dimasik87 commited on
Commit
440eb6c
·
verified ·
1 Parent(s): dd2e183

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:b20350b6df1fc085ff6e6095466515857695825f5894f7fc63c4724681c288d2
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d943ab670d2ec02491e4ebe4f1f2ed01bfa629f3da4219180d49a36fa32e8b2
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f90a07ac8c3e45fbf8562cf4d3e39253616968979deb41aa0b7191252956add8
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90df2dd65c3d8592c96c2fd7951235ae235e6e1012c064ef1d64e770c929963d
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:206b1a7321c484e02aa59caf49e2a72a659e69232403bf3a5d7a506abcc55a7b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a271bbcc82508aea764d98d0927295201f535afc9927e075a565c461e2f8b86
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:420c9c3b2300136316283bf07027d494a21b6b2c5dcebe052deac7037529e10e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c41bb450efe89fd65fecb2593939b817f9b2794a5d87a632ad90e5ebc9b592b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.7083282470703125,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.005125051250512505,
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": 19.206,
374
  "eval_steps_per_second": 4.801,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.795134465245184e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.6530330181121826,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.01025010250102501,
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": 19.206,
374
  "eval_steps_per_second": 4.801,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0052275522755227555,
379
+ "grad_norm": 0.7324660420417786,
380
+ "learning_rate": 7.849947368421052e-05,
381
+ "loss": 1.7833,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.005330053300533005,
386
+ "grad_norm": 1.0079008340835571,
387
+ "learning_rate": 7.797263157894736e-05,
388
+ "loss": 2.0611,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.005432554325543256,
393
+ "grad_norm": 1.0478756427764893,
394
+ "learning_rate": 7.744578947368421e-05,
395
+ "loss": 1.5655,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.005535055350553505,
400
+ "grad_norm": 1.1489282846450806,
401
+ "learning_rate": 7.691894736842104e-05,
402
+ "loss": 2.0112,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.005637556375563756,
407
+ "grad_norm": 1.0685741901397705,
408
+ "learning_rate": 7.63921052631579e-05,
409
+ "loss": 1.837,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.005740057400574006,
414
+ "grad_norm": 0.9752334952354431,
415
+ "learning_rate": 7.586526315789473e-05,
416
+ "loss": 1.8408,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.005842558425584256,
421
+ "grad_norm": 1.0988349914550781,
422
+ "learning_rate": 7.533842105263158e-05,
423
+ "loss": 1.6708,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.005945059450594506,
428
+ "grad_norm": 1.059479832649231,
429
+ "learning_rate": 7.481157894736841e-05,
430
+ "loss": 1.4579,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.006047560475604756,
435
+ "grad_norm": 1.0964906215667725,
436
+ "learning_rate": 7.428473684210526e-05,
437
+ "loss": 1.944,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.006150061500615006,
442
+ "grad_norm": 1.0522820949554443,
443
+ "learning_rate": 7.375789473684209e-05,
444
+ "loss": 1.762,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0062525625256252566,
449
+ "grad_norm": 1.0768394470214844,
450
+ "learning_rate": 7.323105263157895e-05,
451
+ "loss": 1.7185,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.006355063550635506,
456
+ "grad_norm": 1.1058900356292725,
457
+ "learning_rate": 7.270421052631578e-05,
458
+ "loss": 1.6855,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.006457564575645757,
463
+ "grad_norm": 1.0793980360031128,
464
+ "learning_rate": 7.217736842105263e-05,
465
+ "loss": 1.6553,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.006560065600656006,
470
+ "grad_norm": 1.257716417312622,
471
+ "learning_rate": 7.165052631578947e-05,
472
+ "loss": 1.5379,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.006662566625666257,
477
+ "grad_norm": 1.116843581199646,
478
+ "learning_rate": 7.11236842105263e-05,
479
+ "loss": 1.6653,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.006765067650676507,
484
+ "grad_norm": 1.016861081123352,
485
+ "learning_rate": 7.059684210526315e-05,
486
+ "loss": 1.3905,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.006867568675686757,
491
+ "grad_norm": 1.1021226644515991,
492
+ "learning_rate": 7.006999999999998e-05,
493
+ "loss": 1.6295,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.006970069700697007,
498
+ "grad_norm": 1.1197590827941895,
499
+ "learning_rate": 6.954315789473684e-05,
500
+ "loss": 1.6643,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.007072570725707257,
505
+ "grad_norm": 1.242423415184021,
506
+ "learning_rate": 6.901631578947368e-05,
507
+ "loss": 1.7367,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.007175071750717507,
512
+ "grad_norm": 1.1498782634735107,
513
+ "learning_rate": 6.848947368421052e-05,
514
+ "loss": 1.6476,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.007277572775727758,
519
+ "grad_norm": 1.174621820449829,
520
+ "learning_rate": 6.796263157894737e-05,
521
+ "loss": 2.0002,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.007380073800738007,
526
+ "grad_norm": 1.1680294275283813,
