cwaud commited on
Commit
13686c5
1 Parent(s): 00a9756

Training in progress, epoch 2, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26afaa8e070b20f1d4446a9ce387f4533c53029949b4aced1125c6132e336807
3
  size 45118424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5deef1e641a03f70336b52c3a3efb8ebefbcdb16eb98aa75bba08e1fe4032873
3
  size 45118424
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b5f73db634b92adb2988cb36a651d04a1e23bea5aeb0f2f2e37371852e1d052
3
  size 23159290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:461c10d7d47f690a9bad0ea0840c0e8dc09b351a785d985dc1f32b20c4068ecc
3
  size 23159290
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47d14ad9829124b18f2a93865fcc302b3991ce88e358c3a0da65514819594288
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a75c8ddc1097597193455db293c6504cd13a1c1919dbd19099b4ad60d6bfabb0
3
  size 14960
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:735167e790db5cb8bff2ce4b18890b4fe281d35b88f632bd30a62e5efa53a49e
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:094216163007d45050b212c7a70efe5fae78f962c8cb96c9335b05613a3052f2
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:823ab2e571bca139662e8940715d1e30a41910b2b7fa1e95b76ac5c08a9e2505
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fb1c6881d979182b2b854d82868818657102f22e08698828a952d734455b26f
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c7d2d91dfeb17ba7393f085a6ac3ebc67e92dc100cdf21f43d2f6ce2f56ca83
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e871667ddc380695d990d6c2ad338fc24321a2ffbfd570f50f1a355b41fce9f
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82e9ec35568f51cdc3e18cd10aa5a917fea7d399cd24bb6e9ad57bd20daa6db5
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f01d1f39c96959ff207a7ea1e1ec315077fbaf203b474a1febad2bfc263e3a
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": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 67,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -476,6 +476,475 @@
476
  "learning_rate": 0.0001599259454781625,
477
  "loss": 0.9156,
478
  "step": 67
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
479
  }
480
  ],
481
  "logging_steps": 1,
@@ -495,7 +964,7 @@
495
  "attributes": {}
496
  }
497
  },
498
- "total_flos": 1.7506100833786266e+17,
499
  "train_batch_size": 18,
500
  "trial_name": null,
501
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
  "eval_steps": 500,
6
+ "global_step": 134,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
476
  "learning_rate": 0.0001599259454781625,
477
  "loss": 0.9156,
478
  "step": 67
479
+ },
480
+ {
481
+ "epoch": 1.0149253731343284,
482
+ "grad_norm": 0.421875536441803,
483
+ "learning_rate": 0.00015871310546851383,
484
+ "loss": 1.1974,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 1.0298507462686568,
489
+ "grad_norm": 0.39584335684776306,
490
+ "learning_rate": 0.00015748762196955197,
491
+ "loss": 1.1015,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 1.044776119402985,
496
+ "grad_norm": 0.37235844135284424,
497
+ "learning_rate": 0.00015624981305558918,
498
+ "loss": 1.0992,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 1.0597014925373134,
503
+ "grad_norm": 0.3330038785934448,
504
+ "learning_rate": 0.000155,
505
+ "loss": 1.0614,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 1.0746268656716418,
510
+ "grad_norm": 0.3231871724128723,
511
+ "learning_rate": 0.00015373850719183454,
512
+ "loss": 0.9913,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 1.0895522388059702,
517
+ "grad_norm": 0.3235574960708618,
518
+ "learning_rate": 0.0001524656620516234,
519
+ "loss": 0.9477,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 1.1044776119402986,
524
+ "grad_norm": 0.37417852878570557,
525
+ "learning_rate": 0.0001511817949463956,
526
+ "loss": 0.9286,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 1.1194029850746268,
531
+ "grad_norm": 0.39474931359291077,
532
+ "learning_rate": 0.00014988723910393175,
533
+ "loss": 0.9042,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 1.1343283582089552,
538
+ "grad_norm": 0.485606849193573,
539
+ "learning_rate": 0.00014858233052627488,
540
+ "loss": 0.8646,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 1.1492537313432836,
545
+ "grad_norm": 0.49617916345596313,
546
+ "learning_rate": 0.00014726740790252108,
547
+ "loss": 0.8742,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 1.164179104477612,
552
+ "grad_norm": 0.46328800916671753,
553
+ "learning_rate": 0.0001459428125209126,
554
+ "loss": 0.8256,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 1.1791044776119404,
559
+ "grad_norm": 0.41910260915756226,
560
+ "learning_rate": 0.0001446088881802566,
561
+ "loss": 0.7242,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 1.1940298507462686,
566
+ "grad_norm": 0.3721103072166443,
567
+ "learning_rate": 0.000143265981100692,
568
+ "loss": 0.9349,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 1.208955223880597,
