bbytxt commited on
Commit
ff59d6c
·
verified ·
1 Parent(s): dfee0b4

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 sha256:0958b7c2f0601e62bee2087e2007d80b5b2acfceb5f2a49fe52f88f3273d6630
3
  size 63592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd2f671d7188fe94c623790ad2e45a520a6bca830cb2204cefb7c47dcd122800
3
  size 63592
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20e564c96da04714fdfd654420aee3868eda81ce312b8db914eba996352a1f57
3
  size 136814
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25479eb18f573d534f178ada9b9e969f221e608667a9ca3e432f82ff0d14f87c
3
  size 136814
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46557ca5ec0a1a09e98baf727fca56ea3045f27e6aa2396d49d26a03ff7dcceb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d00b899626390a5d0d26e6a5ae73a9418e5abd2a9a1c34b8878959082261e1a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f1cc9afd56c8282f59607c4f273b7bc247d970043d317c3651db16eb05eaec8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33fdeac700456f590554babdb1bb06f3350befc1bacd0a19b3d33f64c1a1c32d
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 10.535416603088379,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.7604562737642585,
5
  "eval_steps": 25,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -381,6 +381,372 @@
381
  "eval_samples_per_second": 463.538,
382
  "eval_steps_per_second": 64.895,
383
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
384
  }
385
  ],
386
  "logging_steps": 1,
@@ -409,7 +775,7 @@
409
  "attributes": {}
410
  }
411
  },
412
- "total_flos": 397737984000.0,
413
  "train_batch_size": 8,
414
  "trial_name": null,
415
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.526249885559082,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.5285171102661597,
5
  "eval_steps": 25,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
381
  "eval_samples_per_second": 463.538,
382
  "eval_steps_per_second": 64.895,
383
  "step": 50
384
+ },
385
+ {
386
+ "epoch": 0.7756653992395437,
387
+ "grad_norm": 0.7378947138786316,
388
+ "learning_rate": 0.00022388221019307967,
389
+ "loss": 42.1719,
390
+ "step": 51
391
+ },
392
+ {
393
+ "epoch": 0.7908745247148289,
394
+ "grad_norm": 0.8719134330749512,
395
+ "learning_rate": 0.000220496511454098,
396
+ "loss": 42.1641,
397
+ "step": 52
398
+ },
399
+ {
400
+ "epoch": 0.8060836501901141,
401
+ "grad_norm": 0.7421266436576843,
402
+ "learning_rate": 0.00021706406894776709,
403
+ "loss": 42.2005,
404
+ "step": 53
405
+ },
406
+ {
407
+ "epoch": 0.8212927756653993,
408
+ "grad_norm": 0.8768603205680847,
409
+ "learning_rate": 0.0002135871586064791,
410
+ "loss": 42.1771,
411
+ "step": 54
412
+ },
413
+ {
414
+ "epoch": 0.8365019011406845,
415
+ "grad_norm": 0.6931475400924683,
416
+ "learning_rate": 0.00021006808584768998,
417
+ "loss": 42.1979,
418
+ "step": 55
419
+ },
420
+ {
421
+ "epoch": 0.8517110266159695,
422
+ "grad_norm": 0.5837717652320862,
423
+ "learning_rate": 0.00020650918404527775,
424
+ "loss": 42.1406,
425
+ "step": 56
426
+ },
427
+ {
428
+ "epoch": 0.8669201520912547,
429
+ "grad_norm": 0.712273895740509,
430
+ "learning_rate": 0.00020291281298236423,
431
+ "loss": 42.1328,
432
+ "step": 57
433
+ },
434
+ {
435
+ "epoch": 0.8821292775665399,
436
+ "grad_norm": 0.8226441740989685,
437
+ "learning_rate": 0.00019928135728662522,
438
+ "loss": 42.1745,
439
+ "step": 58
440
+ },
441
+ {
442
+ "epoch": 0.8973384030418251,
443
+ "grad_norm": 0.617861270904541,
444
+ "learning_rate": 0.0001956172248491277,
445
+ "loss": 42.1719,
446
+ "step": 59
447
+ },
448
+ {
449
+ "epoch": 0.9125475285171103,
450
+ "grad_norm": 0.6812199950218201,
451
+ "learning_rate": 0.00019192284522774142,
452
+ "loss": 42.1484,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 0.9277566539923955,
457
