End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Nov22_06-22-32_535bd66b48f0/events.out.tfevents.1669102571.535bd66b48f0.6159.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +2245 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 99.98,
|
| 3 |
+
"eval_loss": 0.5264096260070801,
|
| 4 |
+
"eval_runtime": 2.4548,
|
| 5 |
+
"eval_samples": 17,
|
| 6 |
+
"eval_samples_per_second": 6.925,
|
| 7 |
+
"eval_steps_per_second": 2.037,
|
| 8 |
+
"eval_wer": 0.3635280095351609,
|
| 9 |
+
"train_loss": 0.5098017852956599,
|
| 10 |
+
"train_runtime": 3993.9176,
|
| 11 |
+
"train_samples": 179,
|
| 12 |
+
"train_samples_per_second": 4.482,
|
| 13 |
+
"train_steps_per_second": 0.551
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 99.98,
|
| 3 |
+
"eval_loss": 0.5264096260070801,
|
| 4 |
+
"eval_runtime": 2.4548,
|
| 5 |
+
"eval_samples": 17,
|
| 6 |
+
"eval_samples_per_second": 6.925,
|
| 7 |
+
"eval_steps_per_second": 2.037,
|
| 8 |
+
"eval_wer": 0.3635280095351609
|
| 9 |
+
}
|
runs/Nov22_06-22-32_535bd66b48f0/events.out.tfevents.1669102571.535bd66b48f0.6159.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6714881e662e21aceb23dd39cbded0f44123b157e4e817c97aae7b0f3d45b462
|
| 3 |
+
size 358
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 99.98,
|
| 3 |
+
"train_loss": 0.5098017852956599,
|
| 4 |
+
"train_runtime": 3993.9176,
|
| 5 |
+
"train_samples": 179,
|
| 6 |
+
"train_samples_per_second": 4.482,
|
| 7 |
+
"train_steps_per_second": 0.551
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2245 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5264096260070801,
|
| 3 |
+
"best_model_checkpoint": "ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-v2/checkpoint-1188",
|
| 4 |
+
"epoch": 99.97777777777777,
|
| 5 |
+
"global_step": 2200,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.44,
|
| 12 |
+
"learning_rate": 0.00024,
|
| 13 |
+
"loss": 12.475,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.89,
|
| 18 |
+
"learning_rate": 0.00039890410958904113,
|
| 19 |
+
"loss": 4.6468,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.98,
|
| 24 |
+
"eval_loss": 3.2315070629119873,
|
| 25 |
+
"eval_runtime": 2.3722,
|
| 26 |
+
"eval_samples_per_second": 7.166,
|
| 27 |
+
"eval_steps_per_second": 2.108,
|
| 28 |
+
"eval_wer": 1.0,
|
| 29 |
+
"step": 22
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.36,
|
| 33 |
+
"learning_rate": 0.00039707762557077624,
|
| 34 |
+
"loss": 2.2321,
|
| 35 |
+
"step": 30
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.8,
|
| 39 |
+
"learning_rate": 0.0003952511415525114,
|
| 40 |
+
"loss": 1.5745,
|
| 41 |
+
"step": 40
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 1.98,
|
| 45 |
+
"eval_loss": 3.1603267192840576,
|
| 46 |
+
"eval_runtime": 2.5264,
|
| 47 |
+
"eval_samples_per_second": 6.729,
|
| 48 |
+
"eval_steps_per_second": 1.979,
|
| 49 |
+
"eval_wer": 1.0,
|
| 50 |
+
"step": 44
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 2.27,
|
| 54 |
+
"learning_rate": 0.0003934246575342466,
|
| 55 |
+
"loss": 1.6456,
|
| 56 |
+
"step": 50
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.71,
|
| 60 |
+
"learning_rate": 0.00039159817351598175,
|
| 61 |
+
"loss": 1.465,
|
| 62 |
+
"step": 60
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.98,
|
| 66 |
+
"eval_loss": 2.2551496028900146,
|
| 67 |
+
"eval_runtime": 2.4489,
|
| 68 |
+
"eval_samples_per_second": 6.942,
|
| 69 |
+
"eval_steps_per_second": 2.042,
|
| 70 |
+
"eval_wer": 1.0,
|
| 71 |
+
"step": 66
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 3.18,
|
| 75 |
+
"learning_rate": 0.0003897716894977169,
|
| 76 |
+
"loss": 1.3799,
|
| 77 |
+
"step": 70
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 3.62,
|
| 81 |
+
"learning_rate": 0.0003879452054794521,
|
| 82 |
+
"loss": 1.3168,
|
| 83 |
+
"step": 80
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 3.98,
|
| 87 |
+
"eval_loss": 1.8460932970046997,
|
| 88 |
+
"eval_runtime": 2.5217,
|
| 89 |
+
"eval_samples_per_second": 6.741,
|
| 90 |
+
"eval_steps_per_second": 1.983,
|
| 91 |
+
"eval_wer": 1.0,
|
| 92 |
+
"step": 88
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 4.09,
|
| 96 |
+
"learning_rate": 0.0003861187214611872,
|
| 97 |
+
"loss": 1.4043,
|
| 98 |
+
"step": 90
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 4.53,
|
| 102 |
+
"learning_rate": 0.0003842922374429224,
|
| 103 |
+
"loss": 1.2482,
|
| 104 |
+
"step": 100
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.98,
|
| 108 |
+
"learning_rate": 0.00038246575342465753,
|
| 109 |
+
"loss": 1.1359,
|
| 110 |
+
"step": 110
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 4.98,
|
| 114 |
+
"eval_loss": 1.4874340295791626,
|
| 115 |
+
"eval_runtime": 2.4675,
|
| 116 |
+
"eval_samples_per_second": 6.89,
|
| 117 |
+
"eval_steps_per_second": 2.026,
|
| 118 |
+
"eval_wer": 0.9797377830750894,
|
| 119 |
+
"step": 110
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 5.44,
|
| 123 |
+
"learning_rate": 0.0003806392694063927,
|
| 124 |
+
"loss": 1.085,
|
| 125 |
+
"step": 120
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 5.89,
|
| 129 |
+
"learning_rate": 0.00037881278538812787,
|
| 130 |
+
"loss": 0.9769,
|
| 131 |
+
"step": 130
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 5.98,
|
| 135 |
+
"eval_loss": 1.7358566522598267,
|
| 136 |
+
"eval_runtime": 2.4383,
|
| 137 |
+
"eval_samples_per_second": 6.972,
|
| 138 |
+
"eval_steps_per_second": 2.051,
|
| 139 |
+
"eval_wer": 0.5494636471990465,
|
| 140 |
+
"step": 132
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 6.36,
|
| 144 |
+
"learning_rate": 0.00037698630136986304,
|
| 145 |
+
"loss": 1.0217,
|
| 146 |
+
"step": 140
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 6.8,
|
| 150 |
+
"learning_rate": 0.00037515981735159815,
|
| 151 |
+
"loss": 0.9019,
|
| 152 |
+
"step": 150
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 6.98,
|
| 156 |
+
"eval_loss": 1.5833041667938232,
|
| 157 |
+
"eval_runtime": 2.5274,
|
| 158 |
+
"eval_samples_per_second": 6.726,
|
| 159 |
+
"eval_steps_per_second": 1.978,
|
| 160 |
+
"eval_wer": 0.5268176400476758,
|
| 161 |
+
"step": 154
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 7.27,
|
| 165 |
+
"learning_rate": 0.0003733333333333334,
|
| 166 |
+
"loss": 0.9973,
|
| 167 |
+
"step": 160
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 7.71,
|
| 171 |
+
"learning_rate": 0.0003715068493150685,
|
| 172 |
+
"loss": 0.8057,
|
| 173 |
+
"step": 170
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 7.98,
|
| 177 |
+
"eval_loss": 1.4891672134399414,
|
| 178 |
+
"eval_runtime": 2.5017,
|
| 179 |
+
"eval_samples_per_second": 6.795,
|
| 180 |
+
"eval_steps_per_second": 1.999,
|
| 181 |
+
"eval_wer": 0.5303933253873659,
|
| 182 |
+
"step": 176
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 8.18,
|
| 186 |
+
"learning_rate": 0.00036968036529680365,
|
| 187 |
+
"loss": 0.7626,
|
| 188 |
+
"step": 180
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 8.62,
|
| 192 |
+
"learning_rate": 0.0003678538812785388,
|
| 193 |
+
"loss": 1.0845,
|
| 194 |
+
"step": 190
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 8.98,
|
| 198 |
+
"eval_loss": 1.393895149230957,
|
| 199 |
+
"eval_runtime": 2.5045,
|
| 200 |
+
"eval_samples_per_second": 6.788,
|
| 201 |
+
"eval_steps_per_second": 1.996,
|
| 202 |
+
"eval_wer": 0.5196662693682956,
|
| 203 |
+
"step": 198
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 9.09,
|
| 207 |
+
"learning_rate": 0.000366027397260274,
|
| 208 |
+
"loss": 0.788,
|
| 209 |
+
"step": 200
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 9.53,
|
| 213 |
+
"learning_rate": 0.00036420091324200916,
|
| 214 |
+
"loss": 0.6903,
|
| 215 |
+
"step": 210
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 9.98,
|
| 219 |
+
"learning_rate": 0.0003623744292237443,
|
| 220 |
+
"loss": 0.7562,
|
| 221 |
+
"step": 220
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 9.98,
|
| 225 |
+
"eval_loss": 1.1237640380859375,
|
| 226 |
+
"eval_runtime": 2.4848,
|
| 227 |
+
"eval_samples_per_second": 6.842,
|
| 228 |
+
"eval_steps_per_second": 2.012,
|
| 229 |
+
"eval_wer": 0.5446960667461264,
|
| 230 |
+
"step": 220
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 10.44,
|
| 234 |
+
"learning_rate": 0.00036054794520547944,
|
| 235 |
+
"loss": 0.702,
|
| 236 |
+
"step": 230
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 10.89,
|
| 240 |
+
"learning_rate": 0.00035872146118721466,
|
| 241 |
+
"loss": 0.7259,
|
| 242 |
+
"step": 240
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 10.98,
|
| 246 |
+
"eval_loss": 1.2935717105865479,
|
| 247 |
+
"eval_runtime": 2.35,
|
