End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Nov25_05-17-07_4b2aca464fe8/events.out.tfevents.1669358096.4b2aca464fe8.8241.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +1585 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 99.98,
|
| 3 |
+
"eval_loss": 0.43458130955696106,
|
| 4 |
+
"eval_runtime": 2.5109,
|
| 5 |
+
"eval_samples": 17,
|
| 6 |
+
"eval_samples_per_second": 6.77,
|
| 7 |
+
"eval_steps_per_second": 1.991,
|
| 8 |
+
"eval_wer": 0.22418879056047197,
|
| 9 |
+
"train_loss": 0.679512545520609,
|
| 10 |
+
"train_runtime": 4168.4023,
|
| 11 |
+
"train_samples": 179,
|
| 12 |
+
"train_samples_per_second": 4.294,
|
| 13 |
+
"train_steps_per_second": 0.264
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 99.98,
|
| 3 |
+
"eval_loss": 0.43458130955696106,
|
| 4 |
+
"eval_runtime": 2.5109,
|
| 5 |
+
"eval_samples": 17,
|
| 6 |
+
"eval_samples_per_second": 6.77,
|
| 7 |
+
"eval_steps_per_second": 1.991,
|
| 8 |
+
"eval_wer": 0.22418879056047197
|
| 9 |
+
}
|
runs/Nov25_05-17-07_4b2aca464fe8/events.out.tfevents.1669358096.4b2aca464fe8.8241.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0887fb72bdefde469e9aa076e78449996419d957a4ebcf0d0fddf4f97bade762
|
| 3 |
+
size 358
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 99.98,
|
| 3 |
+
"train_loss": 0.679512545520609,
|
| 4 |
+
"train_runtime": 4168.4023,
|
| 5 |
+
"train_samples": 179,
|
| 6 |
+
"train_samples_per_second": 4.294,
|
| 7 |
+
"train_steps_per_second": 0.264
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1585 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.43458130955696106,
|
| 3 |
+
"best_model_checkpoint": "ai-light-dance_drums_ft_pretrain_wav2vec2-base-new_onset-idmt-mdb-2/checkpoint-638",
|
| 4 |
+
"epoch": 99.97777777777777,
|
| 5 |
+
"global_step": 1100,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.89,
|
| 12 |
+
"learning_rate": 3.9999999999999996e-05,
|
| 13 |
+
"loss": 22.7802,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.98,
|
| 18 |
+
"eval_loss": 60.154850006103516,
|
| 19 |
+
"eval_runtime": 2.4092,
|
| 20 |
+
"eval_samples_per_second": 7.056,
|
| 21 |
+
"eval_steps_per_second": 2.075,
|
| 22 |
+
"eval_wer": 0.9882005899705014,
|
| 23 |
+
"step": 11
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.8,
|
| 27 |
+
"learning_rate": 0.00014,
|
| 28 |
+
"loss": 13.7635,
|
| 29 |
+
"step": 20
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.98,
|
| 33 |
+
"eval_loss": 18.182188034057617,
|
| 34 |
+
"eval_runtime": 2.5023,
|
| 35 |
+
"eval_samples_per_second": 6.794,
|
| 36 |
+
"eval_steps_per_second": 1.998,
|
| 37 |
+
"eval_wer": 0.9985250737463127,
|
| 38 |
+
"step": 22
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.71,
|
| 42 |
+
"learning_rate": 0.00023999999999999998,
|
| 43 |
+
"loss": 3.4364,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.98,
|
| 48 |
+
"eval_loss": 1.2338517904281616,
|
| 49 |
+
"eval_runtime": 2.5133,
|
| 50 |
+
"eval_samples_per_second": 6.764,
|
| 51 |
+
"eval_steps_per_second": 1.989,
|
| 52 |
+
"eval_wer": 0.7315634218289085,
|
| 53 |
+
"step": 33
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.62,
|
| 57 |
+
"learning_rate": 0.00029887850467289715,
|
| 58 |
+
"loss": 1.0479,
|
| 59 |
+
"step": 40
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 3.98,
|
| 63 |
+
"eval_loss": 0.8432507514953613,
|
| 64 |
+
"eval_runtime": 2.5729,
|
| 65 |
+
"eval_samples_per_second": 6.607,
|
| 66 |
+
"eval_steps_per_second": 1.943,
|
| 67 |
+
"eval_wer": 0.4085545722713864,
|
| 68 |
+
"step": 44
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.53,
|
| 72 |
+
"learning_rate": 0.00029607476635514017,
|
| 73 |
+
"loss": 0.739,
|
| 74 |
+
"step": 50
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 4.98,
|
| 78 |
+
"eval_loss": 0.7656970620155334,
|
| 79 |
+
"eval_runtime": 2.5779,
|
| 80 |
+
"eval_samples_per_second": 6.595,
|
| 81 |
+
"eval_steps_per_second": 1.94,
|
| 82 |
+
"eval_wer": 0.30973451327433627,
|
| 83 |
+
"step": 55
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 5.44,
|
| 87 |
+
"learning_rate": 0.00029327102803738313,
|
| 88 |
+
"loss": 0.6492,
|
| 89 |
+
"step": 60
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.98,
|
| 93 |
+
"eval_loss": 0.8034406900405884,
|
| 94 |
+
"eval_runtime": 2.5383,
|
| 95 |
+
"eval_samples_per_second": 6.697,
|
| 96 |
+
"eval_steps_per_second": 1.97,
|
| 97 |
+
"eval_wer": 0.2994100294985251,
|
| 98 |
+
"step": 66
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.36,
|
| 102 |
+
"learning_rate": 0.00029046728971962615,
|
| 103 |
+
"loss": 0.6044,
|
| 104 |
+
"step": 70
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.98,
|
| 108 |
+
"eval_loss": 0.6401463150978088,
|
| 109 |
+
"eval_runtime": 2.5648,
|
| 110 |
+
"eval_samples_per_second": 6.628,
|
| 111 |
+
"eval_steps_per_second": 1.949,
|
| 112 |
+
"eval_wer": 0.3333333333333333,
|
| 113 |
+
"step": 77
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 7.27,
|
| 117 |
+
"learning_rate": 0.0002876635514018691,
|
| 118 |
+
"loss": 0.5662,
|
| 119 |
+
"step": 80
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 7.98,
|
| 123 |
+
"eval_loss": 0.7298213243484497,
|
| 124 |
+
"eval_runtime": 2.5349,
|
| 125 |
+
"eval_samples_per_second": 6.706,
|
| 126 |
+
"eval_steps_per_second": 1.972,
|
| 127 |
+
"eval_wer": 0.2610619469026549,
|
| 128 |
+
"step": 88
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.18,
|
| 132 |
+
"learning_rate": 0.00028485981308411213,
|
| 133 |
+
"loss": 0.5321,
|
| 134 |
+
"step": 90
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 8.98,
|
| 138 |
+
"eval_loss": 0.8125590085983276,
|
| 139 |
+
"eval_runtime": 2.5294,
|
| 140 |
+
"eval_samples_per_second": 6.721,
|
| 141 |
+
"eval_steps_per_second": 1.977,
|
| 142 |
+
"eval_wer": 0.29793510324483774,
|
| 143 |
+
"step": 99
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 9.09,
|
| 147 |
+
"learning_rate": 0.0002820560747663551,
|
| 148 |
+
"loss": 0.5423,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 9.98,
|
| 153 |
+
"learning_rate": 0.0002792523364485981,
|
| 154 |
+
"loss": 0.5037,
|
| 155 |
+
"step": 110
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 9.98,
|
| 159 |
+
"eval_loss": 0.7135093212127686,
|
| 160 |
+
"eval_runtime": 2.5473,
|
| 161 |
+
"eval_samples_per_second": 6.674,
