adammandic87 commited on
Commit
0213113
·
verified ·
1 Parent(s): 7ed335d

Training in progress, step 150, 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:a0a96a2e7cf953b933f7821f6c6fe2ec6cc1df94a1c5fe701bc8d0c1480a161f
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59e723fec7efcf765b6718ac9fc2a4470eea07f988b756bd6885da87a02e56de
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c804bba2dd8a410c88ebd927b70bfc7182d9cfb0d6a36bf9c4fc2dd815eb07d6
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c8481c716bd5615b58b07ea7c11bb1b5ef46af7865a6ebea3f24d89cc60293f
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:955fc11d95973ad3e55aafab2e3c2f9e1ac3dd672ace2bf41cd1f3359c6778ae
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a701f637c15f3cdfd7666884f9cc5c15b42b346d8a6766fda320843e4c8da6b3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fc7800513a1b4dd006c457152c700dd768bb49ee4ed8e4d9665a4e42095b054
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd5d42bb0afda20ec4c83d38c6af1131541c335ecab229c74e7f418894f3c13b
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": 0.0121558378411232,
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,
@@ -731,6 +731,364 @@
731
  "eval_samples_per_second": 26.561,
732
  "eval_steps_per_second": 13.28,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -750,7 +1108,7 @@
750
  "attributes": {}
751
  }
752
  },
753
- "total_flos": 1.873061628346368e+16,
754
  "train_batch_size": 2,
755
  "trial_name": null,
756
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0182337567616848,
5
  "eval_steps": 50,
6
+ "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
731
  "eval_samples_per_second": 26.561,
732
  "eval_steps_per_second": 13.28,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.012277396219534432,
737
+ "grad_norm": 2.1093552112579346,
738
+ "learning_rate": 0.00010660905843256994,
739
+ "loss": 10.0093,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.012398954597945664,
744
+ "grad_norm": 2.1423592567443848,
745
+ "learning_rate": 0.00010495837546732224,
746
+ "loss": 9.6464,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.012520512976356896,
751
+ "grad_norm": 1.413726568222046,
752
+ "learning_rate": 0.00010330633693173082,
753
+ "loss": 9.0782,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.012642071354768128,
758
+ "grad_norm": 2.7693593502044678,
759
+ "learning_rate": 0.00010165339447663587,
760
+ "loss": 9.1446,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.01276362973317936,
765
+ "grad_norm": 1.9296963214874268,
766
+ "learning_rate": 0.0001,
767
+ "loss": 8.2252,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.012885188111590591,
772
+ "grad_norm": 2.1879448890686035,
773
+ "learning_rate": 9.834660552336415e-05,
774
+ "loss": 10.2142,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.013006746490001823,
779
+ "grad_norm": 1.3834993839263916,
780
+ "learning_rate": 9.669366306826919e-05,
781
+ "loss": 9.5412,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.013128304868413055,
786
+ "grad_norm": 1.5268234014511108,
787
+ "learning_rate": 9.504162453267777e-05,
788
+ "loss": 8.0744,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.013249863246824287,
793
+ "grad_norm": 1.9845620393753052,
794
+ "learning_rate": 9.339094156743007e-05,
795
+ "loss": 8.4186,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.01337142162523552,
800
+ "grad_norm": 1.6854311227798462,
801
+ "learning_rate": 9.174206545276677e-05,
802
+ "loss": 8.4435,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.013492980003646751,
807
+ "grad_norm": 1.5681287050247192,
808
+ "learning_rate": 9.009544697495374e-05,
809
+ "loss": 8.6079,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.013614538382057983,
814
+ "grad_norm": 1.6393003463745117,
815
+ "learning_rate": 8.845153630304139e-05,
816
+ "loss": 9.3246,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.013736096760469215,
821
+ "grad_norm": 1.6968841552734375,
822
+ "learning_rate": 8.681078286579311e-05,
823
+ "loss": 7.5143,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.013857655138880447,
828
+ "grad_norm": 1.4313429594039917,
829
+ "learning_rate": 8.517363522881579e-05,
830
+ "loss": 9.078,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.013979213517291679,
835
+ "grad_norm": 1.592039942741394,
836
+ "learning_rate": 8.35405409719266e-05,
837
+ "loss": 8.1703,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.014100771895702911,
842
+ "grad_norm": 1.4118988513946533,
843
+ "learning_rate": 8.191194656678904e-05,
844
+ "loss": 8.941,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.014222330274114143,
849
+ "grad_norm": 1.3782672882080078,
850
+ "learning_rate": 8.028829725485199e-05,
851
+ "loss": 8.4541,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.014343888652525375,
856
+ "grad_norm": 2.4915947914123535,
857
+ "learning_rate": 7.867003692562534e-05,
858
+ "loss": 7.8308,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.014465447030936607,
863
+ "grad_norm": 1.6528788805007935,
864
+ "learning_rate": 7.705760799532485e-05,
865
+ "loss": 8.732,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.014587005409347839,
870
+ "grad_norm": 2.2975354194641113,
871
+ "learning_rate": 7.54514512859201e-05,
872
+ "loss": 9.3207,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.01470856378775907,
877
+ "grad_norm": 2.4572110176086426,
878
+ "learning_rate": 7.385200590461803e-05,
879
+ "loss": 9.4007,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.014830122166170303,
884
+ "grad_norm": 1.338627576828003,
