End of training
Browse files- all_results.json +12 -0
- eval_results.json +8 -0
- train_results.json +7 -0
- trainer_state.json +2119 -0
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9168873197999412,
|
| 4 |
+
"eval_loss": 0.2988849878311157,
|
| 5 |
+
"eval_runtime": 141.4021,
|
| 6 |
+
"eval_samples_per_second": 48.076,
|
| 7 |
+
"eval_steps_per_second": 0.757,
|
| 8 |
+
"train_loss": 0.8135456519344858,
|
| 9 |
+
"train_runtime": 27591.4491,
|
| 10 |
+
"train_samples_per_second": 37.036,
|
| 11 |
+
"train_steps_per_second": 1.158
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9168873197999412,
|
| 4 |
+
"eval_loss": 0.2988849878311157,
|
| 5 |
+
"eval_runtime": 141.4021,
|
| 6 |
+
"eval_samples_per_second": 48.076,
|
| 7 |
+
"eval_steps_per_second": 0.757
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.8135456519344858,
|
| 4 |
+
"train_runtime": 27591.4491,
|
| 5 |
+
"train_samples_per_second": 37.036,
|
| 6 |
+
"train_steps_per_second": 1.158
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9168873197999412,
|
| 3 |
+
"best_model_checkpoint": "trillsson3-ft-keyword-spotting-12/checkpoint-27149",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"global_step": 31940,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 8.73512836568566e-06,
|
| 13 |
+
"loss": 8.0466,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.13,
|
| 18 |
+
"learning_rate": 1.812773951158422e-05,
|
| 19 |
+
"loss": 7.1478,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.19,
|
| 24 |
+
"learning_rate": 2.7520350657482777e-05,
|
| 25 |
+
"loss": 5.5962,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.25,
|
| 30 |
+
"learning_rate": 3.691296180338134e-05,
|
| 31 |
+
"loss": 4.2177,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.31,
|
| 36 |
+
"learning_rate": 4.6305572949279896e-05,
|
| 37 |
+
"loss": 3.3186,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.38,
|
| 42 |
+
"learning_rate": 5.5698184095178454e-05,
|
| 43 |
+
"loss": 2.986,
|
| 44 |
+
"step": 600
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.44,
|
| 48 |
+
"learning_rate": 6.509079524107701e-05,
|
| 49 |
+
"loss": 2.7112,
|
| 50 |
+
"step": 700
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.5,
|
| 54 |
+
"learning_rate": 7.448340638697557e-05,
|
| 55 |
+
"loss": 2.5722,
|
| 56 |
+
"step": 800
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.56,
|
| 60 |
+
"learning_rate": 8.387601753287413e-05,
|
| 61 |
+
"loss": 2.3806,
|
| 62 |
+
"step": 900
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.63,
|
| 66 |
+
"learning_rate": 9.326862867877268e-05,
|
| 67 |
+
"loss": 2.146,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.69,
|
| 72 |
+
"learning_rate": 0.00010266123982467126,
|
| 73 |
+
"loss": 1.8771,
|
| 74 |
+
"step": 1100
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.75,
|
| 78 |
+
"learning_rate": 0.0001120538509705698,
|
| 79 |
+
"loss": 1.6311,
|
| 80 |
+
"step": 1200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.81,
|
| 84 |
+
"learning_rate": 0.00012144646211646837,
|
| 85 |
+
"loss": 1.5842,
|
| 86 |
+
"step": 1300
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.88,
|
| 90 |
+
"learning_rate": 0.00013083907326236693,
|
| 91 |
+
"loss": 1.4234,
|
| 92 |
+
"step": 1400
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.94,
|
| 96 |
+
"learning_rate": 0.0001402316844082655,
|
| 97 |
+
"loss": 1.2304,
|
| 98 |
+
"step": 1500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.0,
|
| 102 |
+
"eval_accuracy": 0.6844660194174758,
|
| 103 |
+
"eval_loss": 0.7905995845794678,
|
| 104 |
+
"eval_runtime": 146.1452,
|
| 105 |
+
"eval_samples_per_second": 46.515,
|
| 106 |
+
"eval_steps_per_second": 0.732,
|
| 107 |
+
"step": 1597
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.0,
|
| 111 |
+
"learning_rate": 0.00014962429555416404,
|
| 112 |
+
"loss": 1.2104,
|
| 113 |
+
"step": 1600
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.06,
|
| 117 |
+
"learning_rate": 0.0001590169067000626,
|
| 118 |
+
"loss": 1.1652,
|
| 119 |
+
"step": 1700
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.13,
|
| 123 |
+
"learning_rate": 0.00016840951784596116,
|
| 124 |
+
"loss": 1.1149,
|
| 125 |
+
"step": 1800
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.19,
|
| 129 |
+
"learning_rate": 0.00017780212899185972,
|
| 130 |
+
"loss": 1.0575,
|
| 131 |
+
"step": 1900
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.25,
|
| 135 |
+
"learning_rate": 0.0001871947401377583,
|
| 136 |
+
"loss": 1.0265,
|
| 137 |
+
"step": 2000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.31,
|
| 141 |
+
"learning_rate": 0.00019658735128365683,
|
| 142 |
+
"loss": 0.9752,
|
| 143 |
+
"step": 2100
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.38,
|
| 147 |
+
"learning_rate": 0.0002059799624295554,
|
| 148 |
+
"loss": 0.9388,
|
| 149 |
+
"step": 2200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.44,
|
| 153 |
+
"learning_rate": 0.00021537257357545395,
|
| 154 |
+
"loss": 0.9153,
|
| 155 |
+
"step": 2300
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.5,
|
| 159 |
+
"learning_rate": 0.00022476518472135253,
|
| 160 |
+
"loss": 0.9111,
|
| 161 |
+
"step": 2400
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.57,
|
| 165 |
+
"learning_rate": 0.0002341577958672511,
|
| 166 |
+
"loss": 0.9077,
|
| 167 |
+
"step": 2500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.63,
|
| 171 |
+
"learning_rate": 0.00024355040701314962,
|
| 172 |
+
"loss": 0.8233,
|
| 173 |
+
"step": 2600
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.69,
|
| 177 |
+
"learning_rate": 0.0002529430181590482,
|
| 178 |
+
"loss": 0.8334,
|
| 179 |
+
"step": 2700
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.75,
|
| 183 |
+
"learning_rate": 0.00026233562930494674,
|
| 184 |
+
"loss": 0.8003,
|
| 185 |
+
"step": 2800
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.82,
|
| 189 |
+
"learning_rate": 0.0002717282404508453,
|
| 190 |
+
"loss": 0.838,
|
| 191 |
+
"step": 2900
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.88,
|
| 195 |
+
"learning_rate": 0.00028112085159674385,
|
| 196 |
+
"loss": 0.7956,
|
| 197 |
+
"step": 3000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.94,
|
| 201 |
+
"learning_rate": 0.00029051346274264244,
|
| 202 |
+
"loss": 0.8117,
|
| 203 |
+
"step": 3100
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.0,
|
| 207 |
+
"eval_accuracy": 0.8673139158576052,
|
| 208 |
+
"eval_loss": 0.435994416475296,
|
| 209 |
+
"eval_runtime": 148.4175,
|
| 210 |
+
"eval_samples_per_second": 45.803,
|
| 211 |
+
"eval_steps_per_second": 0.721,
|
| 212 |
+
"step": 3194
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.0,
|
| 216 |
+
"learning_rate": 0.00029990607388854097,
|
| 217 |
+
"loss": 0.7923,
|
| 218 |
+
"step": 3200
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.07,
|
| 222 |
+
"learning_rate": 0.0002989668127739511,
|
| 223 |
+
"loss": 0.8091,
|
| 224 |
+
"step": 3300
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.13,
|
| 228 |
+
"learning_rate": 0.00029792318931329574,
|
| 229 |
+
"loss": 0.808,
|
| 230 |
+
"step": 3400
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.19,
|
| 234 |
+
"learning_rate": 0.00029687956585264035,
|
| 235 |
+
"loss": 0.768,
|
| 236 |
+
"step": 3500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.25,
|
| 240 |
+
"learning_rate": 0.00029583594239198497,
|
| 241 |
+
"loss": 0.7865,
|
| 242 |
+
"step": 3600
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.32,
|
| 246 |
+
"learning_rate": 0.0002947923189313295,
|
| 247 |
+
"loss": 0.745,
|
| 248 |
+