| 248 |
+
"eval_samples_per_second": 7.234,
|
| 249 |
+
"eval_steps_per_second": 2.128,
|
| 250 |
+
"eval_wer": 0.5005959475566151,
|
| 251 |
+
"step": 242
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 11.36,
|
| 255 |
+
"learning_rate": 0.0003568949771689498,
|
| 256 |
+
"loss": 0.6347,
|
| 257 |
+
"step": 250
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 11.8,
|
| 261 |
+
"learning_rate": 0.00035506849315068494,
|
| 262 |
+
"loss": 0.7318,
|
| 263 |
+
"step": 260
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 11.98,
|
| 267 |
+
"eval_loss": 1.2763104438781738,
|
| 268 |
+
"eval_runtime": 2.3731,
|
| 269 |
+
"eval_samples_per_second": 7.164,
|
| 270 |
+
"eval_steps_per_second": 2.107,
|
| 271 |
+
"eval_wer": 0.466030989272944,
|
| 272 |
+
"step": 264
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 12.27,
|
| 276 |
+
"learning_rate": 0.0003532420091324201,
|
| 277 |
+
"loss": 0.8421,
|
| 278 |
+
"step": 270
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 12.71,
|
| 282 |
+
"learning_rate": 0.0003514155251141553,
|
| 283 |
+
"loss": 0.6452,
|
| 284 |
+
"step": 280
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 12.98,
|
| 288 |
+
"eval_loss": 1.2947018146514893,
|
| 289 |
+
"eval_runtime": 2.3625,
|
| 290 |
+
"eval_samples_per_second": 7.196,
|
| 291 |
+
"eval_steps_per_second": 2.116,
|
| 292 |
+
"eval_wer": 0.47794994040524436,
|
| 293 |
+
"step": 286
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 13.18,
|
| 297 |
+
"learning_rate": 0.0003495890410958904,
|
| 298 |
+
"loss": 0.663,
|
| 299 |
+
"step": 290
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 13.62,
|
| 303 |
+
"learning_rate": 0.0003477625570776256,
|
| 304 |
+
"loss": 0.6353,
|
| 305 |
+
"step": 300
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 13.98,
|
| 309 |
+
"eval_loss": 1.1925369501113892,
|
| 310 |
+
"eval_runtime": 2.3586,
|
| 311 |
+
"eval_samples_per_second": 7.208,
|
| 312 |
+
"eval_steps_per_second": 2.12,
|
| 313 |
+
"eval_wer": 0.45172824791418353,
|
| 314 |
+
"step": 308
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 14.09,
|
| 318 |
+
"learning_rate": 0.00034593607305936073,
|
| 319 |
+
"loss": 0.6161,
|
| 320 |
+
"step": 310
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 14.53,
|
| 324 |
+
"learning_rate": 0.0003441095890410959,
|
| 325 |
+
"loss": 0.657,
|
| 326 |
+
"step": 320
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 14.98,
|
| 330 |
+
"learning_rate": 0.00034228310502283106,
|
| 331 |
+
"loss": 0.6463,
|
| 332 |
+
"step": 330
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 14.98,
|
| 336 |
+
"eval_loss": 0.8667492866516113,
|
| 337 |
+
"eval_runtime": 2.3648,
|
| 338 |
+
"eval_samples_per_second": 7.189,
|
| 339 |
+
"eval_steps_per_second": 2.114,
|
| 340 |
+
"eval_wer": 0.4100119189511323,
|
| 341 |
+
"step": 330
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 15.44,
|
| 345 |
+
"learning_rate": 0.00034045662100456623,
|
| 346 |
+
"loss": 0.6894,
|
| 347 |
+
"step": 340
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 15.89,
|
| 351 |
+
"learning_rate": 0.00033863013698630135,
|
| 352 |
+
"loss": 0.5381,
|
| 353 |
+
"step": 350
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 15.98,
|
| 357 |
+
"eval_loss": 1.1242961883544922,
|
| 358 |
+
"eval_runtime": 2.3712,
|
| 359 |
+
"eval_samples_per_second": 7.169,
|
| 360 |
+
"eval_steps_per_second": 2.109,
|
| 361 |
+
"eval_wer": 0.3909415971394517,
|
| 362 |
+
"step": 352
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 16.36,
|
| 366 |
+
"learning_rate": 0.00033680365296803657,
|
| 367 |
+
"loss": 0.6061,
|
| 368 |
+
"step": 360
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 16.8,
|
| 372 |
+
"learning_rate": 0.0003349771689497717,
|
| 373 |
+
"loss": 0.5637,
|
| 374 |
+
"step": 370
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 16.98,
|
| 378 |
+
"eval_loss": 0.8682847023010254,
|
| 379 |
+
"eval_runtime": 2.3793,
|
| 380 |
+
"eval_samples_per_second": 7.145,
|
| 381 |
+
"eval_steps_per_second": 2.101,
|
| 382 |
+
"eval_wer": 0.37544696066746125,
|
| 383 |
+
"step": 374
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 17.27,
|
| 387 |
+
"learning_rate": 0.00033315068493150685,
|
| 388 |
+
"loss": 0.5715,
|
| 389 |
+
"step": 380
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 17.71,
|
| 393 |
+
"learning_rate": 0.000331324200913242,
|
| 394 |
+
"loss": 0.6149,
|
| 395 |
+
"step": 390
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 17.98,
|
| 399 |
+
"eval_loss": 1.1040120124816895,
|
| 400 |
+
"eval_runtime": 2.3707,
|
| 401 |
+
"eval_samples_per_second": 7.171,
|
| 402 |
+
"eval_steps_per_second": 2.109,
|
| 403 |
+
"eval_wer": 0.3730631704410012,
|
| 404 |
+
"step": 396
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 18.18,
|
| 408 |
+
"learning_rate": 0.0003294977168949772,
|
| 409 |
+
"loss": 0.5399,
|
| 410 |
+
"step": 400
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 18.62,
|
| 414 |
+
"learning_rate": 0.00032767123287671235,
|
| 415 |
+
"loss": 0.6138,
|
| 416 |
+
"step": 410
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 18.98,
|
| 420 |
+
"eval_loss": 1.1067866086959839,
|
| 421 |
+
"eval_runtime": 2.3709,
|
| 422 |
+
"eval_samples_per_second": 7.17,
|
| 423 |
+
"eval_steps_per_second": 2.109,
|
| 424 |
+
"eval_wer": 0.38498212157330153,
|
| 425 |
+
"step": 418
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 19.09,
|
| 429 |
+
"learning_rate": 0.0003258447488584475,
|
| 430 |
+
"loss": 0.5364,
|
| 431 |
+
"step": 420
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 19.53,
|
| 435 |
+
"learning_rate": 0.00032401826484018264,
|
| 436 |
+
"loss": 0.4998,
|
| 437 |
+
"step": 430
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 19.98,
|
| 441 |
+
"learning_rate": 0.00032219178082191786,
|
| 442 |
+
"loss": 0.7381,
|
| 443 |
+
"step": 440
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 19.98,
|
| 447 |
+
"eval_loss": 0.9203162789344788,
|
| 448 |
+
"eval_runtime": 2.3697,
|
| 449 |
+
"eval_samples_per_second": 7.174,
|
| 450 |
+
"eval_steps_per_second": 2.11,
|
| 451 |
+
"eval_wer": 0.36233611442193087,
|
| 452 |
+
"step": 440
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 20.44,
|
| 456 |
+
"learning_rate": 0.00032036529680365297,
|
| 457 |
+
"loss": 0.5755,
|
| 458 |
+
"step": 450
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 20.89,
|
| 462 |
+
"learning_rate": 0.00031853881278538814,
|
| 463 |
+
"loss": 0.5064,
|
| 464 |
+
"step": 460
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 20.98,
|
| 468 |
+
"eval_loss": 0.8806262016296387,
|
| 469 |
+
"eval_runtime": 2.3863,
|
| 470 |
+
"eval_samples_per_second": 7.124,
|
| 471 |
+
"eval_steps_per_second": 2.095,
|
| 472 |
+
"eval_wer": 0.3539928486293206,
|
| 473 |
+
"step": 462
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 21.36,
|
| 477 |
+
"learning_rate": 0.0003167123287671233,
|
| 478 |
+
"loss": 0.5148,
|
| 479 |
+
"step": 470
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 21.8,
|
| 483 |
+
"learning_rate": 0.0003148858447488585,
|
| 484 |
+
"loss": 0.4731,
|
| 485 |
+
"step": 480
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 21.98,
|
| 489 |
+
"eval_loss": 0.7259242534637451,
|
| 490 |
+
"eval_runtime": 2.3798,
|
| 491 |
+
"eval_samples_per_second": 7.144,
|
| 492 |
+
"eval_steps_per_second": 2.101,
|
| 493 |
+
"eval_wer": 0.36233611442193087,
|
| 494 |
+
"step": 484
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 22.27,
|
| 498 |
+
"learning_rate": 0.0003130593607305936,
|
| 499 |
+
"loss": 0.5034,
|
| 500 |
+
"step": 490
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 22.71,
|
| 504 |
+
"learning_rate": 0.0003112328767123288,
|
| 505 |
+
"loss": 0.5232,
|
| 506 |
+
"step": 500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 22.98,
|
| 510 |
+
"eval_loss": 0.7934766411781311,
|
| 511 |
+
"eval_runtime": 2.3715,
|
| 512 |
+
"eval_samples_per_second": 7.168,
|
| 513 |
+
"eval_steps_per_second": 2.108,
|
| 514 |
+
"eval_wer": 0.35160905840286055,
|
| 515 |
+
"step": 506
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 23.18,
|
| 519 |
+
"learning_rate": 0.0003094063926940639,
|
| 520 |
+
"loss": 0.4923,
|
| 521 |
+
"step": 510
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 23.62,
|
| 525 |
+
"learning_rate": 0.0003075799086757991,
|
| 526 |
+
"loss": 0.4689,
|
| 527 |
+
"step": 520
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 23.98,
|
| 531 |
+
"eval_loss": 0.777065634727478,
|
| 532 |
+
"eval_runtime": 2.3797,
|
| 533 |
+
"eval_samples_per_second": 7.144,
|
| 534 |
+
"eval_steps_per_second": 2.101,
|
| 535 |
+
"eval_wer": 0.3539928486293206,
|
| 536 |
