prxy5608 commited on
Commit
afd8085
·
verified ·
1 Parent(s): 5a94913

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:ac1d2f7e1abd95a89530dd0d4f778c9100c44bbeec8fbcb48fdf4d12eb524480
3
  size 239906848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99d62c7ee21e1179da8d694b0e7d0891a39c27b78379570ca555db8c4357c365
3
  size 239906848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d868fe2217c545dc73bd5ef74fb689326c9ca3fa9e1f6441e18d2605393d7a63
3
  size 122200212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89fc56e5702137f81a9e3b254846ba6ced59ab927e2076471ab19ffcdd23e9a6
3
  size 122200212
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23129ad987a265315df526ef0e5112247fc3b18fe86fc980088b8f7016853a2f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aaf711658cd51445671fdd962cb28b0a4fc1238ef53696203c58bbcad8ea57c
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": 1.4100725650787354,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.010804094751910975,
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": 28.966,
732
  "eval_steps_per_second": 7.243,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.87894460022784e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3888720273971558,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.01620614212786646,
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": 28.966,
732
  "eval_steps_per_second": 7.243,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.010912135699430083,
737
+ "grad_norm": 0.5693991184234619,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.5698,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.011020176646949193,
744
+ "grad_norm": 0.49347609281539917,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.4305,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.011128217594468304,
751
+ "grad_norm": 0.5346347093582153,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.5587,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.011236258541987414,
758
+ "grad_norm": 0.5068135261535645,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.5091,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.011344299489506523,
765
+ "grad_norm": 0.4623704254627228,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.5017,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.011452340437025633,
772
+ "grad_norm": 0.5210311412811279,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.36,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.011560381384544743,
779
+ "grad_norm": 0.5300119519233704,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.6299,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.011668422332063852,
786
+ "grad_norm": 0.5147326588630676,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.4485,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.011776463279582962,
793
+ "grad_norm": 0.5882423520088196,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.7687,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.011884504227102072,
800
+ "grad_norm": 0.5375576019287109,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.4911,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.01199254517462118,
807
+ "grad_norm": 0.5624399185180664,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.5786,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.012100586122140291,
814
+ "grad_norm": 0.6138778924942017,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.6166,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.012208627069659401,
821
+ "grad_norm": 0.5514253973960876,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.5979,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.012316668017178511,
828
+ "grad_norm": 0.564391016960144,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.5839,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.01242470896469762,
835
+ "grad_norm": 0.5756611824035645,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.5276,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.01253274991221673,
842
+ "grad_norm": 0.57477205991745,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.6878,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.01264079085973584,
849
+ "grad_norm": 0.5562359094619751,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.6031,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.012748831807254949,
856
+ "grad_norm": 0.5711321234703064,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.604,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.01285687275477406,
863
+ "grad_norm": 0.5932537317276001,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.5897,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.01296491370229317,
870
+ "grad_norm": 0.6095288395881653,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.5861,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.013072954649812278,
877
+ "grad_norm": 0.5559149384498596,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.4496,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.013180995597331388,
884
+ "grad_norm": 0.6278871297836304,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.3942,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.013289036544850499,
891
+ "grad_norm": 0.7265165448188782,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.5126,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.013397077492369609,
898
+ "grad_norm": 0.5562739968299866,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.4249,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.013505118439888717,
905
+ "grad_norm": 0.5824069380760193,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.3123,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.013613159387407828,
912
+ "grad_norm": 0.5717520117759705,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.3415,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.013721200334926938,
919
+ "grad_norm": 0.5535140037536621,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.3216,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.013829241282446047,
926
+ "grad_norm": 0.5388808846473694,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.3851,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.013937282229965157,
933
+ "grad_norm": 0.5416645407676697,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.3414,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.014045323177484267,
940
+ "grad_norm": 0.5166726112365723,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.342,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.014153364125003376,
947
+ "grad_norm": 0.527347981929779,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.3069,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.014261405072522486,
954
+ "grad_norm": 0.4782974421977997,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.1905,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.014369446020041596,
961
+ "grad_norm": 0.477867990732193,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.2083,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.014477486967560705,
968
+ "grad_norm": 0.5195420980453491,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.3235,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.014585527915079815,
975
+ "grad_norm": 0.5254411697387695,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.2766,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.014693568862598925,
982
+ "grad_norm": 0.5908624529838562,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.2454,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.014801609810118035,
989
+ "grad_norm": 0.49801841378211975,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.1768,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.014909650757637144,
996
+ "grad_norm": 0.5246025919914246,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.2514,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.015017691705156254,
1003
+ "grad_norm": 0.5168302655220032,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.2134,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.015125732652675365,
1010
+ "grad_norm": 0.6382246017456055,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.3435,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.015233773600194473,
1017
+ "grad_norm": 0.5208078026771545,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.2451,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.015341814547713583,
1024
+ "grad_norm": 0.5606635808944702,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.2622,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.015449855495232694,
1031
+ "grad_norm": 0.5353780388832092,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.1051,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.015557896442751802,
1038
+ "grad_norm": 0.5248527526855469,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.2632,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.015665937390270914,
1045
+ "grad_norm": 0.5635786056518555,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.2632,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.015773978337790023,
1052
+ "grad_norm": 0.5712494254112244,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.2468,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.01588201928530913,
1059
+ "grad_norm": 0.4934338927268982,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.1091,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.015990060232828243,
1066
+ "grad_norm": 0.5326967239379883,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.1771,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.01609810118034735,
1073
+ "grad_norm": 0.5374605059623718,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.0806,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.01620614212786646,
1080
+ "grad_norm": 0.6305158734321594,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.2577,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.01620614212786646,
1087
+ "eval_loss": 1.3888720273971558,
1088
+ "eval_runtime": 538.0843,
1089
+ "eval_samples_per_second": 28.971,
1090
+ "eval_steps_per_second": 7.244,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5.84805230051328e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null