adammandic87 commited on
Commit
fdd7c44
·
verified ·
1 Parent(s): e04f043

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:d70cb3e47b8bd9ee979708c8996046f7b914dabbeb0a4d39760a855e2b9f269e
3
  size 28351000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de78dc3363aecb9f22ecdfbeed8979c835ca4e7d5cdb30003dad7fdffe8c291a
3
  size 28351000
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75b59cd6c85c3a83d9e23469e0d25f0181da184f3fb85efaa471e939f89700ad
3
  size 14714068
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4052c7c42a47651b4b714e5edb7759f4a6564dd62afd8d519c47678b8af5170f
3
  size 14714068
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7575f737ffec765adaf6668cf5940187bdf07b93efbe422651e88cb99bf6123f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5594de2e446a7045aac3b386e78d4c1f13a9fe11214316d6159d55a78f75c60
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": 0.012718600953895072,
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": 57.185,
732
  "eval_steps_per_second": 28.601,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -750,7 +1108,7 @@
750
  "attributes": {}
751
  }
752
  },
753
- "total_flos": 5975312852582400.0,
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": 0.019077901430842606,
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": 57.185,
732
  "eval_steps_per_second": 28.601,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.012845786963434021,
737
+ "grad_norm": 2.3275163173675537,
738
+ "learning_rate": 0.00010660905843256994,
739
+ "loss": 3.1327,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.012972972972972972,
744
+ "grad_norm": 2.0324950218200684,
745
+ "learning_rate": 0.00010495837546732224,
746
+ "loss": 2.7223,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.013100158982511923,
751
+ "grad_norm": 2.420083999633789,
752
+ "learning_rate": 0.00010330633693173082,
753
+ "loss": 3.1192,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.013227344992050874,
758
+ "grad_norm": 2.116345167160034,
759
+ "learning_rate": 0.00010165339447663587,
760
+ "loss": 3.1318,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.013354531001589825,
765
+ "grad_norm": 2.523977756500244,
766
+ "learning_rate": 0.0001,
767
+ "loss": 2.8798,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.013481717011128776,
772
+ "grad_norm": 2.141871213912964,
773
+ "learning_rate": 9.834660552336415e-05,
774
+ "loss": 3.1058,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.013608903020667727,
779
+ "grad_norm": 2.2081823348999023,
780
+ "learning_rate": 9.669366306826919e-05,
781
+ "loss": 2.9769,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.013736089030206677,
786
+ "grad_norm": 2.0940332412719727,
787
+ "learning_rate": 9.504162453267777e-05,
788
+ "loss": 2.9284,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.013863275039745628,
793
+ "grad_norm": 2.2576355934143066,
794
+ "learning_rate": 9.339094156743007e-05,
795
+ "loss": 3.0978,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.013990461049284579,
800
+ "grad_norm": 2.107511043548584,
801
+ "learning_rate": 9.174206545276677e-05,
802
+ "loss": 2.8895,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.01411764705882353,
807
+ "grad_norm": 2.289916515350342,
808
+ "learning_rate": 9.009544697495374e-05,
809
+ "loss": 3.1167,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.01424483306836248,
814
+ "grad_norm": 2.1832778453826904,
815
+ "learning_rate": 8.845153630304139e-05,
816
+ "loss": 2.8849,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.014372019077901432,
821
+ "grad_norm": 2.0638606548309326,
822
+ "learning_rate": 8.681078286579311e-05,
823
+ "loss": 2.8642,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.01449920508744038,
828
+ "grad_norm": 2.2622199058532715,
829
+ "learning_rate": 8.517363522881579e-05,
830
+ "loss": 3.1066,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.014626391096979332,
835
+ "grad_norm": 2.0616939067840576,
836
+ "learning_rate": 8.35405409719266e-05,
837
+ "loss": 2.9251,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.014753577106518282,
842
+ "grad_norm": 2.2342519760131836,
843
+ "learning_rate": 8.191194656678904e-05,
844
+ "loss": 3.1882,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.014880763116057233,
849
+ "grad_norm": 2.0429413318634033,
850
+ "learning_rate": 8.028829725485199e-05,
851
+ "loss": 3.0048,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.015007949125596184,
856
+ "grad_norm": 2.2607035636901855,
857
+ "learning_rate": 7.867003692562534e-05,
858
+ "loss": 3.0522,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.015135135135135135,
863
+ "grad_norm": 2.1233274936676025,
864
+ "learning_rate": 7.705760799532485e-05,
865
+ "loss": 2.952,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.015262321144674086,
870
+ "grad_norm": 2.23429274559021,
871
+ "learning_rate": 7.54514512859201e-05,
872
+ "loss": 2.9693,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.015389507154213037,
877
+ "grad_norm": 2.315385103225708,
878
+ "learning_rate": 7.385200590461803e-05,
879
+ "loss": 3.2038,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.015516693163751987,
884
+ "grad_norm": 2.2843518257141113,
885
+ "learning_rate": 7.225970912381556e-05,
886
+ "loss": 2.7576,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.015643879173290937,
891
+ "grad_norm": 2.316584825515747,
