cimol commited on
Commit
a3ce129
·
verified ·
1 Parent(s): 280a1cf

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:f2b74fb47b1ae4d8d4d4d71e4a0420a19f1f4de20d99705b3847b8f893535fee
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a08f2b9b64a428e555d0dad08f9788b16981854cc443ca12b0c5db14a0b11ec9
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6eebf857e70098b3361b52882591063049f71b87a543d937f903eab602c40c37
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfaa80d1349d969f287b29c73d47462f4ea2be9cc7af3d8090b644c633d464c2
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d247636ec314006bef35549f310d4bbdb499f768831af208bf0ab8d3981cf780
3
  size 14180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbc8a8795bda86fdcb7e7f271436d3a28caee8850ec4cd224646f5bf4dd04f2c
3
  size 14180
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:947b4b7e8b578cfa0f90060cb87e8d28c0e6be86b5cadcb00b9f65c8cbebcbb8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d94dee72c7d02de6c69d9fa4cc2d9dd3225f09ac52c6adcb59ec7bae1df8f10
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.031134843826294,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.5376344086021505,
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": 10.644,
374
  "eval_steps_per_second": 2.712,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.65254329581568e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8277088403701782,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.075268817204301,
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": 10.644,
374
  "eval_steps_per_second": 2.712,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.5483870967741935,
379
+ "grad_norm": 3.2802512645721436,
380
+ "learning_rate": 6.226070475667393e-05,
381
+ "loss": 5.2625,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.5591397849462365,
386
+ "grad_norm": 3.9532055854797363,
387
+ "learning_rate": 6.189403887999006e-05,
388
+ "loss": 4.5323,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.5698924731182796,
393
+ "grad_norm": 4.0816731452941895,
394
+ "learning_rate": 6.152002044161171e-05,
395
+ "loss": 5.2472,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.5806451612903226,
400
+ "grad_norm": 3.2194178104400635,
401
+ "learning_rate": 6.113875169444539e-05,
402
+ "loss": 4.1174,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.5913978494623656,
407
+ "grad_norm": 3.1189627647399902,
408
+ "learning_rate": 6.0750336873559605e-05,
409
+ "loss": 3.5628,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.6021505376344086,
414
+ "grad_norm": 3.0379552841186523,
415
+ "learning_rate": 6.035488216768811e-05,
416
+ "loss": 2.5643,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.6129032258064516,
421
+ "grad_norm": 2.96771240234375,
422
+ "learning_rate": 5.9952495690198894e-05,
423
+ "loss": 3.8131,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.6236559139784946,
428
+ "grad_norm": 3.369340181350708,
429
+ "learning_rate": 5.954328744953709e-05,
430
+ "loss": 2.6112,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.6344086021505376,
435
+ "grad_norm": 2.662733793258667,
436
+ "learning_rate": 5.91273693191498e-05,
437
+ "loss": 2.678,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.6451612903225806,
442
+ "grad_norm": 2.3960416316986084,
443
+ "learning_rate": 5.870485500690094e-05,
444
+ "loss": 1.9448,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.6559139784946236,
449
+ "grad_norm": 3.0840823650360107,
450
+ "learning_rate": 5.827586002398468e-05,
451
+ "loss": 3.0983,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.6666666666666666,
456
+ "grad_norm": 4.117824077606201,
457
+ "learning_rate": 5.784050165334589e-05,
458
+ "loss": 2.1824,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.6774193548387096,
463
+ "grad_norm": 3.039947271347046,
464
+ "learning_rate": 5.739889891761608e-05,
465
+ "loss": 3.4342,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.6881720430107527,
470
+ "grad_norm": 3.3664510250091553,
471
+ "learning_rate": 5.6951172546573794e-05,
472
+ "loss": 2.7055,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.6989247311827957,
477
+ "grad_norm": 7.528428077697754,
478
+ "learning_rate": 5.6497444944138376e-05,
479
+ "loss": 3.2575,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.7096774193548387,
484
+ "grad_norm": 2.7763924598693848,
485
+ "learning_rate": 5.603784015490587e-05,
486
+ "loss": 2.7032,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.7204301075268817,
491
+ "grad_norm": 4.630373001098633,
492
+ "learning_rate": 5.557248383023655e-05,
493
+ "loss": 3.1262,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.7311827956989247,
498
+ "grad_norm": 4.628628730773926,
499
+ "learning_rate": 5.510150319390302e-05,
500
+ "loss": 2.4391,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.7419354838709677,
505
+ "grad_norm": 6.389301300048828,
506
+ "learning_rate": 5.4625027007308546e-05,
507
+ "loss": 1.6421,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.7526881720430108,
512
+ "grad_norm": 3.937209129333496,
513
+ "learning_rate": 5.414318553428494e-05,
514
+ "loss": 6.887,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.7634408602150538,
519
+ "grad_norm": 3.489776611328125,
520
+ "learning_rate": 5.3656110505479776e-05,
521
+ "loss": 5.776,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.7741935483870968,
526
