End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Nov25_12-47-54_3eaf2a5ef33d/events.out.tfevents.1669384228.3eaf2a5ef33d.2357.2 +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": 0.5028899908065796,
|
| 4 |
+
"eval_runtime": 2.7223,
|
| 5 |
+
"eval_samples": 17,
|
| 6 |
+
"eval_samples_per_second": 6.245,
|
| 7 |
+
"eval_steps_per_second": 1.837,
|
| 8 |
+
"eval_wer": 0.31777777777777777,
|
| 9 |
+
"train_loss": 0.9807351756095887,
|
| 10 |
+
"train_runtime": 3338.9131,
|
| 11 |
+
"train_samples": 141,
|
| 12 |
+
"train_samples_per_second": 4.223,
|
| 13 |
+
"train_steps_per_second": 0.27
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_loss": 0.5028899908065796,
|
| 4 |
+
"eval_runtime": 2.7223,
|
| 5 |
+
"eval_samples": 17,
|
| 6 |
+
"eval_samples_per_second": 6.245,
|
| 7 |
+
"eval_steps_per_second": 1.837,
|
| 8 |
+
"eval_wer": 0.31777777777777777
|
| 9 |
+
}
|
runs/Nov25_12-47-54_3eaf2a5ef33d/events.out.tfevents.1669384228.3eaf2a5ef33d.2357.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edc69567a4f30ec0d036f0cdb63994b7fdea3c76f89dbd459c677e9575426cbd
|
| 3 |
+
size 358
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"train_loss": 0.9807351756095887,
|
| 4 |
+
"train_runtime": 3338.9131,
|
| 5 |
+
"train_samples": 141,
|
| 6 |
+
"train_samples_per_second": 4.223,
|
| 7 |
+
"train_steps_per_second": 0.27
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1465 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5028899908065796,
|
| 3 |
+
"best_model_checkpoint": "ai-light-dance_drums_ft_pretrain_wav2vec2-base-new_onset-idmt-2_8k/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": 101.80458068847656,
|
| 13 |
+
"eval_runtime": 2.5283,
|
| 14 |
+
"eval_samples_per_second": 6.724,
|
| 15 |
+
"eval_steps_per_second": 1.978,
|
| 16 |
+
"eval_wer": 0.98,
|
| 17 |
+
"step": 9
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.11,
|
| 21 |
+
"learning_rate": 7e-05,
|
| 22 |
+
"loss": 17.4958,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"eval_loss": 82.49200439453125,
|
| 28 |
+
"eval_runtime": 2.6724,
|
| 29 |
+
"eval_samples_per_second": 6.361,
|
| 30 |
+
"eval_steps_per_second": 1.871,
|
| 31 |
+
"eval_wer": 1.0,
|
| 32 |
+
"step": 18
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.22,
|
| 36 |
+
"learning_rate": 0.00015999999999999999,
|
| 37 |
+
"loss": 16.2087,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"eval_loss": 36.138763427734375,
|
| 43 |
+
"eval_runtime": 2.6141,
|
| 44 |
+
"eval_samples_per_second": 6.503,
|
| 45 |
+
"eval_steps_per_second": 1.913,
|
| 46 |
+
"eval_wer": 1.0,
|
| 47 |
+
"step": 27
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.33,
|
| 51 |
+
"learning_rate": 0.00026,
|
| 52 |
+
"loss": 6.2942,
|
| 53 |
+
"step": 30
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 4.0,
|
| 57 |
+
"eval_loss": 8.326688766479492,
|
| 58 |
+
"eval_runtime": 2.6808,
|
| 59 |
+
"eval_samples_per_second": 6.341,
|
| 60 |
+
"eval_steps_per_second": 1.865,
|
| 61 |
+
"eval_wer": 1.0,
|
| 62 |
+
"step": 36
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.44,
|
| 66 |
+
"learning_rate": 0.0002979310344827586,
|
| 67 |
+
"loss": 2.0411,
|
| 68 |
+
"step": 40
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.0,
|
| 72 |
+
"eval_loss": 6.8215179443359375,
|
| 73 |
+
"eval_runtime": 2.696,
|
| 74 |
+
"eval_samples_per_second": 6.306,
|
| 75 |
+
"eval_steps_per_second": 1.855,
|
| 76 |
+
"eval_wer": 1.0,
|
| 77 |
+
"step": 45
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 5.56,
|
| 81 |
+
"learning_rate": 0.00029448275862068964,
|
| 82 |
+
"loss": 1.554,
|
| 83 |
+
"step": 50
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 6.0,
|
| 87 |
+
"eval_loss": 5.384669780731201,
|
| 88 |
+
"eval_runtime": 2.7298,
|
| 89 |
+
"eval_samples_per_second": 6.228,
|
| 90 |
+
"eval_steps_per_second": 1.832,
|
| 91 |
+
"eval_wer": 1.0,
|
| 92 |
+
"step": 54
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 6.67,
|
| 96 |
+
"learning_rate": 0.00029103448275862064,
|
| 97 |
+
"loss": 1.6215,
|
| 98 |
+
"step": 60
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 7.0,
|
| 102 |
+
"eval_loss": 4.4644598960876465,
|
| 103 |
+
"eval_runtime": 2.6233,
|
| 104 |
+
"eval_samples_per_second": 6.48,
|
| 105 |
+
"eval_steps_per_second": 1.906,
|
| 106 |
+
"eval_wer": 1.0,
|
| 107 |
+
"step": 63
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 7.78,
|
| 111 |
+
"learning_rate": 0.0002875862068965517,
|
| 112 |
+
"loss": 1.4962,
|
| 113 |
+
"step": 70
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 8.0,
|
| 117 |
+
"eval_loss": 3.221142053604126,
|
| 118 |
+
"eval_runtime": 2.7171,
|
| 119 |
+
"eval_samples_per_second": 6.257,
|
| 120 |
+
"eval_steps_per_second": 1.84,
|
| 121 |
+
"eval_wer": 1.0,
|
| 122 |
+
"step": 72
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 8.89,
|
| 126 |
+
"learning_rate": 0.00028413793103448275,
|
| 127 |
+
"loss": 1.3825,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 9.0,
|
| 132 |
+
"eval_loss": 2.5513429641723633,
|
| 133 |
+
"eval_runtime": 2.6858,
|
| 134 |
+
"eval_samples_per_second": 6.329,
|
| 135 |
+
"eval_steps_per_second": 1.862,
|
| 136 |
+
"eval_wer": 1.0,
|
| 137 |
+
"step": 81
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 10.0,
|
| 141 |
+
"learning_rate": 0.00028068965517241375,
|
| 142 |
+
"loss": 1.3443,
|
| 143 |
+
"step": 90
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 10.0,
|
| 147 |
+
"eval_loss": 2.8581652641296387,
|
| 148 |
+
"eval_runtime": 2.7157,
|
| 149 |
+
"eval_samples_per_second": 6.26,
|
| 150 |
+
"eval_steps_per_second": 1.841,
|
| 151 |
+
"eval_wer": 1.0,
|
| 152 |
+
"step": 90
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 11.0,
|
| 156 |
+
"eval_loss": 2.544593572616577,
|
| 157 |
+
"eval_runtime": 2.6215,
|
| 158 |
+
