feat: update to step 1480
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +219 -3
- training_args.bin +1 -1
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5922605
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9095cf091f13fef28be3b337c0de7a461356f4207894f2e9211e1e414b251244
|
3 |
size 5922605
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3282182981
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f94103909eef81b12ecf00936e61da446886031622a51849f53753c95eecdeff
|
3 |
size 3282182981
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b8eabf76fcd8bc7449a6b05ba51e815397e565ade9671197a70e60312fa2c02
|
3 |
size 14575
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92a33c4cb7d8c9dad3255cdd0b6067ad6b7d77dc9943d79714a9d617088adb67
|
3 |
size 627
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -678,11 +678,227 @@
|
|
678 |
"learning_rate": 0.0022400000000000002,
|
679 |
"loss": 2.4506,
|
680 |
"step": 1120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
681 |
}
|
682 |
],
|
683 |
"max_steps": 172326,
|
684 |
"num_train_epochs": 3,
|
685 |
-
"total_flos":
|
686 |
"trial_name": null,
|
687 |
"trial_params": null
|
688 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.025764811230324137,
|
5 |
+
"global_step": 1480,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
678 |
"learning_rate": 0.0022400000000000002,
|
679 |
"loss": 2.4506,
|
680 |
"step": 1120
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.02,
|
684 |
+
"learning_rate": 0.00226,
|
685 |
+
"loss": 2.462,
|
686 |
+
"step": 1130
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 0.02,
|
690 |
+
"learning_rate": 0.00228,
|
691 |
+
"loss": 2.4535,
|
692 |
+
"step": 1140
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.02,
|
696 |
+
"learning_rate": 0.0023,
|
697 |
+
"loss": 2.4162,
|
698 |
+
"step": 1150
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.02,
|
702 |
+
"learning_rate": 0.00232,
|
703 |
+
"loss": 2.3739,
|
704 |
+
"step": 1160
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.02,
|
708 |
+
"learning_rate": 0.00234,
|
709 |
+
"loss": 2.4125,
|
710 |
+
"step": 1170
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.02,
|
714 |
+
"learning_rate": 0.00236,
|
715 |
+
"loss": 2.4172,
|
716 |
+
"step": 1180
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.02,
|
720 |
+
"learning_rate": 0.0023799999999999997,
|
721 |
+
"loss": 2.4006,
|
722 |
+
"step": 1190
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 0.02,
|
726 |
+
"learning_rate": 0.0024,
|
727 |
+
"loss": 2.517,
|
728 |
+
"step": 1200
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 0.02,
|
732 |
+
"learning_rate": 0.00242,
|
733 |
+
"loss": 2.4768,
|
734 |
+
"step": 1210
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.02,
|
738 |
+
"learning_rate": 0.00244,
|
739 |
+
"loss": 2.4303,
|
740 |
+
"step": 1220
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.02,
|
744 |
+
"learning_rate": 0.00246,
|
745 |
+
"loss": 2.4002,
|
746 |
+
"step": 1230
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.02,
|
750 |
+
"learning_rate": 0.00248,
|
751 |
+
"loss": 2.4263,
|
752 |
+
"step": 1240
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.02,
|
756 |
+
"learning_rate": 0.0025,
|
757 |
+
"loss": 2.4114,
|
758 |
+
"step": 1250
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.02,
|
762 |
+
"learning_rate": 0.00252,
|
763 |
+
"loss": 2.4964,
|
764 |
+
"step": 1260
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 0.02,
|
768 |
+
"learning_rate": 0.00254,
|
769 |
+
"loss": 2.4425,
|
770 |
+
"step": 1270
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 0.02,
|
774 |
+
"learning_rate": 0.00256,
|
775 |
+
"loss": 2.4163,
|
776 |
+
"step": 1280
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 0.02,
|
780 |
+
"learning_rate": 0.0025800000000000003,
|
781 |
+
"loss": 2.4091,
|
782 |
+
"step": 1290
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 0.02,
|
786 |
+
"learning_rate": 0.0026000000000000003,
|
787 |
+
"loss": 2.4029,
|
788 |
+
"step": 1300
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.02,
|
792 |
+
"learning_rate": 0.0026200000000000004,
|
793 |
+
"loss": 2.4061,
|
794 |
+
"step": 1310
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.02,
|
798 |
+
"learning_rate": 0.00264,
|
799 |
+
"loss": 2.3963,
|
800 |
+
"step": 1320
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.02,
|
804 |
+
"learning_rate": 0.00266,
|
805 |
+
"loss": 2.412,
|
806 |
+
"step": 1330
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 0.02,
|
810 |
+
"learning_rate": 0.00268,
|
811 |
+
"loss": 2.3639,
|
812 |
+
"step": 1340
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 0.02,
|
816 |
+
"learning_rate": 0.0027,
|
817 |
+
"loss": 2.3454,
|
818 |
+
"step": 1350
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 0.02,
|
822 |
+
"learning_rate": 0.00272,
|
823 |
+
"loss": 2.41,
|
824 |
+
"step": 1360
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.02,
|
828 |
+
"learning_rate": 0.0027400000000000002,
|
829 |
+
"loss": 2.3901,
|
830 |
+
"step": 1370
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.02,
|
834 |
+
"learning_rate": 0.00276,
|
835 |
+
"loss": 2.352,
|
836 |
+
"step": 1380
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.02,
|
840 |
+
"learning_rate": 0.00278,
|
841 |
+
"loss": 2.3873,
|
842 |
+
"step": 1390
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.02,
|
846 |
+
"learning_rate": 0.0028,
|
847 |
+
"loss": 2.4287,
|
848 |
+
"step": 1400
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 0.02,
|
852 |
+
"learning_rate": 0.00282,
|
853 |
+
"loss": 2.4252,
|
854 |
+
"step": 1410
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 0.02,
|
858 |
+
"learning_rate": 0.00284,
|
859 |
+
"loss": 2.4787,
|
860 |
+
"step": 1420
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.02,
|
864 |
+
"learning_rate": 0.00286,
|
865 |
+
"loss": 3.0007,
|
866 |
+
"step": 1430
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 0.03,
|
870 |
+
"learning_rate": 0.0028799999999999997,
|
871 |
+
"loss": 2.4423,
|
872 |
+
"step": 1440
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.03,
|
876 |
+
"learning_rate": 0.0029,
|
877 |
+
"loss": 2.4445,
|
878 |
+
"step": 1450
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.03,
|
882 |
+
"learning_rate": 0.00292,
|
883 |
+
"loss": 2.4369,
|
884 |
+
"step": 1460
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.03,
|
888 |
+
"learning_rate": 0.00294,
|
889 |
+
"loss": 2.423,
|
890 |
+
"step": 1470
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 0.03,
|
894 |
+
"learning_rate": 0.00296,
|
895 |
+
"loss": 3.6744,
|
896 |
+
"step": 1480
|
897 |
}
|
898 |
],
|
899 |
"max_steps": 172326,
|
900 |
"num_train_epochs": 3,
|
901 |
+
"total_flos": 8.798474662104269e+17,
|
902 |
"trial_name": null,
|
903 |
"trial_params": null
|
904 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4091
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6a68bfa120887ec0f5e2ec991631838aa62faba58a52de7e0feea3f2c228567
|
3 |
size 4091
|