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 838904832
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a3d1b036ff3cb5ac02c5acf6005e92e48b05c61587c49579854c2529afea41f
|
3 |
size 838904832
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 420633876
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59b42bcd4eadba12555b9589f81e0afdd6e7d134c2b0fbdedc77c7bced004ef9
|
3 |
size 420633876
|
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 sha256:145f1a4da4a46bf2b53df9260772ce418443341bad1fbda0361575d00cb23c5d
|
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:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
|
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": 500,
|
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": 0.0002,
|
758 |
"loss": 0.5121,
|
759 |
"step": 125
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
760 |
}
|
761 |
],
|
762 |
"logging_steps": 1,
|
763 |
"max_steps": 250,
|
764 |
"num_train_epochs": 1,
|
765 |
"save_steps": 25,
|
766 |
-
"total_flos": 1.
|
767 |
"trial_name": null,
|
768 |
"trial_params": null
|
769 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6,
|
5 |
"eval_steps": 500,
|
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": 0.0002,
|
758 |
"loss": 0.5121,
|
759 |
"step": 125
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.5,
|
763 |
+
"learning_rate": 0.0002,
|
764 |
+
"loss": 0.4943,
|
765 |
+
"step": 126
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.51,
|
769 |
+
"learning_rate": 0.0002,
|
770 |
+
"loss": 0.4765,
|
771 |
+
"step": 127
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.51,
|
775 |
+
"learning_rate": 0.0002,
|
776 |
+
"loss": 0.4952,
|
777 |
+
"step": 128
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.52,
|
781 |
+
"learning_rate": 0.0002,
|
782 |
+
"loss": 0.4852,
|
783 |
+
"step": 129
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.52,
|
787 |
+
"learning_rate": 0.0002,
|
788 |
+
"loss": 0.5511,
|
789 |
+
"step": 130
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.52,
|
793 |
+
"learning_rate": 0.0002,
|
794 |
+
"loss": 0.4721,
|
795 |
+
"step": 131
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.53,
|
799 |
+
"learning_rate": 0.0002,
|
800 |
+
"loss": 0.4612,
|
801 |
+
"step": 132
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.53,
|
805 |
+
"learning_rate": 0.0002,
|
806 |
+
"loss": 0.4672,
|
807 |
+
"step": 133
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.54,
|
811 |
+
"learning_rate": 0.0002,
|
812 |
+
"loss": 0.4875,
|
813 |
+
"step": 134
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.54,
|
817 |
+
"learning_rate": 0.0002,
|
818 |
+
"loss": 0.3908,
|
819 |
+
"step": 135
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.54,
|
823 |
+
"learning_rate": 0.0002,
|
824 |
+
"loss": 0.4813,
|
825 |
+
"step": 136
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.55,
|
829 |
+
"learning_rate": 0.0002,
|
830 |
+
"loss": 0.4423,
|
831 |
+
"step": 137
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.55,
|
835 |
+
"learning_rate": 0.0002,
|
836 |
+
"loss": 0.4593,
|
837 |
+
"step": 138
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.56,
|
841 |
+
"learning_rate": 0.0002,
|
842 |
+
"loss": 0.4399,
|
843 |
+
"step": 139
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.56,
|
847 |
+
"learning_rate": 0.0002,
|
848 |
+
"loss": 0.3959,
|
849 |
+
"step": 140
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.56,
|
853 |
+
"learning_rate": 0.0002,
|
854 |
+
"loss": 0.4063,
|
855 |
+
"step": 141
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.57,
|
859 |
+
"learning_rate": 0.0002,
|
860 |
+
"loss": 0.3643,
|
861 |
+
"step": 142
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.57,
|
865 |
+
"learning_rate": 0.0002,
|
866 |
+
"loss": 0.3982,
|
867 |
+
"step": 143
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.58,
|
871 |
+
"learning_rate": 0.0002,
|
872 |
+
"loss": 0.355,
|
873 |
+
"step": 144
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.58,
|
877 |
+
"learning_rate": 0.0002,
|
878 |
+
"loss": 0.3645,
|
879 |
+
"step": 145
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.58,
|
883 |
+
"learning_rate": 0.0002,
|
884 |
+
"loss": 0.3516,
|
885 |
+
"step": 146
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.59,
|
889 |
+
"learning_rate": 0.0002,
|
890 |
+
"loss": 0.3945,
|
891 |
+
"step": 147
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.59,
|
895 |
+
"learning_rate": 0.0002,
|
896 |
+
"loss": 0.3166,
|
897 |
+
"step": 148
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.6,
|
901 |
+
"learning_rate": 0.0002,
|
902 |
+
"loss": 0.3054,
|
903 |
+
"step": 149
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.6,
|
907 |
+
"learning_rate": 0.0002,
|
908 |
+
"loss": 0.3719,
|
909 |
+
"step": 150
|
910 |
}
|
911 |
],
|
912 |
"logging_steps": 1,
|
913 |
"max_steps": 250,
|
914 |
"num_train_epochs": 1,
|
915 |
"save_steps": 25,
|
916 |
+
"total_flos": 1.78966730207232e+16,
|
917 |
"trial_name": null,
|
918 |
"trial_params": null
|
919 |
}
|