prxy5604 commited on
Commit
d5fb585
·
verified ·
1 Parent(s): 366bf8c

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:ddcc753aa500284e4c0450b11a5fedbd3730f8554152424ef6c8ba0bba4e8152
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:390c507cd4fb46e530e722b4235c84db31e73b65fe4616a44d0d47afdab7bf03
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df4c558ab0ad68f32a99286df1eaad02697395129e7d2b067b4bec851e995612
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acdef35c03d7bf6b31e1882db991e3b33c9e03d148fbf8fcd84af7ac5b1652a7
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c5e5120f9a4f01e476250a8df0d1450b740a8b5de3b4c227a957e20b77b993e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc71f673194da85d979727dfb62db517c2e9eab47cc27c38b24c5ab08a683fc
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": 0.9530589580535889,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.6779661016949152,
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": 20.678,
732
  "eval_steps_per_second": 5.232,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 4.735318313926656e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8874126076698303,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.0169491525423728,
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": 20.678,
732
  "eval_steps_per_second": 5.232,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.6847457627118644,
737
+ "grad_norm": 0.8145944476127625,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.9565,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.6915254237288135,
744
+ "grad_norm": 0.7151859998703003,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.9586,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.6983050847457627,
751
+ "grad_norm": 0.6783329844474792,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.9815,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.7050847457627119,
758
+ "grad_norm": 0.7342352271080017,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.03,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.711864406779661,
765
+ "grad_norm": 0.6583441495895386,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.8399,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.7186440677966102,
772
+ "grad_norm": 0.7299189567565918,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.895,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.7254237288135593,
779
+ "grad_norm": 0.8076292872428894,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.0801,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.7322033898305085,
786
+ "grad_norm": 0.8924995064735413,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.7654,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.7389830508474576,
793
+ "grad_norm": 0.4125653803348541,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.9849,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.7457627118644068,
800
+ "grad_norm": 0.5486474633216858,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.2092,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.752542372881356,
807
+ "grad_norm": 0.5774505734443665,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.096,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.7593220338983051,
814
+ "grad_norm": 0.6842017769813538,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.0314,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.7661016949152543,
821
+ "grad_norm": 0.5893596410751343,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.0473,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.7728813559322034,
828
+ "grad_norm": 0.5972430109977722,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.8728,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.7796610169491526,
835
+ "grad_norm": 0.7384089827537537,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.1531,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.7864406779661017,
842
+ "grad_norm": 0.697727382183075,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.9937,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.7932203389830509,
849
+ "grad_norm": 0.7309191226959229,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.8853,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.8,
856
+ "grad_norm": 0.7668942213058472,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.8901,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.8067796610169492,
863
+ "grad_norm": 0.7865873575210571,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.7627,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.8135593220338984,
870
+ "grad_norm": 0.8927539587020874,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.0116,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.8203389830508474,
877
+ "grad_norm": 0.8080148696899414,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.8466,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.8271186440677966,
884
+ "grad_norm": 0.7929520010948181,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.8439,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.8338983050847457,
891
+ "grad_norm": 0.8571904897689819,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.8409,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.8406779661016949,
898
+ "grad_norm": 0.8431151509284973,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.9759,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.847457627118644,
905
+ "grad_norm": 0.9114735722541809,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.8199,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.8542372881355932,
912
+ "grad_norm": 0.9574477076530457,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.8997,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.8610169491525423,
919
+ "grad_norm": 0.9024648070335388,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.6221,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.8677966101694915,
926
+ "grad_norm": 1.1015090942382812,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.706,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.8745762711864407,
933
+ "grad_norm": 1.1271800994873047,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.7401,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.8813559322033898,
940
+ "grad_norm": 1.261331558227539,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.8444,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.888135593220339,
947
+ "grad_norm": 1.139116644859314,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.7163,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.8949152542372881,
954
+ "grad_norm": 1.2368700504302979,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.5519,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.9016949152542373,
961
+ "grad_norm": 0.7187737822532654,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.8445,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.9084745762711864,
968
+ "grad_norm": 0.7398237586021423,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.9588,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.9152542372881356,
975
+ "grad_norm": 0.7324635982513428,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.8997,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.9220338983050848,
982
+ "grad_norm": 0.7759287357330322,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.8906,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.9288135593220339,
989
+ "grad_norm": 0.7547850012779236,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.9413,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.9355932203389831,
996
+ "grad_norm": 0.6890804767608643,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.9953,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.9423728813559322,
1003
+ "grad_norm": 0.7542194128036499,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.842,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.9491525423728814,
1010
+ "grad_norm": 0.7280335426330566,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.7761,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.9559322033898305,
1017
+ "grad_norm": 0.8433640003204346,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.0213,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.9627118644067797,
1024
+ "grad_norm": 0.7220066785812378,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.931,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.9694915254237289,
1031
+ "grad_norm": 0.8239220380783081,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.9224,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.976271186440678,
1038
+ "grad_norm": 1.063681960105896,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.8818,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.9830508474576272,
1045
+ "grad_norm": 0.7143641710281372,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.005,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.9898305084745763,
1052
+ "grad_norm": 0.965940535068512,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.9034,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.9966101694915255,
1059
+ "grad_norm": 0.7812204957008362,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.7964,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.0033898305084745,
1066
+ "grad_norm": 1.1821647882461548,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.364,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.0101694915254238,
1073
+ "grad_norm": 0.5269371867179871,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.0077,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.0169491525423728,
1080
+ "grad_norm": 0.5620221495628357,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.2834,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.0169491525423728,
1087
+ "eval_loss": 0.8874126076698303,
1088
+ "eval_runtime": 12.1169,
1089
+ "eval_samples_per_second": 20.55,
1090
+ "eval_steps_per_second": 5.199,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 6.898868922875904e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null