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 226532664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f06418b91d3d581e8a7b9a4dfbe0999918766c17a0de39190bc99ed67e921cf
|
3 |
size 226532664
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 115354708
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e81a23b25ed6d8d15119861945e256867b31726bd002dc31297da77dd483011
|
3 |
size 115354708
|
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 sha256:9a0bb9d019f346bb0dfb18db7121fc4bf38037b1be5970338f41f1e46b807cc3
|
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": 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": 51.331,
|
374 |
"eval_steps_per_second": 12.864,
|
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": 1.5312721729278564,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.20512820512820512,
|
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": 51.331,
|
374 |
"eval_steps_per_second": 12.864,
|
375 |
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.10461538461538461,
|
379 |
+
"grad_norm": 45.60862350463867,
|
380 |
+
"learning_rate": 8.894386393810563e-05,
|
381 |
+
"loss": 10.9436,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.10666666666666667,
|
386 |
+
"grad_norm": 40.9095458984375,
|
387 |
+
"learning_rate": 8.842005554284296e-05,
|
388 |
+
"loss": 9.8222,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.10871794871794872,
|
393 |
+
"grad_norm": 29.07250213623047,
|
394 |
+
"learning_rate": 8.788574348801675e-05,
|
395 |
+
"loss": 9.7954,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.11076923076923077,
|
400 |
+
"grad_norm": 19.12152671813965,
|
401 |
+
"learning_rate": 8.73410738492077e-05,
|
402 |
+
"loss": 8.7552,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.11282051282051282,
|
407 |
+
"grad_norm": 15.645687103271484,
|
408 |
+
"learning_rate": 8.678619553365659e-05,
|
409 |
+
"loss": 7.9666,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.11487179487179487,
|
414 |
+
"grad_norm": 12.901049613952637,
|
415 |
+
"learning_rate": 8.622126023955446e-05,
|
416 |
+
"loss": 7.2302,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.11692307692307692,
|
421 |
+
"grad_norm": 13.514933586120605,
|
422 |
+
"learning_rate": 8.564642241456986e-05,
|
423 |
+
"loss": 6.9736,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.11897435897435897,
|
428 |
+
"grad_norm": 15.239020347595215,
|
429 |
+
"learning_rate": 8.506183921362443e-05,
|
430 |
+
"loss": 8.2168,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.12102564102564102,
|
435 |
+
"grad_norm": 14.39808177947998,
|
436 |
+
"learning_rate": 8.44676704559283e-05,
|
437 |
+
"loss": 7.7725,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.12307692307692308,
|
442 |
+
"grad_norm": 15.560444831848145,
|
443 |
+
"learning_rate": 8.386407858128706e-05,
|
444 |
+
"loss": 7.7944,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.12512820512820513,
|
449 |
+
"grad_norm": 15.985998153686523,
|
450 |
+
"learning_rate": 8.32512286056924e-05,
|
451 |
+
"loss": 7.5215,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.12717948717948718,
|
456 |
+
"grad_norm": 13.703685760498047,
|
457 |
+
"learning_rate": 8.262928807620843e-05,
|
458 |
+
"loss": 6.4452,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.12923076923076923,
|
463 |
+
"grad_norm": 12.232294082641602,
|
464 |
+
"learning_rate": 8.199842702516583e-05,
|
465 |
+
"loss": 7.0958,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.13128205128205128,
|
470 |
+
"grad_norm": 13.26629638671875,
|
471 |
+
"learning_rate": 8.135881792367686e-05,
|
472 |
+
"loss": 6.9345,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.13333333333333333,
|
477 |
+
"grad_norm": 11.06119155883789,
|
478 |
+
"learning_rate": 8.07106356344834e-05,
|
479 |
+
"loss": 6.4671,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.13538461538461538,
|
484 |
+
"grad_norm": 11.033868789672852,
|
485 |
+
"learning_rate": 8.005405736415126e-05,
|
486 |
+
"loss": 6.283,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.13743589743589743,
|
491 |
+
"grad_norm": 13.029328346252441,
|
492 |
+
"learning_rate": 7.938926261462366e-05,
|
493 |
+
"loss": 7.1083,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.13948717948717948,
|
498 |
+
"grad_norm": 12.15227222442627,
|
499 |
+
"learning_rate": 7.871643313414718e-05,
|
500 |
+
"loss": 6.1792,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.14153846153846153,
|
505 |
+
"grad_norm": 12.2940092086792,
|
506 |
+
"learning_rate": 7.803575286758364e-05,
|
507 |
+
"loss": 6.2194,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.14358974358974358,
|
512 |
+
"grad_norm": 14.503169059753418,
|
513 |
+
"learning_rate": 7.734740790612136e-05,
|
514 |
+
"loss": 7.1527,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.14564102564102563,
|
519 |
+
"grad_norm": 11.903534889221191,
|
520 |
+
"learning_rate": 7.66515864363997e-05,
|
521 |
+
"loss": 5.4591,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.1476923076923077,
|
526 |
+
"grad_norm": 11.99606990814209,
|
527 |
+
"learning_rate": 7.594847868906076e-05,
|
528 |
+
"loss": 5.6798,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.14974358974358976,
|
533 |
+
"grad_norm": 14.259871482849121,
|
534 |
+
"learning_rate": 7.52382768867422e-05,
|
535 |
+
"loss": 6.4076,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.1517948717948718,
|
540 |
+
"grad_norm": 13.62007999420166,
|
541 |
+
