aleegis09 commited on
Commit
e3849f9
·
verified ·
1 Parent(s): 6844552

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 sha256:317ab688919c209ba64017a131bad48b091ce39c352539cd4cac4c24cd95e695
3
  size 406863720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f227b623f8a075672ea79225413b2b2fce2241f30b0954a96eb8fd65f4d00290
3
  size 406863720
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:335daa30350ef7ff6f86d42ec6b3e72962a1af78ee38ec253058c85782b52b59
3
  size 207013892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bfad403a0ebb39bced1a367b6fa9b54cab41bd0ff1239c233fd2904d5d33994
3
  size 207013892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e2dfcbe4fc89a6e08e71533c392194c2997d74e2db2f5ec0c1003d9151fe3cd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2950f6dac83ac119a24d49f55b4575671ea046ff6d1f4c7213cca3c8b1c0efa7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d359eb5d29e75fb2bbe5b7026981da69b95b8ad1fea469302d13cde104f7e8a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.7583083510398865,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.002550760126517702,
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": 23.028,
374
  "eval_steps_per_second": 5.757,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3.384514477817856e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7207558155059814,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.005101520253035404,
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": 23.028,
374
  "eval_steps_per_second": 5.757,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0026017753290480563,
379
+ "grad_norm": 2.367197275161743,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.5955,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.0026527905315784106,
386
+ "grad_norm": 1.655700922012329,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.1209,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0027038057341087643,
393
+ "grad_norm": 1.7417899370193481,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.9548,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0027548209366391185,
400
+ "grad_norm": 1.4532091617584229,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.8967,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0028058361391694723,
407
+ "grad_norm": 1.184683918952942,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.8828,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0028568513416998265,
414
+ "grad_norm": 1.2943260669708252,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.7884,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.0029078665442301807,
421
+ "grad_norm": 1.4289363622665405,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.964,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0029588817467605345,
428
+ "grad_norm": 1.3355457782745361,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.9107,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.0030098969492908887,
435
+ "grad_norm": 1.2480206489562988,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.99,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.003060912151821243,
442
+ "grad_norm": 1.253343105316162,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.8802,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0031119273543515967,
449
+ "grad_norm": 1.1792048215866089,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.8684,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.003162942556881951,
456
+ "grad_norm": 1.4219132661819458,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.8953,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.0032139577594123047,
463
+ "grad_norm": 1.0520647764205933,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.7349,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.003264972961942659,
470
+ "grad_norm": 1.0161808729171753,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.7194,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.003315988164473013,
477
+ "grad_norm": 1.1097899675369263,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.8444,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.003367003367003367,
484
+ "grad_norm": 0.9742171764373779,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.6395,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.003418018569533721,
491
+ "grad_norm": 1.095369577407837,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.79,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.0034690337720640753,
498
+ "grad_norm": 1.0745102167129517,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.6555,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.003520048974594429,
505
+ "grad_norm": 1.1682138442993164,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.7564,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.0035710641771247833,
512
+ "grad_norm": 0.9457067251205444,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.5688,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.003622079379655137,
519
+ "grad_norm": 1.058748483657837,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.7264,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.0036730945821854912,
526
+ "grad_norm": 1.111148476600647,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.7099,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.0037241097847158454,
533
+ "grad_norm": 1.155498743057251,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.659,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.003775124987246199,
540
+ "grad_norm": 1.0034657716751099,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.6234,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.0038261401897765534,
547
+ "grad_norm": 0.9839001297950745,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.6588,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.0038771553923069076,
554
+ "grad_norm": 0.9003528952598572,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.5224,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.003928170594837262,
561
+ "grad_norm": 1.137490153312683,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.6979,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.003979185797367615,
568
+ "grad_norm": 1.0123627185821533,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.6084,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.004030200999897969,
575
+ "grad_norm": 0.9710042476654053,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.5265,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.004081216202428324,
582
+ "grad_norm": 0.852706789970398,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.5406,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.004132231404958678,
589
+ "grad_norm": 1.2595216035842896,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.713,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.004183246607489032,
596
+ "grad_norm": 0.9067636728286743,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.5898,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.004234261810019385,
603
+ "grad_norm": 1.0178347826004028,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.6771,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.0042852770125497396,
610
+ "grad_norm": 1.1163185834884644,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.5688,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.004336292215080094,
617
+ "grad_norm": 0.9268144965171814,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.5357,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.004387307417610448,
624
+ "grad_norm": 1.1120328903198242,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.616,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.004438322620140802,
631
+ "grad_norm": 1.1013883352279663,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.5996,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.004489337822671156,
638
+ "grad_norm": 1.110445261001587,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.533,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.00454035302520151,
645
+ "grad_norm": 1.1144078969955444,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.6819,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.004591368227731864,
652
+ "grad_norm": 0.9260347485542297,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.5444,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.004642383430262218,
659
+ "grad_norm": 1.0573139190673828,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.6318,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.004693398632792572,
666
+ "grad_norm": 1.043210744857788,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.5157,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.0047444138353229266,
673
+ "grad_norm": 1.0416425466537476,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.5391,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.00479542903785328,
680
+ "grad_norm": 1.2475289106369019,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.6276,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.004846444240383634,
687
+ "grad_norm": 1.0211669206619263,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.5017,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.004897459442913988,
694
+ "grad_norm": 1.3028045892715454,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.7187,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.0049484746454443425,
701
+ "grad_norm": 1.1932437419891357,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.591,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.004999489847974697,
708
+ "grad_norm": 1.2623156309127808,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.6682,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.005050505050505051,
715
+ "grad_norm": 1.8324122428894043,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.7281,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.005101520253035404,
722
+ "grad_norm": 1.7937883138656616,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.6457,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.005101520253035404,
729
+ "eval_loss": 0.7207558155059814,
730
+ "eval_runtime": 1433.8662,
731
+ "eval_samples_per_second": 23.024,
732
+ "eval_steps_per_second": 5.756,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6.769028955635712e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null