|
| 162 |
+
"eval_steps_per_second": 1.963,
|
| 163 |
+
"eval_wer": 0.2994100294985251,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 10.89,
|
| 168 |
+
"learning_rate": 0.0002764485981308411,
|
| 169 |
+
"loss": 0.4823,
|
| 170 |
+
"step": 120
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 10.98,
|
| 174 |
+
"eval_loss": 0.5975809097290039,
|
| 175 |
+
"eval_runtime": 2.4821,
|
| 176 |
+
"eval_samples_per_second": 6.849,
|
| 177 |
+
"eval_steps_per_second": 2.014,
|
| 178 |
+
"eval_wer": 0.26548672566371684,
|
| 179 |
+
"step": 121
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 11.8,
|
| 183 |
+
"learning_rate": 0.0002736448598130841,
|
| 184 |
+
"loss": 0.4622,
|
| 185 |
+
"step": 130
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 11.98,
|
| 189 |
+
"eval_loss": 0.6875410079956055,
|
| 190 |
+
"eval_runtime": 2.4654,
|
| 191 |
+
"eval_samples_per_second": 6.895,
|
| 192 |
+
"eval_steps_per_second": 2.028,
|
| 193 |
+
"eval_wer": 0.2448377581120944,
|
| 194 |
+
"step": 132
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 12.71,
|
| 198 |
+
"learning_rate": 0.00027084112149532705,
|
| 199 |
+
"loss": 0.4761,
|
| 200 |
+
"step": 140
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 12.98,
|
| 204 |
+
"eval_loss": 0.6402226090431213,
|
| 205 |
+
"eval_runtime": 2.4808,
|
| 206 |
+
"eval_samples_per_second": 6.853,
|
| 207 |
+
"eval_steps_per_second": 2.015,
|
| 208 |
+
"eval_wer": 0.24631268436578171,
|
| 209 |
+
"step": 143
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 13.62,
|
| 213 |
+
"learning_rate": 0.00026803738317757007,
|
| 214 |
+
"loss": 0.4296,
|
| 215 |
+
"step": 150
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 13.98,
|
| 219 |
+
"eval_loss": 0.82173752784729,
|
| 220 |
+
"eval_runtime": 2.4283,
|
| 221 |
+
"eval_samples_per_second": 7.001,
|
| 222 |
+
"eval_steps_per_second": 2.059,
|
| 223 |
+
"eval_wer": 0.2448377581120944,
|
| 224 |
+
"step": 154
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 14.53,
|
| 228 |
+
"learning_rate": 0.0002652336448598131,
|
| 229 |
+
"loss": 0.4655,
|
| 230 |
+
"step": 160
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 14.98,
|
| 234 |
+
"eval_loss": 0.7825008630752563,
|
| 235 |
+
"eval_runtime": 2.4304,
|
| 236 |
+
"eval_samples_per_second": 6.995,
|
| 237 |
+
"eval_steps_per_second": 2.057,
|
| 238 |
+
"eval_wer": 0.2551622418879056,
|
| 239 |
+
"step": 165
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 15.44,
|
| 243 |
+
"learning_rate": 0.00026242990654205605,
|
| 244 |
+
"loss": 0.4122,
|
| 245 |
+
"step": 170
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 15.98,
|
| 249 |
+
"eval_loss": 0.712116539478302,
|
| 250 |
+
"eval_runtime": 2.4336,
|
| 251 |
+
"eval_samples_per_second": 6.986,
|
| 252 |
+
"eval_steps_per_second": 2.055,
|
| 253 |
+
"eval_wer": 0.2448377581120944,
|
| 254 |
+
"step": 176
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 16.36,
|
| 258 |
+
"learning_rate": 0.00025962616822429907,
|
| 259 |
+
"loss": 0.4234,
|
| 260 |
+
"step": 180
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 16.98,
|
| 264 |
+
"eval_loss": 0.8301025032997131,
|
| 265 |
+
"eval_runtime": 2.4483,
|
| 266 |
+
"eval_samples_per_second": 6.944,
|
| 267 |
+
"eval_steps_per_second": 2.042,
|
| 268 |
+
"eval_wer": 0.2669616519174041,
|
| 269 |
+
"step": 187
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 17.27,
|
| 273 |
+
"learning_rate": 0.00025682242990654204,
|
| 274 |
+
"loss": 0.441,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 17.98,
|
| 279 |
+
"eval_loss": 0.7342628240585327,
|
| 280 |
+
"eval_runtime": 2.4341,
|
| 281 |
+
"eval_samples_per_second": 6.984,
|
| 282 |
+
"eval_steps_per_second": 2.054,
|
| 283 |
+
"eval_wer": 0.2640117994100295,
|
| 284 |
+
"step": 198
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 18.18,
|
| 288 |
+
"learning_rate": 0.00025401869158878505,
|
| 289 |
+
"loss": 0.4781,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 18.98,
|
| 294 |
+
"eval_loss": 0.7387515902519226,
|
| 295 |
+
"eval_runtime": 2.4267,
|
| 296 |
+
"eval_samples_per_second": 7.005,
|
| 297 |
+
"eval_steps_per_second": 2.06,
|
| 298 |
+
"eval_wer": 0.21386430678466076,
|
| 299 |
+
"step": 209
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 19.09,
|
| 303 |
+
"learning_rate": 0.000251214953271028,
|
| 304 |
+
"loss": 0.3873,
|
| 305 |
+
"step": 210
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 19.98,
|
| 309 |
+
"learning_rate": 0.00024841121495327103,
|
| 310 |
+
"loss": 0.4006,
|
| 311 |
+
"step": 220
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 19.98,
|
| 315 |
+
"eval_loss": 0.6700401306152344,
|
| 316 |
+
"eval_runtime": 2.427,
|
| 317 |
+
"eval_samples_per_second": 7.005,
|
| 318 |
+
"eval_steps_per_second": 2.06,
|
| 319 |
+
"eval_wer": 0.252212389380531,
|
| 320 |
+
"step": 220
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 20.89,
|
| 324 |
+
"learning_rate": 0.000245607476635514,
|
| 325 |
+
"loss": 0.42,
|
| 326 |
+
"step": 230
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 20.98,
|
| 330 |
+
"eval_loss": 0.5540403127670288,
|
| 331 |
+
"eval_runtime": 2.4476,
|
| 332 |
+
"eval_samples_per_second": 6.946,
|
| 333 |
+
"eval_steps_per_second": 2.043,
|
| 334 |
+
"eval_wer": 0.24926253687315633,
|
| 335 |
+
"step": 231
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 21.8,
|
| 339 |
+
"learning_rate": 0.000242803738317757,
|
| 340 |
+
"loss": 0.4289,
|
| 341 |
+
"step": 240
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 21.98,
|
| 345 |
+
"eval_loss": 0.9949514865875244,
|
| 346 |
+
"eval_runtime": 2.4445,
|
| 347 |
+
"eval_samples_per_second": 6.954,
|
| 348 |
+
"eval_steps_per_second": 2.045,
|
| 349 |
+
"eval_wer": 0.24926253687315633,
|
| 350 |
+
"step": 242
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 22.71,
|
| 354 |
+
"learning_rate": 0.00023999999999999998,
|
| 355 |
+
"loss": 0.4014,
|
| 356 |
+
"step": 250
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 22.98,
|
| 360 |
+
"eval_loss": 0.7282938957214355,
|
| 361 |
+
"eval_runtime": 2.4265,
|
| 362 |
+
"eval_samples_per_second": 7.006,
|
| 363 |
+
"eval_steps_per_second": 2.061,
|
| 364 |
+
"eval_wer": 0.252212389380531,
|
| 365 |
+
"step": 253
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 23.62,
