Jeremiah Zhou commited on
Commit ·
2d09fc6
1
Parent(s): 180bfeb
End of training
Browse files- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Jun15_16-32-40_pikachu/events.out.tfevents.1655305279.pikachu.277660.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +2859 -0
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9152609448429384,
|
| 4 |
+
"eval_combined_score": 0.9009873932600381,
|
| 5 |
+
"eval_f1": 0.8867138416771377,
|
| 6 |
+
"eval_loss": 0.44352227449417114,
|
| 7 |
+
"eval_runtime": 83.9681,
|
| 8 |
+
"eval_samples": 40430,
|
| 9 |
+
"eval_samples_per_second": 481.492,
|
| 10 |
+
"eval_steps_per_second": 60.19,
|
| 11 |
+
"train_loss": 0.1477880122620598,
|
| 12 |
+
"train_runtime": 22868.2253,
|
| 13 |
+
"train_samples": 363846,
|
| 14 |
+
"train_samples_per_second": 159.105,
|
| 15 |
+
"train_steps_per_second": 9.944
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9152609448429384,
|
| 4 |
+
"eval_combined_score": 0.9009873932600381,
|
| 5 |
+
"eval_f1": 0.8867138416771377,
|
| 6 |
+
"eval_loss": 0.44352227449417114,
|
| 7 |
+
"eval_runtime": 83.9681,
|
| 8 |
+
"eval_samples": 40430,
|
| 9 |
+
"eval_samples_per_second": 481.492,
|
| 10 |
+
"eval_steps_per_second": 60.19
|
| 11 |
+
}
|
runs/Jun15_16-32-40_pikachu/events.out.tfevents.1655305279.pikachu.277660.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bf022ea76197e88d5b66fb861abd10606dceb39fd3964080a0539a7231f3906
|
| 3 |
+
size 475
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.1477880122620598,
|
| 4 |
+
"train_runtime": 22868.2253,
|
| 5 |
+
"train_samples": 363846,
|
| 6 |
+
"train_samples_per_second": 159.105,
|
| 7 |
+
"train_steps_per_second": 9.944
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2859 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9152609448429384,
|
| 3 |
+
"best_model_checkpoint": "./fine-tune/roberta-base/qqp/checkpoint-159187",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 227410,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 7.328691828508612e-07,
|
| 13 |
+
"loss": 0.6927,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 1.4657383657017225e-06,
|
| 19 |
+
"loss": 0.5606,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 2.1986075485525834e-06,
|
| 25 |
+
"loss": 0.4399,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.09,
|
| 30 |
+
"learning_rate": 2.931476731403445e-06,
|
| 31 |
+
"loss": 0.4018,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.11,
|
| 36 |
+
"learning_rate": 3.6643459142543057e-06,
|
| 37 |
+
"loss": 0.3965,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.13,
|
| 42 |
+
"learning_rate": 4.397215097105167e-06,
|
| 43 |
+
"loss": 0.3687,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.15,
|
| 48 |
+
"learning_rate": 5.130084279956028e-06,
|
| 49 |
+
"loss": 0.3724,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.18,
|
| 54 |
+
"learning_rate": 5.86295346280689e-06,
|
| 55 |
+
"loss": 0.3498,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.2,
|
| 60 |
+
"learning_rate": 6.59582264565775e-06,
|
| 61 |
+
"loss": 0.366,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.22,
|
| 66 |
+
"learning_rate": 7.328691828508611e-06,
|
| 67 |
+
"loss": 0.3437,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.24,
|
| 72 |
+
"learning_rate": 8.061561011359473e-06,
|
| 73 |
+
"loss": 0.3419,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.26,
|
| 78 |
+
"learning_rate": 8.794430194210334e-06,
|
| 79 |
+
"loss": 0.3382,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.29,
|
| 84 |
+
"learning_rate": 9.527299377061196e-06,
|
| 85 |
+
"loss": 0.3371,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.31,
|
| 90 |
+
"learning_rate": 1.0260168559912056e-05,
|
| 91 |
+
"loss": 0.341,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.33,
|
| 96 |
+
"learning_rate": 1.0993037742762918e-05,
|
| 97 |
+
"loss": 0.3278,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.35,
|
| 102 |
+
"learning_rate": 1.172590692561378e-05,
|
| 103 |
+
"loss": 0.3338,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.37,
|
| 108 |
+
"learning_rate": 1.245877610846464e-05,
|
| 109 |
+
"loss": 0.3308,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.4,
|
| 114 |
+
"learning_rate": 1.31916452913155e-05,
|
| 115 |
+
"loss": 0.3375,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.42,
|
| 120 |
+
"learning_rate": 1.3924514474166362e-05,
|
| 121 |
+
"loss": 0.3292,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.44,
|
| 126 |
+
"learning_rate": 1.4657383657017223e-05,
|
| 127 |
+
"loss": 0.3196,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.46,
|
| 132 |
+
"learning_rate": 1.5390252839868085e-05,
|
| 133 |
+
"loss": 0.3253,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.48,
|
| 138 |
+
"learning_rate": 1.6123122022718947e-05,
|
| 139 |
+
"loss": 0.3102,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.51,
|
| 144 |
+
"learning_rate": 1.6855991205569805e-05,
|
| 145 |
+
"loss": 0.3211,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.53,
|
| 150 |
+
"learning_rate": 1.7588860388420667e-05,
|
| 151 |
+
"loss": 0.3095,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.55,
|
| 156 |
+
"learning_rate": 1.832172957127153e-05,
|
| 157 |
+
"loss": 0.2994,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.57,
|
| 162 |
+
"learning_rate": 1.905459875412239e-05,
|
| 163 |
+
"loss": 0.3151,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.59,
|
| 168 |
+
"learning_rate": 1.9787467936973253e-05,
|
| 169 |
+
"loss": 0.3009,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.62,
|
| 174 |
+
"learning_rate": 1.9966785956541065e-05,
|
| 175 |
+
"loss": 0.3044,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.64,
|
| 180 |
+
"learning_rate": 1.992000561364115e-05,
|
| 181 |
+
"loss": 0.3051,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.66,
|
| 186 |
+
"learning_rate": 1.9873225270741237e-05,
|
| 187 |
+
"loss": 0.3045,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.68,
|
| 192 |
+
"learning_rate": 1.982644492784132e-05,
|
| 193 |
+
"loss": 0.315,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.7,
|
| 198 |
+
"learning_rate": 1.977966458494141e-05,
|
| 199 |
+
"loss": 0.3165,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.73,
|
| 204 |
+
"learning_rate": 1.9732884242041496e-05,
|
| 205 |
+
"loss": 0.2932,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.75,
