joelniklaus
commited on
Commit
•
8259868
1
Parent(s):
44f4fe1
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/Jan16_18-30-00_t1v-n-eeadb94b-w-0/events.out.tfevents.1673893828.t1v-n-eeadb94b-w-0.17635.0 +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 2693742553
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f75a3ad0bbbc86394f319daec4d3ced52c33745e4b975256e4f5448b0631f4e
|
3 |
size 2693742553
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1346893675
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f669cb82275e0b9b619df35806db65345d133b7785b7d3fe367dd767f9c5fce
|
3 |
size 1346893675
|
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 sha256:5de3357f42c5b073bd69fff2091011011a109b6f0c27bc28d8bb9c4b3ffaf8b3
|
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 sha256:5de3357f42c5b073bd69fff2091011011a109b6f0c27bc28d8bb9c4b3ffaf8b3
|
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 sha256:5de3357f42c5b073bd69fff2091011011a109b6f0c27bc28d8bb9c4b3ffaf8b3
|
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 sha256:5de3357f42c5b073bd69fff2091011011a109b6f0c27bc28d8bb9c4b3ffaf8b3
|
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 sha256:5de3357f42c5b073bd69fff2091011011a109b6f0c27bc28d8bb9c4b3ffaf8b3
|
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 sha256:5de3357f42c5b073bd69fff2091011011a109b6f0c27bc28d8bb9c4b3ffaf8b3
|
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 sha256:5de3357f42c5b073bd69fff2091011011a109b6f0c27bc28d8bb9c4b3ffaf8b3
|
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 sha256:5de3357f42c5b073bd69fff2091011011a109b6f0c27bc28d8bb9c4b3ffaf8b3
|
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 sha256:04ad030a150fa0d8eb5e5920300951e9645dc85319159f9dd4f177aff4c5b722
|
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": 0.
|
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": 252.722,
|
623 |
"eval_steps_per_second": 3.993,
|
624 |
"step": 100000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
625 |
}
|
626 |
],
|
627 |
"max_steps": 1000000,
|
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": 0.15,
|
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": 252.722,
|
623 |
"eval_steps_per_second": 3.993,
|
624 |
"step": 100000
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.1,
|
628 |
+
"learning_rate": 9.929058033379181e-05,
|
629 |
+
"loss": 0.837,
|
630 |
+
"step": 101000
|
631 |
+
},
|
632 |
+
{
|
633 |
+
"epoch": 0.1,
|
634 |
+
"learning_rate": 9.926255646355804e-05,
|
635 |
+
"loss": 0.8858,
|
636 |
+
"step": 102000
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 0.1,
|
640 |
+
"learning_rate": 9.923399386589933e-05,
|
641 |
+
"loss": 0.8565,
|
642 |
+
"step": 103000
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 0.1,
|
646 |
+
"learning_rate": 9.92048928531717e-05,
|
647 |
+
"loss": 0.918,
|
648 |
+
"step": 104000
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.1,
|
652 |
+
"learning_rate": 9.917525374361912e-05,
|
653 |
+
"loss": 0.7992,
|
654 |
+
"step": 105000
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.11,
|
658 |
+
"learning_rate": 9.914507686137019e-05,
|
659 |
+
"loss": 0.768,
|
660 |
+
"step": 106000
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.11,
|
664 |
+
"learning_rate": 9.911436253643445e-05,
|
665 |
+
"loss": 0.8874,
|
666 |
+
"step": 107000
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 0.11,
|
670 |
+
"learning_rate": 9.90831111046988e-05,
|
671 |
+
"loss": 0.9455,
|
672 |
+
"step": 108000
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 0.11,
|
676 |
+
"learning_rate": 9.905132290792394e-05,
|
677 |
+
"loss": 0.9339,
|
678 |
+
"step": 109000