892
+ "learning_rate": 7.067499626155354e-05,
893
+ "loss": 3.1409,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.015771065182829887,
898
+ "grad_norm": 2.1097593307495117,
899
+ "learning_rate": 6.909830056250527e-05,
900
+ "loss": 3.0405,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.01589825119236884,
905
+ "grad_norm": 2.2882628440856934,
906
+ "learning_rate": 6.753005307953167e-05,
907
+ "loss": 2.9586,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.01602543720190779,
912
+ "grad_norm": 2.2434895038604736,
913
+ "learning_rate": 6.59706825558357e-05,
914
+ "loss": 2.8796,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.01615262321144674,
919
+ "grad_norm": 2.2158470153808594,
920
+ "learning_rate": 6.442061530774834e-05,
921
+ "loss": 3.1726,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.01627980922098569,
926
+ "grad_norm": 2.311504364013672,
927
+ "learning_rate": 6.28802751081779e-05,
928
+ "loss": 3.2291,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.01640699523052464,
933
+ "grad_norm": 2.22208833694458,
934
+ "learning_rate": 6.135008307075481e-05,
935
+ "loss": 3.2121,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.016534181240063592,
940
+ "grad_norm": 2.165191650390625,
941
+ "learning_rate": 5.983045753470308e-05,
942
+ "loss": 3.103,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.016661367249602543,
947
+ "grad_norm": 2.0541014671325684,
948
+ "learning_rate": 5.832181395047098e-05,
949
+ "loss": 2.9611,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.016788553259141494,
954
+ "grad_norm": 2.2373898029327393,
955
+ "learning_rate": 5.6824564766150726e-05,
956
+ "loss": 2.7329,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.016915739268680445,
961
+ "grad_norm": 2.2604360580444336,
962
+ "learning_rate": 5.533911931471936e-05,
963
+ "loss": 2.983,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.017042925278219396,
968
+ "grad_norm": 2.3402767181396484,
969
+ "learning_rate": 5.386588370213124e-05,
970
+ "loss": 2.6614,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.017170111287758347,
975
+ "grad_norm": 2.1931848526000977,
976
+ "learning_rate": 5.240526069629265e-05,
977
+ "loss": 3.2408,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.017297297297297298,
982
+ "grad_norm": 2.2224552631378174,
983
+ "learning_rate": 5.095764961694922e-05,
984
+ "loss": 2.8428,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.01742448330683625,
989
+ "grad_norm": 2.2872660160064697,
990
+ "learning_rate": 4.952344622651566e-05,
991
+ "loss": 2.928,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.0175516693163752,
996
+ "grad_norm": 2.107144832611084,
997
+ "learning_rate": 4.810304262187852e-05,
998
+ "loss": 3.1571,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.01767885532591415,
1003
+ "grad_norm": 2.1836090087890625,
1004
+ "learning_rate": 4.669682712720065e-05,
1005
+ "loss": 2.9863,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.0178060413354531,
1010
+ "grad_norm": 2.202346086502075,
1011
+ "learning_rate": 4.530518418775733e-05,
1012
+ "loss": 3.0278,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.017933227344992052,
1017
+ "grad_norm": 2.1937851905822754,
1018
+ "learning_rate": 4.392849426483274e-05,
1019
+ "loss": 2.8878,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.018060413354531003,
1024
+ "grad_norm": 2.231384038925171,
1025
+ "learning_rate": 4.256713373170564e-05,
1026
+ "loss": 3.1869,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.018187599364069953,
1031
+ "grad_norm": 2.143895387649536,
1032
+ "learning_rate": 4.12214747707527e-05,
1033
+ "loss": 2.7143,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.018314785373608904,
1038
+ "grad_norm": 2.0842132568359375,
1039
+ "learning_rate": 3.9891885271697496e-05,
1040
+ "loss": 3.0679,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.018441971383147855,
1045
+ "grad_norm": 2.206463098526001,
1046
+ "learning_rate": 3.857872873103322e-05,
1047
+ "loss": 3.122,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.018569157392686806,
1052
+ "grad_norm": 2.248577833175659,
1053
+ "learning_rate": 3.7282364152646297e-05,
1054
+ "loss": 2.8049,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.018696343402225757,
1059
+ "grad_norm": 2.219324827194214,
1060
+ "learning_rate": 3.600314594966834e-05,
1061
+ "loss": 3.1196,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.018823529411764704,
1066
+ "grad_norm": 2.359001398086548,
1067
+ "learning_rate": 3.4741423847583134e-05,
1068
+ "loss": 3.1775,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.018950715421303655,
1073
+ "grad_norm": 2.1845834255218506,
1074
+ "learning_rate": 3.349754278861517e-05,
1075
+ "loss": 3.0865,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.019077901430842606,
1080
+ "grad_norm": 2.240842580795288,
1081
+ "learning_rate": 3.227184283742591e-05,
1082
+ "loss": 2.7162,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.019077901430842606,
1087
+ "eval_loss": 0.7287956476211548,
1088
+ "eval_runtime": 57.7804,
1089
+ "eval_samples_per_second": 57.303,
1090
+ "eval_steps_per_second": 28.66,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1108
  "attributes": {}
1109
  }
1110
  },
1111
+ "total_flos": 8955500137807872.0,
1112
  "train_batch_size": 2,
1113
  "trial_name": null,
1114
  "trial_params": null