05410821643286573,
|
400 |
+
"grad_norm": 1.2341103553771973,
|
401 |
+
"learning_rate": 5.174497483512506e-05,
|
402 |
+
"loss": 2.0515,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.05511022044088176,
|
407 |
+
"grad_norm": 1.197675108909607,
|
408 |
+
"learning_rate": 5e-05,
|
409 |
+
"loss": 1.9927,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.056112224448897796,
|
414 |
+
"grad_norm": 1.473565936088562,
|
415 |
+
"learning_rate": 4.825502516487497e-05,
|
416 |
+
"loss": 1.9117,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.05711422845691383,
|
421 |
+
"grad_norm": 1.9182207584381104,
|
422 |
+
"learning_rate": 4.6512176312793736e-05,
|
423 |
+
"loss": 1.9596,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.05811623246492986,
|
428 |
+
"grad_norm": 1.9375628232955933,
|
429 |
+
"learning_rate": 4.477357683661734e-05,
|
430 |
+
"loss": 1.8432,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.05911823647294589,
|
435 |
+
"grad_norm": 1.3622163534164429,
|
436 |
+
"learning_rate": 4.3041344951996746e-05,
|
437 |
+
"loss": 1.9311,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.06012024048096192,
|
442 |
+
"grad_norm": 1.1024616956710815,
|
443 |
+
"learning_rate": 4.131759111665349e-05,
|
444 |
+
"loss": 1.9859,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.061122244488977955,
|
449 |
+
"grad_norm": 1.1622207164764404,
|
450 |
+
"learning_rate": 3.960441545911204e-05,
|
451 |
+
"loss": 2.0643,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.06212424849699399,
|
456 |
+
"grad_norm": 0.9732226133346558,
|
457 |
+
"learning_rate": 3.790390522001662e-05,
|
458 |
+
"loss": 1.9253,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.06312625250501001,
|
463 |
+
"grad_norm": 0.9754781723022461,
|
464 |
+
"learning_rate": 3.6218132209150045e-05,
|
465 |
+
"loss": 1.8487,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.06412825651302605,
|
470 |
+
"grad_norm": 0.9494886994361877,
|
471 |
+
"learning_rate": 3.4549150281252636e-05,
|
472 |
+
"loss": 1.8671,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.06513026052104208,
|
477 |
+
"grad_norm": 1.0573123693466187,
|
478 |
+
"learning_rate": 3.289899283371657e-05,
|
479 |
+
"loss": 1.9093,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.06613226452905811,
|
484 |
+
"grad_norm": 0.9759222865104675,
|
485 |
+
"learning_rate": 3.12696703292044e-05,
|
486 |
+
"loss": 1.8703,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.06713426853707415,
|
491 |
+
"grad_norm": 1.0865356922149658,
|
492 |
+
"learning_rate": 2.9663167846209998e-05,
|
493 |
+
"loss": 1.9515,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.06813627254509018,
|
498 |
+
"grad_norm": 1.320967435836792,
|
499 |
+
"learning_rate": 2.8081442660546125e-05,
|
500 |
+
"loss": 2.1222,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.06913827655310621,
|
505 |
+
"grad_norm": 1.0985479354858398,
|
506 |
+
"learning_rate": 2.6526421860705473e-05,
|
507 |
+
"loss": 1.949,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.07014028056112225,
|
512 |
+
"grad_norm": 1.15016508102417,
|
513 |
+
"learning_rate": 2.500000000000001e-05,
|
514 |
+
"loss": 1.9248,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.07114228456913828,
|
519 |
+
"grad_norm": 1.0512685775756836,
|
520 |
+
"learning_rate": 2.350403678833976e-05,
|
521 |
+
"loss": 1.9727,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.07214428857715431,
|
526 |
+
"grad_norm": 1.0246506929397583,
|
527 |
+
"learning_rate": 2.2040354826462668e-05,
|
528 |
+
"loss": 1.9059,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.07314629258517034,
|
533 |
+
"grad_norm": 1.0503231287002563,
|
534 |
+
"learning_rate": 2.061073738537635e-05,
|
535 |
+
"loss": 1.903,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.07414829659318638,
|
540 |
+
"grad_norm": 1.047714352607727,
|
541 |
+
"learning_rate": 1.9216926233717085e-05,
|
542 |
+
"loss": 1.9435,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.07515030060120241,
|
547 |
+
"grad_norm": 0.9988422393798828,
|
548 |
+
"learning_rate": 1.7860619515673033e-05,
|
549 |
+
"loss": 1.8911,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.07615230460921844,
|
554 |
+
"grad_norm": 1.0220667123794556,
|
555 |
+
"learning_rate": 1.6543469682057106e-05,
|
556 |
+
"loss": 1.9138,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.07715430861723446,
|
561 |
+
"grad_norm": 1.0607954263687134,
|
562 |
+
"learning_rate": 1.526708147705013e-05,
|
563 |
+
"loss": 2.0026,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.0781563126252505,
|
568 |
+
"grad_norm": 1.0461175441741943,
|
569 |
+
"learning_rate": 1.4033009983067452e-05,
|
570 |
+
"loss": 1.9518,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.07915831663326653,
