Training in progress, step 100, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 239892858
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adf1e9c86bcadcdd5e9d98aa7f18e59c8474f6374b9a6aa6a79792612fd88311
|
3 |
size 239892858
|
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 sha256:4d6c3ddbae849d3ccbdf9cd52b454876d60f804e513396a998f0af85ccbb336d
|
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 sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": NaN,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
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": 5.156,
|
374 |
"eval_steps_per_second": 2.578,
|
375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
376 |
}
|
377 |
],
|
378 |
"logging_steps": 1,
|
@@ -387,7 +745,7 @@
|
|
387 |
"early_stopping_threshold": 0.0
|
388 |
},
|
389 |
"attributes": {
|
390 |
-
"early_stopping_patience_counter":
|
391 |
}
|
392 |
},
|
393 |
"TrainerControl": {
|
@@ -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": 2,
|
406 |
"trial_name": null,
|
407 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": NaN,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
4 |
+
"epoch": 0.001648750247312537,
|
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": 5.156,
|
374 |
"eval_steps_per_second": 2.578,
|
375 |
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.0008408626261293939,
|
379 |
+
"grad_norm": NaN,
|
380 |
+
"learning_rate": 0.00010495837546732224,
|
381 |
+
"loss": 0.0,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.0008573501286025193,
|
386 |
+
"grad_norm": NaN,
|
387 |
+
"learning_rate": 0.00010165339447663587,
|
388 |
+
"loss": 0.0,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.0008738376310756447,
|
393 |
+
"grad_norm": NaN,
|
394 |
+
"learning_rate": 9.834660552336415e-05,
|
395 |
+
"loss": 0.0,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.00089032513354877,
|
400 |
+
"grad_norm": NaN,
|
401 |
+
"learning_rate": 9.504162453267777e-05,
|
402 |
+
"loss": 0.0,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.0009068126360218954,
|
407 |
+
"grad_norm": NaN,
|
408 |
+
"learning_rate": 9.174206545276677e-05,
|
409 |
+
"loss": 0.0,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.0009233001384950207,
|
414 |
+
"grad_norm": NaN,
|
415 |
+
"learning_rate": 8.845153630304139e-05,
|
416 |
+
"loss": 0.0,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.0009397876409681462,
|
421 |
+
"grad_norm": NaN,
|
422 |
+
"learning_rate": 8.517363522881579e-05,
|
423 |
+
"loss": 0.0,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.0009562751434412715,
|
428 |
+
"grad_norm": NaN,
|
429 |
+
"learning_rate": 8.191194656678904e-05,
|
430 |
+
"loss": 0.0,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.0009727626459143969,
|
435 |
+
"grad_norm": NaN,
|
436 |
+
"learning_rate": 7.867003692562534e-05,
|
437 |
+
"loss": 0.0,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.0009892501483875222,
|
442 |
+
"grad_norm": NaN,
|
443 |
+
"learning_rate": 7.54514512859201e-05,
|
444 |
+
"loss": 0.0,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.0010057376508606475,
|
449 |
+
"grad_norm": NaN,
|
450 |
+
"learning_rate": 7.225970912381556e-05,
|
451 |
+
"loss": 0.0,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.001022225153333773,
|
456 |
+
"grad_norm": NaN,
|
457 |
+
"learning_rate": 6.909830056250527e-05,
|
458 |
+
"loss": 0.0,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.0010387126558068984,
|
463 |
+
"grad_norm": NaN,
|
464 |
+
"learning_rate": 6.59706825558357e-05,
|
465 |
+
"loss": 0.0,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.0010552001582800237,
|
470 |
+
"grad_norm": NaN,
|
471 |
+
"learning_rate": 6.28802751081779e-05,
|
472 |
+
"loss": 0.0,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.001071687660753149,
|
477 |
+
"grad_norm": NaN,
|
478 |
+
"learning_rate": 5.983045753470308e-05,
|
479 |
+
"loss": 0.0,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.0010881751632262745,
|
484 |
+
"grad_norm": NaN,
|
485 |
+
"learning_rate": 5.6824564766150726e-05,
|
486 |
+
"loss": 0.0,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.0011046626656993999,
|
491 |
+
"grad_norm": NaN,
|
492 |
+
"learning_rate": 5.386588370213124e-05,
|
493 |
+
"loss": 0.0,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.0011211501681725252,
|
498 |
+
"grad_norm": NaN,
|
499 |
+
"learning_rate": 5.095764961694922e-05,
|
500 |
+
"loss": 0.0,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.0011376376706456505,
|
505 |
+
"grad_norm": NaN,
|
506 |
+
"learning_rate": 4.810304262187852e-05,
|
507 |
+
"loss": 0.0,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.001154125173118776,
|
512 |
+
"grad_norm": NaN,
|
513 |
+
"learning_rate": 4.530518418775733e-05,
|
514 |
+
"loss": 0.0,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.0011706126755919013,
|
519 |
+
"grad_norm": NaN,
|
520 |
+
"learning_rate": 4.256713373170564e-05,
|
521 |
+
"loss": 0.0,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.0011871001780650267,
|
526 |
+
"grad_norm": NaN,
|
527 |
+
"learning_rate": 3.9891885271697496e-05,
|
528 |
+
"loss": 0.0,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.001203587680538152,
|
533 |
+
"grad_norm": NaN,
|
534 |
+
"learning_rate": 3.7282364152646297e-05,
|
535 |
+
