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 250422888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f46342b1765499ccf6a90b462751720366d1debce0e8f5105f5dadf63029069
|
3 |
size 250422888
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 501168482
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a29f7dad4fe351cd47588f7b0299e464458207ddff995bbb07e7695ab9a4001
|
3 |
size 501168482
|
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:dfde37d974eb135b56f608c6996a529e004f1b3a1386ef7d9997a54d3bdf0ce3
|
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": 2.
|
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": 8.68,
|
374 |
"eval_steps_per_second": 2.17,
|
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": 4,
|
406 |
"trial_name": null,
|
407 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.4464058876037598,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.0541895278737384,
|
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": 8.68,
|
374 |
"eval_steps_per_second": 2.17,
|
375 |
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.027636659215606586,
|
379 |
+
"grad_norm": 1.6957308053970337,
|
380 |
+
"learning_rate": 2.847932752400164e-06,
|
381 |
+
"loss": 12.6216,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.028178554494343967,
|
386 |
+
"grad_norm": 2.395599842071533,
|
387 |
+
"learning_rate": 2.761321158169134e-06,
|
388 |
+
"loss": 13.6985,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.02872044977308135,
|
393 |
+
"grad_norm": 2.4453835487365723,
|
394 |
+
"learning_rate": 2.6743911843603134e-06,
|
395 |
+
"loss": 13.4491,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.029262345051818735,
|
400 |
+
"grad_norm": 4.068036079406738,
|
401 |
+
"learning_rate": 2.587248741756253e-06,
|
402 |
+
"loss": 13.1798,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.02980424033055612,
|
407 |
+
"grad_norm": 3.4825592041015625,
|
408 |
+
"learning_rate": 2.5e-06,
|
409 |
+
"loss": 14.8378,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.030346135609293504,
|
414 |
+
"grad_norm": 3.283317804336548,
|
415 |
+
"learning_rate": 2.4127512582437486e-06,
|
416 |
+
"loss": 14.6238,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.03088803088803089,
|
421 |
+
"grad_norm": 2.9764211177825928,
|
422 |
+
"learning_rate": 2.325608815639687e-06,
|
423 |
+
"loss": 15.7249,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.03142992616676827,
|
428 |
+
"grad_norm": 2.89556622505188,
|
429 |
+
"learning_rate": 2.238678841830867e-06,
|
430 |
+
"loss": 14.5268,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.03197182144550566,
|
435 |
+
"grad_norm": 4.53331995010376,
|
436 |
+
"learning_rate": 2.1520672475998374e-06,
|
437 |
+
"loss": 15.1174,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.03251371672424304,
|
442 |
+
"grad_norm": 3.2078773975372314,
|
443 |
+
"learning_rate": 2.0658795558326745e-06,
|
444 |
+
"loss": 15.0038,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.033055612002980427,
|
449 |
+
"grad_norm": 3.0406272411346436,
|
450 |
+
"learning_rate": 1.9802207729556023e-06,
|
451 |
+
"loss": 15.8146,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.03359750728171781,
|
456 |
+
"grad_norm": 3.8402979373931885,
|
457 |
+
"learning_rate": 1.895195261000831e-06,
|
458 |
+
"loss": 16.1639,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.034139402560455195,
|
463 |
+
"grad_norm": 3.454057455062866,
|
464 |
+
"learning_rate": 1.8109066104575023e-06,
|
465 |
+
"loss": 15.6871,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.034681297839192576,
|
470 |
+
"grad_norm": 3.8209731578826904,
|
471 |
+
"learning_rate": 1.7274575140626318e-06,
|
472 |
+
"loss": 17.064,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.03522319311792996,
|
477 |
+
"grad_norm": 3.635895252227783,
|
478 |
+
"learning_rate": 1.6449496416858285e-06,
|
479 |
+
"loss": 15.6606,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.035765088396667345,
|
484 |
+
"grad_norm": 4.060421466827393,
|
485 |
+
"learning_rate": 1.56348351646022e-06,
|
486 |
+
"loss": 17.5466,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.036306983675404726,
|
491 |
+
"grad_norm": 4.730147361755371,
|
492 |
+
"learning_rate": 1.4831583923105e-06,
|
493 |
+
"loss": 17.1693,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.036848878954142114,
|
498 |
+
"grad_norm": 9.351218223571777,
|
499 |
+
"learning_rate": 1.4040721330273063e-06,
|
500 |
+
"loss": 15.6337,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.037390774232879495,
|
505 |
+
"grad_norm": 4.0762128829956055,
|
506 |
+
"learning_rate": 1.3263210930352737e-06,
|
507 |
+
"loss": 15.6759,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.03793266951161688,
|
512 |
+
"grad_norm": 4.4134907722473145,
|
513 |
+
"learning_rate": 1.2500000000000007e-06,
|
514 |
+
"loss": 16.9798,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.038474564790354264,
|
519 |
+
"grad_norm": 4.037068843841553,
|
520 |
+
"learning_rate": 1.1752018394169882e-06,
|
521 |
+
"loss": 18.4723,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.039016460069091645,
|
526 |
+
"grad_norm": 4.869369983673096,
|
527 |
+
"learning_rate": 1.1020177413231334e-06,
|
528 |
+
"loss": 16.1792,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.03955835534782903,
|
533 |
+
"grad_norm": 4.059152126312256,
|
534 |
+
"learning_rate": 1.0305368692688175e-06,
|
535 |
+
"loss": 18.025,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.040100250626566414,
