prxy5605 commited on
Commit
6237a35
·
verified ·
1 Parent(s): 831a9c0

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 sha256:83f367fa7dcee21db995bb0076a1f1bcbf4f460bd317b2c75873e494ea129706
3
  size 406863720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9d5bbd3213e6430b7bd596627c1ce88a247e50e9754125122417c3af644cfdc
3
  size 406863720
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63bfd0060cea9bc6d8c0bac7e2949fe528ec84db091c1cf14f9f8961b431480b
3
  size 207013892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa9ec085507c5e6e013494ce81a6ab42fee48888afaafec9fabf506633d6b99d
3
  size 207013892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:845d44bea51ae8c852bae051b817d8a4aa017c8030dafad8ac128fab7fa69003
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8e11a89fbf6be88c29777fdbbfe4d4259c26b65e372ad0b0265d65afb8afb8
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": 0.10318926721811295,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.013686443577636351,
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": 23.373,
374
  "eval_steps_per_second": 5.846,
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": 0.0689723864197731,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.027372887155272703,
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": 23.373,
374
  "eval_steps_per_second": 5.846,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.013960172449189078,
379
+ "grad_norm": 1.7688506841659546,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.4599,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.014233901320741805,
386
+ "grad_norm": 0.6852141618728638,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.1715,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.014507630192294532,
393
+ "grad_norm": 0.64682537317276,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.1896,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.01478135906384726,
400
+ "grad_norm": 0.4129149615764618,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.1405,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.015055087935399987,
407
+ "grad_norm": 0.39000850915908813,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.0792,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.015328816806952713,
414
+ "grad_norm": 0.7193068265914917,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.1492,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.01560254567850544,
421
+ "grad_norm": 0.2947554588317871,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.0963,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.01587627455005817,
428
+ "grad_norm": 0.28656435012817383,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.0775,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.016150003421610895,
435
+ "grad_norm": 0.28851979970932007,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.1041,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.016423732293163622,
442
+ "grad_norm": 0.5464861989021301,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.0947,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.01669746116471635,
449
+ "grad_norm": 0.39874088764190674,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.1459,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.016971190036269075,
456
+ "grad_norm": 0.39730069041252136,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.0872,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.017244918907821802,
463
+ "grad_norm": 0.3217560052871704,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.1013,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.01751864777937453,
470
+ "grad_norm": 0.36995869874954224,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.0794,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.017792376650927255,
477
+ "grad_norm": 0.29235830903053284,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.0753,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.018066105522479982,
484
+ "grad_norm": 0.40605628490448,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.1249,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.018339834394032712,
491
+ "grad_norm": 0.24858100712299347,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.0819,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.01861356326558544,
498
+ "grad_norm": 0.30691301822662354,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.0559,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.018887292137138165,
505
+ "grad_norm": 0.27972522377967834,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.0858,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.019161021008690892,
512
+ "grad_norm": 0.28502631187438965,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.0782,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.01943474988024362,
519
+ "grad_norm": 0.27517464756965637,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.1164,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.019708478751796345,
526
+ "grad_norm": 0.2742948830127716,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.0812,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.019982207623349072,
533
+ "grad_norm": 0.2698785364627838,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.0526,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.0202559364949018,
540
+ "grad_norm": 0.1924898773431778,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.0653,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.020529665366454525,
547
+ "grad_norm": 0.24038903415203094,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.0571,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.020803394238007252,
554
+ "grad_norm": 0.2771959602832794,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.0678,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.021077123109559982,
561
+ "grad_norm": 0.3027803599834442,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.0824,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.02135085198111271,
568
+ "grad_norm": 0.34813180565834045,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.0428,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.021624580852665436,
575
+ "grad_norm": 0.18736878037452698,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.0164,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.021898309724218162,
582
+ "grad_norm": 0.1618126630783081,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.0252,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.02217203859577089,
589
+ "grad_norm": 0.18529681861400604,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.0256,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.022445767467323616,
596
+ "grad_norm": 0.5240387916564941,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.0771,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.022719496338876342,
603
+ "grad_norm": 0.3223040699958801,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.1034,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.02299322521042907,
610
+ "grad_norm": 0.342072993516922,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.0586,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.023266954081981796,
617
+ "grad_norm": 0.2215188443660736,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.0384,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.023540682953534522,
624
+ "grad_norm": 0.1570575088262558,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.0218,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.023814411825087253,
631
+ "grad_norm": 0.19102266430854797,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.0424,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.02408814069663998,
638
+ "grad_norm": 0.1055581122636795,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.0121,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.024361869568192706,
645
+ "grad_norm": 0.3091917037963867,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.079,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.024635598439745433,
652
+ "grad_norm": 0.1684788465499878,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.0372,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.02490932731129816,
659
+ "grad_norm": 0.25582513213157654,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.0406,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.025183056182850886,
666
+ "grad_norm": 0.10428531467914581,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.0058,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.025456785054403613,
673
+ "grad_norm": 0.25681793689727783,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.0333,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.02573051392595634,
680
+ "grad_norm": 0.09947719424962997,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.0055,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.026004242797509066,
687
+ "grad_norm": 0.05656822770833969,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.0031,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.026277971669061793,
694
+ "grad_norm": 0.10895723849534988,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.0061,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.026551700540614523,
701
+ "grad_norm": 0.30041539669036865,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.0417,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.02682542941216725,
708
+ "grad_norm": 0.20105572044849396,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.0128,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.027099158283719976,
715
+ "grad_norm": 0.09207609295845032,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.005,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.027372887155272703,
722
+ "grad_norm": 0.07330376654863358,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.0041,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.027372887155272703,
729
+ "eval_loss": 0.0689723864197731,
730
+ "eval_runtime": 263.1747,
731
+ "eval_samples_per_second": 23.38,
732
+ "eval_steps_per_second": 5.848,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6.752190575149056e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null