End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Nov25_03-02-17_4b2aca464fe8/events.out.tfevents.1669349349.4b2aca464fe8.4588.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +1465 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_loss": 0.3162029981613159,
|
| 4 |
+
"eval_runtime": 2.8665,
|
| 5 |
+
"eval_samples": 17,
|
| 6 |
+
"eval_samples_per_second": 5.931,
|
| 7 |
+
"eval_steps_per_second": 1.744,
|
| 8 |
+
"eval_wer": 0.3011111111111111,
|
| 9 |
+
"train_loss": 0.7617763585514492,
|
| 10 |
+
"train_runtime": 3519.9031,
|
| 11 |
+
"train_samples": 141,
|
| 12 |
+
"train_samples_per_second": 4.006,
|
| 13 |
+
"train_steps_per_second": 0.256
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_loss": 0.3162029981613159,
|
| 4 |
+
"eval_runtime": 2.8665,
|
| 5 |
+
"eval_samples": 17,
|
| 6 |
+
"eval_samples_per_second": 5.931,
|
| 7 |
+
"eval_steps_per_second": 1.744,
|
| 8 |
+
"eval_wer": 0.3011111111111111
|
| 9 |
+
}
|
runs/Nov25_03-02-17_4b2aca464fe8/events.out.tfevents.1669349349.4b2aca464fe8.4588.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11f00732dd7683463874a1b3c6fd6a6e74a10111cb4b380ae2dd08f0f01394ee
|
| 3 |
+
size 358
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"train_loss": 0.7617763585514492,
|
| 4 |
+
"train_runtime": 3519.9031,
|
| 5 |
+
"train_samples": 141,
|
| 6 |
+
"train_samples_per_second": 4.006,
|
| 7 |
+
"train_steps_per_second": 0.256
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1465 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3162029981613159,
|
| 3 |
+
"best_model_checkpoint": "ai-light-dance_drums_ft_pretrain_wav2vec2-base-new_onset-idmt-2/checkpoint-459",
|
| 4 |
+
"epoch": 100.0,
|
| 5 |
+
"global_step": 900,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_loss": 97.93186950683594,
|
| 13 |
+
"eval_runtime": 2.7466,
|
| 14 |
+
"eval_samples_per_second": 6.19,
|
| 15 |
+
"eval_steps_per_second": 1.82,
|
| 16 |
+
"eval_wer": 1.0,
|
| 17 |
+
"step": 9
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.11,
|
| 21 |
+
"learning_rate": 2.9999999999999997e-05,
|
| 22 |
+
"loss": 17.1836,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"eval_loss": 45.722869873046875,
|
| 28 |
+
"eval_runtime": 2.9189,
|
| 29 |
+
"eval_samples_per_second": 5.824,
|
| 30 |
+
"eval_steps_per_second": 1.713,
|
| 31 |
+
"eval_wer": 1.0,
|
| 32 |
+
"step": 18
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.22,
|
| 36 |
+
"learning_rate": 0.00013,
|
| 37 |
+
"loss": 13.2869,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"eval_loss": 2.757852554321289,
|
| 43 |
+
"eval_runtime": 2.8561,
|
| 44 |
+
"eval_samples_per_second": 5.952,
|
| 45 |
+
"eval_steps_per_second": 1.751,
|
| 46 |
+
"eval_wer": 1.0,
|
| 47 |
+
"step": 27
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.33,
|
| 51 |
+
"learning_rate": 0.00023,
|
| 52 |
+
"loss": 2.6495,
|
| 53 |
+
"step": 30
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 4.0,
|
| 57 |
+
"eval_loss": 2.7427165508270264,
|
| 58 |
+
"eval_runtime": 2.8408,
|
| 59 |
+
"eval_samples_per_second": 5.984,
|
| 60 |
+
"eval_steps_per_second": 1.76,
|
| 61 |
+
"eval_wer": 1.0,
|
| 62 |
+
"step": 36
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.44,
|
| 66 |
+
"learning_rate": 0.0002989655172413793,
|
| 67 |
+
"loss": 1.7135,
|
| 68 |
+
"step": 40
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.0,
|
| 72 |
+
"eval_loss": 2.5476696491241455,
|
| 73 |
+
"eval_runtime": 2.8174,
|
| 74 |
+
"eval_samples_per_second": 6.034,
|
| 75 |
+
"eval_steps_per_second": 1.775,
|
| 76 |
+
"eval_wer": 1.0,
|
| 77 |
+
"step": 45
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 5.56,
|
| 81 |
+
"learning_rate": 0.00029551724137931033,
|
| 82 |
+
"loss": 1.4609,
|
| 83 |
+
"step": 50
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 6.0,
|
| 87 |
+
"eval_loss": 1.7126435041427612,
|
| 88 |
+
"eval_runtime": 2.9262,
|
| 89 |
+
"eval_samples_per_second": 5.81,
|
| 90 |
+
"eval_steps_per_second": 1.709,
|
| 91 |
+
"eval_wer": 1.0,
|
| 92 |
+
"step": 54
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 6.67,
|
| 96 |
+
"learning_rate": 0.00029206896551724134,
|
| 97 |
+
"loss": 1.374,
|
| 98 |
+
"step": 60
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 7.0,
|
| 102 |
+
"eval_loss": 1.3668222427368164,
|
| 103 |
+
"eval_runtime": 2.8538,
|
| 104 |
+
"eval_samples_per_second": 5.957,
|
| 105 |
+
"eval_steps_per_second": 1.752,
|
| 106 |
+
"eval_wer": 0.9966666666666667,
|
| 107 |
+
"step": 63
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 7.78,
|
| 111 |
+
"learning_rate": 0.0002886206896551724,
|
| 112 |
+
"loss": 1.2951,
|
| 113 |
+
"step": 70
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 8.0,
|
| 117 |
+
"eval_loss": 1.127436637878418,
|
| 118 |
+
"eval_runtime": 2.8558,
|
| 119 |
+
"eval_samples_per_second": 5.953,
|
| 120 |
+
"eval_steps_per_second": 1.751,
|
| 121 |
+
"eval_wer": 0.9866666666666667,
|
| 122 |
+
"step": 72
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 8.89,
|
| 126 |
+
"learning_rate": 0.00028517241379310345,
|
| 127 |
+
"loss": 1.0493,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 9.0,
|
| 132 |
+
"eval_loss": 0.7346072196960449,
|
| 133 |
+
"eval_runtime": 3.0416,
|
| 134 |
+
"eval_samples_per_second": 5.589,
|
| 135 |
+
"eval_steps_per_second": 1.644,
|
| 136 |
+
"eval_wer": 0.5177777777777778,
|
| 137 |
+
"step": 81
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 10.0,
|
| 141 |
+
"learning_rate": 0.00028172413793103445,
|
| 142 |
+
"loss": 0.8835,
|
| 143 |
+
"step": 90
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 10.0,
|
| 147 |
+
"eval_loss": 0.7663962841033936,
|
| 148 |
+
"eval_runtime": 2.8583,
|
| 149 |
+
"eval_samples_per_second": 5.947,
|
| 150 |
+
"eval_steps_per_second": 1.749,
|
| 151 |
+
"eval_wer": 0.4122222222222222,
|
| 152 |
+
"step": 90
