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 295488936
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e51ff6ee7b0dc13783f57f4707f1510d53501b6c70c75a7f4994d0245da09c7
|
3 |
size 295488936
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 591203178
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b440bfd07103a44dc9a73c7960d4fb40db3fac8994b8645940914b17c23ced0d
|
3 |
size 591203178
|
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:dfe96c3e52e6011a229bed48783712999cab744d45eba86dc8a43ce98cd85d49
|
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:f66dcbf4b621c625ceeba56c80d5892269a3e2c2d170fada35f64e1cf6fa1176
|
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":
|
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": 19.591,
|
374 |
"eval_steps_per_second": 9.796,
|
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": 1.00209379196167,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 2.0202020202020203,
|
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": 19.591,
|
374 |
"eval_steps_per_second": 9.796,
|
375 |
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 1.0303030303030303,
|
379 |
+
"grad_norm": 0.9870416522026062,
|
380 |
+
"learning_rate": 8.641507194059579e-05,
|
381 |
+
"loss": 1.1644,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 1.0505050505050506,
|
386 |
+
"grad_norm": 0.9368259906768799,
|
387 |
+
"learning_rate": 8.55699384101589e-05,
|
388 |
+
"loss": 1.2176,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 1.0707070707070707,
|
393 |
+
"grad_norm": 0.9914711117744446,
|
394 |
+
"learning_rate": 8.47037097610317e-05,
|
395 |
+
"loss": 1.2754,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 1.0909090909090908,
|
400 |
+
"grad_norm": 0.9624159336090088,
|
401 |
+
"learning_rate": 8.381689971904514e-05,
|
402 |
+
"loss": 1.2237,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 1.1111111111111112,
|
407 |
+
"grad_norm": 0.8989251852035522,
|
408 |
+
"learning_rate": 8.29100342160374e-05,
|
409 |
+
"loss": 1.1661,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 1.1313131313131313,
|
414 |
+
"grad_norm": 0.8935759663581848,
|
415 |
+
"learning_rate": 8.198365107794457e-05,
|
416 |
+
"loss": 1.1071,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 1.1515151515151516,
|
421 |
+
"grad_norm": 0.8914757370948792,
|
422 |
+
"learning_rate": 8.103829970583742e-05,
|
423 |
+
"loss": 1.1958,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 1.1717171717171717,
|
428 |
+
"grad_norm": 0.9382041692733765,
|
429 |
+
"learning_rate": 8.007454075009351e-05,
|
430 |
+
"loss": 1.0885,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 1.1919191919191918,
|
435 |
+
"grad_norm": 1.026020884513855,
|
436 |
+
"learning_rate": 7.909294577789766e-05,
|
437 |
+
"loss": 1.196,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 1.2121212121212122,
|
442 |
+
"grad_norm": 1.0326781272888184,
|
443 |
+
"learning_rate": 7.809409693426803e-05,
|
444 |
+
"loss": 1.2008,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 1.2323232323232323,
|
449 |
+
"grad_norm": 1.0171078443527222,
|
450 |
+
"learning_rate": 7.707858659680924e-05,
|
451 |
+
"loss": 1.0956,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 1.2525252525252526,
|
456 |
+
"grad_norm": 1.1952531337738037,
|
457 |
+
"learning_rate": 7.604701702439651e-05,
|
458 |
+
"loss": 1.2509,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 1.2727272727272727,
|
463 |
+
"grad_norm": 0.9705902338027954,
|
464 |
+
"learning_rate": 7.500000000000001e-05,
|
465 |
+
"loss": 1.1169,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 1.2929292929292928,
|
470 |
+
"grad_norm": 0.8539131879806519,
|
471 |
+