|
| 210 |
+
"learning_rate": 1.9686103899141583e-05,
|
| 211 |
+
"loss": 0.3014,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.77,
|
| 216 |
+
"learning_rate": 1.963932355624167e-05,
|
| 217 |
+
"loss": 0.3052,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.79,
|
| 222 |
+
"learning_rate": 1.9592543213341755e-05,
|
| 223 |
+
"loss": 0.293,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.81,
|
| 228 |
+
"learning_rate": 1.9545762870441842e-05,
|
| 229 |
+
"loss": 0.29,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.84,
|
| 234 |
+
"learning_rate": 1.9498982527541926e-05,
|
| 235 |
+
"loss": 0.2814,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.86,
|
| 240 |
+
"learning_rate": 1.9452202184642014e-05,
|
| 241 |
+
"loss": 0.2884,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.88,
|
| 246 |
+
"learning_rate": 1.94054218417421e-05,
|
| 247 |
+
"loss": 0.2901,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.9,
|
| 252 |
+
"learning_rate": 1.935864149884219e-05,
|
| 253 |
+
"loss": 0.2833,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.92,
|
| 258 |
+
"learning_rate": 1.9311861155942276e-05,
|
| 259 |
+
"loss": 0.2877,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.95,
|
| 264 |
+
"learning_rate": 1.926508081304236e-05,
|
| 265 |
+
"loss": 0.2935,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.97,
|
| 270 |
+
"learning_rate": 1.9218300470142448e-05,
|
| 271 |
+
"loss": 0.2783,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.99,
|
| 276 |
+
"learning_rate": 1.9171520127242532e-05,
|
| 277 |
+
"loss": 0.2751,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.0,
|
| 282 |
+
"eval_accuracy": 0.8904773682908731,
|
| 283 |
+
"eval_combined_score": 0.8708585188561804,
|
| 284 |
+
"eval_f1": 0.8512396694214877,
|
| 285 |
+
"eval_loss": 0.3056511878967285,
|
| 286 |
+
"eval_runtime": 72.5914,
|
| 287 |
+
"eval_samples_per_second": 556.953,
|
| 288 |
+
"eval_steps_per_second": 69.623,
|
| 289 |
+
"step": 22741
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.01,
|
| 293 |
+
"learning_rate": 1.912473978434262e-05,
|
| 294 |
+
"loss": 0.2699,
|
| 295 |
+
"step": 23000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.03,
|
| 299 |
+
"learning_rate": 1.9077959441442707e-05,
|
| 300 |
+
"loss": 0.2617,
|
| 301 |
+
"step": 23500
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.06,
|
| 305 |
+
"learning_rate": 1.9031179098542794e-05,
|
| 306 |
+
"loss": 0.246,
|
| 307 |
+
"step": 24000
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.08,
|
| 311 |
+
"learning_rate": 1.898439875564288e-05,
|
| 312 |
+
"loss": 0.2603,
|
| 313 |
+
"step": 24500
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.1,
|
| 317 |
+
"learning_rate": 1.8937618412742966e-05,
|
| 318 |
+
"loss": 0.2488,
|
| 319 |
+
"step": 25000
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 1.12,
|
| 323 |
+
"learning_rate": 1.8890838069843053e-05,
|
| 324 |
+
"loss": 0.2394,
|
| 325 |
+
"step": 25500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.14,
|
| 329 |
+
"learning_rate": 1.884405772694314e-05,
|
| 330 |
+
"loss": 0.2558,
|
| 331 |
+
"step": 26000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.17,
|
| 335 |
+
"learning_rate": 1.8797277384043228e-05,
|
| 336 |
+
"loss": 0.2536,
|
| 337 |
+
"step": 26500
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.19,
|
| 341 |
+
"learning_rate": 1.8750497041143315e-05,
|
| 342 |
+
"loss": 0.2459,
|
| 343 |
+
"step": 27000
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 1.21,
|
| 347 |
+
"learning_rate": 1.87037166982434e-05,
|
| 348 |
+
"loss": 0.2451,
|
| 349 |
+
"step": 27500
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.23,
|
| 353 |
+
"learning_rate": 1.8656936355343487e-05,
|
| 354 |
+
"loss": 0.2547,
|
| 355 |
+
"step": 28000
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.25,
|
| 359 |
+
"learning_rate": 1.861015601244357e-05,
|
| 360 |
+
"loss": 0.2571,
|
| 361 |
+
"step": 28500
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.28,
|
| 365 |
+
"learning_rate": 1.856337566954366e-05,
|
| 366 |
+
"loss": 0.2622,
|
| 367 |
+
"step": 29000
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.3,
|
| 371 |
+
"learning_rate": 1.8516595326643746e-05,
|
| 372 |
+
"loss": 0.2642,
|
| 373 |
+
"step": 29500
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.32,
|
| 377 |
+
"learning_rate": 1.8469814983743833e-05,
|
| 378 |
+
"loss": 0.2524,
|
| 379 |
+
"step": 30000
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.34,
|
| 383 |
+
"learning_rate": 1.842303464084392e-05,
|
| 384 |
+
"loss": 0.2604,
|
| 385 |
+
"step": 30500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 1.36,
|
| 389 |
+
"learning_rate": 1.8376254297944005e-05,
|
| 390 |
+
"loss": 0.2476,
|
| 391 |
+
"step": 31000
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.39,
|
| 395 |
+
"learning_rate": 1.8329473955044092e-05,
|
| 396 |
+
"loss": 0.2494,
|
| 397 |
+
"step": 31500
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 1.41,
|
| 401 |
+
"learning_rate": 1.8282693612144176e-05,
|
| 402 |
+
"loss": 0.2513,
|
| 403 |
+
"step": 32000
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 1.43,
|
| 407 |
+
"learning_rate": 1.8235913269244264e-05,
|
| 408 |
+
"loss": 0.254,
|
| 409 |
+
"step": 32500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.45,
|
| 413 |
+
"learning_rate": 1.818913292634435e-05,
|
| 414 |
+
"loss": 0.2505,
|
| 415 |
+
"step": 33000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.47,
|
| 419 |
+
"learning_rate": 1.814235258344444e-05,
|
| 420 |
+
"loss": 0.249,
|
| 421 |
+
"step": 33500
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.5,
|
| 425 |
+
"learning_rate": 1.8095572240544526e-05,
|
| 426 |
+
"loss": 0.2469,
|
| 427 |
+
"step": 34000
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.52,
|
| 431 |
+
"learning_rate": 1.804879189764461e-05,
|
| 432 |
+
"loss": 0.2538,
|
| 433 |
+
"step": 34500
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.54,
|
| 437 |
+
"learning_rate": 1.8002011554744698e-05,
|
| 438 |
+
"loss": 0.24,
|
| 439 |
+
"step": 35000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.56,
|
| 443 |
+
"learning_rate": 1.7955231211844785e-05,
|
| 444 |
+
"loss": 0.2488,
|
| 445 |
+
"step": 35500
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.58,
|
| 449 |
+