573
+ "grad_norm": 0.35940876603126526,
574
+ "learning_rate": 0.00014191443983382822,
575
+ "loss": 1.1032,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 1.2238805970149254,
580
+ "grad_norm": 0.4461018145084381,
581
+ "learning_rate": 0.00014055461517227847,
582
+ "loss": 1.0979,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 1.2388059701492538,
587
+ "grad_norm": 0.5155666470527649,
588
+ "learning_rate": 0.00013918686005861145,
589
+ "loss": 1.0231,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 1.2537313432835822,
594
+ "grad_norm": 0.5260865092277527,
595
+ "learning_rate": 0.00013781152949374526,
596
+ "loss": 1.0228,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 1.2686567164179103,
601
+ "grad_norm": 0.47857630252838135,
602
+ "learning_rate": 0.0001364289804448068,
603
+ "loss": 0.9576,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 1.2835820895522387,
608
+ "grad_norm": 0.4128516912460327,
609
+ "learning_rate": 0.00013503957175248075,
610
+ "loss": 0.9763,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 1.2985074626865671,
615
+ "grad_norm": 0.3800605535507202,
616
+ "learning_rate": 0.00013364366403787283,
617
+ "loss": 0.9272,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 1.3134328358208955,
622
+ "grad_norm": 0.3839597702026367,
623
+ "learning_rate": 0.00013224161960891025,
624
+ "loss": 0.8632,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 1.328358208955224,
629
+ "grad_norm": 0.4173763394355774,
630
+ "learning_rate": 0.0001308338023663049,
631
+ "loss": 0.8838,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 1.3432835820895521,
636
+ "grad_norm": 0.5093969106674194,
637
+ "learning_rate": 0.00012942057770910255,
638
+ "loss": 0.8444,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 1.3582089552238805,
643
+ "grad_norm": 0.5481818914413452,
644
+ "learning_rate": 0.00012800231243984401,
645
+ "loss": 0.7714,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 1.373134328358209,
650
+ "grad_norm": 0.6201927065849304,
651
+ "learning_rate": 0.00012657937466936106,
652
+ "loss": 0.707,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 1.3880597014925373,
657
+ "grad_norm": 0.5079281330108643,
658
+ "learning_rate": 0.00012515213372123345,
659
+ "loss": 1.1623,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 1.4029850746268657,
664
+ "grad_norm": 0.4763680398464203,
665
+ "learning_rate": 0.0001237209600359311,
666
+ "loss": 1.1181,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 1.417910447761194,
671
+ "grad_norm": 0.38111981749534607,
672
+ "learning_rate": 0.00012228622507466587,
673
+ "loss": 0.9978,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 1.4328358208955223,
678
+ "grad_norm": 0.38934579491615295,
679
+ "learning_rate": 0.00012084830122297907,
680
+ "loss": 1.0207,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 1.4477611940298507,
685
+ "grad_norm": 0.5346177816390991,
686
+ "learning_rate": 0.00011940756169408881,
687
+ "loss": 1.0358,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 1.462686567164179,
692
+ "grad_norm": 0.5502073764801025,
693
+ "learning_rate": 0.00011796438043202227,
694
+ "loss": 0.919,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 1.4776119402985075,
699
+ "grad_norm": 0.5650199055671692,
700
+ "learning_rate": 0.00011651913201455864,
701
+ "loss": 0.9101,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 1.4925373134328357,
706
+ "grad_norm": 0.46825388073921204,
707
+ "learning_rate": 0.00011507219155600737,
708
+ "loss": 0.9228,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 1.5074626865671643,
713
+ "grad_norm": 0.42388054728507996,
714
+ "learning_rate": 0.00011362393460984737,
715
+ "loss": 0.8535,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 1.5223880597014925,
720
+ "grad_norm": 0.39270514249801636,
721
+ "learning_rate": 0.00011217473707125192,
722
+ "loss": 0.8353,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 1.537313432835821,
727
+ "grad_norm": 0.42990821599960327,
728
+ "learning_rate": 0.0001107249750795251,
729
+ "loss": 0.7997,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 1.5522388059701493,
734
+ "grad_norm": 0.4879288375377655,
735
+ "learning_rate": 0.00010927502492047492,
736
+ "loss": 0.7087,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 1.5671641791044775,
741
+ "grad_norm": 0.4773794114589691,
742
+ "learning_rate": 0.00010782526292874813,
743
+ "loss": 0.9446,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 1.582089552238806,
748
+ "grad_norm": 0.3559342622756958,
749
+ "learning_rate": 0.00010637606539015268,
750
+ "loss": 1.0926,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 1.5970149253731343,
755
+ "grad_norm": 0.38176605105400085,
756
+ "learning_rate": 0.00010492780844399264,
757
+ "loss": 1.0961,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 1.6119402985074627,
762
+ "grad_norm": 0.37334877252578735,
763
