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:
|
3 |
size 100690184
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5dc469b2fe3f7617ccc7636806852028d13117c750ad401fe01aa295417624e3
|
3 |
size 100690184
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 51344890
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc519571ab2955716cae7dc1de3561bd34e5445714618b2c3537f5d431f2bf14
|
3 |
size 51344890
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d633bcc0e6a652a898770443fcc088887dd15666cc22c7af322eb1adbc986e74
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
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": 2.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 50,
|
6 |
-
"global_step":
|
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": 87.531,
|
732 |
"eval_steps_per_second": 22.058,
|
733 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
734 |
}
|
735 |
],
|
736 |
"logging_steps": 1,
|
@@ -759,7 +1117,7 @@
|
|
759 |
"attributes": {}
|
760 |
}
|
761 |
},
|
762 |
-
"total_flos":
|
763 |
"train_batch_size": 8,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.1300928592681885,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
4 |
+
"epoch": 1.0101010101010102,
|
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": 87.531,
|
732 |
"eval_steps_per_second": 22.058,
|
733 |
"step": 100
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 0.6801346801346801,
|
737 |
+
"grad_norm": 53.02522659301758,
|
738 |
+
"learning_rate": 5.330452921628497e-05,
|
739 |
+
"loss": 7.8997,
|
740 |
+
"step": 101
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.6868686868686869,
|
744 |
+
"grad_norm": 67.17434692382812,
|
745 |
+
"learning_rate": 5.247918773366112e-05,
|
746 |
+
"loss": 7.3731,
|
747 |
+
"step": 102
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.6936026936026936,
|
751 |
+
"grad_norm": 59.72895431518555,
|
752 |
+
"learning_rate": 5.165316846586541e-05,
|
753 |
+
"loss": 7.0059,
|
754 |
+
"step": 103
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 0.7003367003367004,
|
758 |
+
"grad_norm": 53.37847137451172,
|
759 |
+
"learning_rate": 5.0826697238317935e-05,
|
760 |
+
"loss": 8.9512,
|
761 |
+
"step": 104
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 0.7070707070707071,
|
765 |
+
"grad_norm": 70.16453552246094,
|
766 |
+
"learning_rate": 5e-05,
|
767 |
+
"loss": 8.3674,
|
768 |
+
"step": 105
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.7138047138047138,
|
772 |
+
"grad_norm": 100.9383316040039,
|
773 |
+
"learning_rate": 4.917330276168208e-05,
|
774 |
+
"loss": 9.4618,
|
775 |
+
"step": 106
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 0.7205387205387206,
|
779 |
+
"grad_norm": 68.87419128417969,
|
780 |
+
"learning_rate": 4.834683153413459e-05,
|
781 |
+
"loss": 8.5877,
|
782 |
+
"step": 107
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 0.7272727272727273,
|
786 |
+
"grad_norm": 65.74427032470703,
|
787 |
+
"learning_rate": 4.7520812266338885e-05,
|
788 |
+
"loss": 11.0717,
|
789 |
+
"step": 108
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.734006734006734,
|
793 |
+
"grad_norm": 81.13140869140625,
|
794 |
+
"learning_rate": 4.669547078371504e-05,
|
795 |
+
"loss": 10.0225,
|
796 |
+
"step": 109
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 0.7407407407407407,
|
800 |
+
"grad_norm": 79.43911743164062,
|
801 |
+
"learning_rate": 4.5871032726383386e-05,
|
802 |
+
"loss": 11.1211,
|
803 |
+
"step": 110
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 0.7474747474747475,
|
807 |
+
"grad_norm": 96.10649871826172,
|
808 |
+
"learning_rate": 4.504772348747687e-05,
|
809 |
+
"loss": 14.4545,
|
810 |
+
"step": 111
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 0.7542087542087542,
|
814 |
+
"grad_norm": 42.719512939453125,
|
815 |
+
"learning_rate": 4.4225768151520694e-05,
|
816 |
+
"loss": 7.3726,
|
817 |
+
"step": 112
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 0.7609427609427609,
|
821 |
+
"grad_norm": 43.786014556884766,
|
822 |
+
"learning_rate": 4.3405391432896555e-05,
|
823 |
+
"loss": 8.2409,
|
824 |
+
"step": 113
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.7676767676767676,