"learning_rate": 1.7908450868944873e-05,
|
| 450 |
+
"loss": 0.2552,
|
| 451 |
+
"step": 36000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.61,
|
| 455 |
+
"learning_rate": 1.7861670526044957e-05,
|
| 456 |
+
"loss": 0.2485,
|
| 457 |
+
"step": 36500
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.63,
|
| 461 |
+
"learning_rate": 1.7814890183145044e-05,
|
| 462 |
+
"loss": 0.2518,
|
| 463 |
+
"step": 37000
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 1.65,
|
| 467 |
+
"learning_rate": 1.776810984024513e-05,
|
| 468 |
+
"loss": 0.2316,
|
| 469 |
+
"step": 37500
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.67,
|
| 473 |
+
"learning_rate": 1.7721329497345216e-05,
|
| 474 |
+
"loss": 0.2382,
|
| 475 |
+
"step": 38000
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 1.69,
|
| 479 |
+
"learning_rate": 1.7674549154445303e-05,
|
| 480 |
+
"loss": 0.2435,
|
| 481 |
+
"step": 38500
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.71,
|
| 485 |
+
"learning_rate": 1.762776881154539e-05,
|
| 486 |
+
"loss": 0.2359,
|
| 487 |
+
"step": 39000
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 1.74,
|
| 491 |
+
"learning_rate": 1.7580988468645478e-05,
|
| 492 |
+
"loss": 0.2439,
|
| 493 |
+
"step": 39500
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.76,
|
| 497 |
+
"learning_rate": 1.7534208125745562e-05,
|
| 498 |
+
"loss": 0.2386,
|
| 499 |
+
"step": 40000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.78,
|
| 503 |
+
"learning_rate": 1.748742778284565e-05,
|
| 504 |
+
"loss": 0.2404,
|
| 505 |
+
"step": 40500
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.8,
|
| 509 |
+
"learning_rate": 1.7440647439945737e-05,
|
| 510 |
+
"loss": 0.2534,
|
| 511 |
+
"step": 41000
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.82,
|
| 515 |
+
"learning_rate": 1.739386709704582e-05,
|
| 516 |
+
"loss": 0.2416,
|
| 517 |
+
"step": 41500
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 1.85,
|
| 521 |
+
"learning_rate": 1.734708675414591e-05,
|
| 522 |
+
"loss": 0.2517,
|
| 523 |
+
"step": 42000
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 1.87,
|
| 527 |
+
"learning_rate": 1.7300306411245996e-05,
|
| 528 |
+
"loss": 0.2508,
|
| 529 |
+
"step": 42500
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.89,
|
| 533 |
+
"learning_rate": 1.7253526068346083e-05,
|
| 534 |
+
"loss": 0.2515,
|
| 535 |
+
"step": 43000
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.91,
|
| 539 |
+
"learning_rate": 1.7206745725446168e-05,
|
| 540 |
+
"loss": 0.2507,
|
| 541 |
+
"step": 43500
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.93,
|
| 545 |
+
"learning_rate": 1.7159965382546255e-05,
|
| 546 |
+
"loss": 0.2528,
|
| 547 |
+
"step": 44000
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 1.96,
|
| 551 |
+
"learning_rate": 1.7113185039646342e-05,
|
| 552 |
+
"loss": 0.2471,
|
| 553 |
+
"step": 44500
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 1.98,
|
| 557 |
+
"learning_rate": 1.7066404696746426e-05,
|
| 558 |
+
"loss": 0.2443,
|
| 559 |
+
"step": 45000
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 2.0,
|
| 563 |
+
"eval_accuracy": 0.9004699480583725,
|
| 564 |
+
"eval_combined_score": 0.8857477945420068,
|
| 565 |
+
"eval_f1": 0.8710256410256411,
|
| 566 |
+
"eval_loss": 0.2529826760292053,
|
| 567 |
+
"eval_runtime": 71.9777,
|
| 568 |
+
"eval_samples_per_second": 561.702,
|
| 569 |
+
"eval_steps_per_second": 70.216,
|
| 570 |
+
"step": 45482
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.0,
|
| 574 |
+
"learning_rate": 1.7019624353846514e-05,
|
| 575 |
+
"loss": 0.2582,
|
| 576 |
+
"step": 45500
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.02,
|
| 580 |
+
"learning_rate": 1.69728440109466e-05,
|
| 581 |
+
"loss": 0.2023,
|
| 582 |
+
"step": 46000
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 2.04,
|
| 586 |
+
"learning_rate": 1.692606366804669e-05,
|
| 587 |
+
"loss": 0.2099,
|
| 588 |
+
"step": 46500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 2.07,
|
| 592 |
+
"learning_rate": 1.6879283325146776e-05,
|
| 593 |
+
"loss": 0.2071,
|
| 594 |
+
"step": 47000
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 2.09,
|
| 598 |
+
"learning_rate": 1.683250298224686e-05,
|
| 599 |
+
"loss": 0.213,
|
| 600 |
+
"step": 47500
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 2.11,
|
| 604 |
+
"learning_rate": 1.6785722639346948e-05,
|
| 605 |
+
"loss": 0.2089,
|
| 606 |
+
"step": 48000
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.13,
|
| 610 |
+
"learning_rate": 1.6738942296447035e-05,
|
| 611 |
+
"loss": 0.2201,
|
| 612 |
+
"step": 48500
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 2.15,
|
| 616 |
+
"learning_rate": 1.6692161953547123e-05,
|
| 617 |
+
"loss": 0.1979,
|
| 618 |
+
"step": 49000
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.18,
|
| 622 |
+
"learning_rate": 1.6645381610647207e-05,
|
| 623 |
+
"loss": 0.2059,
|
| 624 |
+
"step": 49500
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.2,
|
| 628 |
+
"learning_rate": 1.6598601267747294e-05,
|
| 629 |
+
"loss": 0.2146,
|
| 630 |
+
"step": 50000
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 2.22,
|
| 634 |
+
"learning_rate": 1.655182092484738e-05,
|
| 635 |
+
"loss": 0.2008,
|
| 636 |
+
"step": 50500
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 2.24,
|
| 640 |
+
"learning_rate": 1.6505040581947466e-05,
|
| 641 |
+
"loss": 0.205,
|
| 642 |
+
"step": 51000
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 2.26,
|
| 646 |
+
"learning_rate": 1.6458260239047553e-05,
|
| 647 |
+
"loss": 0.2135,
|
| 648 |
+
"step": 51500
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.29,
|
| 652 |
+
"learning_rate": 1.641147989614764e-05,
|
| 653 |
+
"loss": 0.2099,
|
| 654 |
+
"step": 52000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.31,
|
| 658 |
+
"learning_rate": 1.6364699553247728e-05,
|
| 659 |
+
"loss": 0.1999,
|
| 660 |
+
"step": 52500
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 2.33,
|
| 664 |
+
"learning_rate": 1.6317919210347812e-05,
|
| 665 |
+
"loss": 0.2104,
|
| 666 |
+
"step": 53000
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 2.35,
|
| 670 |
+
"learning_rate": 1.62711388674479e-05,
|
| 671 |
+
"loss": 0.2135,
|
| 672 |
+
"step": 53500
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 2.37,
|
| 676 |
+
"learning_rate": 1.6224358524547987e-05,
