Commit
•
d2f1604
1
Parent(s):
952478b
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 +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:a7c9ecfd8cb0e06bed2cac1481c181a5f5806b9fbb515be84dd43196c51028d7
|
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 sha256:277228f7704eb9c2030d52a5e32186caa0e78367a08ec5637af6d3bdaf2272a8
|
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 sha256:28ae1a2ba23ced9a3c01553e9871d4c80b2fa566d38f5b037e8bad7cad979aa1
|
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 sha256:6aa6b07303f228edfba2736d5f036cc1b3f8047a6cbf3bc89bdceff6f9b1a850
|
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 sha256:47e741874f800d6c85d0ad4fac0bcbd8bbe385fe10b357506f204fa594702563
|
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": 24.448,
|
24 |
"eval_steps_per_second": 3.143,
|
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": 24.448,
|
24 |
"eval_steps_per_second": 3.143,
|
25 |
"step": 4270
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"learning_rate": 9.124046805153827e-05,
|
30 |
+
"loss": 0.9517,
|
31 |
+
"step": 8540
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 2.0,
|
35 |
+
"eval_cer": 0.14545454545454545,
|
36 |
+
"eval_loss": 0.8618147373199463,
|
37 |
+
"eval_new_wer": 0.12857142857142856,
|
38 |
+
"eval_old_wer": 0.30952380952380953,
|
39 |
+
"eval_runtime": 8.4071,
|
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": 6.465255166176154e+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 sha256:277228f7704eb9c2030d52a5e32186caa0e78367a08ec5637af6d3bdaf2272a8
|
3 |
size 377646433
|