mprzibilla
commited on
Commit
•
933f1b3
1
Parent(s):
f4d8b96
Training in progress, epoch 9
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 721661957
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:745e302d3c28d1ecfd6bf63b5b26765fafd24857219333d8c8adec58a11a8473
|
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:c3970293ec14528092d6ca1debf3fc3ad39d7d84a2d74df9c18c36eb3b48a7c9
|
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:cff87da20c71f603e8023886f748a7a90ad51a74dd3e257041031deac40726e3
|
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:e9e056a14039066710c55d865723e703d98f3fcc915514a0580416816023f68e
|
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 sha256:7babf57865d31d5177ad3e6889bb5a4c41062ad6b69e376c5e9c2e44eb18880d
|
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,
|
@@ -142,11 +142,28 @@
|
|
142 |
"eval_samples_per_second": 24.653,
|
143 |
"eval_steps_per_second": 3.17,
|
144 |
"step": 34160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
145 |
}
|
146 |
],
|
147 |
"max_steps": 64050,
|
148 |
"num_train_epochs": 15,
|
149 |
-
"total_flos": 2.
|
150 |
"trial_name": null,
|
151 |
"trial_params": null
|
152 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.0,
|
5 |
+
"global_step": 38430,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
142 |
"eval_samples_per_second": 24.653,
|
143 |
"eval_steps_per_second": 3.17,
|
144 |
"step": 34160
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 9.0,
|
148 |
+
"learning_rate": 4.213778595845386e-05,
|
149 |
+
"loss": 0.1601,
|
150 |
+
"step": 38430
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 9.0,
|
154 |
+
"eval_cer": 0.14805194805194805,
|
155 |
+
"eval_loss": 1.2215726375579834,
|
156 |
+
"eval_new_wer": 0.18095238095238095,
|
157 |
+
"eval_old_wer": 0.24285714285714285,
|
158 |
+
"eval_runtime": 8.367,
|
159 |
+
"eval_samples_per_second": 25.098,
|
160 |
+
"eval_steps_per_second": 3.227,
|
161 |
+
"step": 38430
|
162 |
}
|
163 |
],
|
164 |
"max_steps": 64050,
|
165 |
"num_train_epochs": 15,
|
166 |
+
"total_flos": 2.911541312483291e+19,
|
167 |
"trial_name": null,
|
168 |
"trial_params": null
|
169 |
}
|
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:c3970293ec14528092d6ca1debf3fc3ad39d7d84a2d74df9c18c36eb3b48a7c9
|
3 |
size 377646433
|