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 11.0,
|
| 156 |
+
"eval_loss": 0.5438075065612793,
|
| 157 |
+
"eval_runtime": 2.9205,
|
| 158 |
+
"eval_samples_per_second": 5.821,
|
| 159 |
+
"eval_steps_per_second": 1.712,
|
| 160 |
+
"eval_wer": 0.38666666666666666,
|
| 161 |
+
"step": 99
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 11.11,
|
| 165 |
+
"learning_rate": 0.0002782758620689655,
|
| 166 |
+
"loss": 0.7019,
|
| 167 |
+
"step": 100
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 12.0,
|
| 171 |
+
"eval_loss": 0.4876076281070709,
|
| 172 |
+
"eval_runtime": 2.8398,
|
| 173 |
+
"eval_samples_per_second": 5.986,
|
| 174 |
+
"eval_steps_per_second": 1.761,
|
| 175 |
+
"eval_wer": 0.3711111111111111,
|
| 176 |
+
"step": 108
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 12.22,
|
| 180 |
+
"learning_rate": 0.0002748275862068965,
|
| 181 |
+
"loss": 0.6906,
|
| 182 |
+
"step": 110
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 13.0,
|
| 186 |
+
"eval_loss": 0.519428551197052,
|
| 187 |
+
"eval_runtime": 2.7785,
|
| 188 |
+
"eval_samples_per_second": 6.119,
|
| 189 |
+
"eval_steps_per_second": 1.8,
|
| 190 |
+
"eval_wer": 0.36,
|
| 191 |
+
"step": 117
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 13.33,
|
| 195 |
+
"learning_rate": 0.00027137931034482756,
|
| 196 |
+
"loss": 0.6535,
|
| 197 |
+
"step": 120
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 14.0,
|
| 201 |
+
"eval_loss": 0.4489333927631378,
|
| 202 |
+
"eval_runtime": 2.8252,
|
| 203 |
+
"eval_samples_per_second": 6.017,
|
| 204 |
+
"eval_steps_per_second": 1.77,
|
| 205 |
+
"eval_wer": 0.35555555555555557,
|
| 206 |
+
"step": 126
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 14.44,
|
| 210 |
+
"learning_rate": 0.0002679310344827586,
|
| 211 |
+
"loss": 0.6225,
|
| 212 |
+
"step": 130
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 15.0,
|
| 216 |
+
"eval_loss": 0.4382663071155548,
|
| 217 |
+
"eval_runtime": 2.7906,
|
| 218 |
+
"eval_samples_per_second": 6.092,
|
| 219 |
+
"eval_steps_per_second": 1.792,
|
| 220 |
+
"eval_wer": 0.3333333333333333,
|
| 221 |
+
"step": 135
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 15.56,
|
| 225 |
+
"learning_rate": 0.0002644827586206896,
|
| 226 |
+
"loss": 0.547,
|
| 227 |
+
"step": 140
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 16.0,
|
| 231 |
+
"eval_loss": 0.4521160423755646,
|
| 232 |
+
"eval_runtime": 2.8251,
|
| 233 |
+
"eval_samples_per_second": 6.017,
|
| 234 |
+
"eval_steps_per_second": 1.77,
|
| 235 |
+
"eval_wer": 0.35555555555555557,
|
| 236 |
+
"step": 144
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 16.67,
|
| 240 |
+
"learning_rate": 0.00026103448275862067,
|
| 241 |
+
"loss": 0.5525,
|
| 242 |
+
"step": 150
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 17.0,
|
| 246 |
+
"eval_loss": 0.5476210117340088,
|
| 247 |
+
"eval_runtime": 2.8122,
|
| 248 |
+
"eval_samples_per_second": 6.045,
|
| 249 |
+
"eval_steps_per_second": 1.778,
|
| 250 |
+
"eval_wer": 0.33444444444444443,
|
| 251 |
+
"step": 153
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 17.78,
|
| 255 |
+
"learning_rate": 0.0002575862068965517,
|
| 256 |
+
"loss": 0.6152,
|
| 257 |
+
"step": 160
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 18.0,
|
| 261 |
+
"eval_loss": 0.4465982913970947,
|
| 262 |
+
"eval_runtime": 2.8461,
|
| 263 |
+
"eval_samples_per_second": 5.973,
|
| 264 |
+
"eval_steps_per_second": 1.757,
|
| 265 |
+
"eval_wer": 0.36,
|
| 266 |
+
"step": 162
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 18.89,
|
| 270 |
+
"learning_rate": 0.00025413793103448273,
|
| 271 |
+
"loss": 0.5055,
|
| 272 |
+
"step": 170
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 19.0,
|
| 276 |
+
"eval_loss": 0.39812201261520386,
|
| 277 |
+
"eval_runtime": 2.805,
|
| 278 |
+
"eval_samples_per_second": 6.061,
|
| 279 |
+
"eval_steps_per_second": 1.783,
|
| 280 |
+
"eval_wer": 0.32555555555555554,
|
| 281 |
+
"step": 171
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 20.0,
|
| 285 |
+
"learning_rate": 0.0002506896551724138,
|
| 286 |
+
"loss": 0.5204,
|
| 287 |
+
"step": 180
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 20.0,
|
| 291 |
+
"eval_loss": 0.4923681318759918,
|
| 292 |
+
"eval_runtime": 2.8028,
|
| 293 |
+
"eval_samples_per_second": 6.065,
|
| 294 |
+
"eval_steps_per_second": 1.784,
|
| 295 |
+
"eval_wer": 0.30777777777777776,
|
| 296 |
+
"step": 180
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 21.0,
|
| 300 |
+
"eval_loss": 0.4085298776626587,
|
| 301 |
+
"eval_runtime": 2.8109,
|
| 302 |
+
"eval_samples_per_second": 6.048,
|
| 303 |
+
"eval_steps_per_second": 1.779,
|
| 304 |
+
"eval_wer": 0.32,
|
| 305 |
+
"step": 189
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 21.11,
|
| 309 |
+
"learning_rate": 0.0002472413793103448,
|
| 310 |
+
"loss": 0.4742,
|
| 311 |
+
"step": 190
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 22.0,
|
| 315 |
+
"eval_loss": 0.4254695177078247,
|
| 316 |
+
"eval_runtime": 2.7979,
|
| 317 |
+
"eval_samples_per_second": 6.076,
|
| 318 |
+
"eval_steps_per_second": 1.787,
|
| 319 |
+
"eval_wer": 0.3233333333333333,
|
| 320 |
+
"step": 198
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 22.22,
|
| 324 |
+
"learning_rate": 0.00024379310344827584,
|
| 325 |
+
"loss": 0.4774,
|
| 326 |
+
"step": 200
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 23.0,
|
| 330 |
+
"eval_loss": 0.43211016058921814,
|
| 331 |
+
"eval_runtime": 2.8119,
|
| 332 |
+
"eval_samples_per_second": 6.046,
|
| 333 |
+
"eval_steps_per_second": 1.778,
|
| 334 |
+
"eval_wer": 0.28888888888888886,
|
| 335 |
+
"step": 207
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 23.33,
|
| 339 |
+
"learning_rate": 0.00024034482758620687,
|
| 340 |
+
"loss": 0.5029,
|
| 341 |
+
"step": 210
