Commit
•
b0caae6
1
Parent(s):
7cd0181
Training in progress, step 37074
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 +9 -3
- pytorch_model.bin +1 -1
- runs/Jun04_13-23-35_1c0366a2fd20/events.out.tfevents.1685885434.1c0366a2fd20.848.0 +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 6319689
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c0e997ec248e01146ddace3a10e7150e6f76dc22b5ddfa2ee5d39192a8b899f
|
3 |
size 6319689
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1121737121
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f435fffa985fe6b9eebe03ecf90ade47f162129f10d597f777825621b6d4fe4
|
3 |
size 1121737121
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14639
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92442abab44c44e49d6518b1f9c30d17b3d257a26012cd5dcdcc77f1ba853278
|
3 |
size 14639
|
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 sha256:89c5e9367ad20e4449b892e15d64442e796001d0740ab861ba14e0fcf7ea4549
|
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:af9db7b656f79d793c1fd1b36ab1006e2d6415ccf404c64e75c9565e2f495cdf
|
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": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -234,11 +234,17 @@
|
|
234 |
"learning_rate": 1.1668113777654293e-05,
|
235 |
"loss": 1.4915,
|
236 |
"step": 36000
|
|
|
|
|
|
|
|
|
|
|
|
|
237 |
}
|
238 |
],
|
239 |
"max_steps": 86379,
|
240 |
"num_train_epochs": 1,
|
241 |
-
"total_flos": 6.
|
242 |
"trial_name": null,
|
243 |
"trial_params": null
|
244 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.42920154204146843,
|
5 |
+
"global_step": 37074,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
234 |
"learning_rate": 1.1668113777654293e-05,
|
235 |
"loss": 1.4915,
|
236 |
"step": 36000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.43,
|
240 |
+
"learning_rate": 1.1436576019634403e-05,
|
241 |
+
"loss": 1.5016,
|
242 |
+
"step": 37000
|
243 |
}
|
244 |
],
|
245 |
"max_steps": 86379,
|
246 |
"num_train_epochs": 1,
|
247 |
+
"total_flos": 6.904090116646502e+16,
|
248 |
"trial_name": null,
|
249 |
"trial_params": null
|
250 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1121737121
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f435fffa985fe6b9eebe03ecf90ade47f162129f10d597f777825621b6d4fe4
|
3 |
size 1121737121
|
runs/Jun04_13-23-35_1c0366a2fd20/events.out.tfevents.1685885434.1c0366a2fd20.848.0
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 sha256:31c4386dd9463bca7616bd5a176630ea72c64ac137d0c2c55de4025f4ccad7eb
|
3 |
+
size 6429
|