kiddothe2b
commited on
Commit
•
a9150e3
1
Parent(s):
e3f0379
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
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/Nov16_15-57-21_t1v-n-7cb529b4-w-0/1668614313.8713548/events.out.tfevents.1668614313.t1v-n-7cb529b4-w-0.98881.1 +3 -0
- runs/Nov16_15-57-21_t1v-n-7cb529b4-w-0/events.out.tfevents.1668614313.t1v-n-7cb529b4-w-0.98881.0 +3 -0
- training_args.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2841350745
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a53fa93ca662c0bc47c9d6d9f05165b95e8fb0b07e5b6403ba005c9cd3032b3
|
3 |
size 2841350745
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1420697771
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4f23cdeceba549e1359f551d695effa6180114e9c8a913609d4e89fb79cc965
|
3 |
size 1420697771
|
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 sha256:8ccadf308d5eede31bd23f361422f848997534a5b5edd908bc19d6cd2ca8e824
|
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 sha256:8ccadf308d5eede31bd23f361422f848997534a5b5edd908bc19d6cd2ca8e824
|
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 sha256:8ccadf308d5eede31bd23f361422f848997534a5b5edd908bc19d6cd2ca8e824
|
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 sha256:8ccadf308d5eede31bd23f361422f848997534a5b5edd908bc19d6cd2ca8e824
|
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 sha256:8ccadf308d5eede31bd23f361422f848997534a5b5edd908bc19d6cd2ca8e824
|
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 sha256:8ccadf308d5eede31bd23f361422f848997534a5b5edd908bc19d6cd2ca8e824
|
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 sha256:8ccadf308d5eede31bd23f361422f848997534a5b5edd908bc19d6cd2ca8e824
|
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 sha256:8ccadf308d5eede31bd23f361422f848997534a5b5edd908bc19d6cd2ca8e824
|
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": 257.13,
|
623 |
"eval_steps_per_second": 4.037,
|
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": 257.13,
|
623 |
"eval_steps_per_second": 4.037,
|
624 |
"step": 100000
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.1,
|
628 |
+
"learning_rate": 9.929058033379181e-05,
|
629 |
+
"loss": 1.0156,
|
630 |
+
"step": 101000
|
631 |
+
},
|
632 |
+
{
|
633 |
+
"epoch": 0.1,
|
634 |
+
"learning_rate": 9.926255646355804e-05,
|
635 |
+
"loss": 1.0274,
|
636 |
+
"step": 102000
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 0.1,
|
640 |
+
"learning_rate": 9.923399386589933e-05,
|
641 |
+
"loss": 1.0336,
|
642 |
+
"step": 103000
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 0.1,
|
646 |
+
"learning_rate": 9.92048928531717e-05,
|
647 |
+
"loss": 1.0492,
|
648 |
+
"step": 104000
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.1,
|
652 |
+
"learning_rate": 9.917525374361912e-05,
|
653 |
+
"loss": 1.0562,
|
654 |
+
"step": 105000
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.11,
|
658 |
+
"learning_rate": 9.914507686137019e-05,
|
659 |
+
"loss": 1.0514,
|
660 |
+
"step": 106000
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.11,
|
664 |
+
"learning_rate": 9.911436253643445e-05,
|
665 |
+
"loss": 1.0364,
|
666 |
+
"step": 107000
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 0.11,
|
670 |
+
"learning_rate": 9.90831111046988e-05,
|
671 |
+
"loss": 1.0307,
|
672 |
+
"step": 108000
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 0.11,
|
676 |
+
"learning_rate": 9.905132290792394e-05,
|
677 |
+
"loss": 1.0463,
|
678 |
+
"step": 109000
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 0.11,
|
682 |
+
"learning_rate": 9.901899829374047e-05,
|
683 |
+
"loss": 1.0372,
|
684 |
+
"step": 110000
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.11,
|
688 |
+
"learning_rate": 9.89861376156452e-05,
|
689 |
+
"loss": 1.0376,
|
690 |
+
"step": 111000
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.11,
