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 sha256:180bd8afcb8ea5ad3ae5a04d5f826ec4d98e9451644a379bcab2f975d3632c6f
|
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 sha256:0454b1e243d2b5dca220df0685fba6335eb1b63797f2431af905499564f43e15
|
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 sha256:70b73a32ed5abbbe50bd03d52cbc0d9f97f3bad9c8c83394d1113e5e9a9c7c63
|
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 sha256:4f22de639dadaf8f5ca48485412759765d7b50886c5fd569dc2a771bad6b9966
|
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:b862981d7b744793ba14de4eb91fa95c39e539315482c513f3de839b7f196be9
|
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:a842a7ac403f25c499f6e5769786574ac0afe54e735c6b7d2cf5e5b07eb1651b
|
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:ae031280daf8907f446f3bdbb161df8e5e839f1f031c6cce17991477b9b4dddf
|
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 sha256:068e1b75a2254acb81dd3afc8ec00c3c6ffb9c49ea1f1957f47f3efdd8db87e2
|
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": 0.0001211659584640809,
|
1807 |
"loss": 0.3427,
|
1808 |
"step": 150000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1809 |
}
|
1810 |
],
|
1811 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.63829244006434,
|
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": 0.0001211659584640809,
|
1807 |
"loss": 0.3427,
|
1808 |
"step": 150000
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 2.56,
|
1812 |
+
"learning_rate": 0.00012098789141193026,
|
1813 |
+
"loss": 0.3423,
|
1814 |
+
"step": 150500
|
1815 |
+
},
|
1816 |
+
{
|
1817 |
+
"epoch": 2.57,
|
1818 |
+
"learning_rate": 0.00012080941982583888,
|
1819 |
+
"loss": 0.3425,
|
1820 |
+
"step": 151000
|
1821 |
+
},
|
1822 |
+
{
|
1823 |
+
"epoch": 2.58,
|
1824 |
+
"learning_rate": 0.00012063054546724922,
|
1825 |
+
"loss": 0.3425,
|
1826 |
+
"step": 151500
|
1827 |
+
},
|
1828 |
+
{
|
1829 |
+
"epoch": 2.59,
|
1830 |
+
"learning_rate": 0.00012045127010157905,
|
1831 |
+
"loss": 0.3426,
|
1832 |
+
"step": 152000
|
1833 |
+
},
|
1834 |
+
{
|
1835 |
+
"epoch": 2.6,
|
1836 |
+
"learning_rate": 0.00012027195524467175,
|
1837 |
+
"loss": 0.3422,
|
1838 |
+
"step": 152500
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"epoch": 2.6,
|
1842 |
+
"learning_rate": 0.00012009188397006361,
|
1843 |
+
"loss": 0.342,
|
1844 |
+
"step": 153000
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 2.61,
|
1848 |
+
"learning_rate": 0.00011991141700474647,
|
1849 |
+
"loss": 0.3422,
|
1850 |
+
"step": 153500
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 2.62,
|
1854 |
+
"learning_rate": 0.00011973055612985635,
|
1855 |
+
"loss": 0.3417,
|
1856 |
+
"step": 154000
|
1857 |
+
},
|
1858 |
+
{
|
1859 |
+
"epoch": 2.63,
|
1860 |
+
"learning_rate": 0.00011954930313041712,
|
1861 |
+
"loss": 0.3416,
|
1862 |
+
"step": 154500
|
1863 |
+
},
|
1864 |
+
{
|
1865 |
+
"epoch": 2.64,
|
1866 |
+
"learning_rate": 0.00011936802347035692,
|
1867 |
+
"loss": 0.3417,
|
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 sha256:0454b1e243d2b5dca220df0685fba6335eb1b63797f2431af905499564f43e15
|
3 |
size 201355195
|