Training in progress, step 160000
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:b8968668f8e27a4b1f96233ae49ecc50f9c5e2545b54cfd93a555e927df80094
|
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:b89bdd1c6f08275cb2e1aa04e72a056b06bf108dbc0c3d5afa37eabd03b17492
|
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:f3b3067508029879e87896713b3349dd43bd7950f30ba5b07186a08274e98f7c
|
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 sha256:9474c05d6e8a6f5b3019c66a256463bb7adb6a64e5874719f1764013b2276887
|
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:acc0bbfd6cb18044a737e07a313f5f858ebe57567f2d9d9913eda502ae80129e
|
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 sha256:2f8038127f9fec31bcc4140df87dba7f06dcbd7f6877e348434496dc82dc7b3e
|
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 sha256:0c96c7d78c8952f41e39235dd3c789bd91208bed751957c893a54fb569c1a59d
|
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 sha256:942a796eb949e7a972ad24a9f551ee4a24f1d706d7871dd44739891b623c5763
|
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": 2.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1866,6 +1866,66 @@
|
|
1866 |
"learning_rate": 0.00011936802347035692,
|
1867 |
"loss": 0.3417,
|
1868 |
"step": 155000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1869 |
}
|
1870 |
],
|
1871 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.723398098739585,
|
5 |
+
"global_step": 160000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1866 |
"learning_rate": 0.00011936802347035692,
|
1867 |
"loss": 0.3417,
|
1868 |
"step": 155000
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 2.65,
|
1872 |
+
"learning_rate": 0.00011918599236764778,
|
1873 |
+
"loss": 0.3415,
|
1874 |
+
"step": 155500
|
1875 |
+
},
|
1876 |
+
{
|
1877 |
+
"epoch": 2.66,
|
1878 |
+
"learning_rate": 0.00011900357451501401,
|
1879 |
+
"loss": 0.3417,
|
1880 |
+
"step": 156000
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 2.66,
|
1884 |
+
"learning_rate": 0.00011882077171284612,
|
1885 |
+
"loss": 0.3421,
|
1886 |
+
"step": 156500
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 2.67,
|
1890 |
+
"learning_rate": 0.00011863795251840704,
|
1891 |
+
"loss": 0.3414,
|
1892 |
+
"step": 157000
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 2.68,
|
1896 |
+
"learning_rate": 0.00011845512101771738,
|
1897 |
+
"loss": 0.3419,
|
1898 |
+
"step": 157500
|
1899 |
+
},
|
1900 |
+
{
|
1901 |
+
"epoch": 2.69,
|
1902 |
+
"learning_rate": 0.00011827117647893832,
|
1903 |
+
"loss": 0.3414,
|
1904 |
+
"step": 158000
|
1905 |
+
},
|
1906 |
+
{
|
1907 |
+
"epoch": 2.7,
|
1908 |
+
"learning_rate": 0.0001180868542190981,
|
1909 |
+
"loss": 0.3423,
|
1910 |
+
"step": 158500
|
1911 |
+
},
|
1912 |
+
{
|
1913 |
+
"epoch": 2.71,
|
1914 |
+
"learning_rate": 0.00011790215605738305,
|
1915 |
+
"loss": 0.3417,
|
1916 |
+
"step": 159000
|
1917 |
+
},
|
1918 |
+
{
|
1919 |
+
"epoch": 2.71,
|
1920 |
+
"learning_rate": 0.00011771708381668941,
|
1921 |
+
"loss": 0.3412,
|
1922 |
+
"step": 159500
|
1923 |
+
},
|
1924 |
+
{
|
1925 |
+
"epoch": 2.72,
|
1926 |
+
"learning_rate": 0.00011753163932360551,
|
1927 |
+
"loss": 0.3408,
|
1928 |
+
"step": 160000
|
1929 |
}
|
1930 |
],
|
1931 |
"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:b89bdd1c6f08275cb2e1aa04e72a056b06bf108dbc0c3d5afa37eabd03b17492
|
3 |
size 201355195
|