"step": 3700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.38,
|
| 252 |
+
"learning_rate": 0.00029374869547067414,
|
| 253 |
+
"loss": 0.7788,
|
| 254 |
+
"step": 3800
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.44,
|
| 258 |
+
"learning_rate": 0.00029270507201001875,
|
| 259 |
+
"loss": 0.73,
|
| 260 |
+
"step": 3900
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.5,
|
| 264 |
+
"learning_rate": 0.00029166144854936337,
|
| 265 |
+
"loss": 0.7761,
|
| 266 |
+
"step": 4000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.57,
|
| 270 |
+
"learning_rate": 0.000290617825088708,
|
| 271 |
+
"loss": 0.7531,
|
| 272 |
+
"step": 4100
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.63,
|
| 276 |
+
"learning_rate": 0.0002895742016280526,
|
| 277 |
+
"loss": 0.7449,
|
| 278 |
+
"step": 4200
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.69,
|
| 282 |
+
"learning_rate": 0.00028853057816739715,
|
| 283 |
+
"loss": 0.7532,
|
| 284 |
+
"step": 4300
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.76,
|
| 288 |
+
"learning_rate": 0.00028748695470674177,
|
| 289 |
+
"loss": 0.7488,
|
| 290 |
+
"step": 4400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.82,
|
| 294 |
+
"learning_rate": 0.0002864433312460864,
|
| 295 |
+
"loss": 0.7766,
|
| 296 |
+
"step": 4500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.88,
|
| 300 |
+
"learning_rate": 0.000285399707785431,
|
| 301 |
+
"loss": 0.7362,
|
| 302 |
+
"step": 4600
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.94,
|
| 306 |
+
"learning_rate": 0.0002843560843247756,
|
| 307 |
+
"loss": 0.7322,
|
| 308 |
+
"step": 4700
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.0,
|
| 312 |
+
"eval_accuracy": 0.884377758164166,
|
| 313 |
+
"eval_loss": 0.3766401708126068,
|
| 314 |
+
"eval_runtime": 145.2147,
|
| 315 |
+
"eval_samples_per_second": 46.813,
|
| 316 |
+
"eval_steps_per_second": 0.737,
|
| 317 |
+
"step": 4791
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 3.01,
|
| 321 |
+
"learning_rate": 0.00028331246086412017,
|
| 322 |
+
"loss": 0.7419,
|
| 323 |
+
"step": 4800
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.07,
|
| 327 |
+
"learning_rate": 0.00028226883740346484,
|
| 328 |
+
"loss": 0.75,
|
| 329 |
+
"step": 4900
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.13,
|
| 333 |
+
"learning_rate": 0.0002812252139428094,
|
| 334 |
+
"loss": 0.7245,
|
| 335 |
+
"step": 5000
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.19,
|
| 339 |
+
"learning_rate": 0.000280181590482154,
|
| 340 |
+
"loss": 0.7237,
|
| 341 |
+
"step": 5100
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 3.26,
|
| 345 |
+
"learning_rate": 0.0002791379670214986,
|
| 346 |
+
"loss": 0.6822,
|
| 347 |
+
"step": 5200
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 3.32,
|
| 351 |
+
"learning_rate": 0.00027809434356084324,
|
| 352 |
+
"loss": 0.6956,
|
| 353 |
+
"step": 5300
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.38,
|
| 357 |
+
"learning_rate": 0.0002770507201001878,
|
| 358 |
+
"loss": 0.7233,
|
| 359 |
+
"step": 5400
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.44,
|
| 363 |
+
"learning_rate": 0.00027600709663953247,
|
| 364 |
+
"loss": 0.6914,
|
| 365 |
+
"step": 5500
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.51,
|
| 369 |
+
"learning_rate": 0.000274963473178877,
|
| 370 |
+
"loss": 0.6867,
|
| 371 |
+
"step": 5600
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.57,
|
| 375 |
+
"learning_rate": 0.00027391984971822164,
|
| 376 |
+
"loss": 0.7331,
|
| 377 |
+
"step": 5700
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.63,
|
| 381 |
+
"learning_rate": 0.00027287622625756625,
|
| 382 |
+
"loss": 0.742,
|
| 383 |
+
"step": 5800
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.69,
|
| 387 |
+
"learning_rate": 0.00027183260279691087,
|
| 388 |
+
"loss": 0.7081,
|
| 389 |
+
"step": 5900
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.76,
|
| 393 |
+
"learning_rate": 0.0002707889793362554,
|
| 394 |
+
"loss": 0.7142,
|
| 395 |
+
"step": 6000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.82,
|
| 399 |
+
"learning_rate": 0.0002697557921102066,
|
| 400 |
+
"loss": 0.7088,
|
| 401 |
+
"step": 6100
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.88,
|
| 405 |
+
"learning_rate": 0.00026871216864955125,
|
| 406 |
+
"loss": 0.7029,
|
| 407 |
+
"step": 6200
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.94,
|
| 411 |
+
"learning_rate": 0.0002676685451888958,
|
| 412 |
+
"loss": 0.7458,
|
| 413 |
+
"step": 6300
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 4.0,
|
| 417 |
+
"eval_accuracy": 0.8986466607825832,
|
| 418 |
+
"eval_loss": 0.34493356943130493,
|
| 419 |
+
"eval_runtime": 145.403,
|
| 420 |
+
"eval_samples_per_second": 46.753,
|
| 421 |
+
"eval_steps_per_second": 0.736,
|
| 422 |
+
"step": 6388
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 4.01,
|
| 426 |
+
"learning_rate": 0.0002666249217282404,
|
| 427 |
+
"loss": 0.7236,
|
| 428 |
+
"step": 6400
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 4.07,
|
| 432 |
+
"learning_rate": 0.00026558129826758503,
|
| 433 |
+
"loss": 0.7012,
|
| 434 |
+
"step": 6500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.13,
|
| 438 |
+
"learning_rate": 0.00026453767480692965,
|
| 439 |
+
"loss": 0.7051,
|
| 440 |
+
"step": 6600
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 4.2,
|
| 444 |
+
"learning_rate": 0.0002634940513462742,
|
| 445 |
+
"loss": 0.7298,
|
| 446 |
+
"step": 6700
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 4.26,
|
| 450 |
+
"learning_rate": 0.0002624504278856189,
|
| 451 |
+
"loss": 0.6991,
|
| 452 |
+
"step": 6800
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 4.32,
|
| 456 |
+
"learning_rate": 0.00026141724065957,
|
| 457 |
+
"loss": 0.7047,
|
| 458 |
+
"step": 6900
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 4.38,
|
| 462 |
+
"learning_rate": 0.0002603736171989146,
|
| 463 |
+
"loss": 0.6833,
|
| 464 |
+
"step": 7000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 4.45,
|
| 468 |
+
"learning_rate": 0.0002593299937382592,
|
| 469 |
+
"loss": 0.7374,
|
| 470 |
+
"step": 7100
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 4.51,
|
| 474 |
+
"learning_rate": 0.0002582863702776038,
|
| 475 |
+
"loss": 0.7404,
|
| 476 |
+
"step": 7200
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 4.57,
|
| 480 |
+
"learning_rate": 0.0002572427468169484,
|
| 481 |
+
"loss": 0.6973,
|
| 482 |
+
"step": 7300
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 4.63,
|
| 486 |
+
"learning_rate": 0.000256199123356293,
|
| 487 |
+
"loss": 0.7085,
|
| 488 |
+
"step": 7400
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 4.7,
|
| 492 |
+
"learning_rate": 0.00025515549989563765,
|
| 493 |
+
"loss": 0.7029,
|
| 494 |
+
"step": 7500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 4.76,
|
| 498 |
+
"learning_rate": 0.0002541118764349822,
|
| 499 |
+
"loss": 0.7181,
|
| 500 |
+
"step": 7600
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 4.82,
|
| 504 |
+
"learning_rate": 0.0002530682529743269,
|
| 505 |
+
"loss": 0.7089,
|
| 506 |
+
"step": 7700
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 4.88,
|
| 510 |
+
"learning_rate": 0.00025202462951367144,
|
| 511 |
+
"loss": 0.693,
|
| 512 |
+
"step": 7800
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 4.95,
|
| 516 |
+
"learning_rate": 0.00025098100605301605,
|
| 517 |
+
"loss": 0.7312,
|
| 518 |
+
"step": 7900
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 5.0,
|
| 522 |
+
"eval_accuracy": 0.913503971756399,
|
| 523 |
+
"eval_loss": 0.32345056533813477,
|
| 524 |
+
"eval_runtime": 144.554,
