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 72673016
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9128c30f8a3b26280560a868afe89cca76661efd2a33ceb3c658eddf190de8bb
|
3 |
size 72673016
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 36892116
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cc10cf500af2626b5d2b4f076a07c678e565cf08a810b0e33e8a52555d5cc40
|
3 |
size 36892116
|
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 sha256:3ece262c534d1b7d1db5a2ce2fd578c733d0164261019904322133288edf8c12
|
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 sha256:34561662f8e54ce65c36d4fcca2b1c512c5ba02e6fc1a025cbd92eb43f288458
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -757,13 +757,163 @@
|
|
757 |
"learning_rate": 0.00015524193548387098,
|
758 |
"loss": 1.8046,
|
759 |
"step": 125
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
760 |
}
|
761 |
],
|
762 |
"logging_steps": 1,
|
763 |
"max_steps": 501,
|
764 |
"num_train_epochs": 1,
|
765 |
"save_steps": 25,
|
766 |
-
"total_flos":
|
767 |
"trial_name": null,
|
768 |
"trial_params": null
|
769 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.028358067870309103,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 150,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
757 |
"learning_rate": 0.00015524193548387098,
|
758 |
"loss": 1.8046,
|
759 |
"step": 125
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.02,
|
763 |
+
"learning_rate": 0.00015483870967741937,
|
764 |
+
"loss": 1.8889,
|
765 |
+
"step": 126
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.02,
|
769 |
+
"learning_rate": 0.00015443548387096776,
|
770 |
+
"loss": 1.9183,
|
771 |
+
"step": 127
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.02,
|
775 |
+
"learning_rate": 0.00015403225806451615,
|
776 |
+
"loss": 1.6254,
|
777 |
+
"step": 128
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.02,
|
781 |
+
"learning_rate": 0.00015362903225806454,
|
782 |
+
"loss": 1.8339,
|
783 |
+
"step": 129
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.02,
|
787 |
+
"learning_rate": 0.0001532258064516129,
|
788 |
+
"loss": 1.94,
|
789 |
+
"step": 130
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.02,
|
793 |
+
"learning_rate": 0.00015282258064516131,
|
794 |
+
"loss": 1.9235,
|
795 |
+
"step": 131
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.02,
|
799 |
+
"learning_rate": 0.00015241935483870968,
|
800 |
+
"loss": 1.78,
|
801 |
+
"step": 132
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.03,
|
805 |
+
"learning_rate": 0.0001520161290322581,
|
806 |
+
"loss": 1.7514,
|
807 |
+
"step": 133
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.03,
|
811 |
+
"learning_rate": 0.00015161290322580646,
|
812 |
+
"loss": 1.8281,
|
813 |
+
"step": 134
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.03,
|
817 |
+
"learning_rate": 0.00015120967741935485,
|
818 |
+
"loss": 1.8109,
|
819 |
+
"step": 135
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.03,
|
823 |
+
"learning_rate": 0.00015080645161290323,
|
824 |
+
"loss": 1.9297,
|
825 |
+
"step": 136
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.03,
|
829 |
+
"learning_rate": 0.00015040322580645162,
|
830 |
+
"loss": 1.7198,
|
831 |
+
"step": 137
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.03,
|
835 |
+
"learning_rate": 0.00015000000000000001,
|
836 |
+
"loss": 1.7704,
|
837 |
+
"step": 138
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.03,
|
841 |
+
"learning_rate": 0.00014959677419354838,
|
842 |
+
"loss": 1.8345,
|
843 |
+
"step": 139
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.03,
|
847 |
+
"learning_rate": 0.0001491935483870968,
|
848 |
+
"loss": 1.7694,
|
849 |
+
"step": 140
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.03,
|
853 |
+
"learning_rate": 0.00014879032258064516,
|
854 |
+
"loss": 1.8196,
|
855 |
+
"step": 141
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.03,
|
859 |
+
"learning_rate": 0.00014838709677419355,
|
860 |
+
"loss": 1.8625,
|
861 |
+
"step": 142
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.03,
|
865 |
+
"learning_rate": 0.00014798387096774193,
|
866 |
+
"loss": 1.9182,
|
867 |
+
"step": 143
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.03,
|
871 |
+
"learning_rate": 0.00014758064516129032,
|
872 |
+
"loss": 1.4297,
|
873 |
+
"step": 144
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.03,
|
877 |
+
"learning_rate": 0.00014717741935483871,
|
878 |
+
"loss": 1.929,
|
879 |
+
"step": 145
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.03,
|
883 |
+
"learning_rate": 0.0001467741935483871,
|
884 |
+
"loss": 1.9118,
|
885 |
+
"step": 146
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.03,
|
889 |
+
"learning_rate": 0.0001463709677419355,
|
890 |
+
"loss": 2.0179,
|
891 |
+
"step": 147
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.03,
|
895 |
+
"learning_rate": 0.00014596774193548388,
|
896 |
+
"loss": 1.8938,
|
897 |
+
"step": 148
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.03,
|
901 |
+
"learning_rate": 0.00014556451612903224,
|
902 |
+
"loss": 1.8689,
|
903 |
+
"step": 149
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.03,
|
907 |
+
"learning_rate": 0.00014516129032258066,
|
908 |
+
"loss": 1.6793,
|
909 |
+
"step": 150
|
910 |
}
|
911 |
],
|
912 |
"logging_steps": 1,
|
913 |
"max_steps": 501,
|
914 |
"num_train_epochs": 1,
|
915 |
"save_steps": 25,
|
916 |
+
"total_flos": 7280753121067008.0,
|
917 |
"trial_name": null,
|
918 |
"trial_params": null
|
919 |
}
|