Training in progress, step 75000
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 402588883
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0d07af011838f993a544d0d02b38265dac8d41c34aab6379e41f7bc77d48094
|
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 sha256:473706825a9b4aa19902641b7ee3768e1c60dd9464b846ba89f1d10d52253b12
|
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 sha256:9c7cdcf1b8cda073df90d257faf9337b2880cb8e3f2f8d3bbe87d5e0afe5ed3b
|
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 sha256:36192d2bef6cf30c681567b08e73d1b886a1fd0830e0cdd6bc5b220284b2f8bc
|
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:dac06026e4f5bbce885225c64fcc3791323c806a8653cb4f669287f5f812b355
|
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 sha256:62a4483973cba21d2355f7f8e4905cdfd0e8ee8b56d0382d9079bf7e677060f0
|
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 sha256:8c5516e1bb600442587bbc86f33aae3bf87afa369754d1c6c6c42df83a1eb2d9
|
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 sha256:325dbba8e79ee8b2de67f010b0f1fc6029f1fe483402304dbc3c73eed6f614e7
|
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,
|
@@ -846,6 +846,66 @@
|
|
846 |
"learning_rate": 0.00014334257457903268,
|
847 |
"loss": 0.3572,
|
848 |
"step": 70000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
849 |
}
|
850 |
],
|
851 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.2765957446808511,
|
5 |
+
"global_step": 75000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
846 |
"learning_rate": 0.00014334257457903268,
|
847 |
"loss": 0.3572,
|
848 |
"step": 70000
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 1.2,
|
852 |
+
"learning_rate": 0.00014324865965072573,
|
853 |
+
"loss": 0.3569,
|
854 |
+
"step": 70500
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 1.21,
|
858 |
+
"learning_rate": 0.00014315412048368257,
|
859 |
+
"loss": 0.357,
|
860 |
+
"step": 71000
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 1.22,
|
864 |
+
"learning_rate": 0.0001430589580109666,
|
865 |
+
"loss": 0.3565,
|
866 |
+
"step": 71500
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 1.23,
|
870 |
+
"learning_rate": 0.00014296355754965273,
|
871 |
+
"loss": 0.3563,
|
872 |
+
"step": 72000
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 1.23,
|
876 |
+
"learning_rate": 0.00014286715377317228,
|
877 |
+
"loss": 0.3563,
|
878 |
+
"step": 72500
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 1.24,
|
882 |
+
"learning_rate": 0.00014277012952326458,
|
883 |
+
"loss": 0.3563,
|
884 |
+
"step": 73000
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 1.25,
|
888 |
+
"learning_rate": 0.0001426724857575198,
|
889 |
+
"loss": 0.3561,
|
890 |
+
"step": 73500
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 1.26,
|
894 |
+
"learning_rate": 0.00014257422343964251,
|
895 |
+
"loss": 0.3562,
|
896 |
+
"step": 74000
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 1.27,
|
900 |
+
"learning_rate": 0.0001424753435394421,
|
901 |
+
"loss": 0.3558,
|
902 |
+
"step": 74500
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 1.28,
|
906 |
+
"learning_rate": 0.00014237584703282328,
|
907 |
+
"loss": 0.3557,
|
908 |
+
"step": 75000
|
909 |
}
|
910 |
],
|
911 |
"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 sha256:473706825a9b4aa19902641b7ee3768e1c60dd9464b846ba89f1d10d52253b12
|
3 |
size 201355195
|