adammandic87 commited on
Commit
bdec291
·
verified ·
1 Parent(s): 7ef9053

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 sha256:2617d34b7ff02620a0f15ec4bcb74742614d8e1caa6884632807eab3fd334723
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e06a7f677e4b3e62474b442d04d26b5557643d62b5b44dee9c369094df5e130e
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fbf860ad6081bac1cb59420081196853f0e36521c336f060271adf96dbb12d6
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee9161efefcbd4fb1c9356b062d22946c49f7c58f1ab10310d9983dab057531c
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6782a17cd94b88584cdd39e48a03aa9ee53aa99ebb01a7ca50bd04caffebba8e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac2fbbcfec39a266c55920bef9e4f13dec185fbafadb2891cdbdeaddfff2bb90
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": 0.040096230954290296,
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": 31.961,
732
  "eval_steps_per_second": 15.996,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -750,7 +1108,7 @@
750
  "attributes": {}
751
  }
752
  },
753
- "total_flos": 1.84956424814592e+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": 0.060144346431435444,
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": 31.961,
732
  "eval_steps_per_second": 15.996,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0404971932638332,
737
+ "grad_norm": 1.5585349798202515,
738
+ "learning_rate": 0.00010660905843256994,
739
+ "loss": 2.2842,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0408981555733761,
744
+ "grad_norm": 1.543447732925415,
745
+ "learning_rate": 0.00010495837546732224,
746
+ "loss": 2.4917,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.041299117882919005,
751
+ "grad_norm": 2.1124114990234375,
752
+ "learning_rate": 0.00010330633693173082,
753
+ "loss": 2.846,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.04170008019246191,
758
+ "grad_norm": 1.4116714000701904,
759
+ "learning_rate": 0.00010165339447663587,
760
+ "loss": 2.6442,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.04210104250200481,
765
+ "grad_norm": 1.71239173412323,
766
+ "learning_rate": 0.0001,
767
+ "loss": 2.6225,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.042502004811547714,
772
+ "grad_norm": 1.4659894704818726,
773
+ "learning_rate": 9.834660552336415e-05,
774
+ "loss": 2.4606,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.04290296712109062,
779
+ "grad_norm": 1.3995301723480225,
780
+ "learning_rate": 9.669366306826919e-05,
781
+ "loss": 2.4277,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.04330392943063352,
786
+ "grad_norm": 1.603670358657837,
787
+ "learning_rate": 9.504162453267777e-05,
788
+ "loss": 2.3628,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.04370489174017642,
793
+ "grad_norm": 1.8557121753692627,
794
+ "learning_rate": 9.339094156743007e-05,
795
+ "loss": 2.4918,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.044105854049719326,
800
+ "grad_norm": 1.9693793058395386,
801
+ "learning_rate": 9.174206545276677e-05,
802
+ "loss": 2.8932,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.04450681635926223,
807
+ "grad_norm": 1.4857544898986816,
808
+ "learning_rate": 9.009544697495374e-05,
809
+ "loss": 2.8325,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.04490777866880513,
814
+ "grad_norm": 1.337137222290039,
815
+ "learning_rate": 8.845153630304139e-05,
816
+ "loss": 2.1673,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.045308740978348035,
821
+ "grad_norm": 1.5540701150894165,
822
+ "learning_rate": 8.681078286579311e-05,
823
+ "loss": 2.5595,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.04570970328789094,
828
+ "grad_norm": 1.5499356985092163,
829
+ "learning_rate": 8.517363522881579e-05,
830
+ "loss": 2.7134,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.04611066559743384,
835
+ "grad_norm": 1.7475309371948242,
836
+ "learning_rate": 8.35405409719266e-05,
837
+ "loss": 2.5473,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.046511627906976744,
842
+ "grad_norm": 1.9956613779067993,
843
+ "learning_rate": 8.191194656678904e-05,
844
+ "loss": 2.8532,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.046912590216519647,
849
+ "grad_norm": 1.6928483247756958,
850
+ "learning_rate": 8.028829725485199e-05,
851
+ "loss": 2.6849,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.04731355252606255,
856
+ "grad_norm": 1.8816181421279907,
857
+ "learning_rate": 7.867003692562534e-05,
858
+ "loss": 3.0711,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.04771451483560545,
863
+ "grad_norm": 1.872065544128418,
864
+ "learning_rate": 7.705760799532485e-05,
865
+ "loss": 2.5067,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.048115477145148355,
870
+ "grad_norm": 1.433624029159546,
871
+ "learning_rate": 7.54514512859201e-05,
872
+ "loss": 2.3726,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.04851643945469126,
877
+ "grad_norm": 1.5744678974151611,
878
+ "learning_rate": 7.385200590461803e-05,
879
+ "loss": 2.3876,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.04891740176423416,
884
+ "grad_norm": 1.795422077178955,
885
+ "learning_rate": 7.225970912381556e-05,
886
+ "loss": 2.743,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.049318364073777064,
891
+ "grad_norm": 1.6976191997528076,
892
+ "learning_rate": 7.067499626155354e-05,