|
| 525 |
+
"eval_samples_per_second": 47.027,
|
| 526 |
+
"eval_steps_per_second": 0.74,
|
| 527 |
+
"step": 7985
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 5.01,
|
| 531 |
+
"learning_rate": 0.00024993738259236067,
|
| 532 |
+
"loss": 0.7072,
|
| 533 |
+
"step": 8000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 5.07,
|
| 537 |
+
"learning_rate": 0.0002488937591317053,
|
| 538 |
+
"loss": 0.7333,
|
| 539 |
+
"step": 8100
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 5.13,
|
| 543 |
+
"learning_rate": 0.00024785013567104984,
|
| 544 |
+
"loss": 0.7247,
|
| 545 |
+
"step": 8200
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 5.2,
|
| 549 |
+
"learning_rate": 0.00024680651221039445,
|
| 550 |
+
"loss": 0.6973,
|
| 551 |
+
"step": 8300
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 5.26,
|
| 555 |
+
"learning_rate": 0.00024576288874973907,
|
| 556 |
+
"loss": 0.7303,
|
| 557 |
+
"step": 8400
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 5.32,
|
| 561 |
+
"learning_rate": 0.0002447192652890837,
|
| 562 |
+
"loss": 0.7084,
|
| 563 |
+
"step": 8500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 5.39,
|
| 567 |
+
"learning_rate": 0.0002436756418284283,
|
| 568 |
+
"loss": 0.6678,
|
| 569 |
+
"step": 8600
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 5.45,
|
| 573 |
+
"learning_rate": 0.00024263201836777288,
|
| 574 |
+
"loss": 0.7386,
|
| 575 |
+
"step": 8700
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 5.51,
|
| 579 |
+
"learning_rate": 0.00024158839490711747,
|
| 580 |
+
"loss": 0.665,
|
| 581 |
+
"step": 8800
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 5.57,
|
| 585 |
+
"learning_rate": 0.0002405447714464621,
|
| 586 |
+
"loss": 0.7161,
|
| 587 |
+
"step": 8900
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 5.64,
|
| 591 |
+
"learning_rate": 0.0002395011479858067,
|
| 592 |
+
"loss": 0.6969,
|
| 593 |
+
"step": 9000
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 5.7,
|
| 597 |
+
"learning_rate": 0.00023846796075975785,
|
| 598 |
+
"loss": 0.6958,
|
| 599 |
+
"step": 9100
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 5.76,
|
| 603 |
+
"learning_rate": 0.00023742433729910246,
|
| 604 |
+
"loss": 0.6686,
|
| 605 |
+
"step": 9200
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 5.82,
|
| 609 |
+
"learning_rate": 0.00023638071383844708,
|
| 610 |
+
"loss": 0.7263,
|
| 611 |
+
"step": 9300
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 5.89,
|
| 615 |
+
"learning_rate": 0.00023533709037779166,
|
| 616 |
+
"loss": 0.671,
|
| 617 |
+
"step": 9400
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 5.95,
|
| 621 |
+
"learning_rate": 0.00023429346691713628,
|
| 622 |
+
"loss": 0.7199,
|
| 623 |
+
"step": 9500
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 6.0,
|
| 627 |
+
"eval_accuracy": 0.9058546631362165,
|
| 628 |
+
"eval_loss": 0.3211215138435364,
|
| 629 |
+
"eval_runtime": 144.8271,
|
| 630 |
+
"eval_samples_per_second": 46.939,
|
| 631 |
+
"eval_steps_per_second": 0.739,
|
| 632 |
+
"step": 9582
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 6.01,
|
| 636 |
+
"learning_rate": 0.0002332498434564809,
|
| 637 |
+
"loss": 0.697,
|
| 638 |
+
"step": 9600
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 6.07,
|
| 642 |
+
"learning_rate": 0.00023220621999582548,
|
| 643 |
+
"loss": 0.7058,
|
| 644 |
+
"step": 9700
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 6.14,
|
| 648 |
+
"learning_rate": 0.00023116259653517006,
|
| 649 |
+
"loss": 0.6958,
|
| 650 |
+
"step": 9800
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 6.2,
|
| 654 |
+
"learning_rate": 0.0002301189730745147,
|
| 655 |
+
"loss": 0.7128,
|
| 656 |
+
"step": 9900
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 6.26,
|
| 660 |
+
"learning_rate": 0.0002290753496138593,
|
| 661 |
+
"loss": 0.6806,
|
| 662 |
+
"step": 10000
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 6.32,
|
| 666 |
+
"learning_rate": 0.00022803172615320393,
|
| 667 |
+
"loss": 0.6512,
|
| 668 |
+
"step": 10100
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 6.39,
|
| 672 |
+
"learning_rate": 0.00022698810269254852,
|
| 673 |
+
"loss": 0.682,
|
| 674 |
+
"step": 10200
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 6.45,
|
| 678 |
+
"learning_rate": 0.0002259444792318931,
|
| 679 |
+
"loss": 0.739,
|
| 680 |
+
"step": 10300
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 6.51,
|
| 684 |
+
"learning_rate": 0.00022490085577123772,
|
| 685 |
+
"loss": 0.7002,
|
| 686 |
+
"step": 10400
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 6.57,
|
| 690 |
+
"learning_rate": 0.00022385723231058233,
|
| 691 |
+
"loss": 0.6605,
|
| 692 |
+
"step": 10500
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 6.64,
|
| 696 |
+
"learning_rate": 0.00022281360884992692,
|
| 697 |
+
"loss": 0.695,
|
| 698 |
+
"step": 10600
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 6.7,
|
| 702 |
+
"learning_rate": 0.00022176998538927153,
|
| 703 |
+
"loss": 0.7051,
|
| 704 |
+
"step": 10700
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 6.76,
|
| 708 |
+
"learning_rate": 0.00022072636192861615,
|
| 709 |
+
"loss": 0.6833,
|
| 710 |
+
"step": 10800
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 6.83,
|
| 714 |
+
"learning_rate": 0.00021968273846796073,
|
| 715 |
+
"loss": 0.6494,
|
| 716 |
+
"step": 10900
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 6.89,
|
| 720 |
+
"learning_rate": 0.00021863911500730535,
|
| 721 |
+
"loss": 0.6715,
|
| 722 |
+
"step": 11000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 6.95,
|
| 726 |
+
"learning_rate": 0.00021759549154664993,
|
| 727 |
+
"loss": 0.72,
|
| 728 |
+
"step": 11100
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 7.0,
|
| 732 |
+
"eval_accuracy": 0.9020300088261254,
|
| 733 |
+
"eval_loss": 0.32632216811180115,
|
| 734 |
+
"eval_runtime": 144.3277,
|
| 735 |
+
"eval_samples_per_second": 47.101,
|
| 736 |
+
"eval_steps_per_second": 0.741,
|
| 737 |
+
"step": 11179
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 7.01,
|
| 741 |
+
"learning_rate": 0.00021655186808599455,
|
| 742 |
+
"loss": 0.6672,
|
| 743 |
+
"step": 11200
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 7.08,
|
| 747 |
+
"learning_rate": 0.00021550824462533916,
|
| 748 |
+
"loss": 0.7304,
|
| 749 |
+
"step": 11300
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 7.14,
|
| 753 |
+
"learning_rate": 0.00021446462116468375,
|
| 754 |
+
"loss": 0.6994,
|
| 755 |
+
"step": 11400
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 7.2,
|
| 759 |
+
"learning_rate": 0.00021342099770402836,
|
| 760 |
+
"loss": 0.6855,
|
| 761 |
+
"step": 11500
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 7.26,
|
| 765 |
+
"learning_rate": 0.00021237737424337298,
|
| 766 |
+
"loss": 0.6865,
|
| 767 |
+
"step": 11600
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 7.33,
|
| 771 |
+
"learning_rate": 0.00021133375078271756,
|
| 772 |
+
"loss": 0.6766,
|
| 773 |
+
"step": 11700
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 7.39,
|
| 777 |
+
"learning_rate": 0.0002102901273220622,
|
| 778 |
+
"loss": 0.6909,
|
| 779 |
+
"step": 11800
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 7.45,
|
| 783 |
+
"learning_rate": 0.0002092465038614068,
|
| 784 |
+
"loss": 0.6816,
|
| 785 |
+
"step": 11900
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 7.51,
|
| 789 |
+
"learning_rate": 0.00020820288040075138,
|
| 790 |
+
"loss": 0.6818,
|
| 791 |
+
"step": 12000
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 7.58,
|
| 795 |
+
"learning_rate": 0.00020715925694009602,
