Commit
•
6374004
1
Parent(s):
261f51b
End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1330 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 2.6778283831716956,
|
| 4 |
+
"train_runtime": 390.8223,
|
| 5 |
+
"train_samples": 459,
|
| 6 |
+
"train_samples_per_second": 3.523,
|
| 7 |
+
"train_steps_per_second": 0.223
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 2.6778283831716956,
|
| 4 |
+
"train_runtime": 390.8223,
|
| 5 |
+
"train_samples": 459,
|
| 6 |
+
"train_samples_per_second": 3.523,
|
| 7 |
+
"train_steps_per_second": 0.223
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 87,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 3e-05,
|
| 13 |
+
"loss": 3.1406,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"eval_accuracy": 0.04514027769841723,
|
| 19 |
+
"eval_loss": 3.076171875,
|
| 20 |
+
"eval_runtime": 2.8635,
|
| 21 |
+
"eval_samples_per_second": 30.033,
|
| 22 |
+
"eval_steps_per_second": 2.095,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.07,
|
| 27 |
+
"learning_rate": 3e-05,
|
| 28 |
+
"loss": 3.074,
|
| 29 |
+
"step": 2
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.07,
|
| 33 |
+
"eval_accuracy": 0.04514027769841723,
|
| 34 |
+
"eval_loss": 3.076171875,
|
| 35 |
+
"eval_runtime": 2.8038,
|
| 36 |
+
"eval_samples_per_second": 30.673,
|
| 37 |
+
"eval_steps_per_second": 2.14,
|
| 38 |
+
"step": 2
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1,
|
| 42 |
+
"learning_rate": 3e-05,
|
| 43 |
+
"loss": 3.0557,
|
| 44 |
+
"step": 3
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1,
|
| 48 |
+
"eval_accuracy": 0.04514027769841723,
|
| 49 |
+
"eval_loss": 3.076171875,
|
| 50 |
+
"eval_runtime": 1.812,
|
| 51 |
+
"eval_samples_per_second": 47.46,
|
| 52 |
+
"eval_steps_per_second": 3.311,
|
| 53 |
+
"step": 3
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.14,
|
| 57 |
+
"learning_rate": 2.9990221430845156e-05,
|
| 58 |
+
"loss": 3.2166,
|
| 59 |
+
"step": 4
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14,
|
| 63 |
+
"eval_accuracy": 0.045697388720644536,
|
| 64 |
+
"eval_loss": 3.017578125,
|
| 65 |
+
"eval_runtime": 1.7487,
|
| 66 |
+
"eval_samples_per_second": 49.181,
|
| 67 |
+
"eval_steps_per_second": 3.431,
|
| 68 |
+
"step": 4
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.17,
|
| 72 |
+
"learning_rate": 2.996089847276925e-05,
|
| 73 |
+
"loss": 3.0989,
|
| 74 |
+
"step": 5
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.17,
|
| 78 |
+
"eval_accuracy": 0.04601165647677276,
|
| 79 |
+
"eval_loss": 2.9921875,
|
| 80 |
+
"eval_runtime": 2.7561,
|
| 81 |
+
"eval_samples_per_second": 31.204,
|
| 82 |
+
"eval_steps_per_second": 2.177,
|
| 83 |
+
"step": 5
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.21,
|
| 87 |
+
"learning_rate": 2.9912069357315394e-05,
|
| 88 |
+
"loss": 3.0732,
|
| 89 |
+
"step": 6
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.21,
|
| 93 |
+
"eval_accuracy": 0.04635449402891263,
|
| 94 |
+
"eval_loss": 2.974609375,
|
| 95 |
+
"eval_runtime": 2.7568,
|
| 96 |
+
"eval_samples_per_second": 31.196,
|
| 97 |
+
"eval_steps_per_second": 2.176,
|
| 98 |
+
"step": 6
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.24,
|
| 102 |
+
"learning_rate": 2.9843797748334563e-05,
|
| 103 |
+
"loss": 3.0867,
|
| 104 |
+
"step": 7
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.24,
|
| 108 |
+
"eval_accuracy": 0.04628306953888349,
|
| 109 |
+
"eval_loss": 2.962890625,
|
| 110 |
+
"eval_runtime": 1.7772,
|
| 111 |
+
"eval_samples_per_second": 48.39,
|
| 112 |
+
"eval_steps_per_second": 3.376,
|
| 113 |
+
"step": 7
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.28,
|
| 117 |
+
"learning_rate": 2.975617265898004e-05,
|
| 118 |
+
"loss": 2.979,
|
| 119 |
+
"step": 8
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.28,
|
| 123 |
+
"eval_accuracy": 0.04668304668304668,
|
| 124 |
+
"eval_loss": 2.951171875,
|
| 125 |
+
"eval_runtime": 2.0751,
|
| 126 |
+
"eval_samples_per_second": 41.444,
|
| 127 |
+
"eval_steps_per_second": 2.891,
|
| 128 |
+
"step": 8
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.31,
|
| 132 |
+
"learning_rate": 2.96493083356513e-05,
|
| 133 |
+
"loss": 3.1838,
|
| 134 |
+
"step": 9
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.31,
|
| 138 |
+
"eval_accuracy": 0.04668304668304668,
|
| 139 |
+
"eval_loss": 2.94140625,
|
| 140 |
+
"eval_runtime": 2.063,
|
| 141 |
+
"eval_samples_per_second": 41.687,
|
| 142 |
+
"eval_steps_per_second": 2.908,
|
| 143 |
+
"step": 9
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.34,
|
| 147 |
+
"learning_rate": 2.952334410903845e-05,
|
| 148 |
+
"loss": 2.9399,
|
| 149 |
+
"step": 10
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.34,
|
| 153 |
+
"eval_accuracy": 0.04674018627507,
|
| 154 |
+
"eval_loss": 2.93359375,
|
| 155 |
+
"eval_runtime": 1.7666,
|
| 156 |
+
"eval_samples_per_second": 48.681,
|
| 157 |
+
"eval_steps_per_second": 3.396,
|
| 158 |
+
"step": 10
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.38,
|
| 162 |
+
"learning_rate": 2.937844421246162e-05,
|
| 163 |
+
"loss": 2.926,
|
| 164 |