885
+ "learning_rate": 7.225970912381556e-05,
886
+ "loss": 8.8468,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.014951680544581535,
891
+ "grad_norm": 1.862164855003357,
892
+ "learning_rate": 7.067499626155354e-05,
893
+ "loss": 8.9436,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.015073238922992767,
898
+ "grad_norm": 2.2516064643859863,
899
+ "learning_rate": 6.909830056250527e-05,
900
+ "loss": 8.7996,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.015194797301403998,
905
+ "grad_norm": 1.4722728729248047,
906
+ "learning_rate": 6.753005307953167e-05,
907
+ "loss": 7.7244,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.01531635567981523,
912
+ "grad_norm": 2.090157985687256,
913
+ "learning_rate": 6.59706825558357e-05,
914
+ "loss": 8.5753,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.015437914058226464,
919
+ "grad_norm": 1.8846075534820557,
920
+ "learning_rate": 6.442061530774834e-05,
921
+ "loss": 8.9389,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.015559472436637696,
926
+ "grad_norm": 1.606086254119873,
927
+ "learning_rate": 6.28802751081779e-05,
928
+ "loss": 7.7107,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.015681030815048926,
933
+ "grad_norm": 1.6152966022491455,
934
+ "learning_rate": 6.135008307075481e-05,
935
+ "loss": 9.4444,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.01580258919346016,
940
+ "grad_norm": 2.8925600051879883,
941
+ "learning_rate": 5.983045753470308e-05,
942
+ "loss": 8.2291,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.01592414757187139,
947
+ "grad_norm": 1.3763501644134521,
948
+ "learning_rate": 5.832181395047098e-05,
949
+ "loss": 8.9548,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.016045705950282624,
954
+ "grad_norm": 1.7891381978988647,
955
+ "learning_rate": 5.6824564766150726e-05,
956
+ "loss": 8.7198,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.016167264328693854,
961
+ "grad_norm": 1.6122995615005493,
962
+ "learning_rate": 5.533911931471936e-05,
963
+ "loss": 9.8015,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.016288822707105088,
968
+ "grad_norm": 2.285371780395508,
969
+ "learning_rate": 5.386588370213124e-05,
970
+ "loss": 8.8946,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.016410381085516318,
975
+ "grad_norm": 2.1016831398010254,
976
+ "learning_rate": 5.240526069629265e-05,
977
+ "loss": 8.5699,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.01653193946392755,
982
+ "grad_norm": 1.6653213500976562,
983
+ "learning_rate": 5.095764961694922e-05,
984
+ "loss": 8.6184,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.016653497842338782,
989
+ "grad_norm": 1.4281337261199951,
990
+ "learning_rate": 4.952344622651566e-05,
991
+ "loss": 8.0501,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.016775056220750015,
996
+ "grad_norm": 1.9814000129699707,
997
+ "learning_rate": 4.810304262187852e-05,
998
+ "loss": 7.7907,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.016896614599161246,
1003
+ "grad_norm": 1.6379835605621338,
1004
+ "learning_rate": 4.669682712720065e-05,
1005
+ "loss": 8.7783,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.01701817297757248,
1010
+ "grad_norm": 2.8867030143737793,
1011
+ "learning_rate": 4.530518418775733e-05,
1012
+ "loss": 8.2023,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.01713973135598371,
1017
+ "grad_norm": 1.8214524984359741,
1018
+ "learning_rate": 4.392849426483274e-05,
1019
+ "loss": 9.0595,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.017261289734394943,
1024
+ "grad_norm": 1.807656168937683,
1025
+ "learning_rate": 4.256713373170564e-05,
1026
+ "loss": 8.4609,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.017382848112806173,
1031
+ "grad_norm": 1.7904338836669922,
1032
+ "learning_rate": 4.12214747707527e-05,
1033
+ "loss": 8.0106,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.017504406491217407,
1038
+ "grad_norm": 2.073862314224243,
1039
+ "learning_rate": 3.9891885271697496e-05,
1040
+ "loss": 8.6199,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.01762596486962864,
1045
+ "grad_norm": 1.665391445159912,
1046
+ "learning_rate": 3.857872873103322e-05,
1047
+ "loss": 9.1573,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.01774752324803987,
1052
+ "grad_norm": 2.4493348598480225,
1053
+ "learning_rate": 3.7282364152646297e-05,
1054
+ "loss": 7.3018,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.017869081626451105,
1059
+ "grad_norm": 1.4470022916793823,
1060
+ "learning_rate": 3.600314594966834e-05,
1061
+ "loss": 8.5612,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.017990640004862335,
1066
+ "grad_norm": 1.7825874090194702,
1067
+ "learning_rate": 3.4741423847583134e-05,
1068
+ "loss": 9.3814,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.01811219838327357,
1073
+ "grad_norm": 1.5861843824386597,
1074
+ "learning_rate": 3.349754278861517e-05,
1075
+ "loss": 9.1074,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.0182337567616848,
1080
+ "grad_norm": 1.8981313705444336,
1081
+ "learning_rate": 3.227184283742591e-05,
1082
+ "loss": 7.7665,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.0182337567616848,
1087
+ "eval_loss": 2.19260835647583,
1088
+ "eval_runtime": 130.7594,
1089
+ "eval_samples_per_second": 26.491,
1090
+ "eval_steps_per_second": 13.246,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1108
  "attributes": {}
1109
  }
1110
  },
1111
+ "total_flos": 2.8014486963093504e+16,
1112
  "train_batch_size": 2,
1113
  "trial_name": null,
1114
  "trial_params": null