"eval_samples_per_second": 6.485,
|
| 159 |
+
"eval_steps_per_second": 1.907,
|
| 160 |
+
"eval_wer": 1.0,
|
| 161 |
+
"step": 99
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 11.11,
|
| 165 |
+
"learning_rate": 0.0002772413793103448,
|
| 166 |
+
"loss": 1.3096,
|
| 167 |
+
"step": 100
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 12.0,
|
| 171 |
+
"eval_loss": 2.021075963973999,
|
| 172 |
+
"eval_runtime": 2.6505,
|
| 173 |
+
"eval_samples_per_second": 6.414,
|
| 174 |
+
"eval_steps_per_second": 1.886,
|
| 175 |
+
"eval_wer": 0.9955555555555555,
|
| 176 |
+
"step": 108
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 12.22,
|
| 180 |
+
"learning_rate": 0.0002737931034482758,
|
| 181 |
+
"loss": 1.3361,
|
| 182 |
+
"step": 110
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 13.0,
|
| 186 |
+
"eval_loss": 1.8110406398773193,
|
| 187 |
+
"eval_runtime": 2.6015,
|
| 188 |
+
"eval_samples_per_second": 6.535,
|
| 189 |
+
"eval_steps_per_second": 1.922,
|
| 190 |
+
"eval_wer": 0.9944444444444445,
|
| 191 |
+
"step": 117
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 13.33,
|
| 195 |
+
"learning_rate": 0.00027034482758620687,
|
| 196 |
+
"loss": 1.2862,
|
| 197 |
+
"step": 120
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 14.0,
|
| 201 |
+
"eval_loss": 1.7796473503112793,
|
| 202 |
+
"eval_runtime": 2.6116,
|
| 203 |
+
"eval_samples_per_second": 6.509,
|
| 204 |
+
"eval_steps_per_second": 1.915,
|
| 205 |
+
"eval_wer": 0.9933333333333333,
|
| 206 |
+
"step": 126
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 14.44,
|
| 210 |
+
"learning_rate": 0.0002668965517241379,
|
| 211 |
+
"loss": 1.2556,
|
| 212 |
+
"step": 130
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 15.0,
|
| 216 |
+
"eval_loss": 1.730082631111145,
|
| 217 |
+
"eval_runtime": 2.5934,
|
| 218 |
+
"eval_samples_per_second": 6.555,
|
| 219 |
+
"eval_steps_per_second": 1.928,
|
| 220 |
+
"eval_wer": 0.9922222222222222,
|
| 221 |
+
"step": 135
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 15.56,
|
| 225 |
+
"learning_rate": 0.0002634482758620689,
|
| 226 |
+
"loss": 1.1959,
|
| 227 |
+
"step": 140
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 16.0,
|
| 231 |
+
"eval_loss": 1.4244635105133057,
|
| 232 |
+
"eval_runtime": 2.6511,
|
| 233 |
+
"eval_samples_per_second": 6.412,
|
| 234 |
+
"eval_steps_per_second": 1.886,
|
| 235 |
+
"eval_wer": 0.9988888888888889,
|
| 236 |
+
"step": 144
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 16.67,
|
| 240 |
+
"learning_rate": 0.00026,
|
| 241 |
+
"loss": 1.1161,
|
| 242 |
+
"step": 150
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 17.0,
|
| 246 |
+
"eval_loss": 1.1931955814361572,
|
| 247 |
+
"eval_runtime": 2.6143,
|
| 248 |
+
"eval_samples_per_second": 6.503,
|
| 249 |
+
"eval_steps_per_second": 1.913,
|
| 250 |
+
"eval_wer": 0.5677777777777778,
|
| 251 |
+
"step": 153
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 17.78,
|
| 255 |
+
"learning_rate": 0.00025655172413793103,
|
| 256 |
+
"loss": 0.8853,
|
| 257 |
+
"step": 160
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 18.0,
|
| 261 |
+
"eval_loss": 1.2725539207458496,
|
| 262 |
+
"eval_runtime": 2.6031,
|
| 263 |
+
"eval_samples_per_second": 6.531,
|
| 264 |
+
"eval_steps_per_second": 1.921,
|
| 265 |
+
"eval_wer": 0.4922222222222222,
|
| 266 |
+
"step": 162
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 18.89,
|
| 270 |
+
"learning_rate": 0.00025310344827586203,
|
| 271 |
+
"loss": 0.7996,
|
| 272 |
+
"step": 170
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 19.0,
|
| 276 |
+
"eval_loss": 1.0841138362884521,
|
| 277 |
+
"eval_runtime": 2.6115,
|
| 278 |
+
"eval_samples_per_second": 6.51,
|
| 279 |
+
"eval_steps_per_second": 1.915,
|
| 280 |
+
"eval_wer": 0.5511111111111111,
|
| 281 |
+
"step": 171
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 20.0,
|
| 285 |
+
"learning_rate": 0.0002496551724137931,
|
| 286 |
+
"loss": 0.8165,
|
| 287 |
+
"step": 180
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 20.0,
|
| 291 |
+
"eval_loss": 1.406151294708252,
|
| 292 |
+
"eval_runtime": 2.6236,
|
| 293 |
+
"eval_samples_per_second": 6.48,
|
| 294 |
+
"eval_steps_per_second": 1.906,
|
| 295 |
+
"eval_wer": 0.4411111111111111,
|
| 296 |
+
"step": 180
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 21.0,
|
| 300 |
+
"eval_loss": 1.4218931198120117,
|
| 301 |
+
"eval_runtime": 2.6036,
|
| 302 |
+
"eval_samples_per_second": 6.529,
|
| 303 |
+
"eval_steps_per_second": 1.92,
|
| 304 |
+
"eval_wer": 0.33666666666666667,
|
| 305 |
+
"step": 189
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 21.11,
|
| 309 |
+
"learning_rate": 0.0002462068965517241,
|
| 310 |
+
"loss": 0.6807,
|
| 311 |
+
"step": 190
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 22.0,
|
| 315 |
+
"eval_loss": 1.2106943130493164,
|
| 316 |
+
"eval_runtime": 2.6208,
|
| 317 |
+
"eval_samples_per_second": 6.486,
|
| 318 |
+
"eval_steps_per_second": 1.908,
|
| 319 |
+
"eval_wer": 0.33444444444444443,
|
| 320 |
+
"step": 198
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 22.22,
|
| 324 |
+
"learning_rate": 0.00024275862068965515,
|
| 325 |
+
"loss": 0.7315,
|
| 326 |
+
"step": 200
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 23.0,
|
| 330 |
+
"eval_loss": 1.1419602632522583,
|
| 331 |
+
"eval_runtime": 2.6272,
|
| 332 |
+
"eval_samples_per_second": 6.471,
|
| 333 |
+
"eval_steps_per_second": 1.903,
|
| 334 |
+
"eval_wer": 0.3188888888888889,
|
| 335 |
+
"step": 207
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 23.33,
|
| 339 |
+
"learning_rate": 0.00023931034482758617,
|
| 340 |
+
"loss": 0.6203,
|
| 341 |
+
"step": 210
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 24.0,
|
| 345 |
+
"eval_loss": 1.0770384073257446,
|
| 346 |
+
"eval_runtime": 2.6173,
