nttx commited on
Commit
3ef3c65
·
verified ·
1 Parent(s): 46f5147

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 sha256:6a10e85d0728ab5bb7cfad7cc52da84903c177c0d0e2b73757cf83db50f704d4
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01e7f8a022cd09f3ac69d690ab3483cda1c7c7e8cf152c0c032fd0b1f846e08f
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1f9b116628bd10f5316343fa01ce0ee24123d63670c8427b792897280d0a512
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4c5c879bdd4490b819b8fef8d7f358fe4423450997475a4c64c7fa2592fcf6c
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:572be7ccf37545493bf8972ac483bb8f2a29a96ec513a15b1fa85cf174f7dd4e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:029ae6d42888f0f9e4bb9312ba6e8b60d0215919beaff69d83f06391ed42bfa5
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.03212686628103256,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.4652014652014653,
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": 33.37,
732
  "eval_steps_per_second": 8.415,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.729101377404928e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.0043426197953522205,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 2.197802197802198,
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": 33.37,
732
  "eval_steps_per_second": 8.415,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.47985347985348,
737
+ "grad_norm": 0.22860318422317505,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.0025,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.4945054945054945,
744
+ "grad_norm": 0.3643300235271454,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.0029,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.5091575091575091,
751
+ "grad_norm": 1.091467022895813,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.1556,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.5238095238095237,
758
+ "grad_norm": 0.8354416489601135,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.0959,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.5384615384615383,
765
+ "grad_norm": 1.269963264465332,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.0634,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.5531135531135531,
772
+ "grad_norm": 0.41050803661346436,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.0348,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.5677655677655677,
779
+ "grad_norm": 0.381136029958725,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.0258,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.5824175824175826,
786
+ "grad_norm": 0.3236844837665558,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.026,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.5970695970695972,
793
+ "grad_norm": 0.6296079754829407,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.0352,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.6117216117216118,
800
+ "grad_norm": 0.43410807847976685,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.0241,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.6263736263736264,
807
+ "grad_norm": 0.5278913378715515,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.0235,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.641025641025641,
814
+ "grad_norm": 0.4789339005947113,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.0134,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.6556776556776556,
821
+ "grad_norm": 0.14194229245185852,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.0037,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.6703296703296702,
828
+ "grad_norm": 0.06887496262788773,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.0027,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.684981684981685,
835
+ "grad_norm": 0.1691749542951584,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.0041,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.6996336996336996,
842
+ "grad_norm": 0.32316136360168457,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.0087,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.7142857142857144,
849
+ "grad_norm": 0.20666715502738953,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.0069,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.728937728937729,
856
+ "grad_norm": 0.1677791327238083,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.0041,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.7435897435897436,
863
+ "grad_norm": 0.2694739103317261,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.0149,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.7582417582417582,
870
+ "grad_norm": 0.5503838658332825,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.0483,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.7728937728937728,
877
+ "grad_norm": 0.8629624843597412,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.0514,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.7875457875457874,
884
+ "grad_norm": 0.7726304531097412,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.0419,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.8021978021978022,
891
+ "grad_norm": 0.4805305004119873,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.02,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.8168498168498168,
898
+ "grad_norm": 0.2010086476802826,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.0109,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.8315018315018317,
905
+ "grad_norm": 0.20322047173976898,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.0144,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.8461538461538463,
912
+ "grad_norm": 0.8529400825500488,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.0378,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.8608058608058609,
919
+ "grad_norm": 0.5172489881515503,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.018,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.8754578754578755,
926
+ "grad_norm": 0.6631051898002625,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.0155,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.89010989010989,
933
+ "grad_norm": 0.19856305420398712,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.0065,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.9047619047619047,
940
+ "grad_norm": 0.2891700267791748,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.0053,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.9194139194139193,
947
+ "grad_norm": 0.15734972059726715,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.0022,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.934065934065934,
954
+ "grad_norm": 0.048469528555870056,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.0018,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.9487179487179487,
961
+ "grad_norm": 0.05388571694493294,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.0018,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.9633699633699635,
968
+ "grad_norm": 0.05657542869448662,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.0017,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.978021978021978,
975
+ "grad_norm": 0.24223290383815765,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.0061,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.9926739926739927,
982
+ "grad_norm": 0.1939966380596161,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.0055,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 2.0073260073260073,
989
+ "grad_norm": 0.27042555809020996,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.017,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 2.021978021978022,
996
+ "grad_norm": 0.32032516598701477,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.0222,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 2.0366300366300365,
1003
+ "grad_norm": 0.3312196433544159,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.0122,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 2.051282051282051,
1010
+ "grad_norm": 0.35154223442077637,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.0074,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 2.065934065934066,
1017
+ "grad_norm": 0.16670069098472595,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.0063,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 2.0805860805860807,
1024
+ "grad_norm": 0.06954033672809601,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.0041,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 2.0952380952380953,
1031
+ "grad_norm": 0.08824688196182251,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.0042,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 2.10989010989011,
1038
+ "grad_norm": 0.11472660303115845,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.0044,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 2.1245421245421245,
1045
+ "grad_norm": 0.20808860659599304,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.0049,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 2.139194139194139,
1052
+ "grad_norm": 0.15601789951324463,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.0053,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 2.1538461538461537,
1059
+ "grad_norm": 0.07053323835134506,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.0019,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 2.1684981684981683,
1066
+ "grad_norm": 0.04543652758002281,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.0016,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 2.183150183150183,
1073
+ "grad_norm": 0.02706839144229889,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.0011,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 2.197802197802198,
1080
+ "grad_norm": 0.028567973524332047,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.0012,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 2.197802197802198,
1087
+ "eval_loss": 0.0043426197953522205,
1088
+ "eval_runtime": 3.4484,
1089
+ "eval_samples_per_second": 33.348,
1090
+ "eval_steps_per_second": 8.41,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.09067548311552e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null