|
| 796 |
+
"loss": 0.6503,
|
| 797 |
+
"step": 12100
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 7.64,
|
| 801 |
+
"learning_rate": 0.0002061156334794406,
|
| 802 |
+
"loss": 0.6734,
|
| 803 |
+
"step": 12200
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 7.7,
|
| 807 |
+
"learning_rate": 0.0002050720100187852,
|
| 808 |
+
"loss": 0.6815,
|
| 809 |
+
"step": 12300
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 7.76,
|
| 813 |
+
"learning_rate": 0.00020402838655812983,
|
| 814 |
+
"loss": 0.719,
|
| 815 |
+
"step": 12400
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 7.83,
|
| 819 |
+
"learning_rate": 0.00020298476309747442,
|
| 820 |
+
"loss": 0.6887,
|
| 821 |
+
"step": 12500
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 7.89,
|
| 825 |
+
"learning_rate": 0.000201941139636819,
|
| 826 |
+
"loss": 0.6622,
|
| 827 |
+
"step": 12600
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 7.95,
|
| 831 |
+
"learning_rate": 0.00020089751617616362,
|
| 832 |
+
"loss": 0.6992,
|
| 833 |
+
"step": 12700
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 8.0,
|
| 837 |
+
"eval_accuracy": 0.9032068255369227,
|
| 838 |
+
"eval_loss": 0.3186171054840088,
|
| 839 |
+
"eval_runtime": 139.1912,
|
| 840 |
+
"eval_samples_per_second": 48.839,
|
| 841 |
+
"eval_steps_per_second": 0.769,
|
| 842 |
+
"step": 12776
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 8.02,
|
| 846 |
+
"learning_rate": 0.0001998643289501148,
|
| 847 |
+
"loss": 0.6696,
|
| 848 |
+
"step": 12800
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 8.08,
|
| 852 |
+
"learning_rate": 0.00019882070548945938,
|
| 853 |
+
"loss": 0.6972,
|
| 854 |
+
"step": 12900
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 8.14,
|
| 858 |
+
"learning_rate": 0.00019777708202880397,
|
| 859 |
+
"loss": 0.6782,
|
| 860 |
+
"step": 13000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 8.2,
|
| 864 |
+
"learning_rate": 0.0001967334585681486,
|
| 865 |
+
"loss": 0.6566,
|
| 866 |
+
"step": 13100
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 8.27,
|
| 870 |
+
"learning_rate": 0.0001956898351074932,
|
| 871 |
+
"loss": 0.6823,
|
| 872 |
+
"step": 13200
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 8.33,
|
| 876 |
+
"learning_rate": 0.00019464621164683778,
|
| 877 |
+
"loss": 0.6772,
|
| 878 |
+
"step": 13300
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 8.39,
|
| 882 |
+
"learning_rate": 0.00019360258818618243,
|
| 883 |
+
"loss": 0.7382,
|
| 884 |
+
"step": 13400
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 8.45,
|
| 888 |
+
"learning_rate": 0.000192558964725527,
|
| 889 |
+
"loss": 0.6941,
|
| 890 |
+
"step": 13500
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 8.52,
|
| 894 |
+
"learning_rate": 0.0001915153412648716,
|
| 895 |
+
"loss": 0.7093,
|
| 896 |
+
"step": 13600
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 8.58,
|
| 900 |
+
"learning_rate": 0.00019047171780421624,
|
| 901 |
+
"loss": 0.6985,
|
| 902 |
+
"step": 13700
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 8.64,
|
| 906 |
+
"learning_rate": 0.00018942809434356083,
|
| 907 |
+
"loss": 0.6738,
|
| 908 |
+
"step": 13800
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 8.7,
|
| 912 |
+
"learning_rate": 0.00018838447088290544,
|
| 913 |
+
"loss": 0.6886,
|
| 914 |
+
"step": 13900
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 8.77,
|
| 918 |
+
"learning_rate": 0.00018734084742225005,
|
| 919 |
+
"loss": 0.7027,
|
| 920 |
+
"step": 14000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 8.83,
|
| 924 |
+
"learning_rate": 0.00018629722396159464,
|
| 925 |
+
"loss": 0.681,
|
| 926 |
+
"step": 14100
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 8.89,
|
| 930 |
+
"learning_rate": 0.00018525360050093925,
|
| 931 |
+
"loss": 0.6649,
|
| 932 |
+
"step": 14200
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 8.95,
|
| 936 |
+
"learning_rate": 0.00018420997704028384,
|
| 937 |
+
"loss": 0.6543,
|
| 938 |
+
"step": 14300
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 9.0,
|
| 942 |
+
"eval_accuracy": 0.911738746690203,
|
| 943 |
+
"eval_loss": 0.3115650713443756,
|
| 944 |
+
"eval_runtime": 142.7126,
|
| 945 |
+
"eval_samples_per_second": 47.634,
|
| 946 |
+
"eval_steps_per_second": 0.75,
|
| 947 |
+
"step": 14373
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 9.02,
|
| 951 |
+
"learning_rate": 0.00018316635357962845,
|
| 952 |
+
"loss": 0.679,
|
| 953 |
+
"step": 14400
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 9.08,
|
| 957 |
+
"learning_rate": 0.00018212273011897307,
|
| 958 |
+
"loss": 0.6992,
|
| 959 |
+
"step": 14500
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 9.14,
|
| 963 |
+
"learning_rate": 0.00018107910665831765,
|
| 964 |
+
"loss": 0.6443,
|
| 965 |
+
"step": 14600
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 9.2,
|
| 969 |
+
"learning_rate": 0.00018003548319766227,
|
| 970 |
+
"loss": 0.6952,
|
| 971 |
+
"step": 14700
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 9.27,
|
| 975 |
+
"learning_rate": 0.00017900229597161342,
|
| 976 |
+
"loss": 0.7096,
|
| 977 |
+
"step": 14800
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 9.33,
|
| 981 |
+
"learning_rate": 0.00017795867251095803,
|
| 982 |
+
"loss": 0.6808,
|
| 983 |
+
"step": 14900
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 9.39,
|
| 987 |
+
"learning_rate": 0.00017691504905030265,
|
| 988 |
+
"loss": 0.6456,
|
| 989 |
+
"step": 15000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 9.46,
|
| 993 |
+
"learning_rate": 0.00017587142558964723,
|
| 994 |
+
"loss": 0.68,
|
| 995 |
+
"step": 15100
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 9.52,
|
| 999 |
+
"learning_rate": 0.00017482780212899185,
|
| 1000 |
+
"loss": 0.6753,
|
| 1001 |
+
"step": 15200
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 9.58,
|
| 1005 |
+
"learning_rate": 0.00017378417866833646,
|
| 1006 |
+
"loss": 0.7015,
|
| 1007 |
+
"step": 15300
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 9.64,
|
| 1011 |
+
"learning_rate": 0.00017274055520768105,
|
| 1012 |
+
"loss": 0.6481,
|
| 1013 |
+
"step": 15400
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 9.71,
|
| 1017 |
+
"learning_rate": 0.00017169693174702566,
|
| 1018 |
+
"loss": 0.6632,
|
| 1019 |
+
"step": 15500
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 9.77,
|
| 1023 |
+
"learning_rate": 0.00017065330828637025,
|
| 1024 |
+
"loss": 0.684,
|
| 1025 |
+
"step": 15600
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 9.83,
|
| 1029 |
+
"learning_rate": 0.00016960968482571486,
|
| 1030 |
+
"loss": 0.6991,
|
| 1031 |
+
"step": 15700
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 9.89,
|
| 1035 |
+
"learning_rate": 0.00016856606136505948,
|
| 1036 |
+
"loss": 0.6676,
|
| 1037 |
+
"step": 15800
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 9.96,
|
| 1041 |
+
"learning_rate": 0.00016752243790440406,
|
| 1042 |
+
"loss": 0.6346,
|
| 1043 |
+
"step": 15900
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 10.0,
|
| 1047 |
+
"eval_accuracy": 0.9015887025595763,
|
| 1048 |
+
"eval_loss": 0.317617267370224,
|
| 1049 |
+
"eval_runtime": 141.8277,
|
| 1050 |
+
"eval_samples_per_second": 47.931,
|
| 1051 |
+
"eval_steps_per_second": 0.754,
|
| 1052 |
+
"step": 15970
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 10.02,
|
| 1056 |
+
"learning_rate": 0.00016647881444374868,
|
| 1057 |
+
"loss": 0.6998,
|
| 1058 |
+
"step": 16000
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 10.08,
|
| 1062 |
+
"learning_rate": 0.0001654351909830933,
|
| 1063 |
+
"loss": 0.6607,
