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 295488936
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4076a7433fb71566cd01561db05d173d8259527bd856f4ceea8200eacf7fb33
|
3 |
size 295488936
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 591203178
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8436b47d3f578e383a50f394f82c5f7b94dacb9428db0bb66157dd27034f6c5
|
3 |
size 591203178
|
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 sha256:41c7e98cf7f462669215a7e97e11b44079c2937832140a08756465981dfad2c0
|
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": 0.
|
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": 35.402,
|
374 |
"eval_steps_per_second": 4.487,
|
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": 0.6673134565353394,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.333889816360601,
|
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": 35.402,
|
374 |
"eval_steps_per_second": 4.487,
|
375 |
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.17028380634390652,
|
379 |
+
"grad_norm": 2.774435043334961,
|
380 |
+
"learning_rate": 3.969463130731183e-06,
|
381 |
+
"loss": 0.5446,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.17362270450751252,
|
386 |
+
"grad_norm": 3.7148523330688477,
|
387 |
+
"learning_rate": 3.8772424536302565e-06,
|
388 |
+
"loss": 0.5936,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.17696160267111852,
|
393 |
+
"grad_norm": 3.6507351398468018,
|
394 |
+
"learning_rate": 3.782248193514766e-06,
|
395 |
+
"loss": 0.7174,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.18030050083472454,
|
400 |
+
"grad_norm": 3.6278743743896484,
|
401 |
+
"learning_rate": 3.684671656182497e-06,
|
402 |
+
"loss": 0.6394,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.18363939899833054,
|
407 |
+
"grad_norm": 3.270397186279297,
|
408 |
+
"learning_rate": 3.5847093477938955e-06,
|
409 |
+
"loss": 0.6554,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.18697829716193656,
|
414 |
+
"grad_norm": 2.640061140060425,
|
415 |
+
"learning_rate": 3.4825625791348093e-06,
|
416 |
+
"loss": 0.6313,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.19031719532554256,
|
421 |
+
"grad_norm": 2.5344226360321045,
|
422 |
+
"learning_rate": 3.3784370602033572e-06,
|
423 |
+
"loss": 0.6616,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.19365609348914858,
|
428 |
+
"grad_norm": 1.8079237937927246,
|
429 |
+
"learning_rate": 3.272542485937369e-06,
|
430 |
+
"loss": 0.6266,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.19699499165275458,
|
435 |
+
"grad_norm": 1.5996860265731812,
|
436 |
+
"learning_rate": 3.165092113916688e-06,
|
437 |
+
"loss": 0.6096,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.2003338898163606,
|
442 |
+
"grad_norm": 1.3042566776275635,
|
443 |
+
"learning_rate": 3.056302334890786e-06,
|
444 |
+
"loss": 0.6548,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.2036727879799666,
|
449 |
+
"grad_norm": 1.1529649496078491,
|
450 |
+
"learning_rate": 2.946392236996592e-06,
|
451 |
+
"loss": 0.6394,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.20701168614357263,
|
456 |
+
"grad_norm": 1.0117923021316528,
|
457 |
+
"learning_rate": 2.835583164544139e-06,
|
458 |
+
"loss": 0.6212,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.21035058430717862,
|
463 |
+
"grad_norm": 0.8776710033416748,
|
464 |
+
"learning_rate": 2.724098272258584e-06,
|
465 |
+
"loss": 0.5597,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.21368948247078465,
|
470 |
+
"grad_norm": 0.9580402970314026,
|
471 |
+
"learning_rate": 2.6121620758762877e-06,
|
472 |
+
"loss": 0.6268,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.21702838063439064,
|
477 |
+
"grad_norm": 0.9075307250022888,
|
478 |
+
"learning_rate": 2.5e-06,
|
479 |
+
"loss": 0.5357,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.22036727879799667,
|
484 |
+
"grad_norm": 0.9319755434989929,
|
485 |
+
"learning_rate": 2.3878379241237136e-06,
|
486 |
+
"loss": 0.5899,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.22370617696160267,
|
491 |
+
"grad_norm": 0.9590993523597717,
|
492 |
+
"learning_rate": 2.2759017277414165e-06,
|
493 |
+
"loss": 0.618,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.2270450751252087,
|
498 |
+
"grad_norm": 1.0425666570663452,
|
499 |
+
"learning_rate": 2.1644168354558623e-06,
|
500 |
+
"loss": 0.5349,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.2303839732888147,
|
505 |
+
"grad_norm": 0.9576693177223206,
|
506 |
+
"learning_rate": 2.053607763003409e-06,
|
507 |
+
"loss": 0.5221,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.2337228714524207,
|
512 |
+
"grad_norm": 0.8880669474601746,
|
513 |
+
"learning_rate": 1.9436976651092143e-06,
|
514 |
+
"loss": 0.493,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.2370617696160267,
|
519 |
+
"grad_norm": 1.1609593629837036,
|
520 |
+
"learning_rate": 1.8349078860833125e-06,
|
521 |
+
"loss": 0.62,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.24040066777963273,
|
526 |
+
"grad_norm": 1.0580207109451294,
|
527 |
+
"learning_rate": 1.7274575140626318e-06,
|
528 |
+
"loss": 0.5414,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.24373956594323873,
|
533 |
+
"grad_norm": 0.9047161340713501,
|
534 |
+
"learning_rate": 1.6215629397966432e-06,
|
535 |
+
"loss": 0.4679,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.24707846410684475,
|
540 |
+
