aleegis10 commited on
Commit
7724e43
·
verified ·
1 Parent(s): b1eb775

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:ebb648d9fa9b394d6be3a34d1553e5d28d5ad604aeb59e3bc217775e7c63a631
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11d4be5d4170423db47f89199892e411da10143208e871189601852394ff720e
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4113403d257bbd2bcac025753efaf177b27ffa2e1ca306b960543ba0c19081f8
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:411799e561cc410b78822788ffb1fc3b465c7062f4704b0d610691f9990e3f92
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c14fa63072356b62a1fcccf17dee3661f1c15a026f0da3411341f2f4dd8a8924
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7bbff652b3a1c523a517ec0158682b45b3325d70056c0d3083da185aea62aa1
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": 0.7089372873306274,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.3669724770642202,
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": 31.152,
374
  "eval_steps_per_second": 7.856,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7728482431795200.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6698483228683472,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.7339449541284404,
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": 31.152,
374
  "eval_steps_per_second": 7.856,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.3743119266055046,
379
+ "grad_norm": 0.45440104603767395,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.6622,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.381651376146789,
386
+ "grad_norm": 0.4386112093925476,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.6675,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.3889908256880734,
393
+ "grad_norm": 0.43003344535827637,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.6793,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.3963302752293578,
400
+ "grad_norm": 0.5001123547554016,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.6817,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.4036697247706422,
407
+ "grad_norm": 0.5568297505378723,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.6538,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.41100917431192663,
414
+ "grad_norm": 0.44233083724975586,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.717,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.41834862385321103,
421
+ "grad_norm": 0.5203274488449097,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.6568,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.42568807339449544,
428
+ "grad_norm": 0.529590368270874,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.7246,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.43302752293577984,
435
+ "grad_norm": 0.47836318612098694,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.6922,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.44036697247706424,
442
+ "grad_norm": 0.5171796083450317,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.7058,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.44770642201834865,
449
+ "grad_norm": 0.49430549144744873,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.6869,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.45504587155963305,
456
+ "grad_norm": 0.5193171501159668,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.7945,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.46238532110091746,
463
+ "grad_norm": 0.6313068866729736,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.7861,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.46972477064220186,
470
+ "grad_norm": 0.6041170358657837,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.7491,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.47706422018348627,
477
+ "grad_norm": 0.6043881773948669,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.9072,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.48440366972477067,
484
+ "grad_norm": 0.6289061307907104,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.9472,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.4917431192660551,
491
+ "grad_norm": 0.7074716091156006,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.0706,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.4990825688073395,
498
+ "grad_norm": 1.0272139310836792,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.249,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.5064220183486239,
505
+ "grad_norm": 0.4037744998931885,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.5478,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.5137614678899083,
512
+ "grad_norm": 0.4181773364543915,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.6575,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.5211009174311927,
519
+ "grad_norm": 0.4181150496006012,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.5975,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.5284403669724771,
526
+ "grad_norm": 0.3705148994922638,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.5462,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.5357798165137615,
533
+ "grad_norm": 0.3600141704082489,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.5123,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.5431192660550459,
540
+ "grad_norm": 0.34120720624923706,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.5915,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.5504587155963303,
547
+ "grad_norm": 0.3528464436531067,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.5901,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.5577981651376147,
554
+ "grad_norm": 0.3352064788341522,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.6071,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.5651376146788991,
561
+ "grad_norm": 0.32289859652519226,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.5741,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.5724770642201835,
568
+ "grad_norm": 0.32375475764274597,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.526,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.5798165137614679,
575
+ "grad_norm": 0.3686944544315338,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.6329,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.5871559633027523,
582
+ "grad_norm": 0.40908193588256836,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.5515,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.5944954128440367,
589
+ "grad_norm": 0.4456939697265625,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.6521,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.6018348623853211,
596
+ "grad_norm": 0.3769167959690094,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.5615,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.6091743119266055,
603
+ "grad_norm": 0.41746941208839417,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.6451,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.6165137614678899,
610
+ "grad_norm": 0.3857053816318512,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.6505,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.6238532110091743,
617
+ "grad_norm": 0.37709927558898926,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.6044,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.6311926605504588,
624
+ "grad_norm": 0.3770582675933838,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.5986,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.6385321100917432,
631
+ "grad_norm": 0.4132257103919983,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.6329,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.6458715596330276,
638
+ "grad_norm": 0.40162786841392517,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.6208,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.653211009174312,
645
+ "grad_norm": 0.428101122379303,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.6981,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.6605504587155964,
652
+ "grad_norm": 0.41267475485801697,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.6747,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.6678899082568808,
659
+ "grad_norm": 0.4253780245780945,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.6754,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.6752293577981652,
666
+ "grad_norm": 0.4702104330062866,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.6771,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.6825688073394496,
673
+ "grad_norm": 0.4644729495048523,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.7873,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.689908256880734,
680
+ "grad_norm": 0.5347480177879333,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.776,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.6972477064220184,
687
+ "grad_norm": 0.48614299297332764,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.6903,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.7045871559633028,
694
+ "grad_norm": 0.5975285768508911,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.7214,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.7119266055045872,
701
+ "grad_norm": 0.5876331329345703,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.6721,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.7192660550458716,
708
+ "grad_norm": 0.6095494031906128,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.8158,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.726605504587156,
715
+ "grad_norm": 0.5459724068641663,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.793,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.7339449541284404,
722
+ "grad_norm": 0.5794693827629089,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.8975,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.7339449541284404,
729
+ "eval_loss": 0.6698483228683472,
730
+ "eval_runtime": 7.4072,
731
+ "eval_samples_per_second": 31.051,
732
+ "eval_steps_per_second": 7.83,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.54569648635904e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null