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 24.0,
|
| 345 |
+
"eval_loss": 0.44116583466529846,
|
| 346 |
+
"eval_runtime": 2.7953,
|
| 347 |
+
"eval_samples_per_second": 6.082,
|
| 348 |
+
"eval_steps_per_second": 1.789,
|
| 349 |
+
"eval_wer": 0.31666666666666665,
|
| 350 |
+
"step": 216
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 24.44,
|
| 354 |
+
"learning_rate": 0.00023689655172413792,
|
| 355 |
+
"loss": 0.4889,
|
| 356 |
+
"step": 220
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 25.0,
|
| 360 |
+
"eval_loss": 0.40511757135391235,
|
| 361 |
+
"eval_runtime": 2.8082,
|
| 362 |
+
"eval_samples_per_second": 6.054,
|
| 363 |
+
"eval_steps_per_second": 1.781,
|
| 364 |
+
"eval_wer": 0.30444444444444446,
|
| 365 |
+
"step": 225
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 25.56,
|
| 369 |
+
"learning_rate": 0.00023344827586206895,
|
| 370 |
+
"loss": 0.4446,
|
| 371 |
+
"step": 230
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 26.0,
|
| 375 |
+
"eval_loss": 0.39176392555236816,
|
| 376 |
+
"eval_runtime": 2.8027,
|
| 377 |
+
"eval_samples_per_second": 6.066,
|
| 378 |
+
"eval_steps_per_second": 1.784,
|
| 379 |
+
"eval_wer": 0.3088888888888889,
|
| 380 |
+
"step": 234
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 26.67,
|
| 384 |
+
"learning_rate": 0.00023,
|
| 385 |
+
"loss": 0.4255,
|
| 386 |
+
"step": 240
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 27.0,
|
| 390 |
+
"eval_loss": 0.403872549533844,
|
| 391 |
+
"eval_runtime": 2.786,
|
| 392 |
+
"eval_samples_per_second": 6.102,
|
| 393 |
+
"eval_steps_per_second": 1.795,
|
| 394 |
+
"eval_wer": 0.29555555555555557,
|
| 395 |
+
"step": 243
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 27.78,
|
| 399 |
+
"learning_rate": 0.000226551724137931,
|
| 400 |
+
"loss": 0.4396,
|
| 401 |
+
"step": 250
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 28.0,
|
| 405 |
+
"eval_loss": 0.4112667143344879,
|
| 406 |
+
"eval_runtime": 2.8335,
|
| 407 |
+
"eval_samples_per_second": 6.0,
|
| 408 |
+
"eval_steps_per_second": 1.765,
|
| 409 |
+
"eval_wer": 0.29555555555555557,
|
| 410 |
+
"step": 252
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 28.89,
|
| 414 |
+
"learning_rate": 0.00022310344827586204,
|
| 415 |
+
"loss": 0.4265,
|
| 416 |
+
"step": 260
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 29.0,
|
| 420 |
+
"eval_loss": 0.5575971603393555,
|
| 421 |
+
"eval_runtime": 2.7693,
|
| 422 |
+
"eval_samples_per_second": 6.139,
|
| 423 |
+
"eval_steps_per_second": 1.806,
|
| 424 |
+
"eval_wer": 0.3022222222222222,
|
| 425 |
+
"step": 261
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 30.0,
|
| 429 |
+
"learning_rate": 0.0002196551724137931,
|
| 430 |
+
"loss": 0.4289,
|
| 431 |
+
"step": 270
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 30.0,
|
| 435 |
+
"eval_loss": 0.35578060150146484,
|
| 436 |
+
"eval_runtime": 2.7632,
|
| 437 |
+
"eval_samples_per_second": 6.152,
|
| 438 |
+
"eval_steps_per_second": 1.81,
|
| 439 |
+
"eval_wer": 0.30777777777777776,
|
| 440 |
+
"step": 270
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 31.0,
|
| 444 |
+
"eval_loss": 0.33904996514320374,
|
| 445 |
+
"eval_runtime": 2.7428,
|
| 446 |
+
"eval_samples_per_second": 6.198,
|
| 447 |
+
"eval_steps_per_second": 1.823,
|
| 448 |
+
"eval_wer": 0.31666666666666665,
|
| 449 |
+
"step": 279
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 31.11,
|
| 453 |
+
"learning_rate": 0.00021620689655172412,
|
| 454 |
+
"loss": 0.3817,
|
| 455 |
+
"step": 280
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 32.0,
|
| 459 |
+
"eval_loss": 0.3738517165184021,
|
| 460 |
+
"eval_runtime": 2.7731,
|
| 461 |
+
"eval_samples_per_second": 6.13,
|
| 462 |
+
"eval_steps_per_second": 1.803,
|
| 463 |
+
"eval_wer": 0.3422222222222222,
|
| 464 |
+
"step": 288
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 32.22,
|
| 468 |
+
"learning_rate": 0.00021275862068965515,
|
| 469 |
+
"loss": 0.4192,
|
| 470 |
+
"step": 290
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 33.0,
|
| 474 |
+
"eval_loss": 0.31792330741882324,
|
| 475 |
+
"eval_runtime": 2.7573,
|
| 476 |
+
"eval_samples_per_second": 6.166,
|
| 477 |
+
"eval_steps_per_second": 1.813,
|
| 478 |
+
"eval_wer": 0.3055555555555556,
|
| 479 |
+
"step": 297
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 33.33,
|
| 483 |
+
"learning_rate": 0.0002093103448275862,
|
| 484 |
+
"loss": 0.3719,
|
| 485 |
+
"step": 300
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 34.0,
|
| 489 |
+
"eval_loss": 0.3621741235256195,
|
| 490 |
+
"eval_runtime": 2.7351,
|
| 491 |
+
"eval_samples_per_second": 6.215,
|
| 492 |
+
"eval_steps_per_second": 1.828,
|
| 493 |
+
"eval_wer": 0.30333333333333334,
|
| 494 |
+
"step": 306
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 34.44,
|
| 498 |
+
"learning_rate": 0.00020586206896551723,
|
| 499 |
+
"loss": 0.3685,
|
| 500 |
+
"step": 310
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 35.0,
|
| 504 |
+
"eval_loss": 0.40566930174827576,
|
| 505 |
+
"eval_runtime": 2.7612,
|
| 506 |
+
"eval_samples_per_second": 6.157,
|
| 507 |
+
"eval_steps_per_second": 1.811,
|
| 508 |
+
"eval_wer": 0.32555555555555554,
|
| 509 |
+
"step": 315
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 35.56,
|
| 513 |
+
"learning_rate": 0.0002024137931034483,
|
| 514 |
+
"loss": 0.3752,
|
| 515 |
+
"step": 320
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 36.0,
|
| 519 |
+
"eval_loss": 0.39497387409210205,
|
| 520 |
+
"eval_runtime": 2.7507,
|
| 521 |
+
"eval_samples_per_second": 6.18,
|
| 522 |
+
"eval_steps_per_second": 1.818,
|
| 523 |
+
"eval_wer": 0.31,
|
| 524 |
+
"step": 324
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 36.67,
|
| 528 |
+
"learning_rate": 0.0001989655172413793,
|
| 529 |
+
"loss": 0.378,
|
| 530 |
+
"step": 330
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 37.0,