|
694 |
+
"learning_rate": 9.895274123299723e-05,
|
695 |
+
"loss": 1.0698,
|
696 |
+
"step": 112000
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.11,
|
700 |
+
"learning_rate": 9.891880951101407e-05,
|
701 |
+
"loss": 1.0634,
|
702 |
+
"step": 113000
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.11,
|
706 |
+
"learning_rate": 9.888434282076758e-05,
|
707 |
+
"loss": 1.059,
|
708 |
+
"step": 114000
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 0.12,
|
712 |
+
"learning_rate": 9.884934153917997e-05,
|
713 |
+
"loss": 1.052,
|
714 |
+
"step": 115000
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.12,
|
718 |
+
"learning_rate": 9.881380604901964e-05,
|
719 |
+
"loss": 1.0415,
|
720 |
+
"step": 116000
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 0.12,
|
724 |
+
"learning_rate": 9.877773673889701e-05,
|
725 |
+
"loss": 1.051,
|
726 |
+
"step": 117000
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 0.12,
|
730 |
+
"learning_rate": 9.87411340032603e-05,
|
731 |
+
"loss": 1.0513,
|
732 |
+
"step": 118000
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.12,
|
736 |
+
"learning_rate": 9.870399824239117e-05,
|
737 |
+
"loss": 1.0563,
|
738 |
+
"step": 119000
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.12,
|
742 |
+
"learning_rate": 9.86663298624003e-05,
|
743 |
+
"loss": 1.067,
|
744 |
+
"step": 120000
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.12,
|
748 |
+
"learning_rate": 9.862812927522309e-05,
|
749 |
+
"loss": 1.0724,
|
750 |
+
"step": 121000
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 0.12,
|
754 |
+
"learning_rate": 9.858939689861506e-05,
|
755 |
+
"loss": 1.046,
|
756 |
+
"step": 122000
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 0.12,
|
760 |
+
"learning_rate": 9.855013315614725e-05,
|
761 |
+
"loss": 1.0402,
|
762 |
+
"step": 123000
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 0.12,
|
766 |
+
"learning_rate": 9.851033847720166e-05,
|
767 |
+
"loss": 1.0145,
|
768 |
+
"step": 124000
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.12,
|
772 |
+
"learning_rate": 9.847001329696653e-05,
|
773 |
+
"loss": 1.0527,
|
774 |
+
"step": 125000
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.13,
|
778 |
+
"learning_rate": 9.842915805643155e-05,
|
779 |
+
"loss": 1.0467,
|
780 |
+
"step": 126000
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.13,
|
784 |
+
"learning_rate": 9.838777320238312e-05,
|
785 |
+
"loss": 1.0358,
|
786 |
+
"step": 127000
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.13,
|
790 |
+
"learning_rate": 9.834585918739936e-05,
|
791 |
+
"loss": 1.0235,
|
792 |
+
"step": 128000
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 0.13,
|
796 |
+
"learning_rate": 9.830341646984521e-05,
|
797 |
+
"loss": 1.0188,
|
798 |
+
"step": 129000
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 0.13,
|
802 |
+
"learning_rate": 9.826044551386744e-05,
|
803 |
+
"loss": 1.0207,
|
804 |
+
"step": 130000
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.13,
|
808 |
+
"learning_rate": 9.821694678938953e-05,
|
809 |
+
"loss": 1.0287,
|
810 |
+
"step": 131000
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 0.13,
|
814 |
+
"learning_rate": 9.817292077210659e-05,
|
815 |
+
"loss": 1.0227,
|
816 |
+
"step": 132000
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.13,
|
820 |
+
"learning_rate": 9.812836794348004e-05,
|
821 |
+
"loss": 1.0121,
|
822 |
+
"step": 133000
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 0.13,
|
826 |
+
"learning_rate": 9.808328879073251e-05,
|
827 |
+
"loss": 1.0159,
|
828 |
+
"step": 134000
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.14,
|
832 |
+
"learning_rate": 9.803768380684242e-05,
|
833 |
+
"loss": 1.0169,
|
834 |
+
"step": 135000
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.14,
|
838 |
+