+
"step": 11
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.38,
|
| 168 |
+
"eval_accuracy": 0.047125878521227356,
|
| 169 |
+
"eval_loss": 2.92578125,
|
| 170 |
+
"eval_runtime": 2.0537,
|
| 171 |
+
"eval_samples_per_second": 41.875,
|
| 172 |
+
"eval_steps_per_second": 2.921,
|
| 173 |
+
"step": 11
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.41,
|
| 177 |
+
"learning_rate": 2.9214797567742036e-05,
|
| 178 |
+
"loss": 3.2144,
|
| 179 |
+
"step": 12
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.41,
|
| 183 |
+
"eval_accuracy": 0.047254442603279816,
|
| 184 |
+
"eval_loss": 2.919921875,
|
| 185 |
+
"eval_runtime": 1.7851,
|
| 186 |
+
"eval_samples_per_second": 48.176,
|
| 187 |
+
"eval_steps_per_second": 3.361,
|
| 188 |
+
"step": 12
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.45,
|
| 192 |
+
"learning_rate": 2.9032617538884018e-05,
|
| 193 |
+
"loss": 2.978,
|
| 194 |
+
"step": 13
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.45,
|
| 198 |
+
"eval_accuracy": 0.04735443688932061,
|
| 199 |
+
"eval_loss": 2.9140625,
|
| 200 |
+
"eval_runtime": 2.7591,
|
| 201 |
+
"eval_samples_per_second": 31.17,
|
| 202 |
+
"eval_steps_per_second": 2.175,
|
| 203 |
+
"step": 13
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.48,
|
| 207 |
+
"learning_rate": 2.8832141653888998e-05,
|
| 208 |
+
"loss": 3.0076,
|
| 209 |
+
"step": 14
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.48,
|
| 213 |
+
"eval_accuracy": 0.047640134849437174,
|
| 214 |
+
"eval_loss": 2.908203125,
|
| 215 |
+
"eval_runtime": 2.6767,
|
| 216 |
+
"eval_samples_per_second": 32.129,
|
| 217 |
+
"eval_steps_per_second": 2.242,
|
| 218 |
+
"step": 14
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.52,
|
| 222 |
+
"learning_rate": 2.861363129506436e-05,
|
| 223 |
+
"loss": 2.9897,
|
| 224 |
+
"step": 15
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.52,
|
| 228 |
+
"eval_accuracy": 0.04772584423747214,
|
| 229 |
+
"eval_loss": 2.90234375,
|
| 230 |
+
"eval_runtime": 1.7524,
|
| 231 |
+
"eval_samples_per_second": 49.075,
|
| 232 |
+
"eval_steps_per_second": 3.424,
|
| 233 |
+
"step": 15
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.55,
|
| 237 |
+
"learning_rate": 2.8377371358230733e-05,
|
| 238 |
+
"loss": 2.8831,
|
| 239 |
+
"step": 16
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.55,
|
| 243 |
+
"eval_accuracy": 0.04792583280955374,
|
| 244 |
+
"eval_loss": 2.89453125,
|
| 245 |
+
"eval_runtime": 2.0593,
|
| 246 |
+
"eval_samples_per_second": 41.762,
|
| 247 |
+
"eval_steps_per_second": 2.914,
|
| 248 |
+
"step": 16
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.59,
|
| 252 |
+
"learning_rate": 2.8123669881272247e-05,
|
| 253 |
+
"loss": 2.9749,
|
| 254 |
+
"step": 17
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.59,
|
| 258 |
+
"eval_accuracy": 0.04786869321753043,
|
| 259 |
+
"eval_loss": 2.88671875,
|
| 260 |
+
"eval_runtime": 2.7597,
|
| 261 |
+
"eval_samples_per_second": 31.163,
|
| 262 |
+
"eval_steps_per_second": 2.174,
|
| 263 |
+
"step": 17
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.62,
|
| 267 |
+
"learning_rate": 2.7852857642513838e-05,
|
| 268 |
+
"loss": 2.9431,
|
| 269 |
+
"step": 18
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.62,
|
| 273 |
+
"eval_accuracy": 0.04776869893148963,
|
| 274 |
+
"eval_loss": 2.8828125,
|
| 275 |
+
"eval_runtime": 1.7792,
|
| 276 |
+
"eval_samples_per_second": 48.336,
|
| 277 |
+
"eval_steps_per_second": 3.372,
|
| 278 |
+
"step": 18
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.66,
|
| 282 |
+
"learning_rate": 2.7565287729449473e-05,
|
| 283 |
+
"loss": 3.0498,
|
| 284 |
+
"step": 19
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.66,
|
| 288 |
+
"eval_accuracy": 0.047882978115536254,
|
| 289 |
+
"eval_loss": 2.876953125,
|
| 290 |
+
"eval_runtime": 2.7592,
|
| 291 |
+
"eval_samples_per_second": 31.168,
|
| 292 |
+
"eval_steps_per_second": 2.175,
|
| 293 |
+
"step": 19
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.69,
|
| 297 |
+
"learning_rate": 2.7261335078383377e-05,
|
| 298 |
+
"loss": 2.9409,
|
| 299 |
+
"step": 20
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.69,
|
| 303 |
+
"eval_accuracy": 0.047854408319524595,
|
| 304 |
+
"eval_loss": 2.87109375,
|
| 305 |
+
"eval_runtime": 1.7642,
|
| 306 |
+
"eval_samples_per_second": 48.747,
|
| 307 |
+
"eval_steps_per_second": 3.401,
|
| 308 |
+
"step": 20
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.72,
|
| 312 |
+
"learning_rate": 2.6941395985584656e-05,
|
| 313 |
+
"loss": 2.96,
|
| 314 |
+
"step": 21
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.72,
|
| 318 |
+
"eval_accuracy": 0.04802582709559454,
|
| 319 |
+
"eval_loss": 2.8671875,
|
| 320 |
+
"eval_runtime": 1.7801,
|
| 321 |
+
"eval_samples_per_second": 48.313,
|
| 322 |
+
"eval_steps_per_second": 3.371,
|
| 323 |
+
"step": 21
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.76,
|
| 327 |
+
"learning_rate": 2.6605887590592547e-05,
|
| 328 |
+
"loss": 3.0767,
|
| 329 |
+
"step": 22
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.76,
|
| 333 |
