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 161714
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a626c80581d9f17e1457b1489f00b21ee0f5d7fc9a3d3c6e64a93406f13133b
|
3 |
size 161714
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 70742
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:071e1c281a247ce9c5912083854774aa0368f904b0444dccd4bfa7ece2b094ad
|
3 |
size 70742
|
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 sha256:6ac7b0f4cb3310ab958c1c49da1e16109271c65fa555c01943c9cf7356d29489
|
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": 6.
|
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": 981.686,
|
374 |
"eval_steps_per_second": 123.523,
|
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": 6.889637470245361,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.05577244841048522,
|
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": 981.686,
|
374 |
"eval_steps_per_second": 123.523,
|
375 |
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.02844394868934746,
|
379 |
+
"grad_norm": 1.3323776721954346,
|
380 |
+
"learning_rate": 3.969463130731183e-06,
|
381 |
+
"loss": 6.9062,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.029001673173452314,
|
386 |
+
"grad_norm": 1.254181981086731,
|
387 |
+
"learning_rate": 3.8772424536302565e-06,
|
388 |
+
"loss": 6.9008,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.029559397657557166,
|
393 |
+
"grad_norm": 1.3206740617752075,
|
394 |
+
"learning_rate": 3.782248193514766e-06,
|
395 |
+
"loss": 6.9099,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.03011712214166202,
|
400 |
+
"grad_norm": 1.2332712411880493,
|
401 |
+
"learning_rate": 3.684671656182497e-06,
|
402 |
+
"loss": 6.8927,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.03067484662576687,
|
407 |
+
"grad_norm": 1.178006649017334,
|
408 |
+
"learning_rate": 3.5847093477938955e-06,
|
409 |
+
"loss": 6.9219,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.031232571109871723,
|
414 |
+
"grad_norm": 1.13715660572052,
|
415 |
+
"learning_rate": 3.4825625791348093e-06,
|
416 |
+
"loss": 6.9068,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.03179029559397657,
|
421 |
+
"grad_norm": 1.5851024389266968,
|
422 |
+
"learning_rate": 3.3784370602033572e-06,
|
423 |
+
"loss": 6.8539,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.03234802007808143,
|
428 |
+
"grad_norm": 1.1820706129074097,
|
429 |
+
"learning_rate": 3.272542485937369e-06,
|
430 |
+
"loss": 6.875,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.03290574456218628,
|
435 |
+
"grad_norm": 1.1604312658309937,
|
436 |
+
"learning_rate": 3.165092113916688e-06,
|
437 |
+
"loss": 6.8862,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.03346346904629113,
|
442 |
+
"grad_norm": 1.1780774593353271,
|
443 |
+
"learning_rate": 3.056302334890786e-06,
|
444 |
+
"loss": 6.8984,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.03402119353039598,
|
449 |
+
"grad_norm": 1.1557505130767822,
|
450 |
+
"learning_rate": 2.946392236996592e-06,
|
451 |
+
"loss": 6.8954,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.03457891801450084,
|
456 |
+
"grad_norm": 1.1038789749145508,
|
457 |
+
"learning_rate": 2.835583164544139e-06,
|
458 |
+
"loss": 6.9242,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.03513664249860569,
|
463 |
+
"grad_norm": 1.0958284139633179,
|
464 |
+
"learning_rate": 2.724098272258584e-06,
|
465 |
+
"loss": 6.8882,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.03569436698271054,
|
470 |
+
"grad_norm": 1.1988102197647095,
|
471 |
+
"learning_rate": 2.6121620758762877e-06,
|
472 |
+
"loss": 6.8943,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.03625209146681539,
|
477 |
+
"grad_norm": 1.1466842889785767,
|
478 |
+
"learning_rate": 2.5e-06,
|
479 |
+
"loss": 6.909,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.03680981595092025,
|
484 |
+
"grad_norm": 1.2120569944381714,
|
485 |
+
"learning_rate": 2.3878379241237136e-06,
|
486 |
+
"loss": 6.8626,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.0373675404350251,
|
491 |
+
"grad_norm": 1.3618991374969482,
|
492 |
+
"learning_rate": 2.2759017277414165e-06,
|
493 |
+
"loss": 6.8536,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.03792526491912995,
|
498 |
+
"grad_norm": 1.167353868484497,
|
499 |
+
"learning_rate": 2.1644168354558623e-06,
|
500 |
+
"loss": 6.8796,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.0384829894032348,
|
505 |
+
"grad_norm": 1.0730359554290771,
|
506 |
+
"learning_rate": 2.053607763003409e-06,
|
507 |
+
"loss": 6.8989,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.03904071388733965,
|
512 |
+
"grad_norm": 1.1657218933105469,
|
513 |
+
"learning_rate": 1.9436976651092143e-06,
|
514 |
+
"loss": 6.8913,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.03959843837144451,
|
519 |
+
"grad_norm": 1.233559489250183,
|
520 |
+
"learning_rate": 1.8349078860833125e-06,
|
521 |
+
"loss": 6.8623,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.040156162855549356,
|
526 |
+
"grad_norm": 1.4005221128463745,
|
527 |
+
"learning_rate": 1.7274575140626318e-06,
|
528 |
+
"loss": 6.8556,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.04071388733965421,
|
533 |
+
"grad_norm": 1.0714030265808105,
|
534 |
+
"learning_rate": 1.6215629397966432e-06,
|
535 |
+
"loss": 6.9189,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.04127161182375906,
|
540 |
+