|
| 677 |
+
"loss": 0.2066,
|
| 678 |
+
"step": 54000
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 2.4,
|
| 682 |
+
"learning_rate": 1.617757818164807e-05,
|
| 683 |
+
"loss": 0.2128,
|
| 684 |
+
"step": 54500
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 2.42,
|
| 688 |
+
"learning_rate": 1.613079783874816e-05,
|
| 689 |
+
"loss": 0.2079,
|
| 690 |
+
"step": 55000
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.44,
|
| 694 |
+
"learning_rate": 1.6084017495848246e-05,
|
| 695 |
+
"loss": 0.2142,
|
| 696 |
+
"step": 55500
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 2.46,
|
| 700 |
+
"learning_rate": 1.6037237152948333e-05,
|
| 701 |
+
"loss": 0.2079,
|
| 702 |
+
"step": 56000
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 2.48,
|
| 706 |
+
"learning_rate": 1.5990456810048418e-05,
|
| 707 |
+
"loss": 0.2065,
|
| 708 |
+
"step": 56500
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 2.51,
|
| 712 |
+
"learning_rate": 1.5943676467148505e-05,
|
| 713 |
+
"loss": 0.2166,
|
| 714 |
+
"step": 57000
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.53,
|
| 718 |
+
"learning_rate": 1.5896896124248592e-05,
|
| 719 |
+
"loss": 0.2135,
|
| 720 |
+
"step": 57500
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 2.55,
|
| 724 |
+
"learning_rate": 1.585011578134868e-05,
|
| 725 |
+
"loss": 0.2072,
|
| 726 |
+
"step": 58000
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 2.57,
|
| 730 |
+
"learning_rate": 1.5803335438448767e-05,
|
| 731 |
+
"loss": 0.2132,
|
| 732 |
+
"step": 58500
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.59,
|
| 736 |
+
"learning_rate": 1.575655509554885e-05,
|
| 737 |
+
"loss": 0.2114,
|
| 738 |
+
"step": 59000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.62,
|
| 742 |
+
"learning_rate": 1.570977475264894e-05,
|
| 743 |
+
"loss": 0.2172,
|
| 744 |
+
"step": 59500
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.64,
|
| 748 |
+
"learning_rate": 1.5662994409749023e-05,
|
| 749 |
+
"loss": 0.198,
|
| 750 |
+
"step": 60000
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 2.66,
|
| 754 |
+
"learning_rate": 1.561621406684911e-05,
|
| 755 |
+
"loss": 0.2013,
|
| 756 |
+
"step": 60500
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 2.68,
|
| 760 |
+
"learning_rate": 1.5569433723949198e-05,
|
| 761 |
+
"loss": 0.2076,
|
| 762 |
+
"step": 61000
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 2.7,
|
| 766 |
+
"learning_rate": 1.5522653381049285e-05,
|
| 767 |
+
"loss": 0.2113,
|
| 768 |
+
"step": 61500
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 2.73,
|
| 772 |
+
"learning_rate": 1.5475873038149373e-05,
|
| 773 |
+
"loss": 0.2132,
|
| 774 |
+
"step": 62000
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.75,
|
| 778 |
+
"learning_rate": 1.5429092695249457e-05,
|
| 779 |
+
"loss": 0.2152,
|
| 780 |
+
"step": 62500
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.77,
|
| 784 |
+
"learning_rate": 1.5382312352349544e-05,
|
| 785 |
+
"loss": 0.2082,
|
| 786 |
+
"step": 63000
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.79,
|
| 790 |
+
"learning_rate": 1.533553200944963e-05,
|
| 791 |
+
"loss": 0.216,
|
| 792 |
+
"step": 63500
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 2.81,
|
| 796 |
+
"learning_rate": 1.5288751666549716e-05,
|
| 797 |
+
"loss": 0.2154,
|
| 798 |
+
"step": 64000
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 2.84,
|
| 802 |
+
"learning_rate": 1.5241971323649805e-05,
|
| 803 |
+
"loss": 0.2087,
|
| 804 |
+
"step": 64500
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 2.86,
|
| 808 |
+
"learning_rate": 1.519519098074989e-05,
|
| 809 |
+
"loss": 0.1985,
|
| 810 |
+
"step": 65000
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 2.88,
|
| 814 |
+
"learning_rate": 1.5148410637849978e-05,
|
| 815 |
+
"loss": 0.2117,
|
| 816 |
+
"step": 65500
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.9,
|
| 820 |
+
"learning_rate": 1.5101630294950062e-05,
|
| 821 |
+
"loss": 0.214,
|
| 822 |
+
"step": 66000
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 2.92,
|
| 826 |
+
"learning_rate": 1.505484995205015e-05,
|
| 827 |
+
"loss": 0.1941,
|
| 828 |
+
"step": 66500
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.95,
|
| 832 |
+
"learning_rate": 1.5008069609150235e-05,
|
| 833 |
+
"loss": 0.208,
|
| 834 |
+
"step": 67000
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 2.97,
|
| 838 |
+
"learning_rate": 1.4961289266250323e-05,
|
| 839 |
+
"loss": 0.2205,
|
| 840 |
+
"step": 67500
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 2.99,
|
| 844 |
+
"learning_rate": 1.491450892335041e-05,
|
| 845 |
+
"loss": 0.2157,
|
| 846 |
+
"step": 68000
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 3.0,
|
| 850 |
+
"eval_accuracy": 0.9069502844422459,
|
| 851 |
+
"eval_combined_score": 0.8919079780420185,
|
| 852 |
+
"eval_f1": 0.876865671641791,
|
| 853 |
+
"eval_loss": 0.2643309533596039,
|
| 854 |
+
"eval_runtime": 71.5158,
|
| 855 |
+
"eval_samples_per_second": 565.33,
|
| 856 |
+
"eval_steps_per_second": 70.67,
|
| 857 |
+
"step": 68223
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.01,
|
| 861 |
+
"learning_rate": 1.4867728580450496e-05,
|
| 862 |
+
"loss": 0.1811,
|
| 863 |
+
"step": 68500
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 3.03,
|
| 867 |
+
"learning_rate": 1.4820948237550584e-05,
|
| 868 |
+
"loss": 0.1629,
|
| 869 |
+
"step": 69000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 3.06,
|
| 873 |
+
"learning_rate": 1.4774167894650668e-05,
|
| 874 |
+
"loss": 0.1615,
|
| 875 |
+
"step": 69500
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 3.08,
|
| 879 |
+
"learning_rate": 1.4727387551750755e-05,
|
| 880 |
+
"loss": 0.1736,
|
| 881 |
+
"step": 70000
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 3.1,
|
| 885 |
+
"learning_rate": 1.468060720885084e-05,
|
| 886 |
+
"loss": 0.1738,
|
| 887 |
+
"step": 70500
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 3.12,
|
| 891 |
+
"learning_rate": 1.4633826865950928e-05,
|
| 892 |
+
"loss": 0.1739,
|
| 893 |
+
"step": 71000
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 3.14,
|
| 897 |
+
"learning_rate": 1.4587046523051016e-05,
|
| 898 |
+
"loss": 0.1712,
|
| 899 |
+
"step": 71500
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 3.17,
|
| 903 |
+
"learning_rate": 1.4540266180151101e-05,