"loss": 0.0,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.0012200751830112775,
|
540 |
+
"grad_norm": NaN,
|
541 |
+
"learning_rate": 3.4741423847583134e-05,
|
542 |
+
"loss": 0.0,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.0012365626854844028,
|
547 |
+
"grad_norm": NaN,
|
548 |
+
"learning_rate": 3.227184283742591e-05,
|
549 |
+
"loss": 0.0,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.0012530501879575281,
|
554 |
+
"grad_norm": NaN,
|
555 |
+
"learning_rate": 2.9876321572751144e-05,
|
556 |
+
"loss": 0.0,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.0012695376904306535,
|
561 |
+
"grad_norm": NaN,
|
562 |
+
"learning_rate": 2.7557479520891104e-05,
|
563 |
+
"loss": 0.0,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.001286025192903779,
|
568 |
+
"grad_norm": NaN,
|
569 |
+
"learning_rate": 2.5317852301584643e-05,
|
570 |
+
"loss": 0.0,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.0013025126953769043,
|
575 |
+
"grad_norm": NaN,
|
576 |
+
"learning_rate": 2.315988891431412e-05,
|
577 |
+
"loss": 0.0,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.0013190001978500296,
|
582 |
+
"grad_norm": NaN,
|
583 |
+
"learning_rate": 2.1085949060360654e-05,
|
584 |
+
"loss": 0.0,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.0013354877003231552,
|
589 |
+
"grad_norm": NaN,
|
590 |
+
"learning_rate": 1.9098300562505266e-05,
|
591 |
+
"loss": 0.0,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.0013519752027962805,
|
596 |
+
"grad_norm": NaN,
|
597 |
+
"learning_rate": 1.7199116885197995e-05,
|
598 |
+
"loss": 0.0,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.0013684627052694058,
|
603 |
+
"grad_norm": NaN,
|
604 |
+
"learning_rate": 1.5390474757906446e-05,
|
605 |
+
"loss": 0.0,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.001384950207742531,
|
610 |
+
"grad_norm": NaN,
|
611 |
+
"learning_rate": 1.3674351904242611e-05,
|
612 |
+
"loss": 0.0,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.0014014377102156566,
|
617 |
+
"grad_norm": NaN,
|
618 |
+
"learning_rate": 1.2052624879351104e-05,
|
619 |
+
"loss": 0.0,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.001417925212688782,
|
624 |
+
"grad_norm": NaN,
|
625 |
+
"learning_rate": 1.0527067017923654e-05,
|
626 |
+
"loss": 0.0,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.0014344127151619073,
|
631 |
+
"grad_norm": NaN,
|
632 |
+
"learning_rate": 9.09934649508375e-06,
|
633 |
+
"loss": 0.0,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.0014509002176350326,
|
638 |
+
"grad_norm": NaN,
|
639 |
+
"learning_rate": 7.771024502261526e-06,
|
640 |
+
"loss": 0.0,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.0014673877201081581,
|
645 |
+
"grad_norm": NaN,
|
646 |
+
"learning_rate": 6.543553540053926e-06,
|
647 |
+
"loss": 0.0,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.0014838752225812834,
|
652 |
+
"grad_norm": NaN,
|
653 |
+
"learning_rate": 5.418275829936537e-06,
|
654 |
+
"loss": 0.0,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.0015003627250544087,
|
659 |
+
"grad_norm": NaN,
|
660 |
+
"learning_rate": 4.3964218465642355e-06,
|
661 |
+
"loss": 0.0,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.001516850227527534,
|
666 |
+
"grad_norm": NaN,
|
667 |
+
"learning_rate": 3.4791089722651436e-06,
|
668 |
+
"loss": 0.0,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.0015333377300006596,
|
673 |
+
"grad_norm": NaN,
|
674 |
+
"learning_rate": 2.667340275199426e-06,
|
675 |
+
"loss": 0.0,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.001549825232473785,
|
680 |
+
"grad_norm": NaN,
|
681 |
+
"learning_rate": 1.9620034125190644e-06,
|
682 |
+
"loss": 0.0,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.0015663127349469102,
|
687 |
+
"grad_norm": NaN,
|
688 |
+
"learning_rate": 1.3638696597277679e-06,
|
689 |
+
"loss": 0.0,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.0015828002374200355,
|
694 |
+
"grad_norm": NaN,
|
695 |
+
"learning_rate": 8.735930673024806e-07,
|
696 |
+
"loss": 0.0,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.001599287739893161,
|
701 |
+
"grad_norm": NaN,
|
702 |
+
"learning_rate": 4.917097454988584e-07,
|
703 |
+
"loss": 0.0,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.0016157752423662864,
|
708 |
+
"grad_norm": NaN,
|
709 |
+
"learning_rate": 2.1863727812254653e-07,
|
710 |
+
"loss": 0.0,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.0016322627448394117,
|
715 |
+
"grad_norm": NaN,
|
716 |
+
"learning_rate": 5.467426590739511e-08,
|
717 |
+
"loss": 0.0,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.001648750247312537,
|
722 |
+
"grad_norm": NaN,
|
723 |
+
"learning_rate": 0.0,
|
724 |
+
"loss": 0.0,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.001648750247312537,
|
729 |
+
"eval_loss": NaN,
|
730 |
+
"eval_runtime": 4954.0916,
|
731 |
+
"eval_samples_per_second": 5.155,
|
732 |
+
"eval_steps_per_second": 2.577,
|
733 |
+
"step": 100
|
734 |
}
|
735 |
],
|
736 |
"logging_steps": 1,
|
|
|
745 |
"early_stopping_threshold": 0.0
|
746 |
},
|
747 |
"attributes": {
|
748 |
+
"early_stopping_patience_counter": 1
|
749 |
}
|
750 |
},
|
751 |
"TrainerControl": {
|
|
|
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": 5.51427898343424e+16,
|
763 |
"train_batch_size": 2,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|