"grad_norm": 1.1474922895431519,
|
541 |
+
"learning_rate": 1.5174374208651913e-06,
|
542 |
+
"loss": 6.8716,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.04182933630786392,
|
547 |
+
"grad_norm": 1.104048728942871,
|
548 |
+
"learning_rate": 1.415290652206105e-06,
|
549 |
+
"loss": 6.8646,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.042387060791968766,
|
554 |
+
"grad_norm": 1.1361018419265747,
|
555 |
+
"learning_rate": 1.3153283438175036e-06,
|
556 |
+
"loss": 6.8972,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.04294478527607362,
|
561 |
+
"grad_norm": 1.131973385810852,
|
562 |
+
"learning_rate": 1.217751806485235e-06,
|
563 |
+
"loss": 6.9103,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.04350250976017847,
|
568 |
+
"grad_norm": 1.4930802583694458,
|
569 |
+
"learning_rate": 1.122757546369744e-06,
|
570 |
+
"loss": 6.858,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.044060234244283326,
|
575 |
+
"grad_norm": 1.213676929473877,
|
576 |
+
"learning_rate": 1.0305368692688175e-06,
|
577 |
+
"loss": 6.871,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.044617958728388175,
|
582 |
+
"grad_norm": 1.1692030429840088,
|
583 |
+
"learning_rate": 9.412754953531664e-07,
|
584 |
+
"loss": 6.8811,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.04517568321249303,
|
589 |
+
"grad_norm": 1.1697320938110352,
|
590 |
+
"learning_rate": 8.551531851507186e-07,
|
591 |
+
"loss": 6.8768,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.04573340769659788,
|
596 |
+
"grad_norm": 1.1767263412475586,
|
597 |
+
"learning_rate": 7.723433775328385e-07,
|
598 |
+
"loss": 6.8627,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.046291132180702736,
|
603 |
+
"grad_norm": 1.1124926805496216,
|
604 |
+
"learning_rate": 6.930128404315214e-07,
|
605 |
+
"loss": 6.8774,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.046848856664807585,
|
610 |
+
"grad_norm": 1.352464199066162,
|
611 |
+
"learning_rate": 6.17321334990973e-07,
|
612 |
+
"loss": 6.8597,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.047406581148912434,
|
617 |
+
"grad_norm": 1.3012317419052124,
|
618 |
+
"learning_rate": 5.454212938299256e-07,
|
619 |
+
"loss": 6.8635,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.04796430563301729,
|
624 |
+
"grad_norm": 1.2052788734436035,
|
625 |
+
"learning_rate": 4.774575140626317e-07,
|
626 |
+
"loss": 6.8514,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.04852203011712214,
|
631 |
+
"grad_norm": 1.200753927230835,
|
632 |
+
"learning_rate": 4.1356686569674344e-07,
|
633 |
+
"loss": 6.8585,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.049079754601226995,
|
638 |
+
"grad_norm": 1.3905110359191895,
|
639 |
+
"learning_rate": 3.538780159953348e-07,
|
640 |
+
"loss": 6.8852,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.049637479085331844,
|
645 |
+
"grad_norm": 1.1501882076263428,
|
646 |
+
"learning_rate": 2.98511170358155e-07,
|
647 |
+
"loss": 6.87,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.0501952035694367,
|
652 |
+
"grad_norm": 1.4343775510787964,
|
653 |
+
"learning_rate": 2.4757783024395244e-07,
|
654 |
+
"loss": 6.8603,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.05075292805354155,
|
659 |
+
"grad_norm": 1.1068586111068726,
|
660 |
+
"learning_rate": 2.0118056862137358e-07,
|
661 |
+
"loss": 6.9276,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.051310652537646405,
|
666 |
+
"grad_norm": 1.2128379344940186,
|
667 |
+
"learning_rate": 1.59412823400657e-07,
|
668 |
+
"loss": 6.891,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.051868377021751254,
|
673 |
+
"grad_norm": 1.271918535232544,
|
674 |
+
"learning_rate": 1.223587092621162e-07,
|
675 |
+
"loss": 6.8973,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.05242610150585611,
|
680 |
+
"grad_norm": 1.1704728603363037,
|
681 |
+
"learning_rate": 9.00928482603669e-08,
|
682 |
+
"loss": 6.8768,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.05298382598996096,
|
687 |
+
"grad_norm": 1.1624881029129028,
|
688 |
+
"learning_rate": 6.268021954544095e-08,
|
689 |
+
"loss": 6.8773,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.053541550474065815,
|
694 |
+
"grad_norm": 1.1013178825378418,
|
695 |
+
"learning_rate": 4.017602850342584e-08,
|
696 |
+
"loss": 6.8871,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.054099274958170664,
|
701 |
+
"grad_norm": 1.1644474267959595,
|
702 |
+
"learning_rate": 2.262559558016325e-08,
|
703 |
+
"loss": 6.9111,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.05465699944227551,
|
708 |
+
"grad_norm": 1.0760912895202637,
|
709 |
+
"learning_rate": 1.006426501190233e-08,
|
710 |
+
"loss": 6.8965,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.05521472392638037,
|
715 |
+
"grad_norm": 1.120246171951294,
|
716 |
+
"learning_rate": 2.5173336467135266e-09,
|
717 |
+
"loss": 6.8703,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.05577244841048522,
|
722 |
+
"grad_norm": 1.1762772798538208,
|
723 |
+
"learning_rate": 0.0,
|
724 |
+
"loss": 6.8797,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.05577244841048522,
|
729 |
+
"eval_loss": 6.889637470245361,
|
730 |
+
"eval_runtime": 0.787,
|
731 |
+
"eval_samples_per_second": 959.313,
|
732 |
+
"eval_steps_per_second": 120.708,
|
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": 263666073600.0,
|
763 |
"train_batch_size": 8,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|