|
| 534 |
+
"eval_loss": 0.39072442054748535,
|
| 535 |
+
"eval_runtime": 2.7439,
|
| 536 |
+
"eval_samples_per_second": 6.196,
|
| 537 |
+
"eval_steps_per_second": 1.822,
|
| 538 |
+
"eval_wer": 0.3566666666666667,
|
| 539 |
+
"step": 333
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 37.78,
|
| 543 |
+
"learning_rate": 0.00019551724137931032,
|
| 544 |
+
"loss": 0.4438,
|
| 545 |
+
"step": 340
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 38.0,
|
| 549 |
+
"eval_loss": 0.33762815594673157,
|
| 550 |
+
"eval_runtime": 2.7815,
|
| 551 |
+
"eval_samples_per_second": 6.112,
|
| 552 |
+
"eval_steps_per_second": 1.798,
|
| 553 |
+
"eval_wer": 0.31,
|
| 554 |
+
"step": 342
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 38.89,
|
| 558 |
+
"learning_rate": 0.00019206896551724134,
|
| 559 |
+
"loss": 0.3978,
|
| 560 |
+
"step": 350
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 39.0,
|
| 564 |
+
"eval_loss": 0.3395032286643982,
|
| 565 |
+
"eval_runtime": 2.8043,
|
| 566 |
+
"eval_samples_per_second": 6.062,
|
| 567 |
+
"eval_steps_per_second": 1.783,
|
| 568 |
+
"eval_wer": 0.2833333333333333,
|
| 569 |
+
"step": 351
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 40.0,
|
| 573 |
+
"learning_rate": 0.0001886206896551724,
|
| 574 |
+
"loss": 0.3639,
|
| 575 |
+
"step": 360
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 40.0,
|
| 579 |
+
"eval_loss": 0.36456623673439026,
|
| 580 |
+
"eval_runtime": 2.7816,
|
| 581 |
+
"eval_samples_per_second": 6.112,
|
| 582 |
+
"eval_steps_per_second": 1.798,
|
| 583 |
+
"eval_wer": 0.28555555555555556,
|
| 584 |
+
"step": 360
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 41.0,
|
| 588 |
+
"eval_loss": 0.3546362519264221,
|
| 589 |
+
"eval_runtime": 2.7679,
|
| 590 |
+
"eval_samples_per_second": 6.142,
|
| 591 |
+
"eval_steps_per_second": 1.806,
|
| 592 |
+
"eval_wer": 0.30444444444444446,
|
| 593 |
+
"step": 369
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 41.11,
|
| 597 |
+
"learning_rate": 0.00018517241379310343,
|
| 598 |
+
"loss": 0.3535,
|
| 599 |
+
"step": 370
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 42.0,
|
| 603 |
+
"eval_loss": 0.36989736557006836,
|
| 604 |
+
"eval_runtime": 2.8116,
|
| 605 |
+
"eval_samples_per_second": 6.046,
|
| 606 |
+
"eval_steps_per_second": 1.778,
|
| 607 |
+
"eval_wer": 0.28888888888888886,
|
| 608 |
+
"step": 378
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 42.22,
|
| 612 |
+
"learning_rate": 0.00018172413793103448,
|
| 613 |
+
"loss": 0.3311,
|
| 614 |
+
"step": 380
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 43.0,
|
| 618 |
+
"eval_loss": 0.38820379972457886,
|
| 619 |
+
"eval_runtime": 2.7493,
|
| 620 |
+
"eval_samples_per_second": 6.183,
|
| 621 |
+
"eval_steps_per_second": 1.819,
|
| 622 |
+
"eval_wer": 0.3022222222222222,
|
| 623 |
+
"step": 387
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 43.33,
|
| 627 |
+
"learning_rate": 0.0001782758620689655,
|
| 628 |
+
"loss": 0.3475,
|
| 629 |
+
"step": 390
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 44.0,
|
| 633 |
+
"eval_loss": 0.4749428331851959,
|
| 634 |
+
"eval_runtime": 2.8377,
|
| 635 |
+
"eval_samples_per_second": 5.991,
|
| 636 |
+
"eval_steps_per_second": 1.762,
|
| 637 |
+
"eval_wer": 0.28888888888888886,
|
| 638 |
+
"step": 396
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 44.44,
|
| 642 |
+
"learning_rate": 0.00017482758620689654,
|
| 643 |
+
"loss": 0.4048,
|
| 644 |
+
"step": 400
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 45.0,
|
| 648 |
+
"eval_loss": 0.34369951486587524,
|
| 649 |
+
"eval_runtime": 2.794,
|
| 650 |
+
"eval_samples_per_second": 6.085,
|
| 651 |
+
"eval_steps_per_second": 1.79,
|
| 652 |
+
"eval_wer": 0.2911111111111111,
|
| 653 |
+
"step": 405
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 45.56,
|
| 657 |
+
"learning_rate": 0.00017137931034482757,
|
| 658 |
+
"loss": 0.2984,
|
| 659 |
+
"step": 410
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 46.0,
|
| 663 |
+
"eval_loss": 0.36636969447135925,
|
| 664 |
+
"eval_runtime": 2.7731,
|
| 665 |
+
"eval_samples_per_second": 6.13,
|
| 666 |
+
"eval_steps_per_second": 1.803,
|
| 667 |
+
"eval_wer": 0.27,
|
| 668 |
+
"step": 414
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 46.67,
|
| 672 |
+
"learning_rate": 0.0001679310344827586,
|
| 673 |
+
"loss": 0.3535,
|
| 674 |
+
"step": 420
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 47.0,
|
| 678 |
+
"eval_loss": 0.3290660083293915,
|
| 679 |
+
"eval_runtime": 2.767,
|
| 680 |
+
"eval_samples_per_second": 6.144,
|
| 681 |
+
"eval_steps_per_second": 1.807,
|
| 682 |
+
"eval_wer": 0.28888888888888886,
|
| 683 |
+
"step": 423
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 47.78,
|
| 687 |
+
"learning_rate": 0.00016448275862068962,
|
| 688 |
+
"loss": 0.3015,
|
| 689 |
+
"step": 430
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 48.0,
|
| 693 |
+
"eval_loss": 0.35376498103141785,
|
| 694 |
+
"eval_runtime": 2.7572,
|
| 695 |
+
"eval_samples_per_second": 6.166,
|
| 696 |
+
"eval_steps_per_second": 1.813,
|
| 697 |
+
"eval_wer": 0.27666666666666667,
|
| 698 |
+
"step": 432
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 48.89,
|
| 702 |
+
"learning_rate": 0.00016103448275862068,
|
| 703 |
+
"loss": 0.3628,
|
| 704 |
+
"step": 440
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 49.0,
|
| 708 |
+
"eval_loss": 0.44109877943992615,
|
| 709 |
+
"eval_runtime": 2.7694,
|
| 710 |
+
"eval_samples_per_second": 6.139,
|
| 711 |
+
"eval_steps_per_second": 1.805,
|
| 712 |
+
"eval_wer": 0.2733333333333333,
|
| 713 |
+
"step": 441
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 50.0,
|
| 717 |
+
"learning_rate": 0.0001575862068965517,
|
| 718 |
+
"loss": 0.3303,
|
| 719 |
+
"step": 450
