nttx commited on
Commit
b3222f3
·
verified ·
1 Parent(s): 94c97d5

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 sha256:24c6d28c51e810c1d5b63d910febaf9507a25d4f15941a752c3af74dbadc4c3e
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c0bb592bda9cb2c46ec6da47b5adaa66da41732ec2d8c60e8de12a37566ae6b
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abddc59c93e369304fb269a99ba5002159f7d91cbc023ff6402e3130014f7bc8
3
  size 278249554
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58801b3879ea9659a1361e631e085c6f40564719c65895b21096db37795b2113
3
  size 278249554
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43666a87aff748af64b5844edfdbe970e4e9982aa9aabc765b7a0ffa071e20e3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8a50273e2c0884ecb0d7fb1230a0b527160c52eb1c35e2c19daa1b836d36278
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79f5b4ba066d00b62be68b9f9ec9376def1ffea9a45f98d620f3198033186a6a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.7963826656341553,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.0023102157741533057,
5
  "eval_steps": 50,
6
- "global_step": 50,
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": 38.406,
374
  "eval_steps_per_second": 19.203,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3485956366663680.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6734322309494019,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.004620431548306611,
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": 38.406,
374
  "eval_steps_per_second": 19.203,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0023564200896363722,
379
+ "grad_norm": 0.3222690522670746,
380
+ "learning_rate": 9.628188298907782e-05,
381
+ "loss": 0.6702,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.0024026244051194383,
386
+ "grad_norm": 0.3845457136631012,
387
+ "learning_rate": 9.592434928729616e-05,
388
+ "loss": 0.3937,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0024488287206025044,
393
+ "grad_norm": 0.4016472399234772,
394
+ "learning_rate": 9.555113246230442e-05,
395
+ "loss": 0.5014,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0024950330360855705,
400
+ "grad_norm": 0.21051602065563202,
401
+ "learning_rate": 9.516235996730645e-05,
402
+ "loss": 0.3835,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0025412373515686366,
407
+ "grad_norm": 0.32177630066871643,
408
+ "learning_rate": 9.475816456775313e-05,
409
+ "loss": 0.52,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0025874416670517027,
414
+ "grad_norm": 0.3018689751625061,
415
+ "learning_rate": 9.43386842960031e-05,
416
+ "loss": 0.5665,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.002633645982534769,
421
+ "grad_norm": 0.24280551075935364,
422
+ "learning_rate": 9.39040624041849e-05,
423
+ "loss": 0.4877,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.002679850298017835,
428
+ "grad_norm": 0.20828717947006226,
429
+ "learning_rate": 9.345444731527642e-05,
430
+ "loss": 0.4176,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.002726054613500901,
435
+ "grad_norm": 0.18063269555568695,
436
+ "learning_rate": 9.298999257241863e-05,
437
+ "loss": 0.5384,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.002772258928983967,
442
+ "grad_norm": 0.277569442987442,
443
+ "learning_rate": 9.251085678648072e-05,
444
+ "loss": 0.4104,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.002818463244467033,
449
+ "grad_norm": 0.29315823316574097,
450
+ "learning_rate": 9.201720358189464e-05,
451
+ "loss": 0.5355,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.0028646675599500993,
456
+ "grad_norm": 0.24790503084659576,
457
+ "learning_rate": 9.150920154077754e-05,
458
+ "loss": 0.5383,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.0029108718754331654,
463
+ "grad_norm": 0.22097140550613403,
464
+ "learning_rate": 9.098702414536107e-05,
465
+ "loss": 0.536,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0029570761909162315,
470
+ "grad_norm": 0.23576390743255615,
471
+ "learning_rate": 9.045084971874738e-05,
472
+ "loss": 0.4857,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0030032805063992976,
477
+ "grad_norm": 0.31752127408981323,
478
+ "learning_rate": 8.9900861364012e-05,
479
+ "loss": 0.5439,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.0030494848218823637,
484
+ "grad_norm": 0.33295369148254395,
485
+ "learning_rate": 8.933724690167417e-05,
486
+ "loss": 0.6619,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.00309568913736543,
491
+ "grad_norm": 0.24967357516288757,
492
+ "learning_rate": 8.876019880555649e-05,
493
+ "loss": 0.4586,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.003141893452848496,
498
+ "grad_norm": 0.3030238449573517,
499
+ "learning_rate": 8.816991413705516e-05,
500
+ "loss": 0.6095,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.003188097768331562,
505
+ "grad_norm": 0.2835695147514343,
506
+ "learning_rate": 8.756659447784368e-05,
507
+ "loss": 0.6811,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.003234302083814628,
512
+ "grad_norm": 0.21882100403308868,
513
+ "learning_rate": 8.695044586103296e-05,
514
+ "loss": 0.4792,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.0032805063992976946,
519
+ "grad_norm": 0.31645792722702026,
520
+ "learning_rate": 8.632167870081121e-05,
521
+ "loss": 0.6682,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.0033267107147807607,
526
+ "grad_norm": 0.17226547002792358,
527