+
"step": 528
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 24.09,
|
| 540 |
+
"learning_rate": 0.00030575342465753426,
|
| 541 |
+
"loss": 0.4745,
|
| 542 |
+
"step": 530
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 24.53,
|
| 546 |
+
"learning_rate": 0.00030392694063926943,
|
| 547 |
+
"loss": 0.4817,
|
| 548 |
+
"step": 540
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 24.98,
|
| 552 |
+
"learning_rate": 0.00030210045662100454,
|
| 553 |
+
"loss": 0.4902,
|
| 554 |
+
"step": 550
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 24.98,
|
| 558 |
+
"eval_loss": 0.6896762847900391,
|
| 559 |
+
"eval_runtime": 2.3739,
|
| 560 |
+
"eval_samples_per_second": 7.161,
|
| 561 |
+
"eval_steps_per_second": 2.106,
|
| 562 |
+
"eval_wer": 0.3909415971394517,
|
| 563 |
+
"step": 550
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 25.44,
|
| 567 |
+
"learning_rate": 0.00030027397260273976,
|
| 568 |
+
"loss": 0.5525,
|
| 569 |
+
"step": 560
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 25.89,
|
| 573 |
+
"learning_rate": 0.0002984474885844749,
|
| 574 |
+
"loss": 0.4079,
|
| 575 |
+
"step": 570
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 25.98,
|
| 579 |
+
"eval_loss": 0.8030110597610474,
|
| 580 |
+
"eval_runtime": 2.3676,
|
| 581 |
+
"eval_samples_per_second": 7.18,
|
| 582 |
+
"eval_steps_per_second": 2.112,
|
| 583 |
+
"eval_wer": 0.35518474374255066,
|
| 584 |
+
"step": 572
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 26.36,
|
| 588 |
+
"learning_rate": 0.00029662100456621005,
|
| 589 |
+
"loss": 0.4054,
|
| 590 |
+
"step": 580
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 26.8,
|
| 594 |
+
"learning_rate": 0.0002947945205479452,
|
| 595 |
+
"loss": 0.5045,
|
| 596 |
+
"step": 590
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 26.98,
|
| 600 |
+
"eval_loss": 0.6778237223625183,
|
| 601 |
+
"eval_runtime": 2.3715,
|
| 602 |
+
"eval_samples_per_second": 7.168,
|
| 603 |
+
"eval_steps_per_second": 2.108,
|
| 604 |
+
"eval_wer": 0.37902264600715135,
|
| 605 |
+
"step": 594
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 27.27,
|
| 609 |
+
"learning_rate": 0.0002929680365296804,
|
| 610 |
+
"loss": 0.4829,
|
| 611 |
+
"step": 600
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 27.71,
|
| 615 |
+
"learning_rate": 0.00029114155251141555,
|
| 616 |
+
"loss": 0.4373,
|
| 617 |
+
"step": 610
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 27.98,
|
| 621 |
+
"eval_loss": 0.7455542683601379,
|
| 622 |
+
"eval_runtime": 2.3574,
|
| 623 |
+
"eval_samples_per_second": 7.211,
|
| 624 |
+
"eval_steps_per_second": 2.121,
|
| 625 |
+
"eval_wer": 0.3694874851013111,
|
| 626 |
+
"step": 616
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 28.18,
|
| 630 |
+
"learning_rate": 0.0002893150684931507,
|
| 631 |
+
"loss": 0.3957,
|
| 632 |
+
"step": 620
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 28.62,
|
| 636 |
+
"learning_rate": 0.00028748858447488583,
|
| 637 |
+
"loss": 0.4366,
|
| 638 |
+
"step": 630
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 28.98,
|
| 642 |
+
"eval_loss": 0.7009137868881226,
|
| 643 |
+
"eval_runtime": 2.3463,
|
| 644 |
+
"eval_samples_per_second": 7.245,
|
| 645 |
+
"eval_steps_per_second": 2.131,
|
| 646 |
+
"eval_wer": 0.3432657926102503,
|
| 647 |
+
"step": 638
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 29.09,
|
| 651 |
+
"learning_rate": 0.00028566210045662105,
|
| 652 |
+
"loss": 0.4075,
|
| 653 |
+
"step": 640
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 29.53,
|
| 657 |
+
"learning_rate": 0.00028383561643835617,
|
| 658 |
+
"loss": 0.4399,
|
| 659 |
+
"step": 650
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 29.98,
|
| 663 |
+
"learning_rate": 0.00028200913242009133,
|
| 664 |
+
"loss": 0.3944,
|
| 665 |
+
"step": 660
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 29.98,
|
| 669 |
+
"eval_loss": 0.6841340661048889,
|
| 670 |
+
"eval_runtime": 2.4508,
|
| 671 |
+
"eval_samples_per_second": 6.936,
|
| 672 |
+
"eval_steps_per_second": 2.04,
|
| 673 |
+
"eval_wer": 0.3468414779499404,
|
| 674 |
+
"step": 660
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 30.44,
|
| 678 |
+
"learning_rate": 0.0002801826484018265,
|
| 679 |
+
"loss": 0.419,
|
| 680 |
+
"step": 670
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 30.89,
|
| 684 |
+
"learning_rate": 0.00027835616438356167,
|
| 685 |
+
"loss": 0.4206,
|
| 686 |
+
"step": 680
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 30.98,
|
| 690 |
+
"eval_loss": 0.7093454599380493,
|
| 691 |
+
"eval_runtime": 2.3527,
|
| 692 |
+
"eval_samples_per_second": 7.226,
|
| 693 |
+
"eval_steps_per_second": 2.125,
|
| 694 |
+
"eval_wer": 0.33730631704410013,
|
| 695 |
+
"step": 682
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 31.36,
|
| 699 |
+
"learning_rate": 0.0002765296803652968,
|
| 700 |
+
"loss": 0.406,
|
| 701 |
+
"step": 690
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 31.8,
|
| 705 |
+
"learning_rate": 0.000274703196347032,
|
| 706 |
+
"loss": 0.3949,
|
| 707 |
+
"step": 700
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 31.98,
|
| 711 |
+
"eval_loss": 0.6900954842567444,
|
| 712 |
+
"eval_runtime": 2.3751,
|
| 713 |
+
"eval_samples_per_second": 7.157,
|
| 714 |
+
"eval_steps_per_second": 2.105,
|
| 715 |
+
"eval_wer": 0.3575685339690107,
|
| 716 |
+
"step": 704
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 32.27,
|
| 720 |
+
"learning_rate": 0.0002728767123287671,
|
| 721 |
+
"loss": 0.4085,
|
| 722 |
+
"step": 710
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 32.71,
|
| 726 |
+
"learning_rate": 0.0002710502283105023,
|
| 727 |
+
"loss": 0.4416,
|
| 728 |
+
"step": 720
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 32.98,
|
| 732 |
+
"eval_loss": 0.6762455105781555,
|
| 733 |
+
"eval_runtime": 2.4676,
|
| 734 |
+
"eval_samples_per_second": 6.889,
|
| 735 |
+
"eval_steps_per_second": 2.026,
|
| 736 |
+
"eval_wer": 0.3396901072705602,
|
| 737 |
+
"step": 726
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 33.18,
|
| 741 |
+
"learning_rate": 0.00026922374429223746,
|
| 742 |
+
"loss": 0.4288,
|
| 743 |
+
"step": 730
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 33.62,
|
| 747 |
+
"learning_rate": 0.0002673972602739726,
|
| 748 |
+
"loss": 0.4248,
|
| 749 |
+
"step": 740
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 33.98,
|
| 753 |
+
"eval_loss": 0.7196361422538757,
|
| 754 |
+
"eval_runtime": 2.3986,
|
| 755 |
+
"eval_samples_per_second": 7.088,
|
| 756 |
+
"eval_steps_per_second": 2.085,
|
| 757 |
+
"eval_wer": 0.3539928486293206,
|
| 758 |
+
"step": 748
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 34.09,
|
| 762 |
+
"learning_rate": 0.0002655707762557078,
|
| 763 |
+
"loss": 0.4098,
|
| 764 |
+
"step": 750
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 34.53,
|
| 768 |
+
"learning_rate": 0.00026374429223744296,
|
| 769 |
+
"loss": 0.4203,
|
| 770 |
+
"step": 760
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 34.98,
|
| 774 |
+
"learning_rate": 0.00026191780821917807,
|
| 775 |
+
"loss": 0.4214,
|
| 776 |
+
"step": 770
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 34.98,
|
| 780 |
+
"eval_loss": 0.6669135093688965,
|
| 781 |
+
"eval_runtime": 2.3951,
|
| 782 |
+
"eval_samples_per_second": 7.098,
|
| 783 |
+
"eval_steps_per_second": 2.088,
|
| 784 |
+
"eval_wer": 0.3253873659117998,
|
| 785 |
+
"step": 770
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 35.44,
|
| 789 |
+
"learning_rate": 0.00026009132420091324,
|
| 790 |
+
"loss": 0.4146,
|
| 791 |
+
"step": 780
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 35.89,
|
| 795 |
+
"learning_rate": 0.0002582648401826484,
|
| 796 |
+
"loss": 0.416,
|
| 797 |
+
"step": 790
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 35.98,
|
| 801 |
+
"eval_loss": 0.6421573758125305,
|
| 802 |
+
"eval_runtime": 2.439,
|
| 803 |
+
"eval_samples_per_second": 6.97,
|
| 804 |
+
"eval_steps_per_second": 2.05,
|
| 805 |
+
"eval_wer": 0.34445768772348034,
|
| 806 |
+
"step": 792
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 36.36,
|
| 810 |
+
"learning_rate": 0.0002564383561643836,
|
| 811 |
+
"loss": 0.443,
|
| 812 |
+
"step": 800
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 36.8,
|
| 816 |
+
"learning_rate": 0.00025461187214611874,
|
| 817 |
+
"loss": 0.3687,
|
| 818 |
+
"step": 810
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 36.98,
|
| 822 |
+
"eval_loss": 0.6344943046569824,
|
| 823 |
+
"eval_runtime": 2.3916,
|
| 824 |
+
"eval_samples_per_second": 7.108,
|
| 825 |
+
"eval_steps_per_second": 2.091,
|
| 826 |
+