+
"eval_accuracy": 0.04784012342151877,
|
| 334 |
+
"eval_loss": 2.86328125,
|
| 335 |
+
"eval_runtime": 2.3678,
|
| 336 |
+
"eval_samples_per_second": 36.32,
|
| 337 |
+
"eval_steps_per_second": 2.534,
|
| 338 |
+
"step": 22
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.79,
|
| 342 |
+
"learning_rate": 2.6255247332346036e-05,
|
| 343 |
+
"loss": 2.772,
|
| 344 |
+
"step": 23
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.79,
|
| 348 |
+
"eval_accuracy": 0.04792583280955374,
|
| 349 |
+
"eval_loss": 2.859375,
|
| 350 |
+
"eval_runtime": 2.7833,
|
| 351 |
+
"eval_samples_per_second": 30.899,
|
| 352 |
+
"eval_steps_per_second": 2.156,
|
| 353 |
+
"step": 23
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.83,
|
| 357 |
+
"learning_rate": 2.5889932378846963e-05,
|
| 358 |
+
"loss": 3.0574,
|
| 359 |
+
"step": 24
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.83,
|
| 363 |
+
"eval_accuracy": 0.04801154219758871,
|
| 364 |
+
"eval_loss": 2.853515625,
|
| 365 |
+
"eval_runtime": 2.7758,
|
| 366 |
+
"eval_samples_per_second": 30.982,
|
| 367 |
+
"eval_steps_per_second": 2.162,
|
| 368 |
+
"step": 24
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.86,
|
| 372 |
+
"learning_rate": 2.5510419031100137e-05,
|
| 373 |
+
"loss": 2.8137,
|
| 374 |
+
"step": 25
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.86,
|
| 378 |
+
"eval_accuracy": 0.048040111993600365,
|
| 379 |
+
"eval_loss": 2.849609375,
|
| 380 |
+
"eval_runtime": 2.7701,
|
| 381 |
+
"eval_samples_per_second": 31.046,
|
| 382 |
+
"eval_steps_per_second": 2.166,
|
| 383 |
+
"step": 25
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.9,
|
| 387 |
+
"learning_rate": 2.5117202102107707e-05,
|
| 388 |
+
"loss": 2.8872,
|
| 389 |
+
"step": 26
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.9,
|
| 393 |
+
"eval_accuracy": 0.048282955259699445,
|
| 394 |
+
"eval_loss": 2.84375,
|
| 395 |
+
"eval_runtime": 1.7514,
|
| 396 |
+
"eval_samples_per_second": 49.103,
|
| 397 |
+
"eval_steps_per_second": 3.426,
|
| 398 |
+
"step": 26
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.93,
|
| 402 |
+
"learning_rate": 2.4710794271727415e-05,
|
| 403 |
+
"loss": 3.0085,
|
| 404 |
+
"step": 27
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.93,
|
| 408 |
+
"eval_accuracy": 0.0484115193417519,
|
| 409 |
+
"eval_loss": 2.83984375,
|
| 410 |
+
"eval_runtime": 1.7625,
|
| 411 |
+
"eval_samples_per_second": 48.794,
|
| 412 |
+
"eval_steps_per_second": 3.404,
|
| 413 |
+
"step": 27
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.97,
|
| 417 |
+
"learning_rate": 2.4291725418235848e-05,
|
| 418 |
+
"loss": 2.9165,
|
| 419 |
+
"step": 28
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.97,
|
| 423 |
+
"eval_accuracy": 0.0485115136277927,
|
| 424 |
+
"eval_loss": 2.8359375,
|
| 425 |
+
"eval_runtime": 2.0562,
|
| 426 |
+
"eval_samples_per_second": 41.824,
|
| 427 |
+
"eval_steps_per_second": 2.918,
|
| 428 |
+
"step": 28
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.0,
|
| 432 |
+
"learning_rate": 2.3860541927468265e-05,
|
| 433 |
+
"loss": 2.8525,
|
| 434 |
+
"step": 29
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.0,
|
| 438 |
+
"eval_accuracy": 0.04861150791383349,
|
| 439 |
+
"eval_loss": 2.833984375,
|
| 440 |
+
"eval_runtime": 2.0728,
|
| 441 |
+
"eval_samples_per_second": 41.49,
|
| 442 |
+
"eval_steps_per_second": 2.895,
|
| 443 |
+
"step": 29
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.03,
|
| 447 |
+
"learning_rate": 2.341780598043574e-05,
|
| 448 |
+
"loss": 2.7759,
|
| 449 |
+
"step": 30
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.03,
|
| 453 |
+
"eval_accuracy": 0.04845437403576938,
|
| 454 |
+
"eval_loss": 2.830078125,
|
| 455 |
+
"eval_runtime": 1.7727,
|
| 456 |
+
"eval_samples_per_second": 48.512,
|
| 457 |
+
"eval_steps_per_second": 3.385,
|
| 458 |
+
"step": 30
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.07,
|
| 462 |
+
"learning_rate": 2.2964094820348302e-05,
|
| 463 |
+
"loss": 2.7312,
|
| 464 |
+
"step": 31
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.07,
|
| 468 |
+
"eval_accuracy": 0.048497228729786866,
|
| 469 |
+
"eval_loss": 2.828125,
|
| 470 |
+
"eval_runtime": 1.7542,
|
| 471 |
+
"eval_samples_per_second": 49.026,
|
| 472 |
+
"eval_steps_per_second": 3.42,
|
| 473 |
+
"step": 31
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.1,
|
| 477 |
+
"learning_rate": 2.25e-05,
|
| 478 |
+
"loss": 2.6641,
|
| 479 |
+
"step": 32
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.1,
|
| 483 |
+
"eval_accuracy": 0.04866864750585681,
|
| 484 |
+
"eval_loss": 2.826171875,
|
| 485 |
+
"eval_runtime": 2.6551,
|
| 486 |
+
"eval_samples_per_second": 32.39,
|
| 487 |
+
"eval_steps_per_second": 2.26,
|
| 488 |
+
"step": 32
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.14,
|
| 492 |
+
"learning_rate": 2.2026126610496852e-05,
|
| 493 |
+
"loss": 2.7896,
|
| 494 |
+
"step": 33
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.14,
|
| 498 |
+
"eval_accuracy": 0.04855436832181018,
|
| 499 |
+
"eval_loss": 2.82421875,
|
| 500 |
+
"eval_runtime": 1.7664,