|
| 1064 |
+
"step": 16100
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 10.14,
|
| 1068 |
+
"learning_rate": 0.00016439156752243788,
|
| 1069 |
+
"loss": 0.6642,
|
| 1070 |
+
"step": 16200
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 10.21,
|
| 1074 |
+
"learning_rate": 0.00016334794406178252,
|
| 1075 |
+
"loss": 0.6505,
|
| 1076 |
+
"step": 16300
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 10.27,
|
| 1080 |
+
"learning_rate": 0.0001623043206011271,
|
| 1081 |
+
"loss": 0.6772,
|
| 1082 |
+
"step": 16400
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 10.33,
|
| 1086 |
+
"learning_rate": 0.0001612606971404717,
|
| 1087 |
+
"loss": 0.6641,
|
| 1088 |
+
"step": 16500
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 10.39,
|
| 1092 |
+
"learning_rate": 0.00016021707367981633,
|
| 1093 |
+
"loss": 0.6523,
|
| 1094 |
+
"step": 16600
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 10.46,
|
| 1098 |
+
"learning_rate": 0.00015917345021916092,
|
| 1099 |
+
"loss": 0.7135,
|
| 1100 |
+
"step": 16700
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 10.52,
|
| 1104 |
+
"learning_rate": 0.0001581298267585055,
|
| 1105 |
+
"loss": 0.6796,
|
| 1106 |
+
"step": 16800
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 10.58,
|
| 1110 |
+
"learning_rate": 0.00015708620329785015,
|
| 1111 |
+
"loss": 0.665,
|
| 1112 |
+
"step": 16900
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 10.64,
|
| 1116 |
+
"learning_rate": 0.00015604257983719473,
|
| 1117 |
+
"loss": 0.6853,
|
| 1118 |
+
"step": 17000
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 10.71,
|
| 1122 |
+
"learning_rate": 0.00015499895637653932,
|
| 1123 |
+
"loss": 0.6851,
|
| 1124 |
+
"step": 17100
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 10.77,
|
| 1128 |
+
"learning_rate": 0.00015395533291588393,
|
| 1129 |
+
"loss": 0.647,
|
| 1130 |
+
"step": 17200
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 10.83,
|
| 1134 |
+
"learning_rate": 0.00015291170945522855,
|
| 1135 |
+
"loss": 0.6446,
|
| 1136 |
+
"step": 17300
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 10.9,
|
| 1140 |
+
"learning_rate": 0.00015186808599457313,
|
| 1141 |
+
"loss": 0.6798,
|
| 1142 |
+
"step": 17400
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 10.96,
|
| 1146 |
+
"learning_rate": 0.00015082446253391775,
|
| 1147 |
+
"loss": 0.7189,
|
| 1148 |
+
"step": 17500
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 11.0,
|
| 1152 |
+
"eval_accuracy": 0.9018829067372757,
|
| 1153 |
+
"eval_loss": 0.3116227686405182,
|
| 1154 |
+
"eval_runtime": 142.1447,
|
| 1155 |
+
"eval_samples_per_second": 47.825,
|
| 1156 |
+
"eval_steps_per_second": 0.753,
|
| 1157 |
+
"step": 17567
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 11.02,
|
| 1161 |
+
"learning_rate": 0.00014978083907326236,
|
| 1162 |
+
"loss": 0.7129,
|
| 1163 |
+
"step": 17600
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 11.08,
|
| 1167 |
+
"learning_rate": 0.00014873721561260695,
|
| 1168 |
+
"loss": 0.6561,
|
| 1169 |
+
"step": 17700
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 11.15,
|
| 1173 |
+
"learning_rate": 0.00014770402838655813,
|
| 1174 |
+
"loss": 0.6796,
|
| 1175 |
+
"step": 17800
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 11.21,
|
| 1179 |
+
"learning_rate": 0.0001466604049259027,
|
| 1180 |
+
"loss": 0.7068,
|
| 1181 |
+
"step": 17900
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 11.27,
|
| 1185 |
+
"learning_rate": 0.00014561678146524733,
|
| 1186 |
+
"loss": 0.6543,
|
| 1187 |
+
"step": 18000
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 11.33,
|
| 1191 |
+
"learning_rate": 0.00014457315800459194,
|
| 1192 |
+
"loss": 0.6708,
|
| 1193 |
+
"step": 18100
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 11.4,
|
| 1197 |
+
"learning_rate": 0.00014352953454393655,
|
| 1198 |
+
"loss": 0.6442,
|
| 1199 |
+
"step": 18200
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 11.46,
|
| 1203 |
+
"learning_rate": 0.00014248591108328114,
|
| 1204 |
+
"loss": 0.7371,
|
| 1205 |
+
"step": 18300
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 11.52,
|
| 1209 |
+
"learning_rate": 0.00014144228762262575,
|
| 1210 |
+
"loss": 0.6647,
|
| 1211 |
+
"step": 18400
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 11.58,
|
| 1215 |
+
"learning_rate": 0.00014039866416197034,
|
| 1216 |
+
"loss": 0.6755,
|
| 1217 |
+
"step": 18500
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 11.65,
|
| 1221 |
+
"learning_rate": 0.00013935504070131495,
|
| 1222 |
+
"loss": 0.686,
|
| 1223 |
+
"step": 18600
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 11.71,
|
| 1227 |
+
"learning_rate": 0.00013831141724065957,
|
| 1228 |
+
"loss": 0.6826,
|
| 1229 |
+
"step": 18700
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 11.77,
|
| 1233 |
+
"learning_rate": 0.00013726779378000416,
|
| 1234 |
+
"loss": 0.723,
|
| 1235 |
+
"step": 18800
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 11.83,
|
| 1239 |
+
"learning_rate": 0.00013622417031934877,
|
| 1240 |
+
"loss": 0.6481,
|
| 1241 |
+
"step": 18900
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 11.9,
|
| 1245 |
+
"learning_rate": 0.00013518054685869336,
|
| 1246 |
+
"loss": 0.6872,
|
| 1247 |
+
"step": 19000
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 11.96,
|
| 1251 |
+
"learning_rate": 0.00013413692339803797,
|
| 1252 |
+
"loss": 0.6628,
|
| 1253 |
+
"step": 19100
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 12.0,
|
| 1257 |
+
"eval_accuracy": 0.9111503383348043,
|
| 1258 |
+
"eval_loss": 0.30716028809547424,
|
| 1259 |
+
"eval_runtime": 141.8819,
|
| 1260 |
+
"eval_samples_per_second": 47.913,
|
| 1261 |
+
"eval_steps_per_second": 0.754,
|
| 1262 |
+
"step": 19164
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 12.02,
|
| 1266 |
+
"learning_rate": 0.00013309329993738258,
|
| 1267 |
+
"loss": 0.6766,
|
| 1268 |
+
"step": 19200
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 12.09,
|
| 1272 |
+
"learning_rate": 0.00013204967647672717,
|
| 1273 |
+
"loss": 0.682,
|
| 1274 |
+
"step": 19300
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 12.15,
|
| 1278 |
+
"learning_rate": 0.00013100605301607178,
|
| 1279 |
+
"loss": 0.6623,
|
| 1280 |
+
"step": 19400
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 12.21,
|
| 1284 |
+
"learning_rate": 0.0001299624295554164,
|
| 1285 |
+
"loss": 0.6597,
|
| 1286 |
+
"step": 19500
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 12.27,
|
| 1290 |
+
"learning_rate": 0.000128918806094761,
|
| 1291 |
+
"loss": 0.669,
|
| 1292 |
+
"step": 19600
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 12.34,
|
| 1296 |
+
"learning_rate": 0.0001278751826341056,
|
| 1297 |
+
"loss": 0.6832,
|
| 1298 |
+
"step": 19700
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 12.4,
|
| 1302 |
+
"learning_rate": 0.0001268315591734502,
|
| 1303 |
+
"loss": 0.6536,
|
| 1304 |
+
"step": 19800
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 12.46,
|
| 1308 |
+
"learning_rate": 0.00012578793571279482,
|
| 1309 |
+
"loss": 0.6808,
|
| 1310 |
+
"step": 19900
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 12.52,
|
| 1314 |
+
"learning_rate": 0.0001247443122521394,
|
| 1315 |
+
"loss": 0.6783,
|
| 1316 |
+
"step": 20000
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 12.59,
|
| 1320 |
+
"learning_rate": 0.00012370068879148403,
|
| 1321 |
+
"loss": 0.6648,
|
| 1322 |
+
"step": 20100
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 12.65,
|
| 1326 |
+
"learning_rate": 0.00012265706533082864,
|
| 1327 |
+
"loss": 0.679,
|
| 1328 |
+
"step": 20200
