mprzibilla
commited on
Commit
•
0c2a045
1
Parent(s):
29eed23
Training in progress, epoch 7
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 sha256:73dcd1e92e52e571adb9dfe38df8191e6d24822af1eb3dafadc77fee56a714eb
|
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 sha256:0e9229ef4974bf1cda2f1c6bdcfd0cfa01a73acfb1a389a14055a67fbc63a5d1
|
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 sha256:9060272459e2f575dc8171594e081ff560c302ef007fe02dfcb7838df3c3b68d
|
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 sha256:6cd01665f7ac70e472ca1525a6b28f0bfe212ce4ae21805b256de84b99adf2e4
|
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:b92d41ef5032da943b4de6703d7e08d9fa46b8ee9708929cdd0c837aac3ec7fa
|
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,
|
@@ -108,11 +108,28 @@
|
|
108 |
"eval_samples_per_second": 25.381,
|
109 |
"eval_steps_per_second": 3.263,
|
110 |
"step": 25620
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
111 |
}
|
112 |
],
|
113 |
"max_steps": 64050,
|
114 |
"num_train_epochs": 15,
|
115 |
-
"total_flos": 2.
|
116 |
"trial_name": null,
|
117 |
"trial_params": null
|
118 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.0,
|
5 |
+
"global_step": 29890,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
108 |
"eval_samples_per_second": 25.381,
|
109 |
"eval_steps_per_second": 3.263,
|
110 |
"step": 25620
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 7.0,
|
114 |
+
"learning_rate": 5.616782803050224e-05,
|
115 |
+
"loss": 2.8792,
|
116 |
+
"step": 29890
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 7.0,
|
120 |
+
"eval_cer": 0.9688311688311688,
|
121 |
+
"eval_loss": 3.118381977081299,
|
122 |
+
"eval_new_wer": 0.9476190476190476,
|
123 |
+
"eval_old_wer": 1.0,
|
124 |
+
"eval_runtime": 8.1799,
|
125 |
+
"eval_samples_per_second": 25.673,
|
126 |
+
"eval_steps_per_second": 3.301,
|
127 |
+
"step": 29890
|
128 |
}
|
129 |
],
|
130 |
"max_steps": 64050,
|
131 |
"num_train_epochs": 15,
|
132 |
+
"total_flos": 2.369404997449814e+19,
|
133 |
"trial_name": null,
|
134 |
"trial_params": null
|
135 |
}
|
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 sha256:0e9229ef4974bf1cda2f1c6bdcfd0cfa01a73acfb1a389a14055a67fbc63a5d1
|
3 |
size 377646433
|