"grad_norm": 1.0645842552185059,
|
541 |
+
"learning_rate": 1.5174374208651913e-06,
|
542 |
+
"loss": 0.5592,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.25041736227045075,
|
547 |
+
"grad_norm": 1.0351444482803345,
|
548 |
+
"learning_rate": 1.415290652206105e-06,
|
549 |
+
"loss": 0.4938,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.25375626043405675,
|
554 |
+
"grad_norm": 1.0303648710250854,
|
555 |
+
"learning_rate": 1.3153283438175036e-06,
|
556 |
+
"loss": 0.5191,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.2570951585976628,
|
561 |
+
"grad_norm": 1.0689729452133179,
|
562 |
+
"learning_rate": 1.217751806485235e-06,
|
563 |
+
"loss": 0.5241,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.2604340567612688,
|
568 |
+
"grad_norm": 1.0949710607528687,
|
569 |
+
"learning_rate": 1.122757546369744e-06,
|
570 |
+
"loss": 0.5091,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.2637729549248748,
|
575 |
+
"grad_norm": 1.066139578819275,
|
576 |
+
"learning_rate": 1.0305368692688175e-06,
|
577 |
+
"loss": 0.5245,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.2671118530884808,
|
582 |
+
"grad_norm": 1.0166308879852295,
|
583 |
+
"learning_rate": 9.412754953531664e-07,
|
584 |
+
"loss": 0.4759,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.2704507512520868,
|
589 |
+
"grad_norm": 1.113553524017334,
|
590 |
+
"learning_rate": 8.551531851507186e-07,
|
591 |
+
"loss": 0.4975,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.27378964941569284,
|
596 |
+
"grad_norm": 1.1330246925354004,
|
597 |
+
"learning_rate": 7.723433775328385e-07,
|
598 |
+
"loss": 0.5459,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.27712854757929883,
|
603 |
+
"grad_norm": 1.0714497566223145,
|
604 |
+
"learning_rate": 6.930128404315214e-07,
|
605 |
+
"loss": 0.4841,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.28046744574290483,
|
610 |
+
"grad_norm": 1.0576684474945068,
|
611 |
+
"learning_rate": 6.17321334990973e-07,
|
612 |
+
"loss": 0.4325,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.2838063439065108,
|
617 |
+
"grad_norm": 1.2464218139648438,
|
618 |
+
"learning_rate": 5.454212938299256e-07,
|
619 |
+
"loss": 0.5759,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.2871452420701169,
|
624 |
+
"grad_norm": 1.2016359567642212,
|
625 |
+
"learning_rate": 4.774575140626317e-07,
|
626 |
+
"loss": 0.4957,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.2904841402337229,
|
631 |
+
"grad_norm": 1.2413355112075806,
|
632 |
+
"learning_rate": 4.1356686569674344e-07,
|
633 |
+
"loss": 0.5146,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.2938230383973289,
|
638 |
+
"grad_norm": 1.3268682956695557,
|
639 |
+
"learning_rate": 3.538780159953348e-07,
|
640 |
+
"loss": 0.6438,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.29716193656093487,
|
645 |
+
"grad_norm": 1.2803572416305542,
|
646 |
+
"learning_rate": 2.98511170358155e-07,
|
647 |
+
"loss": 0.5471,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.3005008347245409,
|
652 |
+
"grad_norm": 1.4874416589736938,
|
653 |
+
"learning_rate": 2.4757783024395244e-07,
|
654 |
+
"loss": 0.548,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.3038397328881469,
|
659 |
+
"grad_norm": 1.5271040201187134,
|
660 |
+
"learning_rate": 2.0118056862137358e-07,
|
661 |
+
"loss": 0.5197,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.3071786310517529,
|
666 |
+
"grad_norm": 1.6254510879516602,
|
667 |
+
"learning_rate": 1.59412823400657e-07,
|
668 |
+
"loss": 0.6227,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.3105175292153589,
|
673 |
+
"grad_norm": 1.617385983467102,
|
674 |
+
"learning_rate": 1.223587092621162e-07,
|
675 |
+
"loss": 0.5972,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.31385642737896496,
|
680 |
+
"grad_norm": 1.9136462211608887,
|
681 |
+
"learning_rate": 9.00928482603669e-08,
|
682 |
+
"loss": 0.7396,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.31719532554257096,
|
687 |
+
"grad_norm": 2.216195821762085,
|
688 |
+
"learning_rate": 6.268021954544095e-08,
|
689 |
+
"loss": 0.6338,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.32053422370617696,
|
694 |
+
"grad_norm": 2.8479862213134766,
|
695 |
+
"learning_rate": 4.017602850342584e-08,
|
696 |
+
"loss": 0.725,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.32387312186978295,
|
701 |
+
"grad_norm": 4.363030910491943,
|
702 |
+
"learning_rate": 2.262559558016325e-08,
|
703 |
+
"loss": 1.1272,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.327212020033389,
|
708 |
+
"grad_norm": 8.434501647949219,
|
709 |
+
"learning_rate": 1.006426501190233e-08,
|
710 |
+
"loss": 1.9515,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.330550918196995,
|
715 |
+
"grad_norm": 16.16083335876465,
|
716 |
+
"learning_rate": 2.5173336467135266e-09,
|
717 |
+
"loss": 3.21,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.333889816360601,
|
722 |
+
"grad_norm": 50.90562057495117,
|
723 |
+
"learning_rate": 0.0,
|
724 |
+
"loss": 7.3095,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.333889816360601,
|
729 |
+
"eval_loss": 0.6673134565353394,
|
730 |
+
"eval_runtime": 14.2635,
|
731 |
+
"eval_samples_per_second": 35.405,
|
732 |
+
"eval_steps_per_second": 4.487,
|
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": 2.728250925121536e+16,
|
763 |
"train_batch_size": 8,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|