|
| 347 |
+
"eval_samples_per_second": 6.495,
|
| 348 |
+
"eval_steps_per_second": 1.91,
|
| 349 |
+
"eval_wer": 0.37777777777777777,
|
| 350 |
+
"step": 216
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 24.44,
|
| 354 |
+
"learning_rate": 0.00023586206896551723,
|
| 355 |
+
"loss": 0.6552,
|
| 356 |
+
"step": 220
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 25.0,
|
| 360 |
+
"eval_loss": 1.1095293760299683,
|
| 361 |
+
"eval_runtime": 2.6206,
|
| 362 |
+
"eval_samples_per_second": 6.487,
|
| 363 |
+
"eval_steps_per_second": 1.908,
|
| 364 |
+
"eval_wer": 0.3788888888888889,
|
| 365 |
+
"step": 225
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 25.56,
|
| 369 |
+
"learning_rate": 0.00023241379310344826,
|
| 370 |
+
"loss": 0.5618,
|
| 371 |
+
"step": 230
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 26.0,
|
| 375 |
+
"eval_loss": 1.0003583431243896,
|
| 376 |
+
"eval_runtime": 2.6097,
|
| 377 |
+
"eval_samples_per_second": 6.514,
|
| 378 |
+
"eval_steps_per_second": 1.916,
|
| 379 |
+
"eval_wer": 0.3477777777777778,
|
| 380 |
+
"step": 234
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 26.67,
|
| 384 |
+
"learning_rate": 0.0002289655172413793,
|
| 385 |
+
"loss": 0.5311,
|
| 386 |
+
"step": 240
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 27.0,
|
| 390 |
+
"eval_loss": 0.8810951113700867,
|
| 391 |
+
"eval_runtime": 2.705,
|
| 392 |
+
"eval_samples_per_second": 6.285,
|
| 393 |
+
"eval_steps_per_second": 1.848,
|
| 394 |
+
"eval_wer": 0.33111111111111113,
|
| 395 |
+
"step": 243
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 27.78,
|
| 399 |
+
"learning_rate": 0.00022551724137931031,
|
| 400 |
+
"loss": 0.5391,
|
| 401 |
+
"step": 250
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 28.0,
|
| 405 |
+
"eval_loss": 0.8162650465965271,
|
| 406 |
+
"eval_runtime": 2.6062,
|
| 407 |
+
"eval_samples_per_second": 6.523,
|
| 408 |
+
"eval_steps_per_second": 1.919,
|
| 409 |
+
"eval_wer": 0.36777777777777776,
|
| 410 |
+
"step": 252
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 28.89,
|
| 414 |
+
"learning_rate": 0.00022206896551724134,
|
| 415 |
+
"loss": 0.5275,
|
| 416 |
+
"step": 260
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 29.0,
|
| 420 |
+
"eval_loss": 0.9999949336051941,
|
| 421 |
+
"eval_runtime": 2.6225,
|
| 422 |
+
"eval_samples_per_second": 6.482,
|
| 423 |
+
"eval_steps_per_second": 1.907,
|
| 424 |
+
"eval_wer": 0.33111111111111113,
|
| 425 |
+
"step": 261
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 30.0,
|
| 429 |
+
"learning_rate": 0.0002186206896551724,
|
| 430 |
+
"loss": 0.4965,
|
| 431 |
+
"step": 270
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 30.0,
|
| 435 |
+
"eval_loss": 0.7320018410682678,
|
| 436 |
+
"eval_runtime": 2.6343,
|
| 437 |
+
"eval_samples_per_second": 6.453,
|
| 438 |
+
"eval_steps_per_second": 1.898,
|
| 439 |
+
"eval_wer": 0.37,
|
| 440 |
+
"step": 270
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 31.0,
|
| 444 |
+
"eval_loss": 0.9642557501792908,
|
| 445 |
+
"eval_runtime": 2.6199,
|
| 446 |
+
"eval_samples_per_second": 6.489,
|
| 447 |
+
"eval_steps_per_second": 1.909,
|
| 448 |
+
"eval_wer": 0.3388888888888889,
|
| 449 |
+
"step": 279
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 31.11,
|
| 453 |
+
"learning_rate": 0.00021517241379310343,
|
| 454 |
+
"loss": 0.4909,
|
| 455 |
+
"step": 280
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 32.0,
|
| 459 |
+
"eval_loss": 0.7662584185600281,
|
| 460 |
+
"eval_runtime": 2.6092,
|
| 461 |
+
"eval_samples_per_second": 6.515,
|
| 462 |
+
"eval_steps_per_second": 1.916,
|
| 463 |
+
"eval_wer": 0.35888888888888887,
|
| 464 |
+
"step": 288
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 32.22,
|
| 468 |
+
"learning_rate": 0.00021172413793103445,
|
| 469 |
+
"loss": 0.5218,
|
| 470 |
+
"step": 290
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 33.0,
|
| 474 |
+
"eval_loss": 0.9004315733909607,
|
| 475 |
+
"eval_runtime": 2.6009,
|
| 476 |
+
"eval_samples_per_second": 6.536,
|
| 477 |
+
"eval_steps_per_second": 1.922,
|
| 478 |
+
"eval_wer": 0.3488888888888889,
|
| 479 |
+
"step": 297
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 33.33,
|
| 483 |
+
"learning_rate": 0.0002082758620689655,
|
| 484 |
+
"loss": 0.4991,
|
| 485 |
+
"step": 300
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 34.0,
|
| 489 |
+
"eval_loss": 0.7342296242713928,
|
| 490 |
+
"eval_runtime": 2.6253,
|
| 491 |
+
"eval_samples_per_second": 6.475,
|
| 492 |
+
"eval_steps_per_second": 1.905,
|
| 493 |
+
"eval_wer": 0.38,
|
| 494 |
+
"step": 306
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 34.44,
|
| 498 |
+
"learning_rate": 0.00020482758620689654,
|
| 499 |
+
"loss": 0.4883,
|
| 500 |
+
"step": 310
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 35.0,
|
| 504 |
+
"eval_loss": 0.7959361672401428,
|
| 505 |
+
"eval_runtime": 2.6169,
|
| 506 |
+
"eval_samples_per_second": 6.496,
|
| 507 |
+
"eval_steps_per_second": 1.911,
|
| 508 |
+
"eval_wer": 0.3388888888888889,
|
| 509 |
+
"step": 315
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 35.56,
|
| 513 |
+
"learning_rate": 0.0002013793103448276,
|
| 514 |
+
"loss": 0.4902,
|
| 515 |
+
"step": 320
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 36.0,
|
| 519 |
+
"eval_loss": 0.6891648173332214,
|
| 520 |
+
"eval_runtime": 2.6322,
|
| 521 |
+
"eval_samples_per_second": 6.458,
|
| 522 |
+
"eval_steps_per_second": 1.9,
|
| 523 |
+
"eval_wer": 0.3377777777777778,
|
| 524 |
+
"step": 324
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 36.67,
|
| 528 |
+
"learning_rate": 0.0001979310344827586,
|
| 529 |
+
"loss": 0.4447,
|
| 530 |
+
"step": 330
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 37.0,
|
| 534 |
+
"eval_loss": 0.6479607224464417,
