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 247944
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01d59ce2a7341922b7a9bf5e3e23574b2900e413612f1c4d474469579bb705c6
|
3 |
size 247944
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 505518
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd6ae76c436a71395bf794c988db3b4d58532b087016948fa2f243b3dc0d5c4f
|
3 |
size 505518
|
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 sha256:0105e19c5d536965e33c0c61571ab948ed5b34b45e0897cd3142cc89461cc76f
|
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": 11.10726547241211,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
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": 363.086,
|
374 |
"eval_steps_per_second": 90.772,
|
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": 4,
|
406 |
"trial_name": null,
|
407 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 11.10726547241211,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
4 |
+
"epoch": 1.5594541910331383,
|
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": 363.086,
|
374 |
"eval_steps_per_second": 90.772,
|
375 |
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.7953216374269005,
|
379 |
+
"grad_norm": 1.4868738651275635,
|
380 |
+
"learning_rate": 2.847932752400164e-06,
|
381 |
+
"loss": 88.9165,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.8109161793372319,
|
386 |
+
"grad_norm": 1.5754703283309937,
|
387 |
+
"learning_rate": 2.761321158169134e-06,
|
388 |
+
"loss": 88.8994,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.8265107212475633,
|
393 |
+
"grad_norm": 1.521441102027893,
|
394 |
+
"learning_rate": 2.6743911843603134e-06,
|
395 |
+
"loss": 88.8922,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.8421052631578947,
|
400 |
+
"grad_norm": 1.5741850137710571,
|
401 |
+
"learning_rate": 2.587248741756253e-06,
|
402 |
+
"loss": 88.9125,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.8576998050682261,
|
407 |
+
"grad_norm": 1.6995844841003418,
|
408 |
+
"learning_rate": 2.5e-06,
|
409 |
+
"loss": 88.8839,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.8732943469785575,
|
414 |
+
"grad_norm": 1.7483824491500854,
|
415 |
+
"learning_rate": 2.4127512582437486e-06,
|
416 |
+
"loss": 88.8931,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.8888888888888888,
|
421 |
+
"grad_norm": 1.6258654594421387,
|
422 |
+
"learning_rate": 2.325608815639687e-06,
|
423 |
+
"loss": 88.9227,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.9044834307992202,
|
428 |
+
"grad_norm": 1.6917520761489868,
|
429 |
+
"learning_rate": 2.238678841830867e-06,
|
430 |
+
"loss": 88.8958,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.9200779727095516,
|
435 |
+
"grad_norm": 1.9397125244140625,
|
436 |
+
"learning_rate": 2.1520672475998374e-06,
|
437 |
+
"loss": 88.8976,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.935672514619883,
|
442 |
+
"grad_norm": 2.0061938762664795,
|
443 |
+
"learning_rate": 2.0658795558326745e-06,
|
444 |
+
"loss": 88.8821,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.9512670565302144,
|
449 |
+
"grad_norm": 2.2613093852996826,
|
450 |
+
"learning_rate": 1.9802207729556023e-06,
|
451 |
+
"loss": 88.9129,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.9668615984405458,
|
456 |
+
"grad_norm": 2.683389186859131,
|
457 |
+
"learning_rate": 1.895195261000831e-06,
|
458 |
+
"loss": 88.7381,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.9824561403508771,
|
463 |
+
"grad_norm": 3.433419704437256,
|
464 |
+
"learning_rate": 1.8109066104575023e-06,
|
465 |
+
"loss": 88.8607,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.9980506822612085,
|
470 |
+
"grad_norm": 6.409455299377441,
