Training in progress, step 657000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +39 -3
- pytorch_model.bin +1 -1
- runs/Jun05_15-52-52_cc80fbc5a73c/events.out.tfevents.1685980427.cc80fbc5a73c.10476.2 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3871544599
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a709bb9b0b3c828f8b50355fccc149df56cd5cb7375483821c8238981190f88a
|
3 |
size 3871544599
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:974538bed07bd80c498e8194c0b7cce0454bcf1e87696f84a11179198e2f301b
|
3 |
size 1944201353
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ff2305055086f0b6360f4f51a015a13846329ab47afa029cfcf438d19aff04a
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b74d61c126edbf5148b356cd53fce0162983b4e7f65c357ac9a130843a11b7f
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1872f0c0f09704c71b4597aab59c53404102ae5a68b0af6472e50532c123a280
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 17.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -7854,11 +7854,47 @@
|
|
7854 |
"learning_rate": 2.485511429528359e-07,
|
7855 |
"loss": 1.0151,
|
7856 |
"step": 654000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7857 |
}
|
7858 |
],
|
7859 |
"max_steps": 762960,
|
7860 |
"num_train_epochs": 20,
|
7861 |
-
"total_flos": 7.
|
7862 |
"trial_name": null,
|
7863 |
"trial_params": null
|
7864 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 17.22239464826834,
|
5 |
+
"global_step": 657000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
7854 |
"learning_rate": 2.485511429528359e-07,
|
7855 |
"loss": 1.0151,
|
7856 |
"step": 654000
|
7857 |
+
},
|
7858 |
+
{
|
7859 |
+
"epoch": 17.16,
|
7860 |
+
"learning_rate": 2.463229956273269e-07,
|
7861 |
+
"loss": 1.0074,
|
7862 |
+
"step": 654500
|
7863 |
+
},
|
7864 |
+
{
|
7865 |
+
"epoch": 17.17,
|
7866 |
+
"learning_rate": 2.4409992626537676e-07,
|
7867 |
+
"loss": 1.0127,
|
7868 |
+
"step": 655000
|
7869 |
+
},
|
7870 |
+
{
|
7871 |
+
"epoch": 17.18,
|
7872 |
+
"learning_rate": 2.4188641906152306e-07,
|
7873 |
+
"loss": 1.0101,
|
7874 |
+
"step": 655500
|
7875 |
+
},
|
7876 |
+
{
|
7877 |
+
"epoch": 17.2,
|
7878 |
+
"learning_rate": 2.3968688171094404e-07,
|
7879 |
+
"loss": 1.0122,
|
7880 |
+
"step": 656000
|
7881 |
+
},
|
7882 |
+
{
|
7883 |
+
"epoch": 17.21,
|
7884 |
+
"learning_rate": 2.374925077590484e-07,
|
7885 |
+
"loss": 1.0292,
|
7886 |
+
"step": 656500
|
7887 |
+
},
|
7888 |
+
{
|
7889 |
+
"epoch": 17.22,
|
7890 |
+
"learning_rate": 2.3530772397233141e-07,
|
7891 |
+
"loss": 0.9995,
|
7892 |
+
"step": 657000
|
7893 |
}
|
7894 |
],
|
7895 |
"max_steps": 762960,
|
7896 |
"num_train_epochs": 20,
|
7897 |
+
"total_flos": 7.797151420425585e+17,
|
7898 |
"trial_name": null,
|
7899 |
"trial_params": null
|
7900 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:974538bed07bd80c498e8194c0b7cce0454bcf1e87696f84a11179198e2f301b
|
3 |
size 1944201353
|
runs/Jun05_15-52-52_cc80fbc5a73c/events.out.tfevents.1685980427.cc80fbc5a73c.10476.2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee87d82742882942179150264ca9f1413c2de5123ccd5c9a216f75cf720f4ab0
|
3 |
+
size 6381
|