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 0.11,
|
682 |
+
"learning_rate": 9.901899829374047e-05,
|
683 |
+
"loss": 0.8543,
|
684 |
+
"step": 110000
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.11,
|
688 |
+
"learning_rate": 9.89861376156452e-05,
|
689 |
+
"loss": 0.8612,
|
690 |
+
"step": 111000
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.11,
|
694 |
+
"learning_rate": 9.895274123299723e-05,
|
695 |
+
"loss": 1.0155,
|
696 |
+
"step": 112000
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.11,
|
700 |
+
"learning_rate": 9.891880951101407e-05,
|
701 |
+
"loss": 1.0372,
|
702 |
+
"step": 113000
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.11,
|
706 |
+
"learning_rate": 9.888434282076758e-05,
|
707 |
+
"loss": 1.0676,
|
708 |
+
"step": 114000
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 0.12,
|
712 |
+
"learning_rate": 9.884934153917997e-05,
|
713 |
+
"loss": 0.9111,
|
714 |
+
"step": 115000
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.12,
|
718 |
+
"learning_rate": 9.881380604901964e-05,
|
719 |
+
"loss": 0.7757,
|
720 |
+
"step": 116000
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 0.12,
|
724 |
+
"learning_rate": 9.877773673889701e-05,
|
725 |
+
"loss": 0.9877,
|
726 |
+
"step": 117000
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 0.12,
|
730 |
+
"learning_rate": 9.87411340032603e-05,
|
731 |
+
"loss": 0.953,
|
732 |
+
"step": 118000
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.12,
|
736 |
+
"learning_rate": 9.870399824239117e-05,
|
737 |
+
"loss": 0.8896,
|
738 |
+
"step": 119000
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.12,
|
742 |
+
"learning_rate": 9.86663298624003e-05,
|
743 |
+
"loss": 0.7065,
|
744 |
+
"step": 120000
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.12,
|
748 |
+
"learning_rate": 9.862812927522309e-05,
|
749 |
+
"loss": 0.7254,
|
750 |
+
"step": 121000
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 0.12,
|
754 |
+
"learning_rate": 9.858939689861506e-05,
|
755 |
+
"loss": 0.8743,
|
756 |
+
"step": 122000
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 0.12,
|
760 |
+
"learning_rate": 9.855013315614725e-05,
|
761 |
+
"loss": 0.9483,
|
762 |
+
"step": 123000
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 0.12,
|
766 |
+
"learning_rate": 9.851033847720166e-05,
|
767 |
+
"loss": 0.9044,
|
768 |
+
"step": 124000
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.12,
|
772 |
+
"learning_rate": 9.847001329696653e-05,
|
773 |
+
"loss": 0.7765,
|
774 |
+
"step": 125000
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.13,
|
778 |
+
"learning_rate": 9.842915805643155e-05,
|
779 |
+
"loss": 0.7459,
|
780 |
+
"step": 126000
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.13,
|
784 |
+
"learning_rate": 9.838777320238312e-05,
|
785 |
+
"loss": 1.0114,
|
786 |
+
"step": 127000
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.13,
|
790 |
+
"learning_rate": 9.834585918739936e-05,
|
791 |
+
"loss": 1.0475,
|
792 |
+
"step": 128000
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 0.13,
|
796 |
+
"learning_rate": 9.830341646984521e-05,
|
797 |
+
"loss": 0.9809,
|
798 |
+
"step": 129000
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 0.13,
|
802 |
+
"learning_rate": 9.826044551386744e-05,
|
803 |
+
"loss": 0.8786,
|
804 |
+
"step": 130000
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.13,
|
808 |
+
"learning_rate": 9.821694678938953e-05,
|
809 |
+
"loss": 0.9085,
|
810 |
+
"step": 131000
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 0.13,
|
814 |
+
"learning_rate": 9.817292077210659e-05,
|
815 |
+
"loss": 0.9959,
|
816 |
+
"step": 132000