|
| 904 |
+
"loss": 0.1846,
|
| 905 |
+
"step": 72000
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.19,
|
| 909 |
+
"learning_rate": 1.4493485837251189e-05,
|
| 910 |
+
"loss": 0.1683,
|
| 911 |
+
"step": 72500
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 3.21,
|
| 915 |
+
"learning_rate": 1.4446705494351275e-05,
|
| 916 |
+
"loss": 0.168,
|
| 917 |
+
"step": 73000
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 3.23,
|
| 921 |
+
"learning_rate": 1.4399925151451362e-05,
|
| 922 |
+
"loss": 0.1761,
|
| 923 |
+
"step": 73500
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 3.25,
|
| 927 |
+
"learning_rate": 1.4353144808551446e-05,
|
| 928 |
+
"loss": 0.1691,
|
| 929 |
+
"step": 74000
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 3.28,
|
| 933 |
+
"learning_rate": 1.4306364465651534e-05,
|
| 934 |
+
"loss": 0.1766,
|
| 935 |
+
"step": 74500
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 3.3,
|
| 939 |
+
"learning_rate": 1.4259584122751621e-05,
|
| 940 |
+
"loss": 0.1738,
|
| 941 |
+
"step": 75000
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 3.32,
|
| 945 |
+
"learning_rate": 1.4212803779851707e-05,
|
| 946 |
+
"loss": 0.1738,
|
| 947 |
+
"step": 75500
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 3.34,
|
| 951 |
+
"learning_rate": 1.4166023436951794e-05,
|
| 952 |
+
"loss": 0.1839,
|
| 953 |
+
"step": 76000
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 3.36,
|
| 957 |
+
"learning_rate": 1.411924309405188e-05,
|
| 958 |
+
"loss": 0.1791,
|
| 959 |
+
"step": 76500
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 3.39,
|
| 963 |
+
"learning_rate": 1.4072462751151967e-05,
|
| 964 |
+
"loss": 0.1773,
|
| 965 |
+
"step": 77000
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 3.41,
|
| 969 |
+
"learning_rate": 1.4025682408252053e-05,
|
| 970 |
+
"loss": 0.1736,
|
| 971 |
+
"step": 77500
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 3.43,
|
| 975 |
+
"learning_rate": 1.397890206535214e-05,
|
| 976 |
+
"loss": 0.1695,
|
| 977 |
+
"step": 78000
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 3.45,
|
| 981 |
+
"learning_rate": 1.3932121722452228e-05,
|
| 982 |
+
"loss": 0.1785,
|
| 983 |
+
"step": 78500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 3.47,
|
| 987 |
+
"learning_rate": 1.3885341379552312e-05,
|
| 988 |
+
"loss": 0.1712,
|
| 989 |
+
"step": 79000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 3.5,
|
| 993 |
+
"learning_rate": 1.38385610366524e-05,
|
| 994 |
+
"loss": 0.1847,
|
| 995 |
+
"step": 79500
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 3.52,
|
| 999 |
+
"learning_rate": 1.3791780693752485e-05,
|
| 1000 |
+
"loss": 0.181,
|
| 1001 |
+
"step": 80000
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 3.54,
|
| 1005 |
+
"learning_rate": 1.3745000350852573e-05,
|
| 1006 |
+
"loss": 0.179,
|
| 1007 |
+
"step": 80500
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 3.56,
|
| 1011 |
+
"learning_rate": 1.3698220007952659e-05,
|
| 1012 |
+
"loss": 0.1827,
|
| 1013 |
+
"step": 81000
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 3.58,
|
| 1017 |
+
"learning_rate": 1.3651439665052746e-05,
|
| 1018 |
+
"loss": 0.1797,
|
| 1019 |
+
"step": 81500
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 3.61,
|
| 1023 |
+
"learning_rate": 1.3604659322152834e-05,
|
| 1024 |
+
"loss": 0.1757,
|
| 1025 |
+
"step": 82000
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 3.63,
|
| 1029 |
+
"learning_rate": 1.355787897925292e-05,
|
| 1030 |
+
"loss": 0.1703,
|
| 1031 |
+
"step": 82500
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 3.65,
|
| 1035 |
+
"learning_rate": 1.3511098636353007e-05,
|
| 1036 |
+
"loss": 0.1751,
|
| 1037 |
+
"step": 83000
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 3.67,
|
| 1041 |
+
"learning_rate": 1.346431829345309e-05,
|
| 1042 |
+
"loss": 0.1886,
|
| 1043 |
+
"step": 83500
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 3.69,
|
| 1047 |
+
"learning_rate": 1.3417537950553178e-05,
|
| 1048 |
+
"loss": 0.1864,
|
| 1049 |
+
"step": 84000
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 3.72,
|
| 1053 |
+
"learning_rate": 1.3370757607653264e-05,
|
| 1054 |
+
"loss": 0.1758,
|
| 1055 |
+
"step": 84500
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 3.74,
|
| 1059 |
+
"learning_rate": 1.3323977264753351e-05,
|
| 1060 |
+
"loss": 0.1819,
|
| 1061 |
+
"step": 85000
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 3.76,
|
| 1065 |
+
"learning_rate": 1.3277196921853439e-05,
|
| 1066 |
+
"loss": 0.171,
|
| 1067 |
+
"step": 85500
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 3.78,
|
| 1071 |
+
"learning_rate": 1.3230416578953525e-05,
|
| 1072 |
+
"loss": 0.1789,
|
| 1073 |
+
"step": 86000
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 3.8,
|
| 1077 |
+
"learning_rate": 1.3183636236053612e-05,
|
| 1078 |
+
"loss": 0.1836,
|
| 1079 |
+
"step": 86500
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 3.83,
|
| 1083 |
+
"learning_rate": 1.3136855893153698e-05,
|
| 1084 |
+
"loss": 0.1841,
|
| 1085 |
+
"step": 87000
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 3.85,
|
| 1089 |
+
"learning_rate": 1.3090075550253785e-05,
|
| 1090 |
+
"loss": 0.1843,
|
| 1091 |
+
"step": 87500
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 3.87,
|
| 1095 |
+
"learning_rate": 1.304329520735387e-05,
|
| 1096 |
+
"loss": 0.1845,
|
| 1097 |
+
"step": 88000
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 3.89,
|
| 1101 |
+
"learning_rate": 1.2996514864453957e-05,
|
| 1102 |
+
"loss": 0.1849,
|
| 1103 |
+
"step": 88500
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 3.91,
|
| 1107 |
+
"learning_rate": 1.2949734521554044e-05,
|
| 1108 |
+
"loss": 0.1822,
|
| 1109 |
+
"step": 89000
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 3.94,
|
| 1113 |
+
"learning_rate": 1.290295417865413e-05,
|
| 1114 |
+
"loss": 0.1859,
|
| 1115 |
+
"step": 89500
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 3.96,
|
| 1119 |
+
"learning_rate": 1.2856173835754218e-05,
|
| 1120 |
+
"loss": 0.1928,
|
| 1121 |
+
"step": 90000
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 3.98,
|
| 1125 |
+
"learning_rate": 1.2809393492854303e-05,
|
| 1126 |
+
"loss": 0.1838,
|
| 1127 |
+
"step": 90500
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 4.0,
|
| 1131 |
+
