Training in progress, step 660000
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:c13a1aabb55645ee7d8c9a39cabd5e3e69e05fa709ca2239844b15bdd30302d5
|
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 sha256:8b6424ffbfec0c9949ea3ff6f9d6b5e679bcfec47db34c19a76c19d60c5c035e
|
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 sha256:48456504425e2a16ea8cb0437d989984020206f6effe31410687734a003ad2d9
|
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:cd9b4bca6bd83b006db8937c0610ee297003c2866f42e0f8719ca89654449c3e
|
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 sha256:198a0ebe3caffa0ab0c1c5d4dffacfd0299f7ae8b7e248bd062c8fdead171625
|
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,
|
@@ -7890,11 +7890,47 @@
|
|
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.
|
7898 |
"trial_name": null,
|
7899 |
"trial_params": null
|
7900 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 17.30103490578897,
|
5 |
+
"global_step": 660000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
7890 |
"learning_rate": 2.3530772397233141e-07,
|
7891 |
"loss": 0.9995,
|
7892 |
"step": 657000
|
7893 |
+
},
|
7894 |
+
{
|
7895 |
+
"epoch": 17.24,
|
7896 |
+
"learning_rate": 2.3313253961150916e-07,
|
7897 |
+
"loss": 1.0093,
|
7898 |
+
"step": 657500
|
7899 |
+
},
|
7900 |
+
{
|
7901 |
+
"epoch": 17.25,
|
7902 |
+
"learning_rate": 2.3096696389660693e-07,
|
7903 |
+
"loss": 1.0065,
|
7904 |
+
"step": 658000
|
7905 |
+
},
|
7906 |
+
{
|
7907 |
+
"epoch": 17.26,
|
7908 |
+
"learning_rate": 2.2881100600692208e-07,
|
7909 |
+
"loss": 1.0142,
|
7910 |
+
"step": 658500
|
7911 |
+
},
|
7912 |
+
{
|
7913 |
+
"epoch": 17.27,
|
7914 |
+
"learning_rate": 2.2666467508098367e-07,
|
7915 |
+
"loss": 1.021,
|
7916 |
+
"step": 659000
|
7917 |
+
},
|
7918 |
+
{
|
7919 |
+
"epoch": 17.29,
|
7920 |
+
"learning_rate": 2.2453224398342994e-07,
|
7921 |
+
"loss": 1.0065,
|
7922 |
+
"step": 659500
|
7923 |
+
},
|
7924 |
+
{
|
7925 |
+
"epoch": 17.3,
|
7926 |
+
"learning_rate": 2.22405174938064e-07,
|
7927 |
+
"loss": 1.0271,
|
7928 |
+
"step": 660000
|
7929 |
}
|
7930 |
],
|
7931 |
"max_steps": 762960,
|
7932 |
"num_train_epochs": 20,
|
7933 |
+
"total_flos": 7.830074924298732e+17,
|
7934 |
"trial_name": null,
|
7935 |
"trial_params": null
|
7936 |
}
|
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 sha256:8b6424ffbfec0c9949ea3ff6f9d6b5e679bcfec47db34c19a76c19d60c5c035e
|
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:e7e9f325eeaeaf12223f32ad9a86ae8a0e517d344ae4db4045e42288c209c342
|
3 |
+
size 7341
|