|
| 535 |
+
"eval_runtime": 2.5996,
|
| 536 |
+
"eval_samples_per_second": 6.539,
|
| 537 |
+
"eval_steps_per_second": 1.923,
|
| 538 |
+
"eval_wer": 0.3333333333333333,
|
| 539 |
+
"step": 333
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 37.78,
|
| 543 |
+
"learning_rate": 0.00019448275862068962,
|
| 544 |
+
"loss": 0.4458,
|
| 545 |
+
"step": 340
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 38.0,
|
| 549 |
+
"eval_loss": 0.6198386549949646,
|
| 550 |
+
"eval_runtime": 2.6161,
|
| 551 |
+
"eval_samples_per_second": 6.498,
|
| 552 |
+
"eval_steps_per_second": 1.911,
|
| 553 |
+
"eval_wer": 0.3333333333333333,
|
| 554 |
+
"step": 342
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 38.89,
|
| 558 |
+
"learning_rate": 0.00019103448275862068,
|
| 559 |
+
"loss": 0.4607,
|
| 560 |
+
"step": 350
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 39.0,
|
| 564 |
+
"eval_loss": 0.6080996990203857,
|
| 565 |
+
"eval_runtime": 2.6354,
|
| 566 |
+
"eval_samples_per_second": 6.451,
|
| 567 |
+
"eval_steps_per_second": 1.897,
|
| 568 |
+
"eval_wer": 0.3111111111111111,
|
| 569 |
+
"step": 351
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 40.0,
|
| 573 |
+
"learning_rate": 0.0001875862068965517,
|
| 574 |
+
"loss": 0.4352,
|
| 575 |
+
"step": 360
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 40.0,
|
| 579 |
+
"eval_loss": 0.6748089790344238,
|
| 580 |
+
"eval_runtime": 2.6402,
|
| 581 |
+
"eval_samples_per_second": 6.439,
|
| 582 |
+
"eval_steps_per_second": 1.894,
|
| 583 |
+
"eval_wer": 0.31555555555555553,
|
| 584 |
+
"step": 360
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 41.0,
|
| 588 |
+
"eval_loss": 0.6885289549827576,
|
| 589 |
+
"eval_runtime": 2.6179,
|
| 590 |
+
"eval_samples_per_second": 6.494,
|
| 591 |
+
"eval_steps_per_second": 1.91,
|
| 592 |
+
"eval_wer": 0.32555555555555554,
|
| 593 |
+
"step": 369
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 41.11,
|
| 597 |
+
"learning_rate": 0.00018413793103448273,
|
| 598 |
+
"loss": 0.4286,
|
| 599 |
+
"step": 370
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 42.0,
|
| 603 |
+
"eval_loss": 0.6806181073188782,
|
| 604 |
+
"eval_runtime": 2.614,
|
| 605 |
+
"eval_samples_per_second": 6.504,
|
| 606 |
+
"eval_steps_per_second": 1.913,
|
| 607 |
+
"eval_wer": 0.3333333333333333,
|
| 608 |
+
"step": 378
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 42.22,
|
| 612 |
+
"learning_rate": 0.0001806896551724138,
|
| 613 |
+
"loss": 0.4314,
|
| 614 |
+
"step": 380
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 43.0,
|
| 618 |
+
"eval_loss": 0.7854954600334167,
|
| 619 |
+
"eval_runtime": 2.5985,
|
| 620 |
+
"eval_samples_per_second": 6.542,
|
| 621 |
+
"eval_steps_per_second": 1.924,
|
| 622 |
+
"eval_wer": 0.32222222222222224,
|
| 623 |
+
"step": 387
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 43.33,
|
| 627 |
+
"learning_rate": 0.00017724137931034482,
|
| 628 |
+
"loss": 0.4476,
|
| 629 |
+
"step": 390
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 44.0,
|
| 633 |
+
"eval_loss": 0.6569249629974365,
|
| 634 |
+
"eval_runtime": 2.5902,
|
| 635 |
+
"eval_samples_per_second": 6.563,
|
| 636 |
+
"eval_steps_per_second": 1.93,
|
| 637 |
+
"eval_wer": 0.31444444444444447,
|
| 638 |
+
"step": 396
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 44.44,
|
| 642 |
+
"learning_rate": 0.00017379310344827587,
|
| 643 |
+
"loss": 0.4815,
|
| 644 |
+
"step": 400
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 45.0,
|
| 648 |
+
"eval_loss": 0.5388519167900085,
|
| 649 |
+
"eval_runtime": 2.6157,
|
| 650 |
+
"eval_samples_per_second": 6.499,
|
| 651 |
+
"eval_steps_per_second": 1.912,
|
| 652 |
+
"eval_wer": 0.30333333333333334,
|
| 653 |
+
"step": 405
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 45.56,
|
| 657 |
+
"learning_rate": 0.00017034482758620687,
|
| 658 |
+
"loss": 0.36,
|
| 659 |
+
"step": 410
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 46.0,
|
| 663 |
+
"eval_loss": 0.5549790263175964,
|
| 664 |
+
"eval_runtime": 2.5979,
|
| 665 |
+
"eval_samples_per_second": 6.544,
|
| 666 |
+
"eval_steps_per_second": 1.925,
|
| 667 |
+
"eval_wer": 0.3011111111111111,
|
| 668 |
+
"step": 414
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 46.67,
|
| 672 |
+
"learning_rate": 0.0001668965517241379,
|
| 673 |
+
"loss": 0.4516,
|
| 674 |
+
"step": 420
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 47.0,
|
| 678 |
+
"eval_loss": 0.5923512578010559,
|
| 679 |
+
"eval_runtime": 2.6204,
|
| 680 |
+
"eval_samples_per_second": 6.488,
|
| 681 |
+
"eval_steps_per_second": 1.908,
|
| 682 |
+
"eval_wer": 0.31444444444444447,
|
| 683 |
+
"step": 423
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 47.78,
|
| 687 |
+
"learning_rate": 0.00016344827586206896,
|
| 688 |
+
"loss": 0.3682,
|
| 689 |
+
"step": 430
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 48.0,
|
| 693 |
+
"eval_loss": 0.727486789226532,
|
| 694 |
+
"eval_runtime": 2.6112,
|
| 695 |
+
"eval_samples_per_second": 6.51,
|
| 696 |
+
"eval_steps_per_second": 1.915,
|
| 697 |
+
"eval_wer": 0.3055555555555556,
|
| 698 |
+
"step": 432
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 48.89,
|
| 702 |
+
"learning_rate": 0.00015999999999999999,
|
| 703 |
+
"loss": 0.4371,
|
| 704 |
+
"step": 440
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 49.0,
|
| 708 |
+
"eval_loss": 0.7050825357437134,
|
| 709 |
+
"eval_runtime": 2.6034,
|
| 710 |
+
"eval_samples_per_second": 6.53,
|
| 711 |
+
"eval_steps_per_second": 1.921,
|
| 712 |
+
"eval_wer": 0.3088888888888889,
|
| 713 |
+
"step": 441
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 50.0,
|
| 717 |
+
"learning_rate": 0.00015655172413793101,
|
| 718 |
+
"loss": 0.4004,
|
| 719 |
+
"step": 450
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 50.0,
