bbytxt commited on
Commit
a0d25e3
·
verified ·
1 Parent(s): 71988a4

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:f11e22314c371aae41118965c662bc627952289ebee2ba149ed2f9465ce713b7
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4645db15cb8051f985e2a50c613e0570afd8d4079e8d83ec368fac88dfe2d209
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac3ec9d7978be5a2c8d06fcfc3ad8581ed2c8e7ca80dc9ade5df25803a82f5e9
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c982507742ded6fb6c09c99f01d0b8ba2ab28404219dceb9bf512b67c6d2189a
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e4147ead9c8567589bfd5851181b566a72644d2a4770c82b2b48fb43a634fbe
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73b1a8839cfb05ca6b01f7cb76ab6a2b0ecb176121723a6354b25d30c2303bbb
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd59dca009004df561617f8f6994512d029a952a68609cac24b36df5a0757ce
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.581653356552124,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.07544322897019992,
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": 10.007,
732
  "eval_steps_per_second": 5.006,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.4345755040101171e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4006094932556152,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.11316484345529988,
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": 10.007,
732
  "eval_steps_per_second": 5.006,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.07619766125990192,
737
+ "grad_norm": 14.999310493469238,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 6.7778,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.07695209354960392,
744
+ "grad_norm": 13.291474342346191,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 7.1744,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.07770652583930593,
751
+ "grad_norm": 9.604938507080078,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 6.6883,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.07846095812900793,
758
+ "grad_norm": 7.80354118347168,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 6.2805,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.07921539041870992,
765
+ "grad_norm": 8.760526657104492,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 6.5151,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.07996982270841192,
772
+ "grad_norm": 8.761163711547852,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 6.4826,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.08072425499811392,
779
+ "grad_norm": 8.215286254882812,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 5.9167,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.08147868728781592,
786
+ "grad_norm": 7.599548816680908,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 6.2646,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.08223311957751792,
793
+ "grad_norm": 7.709637641906738,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 5.8361,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.08298755186721991,
800
+ "grad_norm": 7.818946838378906,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 6.3807,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.08374198415692191,
807
+ "grad_norm": 7.244435787200928,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 6.0912,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.08449641644662391,
814
+ "grad_norm": 7.93871545791626,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 6.1092,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.08525084873632592,
821
+ "grad_norm": 7.6457319259643555,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 5.915,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.08600528102602792,
828
+ "grad_norm": 7.350983619689941,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 5.7853,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.08675971331572992,
835
+ "grad_norm": 7.477654933929443,
836
+ "learning_rate": 5e-05,
837
+ "loss": 5.9845,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.08751414560543191,
842
+ "grad_norm": 7.959140777587891,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 5.3337,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.08826857789513391,
849
+ "grad_norm": 8.025788307189941,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 5.5754,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.08902301018483591,
856
+ "grad_norm": 7.158747673034668,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 5.5501,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.08977744247453791,
863
+ "grad_norm": 7.6621994972229,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 5.9097,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.0905318747642399,
870
+ "grad_norm": 7.132166862487793,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 5.744,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.0912863070539419,
877
+ "grad_norm": 7.8009819984436035,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 5.5201,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.0920407393436439,
884
+ "grad_norm": 7.407027721405029,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 5.6957,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.09279517163334591,
891
+ "grad_norm": 7.293229579925537,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 6.0079,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.09354960392304791,
898
+ "grad_norm": 7.645759105682373,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 4.653,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.09430403621274991,
905
+ "grad_norm": 7.993988513946533,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 5.4163,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.0950584685024519,
912
+ "grad_norm": 7.342037677764893,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 5.9263,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.0958129007921539,
919
+ "grad_norm": 8.084555625915527,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 6.2218,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.0965673330818559,
926
+ "grad_norm": 8.398702621459961,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 5.8363,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.0973217653715579,
933
+ "grad_norm": 8.095590591430664,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 6.0603,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.0980761976612599,
940
+ "grad_norm": 8.621750831604004,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 6.1481,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.0988306299509619,
947
+ "grad_norm": 7.470015048980713,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 5.6436,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.0995850622406639,
954
+ "grad_norm": 8.399615287780762,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 5.7993,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.1003394945303659,
961
+ "grad_norm": 7.979325294494629,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 4.9809,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.1010939268200679,
968
+ "grad_norm": 8.482051849365234,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 4.963,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.1018483591097699,
975
+ "grad_norm": 7.327165603637695,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 4.7399,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.1026027913994719,
982
+ "grad_norm": 7.478617191314697,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 5.3976,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.1033572236891739,
989
+ "grad_norm": 7.518840312957764,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 5.1067,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.1041116559788759,
996
+ "grad_norm": 7.427170276641846,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 4.4334,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.10486608826857789,
1003
+ "grad_norm": 8.182501792907715,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 5.201,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.10562052055827989,
1010
+ "grad_norm": 9.181497573852539,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 5.1471,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.10637495284798189,
1017
+ "grad_norm": 8.158872604370117,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 4.324,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.1071293851376839,
1024
+ "grad_norm": 8.7058744430542,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 5.2668,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.1078838174273859,
1031
+ "grad_norm": 9.988224029541016,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 4.9627,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.1086382497170879,
1038
+ "grad_norm": 9.397239685058594,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 5.4195,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.1093926820067899,
1045
+ "grad_norm": 8.99825668334961,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 4.6881,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.11014711429649189,
1052
+ "grad_norm": 8.604011535644531,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 4.5378,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.11090154658619389,
1059
+ "grad_norm": 9.167732238769531,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 3.5005,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.11165597887589589,
1066
+ "grad_norm": 8.983088493347168,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 3.3061,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.11241041116559788,
1073
+ "grad_norm": 8.106727600097656,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 2.1657,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.11316484345529988,
1080
+ "grad_norm": 10.579435348510742,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 2.5445,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.11316484345529988,
1087
+ "eval_loss": 1.4006094932556152,
1088
+ "eval_runtime": 223.0685,
1089
+ "eval_samples_per_second": 10.01,
1090
+ "eval_steps_per_second": 5.007,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.150074508503941e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null