|
| 369 |
+
"learning_rate": 0.00023719626168224297,
|
| 370 |
+
"loss": 0.3397,
|
| 371 |
+
"step": 260
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 23.98,
|
| 375 |
+
"eval_loss": 0.8326579928398132,
|
| 376 |
+
"eval_runtime": 2.4497,
|
| 377 |
+
"eval_samples_per_second": 6.94,
|
| 378 |
+
"eval_steps_per_second": 2.041,
|
| 379 |
+
"eval_wer": 0.26548672566371684,
|
| 380 |
+
"step": 264
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 24.53,
|
| 384 |
+
"learning_rate": 0.00023439252336448596,
|
| 385 |
+
"loss": 0.3879,
|
| 386 |
+
"step": 270
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 24.98,
|
| 390 |
+
"eval_loss": 0.9388102889060974,
|
| 391 |
+
"eval_runtime": 2.5119,
|
| 392 |
+
"eval_samples_per_second": 6.768,
|
| 393 |
+
"eval_steps_per_second": 1.991,
|
| 394 |
+
"eval_wer": 0.29056047197640117,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 25.44,
|
| 399 |
+
"learning_rate": 0.00023158878504672895,
|
| 400 |
+
"loss": 0.3445,
|
| 401 |
+
"step": 280
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 25.98,
|
| 405 |
+
"eval_loss": 0.7623295783996582,
|
| 406 |
+
"eval_runtime": 2.4514,
|
| 407 |
+
"eval_samples_per_second": 6.935,
|
| 408 |
+
"eval_steps_per_second": 2.04,
|
| 409 |
+
"eval_wer": 0.252212389380531,
|
| 410 |
+
"step": 286
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 26.36,
|
| 414 |
+
"learning_rate": 0.00022878504672897194,
|
| 415 |
+
"loss": 0.3933,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 26.98,
|
| 420 |
+
"eval_loss": 0.9125231504440308,
|
| 421 |
+
"eval_runtime": 2.4489,
|
| 422 |
+
"eval_samples_per_second": 6.942,
|
| 423 |
+
"eval_steps_per_second": 2.042,
|
| 424 |
+
"eval_wer": 0.24188790560471976,
|
| 425 |
+
"step": 297
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 27.27,
|
| 429 |
+
"learning_rate": 0.00022598130841121493,
|
| 430 |
+
"loss": 0.3173,
|
| 431 |
+
"step": 300
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 27.98,
|
| 435 |
+
"eval_loss": 0.7446789741516113,
|
| 436 |
+
"eval_runtime": 2.4479,
|
| 437 |
+
"eval_samples_per_second": 6.945,
|
| 438 |
+
"eval_steps_per_second": 2.043,
|
| 439 |
+
"eval_wer": 0.2448377581120944,
|
| 440 |
+
"step": 308
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 28.18,
|
| 444 |
+
"learning_rate": 0.00022317757009345792,
|
| 445 |
+
"loss": 0.3734,
|
| 446 |
+
"step": 310
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 28.98,
|
| 450 |
+
"eval_loss": 0.6601439118385315,
|
| 451 |
+
"eval_runtime": 2.4288,
|
| 452 |
+
"eval_samples_per_second": 6.999,
|
| 453 |
+
"eval_steps_per_second": 2.059,
|
| 454 |
+
"eval_wer": 0.2935103244837758,
|
| 455 |
+
"step": 319
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 29.09,
|
| 459 |
+
"learning_rate": 0.0002203738317757009,
|
| 460 |
+
"loss": 0.3681,
|
| 461 |
+
"step": 320
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 29.98,
|
| 465 |
+
"learning_rate": 0.0002175700934579439,
|
| 466 |
+
"loss": 0.3347,
|
| 467 |
+
"step": 330
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 29.98,
|
| 471 |
+
"eval_loss": 0.7021532654762268,
|
| 472 |
+
"eval_runtime": 2.4714,
|
| 473 |
+
"eval_samples_per_second": 6.879,
|
| 474 |
+
"eval_steps_per_second": 2.023,
|
| 475 |
+
"eval_wer": 0.26991150442477874,
|
| 476 |
+
"step": 330
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 30.89,
|
| 480 |
+
"learning_rate": 0.0002147663551401869,
|
| 481 |
+
"loss": 0.3564,
|
| 482 |
+
"step": 340
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 30.98,
|
| 486 |
+
"eval_loss": 0.748757004737854,
|
| 487 |
+
"eval_runtime": 2.5209,
|
| 488 |
+
"eval_samples_per_second": 6.744,
|
| 489 |
+
"eval_steps_per_second": 1.983,
|
| 490 |
+
"eval_wer": 0.2920353982300885,
|
| 491 |
+
"step": 341
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 31.8,
|
| 495 |
+
"learning_rate": 0.00021196261682242989,
|
| 496 |
+
"loss": 0.3371,
|
| 497 |
+
"step": 350
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 31.98,
|
| 501 |
+
"eval_loss": 0.6413426995277405,
|
| 502 |
+
"eval_runtime": 2.4848,
|
| 503 |
+
"eval_samples_per_second": 6.842,
|
| 504 |
+
"eval_steps_per_second": 2.012,
|
| 505 |
+
"eval_wer": 0.2581120943952802,
|
| 506 |
+
"step": 352
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 32.71,
|
| 510 |
+
"learning_rate": 0.00020915887850467288,
|
| 511 |
+
"loss": 0.355,
|
| 512 |
+
"step": 360
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 32.98,
|
| 516 |
+
"eval_loss": 0.5131234526634216,
|
| 517 |
+
"eval_runtime": 2.4307,
|
| 518 |
+
"eval_samples_per_second": 6.994,
|
| 519 |
+
"eval_steps_per_second": 2.057,
|
| 520 |
+
"eval_wer": 0.2374631268436578,
|
| 521 |
+
"step": 363
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 33.62,
|
| 525 |
+
"learning_rate": 0.00020635514018691587,
|
| 526 |
+
"loss": 0.3648,
|
| 527 |
+
"step": 370
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 33.98,
|
| 531 |
+
"eval_loss": 0.5807757377624512,
|
| 532 |
+
"eval_runtime": 2.4713,
|
| 533 |
+
"eval_samples_per_second": 6.879,
|
| 534 |
+
"eval_steps_per_second": 2.023,
|
| 535 |
+
"eval_wer": 0.22861356932153393,
|
| 536 |
+
"step": 374
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 34.53,
|
| 540 |
+
"learning_rate": 0.00020355140186915886,
|
| 541 |
+
"loss": 0.3209,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 34.98,
|
| 546 |
+
"eval_loss": 0.5391702651977539,
|
| 547 |
+
"eval_runtime": 2.4562,
|
| 548 |
+
"eval_samples_per_second": 6.921,
|
| 549 |
+
"eval_steps_per_second": 2.036,
|
| 550 |
+
"eval_wer": 0.22566371681415928,
|
| 551 |
+
"step": 385
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 35.44,
|
| 555 |
+
"learning_rate": 0.00020074766355140185,
|
| 556 |
+
"loss": 0.3522,
|
| 557 |
+
"step": 390
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 35.98,
|
| 561 |
+
"eval_loss": 0.4410792887210846,
|
| 562 |
+
"eval_runtime": 2.4622,
|
| 563 |
+
"eval_samples_per_second": 6.904,
|
| 564 |
+
"eval_steps_per_second": 2.031,
|
| 565 |
+
"eval_wer": 0.22271386430678466,
|
| 566 |
+
"step": 396
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 36.36,
|
| 570 |
+
"learning_rate": 0.00019794392523364484,
|
| 571 |
+
"loss": 0.3252,
|
| 572 |
+
"step": 400
