prxy5608 commited on
Commit
4977171
·
verified ·
1 Parent(s): 63691ca

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 sha256:2c6c640ee5da6126222308e98a26548132b3a2d6f6d82c5ea8dd9c3a86d2f9eb
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a457ddeb6106edaa6a0a137d1c4aaf3e58b69f86aa4261d8313a44d2b56daa8
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2ef57654d650911676a4a2b7bdae2f61b38a2a60e21feeb21c8418ee9512462
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab8f83d33f6a1e6d28a89011829f42a41799a68283fe2d1cc4e464f2c61bb480
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c44fca59286bb8ad6160400b1de8d539f30cc954b6ad61a374d6974d34a50d6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1da8de79801394b512820f43a73907307b13e9f9bef31aabe782c52c67f76892
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": 0.28992101550102234,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.06438113632705618,
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": 12.148,
732
  "eval_steps_per_second": 3.037,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.5633670844134195e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.2579449415206909,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.09657170449058426,
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": 12.148,
732
  "eval_steps_per_second": 3.037,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.06502494769032674,
737
+ "grad_norm": 1.655432105064392,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.5385,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0656687590535973,
744
+ "grad_norm": 1.6436342000961304,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.6655,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.06631257041686786,
751
+ "grad_norm": 1.8506100177764893,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.832,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.06695638178013842,
758
+ "grad_norm": 1.301578402519226,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.7436,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.06760019314340898,
765
+ "grad_norm": 1.4872246980667114,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.9278,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.06824400450667954,
772
+ "grad_norm": 1.491284966468811,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.8245,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.0688878158699501,
779
+ "grad_norm": 1.6801183223724365,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.972,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.06953162723322066,
786
+ "grad_norm": 1.4707728624343872,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.7708,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.07017543859649122,
793
+ "grad_norm": 1.550600290298462,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.8869,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.07081924995976178,
800
+ "grad_norm": 1.574897289276123,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.8787,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.07146306132303235,
807
+ "grad_norm": 1.89789879322052,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.0283,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.07210687268630292,
814
+ "grad_norm": 1.9088706970214844,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.1371,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.07275068404957348,
821
+ "grad_norm": 2.1733453273773193,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.306,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.07339449541284404,
828
+ "grad_norm": 2.116964340209961,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.9345,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.0740383067761146,
835
+ "grad_norm": 1.9357224702835083,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.084,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.07468211813938516,
842
+ "grad_norm": 1.759748101234436,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.8709,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.07532592950265572,
849
+ "grad_norm": 2.208758592605591,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.1747,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.07596974086592628,
856
+ "grad_norm": 1.853180170059204,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.8755,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.07661355222919684,
863
+ "grad_norm": 2.052518606185913,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.0298,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.0772573635924674,
870
+ "grad_norm": 2.3367223739624023,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.3256,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.07790117495573796,
877
+ "grad_norm": 2.0620906352996826,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.9399,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.07854498631900853,
884
+ "grad_norm": 2.0867626667022705,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.9868,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.07918879768227909,
891
+ "grad_norm": 2.5150322914123535,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.1192,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.07983260904554966,
898
+ "grad_norm": 2.711125135421753,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.2906,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.08047642040882022,
905
+ "grad_norm": 2.1506714820861816,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.2054,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.08112023177209078,
912
+ "grad_norm": 2.3625669479370117,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.102,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.08176404313536134,
919
+ "grad_norm": 2.0529468059539795,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.0799,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.0824078544986319,
926
+ "grad_norm": 2.3510608673095703,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.1709,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.08305166586190246,
933
+ "grad_norm": 2.228466510772705,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.9181,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.08369547722517302,
940
+ "grad_norm": 2.654266595840454,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.3584,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.08433928858844358,
947
+ "grad_norm": 2.6218576431274414,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.1335,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.08498309995171414,
954
+ "grad_norm": 2.3853259086608887,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.0661,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0856269113149847,
961
+ "grad_norm": 2.351012945175171,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.878,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.08627072267825527,
968
+ "grad_norm": 2.1597161293029785,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.8321,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.08691453404152583,
975
+ "grad_norm": 3.058601140975952,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.3161,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0875583454047964,
982
+ "grad_norm": 2.6464040279388428,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.1124,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.08820215676806696,
989
+ "grad_norm": 2.425506591796875,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.9552,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.08884596813133752,
996
+ "grad_norm": 2.6761343479156494,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.0614,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.08948977949460808,
1003
+ "grad_norm": 2.7491350173950195,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.0011,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.09013359085787864,
1010
+ "grad_norm": 3.208111047744751,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.036,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.0907774022211492,
1017
+ "grad_norm": 3.00718092918396,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.1736,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.09142121358441976,
1024
+ "grad_norm": 2.9277632236480713,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.049,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.09206502494769032,
1031
+ "grad_norm": 3.495861053466797,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.4006,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.09270883631096088,
1038
+ "grad_norm": 2.722851037979126,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.984,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.09335264767423145,
1045
+ "grad_norm": 3.886777400970459,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.1988,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.093996459037502,
1052
+ "grad_norm": 3.3488070964813232,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.392,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.09464027040077258,
1059
+ "grad_norm": 4.061428070068359,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.3468,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.09528408176404314,
1066
+ "grad_norm": 3.773306131362915,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.1455,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.0959278931273137,
1073
+ "grad_norm": 4.972281455993652,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.4787,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.09657170449058426,
1080
+ "grad_norm": 12.073335647583008,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 2.0815,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.09657170449058426,
1087
+ "eval_loss": 0.2579449415206909,
1088
+ "eval_runtime": 215.3156,
1089
+ "eval_samples_per_second": 12.15,
1090
+ "eval_steps_per_second": 3.037,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.3468393761446298e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null