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 12.71,
|
| 1332 |
+
"learning_rate": 0.00012161344187017323,
|
| 1333 |
+
"loss": 0.6344,
|
| 1334 |
+
"step": 20300
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 12.77,
|
| 1338 |
+
"learning_rate": 0.00012056981840951783,
|
| 1339 |
+
"loss": 0.6441,
|
| 1340 |
+
"step": 20400
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 12.84,
|
| 1344 |
+
"learning_rate": 0.00011952619494886244,
|
| 1345 |
+
"loss": 0.6464,
|
| 1346 |
+
"step": 20500
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 12.9,
|
| 1350 |
+
"learning_rate": 0.00011848257148820705,
|
| 1351 |
+
"loss": 0.6828,
|
| 1352 |
+
"step": 20600
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 12.96,
|
| 1356 |
+
"learning_rate": 0.00011743894802755164,
|
| 1357 |
+
"loss": 0.6855,
|
| 1358 |
+
"step": 20700
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 13.0,
|
| 1362 |
+
"eval_accuracy": 0.903059723448073,
|
| 1363 |
+
"eval_loss": 0.31616511940956116,
|
| 1364 |
+
"eval_runtime": 141.8344,
|
| 1365 |
+
"eval_samples_per_second": 47.929,
|
| 1366 |
+
"eval_steps_per_second": 0.754,
|
| 1367 |
+
"step": 20761
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 13.02,
|
| 1371 |
+
"learning_rate": 0.00011639532456689625,
|
| 1372 |
+
"loss": 0.6492,
|
| 1373 |
+
"step": 20800
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 13.09,
|
| 1377 |
+
"learning_rate": 0.00011536213734084742,
|
| 1378 |
+
"loss": 0.6584,
|
| 1379 |
+
"step": 20900
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 13.15,
|
| 1383 |
+
"learning_rate": 0.000114318513880192,
|
| 1384 |
+
"loss": 0.6705,
|
| 1385 |
+
"step": 21000
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 13.21,
|
| 1389 |
+
"learning_rate": 0.00011327489041953662,
|
| 1390 |
+
"loss": 0.6644,
|
| 1391 |
+
"step": 21100
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 13.27,
|
| 1395 |
+
"learning_rate": 0.00011223126695888123,
|
| 1396 |
+
"loss": 0.6988,
|
| 1397 |
+
"step": 21200
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 13.34,
|
| 1401 |
+
"learning_rate": 0.00011118764349822583,
|
| 1402 |
+
"loss": 0.6575,
|
| 1403 |
+
"step": 21300
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 13.4,
|
| 1407 |
+
"learning_rate": 0.00011014402003757043,
|
| 1408 |
+
"loss": 0.6529,
|
| 1409 |
+
"step": 21400
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 13.46,
|
| 1413 |
+
"learning_rate": 0.00010910039657691503,
|
| 1414 |
+
"loss": 0.6453,
|
| 1415 |
+
"step": 21500
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 13.53,
|
| 1419 |
+
"learning_rate": 0.00010805677311625965,
|
| 1420 |
+
"loss": 0.6446,
|
| 1421 |
+
"step": 21600
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 13.59,
|
| 1425 |
+
"learning_rate": 0.00010701314965560425,
|
| 1426 |
+
"loss": 0.6554,
|
| 1427 |
+
"step": 21700
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 13.65,
|
| 1431 |
+
"learning_rate": 0.00010596952619494885,
|
| 1432 |
+
"loss": 0.6584,
|
| 1433 |
+
"step": 21800
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 13.71,
|
| 1437 |
+
"learning_rate": 0.00010492590273429346,
|
| 1438 |
+
"loss": 0.7099,
|
| 1439 |
+
"step": 21900
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 13.78,
|
| 1443 |
+
"learning_rate": 0.00010388227927363808,
|
| 1444 |
+
"loss": 0.6365,
|
| 1445 |
+
"step": 22000
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 13.84,
|
| 1449 |
+
"learning_rate": 0.00010283865581298266,
|
| 1450 |
+
"loss": 0.6561,
|
| 1451 |
+
"step": 22100
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 13.9,
|
| 1455 |
+
"learning_rate": 0.00010179503235232728,
|
| 1456 |
+
"loss": 0.6913,
|
| 1457 |
+
"step": 22200
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 13.96,
|
| 1461 |
+
"learning_rate": 0.00010075140889167188,
|
| 1462 |
+
"loss": 0.6651,
|
| 1463 |
+
"step": 22300
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 14.0,
|
| 1467 |
+
"eval_accuracy": 0.9111503383348043,
|
| 1468 |
+
"eval_loss": 0.30470559000968933,
|
| 1469 |
+
"eval_runtime": 142.7059,
|
| 1470 |
+
"eval_samples_per_second": 47.636,
|
| 1471 |
+
"eval_steps_per_second": 0.75,
|
| 1472 |
+
"step": 22358
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 14.03,
|
| 1476 |
+
"learning_rate": 9.970778543101648e-05,
|
| 1477 |
+
"loss": 0.6411,
|
| 1478 |
+
"step": 22400
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 14.09,
|
| 1482 |
+
"learning_rate": 9.866416197036109e-05,
|
| 1483 |
+
"loss": 0.6754,
|
| 1484 |
+
"step": 22500
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 14.15,
|
| 1488 |
+
"learning_rate": 9.762053850970569e-05,
|
| 1489 |
+
"loss": 0.6787,
|
| 1490 |
+
"step": 22600
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 14.21,
|
| 1494 |
+
"learning_rate": 9.65769150490503e-05,
|
| 1495 |
+
"loss": 0.6687,
|
| 1496 |
+
"step": 22700
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 14.28,
|
| 1500 |
+
"learning_rate": 9.553329158839489e-05,
|
| 1501 |
+
"loss": 0.6355,
|
| 1502 |
+
"step": 22800
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 14.34,
|
| 1506 |
+
"learning_rate": 9.44896681277395e-05,
|
| 1507 |
+
"loss": 0.6498,
|
| 1508 |
+
"step": 22900
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 14.4,
|
| 1512 |
+
"learning_rate": 9.344604466708412e-05,
|
| 1513 |
+
"loss": 0.6685,
|
| 1514 |
+
"step": 23000
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 14.46,
|
| 1518 |
+
"learning_rate": 9.24024212064287e-05,
|
| 1519 |
+
"loss": 0.6741,
|
| 1520 |
+
"step": 23100
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 14.53,
|
| 1524 |
+
"learning_rate": 9.135879774577332e-05,
|
| 1525 |
+
"loss": 0.6701,
|
| 1526 |
+
"step": 23200
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 14.59,
|
| 1530 |
+
"learning_rate": 9.032561051972448e-05,
|
| 1531 |
+
"loss": 0.6508,
|
| 1532 |
+
"step": 23300
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 14.65,
|
| 1536 |
+
"learning_rate": 8.928198705906908e-05,
|
| 1537 |
+
"loss": 0.6571,
|
| 1538 |
+
"step": 23400
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 14.72,
|
| 1542 |
+
"learning_rate": 8.823836359841368e-05,
|
| 1543 |
+
"loss": 0.6508,
|
| 1544 |
+
"step": 23500
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 14.78,
|
| 1548 |
+
"learning_rate": 8.719474013775828e-05,
|
| 1549 |
+
"loss": 0.6202,
|
| 1550 |
+
"step": 23600
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 14.84,
|
| 1554 |
+
"learning_rate": 8.61511166771029e-05,
|
| 1555 |
+
"loss": 0.6657,
|
| 1556 |
+
"step": 23700
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 14.9,
|
| 1560 |
+
"learning_rate": 8.51074932164475e-05,
|
| 1561 |
+
"loss": 0.6301,
|
| 1562 |
+
"step": 23800
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 14.97,
|
| 1566 |
+
"learning_rate": 8.40638697557921e-05,
|
| 1567 |
+
"loss": 0.6962,
|
| 1568 |
+
"step": 23900
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 15.0,
|
| 1572 |
+
"eval_accuracy": 0.912621359223301,
|
| 1573 |
+
"eval_loss": 0.30054593086242676,
|
| 1574 |
+
"eval_runtime": 147.8277,
|
| 1575 |
+
"eval_samples_per_second": 45.986,
|
| 1576 |
+
"eval_steps_per_second": 0.724,
|
| 1577 |
+
"step": 23955
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 15.03,
|
| 1581 |
+
"learning_rate": 8.302024629513671e-05,
|
| 1582 |
+
"loss": 0.6898,
|
| 1583 |
+
"step": 24000
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 15.09,
|
| 1587 |
+
"learning_rate": 8.19766228344813e-05,
|
| 1588 |
+
"loss": 0.6417,
|
| 1589 |
+
"step": 24100
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 15.15,
|
