prxy5605 commited on
Commit
e26a193
·
verified ·
1 Parent(s): 58545fa

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:a5f23bed06c6f6698a348dae656bfb0f246ea6372bedfd2b88fa399c55d57763
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c29a16930cc790b135b6d07660f873099655bdb26b6e08fdd0fc13e67aa6079
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1050a5f3e8018cade3153e4eddcec43445e55d1d7fffe0d6d8b43abddb7a3d6
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace79cc2ef2fb8374d46c52242f5a60f2dc91dcb60efa82cb8e1d20194e92ebd
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fd0608c3e3453c73fdb85c1c65549e4205179ce3d24363aba902e2935b7222f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7145302c1f308df8d6782ec9fe066dd4586495c653a831ff7700b56e35a8a04
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": 0.8197675347328186,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.045599635202918376,
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": 10.566,
732
  "eval_steps_per_second": 2.643,
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": 0.7523689866065979,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.06839945280437756,
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": 10.566,
732
  "eval_steps_per_second": 2.643,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.04605563155494756,
737
+ "grad_norm": 10.61023235321045,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.7583,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.046511627906976744,
744
+ "grad_norm": 9.402891159057617,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 2.6451,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.04696762425900593,
751
+ "grad_norm": 9.066802978515625,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.2557,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.04742362061103511,
758
+ "grad_norm": 8.31011962890625,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.9061,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.047879616963064295,
765
+ "grad_norm": 9.681857109069824,
766
+ "learning_rate": 5e-05,
767
+ "loss": 3.8238,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.04833561331509348,
772
+ "grad_norm": 10.533971786499023,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 3.2304,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.04879160966712266,
779
+ "grad_norm": 9.498639106750488,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 2.0589,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.049247606019151846,
786
+ "grad_norm": 10.653234481811523,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.8517,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.04970360237118103,
793
+ "grad_norm": 9.575819969177246,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 2.7365,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.050159598723210214,
800
+ "grad_norm": 9.632899284362793,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 2.5004,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0506155950752394,
807
+ "grad_norm": 9.333025932312012,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.746,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.05107159142726858,
814
+ "grad_norm": 8.68212604522705,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 2.1002,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.051527587779297765,
821
+ "grad_norm": 9.370121955871582,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.6227,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.05198358413132695,
828
+ "grad_norm": 8.905264854431152,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 2.4046,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.05243958048335613,
835
+ "grad_norm": 10.212873458862305,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.824,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.052895576835385316,
842
+ "grad_norm": 9.993491172790527,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.3992,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.0533515731874145,
849
+ "grad_norm": 11.604905128479004,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.7306,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.053807569539443684,
856
+ "grad_norm": 10.31896686553955,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 3.0943,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.05426356589147287,
863
+ "grad_norm": 10.747237205505371,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 3.0425,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.05471956224350205,
870
+ "grad_norm": 9.785868644714355,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 2.4842,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.055175558595531235,
877
+ "grad_norm": 10.849400520324707,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 3.777,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.05563155494756042,
884
+ "grad_norm": 11.813304901123047,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 3.0709,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.0560875512995896,
891
+ "grad_norm": 10.825654029846191,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 3.3899,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.056543547651618786,
898
+ "grad_norm": 10.39290714263916,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.7794,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.05699954400364797,
905
+ "grad_norm": 9.933770179748535,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 2.875,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.057455540355677154,
912
+ "grad_norm": 10.807685852050781,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 3.2124,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.05791153670770634,
919
+ "grad_norm": 10.649255752563477,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 3.7709,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.05836753305973552,
926
+ "grad_norm": 12.467437744140625,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 3.4853,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.058823529411764705,
933
+ "grad_norm": 12.292319297790527,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 3.7258,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.05927952576379389,
940
+ "grad_norm": 9.66211986541748,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 3.0776,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.05973552211582307,
947
+ "grad_norm": 10.147554397583008,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 3.1498,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.060191518467852256,
954
+ "grad_norm": 11.330928802490234,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 3.2106,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.06064751481988144,
961
+ "grad_norm": 11.31750202178955,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 3.2155,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.061103511171910624,
968
+ "grad_norm": 10.476314544677734,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 3.3905,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.06155950752393981,
975
+ "grad_norm": 11.83663558959961,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 3.4465,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.06201550387596899,
982
+ "grad_norm": 10.024785041809082,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.7385,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.062471500227998175,
989
+ "grad_norm": 11.038595199584961,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.9536,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.06292749658002736,
996
+ "grad_norm": 10.529680252075195,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 3.1882,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.06338349293205654,
1003
+ "grad_norm": 10.84036636352539,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 3.0197,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.06383948928408573,
1010
+ "grad_norm": 11.032572746276855,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 3.8491,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.06429548563611491,
1017
+ "grad_norm": 9.125802040100098,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 2.5575,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.0647514819881441,
1024
+ "grad_norm": 13.208250999450684,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 3.8827,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.06520747834017328,
1031
+ "grad_norm": 10.89819622039795,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 3.476,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.06566347469220246,
1038
+ "grad_norm": 12.219125747680664,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 3.6378,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.06611947104423165,
1045
+ "grad_norm": 11.675637245178223,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 3.2438,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.06657546739626083,
1052
+ "grad_norm": 9.782285690307617,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 2.9421,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.06703146374829001,
1059
+ "grad_norm": 10.580471992492676,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 2.9575,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.0674874601003192,
1066
+ "grad_norm": 12.524446487426758,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 3.7983,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.06794345645234838,
1073
+ "grad_norm": 13.980012893676758,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 4.4534,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.06839945280437756,
1080
+ "grad_norm": 16.460304260253906,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 5.1192,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.06839945280437756,
1087
+ "eval_loss": 0.7523689866065979,
1088
+ "eval_runtime": 349.5702,
1089
+ "eval_samples_per_second": 10.567,
1090
+ "eval_steps_per_second": 2.643,
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