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 36.98,
|
| 576 |
+
"eval_loss": 0.46930572390556335,
|
| 577 |
+
"eval_runtime": 2.419,
|
| 578 |
+
"eval_samples_per_second": 7.028,
|
| 579 |
+
"eval_steps_per_second": 2.067,
|
| 580 |
+
"eval_wer": 0.21091445427728614,
|
| 581 |
+
"step": 407
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 37.27,
|
| 585 |
+
"learning_rate": 0.00019514018691588783,
|
| 586 |
+
"loss": 0.3216,
|
| 587 |
+
"step": 410
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 37.98,
|
| 591 |
+
"eval_loss": 0.4621430039405823,
|
| 592 |
+
"eval_runtime": 2.4503,
|
| 593 |
+
"eval_samples_per_second": 6.938,
|
| 594 |
+
"eval_steps_per_second": 2.041,
|
| 595 |
+
"eval_wer": 0.20648967551622419,
|
| 596 |
+
"step": 418
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 38.18,
|
| 600 |
+
"learning_rate": 0.00019233644859813082,
|
| 601 |
+
"loss": 0.3119,
|
| 602 |
+
"step": 420
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 38.98,
|
| 606 |
+
"eval_loss": 0.5093832612037659,
|
| 607 |
+
"eval_runtime": 2.4699,
|
| 608 |
+
"eval_samples_per_second": 6.883,
|
| 609 |
+
"eval_steps_per_second": 2.024,
|
| 610 |
+
"eval_wer": 0.2168141592920354,
|
| 611 |
+
"step": 429
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 39.09,
|
| 615 |
+
"learning_rate": 0.0001895327102803738,
|
| 616 |
+
"loss": 0.3266,
|
| 617 |
+
"step": 430
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 39.98,
|
| 621 |
+
"learning_rate": 0.0001867289719626168,
|
| 622 |
+
"loss": 0.3247,
|
| 623 |
+
"step": 440
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 39.98,
|
| 627 |
+
"eval_loss": 0.4897085130214691,
|
| 628 |
+
"eval_runtime": 2.4522,
|
| 629 |
+
"eval_samples_per_second": 6.933,
|
| 630 |
+
"eval_steps_per_second": 2.039,
|
| 631 |
+
"eval_wer": 0.23156342182890854,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 40.89,
|
| 636 |
+
"learning_rate": 0.0001839252336448598,
|
| 637 |
+
"loss": 0.3246,
|
| 638 |
+
"step": 450
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 40.98,
|
| 642 |
+
"eval_loss": 0.6471104621887207,
|
| 643 |
+
"eval_runtime": 2.42,
|
| 644 |
+
"eval_samples_per_second": 7.025,
|
| 645 |
+
"eval_steps_per_second": 2.066,
|
| 646 |
+
"eval_wer": 0.22123893805309736,
|
| 647 |
+
"step": 451
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 41.8,
|
| 651 |
+
"learning_rate": 0.00018112149532710278,
|
| 652 |
+
"loss": 0.2997,
|
| 653 |
+
"step": 460
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 41.98,
|
| 657 |
+
"eval_loss": 0.5569115877151489,
|
| 658 |
+
"eval_runtime": 2.4575,
|
| 659 |
+
"eval_samples_per_second": 6.918,
|
| 660 |
+
"eval_steps_per_second": 2.035,
|
| 661 |
+
"eval_wer": 0.2153392330383481,
|
| 662 |
+
"step": 462
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 42.71,
|
| 666 |
+
"learning_rate": 0.00017831775700934577,
|
| 667 |
+
"loss": 0.2969,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 42.98,
|
| 672 |
+
"eval_loss": 0.47663480043411255,
|
| 673 |
+
"eval_runtime": 2.444,
|
| 674 |
+
"eval_samples_per_second": 6.956,
|
| 675 |
+
"eval_steps_per_second": 2.046,
|
| 676 |
+
"eval_wer": 0.20943952802359883,
|
| 677 |
+
"step": 473
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 43.62,
|
| 681 |
+
"learning_rate": 0.00017551401869158876,
|
| 682 |
+
"loss": 0.3202,
|
| 683 |
+
"step": 480
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 43.98,
|
| 687 |
+
"eval_loss": 0.4978266954421997,
|
| 688 |
+
"eval_runtime": 2.4301,
|
| 689 |
+
"eval_samples_per_second": 6.996,
|
| 690 |
+
"eval_steps_per_second": 2.058,
|
| 691 |
+
"eval_wer": 0.23156342182890854,
|
| 692 |
+
"step": 484
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 44.53,
|
| 696 |
+
"learning_rate": 0.00017271028037383175,
|
| 697 |
+
"loss": 0.3093,
|
| 698 |
+
"step": 490
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 44.98,
|
| 702 |
+
"eval_loss": 0.4776196777820587,
|
| 703 |
+
"eval_runtime": 2.4293,
|
| 704 |
+
"eval_samples_per_second": 6.998,
|
| 705 |
+
"eval_steps_per_second": 2.058,
|
| 706 |
+
"eval_wer": 0.2182890855457227,
|
| 707 |
+
"step": 495
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 45.44,
|
| 711 |
+
"learning_rate": 0.00016990654205607475,
|
| 712 |
+
"loss": 0.298,
|
| 713 |
+
"step": 500
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 45.98,
|
| 717 |
+
"eval_loss": 0.5007936954498291,
|
| 718 |
+
"eval_runtime": 2.452,
|
| 719 |
+
"eval_samples_per_second": 6.933,
|
| 720 |
+
"eval_steps_per_second": 2.039,
|
| 721 |
+
"eval_wer": 0.21976401179941002,
|
| 722 |
+
"step": 506
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 46.36,
|
| 726 |
+
"learning_rate": 0.00016710280373831774,
|
| 727 |
+
"loss": 0.3151,
|
| 728 |
+
"step": 510
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 46.98,
|
| 732 |
+
"eval_loss": 0.48113784193992615,
|
| 733 |
+
"eval_runtime": 2.4479,
|
| 734 |
+
"eval_samples_per_second": 6.945,
|
| 735 |
+
"eval_steps_per_second": 2.043,
|
| 736 |
+
"eval_wer": 0.2079646017699115,
|
| 737 |
+
"step": 517
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 47.27,
|
| 741 |
+
"learning_rate": 0.00016429906542056073,
|
| 742 |
+
"loss": 0.2824,
|
| 743 |
+
"step": 520
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 47.98,
|
| 747 |
+
"eval_loss": 0.5011029839515686,
|
| 748 |
+
"eval_runtime": 2.4404,
|
| 749 |
+
"eval_samples_per_second": 6.966,
|
| 750 |
+
"eval_steps_per_second": 2.049,
|
| 751 |
+
"eval_wer": 0.20648967551622419,
|
| 752 |
+
"step": 528
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 48.18,
|
| 756 |
+
"learning_rate": 0.00016149532710280372,
|
| 757 |
+
"loss": 0.3089,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 48.98,
|
| 762 |
+
"eval_loss": 0.5131256580352783,
|
| 763 |
+
"eval_runtime": 2.4575,
|
| 764 |
+
"eval_samples_per_second": 6.917,
|
| 765 |
+
"eval_steps_per_second": 2.035,
|
| 766 |
+
"eval_wer": 0.21386430678466076,
|
| 767 |
+
"step": 539
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 49.09,
|
| 771 |
+
"learning_rate": 0.0001586915887850467,
|
| 772 |
+
"loss": 0.2795,
|
| 773 |
+
"step": 540
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 49.98,
|
| 777 |
+
"learning_rate": 0.0001558878504672897,
|
| 778 |
+
"loss": 0.3064,
|
| 779 |
+
"step": 550
