joelniklaus
commited on
Commit
•
7696932
1
Parent(s):
4075332
Training in progress, step 150000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +311 -3
- pytorch_model.bin +1 -1
- runs/Feb06_00-07-48_t1v-n-58269bec-w-0/events.out.tfevents.1675642086.t1v-n-58269bec-w-0.23209.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 885325017
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e509478b90dcf268fb432a851f88216e1ce1bb569d2ed1bb1961cb04b872d535
|
3 |
size 885325017
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 442675755
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd802ee211fd38688831af0f4163cfa50c7658df48ac5ce868a3662a05e76407
|
3 |
size 442675755
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13611
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0be8d447d63dd679f65a4483bb9d53fac65b6db4a525ca71db850fc792c03c9
|
3 |
size 13611
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13611
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0be8d447d63dd679f65a4483bb9d53fac65b6db4a525ca71db850fc792c03c9
|
3 |
size 13611
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13611
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0be8d447d63dd679f65a4483bb9d53fac65b6db4a525ca71db850fc792c03c9
|
3 |
size 13611
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13611
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0be8d447d63dd679f65a4483bb9d53fac65b6db4a525ca71db850fc792c03c9
|
3 |
size 13611
|
last-checkpoint/rng_state_4.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13611
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0be8d447d63dd679f65a4483bb9d53fac65b6db4a525ca71db850fc792c03c9
|
3 |
size 13611
|
last-checkpoint/rng_state_5.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13611
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0be8d447d63dd679f65a4483bb9d53fac65b6db4a525ca71db850fc792c03c9
|
3 |
size 13611
|
last-checkpoint/rng_state_6.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13611
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0be8d447d63dd679f65a4483bb9d53fac65b6db4a525ca71db850fc792c03c9
|
3 |
size 13611
|
last-checkpoint/rng_state_7.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13611
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0be8d447d63dd679f65a4483bb9d53fac65b6db4a525ca71db850fc792c03c9
|
3 |
size 13611
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:466c6a5b8905e18425c9b34e30a286f9f5cd812d089137c68b3bf75167c114fb
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -622,11 +622,319 @@
|
|
622 |
"eval_samples_per_second": 490.432,
|
623 |
"eval_steps_per_second": 3.923,
|
624 |
"step": 100000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
625 |
}
|
626 |
],
|
627 |
"max_steps": 200000,
|
628 |
"num_train_epochs": 9223372036854775807,
|
629 |
-
"total_flos":
|
630 |
"trial_name": null,
|
631 |
"trial_params": null
|
632 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.355105,
|
5 |
+
"global_step": 150000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
622 |
"eval_samples_per_second": 490.432,
|
623 |
"eval_steps_per_second": 3.923,
|
624 |
"step": 100000
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 1.11,
|
628 |
+
"learning_rate": 5.330452921628497e-05,
|
629 |
+
"loss": 0.7451,
|
630 |
+
"step": 101000
|
631 |
+
},
|
632 |
+
{
|
633 |
+
"epoch": 1.12,
|
634 |
+
"learning_rate": 5.247918773366112e-05,
|
635 |
+
"loss": 0.8311,
|
636 |
+
"step": 102000
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 1.12,
|
640 |
+
"learning_rate": 5.165316846586541e-05,
|
641 |
+
"loss": 0.8221,
|
642 |
+
"step": 103000
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 1.13,
|
646 |
+
"learning_rate": 5.0826697238317935e-05,
|
647 |
+
"loss": 0.6741,
|
648 |
+
"step": 104000
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 1.13,
|
652 |
+
"learning_rate": 5e-05,
|
653 |
+
"loss": 0.5447,
|
654 |
+
"step": 105000
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 1.14,
|
658 |
+
"learning_rate": 4.917330276168208e-05,
