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 201892112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1ab6dd2c27b2ce347db68a17525a4af432eadb516d5d2bf551ed5688ca3ffc1
|
3 |
size 201892112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 403961210
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:486a7558397ed20740af5fd01adcc273a09a9ed88d18292c3c899b0bdad76053
|
3 |
size 403961210
|
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 sha256:68a58cc0855ef095298c78dc0a9307c253509bf6cb61679b5b540c9b2bc56dab
|
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:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
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": 49.406,
|
374 |
"eval_steps_per_second": 6.222,
|
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": 0.42480990290641785,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.4241781548250265,
|
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": 49.406,
|
374 |
"eval_steps_per_second": 6.222,
|
375 |
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.2163308589607635,
|
379 |
+
"grad_norm": 1.2941735982894897,
|
380 |
+
"learning_rate": 3.969463130731183e-06,
|
381 |
+
"loss": 0.2063,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.2205726405090138,
|
386 |
+
"grad_norm": 1.8185893297195435,
|
387 |
+
"learning_rate": 3.8772424536302565e-06,
|
388 |
+
"loss": 0.2909,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.22481442205726404,
|
393 |
+
"grad_norm": 2.4603350162506104,
|
394 |
+
"learning_rate": 3.782248193514766e-06,
|
395 |
+
"loss": 0.297,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.22905620360551432,
|
400 |
+
"grad_norm": 2.465657949447632,
|
401 |
+
"learning_rate": 3.684671656182497e-06,
|
402 |
+
"loss": 0.3119,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.23329798515376457,
|
407 |
+
"grad_norm": 2.5236356258392334,
|
408 |
+
"learning_rate": 3.5847093477938955e-06,
|
409 |
+
"loss": 0.2771,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.23753976670201485,
|
414 |
+
"grad_norm": 3.519874095916748,
|
415 |
+
"learning_rate": 3.4825625791348093e-06,
|
416 |
+
"loss": 0.3052,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.2417815482502651,
|
421 |
+
"grad_norm": 2.217327356338501,
|
422 |
+
"learning_rate": 3.3784370602033572e-06,
|
423 |
+
"loss": 0.2883,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.24602332979851538,
|
428 |
+
"grad_norm": 2.3429453372955322,
|
429 |
+
"learning_rate": 3.272542485937369e-06,
|
430 |
+
"loss": 0.3006,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.25026511134676566,
|
435 |
+
"grad_norm": 3.1694295406341553,
|
436 |
+
"learning_rate": 3.165092113916688e-06,
|
437 |
+
"loss": 0.3607,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.2545068928950159,
|
442 |
+
"grad_norm": 2.1960690021514893,
|
443 |
+
"learning_rate": 3.056302334890786e-06,
|
444 |
+
"loss": 0.2782,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.25874867444326616,
|
449 |
+
"grad_norm": 2.5143775939941406,
|
450 |
+
"learning_rate": 2.946392236996592e-06,
|
451 |
+
"loss": 0.327,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.26299045599151644,
|
456 |
+
"grad_norm": 2.0972142219543457,
|
457 |
+
"learning_rate": 2.835583164544139e-06,
|
458 |
+
"loss": 0.2211,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.2672322375397667,
|
463 |
+
"grad_norm": 1.8701742887496948,
|
464 |
+
"learning_rate": 2.724098272258584e-06,
|
465 |
+
"loss": 0.2287,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.271474019088017,
|
470 |
+
"grad_norm": 2.386495351791382,
|
471 |
+
"learning_rate": 2.6121620758762877e-06,
|
472 |
+
"loss": 0.2951,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.2757158006362672,
|
477 |
+
"grad_norm": 2.3010129928588867,
|
478 |
+
"learning_rate": 2.5e-06,
|
479 |
+
"loss": 0.2169,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.2799575821845175,
|
484 |
+
"grad_norm": 2.422025442123413,
|
485 |
+
"learning_rate": 2.3878379241237136e-06,
|
486 |
+
"loss": 0.2676,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.2841993637327678,
|
491 |
+
"grad_norm": 2.306940793991089,
|
492 |
+
"learning_rate": 2.2759017277414165e-06,
|
493 |
+
"loss": 0.2568,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.28844114528101805,
|
498 |
+
"grad_norm": 2.8453123569488525,
|
499 |
+
"learning_rate": 2.1644168354558623e-06,
|
500 |
+
"loss": 0.3003,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.2926829268292683,
|
505 |
+
"grad_norm": 3.1190452575683594,
|
506 |
+
"learning_rate": 2.053607763003409e-06,
|
507 |
+
"loss": 0.3167,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.29692470837751855,
|
512 |
+
"grad_norm": 4.037975788116455,
|
513 |
+
"learning_rate": 1.9436976651092143e-06,
|
514 |
+
"loss": 0.4344,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.30116648992576883,
|
519 |
+
"grad_norm": 4.7273454666137695,
|
520 |
+
"learning_rate": 1.8349078860833125e-06,
|
521 |
+
"loss": 0.4892,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.3054082714740191,
|
526 |
+
"grad_norm": 8.596299171447754,
|
527 |
+
"learning_rate": 1.7274575140626318e-06,
|
528 |
+
"loss": 0.7955,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.30965005302226933,
|
533 |
+
"grad_norm": 6.555408954620361,
|
534 |
+
"learning_rate": 1.6215629397966432e-06,
|
535 |
+
"loss": 0.7031,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.3138918345705196,
