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:c22a9f22e2d5b785df46d9b7a8fe9a9c4efe60bdb34cf132177ee2acc41f26fe
|
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 sha256:5e04cd1040cdc4c57ed88e4272d765f99e2cfaf43a917176af07b16270b8ec4f
|
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:aac258cfa9cde57b545ebcebba3d88b970f0be99ec2525aa6c7d7c91278520a8
|
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 sha256:21fa739593d83437910561e91280223e191faa045c5d781331a0da52db20119f
|
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 sha256:41909d3e589f9f603d1293b38821384d947912fa7f231df4bab76bdae26c7332
|
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:c46695999bc45c6ffb44561be9ac3cc34e5b1c30948ed586cd365b404206c75b
|
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 sha256:22dd04c6be986b933dbf36885b7a308ab00202782f956c433993fd7d5ef14eee
|
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:df2582cf1a8d0ed83809cdd0ef4cf777e1f10582d71345c2c15d4aa973ff3077
|
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": 0.0001193672961187343,
|
1867 |
"loss": 0.3383,
|
1868 |
"step": 155000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1869 |
}
|
1870 |
],
|
1871 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.723404255319149,
|
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": 0.0001193672961187343,
|
1867 |
"loss": 0.3383,
|
1868 |
"step": 155000
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 2.65,
|
1872 |
+
"learning_rate": 0.00011918526346544411,
|
1873 |
+
"loss": 0.3378,
|
1874 |
+
"step": 155500
|
1875 |
+
},
|
1876 |
+
{
|
1877 |
+
"epoch": 2.66,
|
1878 |
+
"learning_rate": 0.0001190028440694233,
|
1879 |
+
"loss": 0.3376,
|
1880 |
+
"step": 156000
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 2.66,
|
1884 |
+
"learning_rate": 0.00011882003973107758,
|
1885 |
+
"loss": 0.3377,
|
1886 |
+
"step": 156500
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 2.67,
|
1890 |
+
"learning_rate": 0.00011863758576533405,
|
1891 |
+
"loss": 0.3376,
|
1892 |
+
"step": 157000
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 2.68,
|
1896 |
+
"learning_rate": 0.00011845438599438996,
|
1897 |
+
"loss": 0.3375,
|
1898 |
+
"step": 157500
|
1899 |
+
},
|
1900 |
+
{
|
1901 |
+
"epoch": 2.69,
|
1902 |
+
"learning_rate": 0.00011827043994110776,
|
1903 |
+
"loss": 0.3374,
|
1904 |
+
"step": 158000
|
1905 |
+
},
|
1906 |
+
{
|
1907 |
+
"epoch": 2.7,
|
1908 |
+
"learning_rate": 0.00011808611617403378,
|
1909 |
+
"loss": 0.3375,
|
1910 |
+
"step": 158500
|
1911 |
+
},
|
1912 |
+
{
|
1913 |
+
"epoch": 2.71,
|
1914 |
+
"learning_rate": 0.00011790141651236913,
|
1915 |
+
"loss": 0.3373,
|
1916 |
+
"step": 159000
|
1917 |
+
},
|
1918 |
+
{
|
1919 |
+
"epoch": 2.71,
|
1920 |
+
"learning_rate": 0.0001177163427790249,
|
1921 |
+
"loss": 0.3374,
|
1922 |
+
"step": 159500
|
1923 |
+
},
|
1924 |
+
{
|
1925 |
+
"epoch": 2.72,
|
1926 |
+
"learning_rate": 0.00011753089680060416,
|
1927 |
+
"loss": 0.3371,
|
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 sha256:5e04cd1040cdc4c57ed88e4272d765f99e2cfaf43a917176af07b16270b8ec4f
|
3 |
size 201355195
|