|
659 |
+
"loss": 0.7913,
|
660 |
+
"step": 106000
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 1.14,
|
664 |
+
"learning_rate": 4.834683153413459e-05,
|
665 |
+
"loss": 0.8348,
|
666 |
+
"step": 107000
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 1.15,
|
670 |
+
"learning_rate": 4.7520812266338885e-05,
|
671 |
+
"loss": 0.7295,
|
672 |
+
"step": 108000
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 1.15,
|
676 |
+
"learning_rate": 4.669547078371504e-05,
|
677 |
+
"loss": 0.8008,
|
678 |
+
"step": 109000
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 1.16,
|
682 |
+
"learning_rate": 4.5871032726383386e-05,
|
683 |
+
"loss": 0.6031,
|
684 |
+
"step": 110000
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 1.16,
|
688 |
+
"learning_rate": 4.504772348747687e-05,
|
689 |
+
"loss": 0.5856,
|
690 |
+
"step": 111000
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 1.17,
|
694 |
+
"learning_rate": 4.4225768151520694e-05,
|
695 |
+
"loss": 0.8584,
|
696 |
+
"step": 112000
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 1.17,
|
700 |
+
"learning_rate": 4.3405391432896555e-05,
|
701 |
+
"loss": 0.8269,
|
702 |
+
"step": 113000
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 1.18,
|
706 |
+
"learning_rate": 4.2586817614407895e-05,
|
707 |
+
"loss": 0.6727,
|
708 |
+
"step": 114000
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 1.18,
|
712 |
+
"learning_rate": 4.17702704859633e-05,
|
713 |
+
"loss": 0.7562,
|
714 |
+
"step": 115000
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 1.19,
|
718 |
+
"learning_rate": 4.095597328339452e-05,
|
719 |
+
"loss": 0.5582,
|
720 |
+
"step": 116000
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 1.19,
|
724 |
+
"learning_rate": 4.0144148627425993e-05,
|
725 |
+
"loss": 0.6643,
|
726 |
+
"step": 117000
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 1.2,
|
730 |
+
"learning_rate": 3.933501846281267e-05,
|
731 |
+
"loss": 0.9486,
|
732 |
+
"step": 118000
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 1.2,
|
736 |
+
"learning_rate": 3.852880399766243e-05,
|
737 |
+
"loss": 0.7244,
|
738 |
+
"step": 119000
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 1.21,
|
742 |
+
"learning_rate": 3.772572564296005e-05,
|
743 |
+
"loss": 0.6545,
|
744 |
+
"step": 120000
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 1.21,
|
748 |
+
"learning_rate": 3.6926002952309016e-05,
|
749 |
+
"loss": 0.6842,
|
750 |
+
"step": 121000
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 1.22,
|
754 |
+
"learning_rate": 3.612985456190778e-05,
|
755 |
+
"loss": 0.6159,
|
756 |
+
"step": 122000
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 1.22,
|
760 |
+
"learning_rate": 3.533749813077677e-05,
|
761 |
+
"loss": 0.7326,
|
762 |
+
"step": 123000
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 1.23,
|
766 |
+
"learning_rate": 3.4549150281252636e-05,
|
767 |
+
"loss": 0.9025,
|
768 |
+
"step": 124000
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 1.23,
|
772 |
+
"learning_rate": 3.3765026539765834e-05,
|
773 |
+
"loss": 0.6844,
|
774 |
+
"step": 125000
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 1.24,
|
778 |
+
"learning_rate": 3.298534127791785e-05,
|
779 |
+
"loss": 0.6053,
|
780 |
+
"step": 126000
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 1.24,
|
784 |
+
"learning_rate": 3.221030765387417e-05,
|
785 |
+
"loss": 0.6597,
|
786 |
+
"step": 127000
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 1.25,
|
790 |
+
"learning_rate": 3.144013755408895e-05,
|
791 |
+
"loss": 0.6888,
|
792 |
+
"step": 128000
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 1.25,
|
796 |
+
"learning_rate": 3.0675041535377405e-05,
|
797 |
+
"loss": 0.8143,
|
798 |
+
"step": 129000
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 1.26,
|
802 |
+
"learning_rate": 2.991522876735154e-05,
|
803 |
+
"loss": 0.8078,
|
804 |
+
"step": 130000
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 1.26,
|
808 |
+
"learning_rate": 2.916090697523549e-05,
