prxy5605 commited on
Commit
b38eaca
·
verified ·
1 Parent(s): a35fd63

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:a9d5bbd3213e6430b7bd596627c1ce88a247e50e9754125122417c3af644cfdc
3
  size 406863720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87dd5d85409864a72d9ec7a8e9ed7d6345891ef5bc4b65bf517e965c4a5a16d0
3
  size 406863720
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa9ec085507c5e6e013494ce81a6ab42fee48888afaafec9fabf506633d6b99d
3
  size 207013892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75db55ed54d1ca77987b0a19115bb24fbbed4d3f9c3dc82bd6cd9862f46b4697
3
  size 207013892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f8e11a89fbf6be88c29777fdbbfe4d4259c26b65e372ad0b0265d65afb8afb8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9db9337d3596e000ad3dca096f5e654129811442d0c39094248df7eecc987cb
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": 0.0689723864197731,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.027372887155272703,
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": 23.38,
732
  "eval_steps_per_second": 5.848,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6.752190575149056e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.053889013826847076,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.04105933073290905,
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": 23.38,
732
  "eval_steps_per_second": 5.848,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.02764661602682543,
737
+ "grad_norm": 1.0368256568908691,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.2054,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.027920344898378156,
744
+ "grad_norm": 0.5863410234451294,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.1558,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.028194073769930883,
751
+ "grad_norm": 0.5034375190734863,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.1396,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.02846780264148361,
758
+ "grad_norm": 0.5163214802742004,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.1619,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.028741531513036336,
765
+ "grad_norm": 0.4672788977622986,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.1527,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.029015260384589063,
772
+ "grad_norm": 0.35526421666145325,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.1102,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.029288989256141793,
779
+ "grad_norm": 0.30567991733551025,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.0776,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.02956271812769452,
786
+ "grad_norm": 0.4598815143108368,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.1627,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.029836446999247247,
793
+ "grad_norm": 0.2589607238769531,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.0687,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.030110175870799973,
800
+ "grad_norm": 0.3864089846611023,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.1135,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0303839047423527,
807
+ "grad_norm": 0.25004953145980835,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.1004,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.030657633613905427,
814
+ "grad_norm": 0.25639253854751587,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.0793,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.030931362485458153,
821
+ "grad_norm": 0.36456888914108276,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.0842,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.03120509135701088,
828
+ "grad_norm": 0.39386072754859924,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.0656,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.03147882022856361,
835
+ "grad_norm": 0.2991383373737335,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.0856,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.03175254910011634,
842
+ "grad_norm": 0.21862885355949402,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.0452,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.032026277971669063,
849
+ "grad_norm": 0.21904170513153076,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.051,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.03230000684322179,
856
+ "grad_norm": 0.2709364593029022,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.0849,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.03257373571477452,
863
+ "grad_norm": 0.27606716752052307,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.0689,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.032847464586327244,
870
+ "grad_norm": 0.3288068175315857,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.0845,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.03312119345787997,
877
+ "grad_norm": 0.2838031053543091,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.0412,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.0333949223294327,
884
+ "grad_norm": 0.18428663909435272,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.0595,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.033668651200985424,
891
+ "grad_norm": 0.37800440192222595,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.0672,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.03394238007253815,
898
+ "grad_norm": 0.22834280133247375,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.0346,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.03421610894409088,
905
+ "grad_norm": 0.2601318955421448,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.1222,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.034489837815643604,
912
+ "grad_norm": 0.1850673258304596,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.0388,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.03476356668719633,
919
+ "grad_norm": 0.3141416311264038,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.0646,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.03503729555874906,
926
+ "grad_norm": 0.18401959538459778,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.034,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.035311024430301784,
933
+ "grad_norm": 0.15586012601852417,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.0326,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.03558475330185451,
940
+ "grad_norm": 0.22381485998630524,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.0342,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.03585848217340724,
947
+ "grad_norm": 0.3787159025669098,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.0816,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.036132211044959964,
954
+ "grad_norm": 0.14897434413433075,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.0296,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0364059399165127,
961
+ "grad_norm": 0.2271733433008194,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.0287,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.036679668788065424,
968
+ "grad_norm": 0.13798674941062927,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.0292,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.03695339765961815,
975
+ "grad_norm": 0.16890235245227814,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.0242,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.03722712653117088,
982
+ "grad_norm": 0.11271921545267105,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.008,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.037500855402723604,
989
+ "grad_norm": 0.11944177746772766,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.0147,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.03777458427427633,
996
+ "grad_norm": 0.14850112795829773,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.0178,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.03804831314582906,
1003
+ "grad_norm": 0.15633860230445862,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.0207,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.038322042017381784,
1010
+ "grad_norm": 0.17218001186847687,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.0389,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.03859577088893451,
1017
+ "grad_norm": 0.08486124128103256,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.0054,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.03886949976048724,
1024
+ "grad_norm": 0.13307073712348938,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.0183,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.039143228632039964,
1031
+ "grad_norm": 0.12460210174322128,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.0074,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.03941695750359269,
1038
+ "grad_norm": 0.1307774931192398,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.0074,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.03969068637514542,
1045
+ "grad_norm": 0.09602323919534683,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.0062,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.039964415246698144,
1052
+ "grad_norm": 0.09614124894142151,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.0177,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.04023814411825087,
1059
+ "grad_norm": 0.04025377333164215,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.0025,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.0405118729898036,
1066
+ "grad_norm": 0.4157078266143799,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.0212,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.040785601861356324,
1073
+ "grad_norm": 0.08781462162733078,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.0055,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.04105933073290905,
1080
+ "grad_norm": 0.16040568053722382,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.0173,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.04105933073290905,
1087
+ "eval_loss": 0.053889013826847076,
1088
+ "eval_runtime": 262.788,
1089
+ "eval_samples_per_second": 23.414,
1090
+ "eval_steps_per_second": 5.856,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.0136705052966912e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null