mprzibilla
commited on
Commit
•
a079b6e
1
Parent(s):
f52bb91
Training in progress, epoch 15
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:f17acd07ffd919b9cece25b1732fa75b44442adac9a88d6b237d2c88d829d30d
|
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 sha256:7275a4b54cba8971d619171b24d3ae296d3b292163b3c8ab7d0be09ae407620b
|
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 sha256:1b91881b8366c0ee34d64ad79fd1ec87310340e876a2c1eaa6476187027e8909
|
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 sha256:899df8085391ac03ccf0f4af4567c1677dd1acf802bc6100800b044eee6b5fd1
|
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 sha256:1b9e5c4b19bf8f91ee0b8c0673c6bc9d7c91750047d52a3c63c167c3159e4c39
|
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,
|
@@ -244,11 +244,28 @@
|
|
244 |
"eval_samples_per_second": 23.55,
|
245 |
"eval_steps_per_second": 3.028,
|
246 |
"step": 4508
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
247 |
}
|
248 |
],
|
249 |
"max_steps": 4830,
|
250 |
"num_train_epochs": 15,
|
251 |
-
"total_flos": 3.
|
252 |
"trial_name": null,
|
253 |
"trial_params": null
|
254 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 15.0,
|
5 |
+
"global_step": 4830,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
244 |
"eval_samples_per_second": 23.55,
|
245 |
"eval_steps_per_second": 3.028,
|
246 |
"step": 4508
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 15.0,
|
250 |
+
"learning_rate": 1.0895619960775767e-07,
|
251 |
+
"loss": 0.025,
|
252 |
+
"step": 4830
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 15.0,
|
256 |
+
"eval_cer": 0.23896103896103896,
|
257 |
+
"eval_loss": 0.5525843501091003,
|
258 |
+
"eval_new_wer": 0.05714285714285714,
|
259 |
+
"eval_old_wer": 0.9809523809523809,
|
260 |
+
"eval_runtime": 8.9193,
|
261 |
+
"eval_samples_per_second": 23.544,
|
262 |
+
"eval_steps_per_second": 3.027,
|
263 |
+
"step": 4830
|
264 |
}
|
265 |
],
|
266 |
"max_steps": 4830,
|
267 |
"num_train_epochs": 15,
|
268 |
+
"total_flos": 3.6064810121869056e+18,
|
269 |
"trial_name": null,
|
270 |
"trial_params": null
|
271 |
}
|
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 sha256:7275a4b54cba8971d619171b24d3ae296d3b292163b3c8ab7d0be09ae407620b
|
3 |
size 377646433
|