|
| 723 |
+
"eval_loss": 0.5668944716453552,
|
| 724 |
+
"eval_runtime": 2.6536,
|
| 725 |
+
"eval_samples_per_second": 6.406,
|
| 726 |
+
"eval_steps_per_second": 1.884,
|
| 727 |
+
"eval_wer": 0.30777777777777776,
|
| 728 |
+
"step": 450
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 51.0,
|
| 732 |
+
"eval_loss": 0.5028899908065796,
|
| 733 |
+
"eval_runtime": 2.6202,
|
| 734 |
+
"eval_samples_per_second": 6.488,
|
| 735 |
+
"eval_steps_per_second": 1.908,
|
| 736 |
+
"eval_wer": 0.31777777777777777,
|
| 737 |
+
"step": 459
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 51.11,
|
| 741 |
+
"learning_rate": 0.00015310344827586207,
|
| 742 |
+
"loss": 0.3298,
|
| 743 |
+
"step": 460
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 52.0,
|
| 747 |
+
"eval_loss": 0.6150208711624146,
|
| 748 |
+
"eval_runtime": 2.602,
|
| 749 |
+
"eval_samples_per_second": 6.534,
|
| 750 |
+
"eval_steps_per_second": 1.922,
|
| 751 |
+
"eval_wer": 0.32,
|
| 752 |
+
"step": 468
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 52.22,
|
| 756 |
+
"learning_rate": 0.00014965517241379307,
|
| 757 |
+
"loss": 0.4083,
|
| 758 |
+
"step": 470
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 53.0,
|
| 762 |
+
"eval_loss": 0.5881750583648682,
|
| 763 |
+
"eval_runtime": 2.6209,
|
| 764 |
+
"eval_samples_per_second": 6.486,
|
| 765 |
+
"eval_steps_per_second": 1.908,
|
| 766 |
+
"eval_wer": 0.33,
|
| 767 |
+
"step": 477
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 53.33,
|
| 771 |
+
"learning_rate": 0.00014620689655172413,
|
| 772 |
+
"loss": 0.4022,
|
| 773 |
+
"step": 480
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 54.0,
|
| 777 |
+
"eval_loss": 0.7253018021583557,
|
| 778 |
+
"eval_runtime": 2.6223,
|
| 779 |
+
"eval_samples_per_second": 6.483,
|
| 780 |
+
"eval_steps_per_second": 1.907,
|
| 781 |
+
"eval_wer": 0.31444444444444447,
|
| 782 |
+
"step": 486
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 54.44,
|
| 786 |
+
"learning_rate": 0.00014275862068965515,
|
| 787 |
+
"loss": 0.4465,
|
| 788 |
+
"step": 490
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 55.0,
|
| 792 |
+
"eval_loss": 0.6807547807693481,
|
| 793 |
+
"eval_runtime": 2.6014,
|
| 794 |
+
"eval_samples_per_second": 6.535,
|
| 795 |
+
"eval_steps_per_second": 1.922,
|
| 796 |
+
"eval_wer": 0.3111111111111111,
|
| 797 |
+
"step": 495
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 55.56,
|
| 801 |
+
"learning_rate": 0.0001393103448275862,
|
| 802 |
+
"loss": 0.3955,
|
| 803 |
+
"step": 500
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 56.0,
|
| 807 |
+
"eval_loss": 0.6001608967781067,
|
| 808 |
+
"eval_runtime": 2.629,
|
| 809 |
+
"eval_samples_per_second": 6.466,
|
| 810 |
+
"eval_steps_per_second": 1.902,
|
| 811 |
+
"eval_wer": 0.31333333333333335,
|
| 812 |
+
"step": 504
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 56.67,
|
| 816 |
+
"learning_rate": 0.0001358620689655172,
|
| 817 |
+
"loss": 0.3877,
|
| 818 |
+
"step": 510
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 57.0,
|
| 822 |
+
"eval_loss": 0.7593300938606262,
|
| 823 |
+
"eval_runtime": 2.6173,
|
| 824 |
+
"eval_samples_per_second": 6.495,
|
| 825 |
+
"eval_steps_per_second": 1.91,
|
| 826 |
+
"eval_wer": 0.3055555555555556,
|
| 827 |
+
"step": 513
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 57.78,
|
| 831 |
+
"learning_rate": 0.00013241379310344827,
|
| 832 |
+
"loss": 0.3486,
|
| 833 |
+
"step": 520
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 58.0,
|
| 837 |
+
"eval_loss": 0.6764330863952637,
|
| 838 |
+
"eval_runtime": 2.646,
|
| 839 |
+
"eval_samples_per_second": 6.425,
|
| 840 |
+
"eval_steps_per_second": 1.89,
|
| 841 |
+
"eval_wer": 0.3188888888888889,
|
| 842 |
+
"step": 522
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 58.89,
|
| 846 |
+
"learning_rate": 0.0001289655172413793,
|
| 847 |
+
"loss": 0.3782,
|
| 848 |
+
"step": 530
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 59.0,
|
| 852 |
+
"eval_loss": 0.6771883368492126,
|
| 853 |
+
"eval_runtime": 2.6301,
|
| 854 |
+
"eval_samples_per_second": 6.464,
|
| 855 |
+
"eval_steps_per_second": 1.901,
|
| 856 |
+
"eval_wer": 0.31333333333333335,
|
| 857 |
+
"step": 531
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 60.0,
|
| 861 |
+
"learning_rate": 0.00012551724137931035,
|
| 862 |
+
"loss": 0.3599,
|
| 863 |
+
"step": 540
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 60.0,
|
| 867 |
+
"eval_loss": 0.8846335411071777,
|
| 868 |
+
"eval_runtime": 2.615,
|
| 869 |
+
"eval_samples_per_second": 6.501,
|
| 870 |
+
"eval_steps_per_second": 1.912,
|
| 871 |
+
"eval_wer": 0.3111111111111111,
|
| 872 |
+
"step": 540
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 61.0,
|
| 876 |
+
"eval_loss": 0.945833683013916,
|
| 877 |
+
"eval_runtime": 2.5924,
|
| 878 |
+
"eval_samples_per_second": 6.558,
|
| 879 |
+
"eval_steps_per_second": 1.929,
|
| 880 |
+
"eval_wer": 0.3233333333333333,
|
| 881 |
+
"step": 549
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 61.11,
|
| 885 |
+
"learning_rate": 0.00012206896551724136,
|
| 886 |
+
"loss": 0.3424,
|
| 887 |
+
"step": 550
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 62.0,
|
| 891 |
+
"eval_loss": 0.8398585319519043,
|
| 892 |
+
"eval_runtime": 2.6035,
|
| 893 |
+
"eval_samples_per_second": 6.53,
|
| 894 |
+
"eval_steps_per_second": 1.921,
|
| 895 |
+
"eval_wer": 0.3233333333333333,
|
| 896 |
+
"step": 558
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 62.22,
|
| 900 |
+
"learning_rate": 0.0001186206896551724,
|
| 901 |
+
"loss": 0.3652,
|
| 902 |
+
"step": 560
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 63.0,
|
| 906 |
+
"eval_loss": 0.8266441822052002,
|
| 907 |
+
"eval_runtime": 2.6064,
|
| 908 |
+
"eval_samples_per_second": 6.522,