|
809 |
+
"loss": 0.6652,
|
810 |
+
"step": 131000
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 1.27,
|
814 |
+
"learning_rate": 2.8412282383075363e-05,
|
815 |
+
"loss": 0.5361,
|
816 |
+
"step": 132000
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 1.27,
|
820 |
+
"learning_rate": 2.766955965735968e-05,
|
821 |
+
"loss": 0.7314,
|
822 |
+
"step": 133000
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 1.28,
|
826 |
+
"learning_rate": 2.693294185106562e-05,
|
827 |
+
"loss": 0.7631,
|
828 |
+
"step": 134000
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 1.28,
|
832 |
+
"learning_rate": 2.6202630348146324e-05,
|
833 |
+
"loss": 0.7479,
|
834 |
+
"step": 135000
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 1.29,
|
838 |
+
"learning_rate": 2.547882480847461e-05,
|
839 |
+
"loss": 0.7767,
|
840 |
+
"step": 136000
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 1.29,
|
844 |
+
"learning_rate": 2.476172311325783e-05,
|
845 |
+
"loss": 0.6033,
|
846 |
+
"step": 137000
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 1.3,
|
850 |
+
"learning_rate": 2.405152131093926e-05,
|
851 |
+
"loss": 0.5424,
|
852 |
+
"step": 138000
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 1.3,
|
856 |
+
"learning_rate": 2.3348413563600325e-05,
|
857 |
+
"loss": 0.7977,
|
858 |
+
"step": 139000
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 1.31,
|
862 |
+
"learning_rate": 2.2652592093878666e-05,
|
863 |
+
"loss": 0.8251,
|
864 |
+
"step": 140000
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 1.31,
|
868 |
+
"learning_rate": 2.196424713241637e-05,
|
869 |
+
"loss": 0.6668,
|
870 |
+
"step": 141000
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 1.32,
|
874 |
+
"learning_rate": 2.128356686585282e-05,
|
875 |
+
"loss": 0.7531,
|
876 |
+
"step": 142000
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 1.32,
|
880 |
+
"learning_rate": 2.061073738537635e-05,
|
881 |
+
"loss": 0.5407,
|
882 |
+
"step": 143000
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 1.33,
|
886 |
+
"learning_rate": 1.9945942635848748e-05,
|
887 |
+
"loss": 0.6199,
|
888 |
+
"step": 144000
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 1.33,
|
892 |
+
"learning_rate": 1.928936436551661e-05,
|
893 |
+
"loss": 0.8869,
|
894 |
+
"step": 145000
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 1.34,
|
898 |
+
"learning_rate": 1.8641182076323148e-05,
|
899 |
+
"loss": 0.7356,
|
900 |
+
"step": 146000
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 1.34,
|
904 |
+
"learning_rate": 1.800157297483417e-05,
|
905 |
+
"loss": 0.6482,
|
906 |
+
"step": 147000
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 1.35,
|
910 |
+
"learning_rate": 1.7370711923791567e-05,
|
911 |
+
"loss": 0.6856,
|
912 |
+
"step": 148000
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 1.35,
|
916 |
+
"learning_rate": 1.6748771394307585e-05,
|
917 |
+
"loss": 0.5664,
|
918 |
+
"step": 149000
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 1.36,
|
922 |
+
"learning_rate": 1.6135921418712956e-05,
|
923 |
+
"loss": 0.6889,
|
924 |
+
"step": 150000
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 1.36,
|
928 |
+
"eval_loss": 0.619526207447052,
|
929 |
+
"eval_runtime": 17.5567,
|
930 |
+
"eval_samples_per_second": 284.792,
|
931 |
+
"eval_steps_per_second": 2.278,
|
932 |
+
"step": 150000
|
933 |
}
|
934 |
],
|
935 |
"max_steps": 200000,
|
936 |
"num_train_epochs": 9223372036854775807,
|
937 |
+
"total_flos": 2.5268140022232515e+18,
|
938 |
"trial_name": null,
|
939 |
"trial_params": null
|
940 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 442675755
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd802ee211fd38688831af0f4163cfa50c7658df48ac5ce868a3662a05e76407
|
3 |
size 442675755
|
runs/Feb06_00-07-48_t1v-n-58269bec-w-0/events.out.tfevents.1675642086.t1v-n-58269bec-w-0.23209.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78e98e11141f78192b1b5e1f4162e925430f8bb67f79567f80ebcf3fef95ccb6
|
3 |
+
size 28550
|