Training in progress, step 65000
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/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +62 -2
- pytorch_model.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 402587859
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4215af6acd9e8a4a54ea8de32144c2c56eab8677dfeede8f27af9a1626fa227e
|
3 |
size 402587859
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a571654f6cf934597476263cdeeabe499658011538e1b517ea554c4ee7542f87
|
3 |
size 201355195
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b18ca3fb7bc0896b053735d228539261bdc3104ffb63c35ec135750024dd0349
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8492c35cabd5e6c8bbd54619022bdae036db2d5c919e2d289d8cbe709440f7b
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2647a174f5bbb6962885cb20d27c5f240547a1659aba992ad01d28c6f3c3521
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df8fd15d6e16cc6c5bfab644513312ede1578148941ba0bdf0b772b9c0e274fe
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a834a65b7e6fa3e930e1ec71b3e3f570746dcd42fb9aa7e950bd9bac5ba5ac65
|
3 |
size 559
|
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 sha256:8a1647e6832313e90a8b67036f3ee420c845103b69095ce22f79ef3f8eeebf2c
|
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,
|
@@ -726,6 +726,66 @@
|
|
726 |
"learning_rate": 0.00014508823910339927,
|
727 |
"loss": 0.3599,
|
728 |
"step": 60000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
729 |
}
|
730 |
],
|
731 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.1063820733440566,
|
5 |
+
"global_step": 65000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
726 |
"learning_rate": 0.00014508823910339927,
|
727 |
"loss": 0.3599,
|
728 |
"step": 60000
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 1.03,
|
732 |
+
"learning_rate": 0.00014500699405591802,
|
733 |
+
"loss": 0.3599,
|
734 |
+
"step": 60500
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 1.04,
|
738 |
+
"learning_rate": 0.00014492510741564985,
|
739 |
+
"loss": 0.3595,
|
740 |
+
"step": 61000
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 1.05,
|
744 |
+
"learning_rate": 0.00014484257999078278,
|
745 |
+
"loss": 0.3593,
|
746 |
+
"step": 61500
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 1.06,
|
750 |
+
"learning_rate": 0.00014475941259582925,
|
751 |
+
"loss": 0.3595,
|
752 |
+
"step": 62000
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 1.06,
|
756 |
+
"learning_rate": 0.0001446756060516178,
|
757 |
+
"loss": 0.359,
|
758 |
+
"step": 62500
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 1.07,
|
762 |
+
"learning_rate": 0.00014459116118528524,
|
763 |
+
"loss": 0.3589,
|
764 |
+
"step": 63000
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 1.08,
|
768 |
+
"learning_rate": 0.00014450607883026827,
|
769 |
+
"loss": 0.3586,
|
770 |
+
"step": 63500
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 1.09,
|
774 |
+
"learning_rate": 0.00014442053189911774,
|
775 |
+
"loss": 0.3587,
|
776 |
+
"step": 64000
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 1.1,
|
780 |
+
"learning_rate": 0.00014433417836295833,
|
781 |
+
"loss": 0.3583,
|
782 |
+
"step": 64500
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 1.11,
|
786 |
+
"learning_rate": 0.00014424718987443127,
|
787 |
+
"loss": 0.3583,
|
788 |
+
"step": 65000
|
789 |
}
|
790 |
],
|
791 |
"max_steps": 500000,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a571654f6cf934597476263cdeeabe499658011538e1b517ea554c4ee7542f87
|
3 |
size 201355195
|