|
| 909 |
+
"eval_steps_per_second": 1.918,
|
| 910 |
+
"eval_wer": 0.31333333333333335,
|
| 911 |
+
"step": 567
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 63.33,
|
| 915 |
+
"learning_rate": 0.00011517241379310343,
|
| 916 |
+
"loss": 0.3327,
|
| 917 |
+
"step": 570
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 64.0,
|
| 921 |
+
"eval_loss": 0.7813167572021484,
|
| 922 |
+
"eval_runtime": 2.6355,
|
| 923 |
+
"eval_samples_per_second": 6.45,
|
| 924 |
+
"eval_steps_per_second": 1.897,
|
| 925 |
+
"eval_wer": 0.30777777777777776,
|
| 926 |
+
"step": 576
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 64.44,
|
| 930 |
+
"learning_rate": 0.00011172413793103448,
|
| 931 |
+
"loss": 0.3603,
|
| 932 |
+
"step": 580
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 65.0,
|
| 936 |
+
"eval_loss": 0.8066079616546631,
|
| 937 |
+
"eval_runtime": 2.5997,
|
| 938 |
+
"eval_samples_per_second": 6.539,
|
| 939 |
+
"eval_steps_per_second": 1.923,
|
| 940 |
+
"eval_wer": 0.31555555555555553,
|
| 941 |
+
"step": 585
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 65.56,
|
| 945 |
+
"learning_rate": 0.0001082758620689655,
|
| 946 |
+
"loss": 0.3401,
|
| 947 |
+
"step": 590
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 66.0,
|
| 951 |
+
"eval_loss": 0.7959613800048828,
|
| 952 |
+
"eval_runtime": 2.6015,
|
| 953 |
+
"eval_samples_per_second": 6.535,
|
| 954 |
+
"eval_steps_per_second": 1.922,
|
| 955 |
+
"eval_wer": 0.30666666666666664,
|
| 956 |
+
"step": 594
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 66.67,
|
| 960 |
+
"learning_rate": 0.00010482758620689655,
|
| 961 |
+
"loss": 0.3797,
|
| 962 |
+
"step": 600
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 67.0,
|
| 966 |
+
"eval_loss": 0.8513309955596924,
|
| 967 |
+
"eval_runtime": 2.6257,
|
| 968 |
+
"eval_samples_per_second": 6.474,
|
| 969 |
+
"eval_steps_per_second": 1.904,
|
| 970 |
+
"eval_wer": 0.29888888888888887,
|
| 971 |
+
"step": 603
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 67.78,
|
| 975 |
+
"learning_rate": 0.00010137931034482757,
|
| 976 |
+
"loss": 0.3353,
|
| 977 |
+
"step": 610
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 68.0,
|
| 981 |
+
"eval_loss": 0.8319157361984253,
|
| 982 |
+
"eval_runtime": 2.5993,
|
| 983 |
+
"eval_samples_per_second": 6.54,
|
| 984 |
+
"eval_steps_per_second": 1.924,
|
| 985 |
+
"eval_wer": 0.2722222222222222,
|
| 986 |
+
"step": 612
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 68.89,
|
| 990 |
+
"learning_rate": 9.793103448275862e-05,
|
| 991 |
+
"loss": 0.3909,
|
| 992 |
+
"step": 620
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 69.0,
|
| 996 |
+
"eval_loss": 0.8244246244430542,
|
| 997 |
+
"eval_runtime": 2.6313,
|
| 998 |
+
"eval_samples_per_second": 6.461,
|
| 999 |
+
"eval_steps_per_second": 1.9,
|
| 1000 |
+
"eval_wer": 0.2877777777777778,
|
| 1001 |
+
"step": 621
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 70.0,
|
| 1005 |
+
"learning_rate": 9.448275862068964e-05,
|
| 1006 |
+
"loss": 0.3263,
|
| 1007 |
+
"step": 630
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 70.0,
|
| 1011 |
+
"eval_loss": 0.9538501501083374,
|
| 1012 |
+
"eval_runtime": 2.6379,
|
| 1013 |
+
"eval_samples_per_second": 6.445,
|
| 1014 |
+
"eval_steps_per_second": 1.895,
|
| 1015 |
+
"eval_wer": 0.3022222222222222,
|
| 1016 |
+
"step": 630
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 71.0,
|
| 1020 |
+
"eval_loss": 1.002958059310913,
|
| 1021 |
+
"eval_runtime": 2.6816,
|
| 1022 |
+
"eval_samples_per_second": 6.34,
|
| 1023 |
+
"eval_steps_per_second": 1.865,
|
| 1024 |
+
"eval_wer": 0.2922222222222222,
|
| 1025 |
+
"step": 639
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 71.11,
|
| 1029 |
+
"learning_rate": 9.103448275862069e-05,
|
| 1030 |
+
"loss": 0.3102,
|
| 1031 |
+
"step": 640
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 72.0,
|
| 1035 |
+
"eval_loss": 0.9874680638313293,
|
| 1036 |
+
"eval_runtime": 2.5977,
|
| 1037 |
+
"eval_samples_per_second": 6.544,
|
| 1038 |
+
"eval_steps_per_second": 1.925,
|
| 1039 |
+
"eval_wer": 0.30444444444444446,
|
| 1040 |
+
"step": 648
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 72.22,
|
| 1044 |
+
"learning_rate": 8.758620689655171e-05,
|
| 1045 |
+
"loss": 0.3577,
|
| 1046 |
+
"step": 650
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 73.0,
|
| 1050 |
+
"eval_loss": 0.9030035138130188,
|
| 1051 |
+
"eval_runtime": 2.6088,
|
| 1052 |
+
"eval_samples_per_second": 6.516,
|
| 1053 |
+
"eval_steps_per_second": 1.917,
|
| 1054 |
+
"eval_wer": 0.29777777777777775,
|
| 1055 |
+
"step": 657
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 73.33,
|
| 1059 |
+
"learning_rate": 8.413793103448276e-05,
|
| 1060 |
+
"loss": 0.2953,
|
| 1061 |
+
"step": 660
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 74.0,
|
| 1065 |
+
"eval_loss": 0.9392061233520508,
|
| 1066 |
+
"eval_runtime": 2.5966,
|
| 1067 |
+
"eval_samples_per_second": 6.547,
|
| 1068 |
+
"eval_steps_per_second": 1.926,
|
| 1069 |
+
"eval_wer": 0.28888888888888886,
|
| 1070 |
+
"step": 666
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 74.44,
|
| 1074 |
+
"learning_rate": 8.068965517241378e-05,
|
| 1075 |
+
"loss": 0.3644,
|
| 1076 |
+
"step": 670
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 75.0,
|
| 1080 |
+
"eval_loss": 0.9088665843009949,
|
| 1081 |
+
"eval_runtime": 2.6416,
|
| 1082 |
+
"eval_samples_per_second": 6.436,
|
| 1083 |
+
"eval_steps_per_second": 1.893,
|
| 1084 |
+
"eval_wer": 0.2877777777777778,
|
| 1085 |
+
"step": 675
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 75.56,
|
| 1089 |
+
"learning_rate": 7.724137931034483e-05,
|
| 1090 |
+
"loss": 0.3231,
|
| 1091 |
+
"step": 680
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 76.0,
|
