fats-fme commited on
Commit
6eaa30e
·
verified ·
1 Parent(s): 0a471b4

Training in progress, step 116, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:098b80fde50b304eb0767b5428c3c8b6cc64b9e6f62c2787efb32488a101b9b7
3
  size 97307544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898721c74f3f6db9754d0e51763590d601ef6f6aa1ea960702dec11ce90f7aa8
3
  size 97307544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01391e3b2fee1bf13f9c89a663ff2c4cb1a65492f7d73617427f196ca2852275
3
  size 194840426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3bbc704f2d554dba80c269377a8d05a954a71224277b51a710ffc1c8c2bcf47
3
  size 194840426
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:659b6a09e964783645b5091e84d59f70d163b6248c5aa2b1897b93e3f0734d14
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b16142a47bc7a326beb92cd8c6e770378643df7060bf0910e73d114e53bbb34
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c652348bad2561cbc556a0980b289872daac78c75d8c8af411d1c4697eee157b
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d7200ae41ef4ca4e25b400cb2c31ee104706220a889be74188adae29a4f900f
3
  size 14512
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bee6f3e53d6ffd322005b179d47bbd4db72e9c2f41c5d899cf3df90d9160c44
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab7b6fce0ffd68999dfaed3e79782a798f64a449077f4f179771fda8a7a023e3
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.25162689804772237,
5
  "eval_steps": 58,
6
- "global_step": 58,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -429,6 +429,420 @@
429
  "eval_samples_per_second": 8.851,
430
  "eval_steps_per_second": 2.23,
431
  "step": 58
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
432
  }
433
  ],
434
  "logging_steps": 1,
@@ -448,7 +862,7 @@
448
  "attributes": {}
449
  }
450
  },
451
- "total_flos": 1.2968071191645389e+17,
452
  "train_batch_size": 2,
453
  "trial_name": null,
454
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.5032537960954447,
5
  "eval_steps": 58,
6
+ "global_step": 116,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
429
  "eval_samples_per_second": 8.851,
430
  "eval_steps_per_second": 2.23,
431
  "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.2559652928416486,
435
+ "grad_norm": 1.147985816001892,
436
+ "learning_rate": 0.00019876883405951377,
437
+ "loss": 3.5368,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.2603036876355748,
442
+ "grad_norm": 1.167962670326233,
443
+ "learning_rate": 0.00019848077530122083,
444
+ "loss": 3.4885,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.2646420824295011,
449
+ "grad_norm": 1.1241693496704102,
450
+ "learning_rate": 0.00019816271834476642,
451
+ "loss": 3.5335,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.26898047722342733,
456
+ "grad_norm": 1.0841178894042969,
457
+ "learning_rate": 0.00019781476007338058,
458
+ "loss": 3.5822,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.27331887201735355,
463
+ "grad_norm": 1.1276164054870605,
464
+ "learning_rate": 0.00019743700647852354,
465
+ "loss": 3.4757,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.27765726681127983,
470
+ "grad_norm": 1.192659854888916,
471
+ "learning_rate": 0.00019702957262759965,
472
+ "loss": 3.4212,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.28199566160520606,
477
+ "grad_norm": 1.2061688899993896,
478
+ "learning_rate": 0.00019659258262890683,
479
+ "loss": 3.4564,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.28633405639913234,
484
+ "grad_norm": 1.4012079238891602,
485
+ "learning_rate": 0.0001961261695938319,
486
+ "loss": 3.423,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.29067245119305857,
491
+ "grad_norm": 1.3591368198394775,
492
+ "learning_rate": 0.00019563047559630357,
493
+ "loss": 3.5284,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.2950108459869848,
498
+ "grad_norm": 1.3555010557174683,
499
+ "learning_rate": 0.00019510565162951537,
500
+ "loss": 3.4406,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.2993492407809111,
505
+ "grad_norm": 1.4745391607284546,
506
+ "learning_rate": 0.0001945518575599317,
507
+ "loss": 3.3899,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.3036876355748373,
512
+ "grad_norm": 1.6432572603225708,
513
+ "learning_rate": 0.00019396926207859084,
514