893
+ "loss": 2.6278,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.04971932638331997,
898
+ "grad_norm": 1.5690020322799683,
899
+ "learning_rate": 6.909830056250527e-05,
900
+ "loss": 2.3457,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.05012028869286287,
905
+ "grad_norm": 1.2351441383361816,
906
+ "learning_rate": 6.753005307953167e-05,
907
+ "loss": 2.3938,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.05052125100240577,
912
+ "grad_norm": 1.6869761943817139,
913
+ "learning_rate": 6.59706825558357e-05,
914
+ "loss": 2.3514,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.050922213311948676,
919
+ "grad_norm": 2.391761064529419,
920
+ "learning_rate": 6.442061530774834e-05,
921
+ "loss": 3.0143,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.05132317562149158,
926
+ "grad_norm": 1.3019609451293945,
927
+ "learning_rate": 6.28802751081779e-05,
928
+ "loss": 2.5286,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.05172413793103448,
933
+ "grad_norm": 1.5257257223129272,
934
+ "learning_rate": 6.135008307075481e-05,
935
+ "loss": 2.4967,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.052125100240577385,
940
+ "grad_norm": 1.4752289056777954,
941
+ "learning_rate": 5.983045753470308e-05,
942
+ "loss": 2.4128,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.05252606255012029,
947
+ "grad_norm": 1.549985408782959,
948
+ "learning_rate": 5.832181395047098e-05,
949
+ "loss": 2.2179,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.05292702485966319,
954
+ "grad_norm": 1.6170833110809326,
955
+ "learning_rate": 5.6824564766150726e-05,
956
+ "loss": 2.575,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.053327987169206094,
961
+ "grad_norm": 1.7084859609603882,
962
+ "learning_rate": 5.533911931471936e-05,
963
+ "loss": 2.7136,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.053728949478749,
968
+ "grad_norm": 1.3158146142959595,
969
+ "learning_rate": 5.386588370213124e-05,
970
+ "loss": 2.5866,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.0541299117882919,
975
+ "grad_norm": 1.4642887115478516,
976
+ "learning_rate": 5.240526069629265e-05,
977
+ "loss": 2.5958,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0545308740978348,
982
+ "grad_norm": 1.5133315324783325,
983
+ "learning_rate": 5.095764961694922e-05,
984
+ "loss": 2.4008,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.054931836407377706,
989
+ "grad_norm": 1.581939697265625,
990
+ "learning_rate": 4.952344622651566e-05,
991
+ "loss": 2.4236,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.05533279871692061,
996
+ "grad_norm": 1.4656046628952026,
997
+ "learning_rate": 4.810304262187852e-05,
998
+ "loss": 2.2784,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.05573376102646351,
1003
+ "grad_norm": 1.921011209487915,
1004
+ "learning_rate": 4.669682712720065e-05,
1005
+ "loss": 2.5987,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.056134723336006415,
1010
+ "grad_norm": 1.7307378053665161,
1011
+ "learning_rate": 4.530518418775733e-05,
1012
+ "loss": 2.4862,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.05653568564554932,
1017
+ "grad_norm": 1.6087528467178345,
1018
+ "learning_rate": 4.392849426483274e-05,
1019
+ "loss": 2.7626,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.05693664795509222,
1024
+ "grad_norm": 1.4487992525100708,
1025
+ "learning_rate": 4.256713373170564e-05,
1026
+ "loss": 2.617,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.057337610264635124,
1031
+ "grad_norm": 1.693425178527832,
1032
+ "learning_rate": 4.12214747707527e-05,
1033
+ "loss": 2.8238,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.057738572574178026,
1038
+ "grad_norm": 1.5075803995132446,
1039
+ "learning_rate": 3.9891885271697496e-05,
1040
+ "loss": 2.1947,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.05813953488372093,
1045
+ "grad_norm": 1.5750367641448975,
1046
+ "learning_rate": 3.857872873103322e-05,
1047
+ "loss": 2.7259,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.05854049719326383,
1052
+ "grad_norm": 1.5153206586837769,
1053
+ "learning_rate": 3.7282364152646297e-05,
1054
+ "loss": 2.5547,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.058941459502806735,
1059
+ "grad_norm": 1.7002588510513306,
1060
+ "learning_rate": 3.600314594966834e-05,
1061
+ "loss": 2.813,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.05934242181234964,
1066
+ "grad_norm": 1.9434531927108765,
1067
+ "learning_rate": 3.4741423847583134e-05,
1068
+ "loss": 2.9695,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.05974338412189254,
1073
+ "grad_norm": 1.6296817064285278,
1074
+ "learning_rate": 3.349754278861517e-05,
1075
+ "loss": 2.5483,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.060144346431435444,
1080
+ "grad_norm": 1.2965495586395264,
1081
+ "learning_rate": 3.227184283742591e-05,
1082
+ "loss": 2.299,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.060144346431435444,
1087
+ "eval_loss": 2.5458035469055176,
1088
+ "eval_runtime": 32.7246,
1089
+ "eval_samples_per_second": 32.117,
1090
+ "eval_steps_per_second": 16.074,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1108
  "attributes": {}
1109
  }
1110
  },
1111
+ "total_flos": 2.77434637221888e+16,
1112
  "train_batch_size": 2,
1113
  "trial_name": null,
1114
  "trial_params": null