mprzibilla
commited on
Commit
•
622eb29
1
Parent(s):
d2f1604
Training in progress, epoch 3
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 +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 721661957
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6b2aa8d5ecf76432f05f192ff200fb716fa8c78842680632b5770377aeb114a
|
3 |
size 721661957
|
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 sha256:459065713e825f184f3249a51b1cb1fdcf8c4e55d65360afde852d992639e851
|
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 14639
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:776a1ffc7ef953e1d194b3c21ab858fead4f972f57a0b06bf2e4701dffb4d441
|
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:cbeff4b41d7db09fb8142adc42392e017e3a3c51c8c7e46d04b5fa617f53bfb3
|
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 sha256:29a1ea701475afc9177572549048e0d86de191233089e775d17466cee30267ad
|
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,
|
@@ -40,11 +40,28 @@
|
|
40 |
"eval_samples_per_second": 24.979,
|
41 |
"eval_steps_per_second": 3.212,
|
42 |
"step": 8540
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
}
|
44 |
],
|
45 |
"max_steps": 64050,
|
46 |
"num_train_epochs": 15,
|
47 |
-
"total_flos":
|
48 |
"trial_name": null,
|
49 |
"trial_params": null
|
50 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 12810,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
40 |
"eval_samples_per_second": 24.979,
|
41 |
"eval_steps_per_second": 3.212,
|
42 |
"step": 8540
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"learning_rate": 8.422626873520904e-05,
|
47 |
+
"loss": 0.6119,
|
48 |
+
"step": 12810
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"eval_cer": 0.15064935064935064,
|
53 |
+
"eval_loss": 0.8806686997413635,
|
54 |
+
"eval_new_wer": 0.12380952380952381,
|
55 |
+
"eval_old_wer": 0.2904761904761905,
|
56 |
+
"eval_runtime": 8.4758,
|
57 |
+
"eval_samples_per_second": 24.776,
|
58 |
+
"eval_steps_per_second": 3.186,
|
59 |
+
"step": 12810
|
60 |
}
|
61 |
],
|
62 |
"max_steps": 64050,
|
63 |
"num_train_epochs": 15,
|
64 |
+
"total_flos": 9.70374678984573e+18,
|
65 |
"trial_name": null,
|
66 |
"trial_params": null
|
67 |
}
|
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 sha256:459065713e825f184f3249a51b1cb1fdcf8c4e55d65360afde852d992639e851
|
3 |
size 377646433
|