"eval_accuracy": 0.9109077417759089,
|
| 1132 |
+
"eval_combined_score": 0.8961948553575517,
|
| 1133 |
+
"eval_f1": 0.8814819689391945,
|
| 1134 |
+
"eval_loss": 0.28062957525253296,
|
| 1135 |
+
"eval_runtime": 73.9944,
|
| 1136 |
+
"eval_samples_per_second": 546.393,
|
| 1137 |
+
"eval_steps_per_second": 68.302,
|
| 1138 |
+
"step": 90964
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 4.0,
|
| 1142 |
+
"learning_rate": 1.276261314995439e-05,
|
| 1143 |
+
"loss": 0.1721,
|
| 1144 |
+
"step": 91000
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 4.02,
|
| 1148 |
+
"learning_rate": 1.2715832807054476e-05,
|
| 1149 |
+
"loss": 0.1357,
|
| 1150 |
+
"step": 91500
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 4.05,
|
| 1154 |
+
"learning_rate": 1.2669052464154564e-05,
|
| 1155 |
+
"loss": 0.1472,
|
| 1156 |
+
"step": 92000
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 4.07,
|
| 1160 |
+
"learning_rate": 1.2622272121254651e-05,
|
| 1161 |
+
"loss": 0.1466,
|
| 1162 |
+
"step": 92500
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 4.09,
|
| 1166 |
+
"learning_rate": 1.2575491778354735e-05,
|
| 1167 |
+
"loss": 0.1449,
|
| 1168 |
+
"step": 93000
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 4.11,
|
| 1172 |
+
"learning_rate": 1.2528711435454823e-05,
|
| 1173 |
+
"loss": 0.1462,
|
| 1174 |
+
"step": 93500
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 4.13,
|
| 1178 |
+
"learning_rate": 1.2481931092554909e-05,
|
| 1179 |
+
"loss": 0.1412,
|
| 1180 |
+
"step": 94000
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 4.16,
|
| 1184 |
+
"learning_rate": 1.2435150749654996e-05,
|
| 1185 |
+
"loss": 0.1477,
|
| 1186 |
+
"step": 94500
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 4.18,
|
| 1190 |
+
"learning_rate": 1.2388370406755084e-05,
|
| 1191 |
+
"loss": 0.1565,
|
| 1192 |
+
"step": 95000
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 4.2,
|
| 1196 |
+
"learning_rate": 1.234159006385517e-05,
|
| 1197 |
+
"loss": 0.1465,
|
| 1198 |
+
"step": 95500
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 4.22,
|
| 1202 |
+
"learning_rate": 1.2294809720955257e-05,
|
| 1203 |
+
"loss": 0.1398,
|
| 1204 |
+
"step": 96000
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 4.24,
|
| 1208 |
+
"learning_rate": 1.224802937805534e-05,
|
| 1209 |
+
"loss": 0.1419,
|
| 1210 |
+
"step": 96500
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 4.27,
|
| 1214 |
+
"learning_rate": 1.220124903515543e-05,
|
| 1215 |
+
"loss": 0.1407,
|
| 1216 |
+
"step": 97000
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 4.29,
|
| 1220 |
+
"learning_rate": 1.2154468692255514e-05,
|
| 1221 |
+
"loss": 0.1563,
|
| 1222 |
+
"step": 97500
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 4.31,
|
| 1226 |
+
"learning_rate": 1.2107688349355601e-05,
|
| 1227 |
+
"loss": 0.1552,
|
| 1228 |
+
"step": 98000
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 4.33,
|
| 1232 |
+
"learning_rate": 1.2060908006455689e-05,
|
| 1233 |
+
"loss": 0.1483,
|
| 1234 |
+
"step": 98500
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 4.35,
|
| 1238 |
+
"learning_rate": 1.2014127663555775e-05,
|
| 1239 |
+
"loss": 0.1568,
|
| 1240 |
+
"step": 99000
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 4.38,
|
| 1244 |
+
"learning_rate": 1.1967347320655862e-05,
|
| 1245 |
+
"loss": 0.1423,
|
| 1246 |
+
"step": 99500
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 4.4,
|
| 1250 |
+
"learning_rate": 1.1920566977755948e-05,
|
| 1251 |
+
"loss": 0.1531,
|
| 1252 |
+
"step": 100000
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 4.42,
|
| 1256 |
+
"learning_rate": 1.1873786634856035e-05,
|
| 1257 |
+
"loss": 0.1465,
|
| 1258 |
+
"step": 100500
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 4.44,
|
| 1262 |
+
"learning_rate": 1.182700629195612e-05,
|
| 1263 |
+
"loss": 0.1551,
|
| 1264 |
+
"step": 101000
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 4.46,
|
| 1268 |
+
"learning_rate": 1.1780225949056207e-05,
|
| 1269 |
+
"loss": 0.1492,
|
| 1270 |
+
"step": 101500
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 4.49,
|
| 1274 |
+
"learning_rate": 1.1733445606156294e-05,
|
| 1275 |
+
"loss": 0.1456,
|
| 1276 |
+
"step": 102000
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 4.51,
|
| 1280 |
+
"learning_rate": 1.168666526325638e-05,
|
| 1281 |
+
"loss": 0.1488,
|
| 1282 |
+
"step": 102500
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 4.53,
|
| 1286 |
+
"learning_rate": 1.1639884920356468e-05,
|
| 1287 |
+
"loss": 0.141,
|
| 1288 |
+
"step": 103000
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 4.55,
|
| 1292 |
+
"learning_rate": 1.1593104577456553e-05,
|
| 1293 |
+
"loss": 0.1518,
|
| 1294 |
+
"step": 103500
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 4.57,
|
| 1298 |
+
"learning_rate": 1.154632423455664e-05,
|
| 1299 |
+
"loss": 0.1471,
|
| 1300 |
+
"step": 104000
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 4.6,
|
| 1304 |
+
"learning_rate": 1.1499543891656727e-05,
|
| 1305 |
+
"loss": 0.1646,
|
| 1306 |
+
"step": 104500
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 4.62,
|
| 1310 |
+
"learning_rate": 1.1452763548756814e-05,
|
| 1311 |
+
"loss": 0.1495,
|
| 1312 |
+
"step": 105000
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 4.64,
|
| 1316 |
+
"learning_rate": 1.1405983205856901e-05,
|
| 1317 |
+
"loss": 0.1424,
|
| 1318 |
+
"step": 105500
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 4.66,
|
| 1322 |
+
"learning_rate": 1.1359202862956985e-05,
|
| 1323 |
+
"loss": 0.1441,
|
| 1324 |
+
"step": 106000
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 4.68,
|
| 1328 |
+
"learning_rate": 1.1312422520057073e-05,
|
| 1329 |
+
"loss": 0.1548,
|
| 1330 |
+
"step": 106500
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 4.71,
|
| 1334 |
+
"learning_rate": 1.1265642177157159e-05,
|
| 1335 |
+
"loss": 0.1555,
|
| 1336 |
+
"step": 107000
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 4.73,
|
| 1340 |
+
"learning_rate": 1.1218861834257246e-05,
|
| 1341 |
+
"loss": 0.1497,
|
| 1342 |
+
"step": 107500
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 4.75,
|
| 1346 |
+
"learning_rate": 1.1172081491357332e-05,
|
| 1347 |
+
"loss": 0.1628,
|
| 1348 |
+
"step": 108000
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 4.77,
|
| 1352 |
+