527
+ "learning_rate": 6.74357894736842e-05,
528
+ "loss": 1.4689,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.007482574825748258,
533
+ "grad_norm": 1.3079551458358765,
534
+ "learning_rate": 6.690894736842105e-05,
535
+ "loss": 1.5757,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.007585075850758507,
540
+ "grad_norm": 1.2481780052185059,
541
+ "learning_rate": 6.638210526315788e-05,
542
+ "loss": 1.6238,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.007687576875768758,
547
+ "grad_norm": 1.3879331350326538,
548
+ "learning_rate": 6.585526315789474e-05,
549
+ "loss": 1.9082,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.007790077900779008,
554
+ "grad_norm": 1.6329386234283447,
555
+ "learning_rate": 6.532842105263157e-05,
556
+ "loss": 1.739,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.007892578925789259,
561
+ "grad_norm": 1.4674111604690552,
562
+ "learning_rate": 6.480157894736842e-05,
563
+ "loss": 1.6045,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.007995079950799507,
568
+ "grad_norm": 1.4382115602493286,
569
+ "learning_rate": 6.427473684210526e-05,
570
+ "loss": 1.4885,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.008097580975809758,
575
+ "grad_norm": 1.4571962356567383,
576
+ "learning_rate": 6.37478947368421e-05,
577
+ "loss": 1.3451,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.008200082000820008,
582
+ "grad_norm": 1.6193132400512695,
583
+ "learning_rate": 6.322105263157894e-05,
584
+ "loss": 1.8344,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.008302583025830259,
589
+ "grad_norm": 1.673788070678711,
590
+ "learning_rate": 6.269421052631577e-05,
591
+ "loss": 1.4983,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.008405084050840509,
596
+ "grad_norm": 1.7791383266448975,
597
+ "learning_rate": 6.216736842105263e-05,
598
+ "loss": 1.8181,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.008507585075850758,
603
+ "grad_norm": 1.6379783153533936,
604
+ "learning_rate": 6.164052631578947e-05,
605
+ "loss": 1.5085,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.008610086100861008,
610
+ "grad_norm": 2.0746712684631348,
611
+ "learning_rate": 6.111368421052631e-05,
612
+ "loss": 1.8331,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.008712587125871259,
617
+ "grad_norm": 1.9016090631484985,
618
+ "learning_rate": 6.058684210526315e-05,
619
+ "loss": 1.6955,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.008815088150881509,
624
+ "grad_norm": 2.0374410152435303,
625
+ "learning_rate": 6.005999999999999e-05,
626
+ "loss": 1.6262,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.00891758917589176,
631
+ "grad_norm": 2.458918809890747,
632
+ "learning_rate": 5.953315789473684e-05,
633
+ "loss": 1.782,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.009020090200902008,
638
+ "grad_norm": 2.420497179031372,
639
+ "learning_rate": 5.9006315789473676e-05,
640
+ "loss": 1.4256,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.009122591225912259,
645
+ "grad_norm": 3.1010406017303467,
646
+ "learning_rate": 5.847947368421053e-05,
647
+ "loss": 1.5861,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.00922509225092251,
652
+ "grad_norm": 2.9462192058563232,
653
+ "learning_rate": 5.795263157894737e-05,
654
+ "loss": 1.7643,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.00932759327593276,
659
+ "grad_norm": 3.0921950340270996,
660
+ "learning_rate": 5.742578947368421e-05,
661
+ "loss": 1.7482,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.00943009430094301,
666
+ "grad_norm": 3.2740588188171387,
667
+ "learning_rate": 5.6898947368421046e-05,
668
+ "loss": 1.7103,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.009532595325953259,
673
+ "grad_norm": 3.282179594039917,
674
+ "learning_rate": 5.6372105263157886e-05,
675
+ "loss": 1.3958,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.00963509635096351,
680
+ "grad_norm": 2.8050053119659424,
681
+ "learning_rate": 5.584526315789473e-05,
682
+ "loss": 1.0987,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.00973759737597376,
687
+ "grad_norm": 3.167931079864502,
688
+ "learning_rate": 5.531842105263158e-05,
689
+ "loss": 1.0239,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.00984009840098401,
694
+ "grad_norm": 4.01984167098999,
695
+ "learning_rate": 5.4791578947368424e-05,
696
+ "loss": 2.1924,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.00994259942599426,
701
+ "grad_norm": 7.1500983238220215,
702
+ "learning_rate": 5.426473684210526e-05,
703
+ "loss": 1.6619,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.01004510045100451,
708
+ "grad_norm": 3.5555317401885986,
709
+ "learning_rate": 5.37378947368421e-05,
710
+ "loss": 1.0794,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.01014760147601476,
715
+ "grad_norm": 3.8048603534698486,
716
+ "learning_rate": 5.321105263157894e-05,
717
+ "loss": 1.4438,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.01025010250102501,
722
+ "grad_norm": 6.511986255645752,
723
+ "learning_rate": 5.268421052631578e-05,
724
+ "loss": 2.3968,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.01025010250102501,
729
+ "eval_loss": 1.6530330181121826,
730
+ "eval_runtime": 213.675,
731
+ "eval_samples_per_second": 19.225,
732
+ "eval_steps_per_second": 4.806,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3.572495321923584e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null