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 49.98,
|
| 783 |
+
"eval_loss": 0.47494271397590637,
|
| 784 |
+
"eval_runtime": 2.4456,
|
| 785 |
+
"eval_samples_per_second": 6.951,
|
| 786 |
+
"eval_steps_per_second": 2.045,
|
| 787 |
+
"eval_wer": 0.22271386430678466,
|
| 788 |
+
"step": 550
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 50.89,
|
| 792 |
+
"learning_rate": 0.0001530841121495327,
|
| 793 |
+
"loss": 0.2734,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 50.98,
|
| 798 |
+
"eval_loss": 0.5396826863288879,
|
| 799 |
+
"eval_runtime": 2.4349,
|
| 800 |
+
"eval_samples_per_second": 6.982,
|
| 801 |
+
"eval_steps_per_second": 2.053,
|
| 802 |
+
"eval_wer": 0.2079646017699115,
|
| 803 |
+
"step": 561
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 51.8,
|
| 807 |
+
"learning_rate": 0.00015028037383177568,
|
| 808 |
+
"loss": 0.2911,
|
| 809 |
+
"step": 570
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 51.98,
|
| 813 |
+
"eval_loss": 0.4975402355194092,
|
| 814 |
+
"eval_runtime": 2.4591,
|
| 815 |
+
"eval_samples_per_second": 6.913,
|
| 816 |
+
"eval_steps_per_second": 2.033,
|
| 817 |
+
"eval_wer": 0.20353982300884957,
|
| 818 |
+
"step": 572
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 52.71,
|
| 822 |
+
"learning_rate": 0.00014747663551401867,
|
| 823 |
+
"loss": 0.2889,
|
| 824 |
+
"step": 580
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 52.98,
|
| 828 |
+
"eval_loss": 0.46327924728393555,
|
| 829 |
+
"eval_runtime": 2.4538,
|
| 830 |
+
"eval_samples_per_second": 6.928,
|
| 831 |
+
"eval_steps_per_second": 2.038,
|
| 832 |
+
"eval_wer": 0.2168141592920354,
|
| 833 |
+
"step": 583
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 53.62,
|
| 837 |
+
"learning_rate": 0.00014467289719626166,
|
| 838 |
+
"loss": 0.2523,
|
| 839 |
+
"step": 590
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 53.98,
|
| 843 |
+
"eval_loss": 0.4589496850967407,
|
| 844 |
+
"eval_runtime": 2.4386,
|
| 845 |
+
"eval_samples_per_second": 6.971,
|
| 846 |
+
"eval_steps_per_second": 2.05,
|
| 847 |
+
"eval_wer": 0.22418879056047197,
|
| 848 |
+
"step": 594
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 54.53,
|
| 852 |
+
"learning_rate": 0.00014186915887850465,
|
| 853 |
+
"loss": 0.272,
|
| 854 |
+
"step": 600
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 54.98,
|
| 858 |
+
"eval_loss": 0.4855732023715973,
|
| 859 |
+
"eval_runtime": 2.4564,
|
| 860 |
+
"eval_samples_per_second": 6.921,
|
| 861 |
+
"eval_steps_per_second": 2.035,
|
| 862 |
+
"eval_wer": 0.21238938053097345,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 55.44,
|
| 867 |
+
"learning_rate": 0.00013906542056074764,
|
| 868 |
+
"loss": 0.2733,
|
| 869 |
+
"step": 610
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 55.98,
|
| 873 |
+
"eval_loss": 0.4474070966243744,
|
| 874 |
+
"eval_runtime": 2.4335,
|
| 875 |
+
"eval_samples_per_second": 6.986,
|
| 876 |
+
"eval_steps_per_second": 2.055,
|
| 877 |
+
"eval_wer": 0.22418879056047197,
|
| 878 |
+
"step": 616
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 56.36,
|
| 882 |
+
"learning_rate": 0.00013626168224299063,
|
| 883 |
+
"loss": 0.2856,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 56.98,
|
| 888 |
+
"eval_loss": 0.4533959627151489,
|
| 889 |
+
"eval_runtime": 2.4476,
|
| 890 |
+
"eval_samples_per_second": 6.946,
|
| 891 |
+
"eval_steps_per_second": 2.043,
|
| 892 |
+
"eval_wer": 0.22713864306784662,
|
| 893 |
+
"step": 627
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 57.27,
|
| 897 |
+
"learning_rate": 0.00013345794392523362,
|
| 898 |
+
"loss": 0.2402,
|
| 899 |
+
"step": 630
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 57.98,
|
| 903 |
+
"eval_loss": 0.43458130955696106,
|
| 904 |
+
"eval_runtime": 2.4576,
|
| 905 |
+
"eval_samples_per_second": 6.917,
|
| 906 |
+
"eval_steps_per_second": 2.034,
|
| 907 |
+
"eval_wer": 0.22418879056047197,
|
| 908 |
+
"step": 638
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 58.18,
|
| 912 |
+
"learning_rate": 0.00013065420560747661,
|
| 913 |
+
"loss": 0.2567,
|
| 914 |
+
"step": 640
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 58.98,
|
| 918 |
+
"eval_loss": 0.501366376876831,
|
| 919 |
+
"eval_runtime": 2.4401,
|
| 920 |
+
"eval_samples_per_second": 6.967,
|
| 921 |
+
"eval_steps_per_second": 2.049,
|
| 922 |
+
"eval_wer": 0.22861356932153393,
|
| 923 |
+
"step": 649
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 59.09,
|
| 927 |
+
"learning_rate": 0.0001278504672897196,
|
| 928 |
+
"loss": 0.294,
|
| 929 |
+
"step": 650
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 59.98,
|
| 933 |
+
"learning_rate": 0.0001250467289719626,
|
| 934 |
+
"loss": 0.28,
|
| 935 |
+
"step": 660
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 59.98,
|
| 939 |
+
"eval_loss": 0.44283339381217957,
|
| 940 |
+
"eval_runtime": 2.4528,
|
| 941 |
+
"eval_samples_per_second": 6.931,
|
| 942 |
+
"eval_steps_per_second": 2.038,
|
| 943 |
+
"eval_wer": 0.2182890855457227,
|
| 944 |
+
"step": 660
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 60.89,
|
| 948 |
+
"learning_rate": 0.00012224299065420559,
|
| 949 |
+
"loss": 0.2541,
|
| 950 |
+
"step": 670
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 60.98,
|
| 954 |
+
"eval_loss": 0.4875503480434418,
|
| 955 |
+
"eval_runtime": 2.4588,
|
| 956 |
+
"eval_samples_per_second": 6.914,
|
| 957 |
+
"eval_steps_per_second": 2.033,
|
| 958 |
+
"eval_wer": 0.22271386430678466,
|
| 959 |
+
"step": 671
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 61.8,
|
| 963 |
+
"learning_rate": 0.00011943925233644859,
|
| 964 |
+
"loss": 0.2544,
|
| 965 |
+
"step": 680
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 61.98,
|
| 969 |
+
"eval_loss": 0.4705180823802948,
|
| 970 |
+
"eval_runtime": 2.4501,
|
| 971 |
+
"eval_samples_per_second": 6.939,
|
| 972 |
+
"eval_steps_per_second": 2.041,
|
| 973 |
+
"eval_wer": 0.20501474926253688,
|
| 974 |
+
"step": 682
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 62.71,
|
| 978 |
+
"learning_rate": 0.00011663551401869158,
|
| 979 |
+
"loss": 0.2786,
|
| 980 |
+
"step": 690
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 62.98,
|
| 984 |
+
"eval_loss": 0.44488102197647095,
|
| 985 |
+
"eval_runtime": 2.4756,
|
| 986 |
