Training in progress, step 155000
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 sha256:68f7daf4ada534975c72881d5abfce2e76bd1f430fb375ea469c904b7a4a97eb
|
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 sha256:448958aa9c632ad5b6b74f6d4ce595e59efc34612ec2852a27b48da8ece6d017
|
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 sha256:6d5d100bd24b7b6b96b8353b3f804819476d9e77fa8e51f82f1605bc7e183e25
|
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:c2ed5b165c26a14ce93d7e7987fb566f40f51d389cc3608aa846709654912416
|
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 sha256:08a496694e65d4cf48f59b4eba320121e4ba3c9c02907ff1a50bc3eed9ddfaad
|
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:ca53e10b010512dccd71884bb9294279e07b9cc7f70d63d77f89884a29cffb21
|
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 sha256:4db330b47705f38a44d9ca503524acd867a7f5b9c7d09cea471cc2d7ef717581
|
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:e8fa9062b07f7bb6d45c3a57d7ae694a8e8584347228866c00cde8aeb5849e95
|
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,
|
@@ -1806,6 +1806,66 @@
|
|
1806 |
"learning_rate": 0.00012116524700403446,
|
1807 |
"loss": 0.3391,
|
1808 |
"step": 150000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1809 |
}
|
1810 |
],
|
1811 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.6382978723404253,
|
5 |
+
"global_step": 155000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1806 |
"learning_rate": 0.00012116524700403446,
|
1807 |
"loss": 0.3391,
|
1808 |
"step": 150000
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 2.56,
|
1812 |
+
"learning_rate": 0.00012098753487189647,
|
1813 |
+
"loss": 0.3388,
|
1814 |
+
"step": 150500
|
1815 |
+
},
|
1816 |
+
{
|
1817 |
+
"epoch": 2.57,
|
1818 |
+
"learning_rate": 0.00012080906247850084,
|
1819 |
+
"loss": 0.3386,
|
1820 |
+
"step": 151000
|
1821 |
+
},
|
1822 |
+
{
|
1823 |
+
"epoch": 2.58,
|
1824 |
+
"learning_rate": 0.00012063018731613381,
|
1825 |
+
"loss": 0.3387,
|
1826 |
+
"step": 151500
|
1827 |
+
},
|
1828 |
+
{
|
1829 |
+
"epoch": 2.59,
|
1830 |
+
"learning_rate": 0.00012045091115022107,
|
1831 |
+
"loss": 0.3389,
|
1832 |
+
"step": 152000
|
1833 |
+
},
|
1834 |
+
{
|
1835 |
+
"epoch": 2.6,
|
1836 |
+
"learning_rate": 0.00012027123575014594,
|
1837 |
+
"loss": 0.3383,
|
1838 |
+
"step": 152500
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"epoch": 2.6,
|
1842 |
+
"learning_rate": 0.00012009116288923213,
|
1843 |
+
"loss": 0.3381,
|
1844 |
+
"step": 153000
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 2.61,
|
1848 |
+
"learning_rate": 0.00011991069434472605,
|
1849 |
+
"loss": 0.3384,
|
1850 |
+
"step": 153500
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 2.62,
|
1854 |
+
"learning_rate": 0.0001197298318977794,
|
1855 |
+
"loss": 0.338,
|
1856 |
+
"step": 154000
|
1857 |
+
},
|
1858 |
+
{
|
1859 |
+
"epoch": 2.63,
|
1860 |
+
"learning_rate": 0.00011954894023270498,
|
1861 |
+
"loss": 0.3379,
|
1862 |
+
"step": 154500
|
1863 |
+
},
|
1864 |
+
{
|
1865 |
+
"epoch": 2.64,
|
1866 |
+
"learning_rate": 0.0001193672961187343,
|
1867 |
+
"loss": 0.3383,
|
1868 |
+
"step": 155000
|
1869 |
}
|
1870 |
],
|
1871 |
"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 sha256:448958aa9c632ad5b6b74f6d4ce595e59efc34612ec2852a27b48da8ece6d017
|
3 |
size 201355195
|