Training in progress, step 490000
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 sha256:178883126f742478215a0267502f52dfe2175462d20f71597ac057f2c185b8df
|
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:c87437fb8d513078a7fa88a77ceb811370c6d45f14ffc8cca34c769e3ad7f6a0
|
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:a5697c37684b08088109f3f0ea1fa303f9cdf765d37e21094da80825b4a2182b
|
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:e2c749b2c3ce91991bf321fefb57404d9e942874eb248e14b427c0b7399112fd
|
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 sha256:10cbf559a2563cd5e52765b8cfa6644692a91812c0c4c969d8cccf14c1c0b692
|
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:a428e64efcf776fc25a7dae24d0ab024bb3c89f64b632625ff152c13603cc3c4
|
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 sha256:9ecc50e62b3b1f6aafdd205bb5c9fdca31f73a64cfab6f0e155711e1e648c11e
|
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 sha256:0df9a10ef6f220c6878ab82924dc84c78c07f3cbd0fb3893855a6bf766550fd9
|
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": 8.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -5826,6 +5826,66 @@
|
|
5826 |
"learning_rate": 1.0318450696414725e-05,
|
5827 |
"loss": 0.3186,
|
5828 |
"step": 485000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5829 |
}
|
5830 |
],
|
5831 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.340422634700982,
|
5 |
+
"global_step": 490000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
5826 |
"learning_rate": 1.0318450696414725e-05,
|
5827 |
"loss": 0.3186,
|
5828 |
"step": 485000
|
5829 |
+
},
|
5830 |
+
{
|
5831 |
+
"epoch": 8.26,
|
5832 |
+
"learning_rate": 1.0297841871085698e-05,
|
5833 |
+
"loss": 0.3183,
|
5834 |
+
"step": 485500
|
5835 |
+
},
|
5836 |
+
{
|
5837 |
+
"epoch": 8.27,
|
5838 |
+
"learning_rate": 1.0277920977917513e-05,
|
5839 |
+
"loss": 0.3184,
|
5840 |
+
"step": 486000
|
5841 |
+
},
|
5842 |
+
{
|
5843 |
+
"epoch": 8.28,
|
5844 |
+
"learning_rate": 1.0258763773572561e-05,
|
5845 |
+
"loss": 0.3186,
|
5846 |
+
"step": 486500
|
5847 |
+
},
|
5848 |
+
{
|
5849 |
+
"epoch": 8.29,
|
5850 |
+
"learning_rate": 1.0240216574124515e-05,
|
5851 |
+
"loss": 0.3183,
|
5852 |
+
"step": 487000
|
5853 |
+
},
|
5854 |
+
{
|
5855 |
+
"epoch": 8.3,
|
5856 |
+
"learning_rate": 1.022235787557572e-05,
|
5857 |
+
"loss": 0.3183,
|
5858 |
+
"step": 487500
|
5859 |
+
},
|
5860 |
+
{
|
5861 |
+
"epoch": 8.31,
|
5862 |
+
"learning_rate": 1.0205187854184327e-05,
|
5863 |
+
"loss": 0.3185,
|
5864 |
+
"step": 488000
|
5865 |
+
},
|
5866 |
+
{
|
5867 |
+
"epoch": 8.31,
|
5868 |
+
"learning_rate": 1.0188706679411501e-05,
|
5869 |
+
"loss": 0.3182,
|
5870 |
+
"step": 488500
|
5871 |
+
},
|
5872 |
+
{
|
5873 |
+
"epoch": 8.32,
|
5874 |
+
"learning_rate": 1.0172914513919786e-05,
|
5875 |
+
"loss": 0.3185,
|
5876 |
+
"step": 489000
|
5877 |
+
},
|
5878 |
+
{
|
5879 |
+
"epoch": 8.33,
|
5880 |
+
"learning_rate": 1.0157811513571486e-05,
|
5881 |
+
"loss": 0.3183,
|
5882 |
+
"step": 489500
|
5883 |
+
},
|
5884 |
+
{
|
5885 |
+
"epoch": 8.34,
|
5886 |
+
"learning_rate": 1.0143397827427121e-05,
|
5887 |
+
"loss": 0.3183,
|
5888 |
+
"step": 490000
|
5889 |
}
|
5890 |
],
|
5891 |
"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:c87437fb8d513078a7fa88a77ceb811370c6d45f14ffc8cca34c769e3ad7f6a0
|
3 |
size 201355195
|