"learning_rate": 9.799155349053851e-05,
|
839 |
+
"loss": 1.0077,
|
840 |
+
"step": 136000
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 0.14,
|
844 |
+
"learning_rate": 9.794489834629455e-05,
|
845 |
+
"loss": 1.0009,
|
846 |
+
"step": 137000
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 0.14,
|
850 |
+
"learning_rate": 9.789771888432375e-05,
|
851 |
+
"loss": 1.041,
|
852 |
+
"step": 138000
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 0.14,
|
856 |
+
"learning_rate": 9.785001562057309e-05,
|
857 |
+
"loss": 1.0423,
|
858 |
+
"step": 139000
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 0.14,
|
862 |
+
"learning_rate": 9.780178907671789e-05,
|
863 |
+
"loss": 1.0141,
|
864 |
+
"step": 140000
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.14,
|
868 |
+
"learning_rate": 9.775303978015585e-05,
|
869 |
+
"loss": 1.0446,
|
870 |
+
"step": 141000
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.14,
|
874 |
+
"learning_rate": 9.77037682640015e-05,
|
875 |
+
"loss": 1.0398,
|
876 |
+
"step": 142000
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 0.14,
|
880 |
+
"learning_rate": 9.765397506708023e-05,
|
881 |
+
"loss": 1.0306,
|
882 |
+
"step": 143000
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 0.14,
|
886 |
+
"learning_rate": 9.760366073392246e-05,
|
887 |
+
"loss": 1.0373,
|
888 |
+
"step": 144000
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 0.14,
|
892 |
+
"learning_rate": 9.755282581475769e-05,
|
893 |
+
"loss": 1.032,
|
894 |
+
"step": 145000
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.15,
|
898 |
+
"learning_rate": 9.750147086550844e-05,
|
899 |
+
"loss": 1.0356,
|
900 |
+
"step": 146000
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 0.15,
|
904 |
+
"learning_rate": 9.744959644778422e-05,
|
905 |
+
"loss": 1.035,
|
906 |
+
"step": 147000
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 0.15,
|
910 |
+
"learning_rate": 9.739720312887535e-05,
|
911 |
+
"loss": 1.041,
|
912 |
+
"step": 148000
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.15,
|
916 |
+
"learning_rate": 9.734429148174675e-05,
|
917 |
+
"loss": 1.0345,
|
918 |
+
"step": 149000
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 0.15,
|
922 |
+
"learning_rate": 9.729086208503174e-05,
|
923 |
+
"loss": 1.0225,
|
924 |
+
"step": 150000
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.15,
|
928 |
+
"eval_loss": 0.7951192259788513,
|
929 |
+
"eval_runtime": 45.8559,
|
930 |
+
"eval_samples_per_second": 218.074,
|
931 |
+
"eval_steps_per_second": 3.424,
|
932 |
+
"step": 150000
|
933 |
}
|
934 |
],
|
935 |
"max_steps": 1000000,
|
936 |
"num_train_epochs": 9223372036854775807,
|
937 |
+
"total_flos": 4.4740077944832e+18,
|
938 |
"trial_name": null,
|
939 |
"trial_params": null
|
940 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3375
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41708c0a8724c41fc71ce304e9e3844c12f12ca174419806118cd58e11ef4acb
|
3 |
size 3375
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1420697771
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4f23cdeceba549e1359f551d695effa6180114e9c8a913609d4e89fb79cc965
|
3 |
size 1420697771
|
runs/Nov16_15-57-21_t1v-n-7cb529b4-w-0/1668614313.8713548/events.out.tfevents.1668614313.t1v-n-7cb529b4-w-0.98881.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1841679cb3029777953dbf349547114d8eb2fb1095e5a362435c9843774e3108
|
3 |
+
size 5405
|
runs/Nov16_15-57-21_t1v-n-7cb529b4-w-0/events.out.tfevents.1668614313.t1v-n-7cb529b4-w-0.98881.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5326594209c1e9e485538fc870ea08205183afc409535a4c7ef4dfee9081a38d
|
3 |
+
size 12010
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3375
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41708c0a8724c41fc71ce304e9e3844c12f12ca174419806118cd58e11ef4acb
|
3 |
size 3375
|