"eval_wer": 0.3504171632896305,
|
| 827 |
+
"step": 814
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 37.27,
|
| 831 |
+
"learning_rate": 0.0002527853881278539,
|
| 832 |
+
"loss": 0.4141,
|
| 833 |
+
"step": 820
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 37.71,
|
| 837 |
+
"learning_rate": 0.000250958904109589,
|
| 838 |
+
"loss": 0.4119,
|
| 839 |
+
"step": 830
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 37.98,
|
| 843 |
+
"eval_loss": 0.63063645362854,
|
| 844 |
+
"eval_runtime": 2.4069,
|
| 845 |
+
"eval_samples_per_second": 7.063,
|
| 846 |
+
"eval_steps_per_second": 2.077,
|
| 847 |
+
"eval_wer": 0.33849821215733017,
|
| 848 |
+
"step": 836
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 38.18,
|
| 852 |
+
"learning_rate": 0.00024913242009132425,
|
| 853 |
+
"loss": 0.3937,
|
| 854 |
+
"step": 840
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 38.62,
|
| 858 |
+
"learning_rate": 0.00024730593607305936,
|
| 859 |
+
"loss": 0.359,
|
| 860 |
+
"step": 850
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 38.98,
|
| 864 |
+
"eval_loss": 0.6538282036781311,
|
| 865 |
+
"eval_runtime": 2.3872,
|
| 866 |
+
"eval_samples_per_second": 7.121,
|
| 867 |
+
"eval_steps_per_second": 2.095,
|
| 868 |
+
"eval_wer": 0.3575685339690107,
|
| 869 |
+
"step": 858
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 39.09,
|
| 873 |
+
"learning_rate": 0.00024547945205479453,
|
| 874 |
+
"loss": 0.4018,
|
| 875 |
+
"step": 860
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 39.53,
|
| 879 |
+
"learning_rate": 0.00024365296803652967,
|
| 880 |
+
"loss": 0.3544,
|
| 881 |
+
"step": 870
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 39.98,
|
| 885 |
+
"learning_rate": 0.00024182648401826487,
|
| 886 |
+
"loss": 0.359,
|
| 887 |
+
"step": 880
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 39.98,
|
| 891 |
+
"eval_loss": 0.661315381526947,
|
| 892 |
+
"eval_runtime": 2.3978,
|
| 893 |
+
"eval_samples_per_second": 7.09,
|
| 894 |
+
"eval_steps_per_second": 2.085,
|
| 895 |
+
"eval_wer": 0.33492252681764006,
|
| 896 |
+
"step": 880
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 40.44,
|
| 900 |
+
"learning_rate": 0.00024,
|
| 901 |
+
"loss": 0.3963,
|
| 902 |
+
"step": 890
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 40.89,
|
| 906 |
+
"learning_rate": 0.00023817351598173517,
|
| 907 |
+
"loss": 0.3488,
|
| 908 |
+
"step": 900
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 40.98,
|
| 912 |
+
"eval_loss": 0.5976209044456482,
|
| 913 |
+
"eval_runtime": 2.3647,
|
| 914 |
+
"eval_samples_per_second": 7.189,
|
| 915 |
+
"eval_steps_per_second": 2.114,
|
| 916 |
+
"eval_wer": 0.3468414779499404,
|
| 917 |
+
"step": 902
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 41.36,
|
| 921 |
+
"learning_rate": 0.00023634703196347031,
|
| 922 |
+
"loss": 0.3752,
|
| 923 |
+
"step": 910
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 41.8,
|
| 927 |
+
"learning_rate": 0.0002345205479452055,
|
| 928 |
+
"loss": 0.3543,
|
| 929 |
+
"step": 920
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 41.98,
|
| 933 |
+
"eval_loss": 0.6326549053192139,
|
| 934 |
+
"eval_runtime": 2.3914,
|
| 935 |
+
"eval_samples_per_second": 7.109,
|
| 936 |
+
"eval_steps_per_second": 2.091,
|
| 937 |
+
"eval_wer": 0.3432657926102503,
|
| 938 |
+
"step": 924
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 42.27,
|
| 942 |
+
"learning_rate": 0.00023269406392694065,
|
| 943 |
+
"loss": 0.3711,
|
| 944 |
+
"step": 930
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 42.71,
|
| 948 |
+
"learning_rate": 0.00023086757990867582,
|
| 949 |
+
"loss": 0.3647,
|
| 950 |
+
"step": 940
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 42.98,
|
| 954 |
+
"eval_loss": 0.6207560300827026,
|
| 955 |
+
"eval_runtime": 2.3947,
|
| 956 |
+
"eval_samples_per_second": 7.099,
|
| 957 |
+
"eval_steps_per_second": 2.088,
|
| 958 |
+
"eval_wer": 0.3599523241954708,
|
| 959 |
+
"step": 946
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 43.18,
|
| 963 |
+
"learning_rate": 0.00022904109589041096,
|
| 964 |
+
"loss": 0.3462,
|
| 965 |
+
"step": 950
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 43.62,
|
| 969 |
+
"learning_rate": 0.00022721461187214615,
|
| 970 |
+
"loss": 0.3529,
|
| 971 |
+
"step": 960
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 43.98,
|
| 975 |
+
"eval_loss": 0.6007660627365112,
|
| 976 |
+
"eval_runtime": 2.4091,
|
| 977 |
+
"eval_samples_per_second": 7.056,
|
| 978 |
+
"eval_steps_per_second": 2.075,
|
| 979 |
+
"eval_wer": 0.3492252681764005,
|
| 980 |
+
"step": 968
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 44.09,
|
| 984 |
+
"learning_rate": 0.00022538812785388127,
|
| 985 |
+
"loss": 0.359,
|
| 986 |
+
"step": 970
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 44.53,
|
| 990 |
+
"learning_rate": 0.00022374429223744296,
|
| 991 |
+
"loss": 0.329,
|
| 992 |
+
"step": 980
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 44.98,
|
| 996 |
+
"learning_rate": 0.0002219178082191781,
|
| 997 |
+
"loss": 0.3691,
|
| 998 |
+
"step": 990
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 44.98,
|
| 1002 |
+
"eval_loss": 0.606474757194519,
|
| 1003 |
+
"eval_runtime": 2.3824,
|
| 1004 |
+
"eval_samples_per_second": 7.136,
|
| 1005 |
+
"eval_steps_per_second": 2.099,
|
| 1006 |
+
"eval_wer": 0.3492252681764005,
|
| 1007 |
+
"step": 990
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 45.44,
|
| 1011 |
+
"learning_rate": 0.00022009132420091327,
|
| 1012 |
+
"loss": 0.3611,
|
| 1013 |
+
"step": 1000
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 45.89,
|
| 1017 |
+
"learning_rate": 0.0002182648401826484,
|
| 1018 |
+
"loss": 0.329,
|
| 1019 |
+
"step": 1010
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 45.98,
|
| 1023 |
+
"eval_loss": 0.6287906169891357,
|
| 1024 |
+
"eval_runtime": 2.4134,
|
| 1025 |
+
"eval_samples_per_second": 7.044,
|
| 1026 |
+
"eval_steps_per_second": 2.072,
|
| 1027 |
+
"eval_wer": 0.33730631704410013,
|
| 1028 |
+
"step": 1012
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 46.36,
|
| 1032 |
+
"learning_rate": 0.00021643835616438358,
|
| 1033 |
+
"loss": 0.3256,
|
| 1034 |
+
"step": 1020
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 46.8,
|
| 1038 |
+
"learning_rate": 0.00021461187214611872,
|
| 1039 |
+
"loss": 0.3357,
|
| 1040 |
+
"step": 1030
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 46.98,
|
| 1044 |
+
"eval_loss": 0.5759619474411011,
|
| 1045 |
+
"eval_runtime": 2.3736,
|
| 1046 |
+
"eval_samples_per_second": 7.162,
|
| 1047 |
+
"eval_steps_per_second": 2.107,
|
| 1048 |
+
"eval_wer": 0.34803337306317045,
|
| 1049 |
+
"step": 1034
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 47.27,
|
| 1053 |
+
"learning_rate": 0.00021278538812785392,
|
| 1054 |
+
"loss": 0.3698,
|
| 1055 |
+
"step": 1040
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 47.71,
|
| 1059 |
+
"learning_rate": 0.00021095890410958906,
|
| 1060 |
+
"loss": 0.3318,
|
| 1061 |
+
"step": 1050
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 47.98,
|
| 1065 |
+
"eval_loss": 0.5636705160140991,
|
| 1066 |
+
"eval_runtime": 2.409,
|
| 1067 |
+
"eval_samples_per_second": 7.057,
|
| 1068 |
+
"eval_steps_per_second": 2.076,
|
| 1069 |
+
"eval_wer": 0.3563766388557807,
|
| 1070 |
+
"step": 1056
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 48.18,
|
| 1074 |
+
"learning_rate": 0.00020913242009132422,
|
| 1075 |
+
"loss": 0.3573,
|
| 1076 |
+
"step": 1060
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 48.62,
|
| 1080 |
+
"learning_rate": 0.00020730593607305937,
|
| 1081 |
+
"loss": 0.3181,
|
| 1082 |
+
"step": 1070
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 48.98,
|
| 1086 |
+
"eval_loss": 0.5560324192047119,
|
| 1087 |
+
"eval_runtime": 2.398,
|
| 1088 |
+
"eval_samples_per_second": 7.089,
|
| 1089 |
+
"eval_steps_per_second": 2.085,
|
| 1090 |
+
"eval_wer": 0.3468414779499404,
|
| 1091 |
+
"step": 1078
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 49.09,
|
| 1095 |
+
"learning_rate": 0.00020547945205479456,
|
| 1096 |
+
"loss": 0.3274,
|
| 1097 |
+
"step": 1080
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 49.53,
|
| 1101 |
+
"learning_rate": 0.0002036529680365297,
|
| 1102 |
+
"loss": 0.3073,
|
| 1103 |
+
"step": 1090
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 49.98,
|
| 1107 |
+
"learning_rate": 0.00020182648401826487,
|
| 1108 |
+
"loss": 0.3313,
|
| 1109 |
+
"step": 1100
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 49.98,
|
| 1113 |
+
"eval_loss": 0.5904679298400879,
|
| 1114 |
+
"eval_runtime": 2.4923,
|
| 1115 |
+