|
471 |
+
"learning_rate": 1.7274575140626318e-06,
|
472 |
+
"loss": 88.5442,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 1.01364522417154,
|
477 |
+
"grad_norm": 1.4463061094284058,
|
478 |
+
"learning_rate": 1.6449496416858285e-06,
|
479 |
+
"loss": 88.9063,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 1.0292397660818713,
|
484 |
+
"grad_norm": 1.4709982872009277,
|
485 |
+
"learning_rate": 1.56348351646022e-06,
|
486 |
+
"loss": 88.9036,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 1.0448343079922027,
|
491 |
+
"grad_norm": 1.5933891534805298,
|
492 |
+
"learning_rate": 1.4831583923105e-06,
|
493 |
+
"loss": 88.9131,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 1.060428849902534,
|
498 |
+
"grad_norm": 1.418686032295227,
|
499 |
+
"learning_rate": 1.4040721330273063e-06,
|
500 |
+
"loss": 88.8879,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 1.0760233918128654,
|
505 |
+
"grad_norm": 1.5968884229660034,
|
506 |
+
"learning_rate": 1.3263210930352737e-06,
|
507 |
+
"loss": 88.8766,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 1.0916179337231968,
|
512 |
+
"grad_norm": 1.7474418878555298,
|
513 |
+
"learning_rate": 1.2500000000000007e-06,
|
514 |
+
"loss": 88.9008,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 1.1072124756335282,
|
519 |
+
"grad_norm": 1.7670066356658936,
|
520 |
+
"learning_rate": 1.1752018394169882e-06,
|
521 |
+
"loss": 88.9295,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 1.1228070175438596,
|
526 |
+
"grad_norm": 1.739268183708191,
|
527 |
+
"learning_rate": 1.1020177413231334e-06,
|
528 |
+
"loss": 88.8783,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 1.138401559454191,
|
533 |
+
"grad_norm": 1.924734354019165,
|
534 |
+
"learning_rate": 1.0305368692688175e-06,
|
535 |
+
"loss": 88.9094,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 1.1539961013645224,
|
540 |
+
"grad_norm": 1.8002381324768066,
|
541 |
+
"learning_rate": 9.608463116858544e-07,
|
542 |
+
"loss": 88.9047,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 1.1695906432748537,
|
547 |
+
"grad_norm": 1.9778398275375366,
|
548 |
+
"learning_rate": 8.930309757836517e-07,
|
549 |
+
"loss": 88.8734,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 1.1851851851851851,
|
554 |
+
"grad_norm": 2.0487163066864014,
|
555 |
+
"learning_rate": 8.271734841028553e-07,
|
556 |
+
"loss": 88.8375,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 1.2007797270955165,
|
561 |
+
"grad_norm": 2.143615484237671,
|
562 |
+
"learning_rate": 7.633540738525066e-07,
|
563 |
+
"loss": 88.8514,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 1.2163742690058479,
|
568 |
+
"grad_norm": 2.540370225906372,
|
569 |
+
"learning_rate": 7.016504991533727e-07,
|
570 |
+
"loss": 88.7744,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 1.2319688109161793,
|
575 |
+
"grad_norm": 3.210033416748047,
|
576 |
+
"learning_rate": 6.421379363065142e-07,
|
577 |
+
"loss": 88.7798,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 1.2475633528265107,
|
582 |
+
"grad_norm": 5.062490463256836,
|
583 |
+
"learning_rate": 5.848888922025553e-07,
|
584 |
+
"loss": 88.712,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 1.263157894736842,
|
589 |
+
"grad_norm": 2.2439610958099365,
|
590 |
+
"learning_rate": 5.299731159831953e-07,
|
591 |
+
"loss": 88.918,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 1.2787524366471734,
|
596 |
+
"grad_norm": 1.4683839082717896,
|
597 |
+
"learning_rate": 4.774575140626317e-07,
|
598 |
+
"loss": 88.9326,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 1.2943469785575048,
|
603 |
+
"grad_norm": 1.4734752178192139,
|
604 |
+
"learning_rate": 4.27406068612396e-07,