|
828 |
+
"grad_norm": 85.84500885009766,
|
829 |
+
"learning_rate": 4.2586817614407895e-05,
|
830 |
+
"loss": 8.5336,
|
831 |
+
"step": 114
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.7744107744107744,
|
835 |
+
"grad_norm": 29.495527267456055,
|
836 |
+
"learning_rate": 4.17702704859633e-05,
|
837 |
+
"loss": 8.626,
|
838 |
+
"step": 115
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 0.7811447811447811,
|
842 |
+
"grad_norm": 31.59947395324707,
|
843 |
+
"learning_rate": 4.095597328339452e-05,
|
844 |
+
"loss": 8.436,
|
845 |
+
"step": 116
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 0.7878787878787878,
|
849 |
+
"grad_norm": 35.00060272216797,
|
850 |
+
"learning_rate": 4.0144148627425993e-05,
|
851 |
+
"loss": 8.8905,
|
852 |
+
"step": 117
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 0.7946127946127947,
|
856 |
+
"grad_norm": 35.44921875,
|
857 |
+
"learning_rate": 3.933501846281267e-05,
|
858 |
+
"loss": 8.8152,
|
859 |
+
"step": 118
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 0.8013468013468014,
|
863 |
+
"grad_norm": 24.749345779418945,
|
864 |
+
"learning_rate": 3.852880399766243e-05,
|
865 |
+
"loss": 8.3101,
|
866 |
+
"step": 119
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 0.8080808080808081,
|
870 |
+
"grad_norm": 26.719274520874023,
|
871 |
+
"learning_rate": 3.772572564296005e-05,
|
872 |
+
"loss": 8.0112,
|
873 |
+
"step": 120
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.8148148148148148,
|
877 |
+
"grad_norm": 26.525959014892578,
|
878 |
+
"learning_rate": 3.6926002952309016e-05,
|
879 |
+
"loss": 8.3156,
|
880 |
+
"step": 121
|
881 |
+
},
|
882 |
+
{
|
883 |
+
"epoch": 0.8215488215488216,
|
884 |
+
"grad_norm": 26.646484375,
|
885 |
+
"learning_rate": 3.612985456190778e-05,
|
886 |
+
"loss": 7.5943,
|
887 |
+
"step": 122
|
888 |
+
},
|
889 |
+
{
|
890 |
+
"epoch": 0.8282828282828283,
|
891 |
+
"grad_norm": 26.210987091064453,
|
892 |
+
"learning_rate": 3.533749813077677e-05,
|
893 |
+
"loss": 8.1803,
|
894 |
+
"step": 123
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.835016835016835,
|
898 |
+
"grad_norm": 27.579328536987305,
|
899 |
+
"learning_rate": 3.4549150281252636e-05,
|
900 |
+
"loss": 7.5849,
|
901 |
+
"step": 124
|
902 |
+
},
|
903 |
+
{
|
904 |
+
"epoch": 0.8417508417508418,
|
905 |
+
"grad_norm": 22.659543991088867,
|
906 |
+
"learning_rate": 3.3765026539765834e-05,
|
907 |
+
"loss": 8.0374,
|
908 |
+
"step": 125
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 0.8484848484848485,
|
912 |
+
"grad_norm": 24.334983825683594,
|
913 |
+
"learning_rate": 3.298534127791785e-05,
|
914 |
+
"loss": 8.5726,
|
915 |
+
"step": 126
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.8552188552188552,
|
919 |
+
"grad_norm": 28.293781280517578,
|
920 |
+
"learning_rate": 3.221030765387417e-05,
|
921 |
+
"loss": 8.3815,
|
922 |
+
"step": 127
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 0.8619528619528619,
|
926 |
+
"grad_norm": 25.025714874267578,
|
927 |
+
"learning_rate": 3.144013755408895e-05,
|
928 |
+
"loss": 8.0767,
|
929 |
+
"step": 128
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"epoch": 0.8686868686868687,
|
933 |
+
"grad_norm": 36.11143112182617,
|
934 |
+
"learning_rate": 3.0675041535377405e-05,
|
935 |
+
"loss": 8.2696,
|
936 |
+
"step": 129
|
937 |
+
},
|
938 |
+
{
|
939 |
+
"epoch": 0.8754208754208754,
|
940 |
+
"grad_norm": 31.006874084472656,
|
941 |
+
"learning_rate": 2.991522876735154e-05,
|
942 |
+
"loss": 8.452,
|
943 |
+
"step": 130
|
944 |
+
},
|
945 |
+
{
|
946 |
+
"epoch": 0.8821548821548821,
|
947 |
+
"grad_norm": 31.031539916992188,
|
948 |
+
"learning_rate": 2.916090697523549e-05,
|
949 |
+
"loss": 8.1796,
|
950 |
+
"step": 131
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 0.8888888888888888,
|
954 |
+
"grad_norm": 34.35560989379883,
|
955 |
+
"learning_rate": 2.8412282383075363e-05,
|
956 |
+
"loss": 7.8535,
|
957 |
+
"step": 132
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.8956228956228957,
|
961 |
+
"grad_norm": 42.85440444946289,
|
962 |
+
"learning_rate": 2.766955965735968e-05,
|
963 |
+
"loss": 8.1856,
|
