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 sha256:646b364c7d4b816341c5736f0be61070471dce6b519c3f2c3092aa6ba655e3e3
|
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 sha256:6cdc11e01f89220aeb85e1610ade8369bc7ff68231fb4f58be93cd45eff1b41f
|
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:a7f190aed2ed983274d65d9fdfeaf963f11d23fbe04e9143be95ed2df679235a
|
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": 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": 8.772,
|
374 |
"eval_steps_per_second": 2.206,
|
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": 1.1555566787719727,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.33641715727502103,
|
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": 8.772,
|
374 |
"eval_steps_per_second": 2.206,
|
375 |
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.17157275021026072,
|
379 |
+
"grad_norm": 5.8676066398620605,
|
380 |
+
"learning_rate": 2.847932752400164e-06,
|
381 |
+
"loss": 4.9187,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.17493692178301093,
|
386 |
+
"grad_norm": 6.816829681396484,
|
387 |
+
"learning_rate": 2.761321158169134e-06,
|
388 |
+
"loss": 5.2629,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.17830109335576114,
|
393 |
+
"grad_norm": 7.70700740814209,
|
394 |
+
"learning_rate": 2.6743911843603134e-06,
|
395 |
+
"loss": 6.4171,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.18166526492851134,
|
400 |
+
"grad_norm": 7.824767589569092,
|
401 |
+
"learning_rate": 2.587248741756253e-06,
|
402 |
+
"loss": 6.0923,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.18502943650126155,
|
407 |
+
"grad_norm": 8.090392112731934,
|
408 |
+
"learning_rate": 2.5e-06,
|
409 |
+
"loss": 6.6339,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.1883936080740118,
|
414 |
+
"grad_norm": 8.604589462280273,
|
415 |
+
"learning_rate": 2.4127512582437486e-06,
|
416 |
+
"loss": 6.1605,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.191757779646762,
|
421 |
+
"grad_norm": 8.222731590270996,
|
422 |
+
"learning_rate": 2.325608815639687e-06,
|
423 |
+
"loss": 6.1605,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.1951219512195122,
|
428 |
+
"grad_norm": 10.205119132995605,
|
429 |
+
"learning_rate": 2.238678841830867e-06,
|
430 |
+
"loss": 7.0509,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.1984861227922624,
|
435 |
+
"grad_norm": 10.104853630065918,
|
436 |
+
"learning_rate": 2.1520672475998374e-06,
|
437 |
+
"loss": 6.9668,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.20185029436501262,
|
442 |
+
"grad_norm": 10.174232482910156,
|
443 |
+
"learning_rate": 2.0658795558326745e-06,
|
444 |
+
"loss": 7.273,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.20521446593776282,
|
449 |
+
"grad_norm": 11.0505952835083,
|
450 |
+
"learning_rate": 1.9802207729556023e-06,
|
451 |
+
"loss": 7.1026,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.20857863751051303,
|
456 |
+
"grad_norm": 10.55052661895752,
|
457 |
+
"learning_rate": 1.895195261000831e-06,
|
458 |
+
"loss": 7.1445,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.21194280908326324,
|
463 |
+
"grad_norm": 10.593603134155273,
|
464 |
+
"learning_rate": 1.8109066104575023e-06,
|
465 |
+
"loss": 6.6755,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.21530698065601345,
|
470 |
+
"grad_norm": 10.96327018737793,
|
471 |
+
"learning_rate": 1.7274575140626318e-06,
|
472 |
+
"loss": 7.2853,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.21867115222876365,
|
477 |
+
"grad_norm": 10.896140098571777,
|
478 |
+
"learning_rate": 1.6449496416858285e-06,
|
479 |
+
"loss": 6.8225,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.2220353238015139,
|
484 |
+
"grad_norm": 10.829171180725098,
|
485 |
+
"learning_rate": 1.56348351646022e-06,
|
486 |
+
"loss": 7.2135,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.2253994953742641,
|
491 |
+
"grad_norm": 12.62612247467041,
|
492 |
+
"learning_rate": 1.4831583923105e-06,
|
493 |
+
"loss": 8.1609,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.2287636669470143,
|
498 |
+
"grad_norm": 12.466354370117188,
|
499 |
+
"learning_rate": 1.4040721330273063e-06,
|
500 |
+
"loss": 7.5541,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.2321278385197645,
|
505 |
+
"grad_norm": 12.358624458312988,
|
506 |
+
"learning_rate": 1.3263210930352737e-06,
|
507 |
+
"loss": 8.0098,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.23549201009251472,
|
512 |
+
"grad_norm": 13.029424667358398,
|
513 |
+
"learning_rate": 1.2500000000000007e-06,
|
514 |
+
"loss": 7.1127,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.23885618166526493,
|
519 |
+
"grad_norm": 12.36991024017334,
|
520 |
+
"learning_rate": 1.1752018394169882e-06,
|
521 |
+
"loss": 7.7343,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.24222035323801513,
|
526 |
+
"grad_norm": 14.253127098083496,
|
527 |
+
"learning_rate": 1.1020177413231334e-06,
|
528 |
+
"loss": 8.1448,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.24558452481076534,
|
533 |
+
"grad_norm": 14.902377128601074,
|
534 |
+
"learning_rate": 1.0305368692688175e-06,
|
535 |
+
"loss": 8.5399,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.24894869638351555,
|
540 |
+
"grad_norm": 13.825746536254883,
|
541 |
+
"learning_rate": 9.608463116858544e-07,
|
542 |
+
