aleegis09 commited on
Commit
ad43d61
·
verified ·
1 Parent(s): b4e3565

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:d44111bd944c2fbe523a1ffe5dee321a8e12f793847e036160fac39eaff7bc7d
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82f5c8dc140b24bae63ef0d36ffeae84bdb32c727dcab89b4d7e6121e7ea6828
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c04c9cc6a81f5a9a68b0c730847e22fd47643d566c17d6acd6ea1f7689c45705
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecfa7c6e29fb78dd53377800cd121776a86e9e659b66a180205537ffe478c7ba
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:d5fc191a39781d29a29532aaeb1654cdf4b0edb91384f565024c58c064def636
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:547212ff5093756d6f7c74d5e6347951b86f5e392a4912233dafd205a955a5d3
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": 0.022433165460824966,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.1936108422071636,
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": 14.025,
374
  "eval_steps_per_second": 3.514,
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": 0.01937755011022091,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.3872216844143272,
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": 14.025,
374
  "eval_steps_per_second": 3.514,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.19748305905130686,
379
+ "grad_norm": 0.05130339413881302,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.0219,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.20135527589545016,
386
+ "grad_norm": 0.054578520357608795,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.0223,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.20522749273959343,
393
+ "grad_norm": 0.06454931199550629,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.027,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.2090997095837367,
400
+ "grad_norm": 0.06821908801794052,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.0162,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.21297192642787996,
407
+ "grad_norm": 0.044611573219299316,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.018,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.21684414327202323,
414
+ "grad_norm": 0.03761984035372734,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.0202,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.2207163601161665,
421
+ "grad_norm": 0.0433681458234787,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.0154,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.2245885769603098,
428
+ "grad_norm": 0.05336097627878189,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.0234,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.22846079380445306,
435
+ "grad_norm": 0.04495273903012276,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.0158,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.23233301064859632,
442
+ "grad_norm": 0.05013081058859825,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.0212,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.2362052274927396,
449
+ "grad_norm": 0.0574067123234272,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.0284,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.24007744433688286,
456
+ "grad_norm": 0.03662450611591339,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.0222,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.24394966118102615,
463
+ "grad_norm": 0.04296913370490074,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.0177,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.24782187802516942,
470
+ "grad_norm": 0.06435459107160568,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.0235,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.25169409486931266,
477
+ "grad_norm": 0.04163075610995293,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.0226,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.25556631171345595,
484
+ "grad_norm": 0.03861234709620476,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.0233,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.25943852855759925,
491
+ "grad_norm": 0.039693742990493774,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.0186,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.2633107454017425,
498
+ "grad_norm": 0.035804882645606995,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.0154,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.2671829622458858,
505
+ "grad_norm": 0.025846365839242935,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.0144,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.271055179090029,
512
+ "grad_norm": 0.05968935042619705,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.0217,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.2749273959341723,
519
+ "grad_norm": 0.06286381930112839,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.0209,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.2787996127783156,
526
+ "grad_norm": 0.028835639357566833,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.0115,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.28267182962245885,
533
+ "grad_norm": 0.04784088954329491,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.0229,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.28654404646660214,
540
+ "grad_norm": 0.05574282631278038,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.0256,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.2904162633107454,
547
+ "grad_norm": 0.04102447256445885,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.0174,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.2942884801548887,
554
+ "grad_norm": 0.0936175063252449,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.024,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.29816069699903197,
561
+ "grad_norm": 0.033699460327625275,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.0156,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.3020329138431752,
568
+ "grad_norm": 0.06190520524978638,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.0245,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.3059051306873185,
575
+ "grad_norm": 0.048285167664289474,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.0219,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.30977734753146174,
582
+ "grad_norm": 0.042587533593177795,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.0166,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.31364956437560504,
589
+ "grad_norm": 0.07332392781972885,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.024,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.31752178121974833,
596
+ "grad_norm": 0.12151223421096802,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.0241,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.3213939980638916,
603
+ "grad_norm": 0.2832794487476349,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.0219,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.32526621490803487,
610
+ "grad_norm": 0.06909225136041641,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.0254,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.3291384317521781,
617
+ "grad_norm": 0.3256091773509979,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.0196,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.3330106485963214,
624
+ "grad_norm": 0.05504089593887329,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.0228,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.33688286544046464,
631
+ "grad_norm": 0.04585348442196846,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.0182,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.34075508228460794,
638
+ "grad_norm": 0.06665895134210587,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.0198,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.34462729912875123,
645
+ "grad_norm": 0.047711923718452454,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.0206,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.34849951597289447,
652
+ "grad_norm": 0.040118634700775146,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.017,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.35237173281703776,
659
+ "grad_norm": 0.0628420040011406,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.0233,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.356243949661181,
666
+ "grad_norm": 0.05141530930995941,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.0246,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.3601161665053243,
673
+ "grad_norm": 0.08067324012517929,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.0215,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.3639883833494676,
680
+ "grad_norm": 0.0874338448047638,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.021,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.36786060019361083,
687
+ "grad_norm": 0.05889058858156204,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.0233,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.3717328170377541,
694
+ "grad_norm": 0.140172079205513,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.0247,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.37560503388189737,
701
+ "grad_norm": 0.05803554505109787,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.014,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.37947725072604066,
708
+ "grad_norm": 0.05956672504544258,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.0139,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.38334946757018395,
715
+ "grad_norm": 0.09673935920000076,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.0224,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.3872216844143272,
722
+ "grad_norm": 0.12850569188594818,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.0284,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.3872216844143272,
729
+ "eval_loss": 0.01937755011022091,
730
+ "eval_runtime": 31.0085,
731
+ "eval_samples_per_second": 14.028,
732
+ "eval_steps_per_second": 3.515,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.330508659163136e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null