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 800116456
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7a169b30226ff8c374ebbde4bf9195d11864eee6a7a9c5478d095aae4b2a8a3
|
3 |
size 800116456
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1600457770
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80c3ae06b7e3627c378467a4440ab3c284f0f07a6e162298c79a89700a475352
|
3 |
size 1600457770
|
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:bfd666132be82d00db6f4728f35d03040dc7ce6a03c9d33355082c1b93e7132d
|
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": 11.099,
|
374 |
"eval_steps_per_second": 1.429,
|
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": 1.432803750038147,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.8333333333333334,
|
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": 11.099,
|
374 |
"eval_steps_per_second": 1.429,
|
375 |
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.425,
|
379 |
+
"grad_norm": 2.499925136566162,
|
380 |
+
"learning_rate": 3.969463130731183e-06,
|
381 |
+
"loss": 1.4591,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.43333333333333335,
|
386 |
+
"grad_norm": 2.638784170150757,
|
387 |
+
"learning_rate": 3.8772424536302565e-06,
|
388 |
+
"loss": 1.3876,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.44166666666666665,
|
393 |
+
"grad_norm": 2.7035515308380127,
|
394 |
+
"learning_rate": 3.782248193514766e-06,
|
395 |
+
"loss": 1.4014,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.45,
|
400 |
+
"grad_norm": 3.1544301509857178,
|
401 |
+
"learning_rate": 3.684671656182497e-06,
|
402 |
+
"loss": 1.3941,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.4583333333333333,
|
407 |
+
"grad_norm": 2.7896924018859863,
|
408 |
+
"learning_rate": 3.5847093477938955e-06,
|
409 |
+
"loss": 1.3751,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.4666666666666667,
|
414 |
+
"grad_norm": 3.281968832015991,
|
415 |
+
"learning_rate": 3.4825625791348093e-06,
|
416 |
+
"loss": 1.2745,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.475,
|
421 |
+
"grad_norm": 3.6155593395233154,
|
422 |
+
"learning_rate": 3.3784370602033572e-06,
|
423 |
+
"loss": 1.1763,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.48333333333333334,
|
428 |
+
"grad_norm": 4.625380039215088,
|
429 |
+
"learning_rate": 3.272542485937369e-06,
|
430 |
+
"loss": 1.407,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.49166666666666664,
|
435 |
+
"grad_norm": 2.164090633392334,
|
436 |
+
"learning_rate": 3.165092113916688e-06,
|
437 |
+
"loss": 1.6163,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.5,
|
442 |
+
"grad_norm": 2.391841173171997,
|
443 |
+
"learning_rate": 3.056302334890786e-06,
|
444 |
+
"loss": 1.6369,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.5083333333333333,
|
449 |
+
"grad_norm": 2.4509174823760986,
|
450 |
+
"learning_rate": 2.946392236996592e-06,
|
451 |
+
"loss": 1.6073,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.5166666666666667,
|
456 |
+
"grad_norm": 2.255946397781372,
|
457 |
+
"learning_rate": 2.835583164544139e-06,
|
458 |
+
"loss": 1.5379,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.525,
|
463 |
+
"grad_norm": 2.5381131172180176,
|
464 |
+
"learning_rate": 2.724098272258584e-06,
|
465 |
+
"loss": 1.5004,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.5333333333333333,
|
470 |
+
"grad_norm": 2.5868146419525146,
|
471 |
+
"learning_rate": 2.6121620758762877e-06,
|
472 |
+
"loss": 1.606,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.5416666666666666,
|
477 |
+
"grad_norm": 2.215385675430298,
|
478 |
+
"learning_rate": 2.5e-06,
|
479 |
+
"loss": 1.4491,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.55,
|
484 |
+
"grad_norm": 2.145747423171997,
|
485 |
+
"learning_rate": 2.3878379241237136e-06,
|
486 |
+
"loss": 1.4185,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.5583333333333333,
|
491 |
+
"grad_norm": 2.2999093532562256,
|
492 |
+
"learning_rate": 2.2759017277414165e-06,
|
493 |
+
"loss": 1.5598,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.5666666666666667,
|
498 |
+
"grad_norm": 1.975134253501892,
|
499 |
+
"learning_rate": 2.1644168354558623e-06,
|
500 |
+
"loss": 1.4346,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.575,
|
505 |
+
"grad_norm": 2.072296380996704,
|
506 |
+
"learning_rate": 2.053607763003409e-06,
|
507 |
+
"loss": 1.4922,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.5833333333333334,
|
512 |
+
"grad_norm": 2.083237409591675,
|
513 |
+
"learning_rate": 1.9436976651092143e-06,
|
514 |
+
"loss": 1.5104,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.5916666666666667,
|
519 |
+
"grad_norm": 2.030505418777466,
|
520 |
+
"learning_rate": 1.8349078860833125e-06,
|
521 |
+
"loss": 1.5242,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.6,
|
526 |
+
"grad_norm": 2.030874013900757,
|
527 |
+
"learning_rate": 1.7274575140626318e-06,
|
528 |
+
"loss": 1.4069,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.6083333333333333,
|
533 |
+
"grad_norm": 2.0785183906555176,
|
534 |
+
"learning_rate": 1.6215629397966432e-06,
|
535 |
+
"loss": 1.4527,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.6166666666666667,
|
540 |
+
"grad_norm": 2.0005362033843994,
|