| 1095 |
+
"eval_loss": 0.926447868347168,
|
| 1096 |
+
"eval_runtime": 2.61,
|
| 1097 |
+
"eval_samples_per_second": 6.513,
|
| 1098 |
+
"eval_steps_per_second": 1.916,
|
| 1099 |
+
"eval_wer": 0.28444444444444444,
|
| 1100 |
+
"step": 684
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 76.67,
|
| 1104 |
+
"learning_rate": 7.379310344827585e-05,
|
| 1105 |
+
"loss": 0.3078,
|
| 1106 |
+
"step": 690
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 77.0,
|
| 1110 |
+
"eval_loss": 1.0535814762115479,
|
| 1111 |
+
"eval_runtime": 2.597,
|
| 1112 |
+
"eval_samples_per_second": 6.546,
|
| 1113 |
+
"eval_steps_per_second": 1.925,
|
| 1114 |
+
"eval_wer": 0.2911111111111111,
|
| 1115 |
+
"step": 693
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 77.78,
|
| 1119 |
+
"learning_rate": 7.034482758620688e-05,
|
| 1120 |
+
"loss": 0.4503,
|
| 1121 |
+
"step": 700
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 78.0,
|
| 1125 |
+
"eval_loss": 0.9473001956939697,
|
| 1126 |
+
"eval_runtime": 2.6482,
|
| 1127 |
+
"eval_samples_per_second": 6.42,
|
| 1128 |
+
"eval_steps_per_second": 1.888,
|
| 1129 |
+
"eval_wer": 0.2966666666666667,
|
| 1130 |
+
"step": 702
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 78.89,
|
| 1134 |
+
"learning_rate": 6.689655172413792e-05,
|
| 1135 |
+
"loss": 0.3492,
|
| 1136 |
+
"step": 710
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 79.0,
|
| 1140 |
+
"eval_loss": 0.8909215331077576,
|
| 1141 |
+
"eval_runtime": 2.6344,
|
| 1142 |
+
"eval_samples_per_second": 6.453,
|
| 1143 |
+
"eval_steps_per_second": 1.898,
|
| 1144 |
+
"eval_wer": 0.3088888888888889,
|
| 1145 |
+
"step": 711
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 80.0,
|
| 1149 |
+
"learning_rate": 6.344827586206895e-05,
|
| 1150 |
+
"loss": 0.347,
|
| 1151 |
+
"step": 720
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 80.0,
|
| 1155 |
+
"eval_loss": 0.8532315492630005,
|
| 1156 |
+
"eval_runtime": 2.6434,
|
| 1157 |
+
"eval_samples_per_second": 6.431,
|
| 1158 |
+
"eval_steps_per_second": 1.891,
|
| 1159 |
+
"eval_wer": 0.30666666666666664,
|
| 1160 |
+
"step": 720
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 81.0,
|
| 1164 |
+
"eval_loss": 0.9552628993988037,
|
| 1165 |
+
"eval_runtime": 2.651,
|
| 1166 |
+
"eval_samples_per_second": 6.413,
|
| 1167 |
+
"eval_steps_per_second": 1.886,
|
| 1168 |
+
"eval_wer": 0.2833333333333333,
|
| 1169 |
+
"step": 729
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 81.11,
|
| 1173 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 1174 |
+
"loss": 0.2949,
|
| 1175 |
+
"step": 730
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 82.0,
|
| 1179 |
+
"eval_loss": 1.0111045837402344,
|
| 1180 |
+
"eval_runtime": 2.6252,
|
| 1181 |
+
"eval_samples_per_second": 6.476,
|
| 1182 |
+
"eval_steps_per_second": 1.905,
|
| 1183 |
+
"eval_wer": 0.2866666666666667,
|
| 1184 |
+
"step": 738
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 82.22,
|
| 1188 |
+
"learning_rate": 5.655172413793103e-05,
|
| 1189 |
+
"loss": 0.3447,
|
| 1190 |
+
"step": 740
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 83.0,
|
| 1194 |
+
"eval_loss": 0.9160183072090149,
|
| 1195 |
+
"eval_runtime": 2.6434,
|
| 1196 |
+
"eval_samples_per_second": 6.431,
|
| 1197 |
+
"eval_steps_per_second": 1.892,
|
| 1198 |
+
"eval_wer": 0.3011111111111111,
|
| 1199 |
+
"step": 747
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 83.33,
|
| 1203 |
+
"learning_rate": 5.3103448275862065e-05,
|
| 1204 |
+
"loss": 0.2878,
|
| 1205 |
+
"step": 750
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 84.0,
|
| 1209 |
+
"eval_loss": 0.8401439785957336,
|
| 1210 |
+
"eval_runtime": 2.7557,
|
| 1211 |
+
"eval_samples_per_second": 6.169,
|
| 1212 |
+
"eval_steps_per_second": 1.814,
|
| 1213 |
+
"eval_wer": 0.29888888888888887,
|
| 1214 |
+
"step": 756
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 84.44,
|
| 1218 |
+
"learning_rate": 4.96551724137931e-05,
|
| 1219 |
+
"loss": 0.3229,
|
| 1220 |
+
"step": 760
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 85.0,
|
| 1224 |
+
"eval_loss": 0.8815315961837769,
|
| 1225 |
+
"eval_runtime": 2.6105,
|
| 1226 |
+
"eval_samples_per_second": 6.512,
|
| 1227 |
+
"eval_steps_per_second": 1.915,
|
| 1228 |
+
"eval_wer": 0.2911111111111111,
|
| 1229 |
+
"step": 765
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 85.56,
|
| 1233 |
+
"learning_rate": 4.6206896551724135e-05,
|
| 1234 |
+
"loss": 0.276,
|
| 1235 |
+
"step": 770
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 86.0,
|
| 1239 |
+
"eval_loss": 0.8801678419113159,
|
| 1240 |
+
"eval_runtime": 2.6513,
|
| 1241 |
+
"eval_samples_per_second": 6.412,
|
| 1242 |
+
"eval_steps_per_second": 1.886,
|
| 1243 |
+
"eval_wer": 0.2911111111111111,
|
| 1244 |
+
"step": 774
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 86.67,
|
| 1248 |
+
"learning_rate": 4.275862068965517e-05,
|
| 1249 |
+
"loss": 0.3469,
|
| 1250 |
+
"step": 780
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 87.0,
|
| 1254 |
+
"eval_loss": 0.9121254682540894,
|
| 1255 |
+
"eval_runtime": 2.6394,
|
| 1256 |
+
"eval_samples_per_second": 6.441,
|
| 1257 |
+
"eval_steps_per_second": 1.894,
|
| 1258 |
+
"eval_wer": 0.29,
|
| 1259 |
+
"step": 783
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 87.78,
|
| 1263 |
+
"learning_rate": 3.9310344827586205e-05,
|
| 1264 |
+
"loss": 0.3044,
|
| 1265 |
+
"step": 790
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 88.0,
|
| 1269 |
+
"eval_loss": 0.8933728337287903,
|
| 1270 |
+
"eval_runtime": 2.6251,
|
| 1271 |
+
"eval_samples_per_second": 6.476,
|
| 1272 |
+
"eval_steps_per_second": 1.905,
|
| 1273 |
+
"eval_wer": 0.29333333333333333,
|
| 1274 |
+
"step": 792
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 88.89,
|
| 1278 |
+
