nttx commited on
Commit
6e86d8d
1 Parent(s): 9bcec14

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 sha256:7af1c60c395f50f4b8964149222245a2fb1af726dfe02d7564c8588f6c6b8762
3
  size 130583912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65c3c008fbebe693d48c3c3c289982803a9089ddc206dd90739ec5a2574c1f40
3
  size 130583912
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:996988ccd4eec472eb1e0bb379df1dc99c50af2d605ff0e984a0b6920dcf264b
3
  size 261311226
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:154095e3f56c856d2019627a7a0e1deb4d5a420097aba2ee5ff882113dacde7f
3
  size 261311226
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd26da0e3feb697052392ba1155269867a812bcdc295eac6dd3d57a53bb4894b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2de528baee32c70568e916c3b8f97af886cc74df910fe8ed9e8f92fd7c304f60
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f1cc9afd56c8282f59607c4f273b7bc247d970043d317c3651db16eb05eaec8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33fdeac700456f590554babdb1bb06f3350befc1bacd0a19b3d33f64c1a1c32d
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.4162628650665283,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.7586533902323376,
5
  "eval_steps": 25,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -381,6 +381,372 @@
381
  "eval_samples_per_second": 11.911,
382
  "eval_steps_per_second": 11.911,
383
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
384
  }
385
  ],
386
  "logging_steps": 1,
@@ -409,7 +775,7 @@
409
  "attributes": {}
410
  }
411
  },
412
- "total_flos": 6.95507593986048e+16,
413
  "train_batch_size": 1,
414
  "trial_name": null,
415
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.39477089047431946,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.5173067804646752,
5
  "eval_steps": 25,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
381
  "eval_samples_per_second": 11.911,
382
  "eval_steps_per_second": 11.911,
383
  "step": 50
384
+ },
385
+ {
386
+ "epoch": 0.7738264580369844,
387
+ "grad_norm": 11.381631851196289,
388
+ "learning_rate": 0.00022388221019307967,
389
+ "loss": 14.1246,
390
+ "step": 51
391
+ },
392
+ {
393
+ "epoch": 0.7889995258416311,
394
+ "grad_norm": 10.287455558776855,
395
+ "learning_rate": 0.000220496511454098,
396
+ "loss": 13.1531,
397
+ "step": 52
398
+ },
399
+ {
400
+ "epoch": 0.8041725936462779,
401
+ "grad_norm": 10.540827751159668,
402
+ "learning_rate": 0.00021706406894776709,
403
+ "loss": 12.6342,
404
+ "step": 53
405
+ },
406
+ {
407
+ "epoch": 0.8193456614509246,
408
+ "grad_norm": 10.495640754699707,
409
+ "learning_rate": 0.0002135871586064791,
410
+ "loss": 13.6827,
411
+ "step": 54
412
+ },
413
+ {
414
+ "epoch": 0.8345187292555714,
415
+ "grad_norm": 12.297253608703613,
416
+ "learning_rate": 0.00021006808584768998,
417
+ "loss": 13.6184,
418
+ "step": 55
419
+ },
420
+ {
421
+ "epoch": 0.8496917970602181,
422
+ "grad_norm": 10.440007209777832,
423
+ "learning_rate": 0.00020650918404527775,
424
+ "loss": 12.9478,
425
+ "step": 56
426
+ },
427
+ {
428
+ "epoch": 0.8648648648648649,
429
+ "grad_norm": 10.427011489868164,
430
+ "learning_rate": 0.00020291281298236423,
431
+ "loss": 12.4868,
432
+ "step": 57
433
+ },
434
+ {
435
+ "epoch": 0.8800379326695116,
436
+ "grad_norm": 9.420439720153809,
437
+ "learning_rate": 0.00019928135728662522,
438
+ "loss": 13.8967,
439
+ "step": 58
440
+ },
441
+ {
442
+ "epoch": 0.8952110004741584,
443
+ "grad_norm": 10.802536964416504,
444
+ "learning_rate": 0.0001956172248491277,
445
+ "loss": 14.1609,
446
+ "step": 59
447
+ },
448
+ {
449
+ "epoch": 0.9103840682788051,
450
+ "grad_norm": 8.980121612548828,
451
+ "learning_rate": 0.00019192284522774142,
452
+ "loss": 13.0885,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 0.9255571360834519,
457