"eval_samples_per_second": 6.821,
|
| 1116 |
+
"eval_steps_per_second": 2.006,
|
| 1117 |
+
"eval_wer": 0.33373063170441003,
|
| 1118 |
+
"step": 1100
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 50.44,
|
| 1122 |
+
"learning_rate": 0.0002,
|
| 1123 |
+
"loss": 0.3322,
|
| 1124 |
+
"step": 1110
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 50.89,
|
| 1128 |
+
"learning_rate": 0.00019817351598173518,
|
| 1129 |
+
"loss": 0.3059,
|
| 1130 |
+
"step": 1120
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 50.98,
|
| 1134 |
+
"eval_loss": 0.5443325042724609,
|
| 1135 |
+
"eval_runtime": 2.3906,
|
| 1136 |
+
"eval_samples_per_second": 7.111,
|
| 1137 |
+
"eval_steps_per_second": 2.091,
|
| 1138 |
+
"eval_wer": 0.32777115613825986,
|
| 1139 |
+
"step": 1122
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 51.36,
|
| 1143 |
+
"learning_rate": 0.00019634703196347032,
|
| 1144 |
+
"loss": 0.2972,
|
| 1145 |
+
"step": 1130
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 51.8,
|
| 1149 |
+
"learning_rate": 0.00019452054794520549,
|
| 1150 |
+
"loss": 0.3375,
|
| 1151 |
+
"step": 1140
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 51.98,
|
| 1155 |
+
"eval_loss": 0.5695326328277588,
|
| 1156 |
+
"eval_runtime": 2.3779,
|
| 1157 |
+
"eval_samples_per_second": 7.149,
|
| 1158 |
+
"eval_steps_per_second": 2.103,
|
| 1159 |
+
"eval_wer": 0.3575685339690107,
|
| 1160 |
+
"step": 1144
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 52.27,
|
| 1164 |
+
"learning_rate": 0.00019269406392694065,
|
| 1165 |
+
"loss": 0.3534,
|
| 1166 |
+
"step": 1150
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 52.71,
|
| 1170 |
+
"learning_rate": 0.00019086757990867582,
|
| 1171 |
+
"loss": 0.3191,
|
| 1172 |
+
"step": 1160
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 52.98,
|
| 1176 |
+
"eval_loss": 0.5874321460723877,
|
| 1177 |
+
"eval_runtime": 2.5159,
|
| 1178 |
+
"eval_samples_per_second": 6.757,
|
| 1179 |
+
"eval_steps_per_second": 1.987,
|
| 1180 |
+
"eval_wer": 0.33849821215733017,
|
| 1181 |
+
"step": 1166
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 53.18,
|
| 1185 |
+
"learning_rate": 0.00018904109589041096,
|
| 1186 |
+
"loss": 0.3002,
|
| 1187 |
+
"step": 1170
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 53.62,
|
| 1191 |
+
"learning_rate": 0.00018721461187214613,
|
| 1192 |
+
"loss": 0.3115,
|
| 1193 |
+
"step": 1180
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 53.98,
|
| 1197 |
+
"eval_loss": 0.5264096260070801,
|
| 1198 |
+
"eval_runtime": 2.4342,
|
| 1199 |
+
"eval_samples_per_second": 6.984,
|
| 1200 |
+
"eval_steps_per_second": 2.054,
|
| 1201 |
+
"eval_wer": 0.3635280095351609,
|
| 1202 |
+
"step": 1188
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 54.09,
|
| 1206 |
+
"learning_rate": 0.0001853881278538813,
|
| 1207 |
+
"loss": 0.3044,
|
| 1208 |
+
"step": 1190
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 54.53,
|
| 1212 |
+
"learning_rate": 0.00018356164383561644,
|
| 1213 |
+
"loss": 0.3179,
|
| 1214 |
+
"step": 1200
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 54.98,
|
| 1218 |
+
"learning_rate": 0.0001817351598173516,
|
| 1219 |
+
"loss": 0.3044,
|
| 1220 |
+
"step": 1210
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 54.98,
|
| 1224 |
+
"eval_loss": 0.5479747653007507,
|
| 1225 |
+
"eval_runtime": 2.3968,
|
| 1226 |
+
"eval_samples_per_second": 7.093,
|
| 1227 |
+
"eval_steps_per_second": 2.086,
|
| 1228 |
+
"eval_wer": 0.3432657926102503,
|
| 1229 |
+
"step": 1210
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 55.44,
|
| 1233 |
+
"learning_rate": 0.00017990867579908678,
|
| 1234 |
+
"loss": 0.3619,
|
| 1235 |
+
"step": 1220
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 55.89,
|
| 1239 |
+
"learning_rate": 0.00017808219178082192,
|
| 1240 |
+
"loss": 0.3256,
|
| 1241 |
+
"step": 1230
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 55.98,
|
| 1245 |
+
"eval_loss": 0.5677239894866943,
|
| 1246 |
+
"eval_runtime": 2.4179,
|
| 1247 |
+
"eval_samples_per_second": 7.031,
|
| 1248 |
+
"eval_steps_per_second": 2.068,
|
| 1249 |
+
"eval_wer": 0.33849821215733017,
|
| 1250 |
+
"step": 1232
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 56.36,
|
| 1254 |
+
"learning_rate": 0.00017625570776255708,
|
| 1255 |
+
"loss": 0.3341,
|
| 1256 |
+
"step": 1240
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 56.8,
|
| 1260 |
+
"learning_rate": 0.00017442922374429225,
|
| 1261 |
+
"loss": 0.2938,
|
| 1262 |
+
"step": 1250
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 56.98,
|
| 1266 |
+
"eval_loss": 0.5597422122955322,
|
| 1267 |
+
"eval_runtime": 2.3754,
|
| 1268 |
+
"eval_samples_per_second": 7.157,
|
| 1269 |
+
"eval_steps_per_second": 2.105,
|
| 1270 |
+
"eval_wer": 0.34445768772348034,
|
| 1271 |
+
"step": 1254
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 57.27,
|
| 1275 |
+
"learning_rate": 0.00017260273972602742,
|
| 1276 |
+
"loss": 0.297,
|
| 1277 |
+
"step": 1260
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 57.71,
|
| 1281 |
+
"learning_rate": 0.00017077625570776256,
|
| 1282 |
+
"loss": 0.2853,
|
| 1283 |
+
"step": 1270
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 57.98,
|
| 1287 |
+
"eval_loss": 0.5942354798316956,
|
| 1288 |
+
"eval_runtime": 2.3904,
|
| 1289 |
+
"eval_samples_per_second": 7.112,
|
| 1290 |
+
"eval_steps_per_second": 2.092,
|
| 1291 |
+
"eval_wer": 0.33730631704410013,
|
| 1292 |
+
"step": 1276
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 58.18,
|
| 1296 |
+
"learning_rate": 0.00016894977168949773,
|
| 1297 |
+
"loss": 0.3409,
|
| 1298 |
+
"step": 1280
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 58.62,
|
| 1302 |
+
"learning_rate": 0.0001671232876712329,
|
| 1303 |
+
"loss": 0.3348,
|
| 1304 |
+
"step": 1290
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 58.98,
|
| 1308 |
+
"eval_loss": 0.5733348727226257,
|
| 1309 |
+
"eval_runtime": 2.3901,
|
| 1310 |
+
"eval_samples_per_second": 7.113,
|
| 1311 |
+
"eval_steps_per_second": 2.092,
|
| 1312 |
+
"eval_wer": 0.3420738974970203,
|
| 1313 |
+
"step": 1298
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 59.09,
|
| 1317 |
+
"learning_rate": 0.00016529680365296804,
|
| 1318 |
+
"loss": 0.341,
|
| 1319 |
+
"step": 1300
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 59.53,
|
| 1323 |
+
"learning_rate": 0.0001634703196347032,
|
| 1324 |
+
"loss": 0.3381,
|
| 1325 |
+
"step": 1310
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 59.98,
|
| 1329 |
+
"learning_rate": 0.00016164383561643837,
|
| 1330 |
+
"loss": 0.3024,
|
| 1331 |
+
"step": 1320
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 59.98,
|
| 1335 |
+
"eval_loss": 0.5603709816932678,
|
| 1336 |
+
"eval_runtime": 2.3597,
|
| 1337 |
+
"eval_samples_per_second": 7.204,
|
| 1338 |
+
"eval_steps_per_second": 2.119,
|
| 1339 |
+
"eval_wer": 0.3432657926102503,
|
| 1340 |
+
"step": 1320
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 60.44,
|
| 1344 |
+
"learning_rate": 0.00015981735159817351,
|
| 1345 |
+
"loss": 0.2983,
|
| 1346 |
+
"step": 1330
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 60.89,
|
| 1350 |
+
"learning_rate": 0.00015799086757990868,
|
| 1351 |
+
"loss": 0.2655,
|
| 1352 |
+
"step": 1340
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 60.98,
|
| 1356 |
+
"eval_loss": 0.5348132252693176,
|
| 1357 |
+
"eval_runtime": 2.4009,
|
| 1358 |
+
"eval_samples_per_second": 7.081,
|
| 1359 |
+
"eval_steps_per_second": 2.083,
|
| 1360 |
+
"eval_wer": 0.3468414779499404,
|
| 1361 |
+
"step": 1342
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 61.36,
|
| 1365 |
+
"learning_rate": 0.00015616438356164385,
|
| 1366 |
+
"loss": 0.3171,
|
| 1367 |
+
"step": 1350
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 61.8,
|
| 1371 |
+
"learning_rate": 0.00015433789954337902,
|
| 1372 |
+
"loss": 0.3029,
|
| 1373 |
+
"step": 1360
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 61.98,
|
| 1377 |
+
"eval_loss": 0.5751910209655762,
|
| 1378 |
+
"eval_runtime": 2.4011,
|
| 1379 |
+
"eval_samples_per_second": 7.08,
|
| 1380 |
+
"eval_steps_per_second": 2.082,
|
| 1381 |
+
"eval_wer": 0.3206197854588796,
|
| 1382 |
+
"step": 1364
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 62.27,
|
| 1386 |
+
"learning_rate": 0.00015251141552511416,
|
| 1387 |
+
"loss": 0.2712,
|
| 1388 |
+
"step": 1370
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 62.71,
|
| 1392 |
+
"learning_rate": 0.00015068493150684933,
|
| 1393 |
+
"loss": 0.3435,
|
| 1394 |
+
"step": 1380
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 62.98,
|
| 1398 |
+
"eval_loss": 0.548903226852417,