| 1593 |
+
"learning_rate": 8.093299937382591e-05,
|
| 1594 |
+
"loss": 0.6322,
|
| 1595 |
+
"step": 24200
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 15.22,
|
| 1599 |
+
"learning_rate": 7.988937591317053e-05,
|
| 1600 |
+
"loss": 0.6142,
|
| 1601 |
+
"step": 24300
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 15.28,
|
| 1605 |
+
"learning_rate": 7.884575245251513e-05,
|
| 1606 |
+
"loss": 0.6659,
|
| 1607 |
+
"step": 24400
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 15.34,
|
| 1611 |
+
"learning_rate": 7.780212899185973e-05,
|
| 1612 |
+
"loss": 0.6626,
|
| 1613 |
+
"step": 24500
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 15.4,
|
| 1617 |
+
"learning_rate": 7.675850553120434e-05,
|
| 1618 |
+
"loss": 0.6477,
|
| 1619 |
+
"step": 24600
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 15.47,
|
| 1623 |
+
"learning_rate": 7.571488207054894e-05,
|
| 1624 |
+
"loss": 0.6066,
|
| 1625 |
+
"step": 24700
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 15.53,
|
| 1629 |
+
"learning_rate": 7.467125860989354e-05,
|
| 1630 |
+
"loss": 0.6713,
|
| 1631 |
+
"step": 24800
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 15.59,
|
| 1635 |
+
"learning_rate": 7.362763514923814e-05,
|
| 1636 |
+
"loss": 0.6725,
|
| 1637 |
+
"step": 24900
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 15.65,
|
| 1641 |
+
"learning_rate": 7.258401168858275e-05,
|
| 1642 |
+
"loss": 0.6442,
|
| 1643 |
+
"step": 25000
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 15.72,
|
| 1647 |
+
"learning_rate": 7.154038822792735e-05,
|
| 1648 |
+
"loss": 0.7171,
|
| 1649 |
+
"step": 25100
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 15.78,
|
| 1653 |
+
"learning_rate": 7.049676476727197e-05,
|
| 1654 |
+
"loss": 0.6558,
|
| 1655 |
+
"step": 25200
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 15.84,
|
| 1659 |
+
"learning_rate": 6.945314130661657e-05,
|
| 1660 |
+
"loss": 0.6759,
|
| 1661 |
+
"step": 25300
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 15.9,
|
| 1665 |
+
"learning_rate": 6.840951784596117e-05,
|
| 1666 |
+
"loss": 0.6378,
|
| 1667 |
+
"step": 25400
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 15.97,
|
| 1671 |
+
"learning_rate": 6.736589438530578e-05,
|
| 1672 |
+
"loss": 0.6348,
|
| 1673 |
+
"step": 25500
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 16.0,
|
| 1677 |
+
"eval_accuracy": 0.9079140923801118,
|
| 1678 |
+
"eval_loss": 0.31096547842025757,
|
| 1679 |
+
"eval_runtime": 148.4859,
|
| 1680 |
+
"eval_samples_per_second": 45.782,
|
| 1681 |
+
"eval_steps_per_second": 0.721,
|
| 1682 |
+
"step": 25552
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 16.03,
|
| 1686 |
+
"learning_rate": 6.632227092465038e-05,
|
| 1687 |
+
"loss": 0.6608,
|
| 1688 |
+
"step": 25600
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 16.09,
|
| 1692 |
+
"learning_rate": 6.527864746399498e-05,
|
| 1693 |
+
"loss": 0.667,
|
| 1694 |
+
"step": 25700
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 16.16,
|
| 1698 |
+
"learning_rate": 6.423502400333958e-05,
|
| 1699 |
+
"loss": 0.6447,
|
| 1700 |
+
"step": 25800
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 16.22,
|
| 1704 |
+
"learning_rate": 6.31914005426842e-05,
|
| 1705 |
+
"loss": 0.649,
|
| 1706 |
+
"step": 25900
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 16.28,
|
| 1710 |
+
"learning_rate": 6.21477770820288e-05,
|
| 1711 |
+
"loss": 0.6438,
|
| 1712 |
+
"step": 26000
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 16.34,
|
| 1716 |
+
"learning_rate": 6.11041536213734e-05,
|
| 1717 |
+
"loss": 0.6727,
|
| 1718 |
+
"step": 26100
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 16.41,
|
| 1722 |
+
"learning_rate": 6.006053016071801e-05,
|
| 1723 |
+
"loss": 0.6467,
|
| 1724 |
+
"step": 26200
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 16.47,
|
| 1728 |
+
"learning_rate": 5.901690670006261e-05,
|
| 1729 |
+
"loss": 0.6365,
|
| 1730 |
+
"step": 26300
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 16.53,
|
| 1734 |
+
"learning_rate": 5.797328323940722e-05,
|
| 1735 |
+
"loss": 0.6642,
|
| 1736 |
+
"step": 26400
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 16.59,
|
| 1740 |
+
"learning_rate": 5.692965977875182e-05,
|
| 1741 |
+
"loss": 0.6404,
|
| 1742 |
+
"step": 26500
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 16.66,
|
| 1746 |
+
"learning_rate": 5.5896472552702984e-05,
|
| 1747 |
+
"loss": 0.6483,
|
| 1748 |
+
"step": 26600
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 16.72,
|
| 1752 |
+
"learning_rate": 5.4852849092047584e-05,
|
| 1753 |
+
"loss": 0.7041,
|
| 1754 |
+
"step": 26700
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 16.78,
|
| 1758 |
+
"learning_rate": 5.3809225631392184e-05,
|
| 1759 |
+
"loss": 0.6534,
|
| 1760 |
+
"step": 26800
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 16.84,
|
| 1764 |
+
"learning_rate": 5.27656021707368e-05,
|
| 1765 |
+
"loss": 0.6355,
|
| 1766 |
+
"step": 26900
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 16.91,
|
| 1770 |
+
"learning_rate": 5.17219787100814e-05,
|
| 1771 |
+
"loss": 0.6394,
|
| 1772 |
+
"step": 27000
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 16.97,
|
| 1776 |
+
"learning_rate": 5.0678355249426005e-05,
|
| 1777 |
+
"loss": 0.6595,
|
| 1778 |
+
"step": 27100
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 17.0,
|
| 1782 |
+
"eval_accuracy": 0.9168873197999412,
|
| 1783 |
+
"eval_loss": 0.2988849878311157,
|
| 1784 |
+
"eval_runtime": 147.5031,
|
| 1785 |
+
"eval_samples_per_second": 46.087,
|
| 1786 |
+
"eval_steps_per_second": 0.725,
|
| 1787 |
+
"step": 27149
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 17.03,
|
| 1791 |
+
"learning_rate": 4.9634731788770605e-05,
|
| 1792 |
+
"loss": 0.6207,
|
| 1793 |
+
"step": 27200
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 17.09,
|
| 1797 |
+
"learning_rate": 4.8591108328115205e-05,
|
| 1798 |
+
"loss": 0.6216,
|
| 1799 |
+
"step": 27300
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 17.16,
|
| 1803 |
+
"learning_rate": 4.754748486745982e-05,
|
| 1804 |
+
"loss": 0.6647,
|
| 1805 |
+
"step": 27400
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 17.22,
|
| 1809 |
+
"learning_rate": 4.650386140680442e-05,
|
| 1810 |
+
"loss": 0.6152,
|
| 1811 |
+
"step": 27500
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 17.28,
|
| 1815 |
+
"learning_rate": 4.5460237946149026e-05,
|
| 1816 |
+
"loss": 0.6531,
|
| 1817 |
+
"step": 27600
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 17.35,
|
| 1821 |
+
"learning_rate": 4.4416614485493626e-05,
|
| 1822 |
+
"loss": 0.6108,
|
| 1823 |
+
"step": 27700
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 17.41,
|
| 1827 |
+
"learning_rate": 4.337299102483824e-05,
|
| 1828 |
+
"loss": 0.6569,
|
| 1829 |
+
"step": 27800
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 17.47,
|
| 1833 |
+
"learning_rate": 4.232936756418284e-05,
|
| 1834 |
+
"loss": 0.666,
|
| 1835 |
+
"step": 27900
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 17.53,
|
| 1839 |
+
"learning_rate": 4.128574410352744e-05,
|
| 1840 |
+
"loss": 0.6344,
|
| 1841 |
+
"step": 28000
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 17.6,
|
| 1845 |
+
"learning_rate": 4.024212064287205e-05,
|
| 1846 |
+
"loss": 0.6627,
|
| 1847 |
+
"step": 28100
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 17.66,
|
| 1851 |
+
"learning_rate": 3.9198497182216654e-05,
|
| 1852 |
+
"loss": 0.6863,
|
| 1853 |
+
"step": 28200
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 17.72,
|
| 1857 |
+
"learning_rate": 3.815487372156126e-05,