+ "loss": 3.4343,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.3080260303687636,
519
+ "grad_norm": 1.9187488555908203,
520
+ "learning_rate": 0.00019335804264972018,
521
+ "loss": 3.5881,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.3123644251626898,
526
+ "grad_norm": 2.1937949657440186,
527
+ "learning_rate": 0.00019271838545667876,
528
+ "loss": 3.3765,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.31670281995661603,
533
+ "grad_norm": 2.376640558242798,
534
+ "learning_rate": 0.00019205048534524406,
535
+ "loss": 3.2758,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.3210412147505423,
540
+ "grad_norm": 3.0442004203796387,
541
+ "learning_rate": 0.0001913545457642601,
542
+ "loss": 3.5366,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.32537960954446854,
547
+ "grad_norm": 3.6359612941741943,
548
+ "learning_rate": 0.000190630778703665,
549
+ "loss": 3.0313,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.3297180043383948,
554
+ "grad_norm": 4.367193698883057,
555
+ "learning_rate": 0.0001898794046299167,
556
+ "loss": 3.3864,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.33405639913232105,
561
+ "grad_norm": 5.261653900146484,
562
+ "learning_rate": 0.0001891006524188368,
563
+ "loss": 3.5411,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.3383947939262473,
568
+ "grad_norm": 5.341316223144531,
569
+ "learning_rate": 0.00018829475928589271,
570
+ "loss": 3.843,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.34273318872017355,
575
+ "grad_norm": 2.9030559062957764,
576
+ "learning_rate": 0.00018746197071393958,
577
+ "loss": 3.4254,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.3470715835140998,
582
+ "grad_norm": 1.4780312776565552,
583
+ "learning_rate": 0.00018660254037844388,
584
+ "loss": 3.4877,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.351409978308026,
589
+ "grad_norm": 1.0593628883361816,
590
+ "learning_rate": 0.00018571673007021123,
591
+ "loss": 3.3987,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.3557483731019523,
596
+ "grad_norm": 0.9910492897033691,
597
+ "learning_rate": 0.0001848048096156426,
598
+ "loss": 3.4944,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.3600867678958785,
603
+ "grad_norm": 1.004767656326294,
604
+ "learning_rate": 0.00018386705679454242,
605
+ "loss": 3.4143,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.3644251626898048,
610
+ "grad_norm": 1.012804627418518,
611
+ "learning_rate": 0.00018290375725550417,
612
+ "loss": 3.4504,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.368763557483731,
617
+ "grad_norm": 1.0758857727050781,
618
+ "learning_rate": 0.0001819152044288992,
619
+ "loss": 3.5181,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.37310195227765725,
624
+ "grad_norm": 1.0776313543319702,
625
+ "learning_rate": 0.00018090169943749476,
626
+ "loss": 3.4293,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.3774403470715835,
631
+ "grad_norm": 1.0856565237045288,
632
+ "learning_rate": 0.00017986355100472928,
633
+ "loss": 3.3012,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.38177874186550975,
638
+ "grad_norm": 1.146246075630188,
639
+ "learning_rate": 0.00017880107536067218,
640
+ "loss": 3.5778,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.38611713665943603,
645
+ "grad_norm": 1.1812922954559326,
646
+ "learning_rate": 0.0001777145961456971,
647
+ "loss": 3.2835,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.39045553145336226,
652
+ "grad_norm": 1.3535960912704468,
653
+ "learning_rate": 0.0001766044443118978,
654
+ "loss": 3.1863,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.3947939262472885,
659
+ "grad_norm": 1.312524437904358,
660
+ "learning_rate": 0.00017547095802227723,
661
+ "loss": 3.3794,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.39913232104121477,
666
+ "grad_norm": 1.2628040313720703,
667
+ "learning_rate": 0.00017431448254773944,
668
+ "loss": 3.2127,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.403470715835141,
673
+ "grad_norm": 1.3810231685638428,
674
+ "learning_rate": 0.00017313537016191706,
675
+ "loss": 3.3664,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.4078091106290672,
680
+ "grad_norm": 1.5726513862609863,
681
+ "learning_rate": 0.0001719339800338651,
682
+ "loss": 3.4052,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.4121475054229935,