"learning_rate": 1.112530114845742e-05,
|
| 1353 |
+
"loss": 0.1454,
|
| 1354 |
+
"step": 108500
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 4.79,
|
| 1358 |
+
"learning_rate": 1.1078520805557507e-05,
|
| 1359 |
+
"loss": 0.1394,
|
| 1360 |
+
"step": 109000
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 4.82,
|
| 1364 |
+
"learning_rate": 1.1031740462657593e-05,
|
| 1365 |
+
"loss": 0.1535,
|
| 1366 |
+
"step": 109500
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 4.84,
|
| 1370 |
+
"learning_rate": 1.098496011975768e-05,
|
| 1371 |
+
"loss": 0.1521,
|
| 1372 |
+
"step": 110000
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 4.86,
|
| 1376 |
+
"learning_rate": 1.0938179776857764e-05,
|
| 1377 |
+
"loss": 0.1429,
|
| 1378 |
+
"step": 110500
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 4.88,
|
| 1382 |
+
"learning_rate": 1.0891399433957852e-05,
|
| 1383 |
+
"loss": 0.1428,
|
| 1384 |
+
"step": 111000
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 4.9,
|
| 1388 |
+
"learning_rate": 1.0844619091057937e-05,
|
| 1389 |
+
"loss": 0.1519,
|
| 1390 |
+
"step": 111500
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 4.93,
|
| 1394 |
+
"learning_rate": 1.0797838748158025e-05,
|
| 1395 |
+
"loss": 0.1456,
|
| 1396 |
+
"step": 112000
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 4.95,
|
| 1400 |
+
"learning_rate": 1.0751058405258112e-05,
|
| 1401 |
+
"loss": 0.1496,
|
| 1402 |
+
"step": 112500
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 4.97,
|
| 1406 |
+
"learning_rate": 1.0704278062358198e-05,
|
| 1407 |
+
"loss": 0.1513,
|
| 1408 |
+
"step": 113000
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 4.99,
|
| 1412 |
+
"learning_rate": 1.0657497719458285e-05,
|
| 1413 |
+
"loss": 0.146,
|
| 1414 |
+
"step": 113500
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 5.0,
|
| 1418 |
+
"eval_accuracy": 0.9112540192926045,
|
| 1419 |
+
"eval_combined_score": 0.8960850249134777,
|
| 1420 |
+
"eval_f1": 0.8809160305343511,
|
| 1421 |
+
"eval_loss": 0.3276694118976593,
|
| 1422 |
+
"eval_runtime": 71.6884,
|
| 1423 |
+
"eval_samples_per_second": 563.969,
|
| 1424 |
+
"eval_steps_per_second": 70.5,
|
| 1425 |
+
"step": 113705
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 5.01,
|
| 1429 |
+
"learning_rate": 1.0610717376558371e-05,
|
| 1430 |
+
"loss": 0.128,
|
| 1431 |
+
"step": 114000
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 5.03,
|
| 1435 |
+
"learning_rate": 1.0563937033658459e-05,
|
| 1436 |
+
"loss": 0.116,
|
| 1437 |
+
"step": 114500
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 5.06,
|
| 1441 |
+
"learning_rate": 1.0517156690758543e-05,
|
| 1442 |
+
"loss": 0.1148,
|
| 1443 |
+
"step": 115000
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 5.08,
|
| 1447 |
+
"learning_rate": 1.047037634785863e-05,
|
| 1448 |
+
"loss": 0.1074,
|
| 1449 |
+
"step": 115500
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 5.1,
|
| 1453 |
+
"learning_rate": 1.0423596004958718e-05,
|
| 1454 |
+
"loss": 0.114,
|
| 1455 |
+
"step": 116000
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 5.12,
|
| 1459 |
+
"learning_rate": 1.0376815662058803e-05,
|
| 1460 |
+
"loss": 0.1092,
|
| 1461 |
+
"step": 116500
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 5.14,
|
| 1465 |
+
"learning_rate": 1.033003531915889e-05,
|
| 1466 |
+
"loss": 0.1183,
|
| 1467 |
+
"step": 117000
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 5.17,
|
| 1471 |
+
"learning_rate": 1.0283254976258977e-05,
|
| 1472 |
+
"loss": 0.1137,
|
| 1473 |
+
"step": 117500
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 5.19,
|
| 1477 |
+
"learning_rate": 1.0236474633359064e-05,
|
| 1478 |
+
"loss": 0.1144,
|
| 1479 |
+
"step": 118000
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 5.21,
|
| 1483 |
+
"learning_rate": 1.018969429045915e-05,
|
| 1484 |
+
"loss": 0.1203,
|
| 1485 |
+
"step": 118500
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 5.23,
|
| 1489 |
+
"learning_rate": 1.0142913947559237e-05,
|
| 1490 |
+
"loss": 0.1175,
|
| 1491 |
+
"step": 119000
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 5.25,
|
| 1495 |
+
"learning_rate": 1.0096133604659325e-05,
|
| 1496 |
+
"loss": 0.1159,
|
| 1497 |
+
"step": 119500
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 5.28,
|
| 1501 |
+
"learning_rate": 1.0049353261759409e-05,
|
| 1502 |
+
"loss": 0.1237,
|
| 1503 |
+
"step": 120000
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 5.3,
|
| 1507 |
+
"learning_rate": 1.0002572918859496e-05,
|
| 1508 |
+
"loss": 0.1203,
|
| 1509 |
+
"step": 120500
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 5.32,
|
| 1513 |
+
"learning_rate": 9.955792575959584e-06,
|
| 1514 |
+
"loss": 0.115,
|
| 1515 |
+
"step": 121000
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 5.34,
|
| 1519 |
+
"learning_rate": 9.90901223305967e-06,
|
| 1520 |
+
"loss": 0.1209,
|
| 1521 |
+
"step": 121500
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 5.36,
|
| 1525 |
+
"learning_rate": 9.862231890159755e-06,
|
| 1526 |
+
"loss": 0.1205,
|
| 1527 |
+
"step": 122000
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 5.39,
|
| 1531 |
+
"learning_rate": 9.815451547259843e-06,
|
| 1532 |
+
"loss": 0.1253,
|
| 1533 |
+
"step": 122500
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 5.41,
|
| 1537 |
+
"learning_rate": 9.768671204359928e-06,
|
| 1538 |
+
"loss": 0.121,
|
| 1539 |
+
"step": 123000
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 5.43,
|
| 1543 |
+
"learning_rate": 9.721890861460014e-06,
|
| 1544 |
+
"loss": 0.1167,
|
| 1545 |
+
"step": 123500
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 5.45,
|
| 1549 |
+
"learning_rate": 9.675110518560102e-06,
|
| 1550 |
+
"loss": 0.1199,
|
| 1551 |
+
"step": 124000
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 5.47,
|
| 1555 |
+
"learning_rate": 9.628330175660189e-06,
|
| 1556 |
+
"loss": 0.1216,
|
| 1557 |
+
"step": 124500
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 5.5,
|
| 1561 |
+
"learning_rate": 9.581549832760275e-06,
|
| 1562 |
+
"loss": 0.1203,
|
| 1563 |
+
"step": 125000
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 5.52,
|
| 1567 |
+
"learning_rate": 9.534769489860362e-06,
|
| 1568 |
+
"loss": 0.1055,
|
| 1569 |
+
"step": 125500
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 5.54,
|
| 1573 |
+
"learning_rate": 9.487989146960448e-06,