|
| 501 |
+
"eval_samples_per_second": 48.686,
|
| 502 |
+
"eval_steps_per_second": 3.397,
|
| 503 |
+
"step": 33
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.17,
|
| 507 |
+
"learning_rate": 2.154309249233351e-05,
|
| 508 |
+
"loss": 2.7878,
|
| 509 |
+
"step": 34
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.17,
|
| 513 |
+
"eval_accuracy": 0.04866864750585681,
|
| 514 |
+
"eval_loss": 2.822265625,
|
| 515 |
+
"eval_runtime": 1.7584,
|
| 516 |
+
"eval_samples_per_second": 48.909,
|
| 517 |
+
"eval_steps_per_second": 3.412,
|
| 518 |
+
"step": 34
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.21,
|
| 522 |
+
"learning_rate": 2.105152742984713e-05,
|
| 523 |
+
"loss": 2.4028,
|
| 524 |
+
"step": 35
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.21,
|
| 528 |
+
"eval_accuracy": 0.04869721730186846,
|
| 529 |
+
"eval_loss": 2.8203125,
|
| 530 |
+
"eval_runtime": 2.7671,
|
| 531 |
+
"eval_samples_per_second": 31.08,
|
| 532 |
+
"eval_steps_per_second": 2.168,
|
| 533 |
+
"step": 35
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.24,
|
| 537 |
+
"learning_rate": 2.055207233009872e-05,
|
| 538 |
+
"loss": 2.5618,
|
| 539 |
+
"step": 36
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.24,
|
| 543 |
+
"eval_accuracy": 0.04878292668990344,
|
| 544 |
+
"eval_loss": 2.818359375,
|
| 545 |
+
"eval_runtime": 1.7727,
|
| 546 |
+
"eval_samples_per_second": 48.514,
|
| 547 |
+
"eval_steps_per_second": 3.385,
|
| 548 |
+
"step": 36
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.28,
|
| 552 |
+
"learning_rate": 2.0045378387252624e-05,
|
| 553 |
+
"loss": 2.6697,
|
| 554 |
+
"step": 37
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.28,
|
| 558 |
+
"eval_accuracy": 0.04875435689389178,
|
| 559 |
+
"eval_loss": 2.81640625,
|
| 560 |
+
"eval_runtime": 2.7791,
|
| 561 |
+
"eval_samples_per_second": 30.945,
|
| 562 |
+
"eval_steps_per_second": 2.159,
|
| 563 |
+
"step": 37
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.31,
|
| 567 |
+
"learning_rate": 1.953210623354359e-05,
|
| 568 |
+
"loss": 2.6333,
|
| 569 |
+
"step": 38
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.31,
|
| 573 |
+
"eval_accuracy": 0.048711502199874294,
|
| 574 |
+
"eval_loss": 2.814453125,
|
| 575 |
+
"eval_runtime": 2.7731,
|
| 576 |
+
"eval_samples_per_second": 31.012,
|
| 577 |
+
"eval_steps_per_second": 2.164,
|
| 578 |
+
"step": 38
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.34,
|
| 582 |
+
"learning_rate": 1.9012925077938318e-05,
|
| 583 |
+
"loss": 2.4897,
|
| 584 |
+
"step": 39
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.34,
|
| 588 |
+
"eval_accuracy": 0.04858293811782184,
|
| 589 |
+
"eval_loss": 2.8125,
|
| 590 |
+
"eval_runtime": 2.7903,
|
| 591 |
+
"eval_samples_per_second": 30.821,
|
| 592 |
+
"eval_steps_per_second": 2.15,
|
| 593 |
+
"step": 39
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.38,
|
| 597 |
+
"learning_rate": 1.848851183361466e-05,
|
| 598 |
+
"loss": 2.4908,
|
| 599 |
+
"step": 40
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.38,
|
| 603 |
+
"eval_accuracy": 0.04865436260785098,
|
| 604 |
+
"eval_loss": 2.810546875,
|
| 605 |
+
"eval_runtime": 2.7759,
|
| 606 |
+
"eval_samples_per_second": 30.981,
|
| 607 |
+
"eval_steps_per_second": 2.161,
|
| 608 |
+
"step": 40
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.41,
|
| 612 |
+
"learning_rate": 1.7959550235396002e-05,
|
| 613 |
+
"loss": 2.6926,
|
| 614 |
+
"step": 41
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.41,
|
| 618 |
+
"eval_accuracy": 0.048768641791897605,
|
| 619 |
+
"eval_loss": 2.80859375,
|
| 620 |
+
"eval_runtime": 2.6681,
|
| 621 |
+
"eval_samples_per_second": 32.233,
|
| 622 |
+
"eval_steps_per_second": 2.249,
|
| 623 |
+
"step": 41
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.45,
|
| 627 |
+
"learning_rate": 1.7426729948291474e-05,
|
| 628 |
+
"loss": 2.6602,
|
| 629 |
+
"step": 42
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.45,
|
| 633 |
+
"eval_accuracy": 0.048868636077938406,
|
| 634 |
+
"eval_loss": 2.806640625,
|
| 635 |
+
"eval_runtime": 1.7824,
|
| 636 |
+
"eval_samples_per_second": 48.25,
|
| 637 |
+
"eval_steps_per_second": 3.366,
|
| 638 |
+
"step": 42
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 1.48,
|
| 642 |
+
"learning_rate": 1.689074566830434e-05,
|
| 643 |
+
"loss": 2.8054,
|
| 644 |
+
"step": 43
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.48,
|
| 648 |
+
"eval_accuracy": 0.04885435117993257,
|
| 649 |
+
"eval_loss": 2.8046875,
|
| 650 |
+
"eval_runtime": 2.6637,
|
| 651 |
+
"eval_samples_per_second": 32.286,
|
| 652 |
+
"eval_steps_per_second": 2.253,
|
| 653 |
+
"step": 43
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.52,
|
| 657 |
+
"learning_rate": 1.635229621668098e-05,
|
| 658 |
+
"loss": 2.5532,
|
| 659 |
+
"step": 44
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 1.52,
|
| 663 |
+
"eval_accuracy": 0.048954345465973374,
|
| 664 |
+
"eval_loss": 2.8046875,
|
| 665 |
+
"eval_runtime": 2.7813,
|
| 666 |
+
"eval_samples_per_second": 30.921,
|
| 667 |
+
