mprzibilla
commited on
Commit
•
8da2b45
1
Parent(s):
7f287f0
Training in progress, epoch 2
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +20 -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 174443
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:765ced0e140406dce9693e502fe8e7bad279c4f3e89931a00e541dac734996db
|
3 |
size 174443
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377646433
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f010b8469779b656996538ec4b4b1ecb6f3bee582183c783ae70c057f71c415a
|
3 |
size 377646433
|
last-checkpoint/rng_state.pth
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 sha256:9b26e050e8f3c2629fc0fe868d03226d373f15019277f7f1282e1212e8bae0c6
|
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 sha256:8be4a5ec3ab2ee6b394d29e5c1ec9999b639163057c9c922f5b8e08f4dd11699
|
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:b3fbbb4c1827564ce4b91c122adadf0dce207e2eabacd79c0d4bd77f13bb4d48
|
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,
|
@@ -23,11 +23,28 @@
|
|
23 |
"eval_samples_per_second": 25.924,
|
24 |
"eval_steps_per_second": 3.333,
|
25 |
"step": 4270
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
27 |
],
|
28 |
"max_steps": 64050,
|
29 |
"num_train_epochs": 15,
|
30 |
-
"total_flos":
|
31 |
"trial_name": null,
|
32 |
"trial_params": null
|
33 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 8540,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
23 |
"eval_samples_per_second": 25.924,
|
24 |
"eval_steps_per_second": 3.333,
|
25 |
"step": 4270
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"learning_rate": 9.124375493031818e-05,
|
30 |
+
"loss": 3.3366,
|
31 |
+
"step": 8540
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 2.0,
|
35 |
+
"eval_cer": 1.0,
|
36 |
+
"eval_loss": 3.467925548553467,
|
37 |
+
"eval_new_wer": 1.0,
|
38 |
+
"eval_old_wer": 1.0,
|
39 |
+
"eval_runtime": 8.5159,
|
40 |
+
"eval_samples_per_second": 24.66,
|
41 |
+
"eval_steps_per_second": 3.171,
|
42 |
+
"step": 8540
|
43 |
}
|
44 |
],
|
45 |
"max_steps": 64050,
|
46 |
"num_train_epochs": 15,
|
47 |
+
"total_flos": 6.75997956949033e+18,
|
48 |
"trial_name": null,
|
49 |
"trial_params": null
|
50 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377646433
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f010b8469779b656996538ec4b4b1ecb6f3bee582183c783ae70c057f71c415a
|
3 |
size 377646433
|