+ "grad_norm": 8.586287498474121,
458
+ "learning_rate": 0.00018820066803618428,
459
+ "loss": 10.7247,
460
+ "step": 61
461
+ },
462
+ {
463
+ "epoch": 0.9407302038880986,
464
+ "grad_norm": 10.254575729370117,
465
+ "learning_rate": 0.00018445316131976934,
466
+ "loss": 12.6883,
467
+ "step": 62
468
+ },
469
+ {
470
+ "epoch": 0.9559032716927454,
471
+ "grad_norm": 10.308297157287598,
472
+ "learning_rate": 0.00018068280991893014,
473
+ "loss": 10.7828,
474
+ "step": 63
475
+ },
476
+ {
477
+ "epoch": 0.9710763394973921,
478
+ "grad_norm": 10.438807487487793,
479
+ "learning_rate": 0.00017689211382161034,
480
+ "loss": 9.4578,
481
+ "step": 64
482
+ },
483
+ {
484
+ "epoch": 0.9862494073020389,
485
+ "grad_norm": 16.487628936767578,
486
+ "learning_rate": 0.00017308358650560928,
487
+ "loss": 13.0305,
488
+ "step": 65
489
+ },
490
+ {
491
+ "epoch": 1.0014224751066856,
492
+ "grad_norm": 8.836454391479492,
493
+ "learning_rate": 0.00016925975327198266,
494
+ "loss": 12.8189,
495
+ "step": 66
496
+ },
497
+ {
498
+ "epoch": 1.0165955429113325,
499
+ "grad_norm": 10.768722534179688,
500
+ "learning_rate": 0.00016542314957060405,
501
+ "loss": 14.4475,
502
+ "step": 67
503
+ },
504
+ {
505
+ "epoch": 1.0317686107159791,
506
+ "grad_norm": 8.652929306030273,
507
+ "learning_rate": 0.00016157631931899697,
508
+ "loss": 15.0635,
509
+ "step": 68
510
+ },
511
+ {
512
+ "epoch": 1.0469416785206258,
513
+ "grad_norm": 7.712925910949707,
514
+ "learning_rate": 0.00015772181321555196,
515
+ "loss": 12.3852,
516
+ "step": 69
517
+ },
518
+ {
519
+ "epoch": 1.0621147463252727,
520
+ "grad_norm": 9.161529541015625,
521
+ "learning_rate": 0.0001538621870482483,
522
+ "loss": 12.3397,
523
+ "step": 70
524
+ },
525
+ {
526
+ "epoch": 1.0772878141299194,
527
+ "grad_norm": 8.765726089477539,
528
+ "learning_rate": 0.00015,
529
+ "loss": 11.8658,
530
+ "step": 71
531
+ },
532
+ {
533
+ "epoch": 1.0924608819345663,
534
+ "grad_norm": 8.678772926330566,
535
+ "learning_rate": 0.00014613781295175172,
536
+ "loss": 11.8749,
537
+ "step": 72
538
+ },
539
+ {
540
+ "epoch": 1.107633949739213,
541
+ "grad_norm": 8.968255996704102,
542
+ "learning_rate": 0.000142278186784448,
543
+ "loss": 11.2309,
544
+ "step": 73
545
+ },
546
+ {
547
+ "epoch": 1.1228070175438596,
548
+ "grad_norm": 8.212029457092285,
549
+ "learning_rate": 0.00013842368068100303,
550
+ "loss": 9.0183,
551
+ "step": 74
552
+ },
553
+ {
554
+ "epoch": 1.1379800853485065,
555
+ "grad_norm": 7.790862560272217,
556
+ "learning_rate": 0.00013457685042939592,
557
+ "loss": 10.4468,
558
+ "step": 75
559
+ },
560
+ {
561
+ "epoch": 1.1379800853485065,
562
+ "eval_loss": 0.39976993203163147,
563
+ "eval_runtime": 4.1988,
564
+ "eval_samples_per_second": 11.908,
565
+ "eval_steps_per_second": 11.908,
566
+ "step": 75
567
+ },
568
+ {
569
+ "epoch": 1.1531531531531531,
570
+ "grad_norm": 7.495136260986328,
571
+ "learning_rate": 0.00013074024672801731,
572
+ "loss": 9.8966,
573
+ "step": 76
574
+ },
575
+ {
576
+ "epoch": 1.1683262209577998,
577
+ "grad_norm": 8.63007640838623,
578
+ "learning_rate": 0.0001269164134943907,
579
+ "loss": 9.9346,
580
+ "step": 77
581
+ },
582
+ {
583
+ "epoch": 1.1834992887624467,
584
+ "grad_norm": 9.116193771362305,
585
+ "learning_rate": 0.00012310788617838966,
586
+ "loss": 11.3677,
587
+ "step": 78
588
+ },
589
+ {
590
+ "epoch": 1.1986723565670934,
591
+ "grad_norm": 9.81653881072998,
592
+ "learning_rate": 0.0001193171900810699,
593
+ "loss": 10.2669,
594
+ "step": 79
595
+ },
596
+ {
597
+ "epoch": 1.2138454243717403,
598
+ "grad_norm": 10.604126930236816,
599
+ "learning_rate": 0.00011554683868023067,
600
+ "loss": 10.7322,
601
+ "step": 80
602
+ },
603
+ {
604
+ "epoch": 1.229018492176387,
605
+ "grad_norm": 10.463966369628906,
606
+ "learning_rate": 0.0001117993319638157,