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 50.0,
|
| 723 |
+
"eval_loss": 0.34246134757995605,
|
| 724 |
+
"eval_runtime": 2.7763,
|
| 725 |
+
"eval_samples_per_second": 6.123,
|
| 726 |
+
"eval_steps_per_second": 1.801,
|
| 727 |
+
"eval_wer": 0.29,
|
| 728 |
+
"step": 450
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 51.0,
|
| 732 |
+
"eval_loss": 0.3162029981613159,
|
| 733 |
+
"eval_runtime": 2.7842,
|
| 734 |
+
"eval_samples_per_second": 6.106,
|
| 735 |
+
"eval_steps_per_second": 1.796,
|
| 736 |
+
"eval_wer": 0.3011111111111111,
|
| 737 |
+
"step": 459
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 51.11,
|
| 741 |
+
"learning_rate": 0.00015413793103448276,
|
| 742 |
+
"loss": 0.271,
|
| 743 |
+
"step": 460
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 52.0,
|
| 747 |
+
"eval_loss": 0.36851903796195984,
|
| 748 |
+
"eval_runtime": 2.7813,
|
| 749 |
+
"eval_samples_per_second": 6.112,
|
| 750 |
+
"eval_steps_per_second": 1.798,
|
| 751 |
+
"eval_wer": 0.29333333333333333,
|
| 752 |
+
"step": 468
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 52.22,
|
| 756 |
+
"learning_rate": 0.0001506896551724138,
|
| 757 |
+
"loss": 0.3299,
|
| 758 |
+
"step": 470
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 53.0,
|
| 762 |
+
"eval_loss": 0.42159539461135864,
|
| 763 |
+
"eval_runtime": 2.767,
|
| 764 |
+
"eval_samples_per_second": 6.144,
|
| 765 |
+
"eval_steps_per_second": 1.807,
|
| 766 |
+
"eval_wer": 0.29333333333333333,
|
| 767 |
+
"step": 477
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 53.33,
|
| 771 |
+
"learning_rate": 0.00014724137931034482,
|
| 772 |
+
"loss": 0.2782,
|
| 773 |
+
"step": 480
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 54.0,
|
| 777 |
+
"eval_loss": 0.4713245928287506,
|
| 778 |
+
"eval_runtime": 2.8739,
|
| 779 |
+
"eval_samples_per_second": 5.915,
|
| 780 |
+
"eval_steps_per_second": 1.74,
|
| 781 |
+
"eval_wer": 0.30444444444444446,
|
| 782 |
+
"step": 486
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 54.44,
|
| 786 |
+
"learning_rate": 0.00014379310344827585,
|
| 787 |
+
"loss": 0.348,
|
| 788 |
+
"step": 490
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 55.0,
|
| 792 |
+
"eval_loss": 0.4310116767883301,
|
| 793 |
+
"eval_runtime": 2.7991,
|
| 794 |
+
"eval_samples_per_second": 6.073,
|
| 795 |
+
"eval_steps_per_second": 1.786,
|
| 796 |
+
"eval_wer": 0.30777777777777776,
|
| 797 |
+
"step": 495
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 55.56,
|
| 801 |
+
"learning_rate": 0.00014034482758620688,
|
| 802 |
+
"loss": 0.2969,
|
| 803 |
+
"step": 500
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 56.0,
|
| 807 |
+
"eval_loss": 0.48976629972457886,
|
| 808 |
+
"eval_runtime": 2.8118,
|
| 809 |
+
"eval_samples_per_second": 6.046,
|
| 810 |
+
"eval_steps_per_second": 1.778,
|
| 811 |
+
"eval_wer": 0.27666666666666667,
|
| 812 |
+
"step": 504
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 56.67,
|
| 816 |
+
"learning_rate": 0.0001368965517241379,
|
| 817 |
+
"loss": 0.2757,
|
| 818 |
+
"step": 510
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 57.0,
|
| 822 |
+
"eval_loss": 0.5194886326789856,
|
| 823 |
+
"eval_runtime": 2.7939,
|
| 824 |
+
"eval_samples_per_second": 6.085,
|
| 825 |
+
"eval_steps_per_second": 1.79,
|
| 826 |
+
"eval_wer": 0.2788888888888889,
|
| 827 |
+
"step": 513
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 57.78,
|
| 831 |
+
"learning_rate": 0.00013344827586206896,
|
| 832 |
+
"loss": 0.2662,
|
| 833 |
+
"step": 520
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 58.0,
|
| 837 |
+
"eval_loss": 0.46313199400901794,
|
| 838 |
+
"eval_runtime": 2.7984,
|
| 839 |
+
"eval_samples_per_second": 6.075,
|
| 840 |
+
"eval_steps_per_second": 1.787,
|
| 841 |
+
"eval_wer": 0.2911111111111111,
|
| 842 |
+
"step": 522
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 58.89,
|
| 846 |
+
"learning_rate": 0.00013,
|
| 847 |
+
"loss": 0.2706,
|
| 848 |
+
"step": 530
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 59.0,
|
| 852 |
+
"eval_loss": 0.427517294883728,
|
| 853 |
+
"eval_runtime": 2.7564,
|
| 854 |
+
"eval_samples_per_second": 6.168,
|
| 855 |
+
"eval_steps_per_second": 1.814,
|
| 856 |
+
"eval_wer": 0.2833333333333333,
|
| 857 |
+
"step": 531
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 60.0,
|
| 861 |
+
"learning_rate": 0.00012655172413793102,
|
| 862 |
+
"loss": 0.2684,
|
| 863 |
+
"step": 540
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 60.0,
|
| 867 |
+
"eval_loss": 0.553533136844635,
|
| 868 |
+
"eval_runtime": 2.7742,
|
| 869 |
+
"eval_samples_per_second": 6.128,
|
| 870 |
+
"eval_steps_per_second": 1.802,
|
| 871 |
+
"eval_wer": 0.2788888888888889,
|
| 872 |
+
"step": 540
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 61.0,
|
| 876 |
+
"eval_loss": 0.4733206331729889,
|
| 877 |
+
"eval_runtime": 2.7693,
|
| 878 |
+
"eval_samples_per_second": 6.139,
|
| 879 |
+
"eval_steps_per_second": 1.806,
|
| 880 |
+
"eval_wer": 0.29777777777777775,
|
| 881 |
+
"step": 549
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 61.11,
|
| 885 |
+
"learning_rate": 0.00012310344827586205,
|
| 886 |
+
"loss": 0.2819,
|
| 887 |
+
"step": 550
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 62.0,
|
| 891 |
+
"eval_loss": 0.49692198634147644,
|
| 892 |
+
"eval_runtime": 2.7566,
|
| 893 |
+
"eval_samples_per_second": 6.167,
|
| 894 |
+
"eval_steps_per_second": 1.814,
|
| 895 |
+
"eval_wer": 0.2833333333333333,
|
| 896 |
+
"step": 558
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 62.22,
|
| 900 |
+
"learning_rate": 0.00011965517241379309,
|
| 901 |
+
"loss": 0.2819,
|
| 902 |
+
"step": 560
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 63.0,
|
| 906 |
+
"eval_loss": 0.6202179789543152,
|
| 907 |
+
"eval_runtime": 2.7859,
|
| 908 |
+
"eval_samples_per_second": 6.102,
|
| 909 |