+
"eval_samples_per_second": 6.867,
|
| 987 |
+
"eval_steps_per_second": 2.02,
|
| 988 |
+
"eval_wer": 0.20206489675516223,
|
| 989 |
+
"step": 693
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 63.62,
|
| 993 |
+
"learning_rate": 0.00011383177570093457,
|
| 994 |
+
"loss": 0.2524,
|
| 995 |
+
"step": 700
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 63.98,
|
| 999 |
+
"eval_loss": 0.558536946773529,
|
| 1000 |
+
"eval_runtime": 2.4336,
|
| 1001 |
+
"eval_samples_per_second": 6.986,
|
| 1002 |
+
"eval_steps_per_second": 2.055,
|
| 1003 |
+
"eval_wer": 0.20943952802359883,
|
| 1004 |
+
"step": 704
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 64.53,
|
| 1008 |
+
"learning_rate": 0.00011102803738317756,
|
| 1009 |
+
"loss": 0.2524,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 64.98,
|
| 1014 |
+
"eval_loss": 0.5178933143615723,
|
| 1015 |
+
"eval_runtime": 2.4703,
|
| 1016 |
+
"eval_samples_per_second": 6.882,
|
| 1017 |
+
"eval_steps_per_second": 2.024,
|
| 1018 |
+
"eval_wer": 0.21091445427728614,
|
| 1019 |
+
"step": 715
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 65.44,
|
| 1023 |
+
"learning_rate": 0.00010822429906542055,
|
| 1024 |
+
"loss": 0.2852,
|
| 1025 |
+
"step": 720
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 65.98,
|
| 1029 |
+
"eval_loss": 0.5062990188598633,
|
| 1030 |
+
"eval_runtime": 2.427,
|
| 1031 |
+
"eval_samples_per_second": 7.004,
|
| 1032 |
+
"eval_steps_per_second": 2.06,
|
| 1033 |
+
"eval_wer": 0.21976401179941002,
|
| 1034 |
+
"step": 726
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 66.36,
|
| 1038 |
+
"learning_rate": 0.00010542056074766354,
|
| 1039 |
+
"loss": 0.2393,
|
| 1040 |
+
"step": 730
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 66.98,
|
| 1044 |
+
"eval_loss": 0.4768075942993164,
|
| 1045 |
+
"eval_runtime": 2.4351,
|
| 1046 |
+
"eval_samples_per_second": 6.981,
|
| 1047 |
+
"eval_steps_per_second": 2.053,
|
| 1048 |
+
"eval_wer": 0.19911504424778761,
|
| 1049 |
+
"step": 737
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 67.27,
|
| 1053 |
+
"learning_rate": 0.00010261682242990653,
|
| 1054 |
+
"loss": 0.2522,
|
| 1055 |
+
"step": 740
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 67.98,
|
| 1059 |
+
"eval_loss": 0.44732481241226196,
|
| 1060 |
+
"eval_runtime": 2.4715,
|
| 1061 |
+
"eval_samples_per_second": 6.878,
|
| 1062 |
+
"eval_steps_per_second": 2.023,
|
| 1063 |
+
"eval_wer": 0.19321533923303835,
|
| 1064 |
+
"step": 748
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 68.18,
|
| 1068 |
+
"learning_rate": 9.981308411214952e-05,
|
| 1069 |
+
"loss": 0.2768,
|
| 1070 |
+
"step": 750
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 68.98,
|
| 1074 |
+
"eval_loss": 0.4713572859764099,
|
| 1075 |
+
"eval_runtime": 2.4588,
|
| 1076 |
+
"eval_samples_per_second": 6.914,
|
| 1077 |
+
"eval_steps_per_second": 2.034,
|
| 1078 |
+
"eval_wer": 0.19911504424778761,
|
| 1079 |
+
"step": 759
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 69.09,
|
| 1083 |
+
"learning_rate": 9.700934579439252e-05,
|
| 1084 |
+
"loss": 0.2484,
|
| 1085 |
+
"step": 760
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 69.98,
|
| 1089 |
+
"learning_rate": 9.42056074766355e-05,
|
| 1090 |
+
"loss": 0.2463,
|
| 1091 |
+
"step": 770
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 69.98,
|
| 1095 |
+
"eval_loss": 0.4947798550128937,
|
| 1096 |
+
"eval_runtime": 2.5096,
|
| 1097 |
+
"eval_samples_per_second": 6.774,
|
| 1098 |
+
"eval_steps_per_second": 1.992,
|
| 1099 |
+
"eval_wer": 0.19469026548672566,
|
| 1100 |
+
"step": 770
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 70.89,
|
| 1104 |
+
"learning_rate": 9.14018691588785e-05,
|
| 1105 |
+
"loss": 0.2379,
|
| 1106 |
+
"step": 780
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 70.98,
|
| 1110 |
+
"eval_loss": 0.4977743923664093,
|
| 1111 |
+
"eval_runtime": 2.4614,
|
| 1112 |
+
"eval_samples_per_second": 6.907,
|
| 1113 |
+
"eval_steps_per_second": 2.031,
|
| 1114 |
+
"eval_wer": 0.19321533923303835,
|
| 1115 |
+
"step": 781
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 71.8,
|
| 1119 |
+
"learning_rate": 8.859813084112149e-05,
|
| 1120 |
+
"loss": 0.2343,
|
| 1121 |
+
"step": 790
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 71.98,
|
| 1125 |
+
"eval_loss": 0.45256489515304565,
|
| 1126 |
+
"eval_runtime": 2.4455,
|
| 1127 |
+
"eval_samples_per_second": 6.952,
|
| 1128 |
+
"eval_steps_per_second": 2.045,
|
| 1129 |
+
"eval_wer": 0.1902654867256637,
|
| 1130 |
+
"step": 792
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 72.71,
|
| 1134 |
+
"learning_rate": 8.579439252336448e-05,
|
| 1135 |
+
"loss": 0.3377,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 72.98,
|
| 1140 |
+
"eval_loss": 0.451813668012619,
|
| 1141 |
+
"eval_runtime": 2.4509,
|
| 1142 |
+
"eval_samples_per_second": 6.936,
|
| 1143 |
+
"eval_steps_per_second": 2.04,
|
| 1144 |
+
"eval_wer": 0.19616519174041297,
|
| 1145 |
+
"step": 803
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 73.62,
|
| 1149 |
+
"learning_rate": 8.299065420560747e-05,
|
| 1150 |
+
"loss": 0.2683,
|
| 1151 |
+
"step": 810
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 73.98,
|
| 1155 |
+
"eval_loss": 0.44569432735443115,
|
| 1156 |
+
"eval_runtime": 2.4492,
|
| 1157 |
+
"eval_samples_per_second": 6.941,
|
| 1158 |
+
"eval_steps_per_second": 2.041,
|
| 1159 |
+
"eval_wer": 0.21091445427728614,
|
| 1160 |
+
"step": 814
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 74.53,
|
| 1164 |
+
"learning_rate": 8.018691588785046e-05,
|
| 1165 |
+
"loss": 0.2371,
|
| 1166 |
+
"step": 820
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 74.98,
|
| 1170 |
+
"eval_loss": 0.4563811719417572,
|
| 1171 |
+
"eval_runtime": 2.4581,
|
| 1172 |
+
"eval_samples_per_second": 6.916,
|
| 1173 |
+
"eval_steps_per_second": 2.034,
|
| 1174 |
+
"eval_wer": 0.20206489675516223,
|
| 1175 |
+
"step": 825
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 75.44,
|
| 1179 |
+
"learning_rate": 7.738317757009345e-05,
|
| 1180 |
+
"loss": 0.2438,
|
| 1181 |
+
"step": 830
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 75.98,
|
| 1185 |
+
"eval_loss": 0.48755523562431335,
|
| 1186 |
+
"eval_runtime": 2.4767,
|
| 1187 |
+