|
| 1399 |
+
"eval_runtime": 2.3839,
|
| 1400 |
+
"eval_samples_per_second": 7.131,
|
| 1401 |
+
"eval_steps_per_second": 2.097,
|
| 1402 |
+
"eval_wer": 0.3063170441001192,
|
| 1403 |
+
"step": 1386
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 63.18,
|
| 1407 |
+
"learning_rate": 0.0001488584474885845,
|
| 1408 |
+
"loss": 0.2861,
|
| 1409 |
+
"step": 1390
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 63.62,
|
| 1413 |
+
"learning_rate": 0.00014703196347031963,
|
| 1414 |
+
"loss": 0.3125,
|
| 1415 |
+
"step": 1400
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 63.98,
|
| 1419 |
+
"eval_loss": 0.5735787749290466,
|
| 1420 |
+
"eval_runtime": 2.5834,
|
| 1421 |
+
"eval_samples_per_second": 6.581,
|
| 1422 |
+
"eval_steps_per_second": 1.935,
|
| 1423 |
+
"eval_wer": 0.3075089392133492,
|
| 1424 |
+
"step": 1408
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 64.09,
|
| 1428 |
+
"learning_rate": 0.0001452054794520548,
|
| 1429 |
+
"loss": 0.2642,
|
| 1430 |
+
"step": 1410
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 64.53,
|
| 1434 |
+
"learning_rate": 0.00014337899543378997,
|
| 1435 |
+
"loss": 0.3023,
|
| 1436 |
+
"step": 1420
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 64.98,
|
| 1440 |
+
"learning_rate": 0.0001415525114155251,
|
| 1441 |
+
"loss": 0.263,
|
| 1442 |
+
"step": 1430
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 64.98,
|
| 1446 |
+
"eval_loss": 0.5505235195159912,
|
| 1447 |
+
"eval_runtime": 2.3983,
|
| 1448 |
+
"eval_samples_per_second": 7.088,
|
| 1449 |
+
"eval_steps_per_second": 2.085,
|
| 1450 |
+
"eval_wer": 0.3206197854588796,
|
| 1451 |
+
"step": 1430
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 65.44,
|
| 1455 |
+
"learning_rate": 0.00013972602739726028,
|
| 1456 |
+
"loss": 0.2621,
|
| 1457 |
+
"step": 1440
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 65.89,
|
| 1461 |
+
"learning_rate": 0.00013789954337899545,
|
| 1462 |
+
"loss": 0.2665,
|
| 1463 |
+
"step": 1450
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 65.98,
|
| 1467 |
+
"eval_loss": 0.5391205549240112,
|
| 1468 |
+
"eval_runtime": 2.4038,
|
| 1469 |
+
"eval_samples_per_second": 7.072,
|
| 1470 |
+
"eval_steps_per_second": 2.08,
|
| 1471 |
+
"eval_wer": 0.3230035756853397,
|
| 1472 |
+
"step": 1452
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 66.36,
|
| 1476 |
+
"learning_rate": 0.00013607305936073061,
|
| 1477 |
+
"loss": 0.3153,
|
| 1478 |
+
"step": 1460
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 66.8,
|
| 1482 |
+
"learning_rate": 0.00013424657534246576,
|
| 1483 |
+
"loss": 0.299,
|
| 1484 |
+
"step": 1470
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 66.98,
|
| 1488 |
+
"eval_loss": 0.5388566255569458,
|
| 1489 |
+
"eval_runtime": 2.4363,
|
| 1490 |
+
"eval_samples_per_second": 6.978,
|
| 1491 |
+
"eval_steps_per_second": 2.052,
|
| 1492 |
+
"eval_wer": 0.3134684147794994,
|
| 1493 |
+
"step": 1474
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 67.27,
|
| 1497 |
+
"learning_rate": 0.00013242009132420092,
|
| 1498 |
+
"loss": 0.2966,
|
| 1499 |
+
"step": 1480
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 67.71,
|
| 1503 |
+
"learning_rate": 0.0001305936073059361,
|
| 1504 |
+
"loss": 0.2909,
|
| 1505 |
+
"step": 1490
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 67.98,
|
| 1509 |
+
"eval_loss": 0.5840542912483215,
|
| 1510 |
+
"eval_runtime": 2.4363,
|
| 1511 |
+
"eval_samples_per_second": 6.978,
|
| 1512 |
+
"eval_steps_per_second": 2.052,
|
| 1513 |
+
"eval_wer": 0.3098927294398093,
|
| 1514 |
+
"step": 1496
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 68.18,
|
| 1518 |
+
"learning_rate": 0.00012876712328767123,
|
| 1519 |
+
"loss": 0.2848,
|
| 1520 |
+
"step": 1500
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 68.62,
|
| 1524 |
+
"learning_rate": 0.0001269406392694064,
|
| 1525 |
+
"loss": 0.2988,
|
| 1526 |
+
"step": 1510
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 68.98,
|
| 1530 |
+
"eval_loss": 0.5847446918487549,
|
| 1531 |
+
"eval_runtime": 2.3833,
|
| 1532 |
+
"eval_samples_per_second": 7.133,
|
| 1533 |
+
"eval_steps_per_second": 2.098,
|
| 1534 |
+
"eval_wer": 0.300357568533969,
|
| 1535 |
+
"step": 1518
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 69.09,
|
| 1539 |
+
"learning_rate": 0.00012511415525114157,
|
| 1540 |
+
"loss": 0.2722,
|
| 1541 |
+
"step": 1520
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 69.53,
|
| 1545 |
+
"learning_rate": 0.0001232876712328767,
|
| 1546 |
+
"loss": 0.2633,
|
| 1547 |
+
"step": 1530
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 69.98,
|
| 1551 |
+
"learning_rate": 0.00012146118721461188,
|
| 1552 |
+
"loss": 0.2879,
|
| 1553 |
+
"step": 1540
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 69.98,
|
| 1557 |
+
"eval_loss": 0.5940636992454529,
|
| 1558 |
+
"eval_runtime": 2.6597,
|
| 1559 |
+
"eval_samples_per_second": 6.392,
|
| 1560 |
+
"eval_steps_per_second": 1.88,
|
| 1561 |
+
"eval_wer": 0.2967818831942789,
|
| 1562 |
+
"step": 1540
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 70.44,
|
| 1566 |
+
"learning_rate": 0.00011963470319634704,
|
| 1567 |
+
"loss": 0.2957,
|
| 1568 |
+
"step": 1550
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 70.89,
|
| 1572 |
+
"learning_rate": 0.0001178082191780822,
|
| 1573 |
+
"loss": 0.2802,
|
| 1574 |
+
"step": 1560
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 70.98,
|
| 1578 |
+
"eval_loss": 0.6612115502357483,
|
| 1579 |
+
"eval_runtime": 2.3737,
|
| 1580 |
+
"eval_samples_per_second": 7.162,
|
| 1581 |
+
"eval_steps_per_second": 2.106,
|
| 1582 |
+
"eval_wer": 0.29201430274135876,
|
| 1583 |
+
"step": 1562
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 71.36,
|
| 1587 |
+
"learning_rate": 0.00011598173515981737,
|
| 1588 |
+
"loss": 0.2691,
|
| 1589 |
+
"step": 1570
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 71.8,
|
| 1593 |
+
"learning_rate": 0.00011415525114155252,
|
| 1594 |
+
"loss": 0.2877,
|
| 1595 |
+
"step": 1580
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 71.98,
|
| 1599 |
+
"eval_loss": 0.5640567541122437,
|
| 1600 |
+
"eval_runtime": 2.4284,
|
| 1601 |
+
"eval_samples_per_second": 7.0,
|
| 1602 |
+
"eval_steps_per_second": 2.059,
|
| 1603 |
+
"eval_wer": 0.30512514898688914,
|
| 1604 |
+
"step": 1584
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 72.27,
|
| 1608 |
+
"learning_rate": 0.00011232876712328768,
|
| 1609 |
+
"loss": 0.295,
|
| 1610 |
+
"step": 1590
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 72.71,
|
| 1614 |
+
"learning_rate": 0.00011050228310502284,
|
| 1615 |
+
"loss": 0.2727,
|
| 1616 |
+
"step": 1600
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 72.98,
|
| 1620 |
+
"eval_loss": 0.6137677431106567,
|
| 1621 |
+
"eval_runtime": 2.404,
|
| 1622 |
+
"eval_samples_per_second": 7.072,
|
| 1623 |
+
"eval_steps_per_second": 2.08,
|
| 1624 |
+
"eval_wer": 0.3063170441001192,
|
| 1625 |
+
"step": 1606
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 73.18,
|
| 1629 |
+
"learning_rate": 0.000108675799086758,
|
| 1630 |
+
"loss": 0.2989,
|
| 1631 |
+
"step": 1610
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 73.62,
|
| 1635 |
+
"learning_rate": 0.00010684931506849317,
|
| 1636 |
+
"loss": 0.2668,
|
| 1637 |
+
"step": 1620
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 73.98,
|
| 1641 |
+
"eval_loss": 0.608710527420044,
|
| 1642 |
+
"eval_runtime": 2.3622,
|
| 1643 |
+
"eval_samples_per_second": 7.197,
|
| 1644 |
+
"eval_steps_per_second": 2.117,
|
| 1645 |
+
"eval_wer": 0.29201430274135876,
|
| 1646 |
+
"step": 1628
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 74.09,
|
| 1650 |
+
"learning_rate": 0.00010502283105022832,
|
| 1651 |
+
"loss": 0.2665,
|
| 1652 |
+
"step": 1630
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 74.53,
|
| 1656 |
+
"learning_rate": 0.00010319634703196347,
|
| 1657 |
+
"loss": 0.2829,
|
| 1658 |
+
"step": 1640
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 74.98,
|
| 1662 |
+
"learning_rate": 0.00010136986301369864,
|
| 1663 |
+
"loss": 0.2675,
|
| 1664 |
+
"step": 1650
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 74.98,
|
| 1668 |
+
"eval_loss": 0.5876254439353943,
|
| 1669 |
+
"eval_runtime": 2.3686,
|
| 1670 |
+
"eval_samples_per_second": 7.177,
|
| 1671 |
+
"eval_steps_per_second": 2.111,
|
| 1672 |
+
"eval_wer": 0.2932061978545888,
|
| 1673 |
+
"step": 1650
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 75.44,
|
| 1677 |
+
"learning_rate": 9.954337899543378e-05,
|
| 1678 |
+
"loss": 0.2837,
|
| 1679 |
+
"step": 1660
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 75.89,