+
"eval_steps_per_second": 1.795,
|
| 910 |
+
"eval_wer": 0.2788888888888889,
|
| 911 |
+
"step": 567
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 63.33,
|
| 915 |
+
"learning_rate": 0.00011620689655172413,
|
| 916 |
+
"loss": 0.2889,
|
| 917 |
+
"step": 570
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 64.0,
|
| 921 |
+
"eval_loss": 0.39546066522598267,
|
| 922 |
+
"eval_runtime": 2.7637,
|
| 923 |
+
"eval_samples_per_second": 6.151,
|
| 924 |
+
"eval_steps_per_second": 1.809,
|
| 925 |
+
"eval_wer": 0.2733333333333333,
|
| 926 |
+
"step": 576
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 64.44,
|
| 930 |
+
"learning_rate": 0.00011275862068965516,
|
| 931 |
+
"loss": 0.2515,
|
| 932 |
+
"step": 580
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 65.0,
|
| 936 |
+
"eval_loss": 0.38055384159088135,
|
| 937 |
+
"eval_runtime": 2.7537,
|
| 938 |
+
"eval_samples_per_second": 6.173,
|
| 939 |
+
"eval_steps_per_second": 1.816,
|
| 940 |
+
"eval_wer": 0.26555555555555554,
|
| 941 |
+
"step": 585
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 65.56,
|
| 945 |
+
"learning_rate": 0.0001093103448275862,
|
| 946 |
+
"loss": 0.2468,
|
| 947 |
+
"step": 590
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 66.0,
|
| 951 |
+
"eval_loss": 0.3472989499568939,
|
| 952 |
+
"eval_runtime": 2.8011,
|
| 953 |
+
"eval_samples_per_second": 6.069,
|
| 954 |
+
"eval_steps_per_second": 1.785,
|
| 955 |
+
"eval_wer": 0.2722222222222222,
|
| 956 |
+
"step": 594
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 66.67,
|
| 960 |
+
"learning_rate": 0.00010586206896551723,
|
| 961 |
+
"loss": 0.2557,
|
| 962 |
+
"step": 600
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 67.0,
|
| 966 |
+
"eval_loss": 0.417023628950119,
|
| 967 |
+
"eval_runtime": 2.7867,
|
| 968 |
+
"eval_samples_per_second": 6.1,
|
| 969 |
+
"eval_steps_per_second": 1.794,
|
| 970 |
+
"eval_wer": 0.2722222222222222,
|
| 971 |
+
"step": 603
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 67.78,
|
| 975 |
+
"learning_rate": 0.00010241379310344827,
|
| 976 |
+
"loss": 0.2477,
|
| 977 |
+
"step": 610
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 68.0,
|
| 981 |
+
"eval_loss": 0.4748758375644684,
|
| 982 |
+
"eval_runtime": 2.7749,
|
| 983 |
+
"eval_samples_per_second": 6.126,
|
| 984 |
+
"eval_steps_per_second": 1.802,
|
| 985 |
+
"eval_wer": 0.2677777777777778,
|
| 986 |
+
"step": 612
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 68.89,
|
| 990 |
+
"learning_rate": 9.89655172413793e-05,
|
| 991 |
+
"loss": 0.2965,
|
| 992 |
+
"step": 620
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 69.0,
|
| 996 |
+
"eval_loss": 0.438679039478302,
|
| 997 |
+
"eval_runtime": 2.7924,
|
| 998 |
+
"eval_samples_per_second": 6.088,
|
| 999 |
+
"eval_steps_per_second": 1.791,
|
| 1000 |
+
"eval_wer": 0.2611111111111111,
|
| 1001 |
+
"step": 621
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 70.0,
|
| 1005 |
+
"learning_rate": 9.551724137931034e-05,
|
| 1006 |
+
"loss": 0.2606,
|
| 1007 |
+
"step": 630
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 70.0,
|
| 1011 |
+
"eval_loss": 0.45858699083328247,
|
| 1012 |
+
"eval_runtime": 2.7888,
|
| 1013 |
+
"eval_samples_per_second": 6.096,
|
| 1014 |
+
"eval_steps_per_second": 1.793,
|
| 1015 |
+
"eval_wer": 0.26555555555555554,
|
| 1016 |
+
"step": 630
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 71.0,
|
| 1020 |
+
"eval_loss": 0.5755282044410706,
|
| 1021 |
+
"eval_runtime": 2.7561,
|
| 1022 |
+
"eval_samples_per_second": 6.168,
|
| 1023 |
+
"eval_steps_per_second": 1.814,
|
| 1024 |
+
"eval_wer": 0.2733333333333333,
|
| 1025 |
+
"step": 639
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 71.11,
|
| 1029 |
+
"learning_rate": 9.206896551724137e-05,
|
| 1030 |
+
"loss": 0.2442,
|
| 1031 |
+
"step": 640
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 72.0,
|
| 1035 |
+
"eval_loss": 0.5582060217857361,
|
| 1036 |
+
"eval_runtime": 2.7794,
|
| 1037 |
+
"eval_samples_per_second": 6.116,
|
| 1038 |
+
"eval_steps_per_second": 1.799,
|
| 1039 |
+
"eval_wer": 0.26555555555555554,
|
| 1040 |
+
"step": 648
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 72.22,
|
| 1044 |
+
"learning_rate": 8.862068965517241e-05,
|
| 1045 |
+
"loss": 0.347,
|
| 1046 |
+
"step": 650
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 73.0,
|
| 1050 |
+
"eval_loss": 0.38965609669685364,
|
| 1051 |
+
"eval_runtime": 2.7716,
|
| 1052 |
+
"eval_samples_per_second": 6.134,
|
| 1053 |
+
"eval_steps_per_second": 1.804,
|
| 1054 |
+
"eval_wer": 0.27111111111111114,
|
| 1055 |
+
"step": 657
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 73.33,
|
| 1059 |
+
"learning_rate": 8.517241379310344e-05,
|
| 1060 |
+
"loss": 0.2444,
|
| 1061 |
+
"step": 660
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 74.0,
|
| 1065 |
+
"eval_loss": 0.33690622448921204,
|
| 1066 |
+
"eval_runtime": 2.7566,
|
| 1067 |
+
"eval_samples_per_second": 6.167,
|
| 1068 |
+
"eval_steps_per_second": 1.814,
|
| 1069 |
+
"eval_wer": 0.25333333333333335,
|
| 1070 |
+
"step": 666
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 74.44,
|
| 1074 |
+
"learning_rate": 8.172413793103448e-05,
|
| 1075 |
+
"loss": 0.2811,
|
| 1076 |
+
"step": 670
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 75.0,
|
| 1080 |
+
"eval_loss": 0.34874993562698364,
|
| 1081 |
+
"eval_runtime": 2.7479,
|
| 1082 |
+
"eval_samples_per_second": 6.186,
|
| 1083 |
+
"eval_steps_per_second": 1.82,
|
| 1084 |
+
"eval_wer": 0.2577777777777778,
|
| 1085 |
+
"step": 675
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 75.56,
|
| 1089 |
+
"learning_rate": 7.827586206896551e-05,
|
| 1090 |
+
"loss": 0.24,
|
| 1091 |
+
"step": 680
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 76.0,
|
| 1095 |
+
"eval_loss": 0.3692302107810974,
|
| 1096 |
+
