nttx commited on
Commit
48ccd64
·
verified ·
1 Parent(s): 421bb2c

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:dae14b45b2aa05876691e23f79429617bf62e1e8afb4d0a5743568fd619d2c54
3
  size 9047632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cc56f67deb779d6052abb900ce052fcd11684d60029cbce871306aed255e2ae
3
  size 9047632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1c05f6d980eff832bf6dd2c25396e96004d3c0e2848e7d831ccd6a4b3f7893a
3
  size 18111946
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d1fe780a142dab3ee2cf45d502b8d4414e7c362871d6e9ab783dc65ff47baea
3
  size 18111946
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da8220ce55eaafcaa352ab22e4d8c0c6f1d426253d50805c3fec604c30f7d073
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4ec831143f16e46d12aa833eb8d03bc97aa2607d0befc8ab206536cbaaa4d29
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": 0.9128943681716919,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.017075773745997867,
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": 275.732,
732
  "eval_steps_per_second": 137.866,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 954972241920000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8842025995254517,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.025613660618996798,
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": 275.732,
732
  "eval_steps_per_second": 137.866,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.017246531483457846,
737
+ "grad_norm": 7.36553955078125,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 3.389,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.01741728922091782,
744
+ "grad_norm": 5.0720367431640625,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 1.5951,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.0175880469583778,
751
+ "grad_norm": 4.1941752433776855,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 1.0009,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.01775880469583778,
758
+ "grad_norm": 2.9722445011138916,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 1.0415,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.01792956243329776,
765
+ "grad_norm": 1.8852466344833374,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 0.9703,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.018100320170757737,
772
+ "grad_norm": 1.7154128551483154,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 0.8274,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.018271077908217716,
779
+ "grad_norm": 1.148832082748413,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 0.6555,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.018441835645677696,
786
+ "grad_norm": 1.6996549367904663,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 1.1596,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.018612593383137675,
793
+ "grad_norm": 1.3889989852905273,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 0.897,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.018783351120597654,
800
+ "grad_norm": 1.1142041683197021,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 0.8444,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.01895410885805763,
807
+ "grad_norm": 1.0875897407531738,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 0.7941,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.019124866595517608,
814
+ "grad_norm": 1.482211947441101,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 0.8514,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.019295624332977587,
821
+ "grad_norm": 1.3092451095581055,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 0.8415,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.019466382070437566,
828
+ "grad_norm": 1.1167197227478027,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 0.8627,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.019637139807897545,
835
+ "grad_norm": 1.0100393295288086,
836
+ "learning_rate": 5e-05,
837
+ "loss": 0.7654,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.019807897545357524,
842
+ "grad_norm": 1.2014217376708984,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 0.7972,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.019978655282817503,
849
+ "grad_norm": 0.9819137454032898,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 0.7866,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.020149413020277483,
856
+ "grad_norm": 1.2597284317016602,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 0.8979,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.02032017075773746,
863
+ "grad_norm": 0.9694597721099854,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 0.8589,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.020490928495197437,
870
+ "grad_norm": 1.2638909816741943,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 0.9064,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.020661686232657416,
877
+ "grad_norm": 1.3041003942489624,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 0.6922,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.020832443970117395,
884
+ "grad_norm": 1.2819812297821045,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 0.9398,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.021003201707577374,
891
+ "grad_norm": 1.2087786197662354,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 0.7732,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.021173959445037353,
898
+ "grad_norm": 1.1736648082733154,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 0.7672,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.021344717182497332,
905
+ "grad_norm": 1.046942114830017,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 0.7634,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.02151547491995731,
912
+ "grad_norm": 1.1425883769989014,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 0.808,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.02168623265741729,
919
+ "grad_norm": 0.9221328496932983,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 0.718,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.02185699039487727,
926
+ "grad_norm": 0.9747080206871033,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 0.769,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.022027748132337245,
933
+ "grad_norm": 1.0447397232055664,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 0.8581,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.022198505869797224,
940
+ "grad_norm": 1.0637578964233398,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 0.6822,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.022369263607257203,
947
+ "grad_norm": 1.0002477169036865,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 0.8158,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.022540021344717182,
954
+ "grad_norm": 0.9726616144180298,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 0.7542,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.02271077908217716,
961
+ "grad_norm": 1.1409964561462402,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 0.9922,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.02288153681963714,
968
+ "grad_norm": 1.2967826128005981,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 0.912,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.02305229455709712,
975
+ "grad_norm": 1.1848523616790771,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 0.7371,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0232230522945571,
982
+ "grad_norm": 1.1654822826385498,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 0.865,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.023393810032017077,
989
+ "grad_norm": 1.1176100969314575,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 0.685,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.023564567769477053,
996
+ "grad_norm": 1.2199519872665405,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 0.7731,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.023735325506937032,
1003
+ "grad_norm": 1.148708462715149,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 0.9054,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.02390608324439701,
1010
+ "grad_norm": 1.3541618585586548,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 0.8916,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.02407684098185699,
1017
+ "grad_norm": 1.2918407917022705,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 0.7598,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.02424759871931697,
1024
+ "grad_norm": 1.2371271848678589,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 0.7015,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.02441835645677695,
1031
+ "grad_norm": 1.3515294790267944,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 0.806,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.024589114194236927,
1038
+ "grad_norm": 1.6061891317367554,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 0.7577,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.024759871931696906,
1045
+ "grad_norm": 1.211403250694275,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 0.6685,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.024930629669156882,
1052
+ "grad_norm": 1.245577096939087,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 0.6328,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.02510138740661686,
1059
+ "grad_norm": 1.5203893184661865,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 0.7963,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.02527214514407684,
1066
+ "grad_norm": 1.4067859649658203,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 0.7993,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.02544290288153682,
1073
+ "grad_norm": 1.456285834312439,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 0.7195,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.025613660618996798,
1080
+ "grad_norm": 1.5420877933502197,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 0.7393,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.025613660618996798,
1087
+ "eval_loss": 0.8842025995254517,
1088
+ "eval_runtime": 35.6967,
1089
+ "eval_samples_per_second": 276.328,
1090
+ "eval_steps_per_second": 138.164,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1431334866124800.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null