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.13,
|
820 |
+
"learning_rate": 9.812836794348004e-05,
|
821 |
+
"loss": 0.9809,
|
822 |
+
"step": 133000
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 0.13,
|
826 |
+
"learning_rate": 9.808328879073251e-05,
|
827 |
+
"loss": 0.8956,
|
828 |
+
"step": 134000
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.14,
|
832 |
+
"learning_rate": 9.803768380684242e-05,
|
833 |
+
"loss": 0.7716,
|
834 |
+
"step": 135000
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.14,
|
838 |
+
"learning_rate": 9.799155349053851e-05,
|
839 |
+
"loss": 0.7292,
|
840 |
+
"step": 136000
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 0.14,
|
844 |
+
"learning_rate": 9.794489834629455e-05,
|
845 |
+
"loss": 0.8515,
|
846 |
+
"step": 137000
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 0.14,
|
850 |
+
"learning_rate": 9.789771888432375e-05,
|
851 |
+
"loss": 0.8932,
|
852 |
+
"step": 138000
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 0.14,
|
856 |
+
"learning_rate": 9.785001562057309e-05,
|
857 |
+
"loss": 0.8301,
|
858 |
+
"step": 139000
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 0.14,
|
862 |
+
"learning_rate": 9.780178907671789e-05,
|
863 |
+
"loss": 0.7513,
|
864 |
+
"step": 140000
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.14,
|
868 |
+
"learning_rate": 9.775303978015585e-05,
|
869 |
+
"loss": 0.8437,
|
870 |
+
"step": 141000
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.14,
|
874 |
+
"learning_rate": 9.77037682640015e-05,
|
875 |
+
"loss": 0.8646,
|
876 |
+
"step": 142000
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 0.14,
|
880 |
+
"learning_rate": 9.765397506708023e-05,
|
881 |
+
"loss": 0.9861,
|
882 |
+
"step": 143000
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 0.14,
|
886 |
+
"learning_rate": 9.760366073392246e-05,
|
887 |
+
"loss": 0.9019,
|
888 |
+
"step": 144000
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 0.14,
|
892 |
+
"learning_rate": 9.755282581475769e-05,
|
893 |
+
"loss": 0.8397,
|
894 |
+
"step": 145000
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.15,
|
898 |
+
"learning_rate": 9.750147086550844e-05,
|
899 |
+
"loss": 0.971,
|
900 |
+
"step": 146000
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 0.15,
|
904 |
+
"learning_rate": 9.744959644778422e-05,
|
905 |
+
"loss": 1.0129,
|
906 |
+
"step": 147000
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 0.15,
|
910 |
+
"learning_rate": 9.739720312887535e-05,
|
911 |
+
"loss": 1.0488,
|
912 |
+
"step": 148000
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.15,
|
916 |
+
"learning_rate": 9.734429148174675e-05,
|
917 |
+
"loss": 0.7958,
|
918 |
+
"step": 149000
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 0.15,
|
922 |
+
"learning_rate": 9.729086208503174e-05,
|
923 |
+
"loss": 0.7959,
|
924 |
+
"step": 150000
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.15,
|
928 |
+
"eval_loss": 0.536599338054657,
|
929 |
+
"eval_runtime": 19.5468,
|
930 |
+
"eval_samples_per_second": 255.796,
|
931 |
+
"eval_steps_per_second": 4.042,
|
932 |
+
"step": 150000
|
933 |
}
|
934 |
],
|
935 |
"max_steps": 1000000,
|
936 |
"num_train_epochs": 9223372036854775807,
|
937 |
+
"total_flos": 8.9474847473664e+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 1346893675
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f669cb82275e0b9b619df35806db65345d133b7785b7d3fe367dd767f9c5fce
|
3 |
size 1346893675
|
runs/Jan16_18-30-00_t1v-n-eeadb94b-w-0/events.out.tfevents.1673893828.t1v-n-eeadb94b-w-0.17635.0
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:a04e8e14cc6239ce59e60d577a447f139386cfb8dae87eb0dee12ba92ba63ec0
|
3 |
+
size 28560
|