"eval_samples_per_second": 6.864,
|
| 1188 |
+
"eval_steps_per_second": 2.019,
|
| 1189 |
+
"eval_wer": 0.20943952802359883,
|
| 1190 |
+
"step": 836
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 76.36,
|
| 1194 |
+
"learning_rate": 7.457943925233644e-05,
|
| 1195 |
+
"loss": 0.2408,
|
| 1196 |
+
"step": 840
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 76.98,
|
| 1200 |
+
"eval_loss": 0.43862077593803406,
|
| 1201 |
+
"eval_runtime": 2.4583,
|
| 1202 |
+
"eval_samples_per_second": 6.915,
|
| 1203 |
+
"eval_steps_per_second": 2.034,
|
| 1204 |
+
"eval_wer": 0.20206489675516223,
|
| 1205 |
+
"step": 847
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 77.27,
|
| 1209 |
+
"learning_rate": 7.177570093457943e-05,
|
| 1210 |
+
"loss": 0.2323,
|
| 1211 |
+
"step": 850
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 77.98,
|
| 1215 |
+
"eval_loss": 0.4512799382209778,
|
| 1216 |
+
"eval_runtime": 2.4462,
|
| 1217 |
+
"eval_samples_per_second": 6.95,
|
| 1218 |
+
"eval_steps_per_second": 2.044,
|
| 1219 |
+
"eval_wer": 0.19911504424778761,
|
| 1220 |
+
"step": 858
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 78.18,
|
| 1224 |
+
"learning_rate": 6.897196261682242e-05,
|
| 1225 |
+
"loss": 0.271,
|
| 1226 |
+
"step": 860
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 78.98,
|
| 1230 |
+
"eval_loss": 0.487374484539032,
|
| 1231 |
+
"eval_runtime": 2.4852,
|
| 1232 |
+
"eval_samples_per_second": 6.841,
|
| 1233 |
+
"eval_steps_per_second": 2.012,
|
| 1234 |
+
"eval_wer": 0.20206489675516223,
|
| 1235 |
+
"step": 869
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 79.09,
|
| 1239 |
+
"learning_rate": 6.616822429906541e-05,
|
| 1240 |
+
"loss": 0.2406,
|
| 1241 |
+
"step": 870
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 79.98,
|
| 1245 |
+
"learning_rate": 6.33644859813084e-05,
|
| 1246 |
+
"loss": 0.229,
|
| 1247 |
+
"step": 880
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 79.98,
|
| 1251 |
+
"eval_loss": 0.4882209002971649,
|
| 1252 |
+
"eval_runtime": 2.454,
|
| 1253 |
+
"eval_samples_per_second": 6.927,
|
| 1254 |
+
"eval_steps_per_second": 2.037,
|
| 1255 |
+
"eval_wer": 0.20648967551622419,
|
| 1256 |
+
"step": 880
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 80.89,
|
| 1260 |
+
"learning_rate": 6.05607476635514e-05,
|
| 1261 |
+
"loss": 0.224,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 80.98,
|
| 1266 |
+
"eval_loss": 0.49814578890800476,
|
| 1267 |
+
"eval_runtime": 2.4571,
|
| 1268 |
+
"eval_samples_per_second": 6.919,
|
| 1269 |
+
"eval_steps_per_second": 2.035,
|
| 1270 |
+
"eval_wer": 0.19911504424778761,
|
| 1271 |
+
"step": 891
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 81.8,
|
| 1275 |
+
"learning_rate": 5.775700934579439e-05,
|
| 1276 |
+
"loss": 0.2442,
|
| 1277 |
+
"step": 900
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 81.98,
|
| 1281 |
+
"eval_loss": 0.5448421835899353,
|
| 1282 |
+
"eval_runtime": 2.4539,
|
| 1283 |
+
"eval_samples_per_second": 6.928,
|
| 1284 |
+
"eval_steps_per_second": 2.038,
|
| 1285 |
+
"eval_wer": 0.20206489675516223,
|
| 1286 |
+
"step": 902
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 82.71,
|
| 1290 |
+
"learning_rate": 5.495327102803738e-05,
|
| 1291 |
+
"loss": 0.2075,
|
| 1292 |
+
"step": 910
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 82.98,
|
| 1296 |
+
"eval_loss": 0.4626116156578064,
|
| 1297 |
+
"eval_runtime": 2.4651,
|
| 1298 |
+
"eval_samples_per_second": 6.896,
|
| 1299 |
+
"eval_steps_per_second": 2.028,
|
| 1300 |
+
"eval_wer": 0.19911504424778761,
|
| 1301 |
+
"step": 913
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 83.62,
|
| 1305 |
+
"learning_rate": 5.214953271028037e-05,
|
| 1306 |
+
"loss": 0.2314,
|
| 1307 |
+
"step": 920
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 83.98,
|
| 1311 |
+
"eval_loss": 0.47063305974006653,
|
| 1312 |
+
"eval_runtime": 2.4549,
|
| 1313 |
+
"eval_samples_per_second": 6.925,
|
| 1314 |
+
"eval_steps_per_second": 2.037,
|
| 1315 |
+
"eval_wer": 0.20648967551622419,
|
| 1316 |
+
"step": 924
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 84.53,
|
| 1320 |
+
"learning_rate": 4.934579439252336e-05,
|
| 1321 |
+
"loss": 0.2208,
|
| 1322 |
+
"step": 930
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 84.98,
|
| 1326 |
+
"eval_loss": 0.5073422789573669,
|
| 1327 |
+
"eval_runtime": 2.4571,
|
| 1328 |
+
"eval_samples_per_second": 6.919,
|
| 1329 |
+
"eval_steps_per_second": 2.035,
|
| 1330 |
+
"eval_wer": 0.20353982300884957,
|
| 1331 |
+
"step": 935
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 85.44,
|
| 1335 |
+
"learning_rate": 4.6542056074766354e-05,
|
| 1336 |
+
"loss": 0.2547,
|
| 1337 |
+
"step": 940
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 85.98,
|
| 1341 |
+
"eval_loss": 0.48184993863105774,
|
| 1342 |
+
"eval_runtime": 2.4595,
|
| 1343 |
+
"eval_samples_per_second": 6.912,
|
| 1344 |
+
"eval_steps_per_second": 2.033,
|
| 1345 |
+
"eval_wer": 0.19616519174041297,
|
| 1346 |
+
"step": 946
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 86.36,
|
| 1350 |
+
"learning_rate": 4.3738317757009345e-05,
|
| 1351 |
+
"loss": 0.2895,
|
| 1352 |
+
"step": 950
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 86.98,
|
| 1356 |
+
"eval_loss": 0.49310269951820374,
|
| 1357 |
+
"eval_runtime": 2.4502,
|
| 1358 |
+
"eval_samples_per_second": 6.938,
|
| 1359 |
+
"eval_steps_per_second": 2.041,
|
| 1360 |
+
"eval_wer": 0.19911504424778761,
|
| 1361 |
+
"step": 957
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 87.27,
|
| 1365 |
+
"learning_rate": 4.0934579439252335e-05,
|
| 1366 |
+
"loss": 0.1988,
|
| 1367 |
+
"step": 960
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 87.98,
|
| 1371 |
+
"eval_loss": 0.47016218304634094,
|
| 1372 |
+
"eval_runtime": 2.4764,
|
| 1373 |
+
"eval_samples_per_second": 6.865,
|
| 1374 |
+
"eval_steps_per_second": 2.019,
|
| 1375 |
+
"eval_wer": 0.20058997050147492,
|
| 1376 |
+
"step": 968
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 88.18,
|
| 1380 |
+
"learning_rate": 3.8130841121495326e-05,
|
| 1381 |
+
"loss": 0.2383,
|
| 1382 |
+
"step": 970
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 88.98,
|
| 1386 |
+
"eval_loss": 0.4681670665740967,
|
| 1387 |
+
"eval_runtime": 2.4685,