"eval_steps_per_second": 2.157,
|
| 668 |
+
"step": 44
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.55,
|
| 672 |
+
"learning_rate": 1.5812083628781265e-05,
|
| 673 |
+
"loss": 2.4756,
|
| 674 |
+
"step": 45
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.55,
|
| 678 |
+
"eval_accuracy": 0.04906862465002,
|
| 679 |
+
"eval_loss": 2.802734375,
|
| 680 |
+
"eval_runtime": 2.3836,
|
| 681 |
+
"eval_samples_per_second": 36.08,
|
| 682 |
+
"eval_steps_per_second": 2.517,
|
| 683 |
+
"step": 45
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 1.59,
|
| 687 |
+
"learning_rate": 1.5270812238758407e-05,
|
| 688 |
+
"loss": 2.6123,
|
| 689 |
+
"step": 46
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.59,
|
| 693 |
+
"eval_accuracy": 0.04912576424204331,
|
| 694 |
+
"eval_loss": 2.80078125,
|
| 695 |
+
"eval_runtime": 1.7527,
|
| 696 |
+
"eval_samples_per_second": 49.068,
|
| 697 |
+
"eval_steps_per_second": 3.423,
|
| 698 |
+
"step": 46
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.62,
|
| 702 |
+
"learning_rate": 1.4729187761241592e-05,
|
| 703 |
+
"loss": 2.5117,
|
| 704 |
+
"step": 47
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.62,
|
| 708 |
+
"eval_accuracy": 0.04902576995600252,
|
| 709 |
+
"eval_loss": 2.798828125,
|
| 710 |
+
"eval_runtime": 1.7703,
|
| 711 |
+
"eval_samples_per_second": 48.579,
|
| 712 |
+
"eval_steps_per_second": 3.389,
|
| 713 |
+
"step": 47
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.66,
|
| 717 |
+
"learning_rate": 1.4187916371218739e-05,
|
| 718 |
+
"loss": 2.5552,
|
| 719 |
+
"step": 48
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 1.66,
|
| 723 |
+
"eval_accuracy": 0.04904005485400834,
|
| 724 |
+
"eval_loss": 2.796875,
|
| 725 |
+
"eval_runtime": 2.7807,
|
| 726 |
+
"eval_samples_per_second": 30.928,
|
| 727 |
+
"eval_steps_per_second": 2.158,
|
| 728 |
+
"step": 48
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 1.69,
|
| 732 |
+
"learning_rate": 1.3647703783319022e-05,
|
| 733 |
+
"loss": 2.5122,
|
| 734 |
+
"step": 49
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.69,
|
| 738 |
+
"eval_accuracy": 0.04902576995600252,
|
| 739 |
+
"eval_loss": 2.794921875,
|
| 740 |
+
"eval_runtime": 1.7675,
|
| 741 |
+
"eval_samples_per_second": 48.658,
|
| 742 |
+
"eval_steps_per_second": 3.395,
|
| 743 |
+
"step": 49
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 1.72,
|
| 747 |
+
"learning_rate": 1.310925433169566e-05,
|
| 748 |
+
"loss": 2.5593,
|
| 749 |
+
"step": 50
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.72,
|
| 753 |
+
"eval_accuracy": 0.04909719444603165,
|
| 754 |
+
"eval_loss": 2.79296875,
|
| 755 |
+
"eval_runtime": 1.7524,
|
| 756 |
+
"eval_samples_per_second": 49.077,
|
| 757 |
+
"eval_steps_per_second": 3.424,
|
| 758 |
+
"step": 50
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.76,
|
| 762 |
+
"learning_rate": 1.2573270051708529e-05,
|
| 763 |
+
"loss": 2.5759,
|
| 764 |
+
"step": 51
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 1.76,
|
| 768 |
+
"eval_accuracy": 0.04909719444603165,
|
| 769 |
+
"eval_loss": 2.791015625,
|
| 770 |
+
"eval_runtime": 2.7672,
|
| 771 |
+
"eval_samples_per_second": 31.079,
|
| 772 |
+
"eval_steps_per_second": 2.168,
|
| 773 |
+
"step": 51
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.79,
|
| 777 |
+
"learning_rate": 1.2040449764604002e-05,
|
| 778 |
+
"loss": 2.5535,
|
| 779 |
+
"step": 52
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.79,
|
| 783 |
+
"eval_accuracy": 0.04929718301811325,
|
| 784 |
+
"eval_loss": 2.7890625,
|
| 785 |
+
"eval_runtime": 2.6669,
|
| 786 |
+
"eval_samples_per_second": 32.247,
|
| 787 |
+
"eval_steps_per_second": 2.25,
|
| 788 |
+
"step": 52
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 1.83,
|
| 792 |
+
"learning_rate": 1.1511488166385349e-05,
|
| 793 |
+
"loss": 2.6531,
|
| 794 |
+
"step": 53
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.83,
|
| 798 |
+
"eval_accuracy": 0.04939717730415405,
|
| 799 |
+
"eval_loss": 2.787109375,
|
| 800 |
+
"eval_runtime": 2.0564,
|
| 801 |
+
"eval_samples_per_second": 41.821,
|
| 802 |
+
"eval_steps_per_second": 2.918,
|
| 803 |
+
"step": 53
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.86,
|
| 807 |
+
"learning_rate": 1.098707492206169e-05,
|
| 808 |
+
"loss": 2.5701,
|
| 809 |
+
"step": 54
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.86,
|
| 813 |
+
"eval_accuracy": 0.0495257413862065,
|
| 814 |
+
"eval_loss": 2.78515625,
|
| 815 |
+
"eval_runtime": 1.7609,
|
| 816 |
+
"eval_samples_per_second": 48.84,
|
| 817 |
+
"eval_steps_per_second": 3.407,
|
| 818 |
+
"step": 54
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.9,
|
| 822 |
+
"learning_rate": 1.0467893766456408e-05,
|
| 823 |
+
"loss": 2.6621,
|
| 824 |
+
"step": 55
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.9,
|
| 828 |
+
"eval_accuracy": 0.049654305468258955,
|
| 829 |
+
"eval_loss": 2.783203125,
|
| 830 |
+
"eval_runtime": 2.0679,
|
| 831 |
+
"eval_samples_per_second": 41.587,
|
| 832 |
+
"eval_steps_per_second": 2.901,
|
| 833 |
+
"step": 55
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.93,