"learning_rate": 7.393815646786046e-05,
|
472 |
+
"loss": 0.9659,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 1.3131313131313131,
|
477 |
+
"grad_norm": 1.0443497896194458,
|
478 |
+
"learning_rate": 7.286211616523193e-05,
|
479 |
+
"loss": 1.1447,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 1.3333333333333333,
|
484 |
+
"grad_norm": 0.9528786540031433,
|
485 |
+
"learning_rate": 7.177251724890956e-05,
|
486 |
+
"loss": 1.0219,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 1.3535353535353536,
|
491 |
+
"grad_norm": 1.04220449924469,
|
492 |
+
"learning_rate": 7.067000591676416e-05,
|
493 |
+
"loss": 0.997,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 1.3737373737373737,
|
498 |
+
"grad_norm": 0.7969975471496582,
|
499 |
+
"learning_rate": 6.95552360245078e-05,
|
500 |
+
"loss": 0.8762,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 1.393939393939394,
|
505 |
+
"grad_norm": 1.0815095901489258,
|
506 |
+
"learning_rate": 6.842886869791809e-05,
|
507 |
+
"loss": 1.0771,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 1.4141414141414141,
|
512 |
+
"grad_norm": 1.0188919305801392,
|
513 |
+
"learning_rate": 6.729157194075057e-05,
|
514 |
+
"loss": 1.0527,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 1.4343434343434343,
|
519 |
+
"grad_norm": 1.126763939857483,
|
520 |
+
"learning_rate": 6.614402023857232e-05,
|
521 |
+
"loss": 1.0613,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 1.4545454545454546,
|
526 |
+
"grad_norm": 0.9159054160118103,
|
527 |
+
"learning_rate": 6.498689415875121e-05,
|
528 |
+
"loss": 0.9561,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 1.4747474747474747,
|
533 |
+
"grad_norm": 1.2112116813659668,
|
534 |
+
"learning_rate": 6.382087994683859e-05,
|
535 |
+
"loss": 1.1898,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 1.494949494949495,
|
540 |
+
"grad_norm": 1.1874535083770752,
|
541 |
+
"learning_rate": 6.264666911958404e-05,
|
542 |
+
"loss": 1.2197,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 1.5151515151515151,
|
547 |
+
"grad_norm": 0.8190261721611023,
|
548 |
+
"learning_rate": 6.146495805482451e-05,
|
549 |
+
"loss": 0.8199,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 1.5353535353535355,
|
554 |
+
"grad_norm": 0.9896472096443176,
|
555 |
+
"learning_rate": 6.0276447578490035e-05,
|
556 |
+
"loss": 1.0456,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 1.5555555555555556,
|
561 |
+
"grad_norm": 0.9824926257133484,
|
562 |
+
"learning_rate": 5.908184254897182e-05,
|
563 |
+
"loss": 1.0388,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 1.5757575757575757,
|
568 |
+
"grad_norm": 0.9661423563957214,
|
569 |
+
"learning_rate": 5.788185143909868e-05,
|
570 |
+
"loss": 0.9587,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 1.595959595959596,
|
575 |
+
"grad_norm": 0.9323811531066895,
|
576 |
+
"learning_rate": 5.66771859159699e-05,
|
577 |
+
"loss": 0.9407,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 1.6161616161616161,
|
582 |
+
"grad_norm": 0.9910972714424133,
|
583 |
+
"learning_rate": 5.546856041889373e-05,
|
584 |
+
"loss": 1.0198,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 1.6363636363636362,
|
589 |
+
"grad_norm": 1.2142277956008911,
|
590 |
+
"learning_rate": 5.4256691735681786e-05,
|
591 |
+
"loss": 1.112,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 1.6565656565656566,
|
596 |
+
"grad_norm": 1.0950809717178345,
|
597 |
+
"learning_rate": 5.3042298577550696e-05,
|
598 |
+
"loss": 0.9386,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 1.676767676767677,
|
603 |
+
"grad_norm": 1.1096038818359375,
|
604 |
+
"learning_rate": 5.182610115288295e-05,
|
605 |
+
