Training in progress, epoch 1
Browse files- .DS_Store +3 -0
- .gitattributes +1 -0
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +9 -3
- pytorch_model.bin +1 -1
.DS_Store
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3facec42dffe56a144fca55e27b342981f24cd1a2ecb16de96eb8ad60b17f33
|
3 |
+
size 6148
|
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
.DS_Store filter=lfs diff=lfs merge=lfs -text
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4549979235
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b93106b874d8244fd56337c49045849ad0d922361313c8e021dd5cded617acc
|
3 |
size 4549979235
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2283790449
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:183bbab7a3a962774bb7bbb26ba88b5e47c1be0c91575142a1ddeece4a55c5fa
|
3 |
size 2283790449
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13547
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:617edc5cf54e4631ea5fd80a3f2514082f76f153e3f643d4e49b5cc5c897a2ae
|
3 |
size 13547
|
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:fa3f55ff9dba325cac918a4dea786efe673f3c5882de38d4fe584b12aa16f472
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -18,11 +18,17 @@
|
|
18 |
"learning_rate": 1.304878048780488e-05,
|
19 |
"loss": 6.7693,
|
20 |
"step": 107
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
}
|
22 |
],
|
23 |
"max_steps": 214,
|
24 |
"num_train_epochs": 2,
|
25 |
-
"total_flos":
|
26 |
"trial_name": null,
|
27 |
"trial_params": null
|
28 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.998833138856476,
|
5 |
+
"global_step": 214,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
18 |
"learning_rate": 1.304878048780488e-05,
|
19 |
"loss": 6.7693,
|
20 |
"step": 107
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.0,
|
24 |
+
"learning_rate": 0.0,
|
25 |
+
"loss": 6.0583,
|
26 |
+
"step": 214
|
27 |
}
|
28 |
],
|
29 |
"max_steps": 214,
|
30 |
"num_train_epochs": 2,
|
31 |
+
"total_flos": 9814686666227712.0,
|
32 |
"trial_name": null,
|
33 |
"trial_params": null
|
34 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2283790449
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:183bbab7a3a962774bb7bbb26ba88b5e47c1be0c91575142a1ddeece4a55c5fa
|
3 |
size 2283790449
|