parambharat
commited on
Commit
·
375f3d6
1
Parent(s):
c081761
Training in progress, step 75
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 +24 -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 199988997
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb5dc933e20332dca1b783534840865d9be3553dbe1e6e43bc0fc07855bd9b85
|
3 |
size 199988997
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 151098921
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a54dc396fadf4c9ef3ae86dac6aaaac0f8a9ecc0d5aba232e8e4d42b45e9b3b
|
3 |
size 151098921
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:061c39cb8624ef96b62598f8440706c207a18357c53acb248bffe9b8b8ce898f
|
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 sha256:5a3138fb3f1edc93feed6daf42736ce072b854299ed7b0ad047c5e667a8ab71f
|
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:d051938d0a389ddc04bc4e71c72d5b650579d4c313a37f90ae1c317ed9f91991
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 31.73913043478261,
|
3 |
"best_model_checkpoint": "../models/whisper-tiny-ta-example/checkpoint-25",
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -54,11 +54,32 @@
|
|
54 |
"eval_steps_per_second": 0.282,
|
55 |
"eval_wer": 35.21739130434783,
|
56 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
}
|
58 |
],
|
59 |
"max_steps": 100,
|
60 |
"num_train_epochs": 9223372036854775807,
|
61 |
-
"total_flos":
|
62 |
"trial_name": null,
|
63 |
"trial_params": null
|
64 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 31.73913043478261,
|
3 |
"best_model_checkpoint": "../models/whisper-tiny-ta-example/checkpoint-25",
|
4 |
+
"epoch": 37.01,
|
5 |
+
"global_step": 75,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
54 |
"eval_steps_per_second": 0.282,
|
55 |
"eval_wer": 35.21739130434783,
|
56 |
"step": 50
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 29.02,
|
60 |
+
"learning_rate": 5.466666666666667e-06,
|
61 |
+
"loss": 0.156,
|
62 |
+
"step": 60
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 34.02,
|
66 |
+
"learning_rate": 4.133333333333333e-06,
|
67 |
+
"loss": 0.1346,
|
68 |
+
"step": 70
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 37.01,
|
72 |
+
"eval_loss": 0.39989081025123596,
|
73 |
+
"eval_runtime": 3.4634,
|
74 |
+
"eval_samples_per_second": 2.887,
|
75 |
+
"eval_steps_per_second": 0.289,
|
76 |
+
"eval_wer": 37.826086956521735,
|
77 |
+
"step": 75
|
78 |
}
|
79 |
],
|
80 |
"max_steps": 100,
|
81 |
"num_train_epochs": 9223372036854775807,
|
82 |
+
"total_flos": 9.266548359168e+16,
|
83 |
"trial_name": null,
|
84 |
"trial_params": null
|
85 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 151098921
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a54dc396fadf4c9ef3ae86dac6aaaac0f8a9ecc0d5aba232e8e4d42b45e9b3b
|
3 |
size 151098921
|