|
| 1683 |
+
"learning_rate": 9.771689497716895e-05,
|
| 1684 |
+
"loss": 0.264,
|
| 1685 |
+
"step": 1670
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 75.98,
|
| 1689 |
+
"eval_loss": 0.6042572855949402,
|
| 1690 |
+
"eval_runtime": 2.4461,
|
| 1691 |
+
"eval_samples_per_second": 6.95,
|
| 1692 |
+
"eval_steps_per_second": 2.044,
|
| 1693 |
+
"eval_wer": 0.29797377830750893,
|
| 1694 |
+
"step": 1672
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 76.36,
|
| 1698 |
+
"learning_rate": 9.58904109589041e-05,
|
| 1699 |
+
"loss": 0.2769,
|
| 1700 |
+
"step": 1680
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 76.8,
|
| 1704 |
+
"learning_rate": 9.406392694063927e-05,
|
| 1705 |
+
"loss": 0.2352,
|
| 1706 |
+
"step": 1690
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 76.98,
|
| 1710 |
+
"eval_loss": 0.5829324722290039,
|
| 1711 |
+
"eval_runtime": 2.389,
|
| 1712 |
+
"eval_samples_per_second": 7.116,
|
| 1713 |
+
"eval_steps_per_second": 2.093,
|
| 1714 |
+
"eval_wer": 0.2932061978545888,
|
| 1715 |
+
"step": 1694
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 77.27,
|
| 1719 |
+
"learning_rate": 9.223744292237443e-05,
|
| 1720 |
+
"loss": 0.364,
|
| 1721 |
+
"step": 1700
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 77.71,
|
| 1725 |
+
"learning_rate": 9.041095890410958e-05,
|
| 1726 |
+
"loss": 0.2494,
|
| 1727 |
+
"step": 1710
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 77.98,
|
| 1731 |
+
"eval_loss": 0.5775046348571777,
|
| 1732 |
+
"eval_runtime": 2.3916,
|
| 1733 |
+
"eval_samples_per_second": 7.108,
|
| 1734 |
+
"eval_steps_per_second": 2.091,
|
| 1735 |
+
"eval_wer": 0.3063170441001192,
|
| 1736 |
+
"step": 1716
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 78.18,
|
| 1740 |
+
"learning_rate": 8.858447488584475e-05,
|
| 1741 |
+
"loss": 0.2494,
|
| 1742 |
+
"step": 1720
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 78.62,
|
| 1746 |
+
"learning_rate": 8.67579908675799e-05,
|
| 1747 |
+
"loss": 0.2621,
|
| 1748 |
+
"step": 1730
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 78.98,
|
| 1752 |
+
"eval_loss": 0.5675925016403198,
|
| 1753 |
+
"eval_runtime": 2.402,
|
| 1754 |
+
"eval_samples_per_second": 7.078,
|
| 1755 |
+
"eval_steps_per_second": 2.082,
|
| 1756 |
+
"eval_wer": 0.29558998808104886,
|
| 1757 |
+
"step": 1738
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 79.09,
|
| 1761 |
+
"learning_rate": 8.493150684931507e-05,
|
| 1762 |
+
"loss": 0.286,
|
| 1763 |
+
"step": 1740
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 79.53,
|
| 1767 |
+
"learning_rate": 8.310502283105023e-05,
|
| 1768 |
+
"loss": 0.2591,
|
| 1769 |
+
"step": 1750
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 79.98,
|
| 1773 |
+
"learning_rate": 8.127853881278538e-05,
|
| 1774 |
+
"loss": 0.2788,
|
| 1775 |
+
"step": 1760
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 79.98,
|
| 1779 |
+
"eval_loss": 0.5863559246063232,
|
| 1780 |
+
"eval_runtime": 2.3868,
|
| 1781 |
+
"eval_samples_per_second": 7.122,
|
| 1782 |
+
"eval_steps_per_second": 2.095,
|
| 1783 |
+
"eval_wer": 0.2932061978545888,
|
| 1784 |
+
"step": 1760
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 80.44,
|
| 1788 |
+
"learning_rate": 7.945205479452055e-05,
|
| 1789 |
+
"loss": 0.2591,
|
| 1790 |
+
"step": 1770
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 80.89,
|
| 1794 |
+
"learning_rate": 7.76255707762557e-05,
|
| 1795 |
+
"loss": 0.2615,
|
| 1796 |
+
"step": 1780
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 80.98,
|
| 1800 |
+
"eval_loss": 0.5754203796386719,
|
| 1801 |
+
"eval_runtime": 2.4207,
|
| 1802 |
+
"eval_samples_per_second": 7.023,
|
| 1803 |
+
"eval_steps_per_second": 2.066,
|
| 1804 |
+
"eval_wer": 0.30154946364719903,
|
| 1805 |
+
"step": 1782
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 81.36,
|
| 1809 |
+
"learning_rate": 7.579908675799087e-05,
|
| 1810 |
+
"loss": 0.307,
|
| 1811 |
+
"step": 1790
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 81.8,
|
| 1815 |
+
"learning_rate": 7.397260273972603e-05,
|
| 1816 |
+
"loss": 0.2542,
|
| 1817 |
+
"step": 1800
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 81.98,
|
| 1821 |
+
"eval_loss": 0.5650574564933777,
|
| 1822 |
+
"eval_runtime": 2.403,
|
| 1823 |
+
"eval_samples_per_second": 7.075,
|
| 1824 |
+
"eval_steps_per_second": 2.081,
|
| 1825 |
+
"eval_wer": 0.30274135876042907,
|
| 1826 |
+
"step": 1804
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 82.27,
|
| 1830 |
+
"learning_rate": 7.21461187214612e-05,
|
| 1831 |
+
"loss": 0.2653,
|
| 1832 |
+
"step": 1810
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 82.71,
|
| 1836 |
+
"learning_rate": 7.031963470319635e-05,
|
| 1837 |
+
"loss": 0.2641,
|
| 1838 |
+
"step": 1820
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 82.98,
|
| 1842 |
+
"eval_loss": 0.5731266736984253,
|
| 1843 |
+
"eval_runtime": 2.415,
|
| 1844 |
+
"eval_samples_per_second": 7.039,
|
| 1845 |
+
"eval_steps_per_second": 2.07,
|
| 1846 |
+
"eval_wer": 0.300357568533969,
|
| 1847 |
+
"step": 1826
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 83.18,
|
| 1851 |
+
"learning_rate": 6.84931506849315e-05,
|
| 1852 |
+
"loss": 0.2684,
|
| 1853 |
+
"step": 1830
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 83.62,
|
| 1857 |
+
"learning_rate": 6.666666666666667e-05,
|
| 1858 |
+
"loss": 0.2532,
|
| 1859 |
+
"step": 1840
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 83.98,
|
| 1863 |
+
"eval_loss": 0.5782402157783508,
|
| 1864 |
+
"eval_runtime": 2.4968,
|
| 1865 |
+
"eval_samples_per_second": 6.809,
|
| 1866 |
+
"eval_steps_per_second": 2.003,
|
| 1867 |
+
"eval_wer": 0.2967818831942789,
|
| 1868 |
+
"step": 1848
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 84.09,
|
| 1872 |
+
"learning_rate": 6.484018264840182e-05,
|
| 1873 |
+
"loss": 0.2521,
|
| 1874 |
+
"step": 1850
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 84.53,
|
| 1878 |
+
"learning_rate": 6.301369863013699e-05,
|
| 1879 |
+
"loss": 0.231,
|
| 1880 |
+
"step": 1860
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 84.98,
|
| 1884 |
+
"learning_rate": 6.118721461187215e-05,
|
| 1885 |
+
"loss": 0.2645,
|
| 1886 |
+
"step": 1870
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 84.98,
|
| 1890 |
+
"eval_loss": 0.5717898011207581,
|
| 1891 |
+
"eval_runtime": 2.3947,
|
| 1892 |
+
"eval_samples_per_second": 7.099,
|
| 1893 |
+
"eval_steps_per_second": 2.088,
|
| 1894 |
+
"eval_wer": 0.3039332538736591,
|
| 1895 |
+
"step": 1870
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 85.44,
|
| 1899 |
+
"learning_rate": 5.936073059360731e-05,
|
| 1900 |
+
"loss": 0.2731,
|
| 1901 |
+
"step": 1880
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 85.89,
|
| 1905 |
+
"learning_rate": 5.753424657534247e-05,
|
| 1906 |
+
"loss": 0.2296,
|
| 1907 |
+
"step": 1890
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 85.98,
|
| 1911 |
+
"eval_loss": 0.5628200173377991,
|
| 1912 |
+
"eval_runtime": 2.3724,
|
| 1913 |
+
"eval_samples_per_second": 7.166,
|
| 1914 |
+
"eval_steps_per_second": 2.108,
|
| 1915 |
+
"eval_wer": 0.3146603098927294,
|
| 1916 |
+
"step": 1892
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 86.36,
|
| 1920 |
+
"learning_rate": 5.570776255707762e-05,
|
| 1921 |
+
"loss": 0.2658,
|
| 1922 |
+
"step": 1900
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 86.8,
|
| 1926 |
+
"learning_rate": 5.3881278538812784e-05,
|
| 1927 |
+
"loss": 0.2394,
|
| 1928 |
+
"step": 1910
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 86.98,
|
| 1932 |
+
"eval_loss": 0.5919906497001648,
|
| 1933 |
+
"eval_runtime": 2.3939,
|
| 1934 |
+
"eval_samples_per_second": 7.101,
|
| 1935 |
+
"eval_steps_per_second": 2.089,
|
| 1936 |
+
"eval_wer": 0.30274135876042907,
|
| 1937 |
+
"step": 1914
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 87.27,
|
| 1941 |
+
"learning_rate": 5.2054794520547945e-05,
|
| 1942 |
+
"loss": 0.2777,
|
| 1943 |
+
"step": 1920
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 87.71,
|
| 1947 |
+
"learning_rate": 5.0228310502283106e-05,
|
| 1948 |
+
"loss": 0.2636,
|
| 1949 |
+
"step": 1930
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 87.98,
|
| 1953 |
+
"eval_loss": 0.6085216999053955,
|
| 1954 |
+
"eval_runtime": 2.389,
|
| 1955 |
+
"eval_samples_per_second": 7.116,
|
| 1956 |
+
"eval_steps_per_second": 2.093,
|
| 1957 |
+
"eval_wer": 0.2967818831942789,
|
| 1958 |
+
"step": 1936
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 88.18,
|
| 1962 |
+
"learning_rate": 4.840182648401827e-05,
|
| 1963 |
+
"loss": 0.2717,
|
| 1964 |
+