+ "learning_rate": 0.00010348086798544141,
764
+ "loss": 1.0699,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 1.626865671641791,
769
+ "grad_norm": 0.34911951422691345,
770
+ "learning_rate": 0.00010203561956797775,
771
+ "loss": 0.9812,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 1.6417910447761193,
776
+ "grad_norm": 0.35348981618881226,
777
+ "learning_rate": 0.00010059243830591121,
778
+ "loss": 0.9875,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 1.6567164179104479,
783
+ "grad_norm": 0.36440154910087585,
784
+ "learning_rate": 9.915169877702095e-05,
785
+ "loss": 0.9164,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 1.671641791044776,
790
+ "grad_norm": 0.3861341178417206,
791
+ "learning_rate": 9.771377492533418e-05,
792
+ "loss": 0.865,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 1.6865671641791045,
797
+ "grad_norm": 0.4054892957210541,
798
+ "learning_rate": 9.627903996406892e-05,
799
+ "loss": 0.8351,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 1.7014925373134329,
804
+ "grad_norm": 0.4275088906288147,
805
+ "learning_rate": 9.484786627876654e-05,
806
+ "loss": 0.8281,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 1.716417910447761,
811
+ "grad_norm": 0.420304536819458,
812
+ "learning_rate": 9.342062533063898e-05,
813
+ "loss": 0.8573,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 1.7313432835820897,
818
+ "grad_norm": 0.3914477527141571,
819
+ "learning_rate": 9.199768756015603e-05,
820
+ "loss": 0.7773,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 1.7462686567164178,
825
+ "grad_norm": 0.43206727504730225,
826
+ "learning_rate": 9.057942229089747e-05,
827
+ "loss": 0.7021,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 1.7611940298507462,
832
+ "grad_norm": 0.43827471137046814,
833
+ "learning_rate": 8.916619763369516e-05,
834
+ "loss": 1.1523,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 1.7761194029850746,
839
+ "grad_norm": 0.3688608407974243,
840
+ "learning_rate": 8.775838039108974e-05,
841
+ "loss": 1.0733,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 1.7910447761194028,
846
+ "grad_norm": 0.35826849937438965,
847
+ "learning_rate": 8.635633596212718e-05,
848
+ "loss": 1.0442,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 1.8059701492537314,
853
+ "grad_norm": 0.35874509811401367,
854
+ "learning_rate": 8.496042824751926e-05,
855
+ "loss": 1.0133,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 1.8208955223880596,
860
+ "grad_norm": 0.3662901818752289,
861
+ "learning_rate": 8.357101955519324e-05,
862
+ "loss": 0.9586,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 1.835820895522388,
867
+ "grad_norm": 0.3741875886917114,
868
+ "learning_rate": 8.218847050625476e-05,
869
+ "loss": 0.9409,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 1.8507462686567164,
874
+ "grad_norm": 0.378964364528656,
875
+ "learning_rate": 8.081313994138857e-05,
876
+ "loss": 0.8868,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 1.8656716417910446,
881
+ "grad_norm": 0.3909272849559784,
882
+ "learning_rate": 7.944538482772156e-05,
883
+ "loss": 0.8837,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 1.8805970149253732,
888
+ "grad_norm": 0.41188931465148926,
889
+ "learning_rate": 7.808556016617178e-05,
890
+ "loss": 0.8514,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 1.8955223880597014,
895
+ "grad_norm": 0.4490172863006592,
896
+ "learning_rate": 7.673401889930802e-05,
897
+ "loss": 0.8751,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 1.9104477611940298,
902
+ "grad_norm": 0.47430258989334106,
903
+ "learning_rate": 7.539111181974343e-05,
904
+ "loss": 0.8221,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 1.9253731343283582,
909
+ "grad_norm": 0.4374563992023468,
910
+ "learning_rate": 7.405718747908743e-05,
911
+ "loss": 0.7239,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 1.9402985074626866,
916
+ "grad_norm": 0.4078747034072876,
917
+ "learning_rate": 7.273259209747896e-05,
918
+ "loss": 0.8874,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 1.955223880597015,
923
+ "grad_norm": 0.42563360929489136,
924
+ "learning_rate": 7.141766947372512e-05,
925
+ "loss": 1.0419,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 1.9701492537313432,
930
+ "grad_norm": 0.4324108362197876,
931
+ "learning_rate": 7.011276089606829e-05,
932
+ "loss": 0.948,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 1.9850746268656716,
937
+ "grad_norm": 0.42789846658706665,
938
+ "learning_rate": 6.881820505360443e-05,
939
+ "loss": 0.852,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 2.0,
944
+ "grad_norm": 0.39731353521347046,
945
+ "learning_rate": 6.753433794837662e-05,
946
+ "loss": 0.8727,
947
+ "step": 134
948
  }
949
  ],
950
  "logging_steps": 1,
 
964
  "attributes": {}
965
  }
966
  },
967
+ "total_flos": 3.501220166757253e+17,
968
  "train_batch_size": 18,
969
  "trial_name": null,
970
  "trial_params": null