|
605 |
+
"loss": 88.9029,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 1.3099415204678362,
|
610 |
+
"grad_norm": 1.5223207473754883,
|
611 |
+
"learning_rate": 3.798797596089351e-07,
|
612 |
+
"loss": 88.9191,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 1.3255360623781676,
|
617 |
+
"grad_norm": 1.5164719820022583,
|
618 |
+
"learning_rate": 3.3493649053890325e-07,
|
619 |
+
"loss": 88.8715,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 1.341130604288499,
|
624 |
+
"grad_norm": 1.6114667654037476,
|
625 |
+
"learning_rate": 2.9263101785268253e-07,
|
626 |
+
"loss": 88.8649,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 1.3567251461988303,
|
631 |
+
"grad_norm": 1.7107863426208496,
|
632 |
+
"learning_rate": 2.53014884252083e-07,
|
633 |
+
"loss": 88.8973,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 1.3723196881091617,
|
638 |
+
"grad_norm": 1.7419860363006592,
|
639 |
+
"learning_rate": 2.1613635589349756e-07,
|
640 |
+
"loss": 88.8746,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 1.387914230019493,
|
645 |
+
"grad_norm": 1.6827164888381958,
|
646 |
+
"learning_rate": 1.8204036358303173e-07,
|
647 |
+
"loss": 88.8891,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 1.4035087719298245,
|
652 |
+
"grad_norm": 1.8386940956115723,
|
653 |
+
"learning_rate": 1.507684480352292e-07,
|
654 |
+
"loss": 88.8503,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 1.4191033138401559,
|
659 |
+
"grad_norm": 1.9322350025177002,
|
660 |
+
"learning_rate": 1.223587092621162e-07,
|
661 |
+
"loss": 88.8244,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 1.4346978557504872,
|
666 |
+
"grad_norm": 1.968429684638977,
|
667 |
+
"learning_rate": 9.684576015420277e-08,
|
668 |
+
"loss": 88.882,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 1.4502923976608186,
|
673 |
+
"grad_norm": 2.1462831497192383,
|
674 |
+
"learning_rate": 7.426068431000883e-08,
|
675 |
+
"loss": 88.8721,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 1.46588693957115,
|
680 |
+
"grad_norm": 2.4528849124908447,
|
681 |
+
"learning_rate": 5.463099816548578e-08,
|
682 |
+
"loss": 88.8235,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 1.4814814814814814,
|
687 |
+
"grad_norm": 2.8609659671783447,
|
688 |
+
"learning_rate": 3.798061746947995e-08,
|
689 |
+
"loss": 88.7827,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 1.4970760233918128,
|
694 |
+
"grad_norm": 4.6707563400268555,
|
695 |
+
"learning_rate": 2.4329828146074096e-08,
|
696 |
+
"loss": 88.6615,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 1.5126705653021442,
|
701 |
+
"grad_norm": 2.532287120819092,
|
702 |
+
"learning_rate": 1.3695261579316776e-08,
|
703 |
+
"loss": 88.8792,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 1.5282651072124755,
|
708 |
+
"grad_norm": 1.508450984954834,
|
709 |
+
"learning_rate": 6.089874350439507e-09,
|
710 |
+
"loss": 88.9139,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 1.543859649122807,
|
715 |
+
"grad_norm": 1.4835156202316284,
|
716 |
+
"learning_rate": 1.5229324522605949e-09,
|
717 |
+
"loss": 88.9422,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 1.5594541910331383,
|
722 |
+
"grad_norm": 1.498764991760254,
|
723 |
+
"learning_rate": 0.0,
|
724 |
+
"loss": 88.9188,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 1.5594541910331383,
|
729 |
+
"eval_loss": 11.107521057128906,
|
730 |
+
"eval_runtime": 0.3045,
|
731 |
+
"eval_samples_per_second": 354.702,
|
732 |
+
"eval_steps_per_second": 88.675,
|
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": 8592815554560.0,
|
763 |
"train_batch_size": 4,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|