bbytxt commited on
Commit
761a5f4
·
verified ·
1 Parent(s): 39c42cd

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 sha256:64c871bc1db4da720ba095f13197eb6bd450f48a2d9e6aab49aac44cf1c3ca96
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00ce167f028439642785b323aaba3815625d8b817e6a62c8b5e458960ca05d58
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f44e040874f342fb1c01b29fc54241f0d948dee0d74020bdff3aa445948ec1df
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52d186477dc4aa39f0d0ca1d944bf526db185bde18bf3dcfa7fb9eb8dbf8c858
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:e0372a767b1e9eb3858edd1a414bd1df06b0bad95b855bd2bf5be8f2cabd5f36
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35d2eeaa65ec1cf376b185932acb238ac83c3599176c917521de47571527cea2
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": 1.4227622747421265,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.06480881399870382,
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": 7.019,
732
  "eval_steps_per_second": 1.755,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.717763934177198e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.323728084564209,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.09721322099805574,
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": 7.019,
732
  "eval_steps_per_second": 1.755,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.06545690213869086,
737
+ "grad_norm": 4.787423133850098,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 5.9553,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0661049902786779,
744
+ "grad_norm": 4.652994155883789,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 5.5491,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.06675307841866494,
751
+ "grad_norm": 5.026247024536133,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 5.59,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.06740116655865197,
758
+ "grad_norm": 5.296930313110352,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 5.7854,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.06804925469863901,
765
+ "grad_norm": 5.847901344299316,
766
+ "learning_rate": 5e-05,
767
+ "loss": 5.9658,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.06869734283862605,
772
+ "grad_norm": 6.000091075897217,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 5.5761,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.06934543097861309,
779
+ "grad_norm": 6.229143142700195,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 5.2815,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.06999351911860013,
786
+ "grad_norm": 6.7049479484558105,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 5.6108,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.07064160725858717,
793
+ "grad_norm": 6.860906600952148,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 5.5159,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.0712896953985742,
800
+ "grad_norm": 7.019985198974609,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 5.6056,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.07193778353856124,
807
+ "grad_norm": 7.05626916885376,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 5.4075,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.07258587167854828,
814
+ "grad_norm": 6.539259910583496,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 5.0558,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.07323395981853532,
821
+ "grad_norm": 7.1625447273254395,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 5.351,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.07388204795852236,
828
+ "grad_norm": 7.557711601257324,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 5.6869,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.07453013609850939,
835
+ "grad_norm": 7.120979309082031,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 5.1624,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.07517822423849643,
842
+ "grad_norm": 7.815059185028076,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 5.8814,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.07582631237848347,
849
+ "grad_norm": 7.95869255065918,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 5.2809,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.07647440051847051,
856
+ "grad_norm": 8.076533317565918,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 5.6616,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.07712248865845756,
863
+ "grad_norm": 7.682056903839111,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 5.1071,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.07777057679844458,
870
+ "grad_norm": 8.244827270507812,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 5.5138,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.07841866493843162,
877
+ "grad_norm": 8.22045612335205,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 5.0651,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.07906675307841866,
884
+ "grad_norm": 8.04766845703125,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 5.567,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.0797148412184057,
891
+ "grad_norm": 8.576169967651367,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 5.454,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.08036292935839275,
898
+ "grad_norm": 8.193389892578125,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 5.1683,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.08101101749837979,
905
+ "grad_norm": 8.050642967224121,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 4.6637,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.08165910563836681,
912
+ "grad_norm": 8.81507396697998,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 5.3693,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.08230719377835385,
919
+ "grad_norm": 8.727811813354492,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 5.714,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.0829552819183409,
926
+ "grad_norm": 8.717565536499023,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 5.7399,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.08360337005832794,
933
+ "grad_norm": 8.756967544555664,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 5.2997,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.08425145819831498,
940
+ "grad_norm": 9.31334400177002,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 5.4564,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.084899546338302,
947
+ "grad_norm": 8.90140151977539,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 5.0921,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.08554763447828904,
954
+ "grad_norm": 9.364441871643066,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 4.495,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.08619572261827609,
961
+ "grad_norm": 10.136019706726074,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 5.7014,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.08684381075826313,
968
+ "grad_norm": 9.147400856018066,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 4.7557,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.08749189889825017,
975
+ "grad_norm": 9.371038436889648,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 4.2169,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0881399870382372,
982
+ "grad_norm": 10.364588737487793,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 5.5328,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.08878807517822424,
989
+ "grad_norm": 12.089287757873535,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 5.7587,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.08943616331821128,
996
+ "grad_norm": 10.678025245666504,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 4.7723,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.09008425145819832,
1003
+ "grad_norm": 10.811649322509766,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 4.6393,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.09073233959818536,
1010
+ "grad_norm": 13.51014518737793,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 5.6152,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.09138042773817238,
1017
+ "grad_norm": 14.925034523010254,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 6.0521,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.09202851587815943,
1024
+ "grad_norm": 13.902508735656738,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 5.4761,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.09267660401814647,
1031
+ "grad_norm": 20.527427673339844,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 7.0354,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.09332469215813351,
1038
+ "grad_norm": 11.042694091796875,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 5.1453,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.09397278029812055,
1045
+ "grad_norm": 9.60646915435791,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 4.696,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.09462086843810759,
1052
+ "grad_norm": 7.381638526916504,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 3.5106,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.09526895657809462,
1059
+ "grad_norm": 8.033303260803223,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 3.8758,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.09591704471808166,
1066
+ "grad_norm": 8.180899620056152,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 3.5253,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.0965651328580687,
1073
+ "grad_norm": 7.356280326843262,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 3.2546,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.09721322099805574,
1080
+ "grad_norm": 9.28185749053955,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 4.0351,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.09721322099805574,
1087
+ "eval_loss": 1.323728084564209,
1088
+ "eval_runtime": 370.5316,
1089
+ "eval_samples_per_second": 7.014,
1090
+ "eval_steps_per_second": 1.754,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.078450525392077e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null