"loss": 8.2775,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.2523128679562658,
|
547 |
+
"grad_norm": 14.28534984588623,
|
548 |
+
"learning_rate": 8.930309757836517e-07,
|
549 |
+
"loss": 8.3315,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.255677039529016,
|
554 |
+
"grad_norm": 14.561500549316406,
|
555 |
+
"learning_rate": 8.271734841028553e-07,
|
556 |
+
"loss": 8.2985,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.2590412111017662,
|
561 |
+
"grad_norm": 16.219362258911133,
|
562 |
+
"learning_rate": 7.633540738525066e-07,
|
563 |
+
"loss": 9.6124,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.2624053826745164,
|
568 |
+
"grad_norm": 16.25676155090332,
|
569 |
+
"learning_rate": 7.016504991533727e-07,
|
570 |
+
"loss": 9.5415,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.2657695542472666,
|
575 |
+
"grad_norm": 15.985312461853027,
|
576 |
+
"learning_rate": 6.421379363065142e-07,
|
577 |
+
"loss": 8.8435,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.2691337258200168,
|
582 |
+
"grad_norm": 17.515792846679688,
|
583 |
+
"learning_rate": 5.848888922025553e-07,
|
584 |
+
"loss": 9.9004,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.27249789739276703,
|
589 |
+
"grad_norm": 18.003767013549805,
|
590 |
+
"learning_rate": 5.299731159831953e-07,
|
591 |
+
"loss": 9.6217,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.27586206896551724,
|
596 |
+
"grad_norm": 17.7401180267334,
|
597 |
+
"learning_rate": 4.774575140626317e-07,
|
598 |
+
"loss": 10.091,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.27922624053826745,
|
603 |
+
"grad_norm": 18.93708038330078,
|
604 |
+
"learning_rate": 4.27406068612396e-07,
|
605 |
+
"loss": 10.3955,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.28259041211101765,
|
610 |
+
"grad_norm": 20.82859992980957,
|
611 |
+
"learning_rate": 3.798797596089351e-07,
|
612 |
+
"loss": 10.6501,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.28595458368376786,
|
617 |
+
"grad_norm": 20.40983009338379,
|
618 |
+
"learning_rate": 3.3493649053890325e-07,
|
619 |
+
"loss": 11.2433,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.28931875525651807,
|
624 |
+
"grad_norm": 20.346174240112305,
|
625 |
+
"learning_rate": 2.9263101785268253e-07,
|
626 |
+
"loss": 11.8944,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.2926829268292683,
|
631 |
+
"grad_norm": 21.919641494750977,
|
632 |
+
"learning_rate": 2.53014884252083e-07,
|
633 |
+
"loss": 11.9275,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.2960470984020185,
|
638 |
+
"grad_norm": 21.59522819519043,
|
639 |
+
"learning_rate": 2.1613635589349756e-07,
|
640 |
+
"loss": 11.1671,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.2994112699747687,
|
645 |
+
"grad_norm": 23.782527923583984,
|
646 |
+
"learning_rate": 1.8204036358303173e-07,
|
647 |
+
"loss": 13.3871,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.3027754415475189,
|
652 |
+
"grad_norm": 22.470487594604492,
|
653 |
+
"learning_rate": 1.507684480352292e-07,
|
654 |
+
"loss": 12.2082,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.30613961312026916,
|
659 |
+
"grad_norm": 22.669078826904297,
|
660 |
+
"learning_rate": 1.223587092621162e-07,
|
661 |
+
"loss": 12.4097,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.30950378469301937,
|
666 |
+
"grad_norm": 23.26660919189453,
|
667 |
+
"learning_rate": 9.684576015420277e-08,
|
668 |
+
"loss": 13.0533,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.3128679562657696,
|
673 |
+
"grad_norm": 25.632230758666992,
|
674 |
+
"learning_rate": 7.426068431000883e-08,
|
675 |
+
"loss": 14.406,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.3162321278385198,
|
680 |
+
"grad_norm": 23.212289810180664,
|
681 |
+
"learning_rate": 5.463099816548578e-08,
|
682 |
+
"loss": 12.672,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.31959629941127,
|
687 |
+
"grad_norm": 26.72962188720703,
|
688 |
+
"learning_rate": 3.798061746947995e-08,
|
689 |
+
"loss": 14.1783,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.3229604709840202,
|
694 |
+
"grad_norm": 26.62249183654785,
|
695 |
+
"learning_rate": 2.4329828146074096e-08,
|
696 |
+
"loss": 14.9785,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.3263246425567704,
|
701 |
+
"grad_norm": 24.253948211669922,
|
702 |
+
"learning_rate": 1.3695261579316776e-08,
|
703 |
+
"loss": 13.4523,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.3296888141295206,
|
708 |
+
"grad_norm": 27.36448860168457,
|
709 |
+
"learning_rate": 6.089874350439507e-09,
|
710 |
+
"loss": 15.0062,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.3330529857022708,
|
715 |
+
"grad_norm": 31.766481399536133,
|
716 |
+
"learning_rate": 1.5229324522605949e-09,
|
717 |
+
"loss": 15.6437,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.33641715727502103,
|
722 |
+
"grad_norm": 31.894515991210938,
|
723 |
+
"learning_rate": 0.0,
|
724 |
+
"loss": 17.4361,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.33641715727502103,
|
729 |
+
"eval_loss": 1.1555566787719727,
|
730 |
+
"eval_runtime": 57.1133,
|
731 |
+
"eval_samples_per_second": 8.772,
|
732 |
+
"eval_steps_per_second": 2.206,
|
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": 2.53913198493696e+17,
|
763 |
"train_batch_size": 4,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|