+ "learning_rate": 8.568050772058762e-05,
528
+ "loss": 0.3664,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.003372915030263827,
533
+ "grad_norm": 0.21164900064468384,
534
+ "learning_rate": 8.502715187966455e-05,
535
+ "loss": 0.5181,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.003419119345746893,
540
+ "grad_norm": 0.2374795526266098,
541
+ "learning_rate": 8.436183429846313e-05,
542
+ "loss": 0.5285,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.003465323661229959,
547
+ "grad_norm": 0.2672363817691803,
548
+ "learning_rate": 8.368478218232787e-05,
549
+ "loss": 0.5057,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.003511527976713025,
554
+ "grad_norm": 0.23033465445041656,
555
+ "learning_rate": 8.299622674393614e-05,
556
+ "loss": 0.5224,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.003557732292196091,
561
+ "grad_norm": 0.2521456778049469,
562
+ "learning_rate": 8.229640312433937e-05,
563
+ "loss": 0.5363,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.0036039366076791573,
568
+ "grad_norm": 0.3108648657798767,
569
+ "learning_rate": 8.158555031266254e-05,
570
+ "loss": 0.5886,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.0036501409231622234,
575
+ "grad_norm": 0.2801637351512909,
576
+ "learning_rate": 8.086391106448965e-05,
577
+ "loss": 0.5706,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.0036963452386452895,
582
+ "grad_norm": 0.2559647262096405,
583
+ "learning_rate": 8.013173181896283e-05,
584
+ "loss": 0.5647,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.0037425495541283556,
589
+ "grad_norm": 0.23344534635543823,
590
+ "learning_rate": 7.938926261462366e-05,
591
+ "loss": 0.4891,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.0037887538696114217,
596
+ "grad_norm": 0.2664535939693451,
597
+ "learning_rate": 7.863675700402526e-05,
598
+ "loss": 0.5494,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.0038349581850944878,
603
+ "grad_norm": 0.31824880838394165,
604
+ "learning_rate": 7.787447196714427e-05,
605
+ "loss": 0.6566,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.003881162500577554,
610
+ "grad_norm": 0.29656538367271423,
611
+ "learning_rate": 7.710266782362247e-05,
612
+ "loss": 0.6361,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.00392736681606062,
617
+ "grad_norm": 0.30476269125938416,
618
+ "learning_rate": 7.63216081438678e-05,
619
+ "loss": 0.6621,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.003973571131543686,
624
+ "grad_norm": 0.29754209518432617,
625
+ "learning_rate": 7.553155965904535e-05,
626
+ "loss": 0.7092,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.004019775447026752,
631
+ "grad_norm": 0.28509530425071716,
632
+ "learning_rate": 7.473279216998895e-05,
633
+ "loss": 0.6042,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.004065979762509818,
638
+ "grad_norm": 0.39861199259757996,
639
+ "learning_rate": 7.392557845506432e-05,
640
+ "loss": 0.8293,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.004112184077992884,
645
+ "grad_norm": 0.28901976346969604,
646
+ "learning_rate": 7.311019417701566e-05,
647
+ "loss": 0.5748,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0041583883934759504,
652
+ "grad_norm": 0.3572286367416382,
653
+ "learning_rate": 7.228691778882693e-05,
654
+ "loss": 0.6117,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.0042045927089590165,
659
+ "grad_norm": 0.3332473039627075,
660
+ "learning_rate": 7.145603043863045e-05,
661
+ "loss": 0.653,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.004250797024442083,
666
+ "grad_norm": 0.3621080815792084,
667
+ "learning_rate": 7.061781587369519e-05,
668
+ "loss": 0.6299,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.004297001339925149,
673
+ "grad_norm": 0.4089956283569336,
674
+ "learning_rate": 6.977256034352712e-05,
675
+ "loss": 0.8945,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.004343205655408215,
680
+ "grad_norm": 0.3218964636325836,
681
+ "learning_rate": 6.892055250211552e-05,
682
+ "loss": 0.7201,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.004389409970891281,
687
+ "grad_norm": 0.3587651252746582,
688
+ "learning_rate": 6.806208330935766e-05,
689
+ "loss": 0.7803,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.004435614286374347,
694
+ "grad_norm": 0.3168658912181854,
695
+ "learning_rate": 6.719744593169641e-05,
696
+ "loss": 0.7799,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.004481818601857413,
701
+ "grad_norm": 0.4870496988296509,
702
+ "learning_rate": 6.632693564200416e-05,
703
+ "loss": 0.9183,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.004528022917340479,
708
+ "grad_norm": 0.31272202730178833,
709
+ "learning_rate": 6.545084971874738e-05,
710
+ "loss": 0.768,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.004574227232823545,
715
+ "grad_norm": 0.300275057554245,
716
+ "learning_rate": 6.456948734446624e-05,
717
+ "loss": 0.6447,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.004620431548306611,
722
+ "grad_norm": 0.377289354801178,
723
+ "learning_rate": 6.368314950360415e-05,
724
+ "loss": 0.7445,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.004620431548306611,
729
+ "eval_loss": 0.6734322309494019,
730
+ "eval_runtime": 950.0633,
731
+ "eval_samples_per_second": 38.367,
732
+ "eval_steps_per_second": 19.184,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6971912733327360.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null