+ "grad_norm": 3.345602035522461,
527
+ "learning_rate": 5.316393508234253e-05,
528
+ "loss": 5.4254,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.7849462365591398,
533
+ "grad_norm": 2.5286366939544678,
534
+ "learning_rate": 5.266679382071953e-05,
535
+ "loss": 5.4602,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.7956989247311828,
540
+ "grad_norm": 2.6356401443481445,
541
+ "learning_rate": 5.216482263406778e-05,
542
+ "loss": 4.1083,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.8064516129032258,
547
+ "grad_norm": 2.794057607650757,
548
+ "learning_rate": 5.1658158756297576e-05,
549
+ "loss": 4.0295,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.8172043010752689,
554
+ "grad_norm": 3.1053338050842285,
555
+ "learning_rate": 5.114694070425407e-05,
556
+ "loss": 4.2456,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.8279569892473119,
561
+ "grad_norm": 3.4362998008728027,
562
+ "learning_rate": 5.063130823984823e-05,
563
+ "loss": 4.0444,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.8387096774193549,
568
+ "grad_norm": 3.6933822631835938,
569
+ "learning_rate": 5.011140233184724e-05,
570
+ "loss": 3.3562,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.8494623655913979,
575
+ "grad_norm": 2.264709711074829,
576
+ "learning_rate": 4.958736511733516e-05,
577
+ "loss": 1.5203,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.8602150537634409,
582
+ "grad_norm": 3.0925395488739014,
583
+ "learning_rate": 4.905933986285393e-05,
584
+ "loss": 3.4232,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.8709677419354839,
589
+ "grad_norm": 3.5374860763549805,
590
+ "learning_rate": 4.8527470925235824e-05,
591
+ "loss": 2.9371,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.8817204301075269,
596
+ "grad_norm": 2.737464666366577,
597
+ "learning_rate": 4.799190371213772e-05,
598
+ "loss": 2.9893,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.8924731182795699,
603
+ "grad_norm": 2.4057750701904297,
604
+ "learning_rate": 4.745278464228808e-05,
605
+ "loss": 2.4454,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.9032258064516129,
610
+ "grad_norm": 3.7483322620391846,
611
+ "learning_rate": 4.69102611054575e-05,
612
+ "loss": 2.2346,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.9139784946236559,
617
+ "grad_norm": 3.1117513179779053,
618
+ "learning_rate": 4.6364481422163926e-05,
619
+ "loss": 2.3842,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.9247311827956989,
624
+ "grad_norm": 2.581960678100586,
625
+ "learning_rate": 4.581559480312316e-05,
626
+ "loss": 2.3513,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.9354838709677419,
631
+ "grad_norm": 2.8223772048950195,
632
+ "learning_rate": 4.526375130845627e-05,
633
+ "loss": 2.713,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.946236559139785,
638
+ "grad_norm": 3.449551582336426,
639
+ "learning_rate": 4.4709101806664554e-05,
640
+ "loss": 2.1045,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.956989247311828,
645
+ "grad_norm": 3.203859329223633,
646
+ "learning_rate": 4.4151797933383685e-05,
647
+ "loss": 2.2587,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.967741935483871,
652
+ "grad_norm": 2.9277474880218506,
653
+ "learning_rate": 4.359199204992797e-05,
654
+ "loss": 2.6041,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.978494623655914,
659
+ "grad_norm": 3.5323002338409424,
660
+ "learning_rate": 4.30298372016363e-05,
661
+ "loss": 2.2093,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.989247311827957,
666
+ "grad_norm": 4.1092681884765625,
667
+ "learning_rate": 4.246548707603114e-05,
668
+ "loss": 1.9357,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.0,
673
+ "grad_norm": 3.2726848125457764,
674
+ "learning_rate": 4.1899095960801805e-05,
675
+ "loss": 2.8715,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.010752688172043,
680
+ "grad_norm": 2.6090543270111084,
681
+ "learning_rate": 4.133081870162385e-05,
682
+ "loss": 6.4364,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.021505376344086,
687
+ "grad_norm": 3.0788755416870117,
688
+ "learning_rate": 4.076081065982569e-05,
689
+ "loss": 6.1323,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.032258064516129,
694
+ "grad_norm": 3.0953359603881836,
695
+ "learning_rate": 4.018922766991447e-05,
696
+ "loss": 5.4343,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.043010752688172,
701
+ "grad_norm": 2.4865167140960693,
702
+ "learning_rate": 3.961622599697241e-05,
703
+ "loss": 3.752,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.053763440860215,
708
+ "grad_norm": 3.014270305633545,
709
+ "learning_rate": 3.9041962293935516e-05,
710
+ "loss": 3.9712,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.064516129032258,
715
+ "grad_norm": 2.697925329208374,
716
+ "learning_rate": 3.84665935587662e-05,
717
+ "loss": 3.8601,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.075268817204301,
722
+ "grad_norm": 2.772761106491089,
723
+ "learning_rate": 3.7890277091531636e-05,
724
+ "loss": 3.554,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.075268817204301,
729
+ "eval_loss": 0.8277088403701782,
730
+ "eval_runtime": 14.7467,
731
+ "eval_samples_per_second": 10.646,
732
+ "eval_steps_per_second": 2.712,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.329677091251159e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null