prxy5606 commited on
Commit
8095691
·
verified ·
1 Parent(s): 76a5cec

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:a64478626e1158ada52bd14065cde9920a785894ac68f4bb7a111c1c8ee3e2f8
3
  size 289452128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3af809830a2054e87872d814ab9ebe0451180179d4f82a820c4b8793c8279eb8
3
  size 289452128
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97d8b4ed926880e436f8a320bb51bcc5b70a72e5ff07e4472414c4e1a478460b
3
  size 147359892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9856b28b070cd867215d4a88aa7b957e01dcd587c3a92dea7a91644a8d1a54e
3
  size 147359892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:520a000e0ef41b9f3c1b019faf83b87863ebfba01b8be82d1c55986afa97a70f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abd1a482e420668d1277f3ad8c2b2f1de528eff5a6f680bdfaad32301916698d
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": 0.7853623032569885,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.10111223458038422,
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": 33.081,
732
  "eval_steps_per_second": 8.28,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.3421305059475456e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7633453607559204,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.15166835187057634,
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": 33.081,
732
  "eval_steps_per_second": 8.28,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.10212335692618807,
737
+ "grad_norm": 0.1445879340171814,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.7155,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.10313447927199192,
744
+ "grad_norm": 0.17979127168655396,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.795,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.10414560161779575,
751
+ "grad_norm": 0.16335216164588928,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.7166,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.1051567239635996,
758
+ "grad_norm": 0.1975068598985672,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.8181,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.10616784630940344,
765
+ "grad_norm": 0.21564233303070068,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.8436,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.10717896865520728,
772
+ "grad_norm": 0.23721911013126373,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.8103,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.10819009100101112,
779
+ "grad_norm": 0.238744854927063,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.8356,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.10920121334681497,
786
+ "grad_norm": 0.24662300944328308,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.8112,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.1102123356926188,
793
+ "grad_norm": 0.2687962055206299,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.7722,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.11122345803842265,
800
+ "grad_norm": 0.24536916613578796,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.795,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.1122345803842265,
807
+ "grad_norm": 0.2373892217874527,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.7835,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.11324570273003033,
814
+ "grad_norm": 0.26101693511009216,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.8022,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.11425682507583418,
821
+ "grad_norm": 0.24881425499916077,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.792,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.11526794742163801,
828
+ "grad_norm": 0.28947913646698,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.7737,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.11627906976744186,
835
+ "grad_norm": 0.23814891278743744,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.7348,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.1172901921132457,
842
+ "grad_norm": 0.2723856568336487,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.843,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.11830131445904954,
849
+ "grad_norm": 0.24490369856357574,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.7405,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.11931243680485339,
856
+ "grad_norm": 0.2560327351093292,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.7397,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.12032355915065723,
863
+ "grad_norm": 0.3040284216403961,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.8526,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.12133468149646107,
870
+ "grad_norm": 0.25108906626701355,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.6855,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.12234580384226491,
877
+ "grad_norm": 0.28637540340423584,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.8158,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.12335692618806876,
884
+ "grad_norm": 0.2800399959087372,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.7052,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.1243680485338726,
891
+ "grad_norm": 0.2940939664840698,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.7797,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.12537917087967643,
898
+ "grad_norm": 0.29059016704559326,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.7584,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.1263902932254803,
905
+ "grad_norm": 0.3029254972934723,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.7925,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.12740141557128412,
912
+ "grad_norm": 0.3084964156150818,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.8653,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.12841253791708795,
919
+ "grad_norm": 0.2903442084789276,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.7248,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.12942366026289182,
926
+ "grad_norm": 0.2756825387477875,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.7159,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.13043478260869565,
933
+ "grad_norm": 0.29607969522476196,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.7328,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.13144590495449948,
940
+ "grad_norm": 0.28305575251579285,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.7405,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.13245702730030334,
947
+ "grad_norm": 0.3362610638141632,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.8088,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.13346814964610718,
954
+ "grad_norm": 0.31651681661605835,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.7738,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.134479271991911,
961
+ "grad_norm": 0.3246115744113922,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.7475,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.13549039433771487,
968
+ "grad_norm": 0.31663426756858826,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.734,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.1365015166835187,
975
+ "grad_norm": 0.3378746509552002,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.7825,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.13751263902932254,
982
+ "grad_norm": 0.3254399001598358,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.7292,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.1385237613751264,
989
+ "grad_norm": 0.3353380262851715,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.7263,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.13953488372093023,
996
+ "grad_norm": 0.3074869215488434,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.6498,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.14054600606673406,
1003
+ "grad_norm": 0.3658754229545593,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.7797,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.14155712841253792,
1010
+ "grad_norm": 0.35673946142196655,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.7939,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.14256825075834176,
1017
+ "grad_norm": 0.3774884343147278,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.7314,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.1435793731041456,
1024
+ "grad_norm": 0.3515547811985016,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.7358,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.14459049544994945,
1031
+ "grad_norm": 0.3989035487174988,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.8463,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.14560161779575329,
1038
+ "grad_norm": 0.39837345480918884,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.7461,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.14661274014155712,
1045
+ "grad_norm": 0.3874199092388153,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.7415,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.14762386248736098,
1052
+ "grad_norm": 0.44643062353134155,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.8106,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.1486349848331648,
1059
+ "grad_norm": 0.43793392181396484,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.7803,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.14964610717896865,
1066
+ "grad_norm": 0.45935964584350586,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.7487,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.1506572295247725,
1073
+ "grad_norm": 0.5578981637954712,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.9711,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.15166835187057634,
1080
+ "grad_norm": 0.6663854718208313,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.9227,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.15166835187057634,
1087
+ "eval_loss": 0.7633453607559204,
1088
+ "eval_runtime": 50.4394,
1089
+ "eval_samples_per_second": 33.03,
1090
+ "eval_steps_per_second": 8.267,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5.021468359183565e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null