mprzibilla
commited on
Commit
•
69454e4
1
Parent(s):
c8536c4
Training in progress, epoch 6
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 sha256:4cdaca9dc87119c7c9ac664917db1efbd4c2580004a1879f35e4408bea1b17c8
|
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:c5c5b17e224fd932443a6c6e78f0d2e60687e890902d06292fd9ffdfc6111685
|
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:dcbe33b2fb93f871876844981b48c3d7a7aaa223055fcbd468280cac93f9f0b4
|
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:e90fe8e53c11b1937fd107aa05834bb3dfe92f7df51df1f4a37f2c9b759f1995
|
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:a558b41152d7e7d017b9298169612ec39c65755dd5a0d11fe955ddadebbf04c8
|
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,
|
@@ -91,11 +91,28 @@
|
|
91 |
"eval_samples_per_second": 24.72,
|
92 |
"eval_steps_per_second": 3.178,
|
93 |
"step": 21350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
94 |
}
|
95 |
],
|
96 |
"max_steps": 64050,
|
97 |
"num_train_epochs": 15,
|
98 |
-
"total_flos": 1.
|
99 |
"trial_name": null,
|
100 |
"trial_params": null
|
101 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.0,
|
5 |
+
"global_step": 25620,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
91 |
"eval_samples_per_second": 24.72,
|
92 |
"eval_steps_per_second": 3.178,
|
93 |
"step": 21350
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 6.0,
|
97 |
+
"learning_rate": 6.318202734683146e-05,
|
98 |
+
"loss": 0.2908,
|
99 |
+
"step": 25620
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 6.0,
|
103 |
+
"eval_cer": 0.10735930735930736,
|
104 |
+
"eval_loss": 0.6425668597221375,
|
105 |
+
"eval_new_wer": 0.10952380952380952,
|
106 |
+
"eval_old_wer": 0.18571428571428572,
|
107 |
+
"eval_runtime": 8.4544,
|
108 |
+
"eval_samples_per_second": 24.839,
|
109 |
+
"eval_steps_per_second": 3.194,
|
110 |
+
"step": 25620
|
111 |
}
|
112 |
],
|
113 |
"max_steps": 64050,
|
114 |
"num_train_epochs": 15,
|
115 |
+
"total_flos": 1.9416182711896904e+19,
|
116 |
"trial_name": null,
|
117 |
"trial_params": null
|
118 |
}
|
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:c5c5b17e224fd932443a6c6e78f0d2e60687e890902d06292fd9ffdfc6111685
|
3 |
size 377646433
|