|
| 1388 |
+
"eval_samples_per_second": 6.887,
|
| 1389 |
+
"eval_steps_per_second": 2.026,
|
| 1390 |
+
"eval_wer": 0.19911504424778761,
|
| 1391 |
+
"step": 979
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 89.09,
|
| 1395 |
+
"learning_rate": 3.5327102803738316e-05,
|
| 1396 |
+
"loss": 0.2235,
|
| 1397 |
+
"step": 980
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 89.98,
|
| 1401 |
+
"learning_rate": 3.252336448598131e-05,
|
| 1402 |
+
"loss": 0.2332,
|
| 1403 |
+
"step": 990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 89.98,
|
| 1407 |
+
"eval_loss": 0.4574868381023407,
|
| 1408 |
+
"eval_runtime": 2.4687,
|
| 1409 |
+
"eval_samples_per_second": 6.886,
|
| 1410 |
+
"eval_steps_per_second": 2.025,
|
| 1411 |
+
"eval_wer": 0.20648967551622419,
|
| 1412 |
+
"step": 990
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 90.89,
|
| 1416 |
+
"learning_rate": 2.9719626168224294e-05,
|
| 1417 |
+
"loss": 0.1983,
|
| 1418 |
+
"step": 1000
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 90.98,
|
| 1422 |
+
"eval_loss": 0.47059592604637146,
|
| 1423 |
+
"eval_runtime": 2.441,
|
| 1424 |
+
"eval_samples_per_second": 6.964,
|
| 1425 |
+
"eval_steps_per_second": 2.048,
|
| 1426 |
+
"eval_wer": 0.19911504424778761,
|
| 1427 |
+
"step": 1001
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 91.8,
|
| 1431 |
+
"learning_rate": 2.6915887850467285e-05,
|
| 1432 |
+
"loss": 0.2182,
|
| 1433 |
+
"step": 1010
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 91.98,
|
| 1437 |
+
"eval_loss": 0.4756470322608948,
|
| 1438 |
+
"eval_runtime": 2.4523,
|
| 1439 |
+
"eval_samples_per_second": 6.932,
|
| 1440 |
+
"eval_steps_per_second": 2.039,
|
| 1441 |
+
"eval_wer": 0.19911504424778761,
|
| 1442 |
+
"step": 1012
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 92.71,
|
| 1446 |
+
"learning_rate": 2.411214953271028e-05,
|
| 1447 |
+
"loss": 0.2161,
|
| 1448 |
+
"step": 1020
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 92.98,
|
| 1452 |
+
"eval_loss": 0.4685567617416382,
|
| 1453 |
+
"eval_runtime": 2.5426,
|
| 1454 |
+
"eval_samples_per_second": 6.686,
|
| 1455 |
+
"eval_steps_per_second": 1.967,
|
| 1456 |
+
"eval_wer": 0.19616519174041297,
|
| 1457 |
+
"step": 1023
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 93.62,
|
| 1461 |
+
"learning_rate": 2.130841121495327e-05,
|
| 1462 |
+
"loss": 0.2215,
|
| 1463 |
+
"step": 1030
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 93.98,
|
| 1467 |
+
"eval_loss": 0.4688819944858551,
|
| 1468 |
+
"eval_runtime": 2.4691,
|
| 1469 |
+
"eval_samples_per_second": 6.885,
|
| 1470 |
+
"eval_steps_per_second": 2.025,
|
| 1471 |
+
"eval_wer": 0.19321533923303835,
|
| 1472 |
+
"step": 1034
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 94.53,
|
| 1476 |
+
"learning_rate": 1.850467289719626e-05,
|
| 1477 |
+
"loss": 0.2223,
|
| 1478 |
+
"step": 1040
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 94.98,
|
| 1482 |
+
"eval_loss": 0.451424241065979,
|
| 1483 |
+
"eval_runtime": 2.4423,
|
| 1484 |
+
"eval_samples_per_second": 6.961,
|
| 1485 |
+
"eval_steps_per_second": 2.047,
|
| 1486 |
+
"eval_wer": 0.1887905604719764,
|
| 1487 |
+
"step": 1045
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 95.44,
|
| 1491 |
+
"learning_rate": 1.570093457943925e-05,
|
| 1492 |
+
"loss": 0.2068,
|
| 1493 |
+
"step": 1050
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 95.98,
|
| 1497 |
+
"eval_loss": 0.44822120666503906,
|
| 1498 |
+
"eval_runtime": 2.455,
|
| 1499 |
+
"eval_samples_per_second": 6.925,
|
| 1500 |
+
"eval_steps_per_second": 2.037,
|
| 1501 |
+
"eval_wer": 0.1887905604719764,
|
| 1502 |
+
"step": 1056
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 96.36,
|
| 1506 |
+
"learning_rate": 1.2897196261682242e-05,
|
| 1507 |
+
"loss": 0.2046,
|
| 1508 |
+
"step": 1060
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 96.98,
|
| 1512 |
+
"eval_loss": 0.4480588138103485,
|
| 1513 |
+
"eval_runtime": 2.4461,
|
| 1514 |
+
"eval_samples_per_second": 6.95,
|
| 1515 |
+
"eval_steps_per_second": 2.044,
|
| 1516 |
+
"eval_wer": 0.18584070796460178,
|
| 1517 |
+
"step": 1067
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 97.27,
|
| 1521 |
+
"learning_rate": 1.0093457943925232e-05,
|
| 1522 |
+
"loss": 0.2411,
|
| 1523 |
+
"step": 1070
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 97.98,
|
| 1527 |
+
"eval_loss": 0.4532119333744049,
|
| 1528 |
+
"eval_runtime": 2.4326,
|
| 1529 |
+
"eval_samples_per_second": 6.988,
|
| 1530 |
+
"eval_steps_per_second": 2.055,
|
| 1531 |
+
"eval_wer": 0.1902654867256637,
|
| 1532 |
+
"step": 1078
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 98.18,
|
| 1536 |
+
"learning_rate": 7.289719626168224e-06,
|
| 1537 |
+
"loss": 0.2296,
|
| 1538 |
+
"step": 1080
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 98.98,
|
| 1542 |
+
"eval_loss": 0.4600735306739807,
|
| 1543 |
+
"eval_runtime": 2.4501,
|
| 1544 |
+
"eval_samples_per_second": 6.939,
|
| 1545 |
+
"eval_steps_per_second": 2.041,
|
| 1546 |
+
"eval_wer": 0.19321533923303835,
|
| 1547 |
+
"step": 1089
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 99.09,
|
| 1551 |
+
"learning_rate": 4.4859813084112145e-06,
|
| 1552 |
+
"loss": 0.2113,
|
| 1553 |
+
"step": 1090
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 99.98,
|
| 1557 |
+
"learning_rate": 1.6822429906542053e-06,
|
| 1558 |
+
"loss": 0.2211,
|
| 1559 |
+
"step": 1100
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 99.98,
|
| 1563 |
+
"eval_loss": 0.462471067905426,
|
| 1564 |
+
"eval_runtime": 2.4339,
|
| 1565 |
+
"eval_samples_per_second": 6.985,
|
| 1566 |
+
"eval_steps_per_second": 2.054,
|
| 1567 |
+
"eval_wer": 0.19469026548672566,
|
| 1568 |
+
"step": 1100
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 99.98,
|
| 1572 |
+
"step": 1100,
|
| 1573 |
+
"total_flos": 1.8082449930602819e+18,
|
| 1574 |
+
"train_loss": 0.679512545520609,
|
| 1575 |
+
"train_runtime": 4168.4023,
|
| 1576 |
+
"train_samples_per_second": 4.294,
|
| 1577 |
+
"train_steps_per_second": 0.264
|
| 1578 |
+
}
|
| 1579 |
+
],
|
| 1580 |
+
"max_steps": 1100,
|
| 1581 |
+
"num_train_epochs": 100,
|
| 1582 |
+
"total_flos": 1.8082449930602819e+18,
|
| 1583 |
+
"trial_name": null,
|
| 1584 |
+
"trial_params": null
|
| 1585 |
+
}
|