prxy5606 commited on
Commit
83d9e41
·
verified ·
1 Parent(s): 6f87d9c

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:e2e5337b4c5b1e97b2b9162fdf11b5dc0d0df1b8b86ba21b9ca0585b5007442b
3
  size 2373352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ef50be43257316c7bf51dd1df13245cee3f2392bf8ac54129b7b48ba0ff5b24
3
  size 2373352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68289fdf918ff029eecbe30c7d79c7c9b91ea203278c850a274247ab79f93325
3
  size 4830714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeb0f8c73c24302cf7cc254c10ded9566fdd063d8c7322f0ecb8b6071d2a7bcf
3
  size 4830714
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e3b293c76329a096ae292671a8f668de652bbc0d440247f251354bbb1065a20
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:682860f4e6c03c451cdedecad97c711de257238eefee48c7b243786fc449021b
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": 11.876375198364258,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.02889755815633579,
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": 105.667,
732
  "eval_steps_per_second": 26.43,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 110454571008000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 11.875956535339355,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.043346337234503686,
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": 105.667,
732
  "eval_steps_per_second": 26.43,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.02918653373789915,
737
+ "grad_norm": 0.09448030591011047,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 11.8769,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.029475509319462505,
744
+ "grad_norm": 0.09203047305345535,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 11.8809,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.029764484901025862,
751
+ "grad_norm": 0.10378605127334595,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 11.8723,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.030053460482589223,
758
+ "grad_norm": 0.07438343018293381,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 11.8738,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.03034243606415258,
765
+ "grad_norm": 0.08363966643810272,
766
+ "learning_rate": 5e-05,
767
+ "loss": 11.8704,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.030631411645715936,
772
+ "grad_norm": 0.07607440650463104,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 11.8709,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.030920387227279293,
779
+ "grad_norm": 0.07229042798280716,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 11.8734,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.031209362808842653,
786
+ "grad_norm": 0.0885797068476677,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 11.8713,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.031498338390406014,
793
+ "grad_norm": 0.08899901807308197,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 11.8746,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.03178731397196937,
800
+ "grad_norm": 0.0725225955247879,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 11.8724,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.03207628955353273,
807
+ "grad_norm": 0.07378460466861725,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 11.868,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.032365265135096084,
814
+ "grad_norm": 0.0828651487827301,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 11.8712,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.03265424071665944,
821
+ "grad_norm": 0.0730227530002594,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 11.8706,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0329432162982228,
828
+ "grad_norm": 0.07580568641424179,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 11.8719,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.033232191879786155,
835
+ "grad_norm": 0.06368804723024368,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 11.8718,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.03352116746134952,
842
+ "grad_norm": 0.08921920508146286,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 11.8736,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.033810143042912875,
849
+ "grad_norm": 0.0802396759390831,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 11.8763,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.03409911862447623,
856
+ "grad_norm": 0.06945715099573135,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 11.8732,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.03438809420603959,
863
+ "grad_norm": 0.07443312555551529,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 11.871,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.034677069787602946,
870
+ "grad_norm": 0.07826009392738342,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 11.8703,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.0349660453691663,
877
+ "grad_norm": 0.06413071602582932,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 11.8765,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.03525502095072967,
884
+ "grad_norm": 0.06165166571736336,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 11.8742,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.035543996532293023,
891
+ "grad_norm": 0.06768231838941574,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 11.8728,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.03583297211385638,
898
+ "grad_norm": 0.08700777590274811,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 11.8732,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.03612194769541974,
905
+ "grad_norm": 0.05918419361114502,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 11.8749,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.036410923276983094,
912
+ "grad_norm": 0.05309590324759483,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 11.8737,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.03669989885854645,
919
+ "grad_norm": 0.07097380608320236,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 11.8802,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.03698887444010981,
926
+ "grad_norm": 0.0766899362206459,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 11.8779,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.03727785002167317,
933
+ "grad_norm": 0.06368804723024368,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 11.8867,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.03756682560323653,
940
+ "grad_norm": 0.06508305668830872,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 11.882,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.037855801184799885,
947
+ "grad_norm": 0.08121135830879211,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 11.8766,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.03814477676636324,
954
+ "grad_norm": 0.07969960570335388,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 11.8755,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0384337523479266,
961
+ "grad_norm": 0.08134438842535019,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 11.8782,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.038722727929489956,
968
+ "grad_norm": 0.07282125949859619,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 11.8758,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.03901170351105332,
975
+ "grad_norm": 0.0943041443824768,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 11.8676,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.039300679092616676,
982
+ "grad_norm": 0.09704722464084625,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 11.8776,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.03958965467418003,
989
+ "grad_norm": 0.08427353948354721,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 11.8774,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.03987863025574339,
996
+ "grad_norm": 0.07390493154525757,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 11.8738,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.04016760583730675,
1003
+ "grad_norm": 0.11108248680830002,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 11.8792,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.040456581418870104,
1010
+ "grad_norm": 0.117488794028759,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 11.8702,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.04074555700043346,
1017
+ "grad_norm": 0.112480029463768,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 11.8731,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.041034532581996824,
1024
+ "grad_norm": 0.11315959692001343,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 11.8755,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.04132350816356018,
1031
+ "grad_norm": 0.1187959685921669,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 11.8769,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.04161248374512354,
1038
+ "grad_norm": 0.08921589702367783,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 11.8715,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.041901459326686895,
1045
+ "grad_norm": 0.10372520238161087,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 11.8759,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.04219043490825025,
1052
+ "grad_norm": 0.10234490782022476,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 11.8821,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.04247941048981361,
1059
+ "grad_norm": 0.10286494344472885,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 11.8825,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.042768386071376965,
1066
+ "grad_norm": 0.0980636477470398,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 11.8819,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.04305736165294033,
1073
+ "grad_norm": 0.1364598423242569,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 11.8917,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.043346337234503686,
1080
+ "grad_norm": 0.11411885917186737,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 11.8883,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.043346337234503686,
1087
+ "eval_loss": 11.875956535339355,
1088
+ "eval_runtime": 54.9073,
1089
+ "eval_samples_per_second": 106.161,
1090
+ "eval_steps_per_second": 26.554,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 165544132608000.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null