+ "grad_norm": 0.6634241342544556,
458
+ "learning_rate": 0.00018820066803618428,
459
+ "loss": 42.1615,
460
+ "step": 61
461
+ },
462
+ {
463
+ "epoch": 0.9429657794676806,
464
+ "grad_norm": 0.5809543132781982,
465
+ "learning_rate": 0.00018445316131976934,
466
+ "loss": 42.1432,
467
+ "step": 62
468
+ },
469
+ {
470
+ "epoch": 0.9581749049429658,
471
+ "grad_norm": 0.8210413455963135,
472
+ "learning_rate": 0.00018068280991893014,
473
+ "loss": 42.1901,
474
+ "step": 63
475
+ },
476
+ {
477
+ "epoch": 0.973384030418251,
478
+ "grad_norm": 1.388875961303711,
479
+ "learning_rate": 0.00017689211382161034,
480
+ "loss": 42.2708,
481
+ "step": 64
482
+ },
483
+ {
484
+ "epoch": 0.9885931558935361,
485
+ "grad_norm": 0.802690327167511,
486
+ "learning_rate": 0.00017308358650560928,
487
+ "loss": 42.1328,
488
+ "step": 65
489
+ },
490
+ {
491
+ "epoch": 1.0114068441064639,
492
+ "grad_norm": 0.6896817088127136,
493
+ "learning_rate": 0.00016925975327198266,
494
+ "loss": 42.1927,
495
+ "step": 66
496
+ },
497
+ {
498
+ "epoch": 1.026615969581749,
499
+ "grad_norm": 0.818332850933075,
500
+ "learning_rate": 0.00016542314957060405,
501
+ "loss": 42.1562,
502
+ "step": 67
503
+ },
504
+ {
505
+ "epoch": 1.0418250950570342,
506
+ "grad_norm": 0.49196258187294006,
507
+ "learning_rate": 0.00016157631931899697,
508
+ "loss": 42.125,
509
+ "step": 68
510
+ },
511
+ {
512
+ "epoch": 1.0570342205323193,
513
+ "grad_norm": 0.43189793825149536,
514
+ "learning_rate": 0.00015772181321555196,
515
+ "loss": 42.1172,
516
+ "step": 69
517
+ },
518
+ {
519
+ "epoch": 1.0722433460076046,
520
+ "grad_norm": 0.3118878901004791,
521
+ "learning_rate": 0.0001538621870482483,
522
+ "loss": 42.1068,
523
+ "step": 70
524
+ },
525
+ {
526
+ "epoch": 1.0874524714828897,
527
+ "grad_norm": 0.5249186158180237,
528
+ "learning_rate": 0.00015,
529
+ "loss": 42.151,
530
+ "step": 71
531
+ },
532
+ {
533
+ "epoch": 1.102661596958175,
534
+ "grad_norm": 0.6453397274017334,
535
+ "learning_rate": 0.00014613781295175172,
536
+ "loss": 42.1589,
537
+ "step": 72
538
+ },
539
+ {
540
+ "epoch": 1.11787072243346,
541
+ "grad_norm": 0.34862664341926575,
542
+ "learning_rate": 0.000142278186784448,
543
+ "loss": 42.125,
544
+ "step": 73
545
+ },
546
+ {
547
+ "epoch": 1.1330798479087452,
548
+ "grad_norm": 0.37730568647384644,
549
+ "learning_rate": 0.00013842368068100303,
550
+ "loss": 42.1198,
551
+ "step": 74
552
+ },
553
+ {
554
+ "epoch": 1.1482889733840305,
555
+ "grad_norm": 0.39992350339889526,
556
+ "learning_rate": 0.00013457685042939592,
557
+ "loss": 42.138,
558
+ "step": 75
559
+ },
560
+ {
561
+ "epoch": 1.1482889733840305,
562
+ "eval_loss": 10.527915954589844,
563
+ "eval_runtime": 0.106,
564
+ "eval_samples_per_second": 471.538,
565
+ "eval_steps_per_second": 66.015,
566
+ "step": 75
567
+ },
568
+ {
569
+ "epoch": 1.1634980988593155,
570
+ "grad_norm": 0.9189149141311646,
571
+ "learning_rate": 0.00013074024672801731,
572
+ "loss": 42.1536,
573
+ "step": 76
574
+ },
575
+ {
576
+ "epoch": 1.1787072243346008,
577
+ "grad_norm": 0.5288547873497009,
578
+ "learning_rate": 0.0001269164134943907,
579
+ "loss": 42.1667,
580
+ "step": 77
581
+ },
582
+ {
583
+ "epoch": 1.193916349809886,
584
+ "grad_norm": 0.5245852470397949,
585
+ "learning_rate": 0.00012310788617838966,
586
+ "loss": 42.1432,
587
+ "step": 78
588
+ },
589
+ {
590
+ "epoch": 1.209125475285171,
591
+ "grad_norm": 0.670550525188446,
592
+ "learning_rate": 0.0001193171900810699,
593
+ "loss": 42.1536,
594
+ "step": 79
595
+ },
596
+ {
597
+ "epoch": 1.2243346007604563,
598
+ "grad_norm": 0.6620810031890869,
599
+ "learning_rate": 0.00011554683868023067,
600
+ "loss": 42.1406,
601
+ "step": 80
602
+ },
603
+ {
604
+ "epoch": 1.2395437262357414,
605
+ "grad_norm": 0.7172536253929138,
606
+ "learning_rate": 0.0001117993319638157,
607