687
+ "grad_norm": 1.5839647054672241,
688
+ "learning_rate": 0.00017071067811865476,
689
+ "loss": 3.2746,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.4164859002169197,
694
+ "grad_norm": 1.7605924606323242,
695
+ "learning_rate": 0.00016946583704589973,
696
+ "loss": 3.48,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.420824295010846,
701
+ "grad_norm": 2.3345723152160645,
702
+ "learning_rate": 0.00016819983600624986,
703
+ "loss": 3.2033,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.42516268980477223,
708
+ "grad_norm": 1.9480637311935425,
709
+ "learning_rate": 0.00016691306063588583,
710
+ "loss": 3.3796,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.42950108459869846,
715
+ "grad_norm": 2.3618791103363037,
716
+ "learning_rate": 0.00016560590289905073,
717
+ "loss": 3.1398,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.43383947939262474,
722
+ "grad_norm": 3.546729326248169,
723
+ "learning_rate": 0.00016427876096865394,
724
+ "loss": 3.0558,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.43817787418655096,
729
+ "grad_norm": 1.5932743549346924,
730
+ "learning_rate": 0.00016293203910498376,
731
+ "loss": 3.3932,
732
+ "step": 101
733
+ },
734
+ {
735
+ "epoch": 0.44251626898047725,
736
+ "grad_norm": 2.039661407470703,
737
+ "learning_rate": 0.0001615661475325658,
738
+ "loss": 3.4066,
739
+ "step": 102
740
+ },
741
+ {
742
+ "epoch": 0.44685466377440347,
743
+ "grad_norm": 1.742119312286377,
744
+ "learning_rate": 0.00016018150231520486,
745
+ "loss": 3.2823,
746
+ "step": 103
747
+ },
748
+ {
749
+ "epoch": 0.4511930585683297,
750
+ "grad_norm": 1.5700186491012573,
751
+ "learning_rate": 0.00015877852522924732,
752
+ "loss": 3.3591,
753
+ "step": 104
754
+ },
755
+ {
756
+ "epoch": 0.455531453362256,
757
+ "grad_norm": 1.136389970779419,
758
+ "learning_rate": 0.0001573576436351046,
759
+ "loss": 3.4663,
760
+ "step": 105
761
+ },
762
+ {
763
+ "epoch": 0.4598698481561822,
764
+ "grad_norm": 0.8537334203720093,
765
+ "learning_rate": 0.0001559192903470747,
766
+ "loss": 3.4367,
767
+ "step": 106
768
+ },
769
+ {
770
+ "epoch": 0.4642082429501085,
771
+ "grad_norm": 0.8642299175262451,
772
+ "learning_rate": 0.00015446390350150273,
773
+ "loss": 3.287,
774
+ "step": 107
775
+ },
776
+ {
777
+ "epoch": 0.4685466377440347,
778
+ "grad_norm": 0.9279235601425171,
779
+ "learning_rate": 0.0001529919264233205,
780
+ "loss": 3.2911,
781
+ "step": 108
782
+ },
783
+ {
784
+ "epoch": 0.47288503253796094,
785
+ "grad_norm": 0.9121331572532654,
786
+ "learning_rate": 0.00015150380749100545,
787
+ "loss": 3.3101,
788
+ "step": 109
789
+ },
790
+ {
791
+ "epoch": 0.4772234273318872,
792
+ "grad_norm": 0.9868795275688171,
793
+ "learning_rate": 0.00015000000000000001,
794
+ "loss": 3.3431,
795
+ "step": 110
796
+ },
797
+ {
798
+ "epoch": 0.48156182212581344,
799
+ "grad_norm": 1.0646886825561523,
800
+ "learning_rate": 0.00014848096202463372,
801
+ "loss": 3.3876,
802
+ "step": 111
803
+ },
804
+ {
805
+ "epoch": 0.48590021691973967,
806
+ "grad_norm": 1.0819416046142578,
807
+ "learning_rate": 0.00014694715627858908,
808
+ "loss": 3.2128,
809
+ "step": 112
810
+ },
811
+ {
812
+ "epoch": 0.49023861171366595,
813
+ "grad_norm": 1.0728636980056763,
814
+ "learning_rate": 0.00014539904997395468,
815
+ "loss": 3.2076,
816
+ "step": 113
817
+ },
818
+ {
819
+ "epoch": 0.4945770065075922,
820
+ "grad_norm": 1.1562669277191162,
821
+ "learning_rate": 0.00014383711467890774,
822
+ "loss": 3.2825,
823
+ "step": 114
824
+ },
825
+ {
826
+ "epoch": 0.49891540130151846,
827
+ "grad_norm": 1.1967557668685913,
828
+ "learning_rate": 0.00014226182617406996,
829
+ "loss": 3.2185,
830
+ "step": 115
831
+ },
832
+ {
833
+ "epoch": 0.5032537960954447,
834
+ "grad_norm": 1.3139584064483643,
835
+ "learning_rate": 0.00014067366430758004,
836
+ "loss": 3.1373,
837
+ "step": 116
838
+ },
839
+ {
840
+ "epoch": 0.5032537960954447,
841
+ "eval_loss": 3.2728052139282227,
842
+ "eval_runtime": 43.9403,
843
+ "eval_samples_per_second": 8.853,
844
+ "eval_steps_per_second": 2.23,
845
+ "step": 116
846
  }
847
  ],
848
  "logging_steps": 1,
 
862
  "attributes": {}
863
  }
864
  },
865
+ "total_flos": 2.5936142383290778e+17,
866
  "train_batch_size": 2,
867
  "trial_name": null,
868
  "trial_params": null