964 |
+
"step": 133
|
965 |
+
},
|
966 |
+
{
|
967 |
+
"epoch": 0.9023569023569024,
|
968 |
+
"grad_norm": 41.15959167480469,
|
969 |
+
"learning_rate": 2.693294185106562e-05,
|
970 |
+
"loss": 8.546,
|
971 |
+
"step": 134
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 0.9090909090909091,
|
975 |
+
"grad_norm": 44.42498016357422,
|
976 |
+
"learning_rate": 2.6202630348146324e-05,
|
977 |
+
"loss": 7.0382,
|
978 |
+
"step": 135
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 0.9158249158249159,
|
982 |
+
"grad_norm": 44.232608795166016,
|
983 |
+
"learning_rate": 2.547882480847461e-05,
|
984 |
+
"loss": 8.3631,
|
985 |
+
"step": 136
|
986 |
+
},
|
987 |
+
{
|
988 |
+
"epoch": 0.9225589225589226,
|
989 |
+
"grad_norm": 44.95029830932617,
|
990 |
+
"learning_rate": 2.476172311325783e-05,
|
991 |
+
"loss": 7.7547,
|
992 |
+
"step": 137
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 0.9292929292929293,
|
996 |
+
"grad_norm": 54.041622161865234,
|
997 |
+
"learning_rate": 2.405152131093926e-05,
|
998 |
+
"loss": 6.9658,
|
999 |
+
"step": 138
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.936026936026936,
|
1003 |
+
"grad_norm": 41.09820556640625,
|
1004 |
+
"learning_rate": 2.3348413563600325e-05,
|
1005 |
+
"loss": 8.1192,
|
1006 |
+
"step": 139
|
1007 |
+
},
|
1008 |
+
{
|
1009 |
+
"epoch": 0.9427609427609428,
|
1010 |
+
"grad_norm": 48.26551818847656,
|
1011 |
+
"learning_rate": 2.2652592093878666e-05,
|
1012 |
+
"loss": 9.2408,
|
1013 |
+
"step": 140
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"epoch": 0.9494949494949495,
|
1017 |
+
"grad_norm": 57.503726959228516,
|
1018 |
+
"learning_rate": 2.196424713241637e-05,
|
1019 |
+
"loss": 8.8095,
|
1020 |
+
"step": 141
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 0.9562289562289562,
|
1024 |
+
"grad_norm": 47.783905029296875,
|
1025 |
+
"learning_rate": 2.128356686585282e-05,
|
1026 |
+
"loss": 8.405,
|
1027 |
+
"step": 142
|
1028 |
+
},
|
1029 |
+
{
|
1030 |
+
"epoch": 0.9629629629629629,
|
1031 |
+
"grad_norm": 67.84696197509766,
|
1032 |
+
"learning_rate": 2.061073738537635e-05,
|
1033 |
+
"loss": 8.6565,
|
1034 |
+
"step": 143
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.9696969696969697,
|
1038 |
+
"grad_norm": 56.10593795776367,
|
1039 |
+
"learning_rate": 1.9945942635848748e-05,
|
1040 |
+
"loss": 9.0028,
|
1041 |
+
"step": 144
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.9764309764309764,
|
1045 |
+
"grad_norm": 67.27642822265625,
|
1046 |
+
"learning_rate": 1.928936436551661e-05,
|
1047 |
+
"loss": 8.055,
|
1048 |
+
"step": 145
|
1049 |
+
},
|
1050 |
+
{
|
1051 |
+
"epoch": 0.9831649831649831,
|
1052 |
+
"grad_norm": 77.75454711914062,
|
1053 |
+
"learning_rate": 1.8641182076323148e-05,
|
1054 |
+
"loss": 8.8995,
|
1055 |
+
"step": 146
|
1056 |
+
},
|
1057 |
+
{
|
1058 |
+
"epoch": 0.98989898989899,
|
1059 |
+
"grad_norm": 83.39681243896484,
|
1060 |
+
"learning_rate": 1.800157297483417e-05,
|
1061 |
+
"loss": 13.9811,
|
1062 |
+
"step": 147
|
1063 |
+
},
|
1064 |
+
{
|
1065 |
+
"epoch": 0.9966329966329966,
|
1066 |
+
"grad_norm": 76.89947509765625,
|
1067 |
+
"learning_rate": 1.7370711923791567e-05,
|
1068 |
+
"loss": 14.4035,
|
1069 |
+
"step": 148
|
1070 |
+
},
|
1071 |
+
{
|
1072 |
+
"epoch": 1.0033670033670035,
|
1073 |
+
"grad_norm": 46.255950927734375,
|
1074 |
+
"learning_rate": 1.6748771394307585e-05,
|
1075 |
+
"loss": 8.0268,
|
1076 |
+
"step": 149
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 1.0101010101010102,
|
1080 |
+
"grad_norm": 31.87166404724121,
|
1081 |
+
"learning_rate": 1.6135921418712956e-05,
|
1082 |
+
"loss": 7.7841,
|
1083 |
+
"step": 150
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 1.0101010101010102,
|
1087 |
+
"eval_loss": 2.1300928592681885,
|
1088 |
+
"eval_runtime": 2.8825,
|
1089 |
+
"eval_samples_per_second": 86.732,
|
1090 |
+
"eval_steps_per_second": 21.856,
|
1091 |
+
"step": 150
|
1092 |
}
|
1093 |
],
|
1094 |
"logging_steps": 1,
|
|
|
1117 |
"attributes": {}
|
1118 |
}
|
1119 |
},
|
1120 |
+
"total_flos": 1.1172169937584128e+16,
|
1121 |
"train_batch_size": 8,
|
1122 |
"trial_name": null,
|
1123 |
"trial_params": null
|