"eval_runtime": 2.785,
|
| 1097 |
+
"eval_samples_per_second": 6.104,
|
| 1098 |
+
"eval_steps_per_second": 1.795,
|
| 1099 |
+
"eval_wer": 0.2588888888888889,
|
| 1100 |
+
"step": 684
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 76.67,
|
| 1104 |
+
"learning_rate": 7.482758620689654e-05,
|
| 1105 |
+
"loss": 0.2466,
|
| 1106 |
+
"step": 690
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 77.0,
|
| 1110 |
+
"eval_loss": 0.45672333240509033,
|
| 1111 |
+
"eval_runtime": 2.7533,
|
| 1112 |
+
"eval_samples_per_second": 6.174,
|
| 1113 |
+
"eval_steps_per_second": 1.816,
|
| 1114 |
+
"eval_wer": 0.2577777777777778,
|
| 1115 |
+
"step": 693
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 77.78,
|
| 1119 |
+
"learning_rate": 7.137931034482758e-05,
|
| 1120 |
+
"loss": 0.2769,
|
| 1121 |
+
"step": 700
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 78.0,
|
| 1125 |
+
"eval_loss": 0.40405967831611633,
|
| 1126 |
+
"eval_runtime": 2.7964,
|
| 1127 |
+
"eval_samples_per_second": 6.079,
|
| 1128 |
+
"eval_steps_per_second": 1.788,
|
| 1129 |
+
"eval_wer": 0.2633333333333333,
|
| 1130 |
+
"step": 702
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 78.89,
|
| 1134 |
+
"learning_rate": 6.79310344827586e-05,
|
| 1135 |
+
"loss": 0.2464,
|
| 1136 |
+
"step": 710
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 79.0,
|
| 1140 |
+
"eval_loss": 0.38128018379211426,
|
| 1141 |
+
"eval_runtime": 2.7812,
|
| 1142 |
+
"eval_samples_per_second": 6.113,
|
| 1143 |
+
"eval_steps_per_second": 1.798,
|
| 1144 |
+
"eval_wer": 0.26222222222222225,
|
| 1145 |
+
"step": 711
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 80.0,
|
| 1149 |
+
"learning_rate": 6.448275862068965e-05,
|
| 1150 |
+
"loss": 0.2791,
|
| 1151 |
+
"step": 720
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 80.0,
|
| 1155 |
+
"eval_loss": 0.3990322947502136,
|
| 1156 |
+
"eval_runtime": 2.7516,
|
| 1157 |
+
"eval_samples_per_second": 6.178,
|
| 1158 |
+
"eval_steps_per_second": 1.817,
|
| 1159 |
+
"eval_wer": 0.25555555555555554,
|
| 1160 |
+
"step": 720
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 81.0,
|
| 1164 |
+
"eval_loss": 0.39965325593948364,
|
| 1165 |
+
"eval_runtime": 2.7649,
|
| 1166 |
+
"eval_samples_per_second": 6.149,
|
| 1167 |
+
"eval_steps_per_second": 1.808,
|
| 1168 |
+
"eval_wer": 0.24888888888888888,
|
| 1169 |
+
"step": 729
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 81.11,
|
| 1173 |
+
"learning_rate": 6.103448275862068e-05,
|
| 1174 |
+
"loss": 0.2365,
|
| 1175 |
+
"step": 730
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 82.0,
|
| 1179 |
+
"eval_loss": 0.4537028968334198,
|
| 1180 |
+
"eval_runtime": 2.7885,
|
| 1181 |
+
"eval_samples_per_second": 6.097,
|
| 1182 |
+
"eval_steps_per_second": 1.793,
|
| 1183 |
+
"eval_wer": 0.25333333333333335,
|
| 1184 |
+
"step": 738
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 82.22,
|
| 1188 |
+
"learning_rate": 5.758620689655172e-05,
|
| 1189 |
+
"loss": 0.2693,
|
| 1190 |
+
"step": 740
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 83.0,
|
| 1194 |
+
"eval_loss": 0.5943002104759216,
|
| 1195 |
+
"eval_runtime": 2.8023,
|
| 1196 |
+
"eval_samples_per_second": 6.067,
|
| 1197 |
+
"eval_steps_per_second": 1.784,
|
| 1198 |
+
"eval_wer": 0.2611111111111111,
|
| 1199 |
+
"step": 747
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 83.33,
|
| 1203 |
+
"learning_rate": 5.413793103448275e-05,
|
| 1204 |
+
"loss": 0.2285,
|
| 1205 |
+
"step": 750
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 84.0,
|
| 1209 |
+
"eval_loss": 0.5804929733276367,
|
| 1210 |
+
"eval_runtime": 2.7598,
|
| 1211 |
+
"eval_samples_per_second": 6.16,
|
| 1212 |
+
"eval_steps_per_second": 1.812,
|
| 1213 |
+
"eval_wer": 0.26555555555555554,
|
| 1214 |
+
"step": 756
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 84.44,
|
| 1218 |
+
"learning_rate": 5.068965517241379e-05,
|
| 1219 |
+
"loss": 0.2468,
|
| 1220 |
+
"step": 760
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 85.0,
|
| 1224 |
+
"eval_loss": 0.5608753561973572,
|
| 1225 |
+
"eval_runtime": 2.7731,
|
| 1226 |
+
"eval_samples_per_second": 6.13,
|
| 1227 |
+
"eval_steps_per_second": 1.803,
|
| 1228 |
+
"eval_wer": 0.26555555555555554,
|
| 1229 |
+
"step": 765
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 85.56,
|
| 1233 |
+
"learning_rate": 4.724137931034482e-05,
|
| 1234 |
+
"loss": 0.2226,
|
| 1235 |
+
"step": 770
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 86.0,
|
| 1239 |
+
"eval_loss": 0.59482342004776,
|
| 1240 |
+
"eval_runtime": 2.7726,
|
| 1241 |
+
"eval_samples_per_second": 6.131,
|
| 1242 |
+
"eval_steps_per_second": 1.803,
|
| 1243 |
+
"eval_wer": 0.26666666666666666,
|
| 1244 |
+
"step": 774
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 86.67,
|
| 1248 |
+
"learning_rate": 4.379310344827586e-05,
|
| 1249 |
+
"loss": 0.2419,
|
| 1250 |
+
"step": 780
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 87.0,
|
| 1254 |
+
"eval_loss": 0.5909682512283325,
|
| 1255 |
+
"eval_runtime": 2.7879,
|
| 1256 |
+
"eval_samples_per_second": 6.098,
|
| 1257 |
+
"eval_steps_per_second": 1.793,
|
| 1258 |
+
"eval_wer": 0.2544444444444444,
|
| 1259 |
+
"step": 783
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 87.78,
|
| 1263 |
+
"learning_rate": 4.034482758620689e-05,
|
| 1264 |
+
"loss": 0.2254,
|
| 1265 |
+
"step": 790
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 88.0,
|
| 1269 |
+
"eval_loss": 0.5740683078765869,
|
| 1270 |
+
"eval_runtime": 2.7572,
|
| 1271 |
+
"eval_samples_per_second": 6.166,
|
| 1272 |
+
"eval_steps_per_second": 1.813,
|
| 1273 |
+
"eval_wer": 0.26,
|
| 1274 |
+
"step": 792
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 88.89,
|
| 1278 |
+
"learning_rate": 3.689655172413793e-05,
|
| 1279 |
+
"loss": 0.2083,
|
| 1280 |
+
"step": 800