|
575 |
+
"grad_norm": 1.0595484972000122,
|
576 |
+
"learning_rate": 1.2842758726130283e-05,
|
577 |
+
"loss": 2.0095,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.08016032064128256,
|
582 |
+
"grad_norm": 1.0464117527008057,
|
583 |
+
"learning_rate": 1.1697777844051105e-05,
|
584 |
+
"loss": 1.9532,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.0811623246492986,
|
589 |
+
"grad_norm": 1.083019495010376,
|
590 |
+
"learning_rate": 1.0599462319663905e-05,
|
591 |
+
"loss": 2.0481,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.08216432865731463,
|
596 |
+
"grad_norm": 1.0056906938552856,
|
597 |
+
"learning_rate": 9.549150281252633e-06,
|
598 |
+
"loss": 1.896,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.08316633266533066,
|
603 |
+
"grad_norm": 1.087171196937561,
|
604 |
+
"learning_rate": 8.548121372247918e-06,
|
605 |
+
"loss": 2.022,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.0841683366733467,
|
610 |
+
"grad_norm": 1.0407052040100098,
|
611 |
+
"learning_rate": 7.597595192178702e-06,
|
612 |
+
"loss": 1.8995,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.08517034068136273,
|
617 |
+
"grad_norm": 1.1170405149459839,
|
618 |
+
"learning_rate": 6.698729810778065e-06,
|
619 |
+
"loss": 1.8842,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.08617234468937876,
|
624 |
+
"grad_norm": 1.1040823459625244,
|
625 |
+
"learning_rate": 5.852620357053651e-06,
|
626 |
+
"loss": 1.867,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.0871743486973948,
|
631 |
+
"grad_norm": 1.0043014287948608,
|
632 |
+
"learning_rate": 5.060297685041659e-06,
|
633 |
+
"loss": 1.9638,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.08817635270541083,
|
638 |
+
"grad_norm": 1.1229714155197144,
|
639 |
+
"learning_rate": 4.322727117869951e-06,
|
640 |
+
"loss": 1.9637,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.08917835671342686,
|
645 |
+
"grad_norm": 1.1226463317871094,
|
646 |
+
"learning_rate": 3.6408072716606346e-06,
|
647 |
+
"loss": 1.953,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.09018036072144289,
|
652 |
+
"grad_norm": 1.147606611251831,
|
653 |
+
"learning_rate": 3.0153689607045845e-06,
|
654 |
+
"loss": 1.927,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.09118236472945891,
|
659 |
+
"grad_norm": 1.227723479270935,
|
660 |
+
"learning_rate": 2.4471741852423237e-06,
|
661 |
+
"loss": 1.9815,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.09218436873747494,
|
666 |
+
"grad_norm": 1.0677237510681152,
|
667 |
+
"learning_rate": 1.9369152030840556e-06,
|
668 |
+
"loss": 1.8739,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.09318637274549098,
|
673 |
+
"grad_norm": 1.1743624210357666,
|
674 |
+
"learning_rate": 1.4852136862001764e-06,
|
675 |
+
"loss": 2.0189,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.09418837675350701,
|
680 |
+
"grad_norm": 1.2376830577850342,
|
681 |
+
"learning_rate": 1.0926199633097157e-06,
|
682 |
+
"loss": 2.0479,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.09519038076152304,
|
687 |
+
"grad_norm": 1.1650396585464478,
|
688 |
+
"learning_rate": 7.596123493895991e-07,
|
689 |
+
"loss": 1.9083,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.09619238476953908,
|
694 |
+
"grad_norm": 1.2286704778671265,
|
695 |
+
"learning_rate": 4.865965629214819e-07,
|
696 |
+
"loss": 2.0419,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.09719438877755511,
|
701 |
+
"grad_norm": 1.3613375425338745,
|
702 |
+
"learning_rate": 2.7390523158633554e-07,
|
703 |
+
"loss": 2.0559,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.09819639278557114,
|
708 |
+
"grad_norm": 1.5550633668899536,
|
709 |
+
"learning_rate": 1.2179748700879012e-07,
|
710 |
+
"loss": 2.3656,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.09919839679358718,
|
715 |
+
"grad_norm": 1.7067337036132812,
|
716 |
+
"learning_rate": 3.04586490452119e-08,
|
717 |
+
"loss": 2.372,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.10020040080160321,
|
722 |
+
"grad_norm": 2.390549421310425,
|
723 |
+
"learning_rate": 0.0,
|
724 |
+
"loss": 2.2388,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.10020040080160321,
|
729 |
+
"eval_loss": 1.9553877115249634,
|
730 |
+
"eval_runtime": 9.5891,
|
731 |
+
"eval_samples_per_second": 175.303,
|
732 |
+
"eval_steps_per_second": 22.004,
|
733 |
+
"step": 100
|
734 |
}
|
735 |
],
|
736 |
"logging_steps": 1,
|
|
|
754 |
"should_evaluate": false,
|
755 |
"should_log": false,
|
756 |
"should_save": true,
|
757 |
+
"should_training_stop": true
|
758 |
},
|
759 |
"attributes": {}
|
760 |
}
|
761 |
},
|
762 |
+
"total_flos": 2976789823488000.0,
|
763 |
"train_batch_size": 8,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|