|
540 |
+
"grad_norm": 6.198925971984863,
|
541 |
+
"learning_rate": 9.608463116858544e-07,
|
542 |
+
"loss": 17.3643,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.0406421459053038,
|
547 |
+
"grad_norm": 4.602997303009033,
|
548 |
+
"learning_rate": 8.930309757836517e-07,
|
549 |
+
"loss": 18.4931,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.04118404118404118,
|
554 |
+
"grad_norm": 5.112064838409424,
|
555 |
+
"learning_rate": 8.271734841028553e-07,
|
556 |
+
"loss": 18.2432,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.04172593646277857,
|
561 |
+
"grad_norm": 5.037693977355957,
|
562 |
+
"learning_rate": 7.633540738525066e-07,
|
563 |
+
"loss": 19.7166,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.04226783174151595,
|
568 |
+
"grad_norm": 6.0072550773620605,
|
569 |
+
"learning_rate": 7.016504991533727e-07,
|
570 |
+
"loss": 19.2431,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.04280972702025334,
|
575 |
+
"grad_norm": 5.383151054382324,
|
576 |
+
"learning_rate": 6.421379363065142e-07,
|
577 |
+
"loss": 19.4844,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.04335162229899072,
|
582 |
+
"grad_norm": 6.218992233276367,
|
583 |
+
"learning_rate": 5.848888922025553e-07,
|
584 |
+
"loss": 18.2424,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.0438935175777281,
|
589 |
+
"grad_norm": 5.023440837860107,
|
590 |
+
"learning_rate": 5.299731159831953e-07,
|
591 |
+
"loss": 18.9336,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.04443541285646549,
|
596 |
+
"grad_norm": 5.840432167053223,
|
597 |
+
"learning_rate": 4.774575140626317e-07,
|
598 |
+
"loss": 18.8547,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.04497730813520287,
|
603 |
+
"grad_norm": 6.296828269958496,
|
604 |
+
"learning_rate": 4.27406068612396e-07,
|
605 |
+
"loss": 20.1747,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.04551920341394026,
|
610 |
+
"grad_norm": 6.640228748321533,
|
611 |
+
"learning_rate": 3.798797596089351e-07,
|
612 |
+
"loss": 20.2483,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.04606109869267764,
|
617 |
+
"grad_norm": 7.213305950164795,
|
618 |
+
"learning_rate": 3.3493649053890325e-07,
|
619 |
+
"loss": 21.2069,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.04660299397141503,
|
624 |
+
"grad_norm": 6.3729567527771,
|
625 |
+
"learning_rate": 2.9263101785268253e-07,
|
626 |
+
"loss": 19.7627,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.04714488925015241,
|
631 |
+
"grad_norm": 7.3160600662231445,
|
632 |
+
"learning_rate": 2.53014884252083e-07,
|
633 |
+
"loss": 20.9435,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.04768678452888979,
|
638 |
+
"grad_norm": 7.332363605499268,
|
639 |
+
"learning_rate": 2.1613635589349756e-07,
|
640 |
+
"loss": 20.6377,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.04822867980762718,
|
645 |
+
"grad_norm": 7.867956161499023,
|
646 |
+
"learning_rate": 1.8204036358303173e-07,
|
647 |
+
"loss": 20.0944,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.04877057508636456,
|
652 |
+
"grad_norm": 7.888767242431641,
|
653 |
+
"learning_rate": 1.507684480352292e-07,
|
654 |
+
"loss": 22.6835,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.049312470365101946,
|
659 |
+
"grad_norm": 9.607979774475098,
|
660 |
+
"learning_rate": 1.223587092621162e-07,
|
661 |
+
"loss": 22.9416,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.04985436564383933,
|
666 |
+
"grad_norm": 8.894455909729004,
|
667 |
+
"learning_rate": 9.684576015420277e-08,
|
668 |
+
"loss": 24.3503,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.050396260922576715,
|
673 |
+
"grad_norm": 8.218143463134766,
|
674 |
+
"learning_rate": 7.426068431000883e-08,
|
675 |
+
"loss": 23.8572,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.050938156201314096,
|
680 |
+
"grad_norm": 9.763501167297363,
|
681 |
+
"learning_rate": 5.463099816548578e-08,
|
682 |
+
"loss": 25.768,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.05148005148005148,
|
687 |
+
"grad_norm": 10.202559471130371,
|
688 |
+
"learning_rate": 3.798061746947995e-08,
|
689 |
+
"loss": 26.5671,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.052021946758788865,
|
694 |
+
"grad_norm": 10.504480361938477,
|
695 |
+
"learning_rate": 2.4329828146074096e-08,
|
696 |
+
"loss": 25.8313,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.052563842037526246,
|
701 |
+
"grad_norm": 11.200603485107422,
|
702 |
+
"learning_rate": 1.3695261579316776e-08,
|
703 |
+
"loss": 27.4676,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.05310573731626363,
|
708 |
+
"grad_norm": 10.476430892944336,
|
709 |
+
"learning_rate": 6.089874350439507e-09,
|
710 |
+
"loss": 29.916,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.053647632595001014,
|
715 |
+
"grad_norm": 13.919726371765137,
|
716 |
+
"learning_rate": 1.5229324522605949e-09,
|
717 |
+
"loss": 35.1479,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.0541895278737384,
|
722 |
+
"grad_norm": 17.542753219604492,
|
723 |
+
"learning_rate": 0.0,
|
724 |
+
"loss": 38.8144,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.0541895278737384,
|
729 |
+
"eval_loss": 2.4464058876037598,
|
730 |
+
"eval_runtime": 357.9028,
|
731 |
+
"eval_samples_per_second": 8.684,
|
732 |
+
"eval_steps_per_second": 2.171,
|
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": 2.5486537298804736e+17,
|
763 |
"train_batch_size": 4,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|