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 89.0,
|
| 1284 |
+
"eval_loss": 0.498391717672348,
|
| 1285 |
+
"eval_runtime": 2.7579,
|
| 1286 |
+
"eval_samples_per_second": 6.164,
|
| 1287 |
+
"eval_steps_per_second": 1.813,
|
| 1288 |
+
"eval_wer": 0.2611111111111111,
|
| 1289 |
+
"step": 801
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 90.0,
|
| 1293 |
+
"learning_rate": 3.344827586206896e-05,
|
| 1294 |
+
"loss": 0.2318,
|
| 1295 |
+
"step": 810
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 90.0,
|
| 1299 |
+
"eval_loss": 0.5093002915382385,
|
| 1300 |
+
"eval_runtime": 2.7728,
|
| 1301 |
+
"eval_samples_per_second": 6.131,
|
| 1302 |
+
"eval_steps_per_second": 1.803,
|
| 1303 |
+
"eval_wer": 0.26,
|
| 1304 |
+
"step": 810
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 91.0,
|
| 1308 |
+
"eval_loss": 0.5284357070922852,
|
| 1309 |
+
"eval_runtime": 2.7447,
|
| 1310 |
+
"eval_samples_per_second": 6.194,
|
| 1311 |
+
"eval_steps_per_second": 1.822,
|
| 1312 |
+
"eval_wer": 0.2633333333333333,
|
| 1313 |
+
"step": 819
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 91.11,
|
| 1317 |
+
"learning_rate": 2.9999999999999997e-05,
|
| 1318 |
+
"loss": 0.2458,
|
| 1319 |
+
"step": 820
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 92.0,
|
| 1323 |
+
"eval_loss": 0.48846206068992615,
|
| 1324 |
+
"eval_runtime": 2.7457,
|
| 1325 |
+
"eval_samples_per_second": 6.192,
|
| 1326 |
+
"eval_steps_per_second": 1.821,
|
| 1327 |
+
"eval_wer": 0.26555555555555554,
|
| 1328 |
+
"step": 828
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 92.22,
|
| 1332 |
+
"learning_rate": 2.6551724137931032e-05,
|
| 1333 |
+
"loss": 0.2394,
|
| 1334 |
+
"step": 830
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 93.0,
|
| 1338 |
+
"eval_loss": 0.4817904829978943,
|
| 1339 |
+
"eval_runtime": 2.7858,
|
| 1340 |
+
"eval_samples_per_second": 6.102,
|
| 1341 |
+
"eval_steps_per_second": 1.795,
|
| 1342 |
+
"eval_wer": 0.26222222222222225,
|
| 1343 |
+
"step": 837
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 93.33,
|
| 1347 |
+
"learning_rate": 2.3103448275862067e-05,
|
| 1348 |
+
"loss": 0.2018,
|
| 1349 |
+
"step": 840
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 94.0,
|
| 1353 |
+
"eval_loss": 0.5037254691123962,
|
| 1354 |
+
"eval_runtime": 2.7345,
|
| 1355 |
+
"eval_samples_per_second": 6.217,
|
| 1356 |
+
"eval_steps_per_second": 1.829,
|
| 1357 |
+
"eval_wer": 0.26,
|
| 1358 |
+
"step": 846
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 94.44,
|
| 1362 |
+
"learning_rate": 1.9655172413793102e-05,
|
| 1363 |
+
"loss": 0.235,
|
| 1364 |
+
"step": 850
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 95.0,
|
| 1368 |
+
"eval_loss": 0.5010991096496582,
|
| 1369 |
+
"eval_runtime": 2.8024,
|
| 1370 |
+
"eval_samples_per_second": 6.066,
|
| 1371 |
+
"eval_steps_per_second": 1.784,
|
| 1372 |
+
"eval_wer": 0.2577777777777778,
|
| 1373 |
+
"step": 855
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 95.56,
|
| 1377 |
+
"learning_rate": 1.6206896551724137e-05,
|
| 1378 |
+
"loss": 0.2252,
|
| 1379 |
+
"step": 860
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 96.0,
|
| 1383 |
+
"eval_loss": 0.49311307072639465,
|
| 1384 |
+
"eval_runtime": 2.7705,
|
| 1385 |
+
"eval_samples_per_second": 6.136,
|
| 1386 |
+
"eval_steps_per_second": 1.805,
|
| 1387 |
+
"eval_wer": 0.2611111111111111,
|
| 1388 |
+
"step": 864
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 96.67,
|
| 1392 |
+
"learning_rate": 1.275862068965517e-05,
|
| 1393 |
+
"loss": 0.2147,
|
| 1394 |
+
"step": 870
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 97.0,
|
| 1398 |
+
"eval_loss": 0.4880674481391907,
|
| 1399 |
+
"eval_runtime": 2.7947,
|
| 1400 |
+
"eval_samples_per_second": 6.083,
|
| 1401 |
+
"eval_steps_per_second": 1.789,
|
| 1402 |
+
"eval_wer": 0.2588888888888889,
|
| 1403 |
+
"step": 873
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 97.78,
|
| 1407 |
+
"learning_rate": 9.310344827586206e-06,
|
| 1408 |
+
"loss": 0.2227,
|
| 1409 |
+
"step": 880
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 98.0,
|
| 1413 |
+
"eval_loss": 0.49562954902648926,
|
| 1414 |
+
"eval_runtime": 2.7533,
|
| 1415 |
+
"eval_samples_per_second": 6.174,
|
| 1416 |
+
"eval_steps_per_second": 1.816,
|
| 1417 |
+
"eval_wer": 0.2588888888888889,
|
| 1418 |
+
"step": 882
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 98.89,
|
| 1422 |
+
"learning_rate": 5.862068965517241e-06,
|
| 1423 |
+
"loss": 0.2168,
|
| 1424 |
+
"step": 890
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 99.0,
|
| 1428 |
+
"eval_loss": 0.5096976161003113,
|
| 1429 |
+
"eval_runtime": 2.7653,
|
| 1430 |
+
"eval_samples_per_second": 6.148,
|
| 1431 |
+
"eval_steps_per_second": 1.808,
|
| 1432 |
+
"eval_wer": 0.2588888888888889,
|
| 1433 |
+
"step": 891
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 100.0,
|
| 1437 |
+
"learning_rate": 2.413793103448276e-06,
|
| 1438 |
+
"loss": 0.2282,
|
| 1439 |
+
"step": 900
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 100.0,
|
| 1443 |
+
"eval_loss": 0.5173905491828918,
|
| 1444 |
+
"eval_runtime": 2.7832,
|
| 1445 |
+
"eval_samples_per_second": 6.108,
|
| 1446 |
+
"eval_steps_per_second": 1.797,
|
| 1447 |
+
"eval_wer": 0.26,
|
| 1448 |
+
"step": 900
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 100.0,
|
| 1452 |
+
"step": 900,
|
| 1453 |
+
"total_flos": 1.389987159899058e+18,
|
| 1454 |
+
"train_loss": 0.7617763585514492,
|
| 1455 |
+
"train_runtime": 3519.9031,
|
| 1456 |
+
"train_samples_per_second": 4.006,
|
| 1457 |
+
"train_steps_per_second": 0.256
|
| 1458 |
+
}
|
| 1459 |
+
],
|
| 1460 |
+
"max_steps": 900,
|
| 1461 |
+
"num_train_epochs": 100,
|
| 1462 |
+
"total_flos": 1.389987159899058e+18,
|
| 1463 |
+
"trial_name": null,
|
| 1464 |
+
"trial_params": null
|
| 1465 |
+
}
|