prxy5607 commited on
Commit
253ee67
·
verified ·
1 Parent(s): 8e88f66

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:ecc08e731f7be8fb0a51942d71927f0f9afe4bd4be004d18c7ff4bdc8eb3b2da
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:915074992fc2bef49db4f98d819cf20ce325c93524e2dd0995b6ca299388d621
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c79c43ebea80e4f155d13dc4e4d89adcef57d533bf13c66636dc7a11c64c2763
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34af74358b9079c55223cd804e8d58c8f93fbc68a0e40c35a6a9c96d0ecb63c8
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19e668f1a45cea6b9c0567125f2d00b18fa782739da61b22880fec33e22c4b37
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e10052395fe68c82c68d2686880be4f2f197da9e0a988048ebc434d723d7f6d
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": 1.814341425895691,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.02010353319595919,
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": 48.563,
732
  "eval_steps_per_second": 12.144,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.159812200628224e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.7307214736938477,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.030155299793938786,
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": 48.563,
732
  "eval_steps_per_second": 12.144,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.02030456852791878,
737
+ "grad_norm": 0.9297945499420166,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.8183,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.020505603859878374,
744
+ "grad_norm": 0.939454197883606,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.8074,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.020706639191837965,
751
+ "grad_norm": 1.0974127054214478,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.8272,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.02090767452379756,
758
+ "grad_norm": 0.8772820234298706,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.808,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.02110870985575715,
765
+ "grad_norm": 0.8370904326438904,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.7561,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.021309745187716743,
772
+ "grad_norm": 0.619301974773407,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.5667,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.021510780519676333,
779
+ "grad_norm": 0.6837291717529297,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.6399,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.021711815851635924,
786
+ "grad_norm": 0.5568907260894775,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.5673,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.021912851183595518,
793
+ "grad_norm": 0.5481559038162231,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.6878,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.02211388651555511,
800
+ "grad_norm": 0.5510746240615845,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.7258,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.022314921847514702,
807
+ "grad_norm": 0.6050065159797668,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.7121,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.022515957179474293,
814
+ "grad_norm": 0.6477292776107788,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.624,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.022716992511433883,
821
+ "grad_norm": 0.6289533972740173,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.754,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.022918027843393477,
828
+ "grad_norm": 0.654630184173584,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.6769,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.023119063175353068,
835
+ "grad_norm": 0.6162823438644409,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.5744,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.02332009850731266,
842
+ "grad_norm": 0.6766645908355713,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.7471,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.023521133839272252,
849
+ "grad_norm": 0.6917820572853088,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.5096,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.023722169171231842,
856
+ "grad_norm": 0.6780633330345154,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.7633,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.023923204503191436,
863
+ "grad_norm": 0.675075888633728,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.7795,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.024124239835151027,
870
+ "grad_norm": 0.642783522605896,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.7796,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.02432527516711062,
877
+ "grad_norm": 0.7685930728912354,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.7594,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.02452631049907021,
884
+ "grad_norm": 0.641385555267334,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.7159,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.024727345831029802,
891
+ "grad_norm": 0.6726094484329224,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.6944,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.024928381162989396,
898
+ "grad_norm": 0.625813901424408,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.6797,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.025129416494948986,
905
+ "grad_norm": 0.7406529188156128,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.5463,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.02533045182690858,
912
+ "grad_norm": 0.7634907364845276,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.654,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.02553148715886817,
919
+ "grad_norm": 0.7529230713844299,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.7993,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.025732522490827765,
926
+ "grad_norm": 0.843103289604187,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.7806,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.025933557822787355,
933
+ "grad_norm": 0.8046737909317017,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.645,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.026134593154746946,
940
+ "grad_norm": 0.6955248713493347,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.7116,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.02633562848670654,
947
+ "grad_norm": 0.6817566156387329,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.8035,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.02653666381866613,
954
+ "grad_norm": 0.709463357925415,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.5567,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.026737699150625724,
961
+ "grad_norm": 0.8133819103240967,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.6997,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.026938734482585314,
968
+ "grad_norm": 0.7387455105781555,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.6745,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.027139769814544905,
975
+ "grad_norm": 0.7375905513763428,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.8471,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0273408051465045,
982
+ "grad_norm": 0.7787903547286987,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.7531,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.02754184047846409,
989
+ "grad_norm": 0.8154503107070923,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.7624,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.027742875810423683,
996
+ "grad_norm": 0.903148889541626,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.7726,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.027943911142383274,
1003
+ "grad_norm": 0.8761181235313416,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.722,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.028144946474342864,
1010
+ "grad_norm": 1.0418727397918701,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.6932,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.028345981806302458,
1017
+ "grad_norm": 0.9624373316764832,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.7963,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.02854701713826205,
1024
+ "grad_norm": 0.9782199859619141,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.9029,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.028748052470221643,
1031
+ "grad_norm": 1.1240954399108887,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.8169,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.028949087802181233,
1038
+ "grad_norm": 1.2213478088378906,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.8265,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.029150123134140827,
1045
+ "grad_norm": 1.1300071477890015,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.8799,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.029351158466100417,
1052
+ "grad_norm": 1.1099785566329956,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.8078,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.029552193798060008,
1059
+ "grad_norm": 1.209250807762146,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.7618,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.029753229130019602,
1066
+ "grad_norm": 1.5932096242904663,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.9006,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.029954264461979192,
1073
+ "grad_norm": 1.4094241857528687,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.4656,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.030155299793938786,
1080
+ "grad_norm": 1.903329610824585,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.8197,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.030155299793938786,
1087
+ "eval_loss": 1.7307214736938477,
1088
+ "eval_runtime": 172.1064,
1089
+ "eval_samples_per_second": 48.679,
1090
+ "eval_steps_per_second": 12.173,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.2423847357579264e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null