|
| 1858 |
+
"loss": 0.7073,
|
| 1859 |
+
"step": 28300
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 17.78,
|
| 1863 |
+
"learning_rate": 3.711125026090586e-05,
|
| 1864 |
+
"loss": 0.6618,
|
| 1865 |
+
"step": 28400
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 17.85,
|
| 1869 |
+
"learning_rate": 3.606762680025047e-05,
|
| 1870 |
+
"loss": 0.6535,
|
| 1871 |
+
"step": 28500
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 17.91,
|
| 1875 |
+
"learning_rate": 3.5024003339595075e-05,
|
| 1876 |
+
"loss": 0.6106,
|
| 1877 |
+
"step": 28600
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 17.97,
|
| 1881 |
+
"learning_rate": 3.3980379878939675e-05,
|
| 1882 |
+
"loss": 0.677,
|
| 1883 |
+
"step": 28700
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 18.0,
|
| 1887 |
+
"eval_accuracy": 0.9098264195351574,
|
| 1888 |
+
"eval_loss": 0.31027764081954956,
|
| 1889 |
+
"eval_runtime": 142.2177,
|
| 1890 |
+
"eval_samples_per_second": 47.8,
|
| 1891 |
+
"eval_steps_per_second": 0.752,
|
| 1892 |
+
"step": 28746
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 18.03,
|
| 1896 |
+
"learning_rate": 3.2936756418284276e-05,
|
| 1897 |
+
"loss": 0.6368,
|
| 1898 |
+
"step": 28800
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 18.1,
|
| 1902 |
+
"learning_rate": 3.189313295762888e-05,
|
| 1903 |
+
"loss": 0.6739,
|
| 1904 |
+
"step": 28900
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 18.16,
|
| 1908 |
+
"learning_rate": 3.084950949697349e-05,
|
| 1909 |
+
"loss": 0.6187,
|
| 1910 |
+
"step": 29000
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 18.22,
|
| 1914 |
+
"learning_rate": 2.9805886036318093e-05,
|
| 1915 |
+
"loss": 0.6197,
|
| 1916 |
+
"step": 29100
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 18.28,
|
| 1920 |
+
"learning_rate": 2.87622625756627e-05,
|
| 1921 |
+
"loss": 0.6583,
|
| 1922 |
+
"step": 29200
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 18.35,
|
| 1926 |
+
"learning_rate": 2.7718639115007304e-05,
|
| 1927 |
+
"loss": 0.6446,
|
| 1928 |
+
"step": 29300
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 18.41,
|
| 1932 |
+
"learning_rate": 2.6675015654351907e-05,
|
| 1933 |
+
"loss": 0.6569,
|
| 1934 |
+
"step": 29400
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 18.47,
|
| 1938 |
+
"learning_rate": 2.563139219369651e-05,
|
| 1939 |
+
"loss": 0.6681,
|
| 1940 |
+
"step": 29500
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 18.53,
|
| 1944 |
+
"learning_rate": 2.4587768733041114e-05,
|
| 1945 |
+
"loss": 0.627,
|
| 1946 |
+
"step": 29600
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 18.6,
|
| 1950 |
+
"learning_rate": 2.354414527238572e-05,
|
| 1951 |
+
"loss": 0.6477,
|
| 1952 |
+
"step": 29700
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 18.66,
|
| 1956 |
+
"learning_rate": 2.2500521811730325e-05,
|
| 1957 |
+
"loss": 0.6745,
|
| 1958 |
+
"step": 29800
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 18.72,
|
| 1962 |
+
"learning_rate": 2.1456898351074932e-05,
|
| 1963 |
+
"loss": 0.6365,
|
| 1964 |
+
"step": 29900
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 18.79,
|
| 1968 |
+
"learning_rate": 2.0413274890419532e-05,
|
| 1969 |
+
"loss": 0.6254,
|
| 1970 |
+
"step": 30000
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 18.85,
|
| 1974 |
+
"learning_rate": 1.936965142976414e-05,
|
| 1975 |
+
"loss": 0.6445,
|
| 1976 |
+
"step": 30100
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 18.91,
|
| 1980 |
+
"learning_rate": 1.8326027969108743e-05,
|
| 1981 |
+
"loss": 0.6744,
|
| 1982 |
+
"step": 30200
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 18.97,
|
| 1986 |
+
"learning_rate": 1.728240450845335e-05,
|
| 1987 |
+
"loss": 0.6394,
|
| 1988 |
+
"step": 30300
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 19.0,
|
| 1992 |
+
"eval_accuracy": 0.9085025007355104,
|
| 1993 |
+
"eval_loss": 0.3055914342403412,
|
| 1994 |
+
"eval_runtime": 142.7169,
|
| 1995 |
+
"eval_samples_per_second": 47.633,
|
| 1996 |
+
"eval_steps_per_second": 0.75,
|
| 1997 |
+
"step": 30343
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 19.04,
|
| 2001 |
+
"learning_rate": 1.6238781047797953e-05,
|
| 2002 |
+
"loss": 0.6256,
|
| 2003 |
+
"step": 30400
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 19.1,
|
| 2007 |
+
"learning_rate": 1.5195157587142557e-05,
|
| 2008 |
+
"loss": 0.6218,
|
| 2009 |
+
"step": 30500
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 19.16,
|
| 2013 |
+
"learning_rate": 1.4161970361093715e-05,
|
| 2014 |
+
"loss": 0.6752,
|
| 2015 |
+
"step": 30600
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 19.22,
|
| 2019 |
+
"learning_rate": 1.311834690043832e-05,
|
| 2020 |
+
"loss": 0.6387,
|
| 2021 |
+
"step": 30700
|
| 2022 |
+
},
|
| 2023 |
+
{
|
| 2024 |
+
"epoch": 19.29,
|
| 2025 |
+
"learning_rate": 1.2074723439782926e-05,
|
| 2026 |
+
"loss": 0.6291,
|
| 2027 |
+
"step": 30800
|
| 2028 |
+
},
|
| 2029 |
+
{
|
| 2030 |
+
"epoch": 19.35,
|
| 2031 |
+
"learning_rate": 1.103109997912753e-05,
|
| 2032 |
+
"loss": 0.6009,
|
| 2033 |
+
"step": 30900
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 19.41,
|
| 2037 |
+
"learning_rate": 9.987476518472135e-06,
|
| 2038 |
+
"loss": 0.6347,
|
| 2039 |
+
"step": 31000
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 19.47,
|
| 2043 |
+
"learning_rate": 8.943853057816738e-06,
|
| 2044 |
+
"loss": 0.6795,
|
| 2045 |
+
"step": 31100
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 19.54,
|
| 2049 |
+
"learning_rate": 7.900229597161344e-06,
|
| 2050 |
+
"loss": 0.6558,
|
| 2051 |
+
"step": 31200
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 19.6,
|
| 2055 |
+
"learning_rate": 6.856606136505948e-06,
|
| 2056 |
+
"loss": 0.6577,
|
| 2057 |
+
"step": 31300
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 19.66,
|
| 2061 |
+
"learning_rate": 5.812982675850552e-06,
|
| 2062 |
+
"loss": 0.6258,
|
| 2063 |
+
"step": 31400
|
| 2064 |
+
},
|
| 2065 |
+
{
|
| 2066 |
+
"epoch": 19.72,
|
| 2067 |
+
"learning_rate": 4.769359215195158e-06,
|
| 2068 |
+
"loss": 0.6196,
|
| 2069 |
+
"step": 31500
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 19.79,
|
| 2073 |
+
"learning_rate": 3.7257357545397616e-06,
|
| 2074 |
+
"loss": 0.6232,
|
| 2075 |
+
"step": 31600
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 19.85,
|
| 2079 |
+
"learning_rate": 2.6821122938843665e-06,
|
| 2080 |
+
"loss": 0.6747,
|
| 2081 |
+
"step": 31700
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 19.91,
|
| 2085 |
+
"learning_rate": 1.638488833228971e-06,
|
| 2086 |
+
"loss": 0.6485,
|
| 2087 |
+
"step": 31800
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 19.97,
|
| 2091 |
+
"learning_rate": 5.948653725735754e-07,
|
| 2092 |
+
"loss": 0.6411,
|
| 2093 |
+
"step": 31900
|
| 2094 |
+
},
|
| 2095 |
+
{
|
| 2096 |
+
"epoch": 20.0,
|
| 2097 |
+
"eval_accuracy": 0.9089438070020595,
|
| 2098 |
+
"eval_loss": 0.30604276061058044,
|
| 2099 |
+
"eval_runtime": 142.2608,
|
| 2100 |
+
"eval_samples_per_second": 47.785,
|
| 2101 |
+
"eval_steps_per_second": 0.752,
|
| 2102 |
+
"step": 31940
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 20.0,
|
| 2106 |
+
"step": 31940,
|
| 2107 |
+
"total_flos": 0.0,
|
| 2108 |
+
"train_loss": 0.8135456519344858,
|
| 2109 |
+
"train_runtime": 27591.4491,
|
| 2110 |
+
"train_samples_per_second": 37.036,
|
| 2111 |
+
"train_steps_per_second": 1.158
|
| 2112 |
+
}
|
| 2113 |
+
],
|
| 2114 |
+
"max_steps": 31940,
|
| 2115 |
+
"num_train_epochs": 20,
|
| 2116 |
+
"total_flos": 0.0,
|
| 2117 |
+
"trial_name": null,
|
| 2118 |
+
"trial_params": null
|
| 2119 |
+
}
|