|
| 837 |
+
"learning_rate": 9.954621612747371e-06,
|
| 838 |
+
"loss": 2.532,
|
| 839 |
+
"step": 56
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 1.93,
|
| 843 |
+
"eval_accuracy": 0.04958288097822981,
|
| 844 |
+
"eval_loss": 2.78125,
|
| 845 |
+
"eval_runtime": 1.7708,
|
| 846 |
+
"eval_samples_per_second": 48.565,
|
| 847 |
+
"eval_steps_per_second": 3.388,
|
| 848 |
+
"step": 56
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 1.97,
|
| 852 |
+
"learning_rate": 9.447927669901284e-06,
|
| 853 |
+
"loss": 2.5928,
|
| 854 |
+
"step": 57
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.97,
|
| 858 |
+
"eval_accuracy": 0.049654305468258955,
|
| 859 |
+
"eval_loss": 2.779296875,
|
| 860 |
+
"eval_runtime": 1.752,
|
| 861 |
+
"eval_samples_per_second": 49.086,
|
| 862 |
+
"eval_steps_per_second": 3.425,
|
| 863 |
+
"step": 57
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.0,
|
| 867 |
+
"learning_rate": 8.948472570152874e-06,
|
| 868 |
+
"loss": 2.5486,
|
| 869 |
+
"step": 58
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 2.0,
|
| 873 |
+
"eval_accuracy": 0.04969716016227644,
|
| 874 |
+
"eval_loss": 2.775390625,
|
| 875 |
+
"eval_runtime": 1.768,
|
| 876 |
+
"eval_samples_per_second": 48.642,
|
| 877 |
+
"eval_steps_per_second": 3.394,
|
| 878 |
+
"step": 58
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.03,
|
| 882 |
+
"learning_rate": 8.456907507666488e-06,
|
| 883 |
+
"loss": 2.5009,
|
| 884 |
+
"step": 59
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.03,
|
| 888 |
+
"eval_accuracy": 0.0497257299582881,
|
| 889 |
+
"eval_loss": 2.7734375,
|
| 890 |
+
"eval_runtime": 2.6592,
|
| 891 |
+
"eval_samples_per_second": 32.341,
|
| 892 |
+
"eval_steps_per_second": 2.256,
|
| 893 |
+
"step": 59
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.07,
|
| 897 |
+
"learning_rate": 7.97387338950315e-06,
|
| 898 |
+
"loss": 2.4346,
|
| 899 |
+
"step": 60
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 2.07,
|
| 903 |
+
"eval_accuracy": 0.049754299754299756,
|
| 904 |
+
"eval_loss": 2.7734375,
|
| 905 |
+
"eval_runtime": 1.77,
|
| 906 |
+
"eval_samples_per_second": 48.588,
|
| 907 |
+
"eval_steps_per_second": 3.39,
|
| 908 |
+
"step": 60
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 2.1,
|
| 912 |
+
"learning_rate": 7.500000000000004e-06,
|
| 913 |
+
"loss": 2.3259,
|
| 914 |
+
"step": 61
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.1,
|
| 918 |
+
"eval_accuracy": 0.049740014856293924,
|
| 919 |
+
"eval_loss": 2.771484375,
|
| 920 |
+
"eval_runtime": 2.7629,
|
| 921 |
+
"eval_samples_per_second": 31.127,
|
| 922 |
+
"eval_steps_per_second": 2.172,
|
| 923 |
+
"step": 61
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 2.14,
|
| 927 |
+
"learning_rate": 7.035905179651701e-06,
|
| 928 |
+
"loss": 2.3569,
|
| 929 |
+
"step": 62
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.14,
|
| 933 |
+
"eval_accuracy": 0.04978286955031141,
|
| 934 |
+
"eval_loss": 2.76953125,
|
| 935 |
+
"eval_runtime": 2.7575,
|
| 936 |
+
"eval_samples_per_second": 31.187,
|
| 937 |
+
"eval_steps_per_second": 2.176,
|
| 938 |
+
"step": 62
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 2.17,
|
| 942 |
+
"learning_rate": 6.582194019564266e-06,
|
| 943 |
+
"loss": 2.5898,
|
| 944 |
+
"step": 63
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 2.17,
|
| 948 |
+
"eval_accuracy": 0.049811439346323066,
|
| 949 |
+
"eval_loss": 2.76953125,
|
| 950 |
+
"eval_runtime": 1.7477,
|
| 951 |
+
"eval_samples_per_second": 49.209,
|
| 952 |
+
"eval_steps_per_second": 3.433,
|
| 953 |
+
"step": 63
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 2.21,
|
| 957 |
+
"learning_rate": 6.1394580725317366e-06,
|
| 958 |
+
"loss": 2.3657,
|
| 959 |
+
"step": 64
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 2.21,
|
| 963 |
+
"eval_accuracy": 0.04976858465230558,
|
| 964 |
+
"eval_loss": 2.767578125,
|
| 965 |
+
"eval_runtime": 1.7819,
|
| 966 |
+
"eval_samples_per_second": 48.263,
|
| 967 |
+
"eval_steps_per_second": 3.367,
|
| 968 |
+
"step": 64
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.24,
|
| 972 |
+
"learning_rate": 5.708274581764155e-06,
|
| 973 |
+
"loss": 2.4875,
|
| 974 |
+
"step": 65
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 2.24,
|
| 978 |
+
"eval_accuracy": 0.049754299754299756,
|
| 979 |
+
"eval_loss": 2.767578125,
|
| 980 |
+
"eval_runtime": 2.7652,
|
| 981 |
+
"eval_samples_per_second": 31.1,
|
| 982 |
+
"eval_steps_per_second": 2.17,
|
| 983 |
+
"step": 65
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 2.28,
|
| 987 |
+
"learning_rate": 5.289205728272587e-06,
|
| 988 |
+
"loss": 2.4392,
|
| 989 |
+
"step": 66
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.28,
|
| 993 |
+
"eval_accuracy": 0.0497257299582881,
|
| 994 |
+
"eval_loss": 2.767578125,
|
| 995 |
+
"eval_runtime": 2.0654,
|
| 996 |
+
"eval_samples_per_second": 41.638,
|
| 997 |
+
"eval_steps_per_second": 2.905,
|
| 998 |
+
"step": 66
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.31,
|
| 1002 |
+
"learning_rate": 4.882797897892293e-06,