"loss": 0.9791,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 1.696969696969697,
|
610 |
+
"grad_norm": 1.2279932498931885,
|
611 |
+
"learning_rate": 5.060882074009988e-05,
|
612 |
+
"loss": 1.167,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 1.7171717171717171,
|
617 |
+
"grad_norm": 1.151942491531372,
|
618 |
+
"learning_rate": 4.9391179259900125e-05,
|
619 |
+
"loss": 0.9379,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 1.7373737373737375,
|
624 |
+
"grad_norm": 1.0891432762145996,
|
625 |
+
"learning_rate": 4.817389884711705e-05,
|
626 |
+
"loss": 1.0535,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 1.7575757575757576,
|
631 |
+
"grad_norm": 0.877910315990448,
|
632 |
+
"learning_rate": 4.695770142244931e-05,
|
633 |
+
"loss": 0.9166,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 1.7777777777777777,
|
638 |
+
"grad_norm": 0.822179913520813,
|
639 |
+
"learning_rate": 4.574330826431821e-05,
|
640 |
+
"loss": 0.8026,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 1.797979797979798,
|
645 |
+
"grad_norm": 0.8958245515823364,
|
646 |
+
"learning_rate": 4.4531439581106295e-05,
|
647 |
+
"loss": 0.8582,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 1.8181818181818183,
|
652 |
+
"grad_norm": 1.048801302909851,
|
653 |
+
"learning_rate": 4.332281408403011e-05,
|
654 |
+
"loss": 0.9083,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 1.8383838383838382,
|
659 |
+
"grad_norm": 1.161761999130249,
|
660 |
+
"learning_rate": 4.2118148560901325e-05,
|
661 |
+
"loss": 0.8411,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 1.8585858585858586,
|
666 |
+
"grad_norm": 0.9891107678413391,
|
667 |
+
"learning_rate": 4.0918157451028185e-05,
|
668 |
+
"loss": 0.8344,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 1.878787878787879,
|
673 |
+
"grad_norm": 0.9550774693489075,
|
674 |
+
"learning_rate": 3.972355242150998e-05,
|
675 |
+
"loss": 0.914,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 1.898989898989899,
|
680 |
+
"grad_norm": 1.0667641162872314,
|
681 |
+
"learning_rate": 3.8535041945175506e-05,
|
682 |
+
"loss": 0.9441,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 1.9191919191919191,
|
687 |
+
"grad_norm": 1.065216302871704,
|
688 |
+
"learning_rate": 3.735333088041596e-05,
|
689 |
+
"loss": 0.9306,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 1.9393939393939394,
|
694 |
+
"grad_norm": 0.9413928985595703,
|
695 |
+
"learning_rate": 3.6179120053161416e-05,
|
696 |
+
"loss": 0.8101,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 1.9595959595959596,
|
701 |
+
"grad_norm": 1.1866222620010376,
|
702 |
+
"learning_rate": 3.5013105841248795e-05,
|
703 |
+
"loss": 0.8617,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 1.9797979797979797,
|
708 |
+
"grad_norm": 1.1086472272872925,
|
709 |
+
"learning_rate": 3.38559797614277e-05,
|
710 |
+
"loss": 1.0243,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 2.0,
|
715 |
+
"grad_norm": 1.5880515575408936,
|
716 |
+
"learning_rate": 3.2708428059249436e-05,
|
717 |
+
"loss": 1.2843,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 2.0202020202020203,
|
722 |
+
"grad_norm": 0.8188629746437073,
|
723 |
+
"learning_rate": 3.157113130208191e-05,
|
724 |
+
"loss": 0.7934,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 2.0202020202020203,
|
729 |
+
"eval_loss": 1.00209379196167,
|
730 |
+
"eval_runtime": 4.3279,
|
731 |
+
"eval_samples_per_second": 19.409,
|
732 |
+
"eval_steps_per_second": 9.704,
|
733 |
+
"step": 100
|
734 |
}
|
735 |
],
|
736 |
"logging_steps": 1,
|
|
|
759 |
"attributes": {}
|
760 |
}
|
761 |
},
|
762 |
+
"total_flos": 2.719746402287616e+16,
|
763 |
"train_batch_size": 8,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|