541 |
+
"learning_rate": 1.5174374208651913e-06,
|
542 |
+
"loss": 1.3144,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.625,
|
547 |
+
"grad_norm": 2.1211068630218506,
|
548 |
+
"learning_rate": 1.415290652206105e-06,
|
549 |
+
"loss": 1.3169,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.6333333333333333,
|
554 |
+
"grad_norm": 2.2621371746063232,
|
555 |
+
"learning_rate": 1.3153283438175036e-06,
|
556 |
+
"loss": 1.366,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.6416666666666667,
|
561 |
+
"grad_norm": 2.462306022644043,
|
562 |
+
"learning_rate": 1.217751806485235e-06,
|
563 |
+
"loss": 1.4933,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.65,
|
568 |
+
"grad_norm": 2.303489923477173,
|
569 |
+
"learning_rate": 1.122757546369744e-06,
|
570 |
+
"loss": 1.3751,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.6583333333333333,
|
575 |
+
"grad_norm": 2.918320655822754,
|
576 |
+
"learning_rate": 1.0305368692688175e-06,
|
577 |
+
"loss": 1.3268,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.6666666666666666,
|
582 |
+
"grad_norm": 2.8498406410217285,
|
583 |
+
"learning_rate": 9.412754953531664e-07,
|
584 |
+
"loss": 1.3434,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.675,
|
589 |
+
"grad_norm": 2.950571060180664,
|
590 |
+
"learning_rate": 8.551531851507186e-07,
|
591 |
+
"loss": 1.4753,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.6833333333333333,
|
596 |
+
"grad_norm": 2.9567456245422363,
|
597 |
+
"learning_rate": 7.723433775328385e-07,
|
598 |
+
"loss": 1.3351,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.6916666666666667,
|
603 |
+
"grad_norm": 3.1769864559173584,
|
604 |
+
"learning_rate": 6.930128404315214e-07,
|
605 |
+
"loss": 1.2743,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.7,
|
610 |
+
"grad_norm": 3.6151397228240967,
|
611 |
+
"learning_rate": 6.17321334990973e-07,
|
612 |
+
"loss": 1.252,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.7083333333333334,
|
617 |
+
"grad_norm": 3.4306578636169434,
|
618 |
+
"learning_rate": 5.454212938299256e-07,
|
619 |
+
"loss": 1.3465,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.7166666666666667,
|
624 |
+
"grad_norm": 4.3413190841674805,
|
625 |
+
"learning_rate": 4.774575140626317e-07,
|
626 |
+
"loss": 1.3886,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.725,
|
631 |
+
"grad_norm": 4.907854080200195,
|
632 |
+
"learning_rate": 4.1356686569674344e-07,
|
633 |
+
"loss": 1.3077,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.7333333333333333,
|
638 |
+
"grad_norm": 1.6578599214553833,
|
639 |
+
"learning_rate": 3.538780159953348e-07,
|
640 |
+
"loss": 1.4823,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.7416666666666667,
|
645 |
+
"grad_norm": 1.7607696056365967,
|
646 |
+
"learning_rate": 2.98511170358155e-07,
|
647 |
+
"loss": 1.463,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.75,
|
652 |
+
"grad_norm": 1.810681939125061,
|
653 |
+
"learning_rate": 2.4757783024395244e-07,
|
654 |
+
"loss": 1.5727,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.7583333333333333,
|
659 |
+
"grad_norm": 1.8448772430419922,
|
660 |
+
"learning_rate": 2.0118056862137358e-07,
|
661 |
+
"loss": 1.4929,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.7666666666666667,
|
666 |
+
"grad_norm": 1.8057886362075806,
|
667 |
+
"learning_rate": 1.59412823400657e-07,
|
668 |
+
"loss": 1.4789,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.775,
|
673 |
+
"grad_norm": 1.8964967727661133,
|
674 |
+
"learning_rate": 1.223587092621162e-07,
|
675 |
+
"loss": 1.4743,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.7833333333333333,
|
680 |
+
"grad_norm": 1.8288004398345947,
|
681 |
+
"learning_rate": 9.00928482603669e-08,
|
682 |
+
"loss": 1.551,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.7916666666666666,
|
687 |
+
"grad_norm": 1.9121664762496948,
|
688 |
+
"learning_rate": 6.268021954544095e-08,
|
689 |
+
"loss": 1.4186,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.8,
|
694 |
+
"grad_norm": 1.9532289505004883,
|
695 |
+
"learning_rate": 4.017602850342584e-08,
|
696 |
+
"loss": 1.3801,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.8083333333333333,
|
701 |
+
"grad_norm": 1.8921444416046143,
|
702 |
+
"learning_rate": 2.262559558016325e-08,
|
703 |
+
"loss": 1.4542,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.8166666666666667,
|
708 |
+
"grad_norm": 1.967811107635498,
|
709 |
+
"learning_rate": 1.006426501190233e-08,
|
710 |
+
"loss": 1.406,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.825,
|
715 |
+
"grad_norm": 1.9999773502349854,
|
716 |
+
"learning_rate": 2.5173336467135266e-09,
|
717 |
+
"loss": 1.4997,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.8333333333333334,
|
722 |
+
"grad_norm": 2.0562117099761963,
|
723 |
+
"learning_rate": 0.0,
|
724 |
+
"loss": 1.3896,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.8333333333333334,
|
729 |
+
"eval_loss": 1.432803750038147,
|
730 |
+
"eval_runtime": 18.1946,
|
731 |
+
"eval_samples_per_second": 11.102,
|
732 |
+
"eval_steps_per_second": 1.429,
|
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": 1.563282263506944e+17,
|
763 |
"train_batch_size": 8,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|