|
540 |
+
"grad_norm": 7.657025337219238,
|
541 |
+
"learning_rate": 1.5174374208651913e-06,
|
542 |
+
"loss": 0.6821,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.3181336161187699,
|
547 |
+
"grad_norm": 7.3240227699279785,
|
548 |
+
"learning_rate": 1.415290652206105e-06,
|
549 |
+
"loss": 0.7677,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.32237539766702017,
|
554 |
+
"grad_norm": 9.968438148498535,
|
555 |
+
"learning_rate": 1.3153283438175036e-06,
|
556 |
+
"loss": 0.6359,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.3266171792152704,
|
561 |
+
"grad_norm": 7.8202338218688965,
|
562 |
+
"learning_rate": 1.217751806485235e-06,
|
563 |
+
"loss": 0.6877,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.33085896076352067,
|
568 |
+
"grad_norm": 7.387623310089111,
|
569 |
+
"learning_rate": 1.122757546369744e-06,
|
570 |
+
"loss": 0.6521,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.33510074231177095,
|
575 |
+
"grad_norm": 8.559468269348145,
|
576 |
+
"learning_rate": 1.0305368692688175e-06,
|
577 |
+
"loss": 0.7261,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.33934252386002123,
|
582 |
+
"grad_norm": 7.285356044769287,
|
583 |
+
"learning_rate": 9.412754953531664e-07,
|
584 |
+
"loss": 0.6358,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.34358430540827145,
|
589 |
+
"grad_norm": 9.018921852111816,
|
590 |
+
"learning_rate": 8.551531851507186e-07,
|
591 |
+
"loss": 0.6657,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.34782608695652173,
|
596 |
+
"grad_norm": 5.554042816162109,
|
597 |
+
"learning_rate": 7.723433775328385e-07,
|
598 |
+
"loss": 0.5567,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.352067868504772,
|
603 |
+
"grad_norm": 11.054597854614258,
|
604 |
+
"learning_rate": 6.930128404315214e-07,
|
605 |
+
"loss": 0.8462,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.3563096500530223,
|
610 |
+
"grad_norm": 6.244119644165039,
|
611 |
+
"learning_rate": 6.17321334990973e-07,
|
612 |
+
"loss": 0.6058,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.3605514316012725,
|
617 |
+
"grad_norm": 10.842486381530762,
|
618 |
+
"learning_rate": 5.454212938299256e-07,
|
619 |
+
"loss": 0.7793,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.3647932131495228,
|
624 |
+
"grad_norm": 7.651045322418213,
|
625 |
+
"learning_rate": 4.774575140626317e-07,
|
626 |
+
"loss": 0.5938,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.36903499469777307,
|
631 |
+
"grad_norm": 10.755373001098633,
|
632 |
+
"learning_rate": 4.1356686569674344e-07,
|
633 |
+
"loss": 0.6908,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.37327677624602335,
|
638 |
+
"grad_norm": 8.134658813476562,
|
639 |
+
"learning_rate": 3.538780159953348e-07,
|
640 |
+
"loss": 0.7198,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.37751855779427357,
|
645 |
+
"grad_norm": 8.481114387512207,
|
646 |
+
"learning_rate": 2.98511170358155e-07,
|
647 |
+
"loss": 0.7024,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.38176033934252385,
|
652 |
+
"grad_norm": 9.80128288269043,
|
653 |
+
"learning_rate": 2.4757783024395244e-07,
|
654 |
+
"loss": 0.6167,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.3860021208907741,
|
659 |
+
"grad_norm": 11.155387878417969,
|
660 |
+
"learning_rate": 2.0118056862137358e-07,
|
661 |
+
"loss": 0.8483,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.3902439024390244,
|
666 |
+
"grad_norm": 7.825685501098633,
|
667 |
+
"learning_rate": 1.59412823400657e-07,
|
668 |
+
"loss": 0.6448,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.3944856839872747,
|
673 |
+
"grad_norm": 7.912622928619385,
|
674 |
+
"learning_rate": 1.223587092621162e-07,
|
675 |
+
"loss": 0.6102,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.3987274655355249,
|
680 |
+
"grad_norm": 11.073833465576172,
|
681 |
+
"learning_rate": 9.00928482603669e-08,
|
682 |
+
"loss": 0.562,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.4029692470837752,
|
687 |
+
"grad_norm": 7.491645336151123,
|
688 |
+
"learning_rate": 6.268021954544095e-08,
|
689 |
+
"loss": 0.4042,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.40721102863202546,
|
694 |
+
"grad_norm": 9.142674446105957,
|
695 |
+
"learning_rate": 4.017602850342584e-08,
|
696 |
+
"loss": 0.4681,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.41145281018027574,
|
701 |
+
"grad_norm": 15.355952262878418,
|
702 |
+
"learning_rate": 2.262559558016325e-08,
|
703 |
+
"loss": 0.7407,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.41569459172852596,
|
708 |
+
"grad_norm": 13.96410083770752,
|
709 |
+
"learning_rate": 1.006426501190233e-08,
|
710 |
+
"loss": 0.5351,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.41993637327677624,
|
715 |
+
"grad_norm": 29.766155242919922,
|
716 |
+
"learning_rate": 2.5173336467135266e-09,
|
717 |
+
"loss": 0.7461,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.4241781548250265,
|
722 |
+
"grad_norm": 28.113073348999023,
|
723 |
+
"learning_rate": 0.0,
|
724 |
+
"loss": 0.8913,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.4241781548250265,
|
729 |
+
"eval_loss": 0.42480990290641785,
|
730 |
+
"eval_runtime": 8.0387,
|
731 |
+
"eval_samples_per_second": 49.386,
|
732 |
+
"eval_steps_per_second": 6.22,
|
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": 2.13314785247232e+16,
|
763 |
"train_batch_size": 8,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|