+ "loss": 42.1667,
608
+ "step": 81
609
+ },
610
+ {
611
+ "epoch": 1.2547528517110267,
612
+ "grad_norm": 0.6294752359390259,
613
+ "learning_rate": 0.00010807715477225858,
614
+ "loss": 42.1797,
615
+ "step": 82
616
+ },
617
+ {
618
+ "epoch": 1.2699619771863118,
619
+ "grad_norm": 0.5978144407272339,
620
+ "learning_rate": 0.00010438277515087233,
621
+ "loss": 42.1667,
622
+ "step": 83
623
+ },
624
+ {
625
+ "epoch": 1.285171102661597,
626
+ "grad_norm": 0.5058898329734802,
627
+ "learning_rate": 0.00010071864271337478,
628
+ "loss": 42.125,
629
+ "step": 84
630
+ },
631
+ {
632
+ "epoch": 1.3003802281368821,
633
+ "grad_norm": 0.5284583568572998,
634
+ "learning_rate": 9.708718701763577e-05,
635
+ "loss": 42.112,
636
+ "step": 85
637
+ },
638
+ {
639
+ "epoch": 1.3155893536121672,
640
+ "grad_norm": 0.5570880770683289,
641
+ "learning_rate": 9.34908159547222e-05,
642
+ "loss": 42.1302,
643
+ "step": 86
644
+ },
645
+ {
646
+ "epoch": 1.3307984790874525,
647
+ "grad_norm": 0.44924110174179077,
648
+ "learning_rate": 8.993191415231e-05,
649
+ "loss": 42.1536,
650
+ "step": 87
651
+ },
652
+ {
653
+ "epoch": 1.3460076045627376,
654
+ "grad_norm": 0.5590141415596008,
655
+ "learning_rate": 8.641284139352091e-05,
656
+ "loss": 42.1406,
657
+ "step": 88
658
+ },
659
+ {
660
+ "epoch": 1.3612167300380227,
661
+ "grad_norm": 0.3548166751861572,
662
+ "learning_rate": 8.293593105223287e-05,
663
+ "loss": 42.1042,
664
+ "step": 89
665
+ },
666
+ {
667
+ "epoch": 1.376425855513308,
668
+ "grad_norm": 0.46111956238746643,
669
+ "learning_rate": 7.950348854590204e-05,
670
+ "loss": 42.112,
671
+ "step": 90
672
+ },
673
+ {
674
+ "epoch": 1.3916349809885933,
675
+ "grad_norm": 0.2855987846851349,
676
+ "learning_rate": 7.611778980692035e-05,
677
+ "loss": 42.1094,
678
+ "step": 91
679
+ },
680
+ {
681
+ "epoch": 1.4068441064638784,
682
+ "grad_norm": 0.3709195852279663,
683
+ "learning_rate": 7.278107977352543e-05,
684
+ "loss": 42.138,
685
+ "step": 92
686
+ },
687
+ {
688
+ "epoch": 1.4220532319391634,
689
+ "grad_norm": 0.8047066330909729,
690
+ "learning_rate": 6.949557090125994e-05,
691
+ "loss": 42.1667,
692
+ "step": 93
693
+ },
694
+ {
695
+ "epoch": 1.4372623574144487,
696
+ "grad_norm": 0.5303740501403809,
697
+ "learning_rate": 6.626344169597031e-05,
698
+ "loss": 42.125,
699
+ "step": 94
700
+ },
701
+ {
702
+ "epoch": 1.4524714828897338,
703
+ "grad_norm": 0.41722556948661804,
704
+ "learning_rate": 6.308683526931545e-05,
705
+ "loss": 42.125,
706
+ "step": 95
707
+ },
708
+ {
709
+ "epoch": 1.467680608365019,
710
+ "grad_norm": 1.1801074743270874,
711
+ "learning_rate": 5.996785791774478e-05,
712
+ "loss": 42.2188,
713
+ "step": 96
714
+ },
715
+ {
716
+ "epoch": 1.4828897338403042,
717
+ "grad_norm": 0.8621243238449097,
718
+ "learning_rate": 5.690857772588657e-05,
719
+ "loss": 42.1849,
720
+ "step": 97
721
+ },
722
+ {
723
+ "epoch": 1.4980988593155893,
724
+ "grad_norm": 1.1932792663574219,
725
+ "learning_rate": 5.391102319527373e-05,
726
+ "loss": 42.2187,
727
+ "step": 98
728
+ },
729
+ {
730
+ "epoch": 1.5133079847908744,
731
+ "grad_norm": 0.38025224208831787,
732
+ "learning_rate": 5.0977181899315214e-05,
733
+ "loss": 42.1276,
734
+ "step": 99
735
+ },
736
+ {
737
+ "epoch": 1.5285171102661597,
738
+ "grad_norm": 0.39083558320999146,
739
+ "learning_rate": 4.8108999165406026e-05,
740
+ "loss": 42.1458,
741
+ "step": 100
742
+ },
743
+ {
744
+ "epoch": 1.5285171102661597,
745
+ "eval_loss": 10.526249885559082,
746
+ "eval_runtime": 0.1068,
747
+ "eval_samples_per_second": 467.988,
748
+ "eval_steps_per_second": 65.518,
749
+ "step": 100
750
  }
751
  ],
752
  "logging_steps": 1,
 
775
  "attributes": {}
776
  }
777
  },
778
+ "total_flos": 795475968000.0,
779
  "train_batch_size": 8,
780
  "trial_name": null,
781
  "trial_params": null