607
+ "loss": 9.2057,
608
+ "step": 81
609
+ },
610
+ {
611
+ "epoch": 1.2441915599810336,
612
+ "grad_norm": 9.727025985717773,
613
+ "learning_rate": 0.00010807715477225858,
614
+ "loss": 8.6479,
615
+ "step": 82
616
+ },
617
+ {
618
+ "epoch": 1.2593646277856805,
619
+ "grad_norm": 13.668055534362793,
620
+ "learning_rate": 0.00010438277515087233,
621
+ "loss": 14.4636,
622
+ "step": 83
623
+ },
624
+ {
625
+ "epoch": 1.2745376955903271,
626
+ "grad_norm": 11.730889320373535,
627
+ "learning_rate": 0.00010071864271337478,
628
+ "loss": 14.0765,
629
+ "step": 84
630
+ },
631
+ {
632
+ "epoch": 1.2897107633949738,
633
+ "grad_norm": 11.76871109008789,
634
+ "learning_rate": 9.708718701763577e-05,
635
+ "loss": 12.6621,
636
+ "step": 85
637
+ },
638
+ {
639
+ "epoch": 1.3048838311996207,
640
+ "grad_norm": 12.476866722106934,
641
+ "learning_rate": 9.34908159547222e-05,
642
+ "loss": 12.6543,
643
+ "step": 86
644
+ },
645
+ {
646
+ "epoch": 1.3200568990042674,
647
+ "grad_norm": 9.014403343200684,
648
+ "learning_rate": 8.993191415231e-05,
649
+ "loss": 10.5078,
650
+ "step": 87
651
+ },
652
+ {
653
+ "epoch": 1.3352299668089143,
654
+ "grad_norm": 8.82985782623291,
655
+ "learning_rate": 8.641284139352091e-05,
656
+ "loss": 10.1313,
657
+ "step": 88
658
+ },
659
+ {
660
+ "epoch": 1.350403034613561,
661
+ "grad_norm": 9.604599952697754,
662
+ "learning_rate": 8.293593105223287e-05,
663
+ "loss": 10.9247,
664
+ "step": 89
665
+ },
666
+ {
667
+ "epoch": 1.3655761024182076,
668
+ "grad_norm": 8.465795516967773,
669
+ "learning_rate": 7.950348854590204e-05,
670
+ "loss": 9.671,
671
+ "step": 90
672
+ },
673
+ {
674
+ "epoch": 1.3807491702228545,
675
+ "grad_norm": 8.575054168701172,
676
+ "learning_rate": 7.611778980692035e-05,
677
+ "loss": 10.2636,
678
+ "step": 91
679
+ },
680
+ {
681
+ "epoch": 1.3959222380275011,
682
+ "grad_norm": 7.928877830505371,
683
+ "learning_rate": 7.278107977352543e-05,
684
+ "loss": 8.982,
685
+ "step": 92
686
+ },
687
+ {
688
+ "epoch": 1.411095305832148,
689
+ "grad_norm": 9.111271858215332,
690
+ "learning_rate": 6.949557090125994e-05,
691
+ "loss": 9.8091,
692
+ "step": 93
693
+ },
694
+ {
695
+ "epoch": 1.4262683736367947,
696
+ "grad_norm": 8.69306468963623,
697
+ "learning_rate": 6.626344169597031e-05,
698
+ "loss": 9.7754,
699
+ "step": 94
700
+ },
701
+ {
702
+ "epoch": 1.4414414414414414,
703
+ "grad_norm": 8.90804386138916,
704
+ "learning_rate": 6.308683526931545e-05,
705
+ "loss": 9.7669,
706
+ "step": 95
707
+ },
708
+ {
709
+ "epoch": 1.4566145092460883,
710
+ "grad_norm": 9.999079704284668,
711
+ "learning_rate": 5.996785791774478e-05,
712
+ "loss": 9.0066,
713
+ "step": 96
714
+ },
715
+ {
716
+ "epoch": 1.471787577050735,
717
+ "grad_norm": 9.848721504211426,
718
+ "learning_rate": 5.690857772588657e-05,
719
+ "loss": 8.0642,
720
+ "step": 97
721
+ },
722
+ {
723
+ "epoch": 1.4869606448553818,
724
+ "grad_norm": 10.121479988098145,
725
+ "learning_rate": 5.391102319527373e-05,
726
+ "loss": 8.1109,
727
+ "step": 98
728
+ },
729
+ {
730
+ "epoch": 1.5021337126600285,
731
+ "grad_norm": 11.15321159362793,
732
+ "learning_rate": 5.0977181899315214e-05,
733
+ "loss": 15.3952,
734
+ "step": 99
735
+ },
736
+ {
737
+ "epoch": 1.5173067804646752,
738
+ "grad_norm": 10.735111236572266,
739
+ "learning_rate": 4.8108999165406026e-05,
740
+ "loss": 14.3337,
741
+ "step": 100
742
+ },
743
+ {
744
+ "epoch": 1.5173067804646752,
745
+ "eval_loss": 0.39477089047431946,
746
+ "eval_runtime": 4.2024,
747
+ "eval_samples_per_second": 11.898,
748
+ "eval_steps_per_second": 11.898,
749
+ "step": 100
750
  }
751
  ],
752
  "logging_steps": 1,
 
775
  "attributes": {}
776
  }
777
  },
778
+ "total_flos": 1.391015187972096e+17,
779
  "train_batch_size": 1,
780
  "trial_name": null,
781
  "trial_params": null