mprzibilla
commited on
Commit
•
8a52de7
1
Parent(s):
ed5dade
Training in progress, step 12900
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 +19 -3
- 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 168299
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5990995660d7c8ef450a06f4f502b88c7d752b56eec9f1cec91e8d3513b2a441
|
3 |
size 168299
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377643361
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:936a710233cf483b671c9477973ee64f4dfca8c393e650dab6af783eb8ddb9b0
|
3 |
size 377643361
|
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 sha256:8ded27760656c0d272b31d2ec257c97ddeec796cbce5f12c71319260e973b38f
|
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:bb3b559632ef334f45db24351ce386ff70c241ff4efb81c961a12e1e7bf84f49
|
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 sha256:3a4a0aa4359797d3666762513dc8ad38c116a34a6308ea535e1a273206e85322
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -22,11 +22,27 @@
|
|
22 |
"eval_steps_per_second": 3.35,
|
23 |
"eval_wer": 1.0,
|
24 |
"step": 6450
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
}
|
26 |
],
|
27 |
"max_steps": 64500,
|
28 |
"num_train_epochs": 250,
|
29 |
-
"total_flos":
|
30 |
"trial_name": null,
|
31 |
"trial_params": null
|
32 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 50.0,
|
5 |
+
"global_step": 12900,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
22 |
"eval_steps_per_second": 3.35,
|
23 |
"eval_wer": 1.0,
|
24 |
"step": 6450
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 50.0,
|
28 |
+
"learning_rate": 8.422521419828641e-05,
|
29 |
+
"loss": 3.1417,
|
30 |
+
"step": 12900
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 50.0,
|
34 |
+
"eval_cer": 0.9991341991341991,
|
35 |
+
"eval_loss": 3.1051225662231445,
|
36 |
+
"eval_runtime": 7.9823,
|
37 |
+
"eval_samples_per_second": 26.308,
|
38 |
+
"eval_steps_per_second": 3.382,
|
39 |
+
"eval_wer": 1.0,
|
40 |
+
"step": 12900
|
41 |
}
|
42 |
],
|
43 |
"max_steps": 64500,
|
44 |
"num_train_epochs": 250,
|
45 |
+
"total_flos": 1.2395173933378003e+19,
|
46 |
"trial_name": null,
|
47 |
"trial_params": null
|
48 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377643361
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:936a710233cf483b671c9477973ee64f4dfca8c393e650dab6af783eb8ddb9b0
|
3 |
size 377643361
|