|
| 1003 |
+
"loss": 2.3595,
|
| 1004 |
+
"step": 67
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.31,
|
| 1008 |
+
"eval_accuracy": 0.0497257299582881,
|
| 1009 |
+
"eval_loss": 2.765625,
|
| 1010 |
+
"eval_runtime": 2.674,
|
| 1011 |
+
"eval_samples_per_second": 32.162,
|
| 1012 |
+
"eval_steps_per_second": 2.244,
|
| 1013 |
+
"step": 67
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.34,
|
| 1017 |
+
"learning_rate": 4.4895809688998655e-06,
|
| 1018 |
+
"loss": 2.4757,
|
| 1019 |
+
"step": 68
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 2.34,
|
| 1023 |
+
"eval_accuracy": 0.049811439346323066,
|
| 1024 |
+
"eval_loss": 2.765625,
|
| 1025 |
+
"eval_runtime": 2.7575,
|
| 1026 |
+
"eval_samples_per_second": 31.187,
|
| 1027 |
+
"eval_steps_per_second": 2.176,
|
| 1028 |
+
"step": 68
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.38,
|
| 1032 |
+
"learning_rate": 4.110067621153041e-06,
|
| 1033 |
+
"loss": 2.4617,
|
| 1034 |
+
"step": 69
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.38,
|
| 1038 |
+
"eval_accuracy": 0.049811439346323066,
|
| 1039 |
+
"eval_loss": 2.765625,
|
| 1040 |
+
"eval_runtime": 2.7642,
|
| 1041 |
+
"eval_samples_per_second": 31.112,
|
| 1042 |
+
"eval_steps_per_second": 2.171,
|
| 1043 |
+
"step": 69
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 2.41,
|
| 1047 |
+
"learning_rate": 3.744752667653965e-06,
|
| 1048 |
+
"loss": 2.3376,
|
| 1049 |
+
"step": 70
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 2.41,
|
| 1053 |
+
"eval_accuracy": 0.049925718530369693,
|
| 1054 |
+
"eval_loss": 2.765625,
|
| 1055 |
+
"eval_runtime": 1.7636,
|
| 1056 |
+
"eval_samples_per_second": 48.763,
|
| 1057 |
+
"eval_steps_per_second": 3.402,
|
| 1058 |
+
"step": 70
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 2.45,
|
| 1062 |
+
"learning_rate": 3.394112409407455e-06,
|
| 1063 |
+
"loss": 2.3129,
|
| 1064 |
+
"step": 71
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 2.45,
|
| 1068 |
+
"eval_accuracy": 0.04982572424432889,
|
| 1069 |
+
"eval_loss": 2.765625,
|
| 1070 |
+
"eval_runtime": 2.0925,
|
| 1071 |
+
"eval_samples_per_second": 41.099,
|
| 1072 |
+
"eval_steps_per_second": 2.867,
|
| 1073 |
+
"step": 71
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.48,
|
| 1077 |
+
"learning_rate": 3.0586040144153436e-06,
|
| 1078 |
+
"loss": 2.5703,
|
| 1079 |
+
"step": 72
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 2.48,
|
| 1083 |
+
"eval_accuracy": 0.04979715444831724,
|
| 1084 |
+
"eval_loss": 2.765625,
|
| 1085 |
+
"eval_runtime": 1.7604,
|
| 1086 |
+
"eval_samples_per_second": 48.851,
|
| 1087 |
+
"eval_steps_per_second": 3.408,
|
| 1088 |
+
"step": 72
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.52,
|
| 1092 |
+
"learning_rate": 2.7386649216166233e-06,
|
| 1093 |
+
"loss": 2.3491,
|
| 1094 |
+
"step": 73
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.52,
|
| 1098 |
+
"eval_accuracy": 0.049811439346323066,
|
| 1099 |
+
"eval_loss": 2.765625,
|
| 1100 |
+
"eval_runtime": 2.7645,
|
| 1101 |
+
"eval_samples_per_second": 31.109,
|
| 1102 |
+
"eval_steps_per_second": 2.17,
|
| 1103 |
+
"step": 73
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 2.55,
|
| 1107 |
+
"learning_rate": 2.4347122705505303e-06,
|
| 1108 |
+
"loss": 2.3484,
|
| 1109 |
+
"step": 74
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.55,
|
| 1113 |
+
"eval_accuracy": 0.049754299754299756,
|
| 1114 |
+
"eval_loss": 2.765625,
|
| 1115 |
+
"eval_runtime": 2.7683,
|
| 1116 |
+
"eval_samples_per_second": 31.066,
|
| 1117 |
+
"eval_steps_per_second": 2.167,
|
| 1118 |
+
"step": 74
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 2.59,
|
| 1122 |
+
"learning_rate": 2.1471423574861643e-06,
|
| 1123 |
+
"loss": 2.3782,
|
| 1124 |
+
"step": 75
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 2.59,
|
| 1128 |
+
"eval_accuracy": 0.049740014856293924,
|
| 1129 |
+
"eval_loss": 2.765625,
|
| 1130 |
+
"eval_runtime": 1.7554,
|
| 1131 |
+
"eval_samples_per_second": 48.991,
|
| 1132 |
+
"eval_steps_per_second": 3.418,
|
| 1133 |
+
"step": 75
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 2.62,
|
| 1137 |
+
"learning_rate": 1.8763301187277554e-06,
|
| 1138 |
+
"loss": 2.4033,
|
| 1139 |
+
"step": 76
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 2.62,
|
| 1143 |
+
"eval_accuracy": 0.04979715444831724,
|
| 1144 |
+
"eval_loss": 2.765625,
|
| 1145 |
+
"eval_runtime": 2.7591,
|
| 1146 |
+
"eval_samples_per_second": 31.17,
|
| 1147 |
+
"eval_steps_per_second": 2.175,
|
| 1148 |
+
"step": 76
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 2.66,
|
| 1152 |
+
"learning_rate": 1.6226286417692666e-06,
|
| 1153 |
+
"loss": 2.3821,
|
| 1154 |
+
"step": 77
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 2.66,
|
| 1158 |
+
"eval_accuracy": 0.04976858465230558,
|
| 1159 |
+
"eval_loss": 2.765625,
|
| 1160 |
+
"eval_runtime": 1.7671,
|
| 1161 |
+
"eval_samples_per_second": 48.668,
|
| 1162 |
+
"eval_steps_per_second": 3.395,
|
| 1163 |
+
"step": 77
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 2.69,
|
| 1167 |
+