"learning_rate": 7.452117519152542e-05,
|
542 |
+
"loss": 6.5447,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.15384615384615385,
|
547 |
+
"grad_norm": 14.751792907714844,
|
548 |
+
"learning_rate": 7.379736965185368e-05,
|
549 |
+
"loss": 6.1957,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.1558974358974359,
|
554 |
+
"grad_norm": 13.583488464355469,
|
555 |
+
"learning_rate": 7.30670581489344e-05,
|
556 |
+
"loss": 6.3676,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.15794871794871795,
|
561 |
+
"grad_norm": 18.381629943847656,
|
562 |
+
"learning_rate": 7.233044034264034e-05,
|
563 |
+
"loss": 5.9277,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.16,
|
568 |
+
"grad_norm": 14.782858848571777,
|
569 |
+
"learning_rate": 7.158771761692464e-05,
|
570 |
+
"loss": 6.1597,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.16205128205128205,
|
575 |
+
"grad_norm": 15.938556671142578,
|
576 |
+
"learning_rate": 7.083909302476453e-05,
|
577 |
+
"loss": 7.3438,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.1641025641025641,
|
582 |
+
"grad_norm": 15.627525329589844,
|
583 |
+
"learning_rate": 7.008477123264848e-05,
|
584 |
+
"loss": 6.3384,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.16615384615384615,
|
589 |
+
"grad_norm": 13.616508483886719,
|
590 |
+
"learning_rate": 6.932495846462261e-05,
|
591 |
+
"loss": 5.6324,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.1682051282051282,
|
596 |
+
"grad_norm": 14.7100830078125,
|
597 |
+
"learning_rate": 6.855986244591104e-05,
|
598 |
+
"loss": 6.0926,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.17025641025641025,
|
603 |
+
"grad_norm": 14.996009826660156,
|
604 |
+
"learning_rate": 6.778969234612584e-05,
|
605 |
+
"loss": 5.5604,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.1723076923076923,
|
610 |
+
"grad_norm": 13.628669738769531,
|
611 |
+
"learning_rate": 6.701465872208216e-05,
|
612 |
+
"loss": 5.1218,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.17435897435897435,
|
617 |
+
"grad_norm": 14.282894134521484,
|
618 |
+
"learning_rate": 6.623497346023418e-05,
|
619 |
+
"loss": 6.0892,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.1764102564102564,
|
624 |
+
"grad_norm": 17.6943302154541,
|
625 |
+
"learning_rate": 6.545084971874738e-05,
|
626 |
+
"loss": 5.5497,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.17846153846153845,
|
631 |
+
"grad_norm": 20.049419403076172,
|
632 |
+
"learning_rate": 6.466250186922325e-05,
|
633 |
+
"loss": 6.8342,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.18051282051282053,
|
638 |
+
"grad_norm": 21.07886505126953,
|
639 |
+
"learning_rate": 6.387014543809223e-05,
|
640 |
+
"loss": 6.2599,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.18256410256410258,
|
645 |
+
"grad_norm": 16.717178344726562,
|
646 |
+
"learning_rate": 6.307399704769099e-05,
|
647 |
+
"loss": 6.7429,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.18461538461538463,
|
652 |
+
"grad_norm": 16.91592025756836,
|
653 |
+
"learning_rate": 6.227427435703997e-05,
|
654 |
+
"loss": 6.2824,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.18666666666666668,
|
659 |
+
"grad_norm": 16.047405242919922,
|
660 |
+
"learning_rate": 6.147119600233758e-05,
|
661 |
+
"loss": 6.1241,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.18871794871794872,
|
666 |
+
"grad_norm": 22.26363754272461,
|
667 |
+
"learning_rate": 6.066498153718735e-05,
|
668 |
+
"loss": 7.1718,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.19076923076923077,
|
673 |
+
"grad_norm": 18.209020614624023,
|
674 |
+
"learning_rate": 5.985585137257401e-05,
|
675 |
+
"loss": 6.7806,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.19282051282051282,
|
680 |
+
"grad_norm": 20.497940063476562,
|
681 |
+
"learning_rate": 5.90440267166055e-05,
|
682 |
+
"loss": 6.0283,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.19487179487179487,
|
687 |
+
"grad_norm": 20.384424209594727,
|
688 |
+
"learning_rate": 5.8229729514036705e-05,
|
689 |
+
"loss": 6.3631,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.19692307692307692,
|
694 |
+
"grad_norm": 19.973844528198242,
|
695 |
+
"learning_rate": 5.74131823855921e-05,
|
696 |
+
"loss": 5.4992,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.19897435897435897,
|
701 |
+
"grad_norm": 21.289518356323242,
|
702 |
+
"learning_rate": 5.6594608567103456e-05,
|
703 |
+
"loss": 5.7895,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.20102564102564102,
|
708 |
+
"grad_norm": 25.144672393798828,
|
709 |
+
"learning_rate": 5.577423184847932e-05,
|
710 |
+
"loss": 6.425,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.20307692307692307,
|
715 |
+
"grad_norm": 36.136009216308594,
|
716 |
+
"learning_rate": 5.495227651252315e-05,
|
717 |
+
"loss": 7.8639,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.20512820512820512,
|
722 |
+
"grad_norm": 52.59331130981445,
|
723 |
+
"learning_rate": 5.4128967273616625e-05,
|
724 |
+
"loss": 9.7029,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.20512820512820512,
|
729 |
+
"eval_loss": 1.5312721729278564,
|
730 |
+
"eval_runtime": 15.9631,
|
731 |
+
"eval_samples_per_second": 51.494,
|
732 |
+
"eval_steps_per_second": 12.905,
|
733 |
+
"step": 100
|
734 |
}
|
735 |
],
|
736 |
"logging_steps": 1,
|
|
|
759 |
"attributes": {}
|
760 |
}
|
761 |
},
|
762 |
+
"total_flos": 2.48753499930624e+16,
|
763 |
"train_batch_size": 8,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|