prxy5607 commited on
Commit
fa525b0
·
verified ·
1 Parent(s): 4e9db4a

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:fb5468db693bb607730575a751fa34339bf3594520b9d84c756c9ed503a11d5b
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c5d4a06f2469d4775ad6e8bc822f97ff09282b64ba8607a986f7a1c50e5de57
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92924e430cf46a24276165e1b03af18dbd8f27f4dd327df696476cafaf4c87c3
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fd891300f0b57151ff5302e0ff23edbb3ccf4ea5801912579cbf537a2ce51de
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21c8a23b0768550574f58fd6414db2c741ca1af594583b6bd21da8ef69f23180
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ec4af7adb98555f7ae27652ffbb35daf6d53924da3f20ae5568655667dab0d
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": 0.614917516708374,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.2737850787132101,
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": 13.097,
732
  "eval_steps_per_second": 3.279,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.5349125663739085e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5806074738502502,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.4106776180698152,
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": 13.097,
732
  "eval_steps_per_second": 3.279,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.27652292950034224,
737
+ "grad_norm": 0.48303577303886414,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.3853,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.2792607802874743,
744
+ "grad_norm": 0.5548361539840698,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.4113,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.28199863107460643,
751
+ "grad_norm": 0.5756526589393616,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.4357,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.28473648186173856,
758
+ "grad_norm": 0.41660749912261963,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.4322,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.2874743326488706,
765
+ "grad_norm": 0.4867987334728241,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.5057,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.29021218343600275,
772
+ "grad_norm": 0.3548595905303955,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.3582,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.2929500342231348,
779
+ "grad_norm": 0.37873682379722595,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.475,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.29568788501026694,
786
+ "grad_norm": 0.4003033936023712,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.4763,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.29842573579739906,
793
+ "grad_norm": 0.4076235592365265,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.4791,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.30116358658453113,
800
+ "grad_norm": 0.4385930001735687,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.452,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.30390143737166325,
807
+ "grad_norm": 0.505478024482727,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.461,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.3066392881587953,
814
+ "grad_norm": 0.5559423565864563,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.5371,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.30937713894592744,
821
+ "grad_norm": 0.42501118779182434,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.4882,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.31211498973305957,
828
+ "grad_norm": 0.4787626564502716,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.4129,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.31485284052019163,
835
+ "grad_norm": 0.4444711208343506,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.4805,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.31759069130732376,
842
+ "grad_norm": 0.49078381061553955,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.5592,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.3203285420944558,
849
+ "grad_norm": 0.48520082235336304,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.5818,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.32306639288158795,
856
+ "grad_norm": 0.5862752199172974,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.5289,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.3258042436687201,
863
+ "grad_norm": 0.4802629351615906,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.5038,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.32854209445585214,
870
+ "grad_norm": 0.5067372918128967,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.6878,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.33127994524298426,
877
+ "grad_norm": 0.5483866930007935,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.5261,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.33401779603011633,
884
+ "grad_norm": 0.5017358064651489,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.6451,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.33675564681724846,
891
+ "grad_norm": 0.5086657404899597,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.6002,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.3394934976043806,
898
+ "grad_norm": 0.5248523950576782,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.6267,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.34223134839151265,
905
+ "grad_norm": 0.5921753644943237,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.5616,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.34496919917864477,
912
+ "grad_norm": 0.5002638697624207,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.6335,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.34770704996577684,
919
+ "grad_norm": 0.480435848236084,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.5823,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.35044490075290896,
926
+ "grad_norm": 0.5894069671630859,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.6518,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.3531827515400411,
933
+ "grad_norm": 0.4762018620967865,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.6609,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.35592060232717315,
940
+ "grad_norm": 0.5682873725891113,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.609,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.3586584531143053,
947
+ "grad_norm": 0.5159348845481873,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.6969,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.3613963039014374,
954
+ "grad_norm": 0.5835972428321838,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.646,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.36413415468856947,
961
+ "grad_norm": 0.5606144666671753,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.617,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.3668720054757016,
968
+ "grad_norm": 0.579714298248291,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.6353,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.36960985626283366,
975
+ "grad_norm": 0.5519105195999146,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.6553,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.3723477070499658,
982
+ "grad_norm": 0.5206592679023743,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.6049,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.3750855578370979,
989
+ "grad_norm": 0.6127930283546448,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.67,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.37782340862423,
996
+ "grad_norm": 0.5896944403648376,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.6948,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.3805612594113621,
1003
+ "grad_norm": 0.6119083166122437,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.646,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.38329911019849416,
1010
+ "grad_norm": 0.6493367552757263,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.6156,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.3860369609856263,
1017
+ "grad_norm": 0.6688011288642883,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.7724,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.3887748117727584,
1024
+ "grad_norm": 0.6897553205490112,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.7065,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.3915126625598905,
1031
+ "grad_norm": 0.716960608959198,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.7023,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.3942505133470226,
1038
+ "grad_norm": 0.7197480201721191,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.6764,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.39698836413415467,
1045
+ "grad_norm": 0.6134107112884521,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.5805,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.3997262149212868,
1052
+ "grad_norm": 0.6910088658332825,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.6979,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.4024640657084189,
1059
+ "grad_norm": 0.6125485301017761,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.519,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.405201916495551,
1066
+ "grad_norm": 0.6933930516242981,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.5607,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.4079397672826831,
1073
+ "grad_norm": 0.8938409686088562,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.6244,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.4106776180698152,
1080
+ "grad_norm": 0.92192143201828,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.5068,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.4106776180698152,
1087
+ "eval_loss": 0.5806074738502502,
1088
+ "eval_runtime": 46.9176,
1089
+ "eval_samples_per_second": 13.108,
1090
+ "eval_steps_per_second": 3.282,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.3004832075874304e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null