"learning_rate": 1.3863687049356465e-06,
|
| 1168 |
+
"loss": 2.39,
|
| 1169 |
+
"step": 78
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 2.69,
|
| 1173 |
+
"eval_accuracy": 0.04979715444831724,
|
| 1174 |
+
"eval_loss": 2.765625,
|
| 1175 |
+
"eval_runtime": 1.7638,
|
| 1176 |
+
"eval_samples_per_second": 48.758,
|
| 1177 |
+
"eval_steps_per_second": 3.402,
|
| 1178 |
+
"step": 78
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.72,
|
| 1182 |
+
"learning_rate": 1.1678583461110026e-06,
|
| 1183 |
+
"loss": 2.3984,
|
| 1184 |
+
"step": 79
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 2.72,
|
| 1188 |
+
"eval_accuracy": 0.049740014856293924,
|
| 1189 |
+
"eval_loss": 2.765625,
|
| 1190 |
+
"eval_runtime": 2.774,
|
| 1191 |
+
"eval_samples_per_second": 31.002,
|
| 1192 |
+
"eval_steps_per_second": 2.163,
|
| 1193 |
+
"step": 79
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.76,
|
| 1197 |
+
"learning_rate": 9.67382461115986e-07,
|
| 1198 |
+
"loss": 2.3936,
|
| 1199 |
+
"step": 80
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.76,
|
| 1203 |
+
"eval_accuracy": 0.049754299754299756,
|
| 1204 |
+
"eval_loss": 2.765625,
|
| 1205 |
+
"eval_runtime": 2.0608,
|
| 1206 |
+
"eval_samples_per_second": 41.732,
|
| 1207 |
+
"eval_steps_per_second": 2.912,
|
| 1208 |
+
"step": 80
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 2.79,
|
| 1212 |
+
"learning_rate": 7.852024322579649e-07,
|
| 1213 |
+
"loss": 2.4414,
|
| 1214 |
+
"step": 81
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.79,
|
| 1218 |
+
"eval_accuracy": 0.0497257299582881,
|
| 1219 |
+
"eval_loss": 2.765625,
|
| 1220 |
+
"eval_runtime": 2.3621,
|
| 1221 |
+
"eval_samples_per_second": 36.408,
|
| 1222 |
+
"eval_steps_per_second": 2.54,
|
| 1223 |
+
"step": 81
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 2.83,
|
| 1227 |
+
"learning_rate": 6.215557875383804e-07,
|
| 1228 |
+
"loss": 2.4727,
|
| 1229 |
+
"step": 82
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 2.83,
|
| 1233 |
+
"eval_accuracy": 0.04969716016227644,
|
| 1234 |
+
"eval_loss": 2.765625,
|
| 1235 |
+
"eval_runtime": 2.7992,
|
| 1236 |
+
"eval_samples_per_second": 30.723,
|
| 1237 |
+
"eval_steps_per_second": 2.143,
|
| 1238 |
+
"step": 82
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 2.86,
|
| 1242 |
+
"learning_rate": 4.766558909615504e-07,
|
| 1243 |
+
"loss": 2.3192,
|
| 1244 |
+
"step": 83
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 2.86,
|
| 1248 |
+
"eval_accuracy": 0.04971144506028227,
|
| 1249 |
+
"eval_loss": 2.765625,
|
| 1250 |
+
"eval_runtime": 2.0548,
|
| 1251 |
+
"eval_samples_per_second": 41.853,
|
| 1252 |
+
"eval_steps_per_second": 2.92,
|
| 1253 |
+
"step": 83
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 2.9,
|
| 1257 |
+
"learning_rate": 3.5069166434870014e-07,
|
| 1258 |
+
"loss": 2.4365,
|
| 1259 |
+
"step": 84
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 2.9,
|
| 1263 |
+
"eval_accuracy": 0.04966859036626479,
|
| 1264 |
+
"eval_loss": 2.765625,
|
| 1265 |
+
"eval_runtime": 1.7544,
|
| 1266 |
+
"eval_samples_per_second": 49.02,
|
| 1267 |
+
"eval_steps_per_second": 3.42,
|
| 1268 |
+
"step": 84
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 2.93,
|
| 1272 |
+
"learning_rate": 2.438273410199598e-07,
|
| 1273 |
+
"loss": 2.5042,
|
| 1274 |
+
"step": 85
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 2.93,
|
| 1278 |
+
"eval_accuracy": 0.04969716016227644,
|
| 1279 |
+
"eval_loss": 2.765625,
|
| 1280 |
+
"eval_runtime": 1.7715,
|
| 1281 |
+
"eval_samples_per_second": 48.545,
|
| 1282 |
+
"eval_steps_per_second": 3.387,
|
| 1283 |
+
"step": 85
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 2.97,
|
| 1287 |
+
"learning_rate": 1.5620225166544155e-07,
|
| 1288 |
+
"loss": 2.4746,
|
| 1289 |
+
"step": 86
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 2.97,
|
| 1293 |
+
"eval_accuracy": 0.04966859036626479,
|
| 1294 |
+
"eval_loss": 2.765625,
|
| 1295 |
+
"eval_runtime": 1.772,
|
| 1296 |
+
"eval_samples_per_second": 48.534,
|
| 1297 |
+
"eval_steps_per_second": 3.386,
|
| 1298 |
+
"step": 86
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 3.0,
|
| 1302 |
+
"learning_rate": 8.793064268460605e-08,
|
| 1303 |
+
"loss": 2.5383,
|
| 1304 |
+
"step": 87
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 3.0,
|
| 1308 |
+
"eval_accuracy": 0.049654305468258955,
|
| 1309 |
+
"eval_loss": 2.765625,
|
| 1310 |
+
"eval_runtime": 1.7578,
|
| 1311 |
+
"eval_samples_per_second": 48.924,
|
| 1312 |
+
"eval_steps_per_second": 3.413,
|
| 1313 |
+
"step": 87
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 3.0,
|
| 1317 |
+
"step": 87,
|
| 1318 |
+
"total_flos": 902636273664.0,
|
| 1319 |
+
"train_loss": 2.6778283831716956,
|
| 1320 |
+
"train_runtime": 390.8223,
|
| 1321 |
+
"train_samples_per_second": 3.523,
|
| 1322 |
+
"train_steps_per_second": 0.223
|
| 1323 |
+
}
|
| 1324 |
+
],
|
| 1325 |
+
"max_steps": 87,
|
| 1326 |
+
"num_train_epochs": 3,
|
| 1327 |
+
"total_flos": 902636273664.0,
|
| 1328 |
+
"trial_name": null,
|
| 1329 |
+
"trial_params": null
|
| 1330 |
+
}
|