"learning_rate": 3.586206896551724e-05,
|
| 1279 |
+
"loss": 0.2885,
|
| 1280 |
+
"step": 800
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 89.0,
|
| 1284 |
+
"eval_loss": 0.8806433081626892,
|
| 1285 |
+
"eval_runtime": 2.618,
|
| 1286 |
+
"eval_samples_per_second": 6.494,
|
| 1287 |
+
"eval_steps_per_second": 1.91,
|
| 1288 |
+
"eval_wer": 0.2966666666666667,
|
| 1289 |
+
"step": 801
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 90.0,
|
| 1293 |
+
"learning_rate": 3.2413793103448275e-05,
|
| 1294 |
+
"loss": 0.3365,
|
| 1295 |
+
"step": 810
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 90.0,
|
| 1299 |
+
"eval_loss": 0.9036632180213928,
|
| 1300 |
+
"eval_runtime": 2.654,
|
| 1301 |
+
"eval_samples_per_second": 6.406,
|
| 1302 |
+
"eval_steps_per_second": 1.884,
|
| 1303 |
+
"eval_wer": 0.28444444444444444,
|
| 1304 |
+
"step": 810
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 91.0,
|
| 1308 |
+
"eval_loss": 0.9217983484268188,
|
| 1309 |
+
"eval_runtime": 2.636,
|
| 1310 |
+
"eval_samples_per_second": 6.449,
|
| 1311 |
+
"eval_steps_per_second": 1.897,
|
| 1312 |
+
"eval_wer": 0.2866666666666667,
|
| 1313 |
+
"step": 819
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 91.11,
|
| 1317 |
+
"learning_rate": 2.8965517241379307e-05,
|
| 1318 |
+
"loss": 0.3239,
|
| 1319 |
+
"step": 820
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 92.0,
|
| 1323 |
+
"eval_loss": 0.9227918386459351,
|
| 1324 |
+
"eval_runtime": 2.6278,
|
| 1325 |
+
"eval_samples_per_second": 6.469,
|
| 1326 |
+
"eval_steps_per_second": 1.903,
|
| 1327 |
+
"eval_wer": 0.28444444444444444,
|
| 1328 |
+
"step": 828
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 92.22,
|
| 1332 |
+
"learning_rate": 2.551724137931034e-05,
|
| 1333 |
+
"loss": 0.3219,
|
| 1334 |
+
"step": 830
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 93.0,
|
| 1338 |
+
"eval_loss": 0.9166781902313232,
|
| 1339 |
+
"eval_runtime": 2.652,
|
| 1340 |
+
"eval_samples_per_second": 6.41,
|
| 1341 |
+
"eval_steps_per_second": 1.885,
|
| 1342 |
+
"eval_wer": 0.28444444444444444,
|
| 1343 |
+
"step": 837
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 93.33,
|
| 1347 |
+
"learning_rate": 2.2068965517241377e-05,
|
| 1348 |
+
"loss": 0.2736,
|
| 1349 |
+
"step": 840
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 94.0,
|
| 1353 |
+
"eval_loss": 0.9494596123695374,
|
| 1354 |
+
"eval_runtime": 2.6316,
|
| 1355 |
+
"eval_samples_per_second": 6.46,
|
| 1356 |
+
"eval_steps_per_second": 1.9,
|
| 1357 |
+
"eval_wer": 0.2877777777777778,
|
| 1358 |
+
"step": 846
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 94.44,
|
| 1362 |
+
"learning_rate": 1.862068965517241e-05,
|
| 1363 |
+
"loss": 0.3587,
|
| 1364 |
+
"step": 850
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 95.0,
|
| 1368 |
+
"eval_loss": 0.9997347593307495,
|
| 1369 |
+
"eval_runtime": 2.657,
|
| 1370 |
+
"eval_samples_per_second": 6.398,
|
| 1371 |
+
"eval_steps_per_second": 1.882,
|
| 1372 |
+
"eval_wer": 0.28444444444444444,
|
| 1373 |
+
"step": 855
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 95.56,
|
| 1377 |
+
"learning_rate": 1.5172413793103447e-05,
|
| 1378 |
+
"loss": 0.3386,
|
| 1379 |
+
"step": 860
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 96.0,
|
| 1383 |
+
"eval_loss": 0.9977498650550842,
|
| 1384 |
+
"eval_runtime": 2.674,
|
| 1385 |
+
"eval_samples_per_second": 6.358,
|
| 1386 |
+
"eval_steps_per_second": 1.87,
|
| 1387 |
+
"eval_wer": 0.28555555555555556,
|
| 1388 |
+
"step": 864
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 96.67,
|
| 1392 |
+
"learning_rate": 1.1724137931034482e-05,
|
| 1393 |
+
"loss": 0.2895,
|
| 1394 |
+
"step": 870
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 97.0,
|
| 1398 |
+
"eval_loss": 0.9963868260383606,
|
| 1399 |
+
"eval_runtime": 2.6883,
|
| 1400 |
+
"eval_samples_per_second": 6.324,
|
| 1401 |
+
"eval_steps_per_second": 1.86,
|
| 1402 |
+
"eval_wer": 0.28888888888888886,
|
| 1403 |
+
"step": 873
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 97.78,
|
| 1407 |
+
"learning_rate": 8.275862068965517e-06,
|
| 1408 |
+
"loss": 0.3496,
|
| 1409 |
+
"step": 880
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 98.0,
|
| 1413 |
+
"eval_loss": 0.9764975309371948,
|
| 1414 |
+
"eval_runtime": 2.6679,
|
| 1415 |
+
"eval_samples_per_second": 6.372,
|
| 1416 |
+
"eval_steps_per_second": 1.874,
|
| 1417 |
+
"eval_wer": 0.28888888888888886,
|
| 1418 |
+
"step": 882
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 98.89,
|
| 1422 |
+
"learning_rate": 4.827586206896552e-06,
|
| 1423 |
+
"loss": 0.2789,
|
| 1424 |
+
"step": 890
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 99.0,
|
| 1428 |
+
"eval_loss": 0.9712777733802795,
|
| 1429 |
+
"eval_runtime": 2.6523,
|
| 1430 |
+
"eval_samples_per_second": 6.41,
|
| 1431 |
+
"eval_steps_per_second": 1.885,
|
| 1432 |
+
"eval_wer": 0.2877777777777778,
|
| 1433 |
+
"step": 891
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 100.0,
|
| 1437 |
+
"learning_rate": 1.379310344827586e-06,
|
| 1438 |
+
"loss": 0.3284,
|
| 1439 |
+
"step": 900
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 100.0,
|
| 1443 |
+
"eval_loss": 0.9687079191207886,
|
| 1444 |
+
"eval_runtime": 2.6458,
|
| 1445 |
+
"eval_samples_per_second": 6.425,
|
| 1446 |
+
"eval_steps_per_second": 1.89,
|
| 1447 |
+
"eval_wer": 0.28888888888888886,
|
| 1448 |
+
"step": 900
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 100.0,
|
| 1452 |
+
"step": 900,
|
| 1453 |
+
"total_flos": 1.389987159899058e+18,
|
| 1454 |
+
"train_loss": 0.9807351756095887,
|
| 1455 |
+
"train_runtime": 3338.9131,
|
| 1456 |
+
"train_samples_per_second": 4.223,
|
| 1457 |
+
"train_steps_per_second": 0.27
|
| 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 |
+
}
|