Training in progress, step 70000
Browse files- last-checkpoint/optimizer.pt +2 -2
- 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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9558c0bd9d5f4aacb5fae161af8898643f92f1f46cbdc853aff47b0be6b9bc49
|
3 |
+
size 402588883
|
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:ca5be79664cd044acd1aac2ca36025ee30cc3b1ceb578cf13a0c799f1149b800
|
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 sha256:24413590dc7a8b937b4007fe70a782c4bde530451d624f5c51ad8cfc9a5db9f3
|
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 sha256:50d21a2c45ce2032ca18b0ca4a0630dc8da17184949e65c53e8b11fc078db533
|
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:d511fbd39ddc83114e3470b2b5fa2b55ba48cefaae2c6ce5083dd0d02f7a3957
|
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 sha256:1384b24e0879e99d6b15e7ad94490d7bf7029f08d1efde0a29539094303e6241
|
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 sha256:729d5fd039a695b7c2e4e605bf60c2fad166564b971bb694ff97159e2fab2525
|
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:c405fd2ae9bfa68c22a1ffee2a23bd1877becbf8302a9c4412c17f7c25d16d90
|
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,
|
@@ -786,6 +786,66 @@
|
|
786 |
"learning_rate": 0.00014424718987443127,
|
787 |
"loss": 0.3583,
|
788 |
"step": 65000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
789 |
}
|
790 |
],
|
791 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.191487732019302,
|
5 |
+
"global_step": 70000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
786 |
"learning_rate": 0.00014424718987443127,
|
787 |
"loss": 0.3583,
|
788 |
"step": 65000
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 1.11,
|
792 |
+
"learning_rate": 0.00014415956729207775,
|
793 |
+
"loss": 0.3582,
|
794 |
+
"step": 65500
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 1.12,
|
798 |
+
"learning_rate": 0.00014407131148069734,
|
799 |
+
"loss": 0.3579,
|
800 |
+
"step": 66000
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 1.13,
|
804 |
+
"learning_rate": 0.00014398260171818916,
|
805 |
+
"loss": 0.3578,
|
806 |
+
"step": 66500
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 1.14,
|
810 |
+
"learning_rate": 0.00014389308333022545,
|
811 |
+
"loss": 0.3576,
|
812 |
+
"step": 67000
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 1.15,
|
816 |
+
"learning_rate": 0.00014380311527004513,
|
817 |
+
"loss": 0.3577,
|
818 |
+
"step": 67500
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 1.16,
|
822 |
+
"learning_rate": 0.00014371233783246623,
|
823 |
+
"loss": 0.3579,
|
824 |
+
"step": 68000
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 1.17,
|
828 |
+
"learning_rate": 0.00014362093157983466,
|
829 |
+
"loss": 0.3572,
|
830 |
+
"step": 68500
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 1.17,
|
834 |
+
"learning_rate": 0.0001435288974142932,
|
835 |
+
"loss": 0.3575,
|
836 |
+
"step": 69000
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 1.18,
|
840 |
+
"learning_rate": 0.00014343623624418192,
|
841 |
+
"loss": 0.3571,
|
842 |
+
"step": 69500
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 1.19,
|
846 |
+
"learning_rate": 0.00014334294898402916,
|
847 |
+
"loss": 0.3567,
|
848 |
+
"step": 70000
|
849 |
}
|
850 |
],
|
851 |
"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:ca5be79664cd044acd1aac2ca36025ee30cc3b1ceb578cf13a0c799f1149b800
|
3 |
size 201355195
|