"step": 1940
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 88.62,
|
| 1968 |
+
"learning_rate": 4.657534246575342e-05,
|
| 1969 |
+
"loss": 0.2371,
|
| 1970 |
+
"step": 1950
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 88.98,
|
| 1974 |
+
"eval_loss": 0.5808770060539246,
|
| 1975 |
+
"eval_runtime": 2.3775,
|
| 1976 |
+
"eval_samples_per_second": 7.15,
|
| 1977 |
+
"eval_steps_per_second": 2.103,
|
| 1978 |
+
"eval_wer": 0.3075089392133492,
|
| 1979 |
+
"step": 1958
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 89.09,
|
| 1983 |
+
"learning_rate": 4.474885844748858e-05,
|
| 1984 |
+
"loss": 0.2616,
|
| 1985 |
+
"step": 1960
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 89.53,
|
| 1989 |
+
"learning_rate": 4.2922374429223744e-05,
|
| 1990 |
+
"loss": 0.2526,
|
| 1991 |
+
"step": 1970
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 89.98,
|
| 1995 |
+
"learning_rate": 4.1095890410958905e-05,
|
| 1996 |
+
"loss": 0.2364,
|
| 1997 |
+
"step": 1980
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 89.98,
|
| 2001 |
+
"eval_loss": 0.592748761177063,
|
| 2002 |
+
"eval_runtime": 2.3694,
|
| 2003 |
+
"eval_samples_per_second": 7.175,
|
| 2004 |
+
"eval_steps_per_second": 2.11,
|
| 2005 |
+
"eval_wer": 0.3039332538736591,
|
| 2006 |
+
"step": 1980
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 90.44,
|
| 2010 |
+
"learning_rate": 3.9269406392694066e-05,
|
| 2011 |
+
"loss": 0.2658,
|
| 2012 |
+
"step": 1990
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 90.89,
|
| 2016 |
+
"learning_rate": 3.744292237442922e-05,
|
| 2017 |
+
"loss": 0.2812,
|
| 2018 |
+
"step": 2000
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 90.98,
|
| 2022 |
+
"eval_loss": 0.5713174343109131,
|
| 2023 |
+
"eval_runtime": 2.3963,
|
| 2024 |
+
"eval_samples_per_second": 7.094,
|
| 2025 |
+
"eval_steps_per_second": 2.087,
|
| 2026 |
+
"eval_wer": 0.31227651966626935,
|
| 2027 |
+
"step": 2002
|
| 2028 |
+
},
|
| 2029 |
+
{
|
| 2030 |
+
"epoch": 91.36,
|
| 2031 |
+
"learning_rate": 3.561643835616438e-05,
|
| 2032 |
+
"loss": 0.2737,
|
| 2033 |
+
"step": 2010
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 91.8,
|
| 2037 |
+
"learning_rate": 3.378995433789954e-05,
|
| 2038 |
+
"loss": 0.2141,
|
| 2039 |
+
"step": 2020
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 91.98,
|
| 2043 |
+
"eval_loss": 0.5742636919021606,
|
| 2044 |
+
"eval_runtime": 2.3763,
|
| 2045 |
+
"eval_samples_per_second": 7.154,
|
| 2046 |
+
"eval_steps_per_second": 2.104,
|
| 2047 |
+
"eval_wer": 0.3039332538736591,
|
| 2048 |
+
"step": 2024
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 92.27,
|
| 2052 |
+
"learning_rate": 3.1963470319634704e-05,
|
| 2053 |
+
"loss": 0.2495,
|
| 2054 |
+
"step": 2030
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 92.71,
|
| 2058 |
+
"learning_rate": 3.0136986301369862e-05,
|
| 2059 |
+
"loss": 0.2919,
|
| 2060 |
+
"step": 2040
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 92.98,
|
| 2064 |
+
"eval_loss": 0.5836674571037292,
|
| 2065 |
+
"eval_runtime": 2.3949,
|
| 2066 |
+
"eval_samples_per_second": 7.098,
|
| 2067 |
+
"eval_steps_per_second": 2.088,
|
| 2068 |
+
"eval_wer": 0.3063170441001192,
|
| 2069 |
+
"step": 2046
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 93.18,
|
| 2073 |
+
"learning_rate": 2.8310502283105023e-05,
|
| 2074 |
+
"loss": 0.2553,
|
| 2075 |
+
"step": 2050
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 93.62,
|
| 2079 |
+
"learning_rate": 2.6484018264840184e-05,
|
| 2080 |
+
"loss": 0.2288,
|
| 2081 |
+
"step": 2060
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 93.98,
|
| 2085 |
+
"eval_loss": 0.5859872102737427,
|
| 2086 |
+
"eval_runtime": 2.3921,
|
| 2087 |
+
"eval_samples_per_second": 7.107,
|
| 2088 |
+
"eval_steps_per_second": 2.09,
|
| 2089 |
+
"eval_wer": 0.30154946364719903,
|
| 2090 |
+
"step": 2068
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 94.09,
|
| 2094 |
+
"learning_rate": 2.4657534246575342e-05,
|
| 2095 |
+
"loss": 0.2978,
|
| 2096 |
+
"step": 2070
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 94.53,
|
| 2100 |
+
"learning_rate": 2.2831050228310503e-05,
|
| 2101 |
+
"loss": 0.2202,
|
| 2102 |
+
"step": 2080
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 94.98,
|
| 2106 |
+
"learning_rate": 2.100456621004566e-05,
|
| 2107 |
+
"loss": 0.2585,
|
| 2108 |
+
"step": 2090
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 94.98,
|
| 2112 |
+
"eval_loss": 0.5775898098945618,
|
| 2113 |
+
"eval_runtime": 2.4084,
|
| 2114 |
+
"eval_samples_per_second": 7.059,
|
| 2115 |
+
"eval_steps_per_second": 2.076,
|
| 2116 |
+
"eval_wer": 0.3146603098927294,
|
| 2117 |
+
"step": 2090
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 95.44,
|
| 2121 |
+
"learning_rate": 1.9178082191780822e-05,
|
| 2122 |
+
"loss": 0.2722,
|
| 2123 |
+
"step": 2100
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 95.89,
|
| 2127 |
+
"learning_rate": 1.7351598173515983e-05,
|
| 2128 |
+
"loss": 0.2529,
|
| 2129 |
+
"step": 2110
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 95.98,
|
| 2133 |
+
"eval_loss": 0.5624773502349854,
|
| 2134 |
+
"eval_runtime": 2.4174,
|
| 2135 |
+
"eval_samples_per_second": 7.032,
|
| 2136 |
+
"eval_steps_per_second": 2.068,
|
| 2137 |
+
"eval_wer": 0.31585220500595945,
|
| 2138 |
+
"step": 2112
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 96.36,
|
| 2142 |
+
"learning_rate": 1.552511415525114e-05,
|
| 2143 |
+
"loss": 0.2285,
|
| 2144 |
+
"step": 2120
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 96.8,
|
| 2148 |
+
"learning_rate": 1.3698630136986302e-05,
|
| 2149 |
+
"loss": 0.2343,
|
| 2150 |
+
"step": 2130
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 96.98,
|
| 2154 |
+
"eval_loss": 0.5700345039367676,
|
| 2155 |
+
"eval_runtime": 2.4887,
|
| 2156 |
+
"eval_samples_per_second": 6.831,
|
| 2157 |
+
"eval_steps_per_second": 2.009,
|
| 2158 |
+
"eval_wer": 0.30870083432657924,
|
| 2159 |
+
"step": 2134
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 97.27,
|
| 2163 |
+
"learning_rate": 1.1872146118721461e-05,
|
| 2164 |
+
"loss": 0.2933,
|
| 2165 |
+
"step": 2140
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 97.71,
|
| 2169 |
+
"learning_rate": 1.004566210045662e-05,
|
| 2170 |
+
"loss": 0.2567,
|
| 2171 |
+
"step": 2150
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"epoch": 97.98,
|
| 2175 |
+
"eval_loss": 0.5728834867477417,
|
| 2176 |
+
"eval_runtime": 2.4553,
|
| 2177 |
+
"eval_samples_per_second": 6.924,
|
| 2178 |
+
"eval_steps_per_second": 2.036,
|
| 2179 |
+
"eval_wer": 0.30870083432657924,
|
| 2180 |
+
"step": 2156
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 98.18,
|
| 2184 |
+
"learning_rate": 8.21917808219178e-06,
|
| 2185 |
+
"loss": 0.2421,
|
| 2186 |
+
"step": 2160
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 98.62,
|
| 2190 |
+
"learning_rate": 6.39269406392694e-06,
|
| 2191 |
+
"loss": 0.2448,
|
| 2192 |
+
"step": 2170
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 98.98,
|
| 2196 |
+
"eval_loss": 0.5728344917297363,
|
| 2197 |
+
"eval_runtime": 2.4689,
|
| 2198 |
+
"eval_samples_per_second": 6.886,
|
| 2199 |
+
"eval_steps_per_second": 2.025,
|
| 2200 |
+
"eval_wer": 0.3110846245530393,
|
| 2201 |
+
"step": 2178
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 99.09,
|
| 2205 |
+
"learning_rate": 4.566210045662101e-06,
|
| 2206 |
+
"loss": 0.2497,
|
| 2207 |
+
"step": 2180
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 99.53,
|
| 2211 |
+
"learning_rate": 2.7397260273972604e-06,
|
| 2212 |
+
"loss": 0.2456,
|
| 2213 |
+
"step": 2190
|
| 2214 |
+
},
|
| 2215 |
+
{
|
| 2216 |
+
"epoch": 99.98,
|
| 2217 |
+
"learning_rate": 9.132420091324201e-07,
|
| 2218 |
+
"loss": 0.2501,
|
| 2219 |
+
"step": 2200
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"epoch": 99.98,
|
| 2223 |
+
"eval_loss": 0.5744234323501587,
|
| 2224 |
+
"eval_runtime": 2.4546,
|
| 2225 |
+
"eval_samples_per_second": 6.926,
|
| 2226 |
+
"eval_steps_per_second": 2.037,
|
| 2227 |
+
"eval_wer": 0.3098927294398093,
|
| 2228 |
+
"step": 2200
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 99.98,
|
| 2232 |
+
"step": 2200,
|
| 2233 |
+
"total_flos": 1.783157786698179e+18,
|
| 2234 |
+
"train_loss": 0.5098017852956599,
|
| 2235 |
+
"train_runtime": 3993.9176,
|
| 2236 |
+
"train_samples_per_second": 4.482,
|
| 2237 |
+
"train_steps_per_second": 0.551
|
| 2238 |
+
}
|
| 2239 |
+
],
|
| 2240 |
+
"max_steps": 2200,
|
| 2241 |
+
"num_train_epochs": 100,
|
| 2242 |
+
"total_flos": 1.783157786698179e+18,
|
| 2243 |
+
"trial_name": null,
|
| 2244 |
+
"trial_params": null
|
| 2245 |
+
}
|