|
| 1574 |
+
"loss": 0.1211,
|
| 1575 |
+
"step": 126000
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 5.56,
|
| 1579 |
+
"learning_rate": 9.441208804060534e-06,
|
| 1580 |
+
"loss": 0.1259,
|
| 1581 |
+
"step": 126500
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 5.58,
|
| 1585 |
+
"learning_rate": 9.394428461160621e-06,
|
| 1586 |
+
"loss": 0.1184,
|
| 1587 |
+
"step": 127000
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 5.61,
|
| 1591 |
+
"learning_rate": 9.347648118260709e-06,
|
| 1592 |
+
"loss": 0.1151,
|
| 1593 |
+
"step": 127500
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 5.63,
|
| 1597 |
+
"learning_rate": 9.300867775360794e-06,
|
| 1598 |
+
"loss": 0.1182,
|
| 1599 |
+
"step": 128000
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 5.65,
|
| 1603 |
+
"learning_rate": 9.25408743246088e-06,
|
| 1604 |
+
"loss": 0.1234,
|
| 1605 |
+
"step": 128500
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 5.67,
|
| 1609 |
+
"learning_rate": 9.207307089560968e-06,
|
| 1610 |
+
"loss": 0.124,
|
| 1611 |
+
"step": 129000
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 5.69,
|
| 1615 |
+
"learning_rate": 9.160526746661053e-06,
|
| 1616 |
+
"loss": 0.1233,
|
| 1617 |
+
"step": 129500
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 5.72,
|
| 1621 |
+
"learning_rate": 9.11374640376114e-06,
|
| 1622 |
+
"loss": 0.1249,
|
| 1623 |
+
"step": 130000
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 5.74,
|
| 1627 |
+
"learning_rate": 9.066966060861227e-06,
|
| 1628 |
+
"loss": 0.1294,
|
| 1629 |
+
"step": 130500
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 5.76,
|
| 1633 |
+
"learning_rate": 9.020185717961314e-06,
|
| 1634 |
+
"loss": 0.1195,
|
| 1635 |
+
"step": 131000
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 5.78,
|
| 1639 |
+
"learning_rate": 8.9734053750614e-06,
|
| 1640 |
+
"loss": 0.121,
|
| 1641 |
+
"step": 131500
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 5.8,
|
| 1645 |
+
"learning_rate": 8.926625032161487e-06,
|
| 1646 |
+
"loss": 0.1222,
|
| 1647 |
+
"step": 132000
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 5.83,
|
| 1651 |
+
"learning_rate": 8.879844689261573e-06,
|
| 1652 |
+
"loss": 0.1253,
|
| 1653 |
+
"step": 132500
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 5.85,
|
| 1657 |
+
"learning_rate": 8.833064346361659e-06,
|
| 1658 |
+
"loss": 0.1286,
|
| 1659 |
+
"step": 133000
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 5.87,
|
| 1663 |
+
"learning_rate": 8.786284003461746e-06,
|
| 1664 |
+
"loss": 0.1246,
|
| 1665 |
+
"step": 133500
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 5.89,
|
| 1669 |
+
"learning_rate": 8.739503660561832e-06,
|
| 1670 |
+
"loss": 0.1243,
|
| 1671 |
+
"step": 134000
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 5.91,
|
| 1675 |
+
"learning_rate": 8.69272331766192e-06,
|
| 1676 |
+
"loss": 0.1237,
|
| 1677 |
+
"step": 134500
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 5.94,
|
| 1681 |
+
"learning_rate": 8.645942974762007e-06,
|
| 1682 |
+
"loss": 0.1131,
|
| 1683 |
+
"step": 135000
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 5.96,
|
| 1687 |
+
"learning_rate": 8.599162631862093e-06,
|
| 1688 |
+
"loss": 0.126,
|
| 1689 |
+
"step": 135500
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 5.98,
|
| 1693 |
+
"learning_rate": 8.552382288962178e-06,
|
| 1694 |
+
"loss": 0.1262,
|
| 1695 |
+
"step": 136000
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 6.0,
|
| 1699 |
+
"eval_accuracy": 0.9112787534009399,
|
| 1700 |
+
"eval_combined_score": 0.8962263843527706,
|
| 1701 |
+
"eval_f1": 0.8811740153046013,
|
| 1702 |
+
"eval_loss": 0.3939257562160492,
|
| 1703 |
+
"eval_runtime": 71.8403,
|
| 1704 |
+
"eval_samples_per_second": 562.776,
|
| 1705 |
+
"eval_steps_per_second": 70.35,
|
| 1706 |
+
"step": 136446
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 6.0,
|
| 1710 |
+
"learning_rate": 8.505601946062266e-06,
|
| 1711 |
+
"loss": 0.1149,
|
| 1712 |
+
"step": 136500
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 6.02,
|
| 1716 |
+
"learning_rate": 8.458821603162352e-06,
|
| 1717 |
+
"loss": 0.0775,
|
| 1718 |
+
"step": 137000
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 6.05,
|
| 1722 |
+
"learning_rate": 8.412041260262437e-06,
|
| 1723 |
+
"loss": 0.0807,
|
| 1724 |
+
"step": 137500
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 6.07,
|
| 1728 |
+
"learning_rate": 8.365260917362525e-06,
|
| 1729 |
+
"loss": 0.0882,
|
| 1730 |
+
"step": 138000
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 6.09,
|
| 1734 |
+
"learning_rate": 8.318480574462612e-06,
|
| 1735 |
+
"loss": 0.0916,
|
| 1736 |
+
"step": 138500
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 6.11,
|
| 1740 |
+
"learning_rate": 8.271700231562698e-06,
|
| 1741 |
+
"loss": 0.0919,
|
| 1742 |
+
"step": 139000
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 6.13,
|
| 1746 |
+
"learning_rate": 8.224919888662784e-06,
|
| 1747 |
+
"loss": 0.0863,
|
| 1748 |
+
"step": 139500
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 6.16,
|
| 1752 |
+
"learning_rate": 8.178139545762871e-06,
|
| 1753 |
+
"loss": 0.0955,
|
| 1754 |
+
"step": 140000
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 6.18,
|
| 1758 |
+
"learning_rate": 8.131359202862957e-06,
|
| 1759 |
+
"loss": 0.0889,
|
| 1760 |
+
"step": 140500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 6.2,
|
| 1764 |
+
"learning_rate": 8.084578859963044e-06,
|
| 1765 |
+
"loss": 0.0957,
|
| 1766 |
+
"step": 141000
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 6.22,
|
| 1770 |
+
"learning_rate": 8.037798517063132e-06,
|
| 1771 |
+
"loss": 0.1,
|
| 1772 |
+
"step": 141500
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 6.24,
|
| 1776 |
+
"learning_rate": 7.991018174163218e-06,
|
| 1777 |
+
"loss": 0.0933,
|
| 1778 |
+
"step": 142000
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 6.27,
|
| 1782 |
+
"learning_rate": 7.944237831263303e-06,
|
| 1783 |
+
"loss": 0.0844,
|
| 1784 |
+
"step": 142500
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 6.29,
|
| 1788 |
+
"learning_rate": 7.89745748836339e-06,
|
| 1789 |
+
"loss": 0.0914,
|
| 1790 |
+
"step": 143000
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 6.31,
|
| 1794 |
+
"learning_rate": 7.850677145463477e-06,
|
| 1795 |
+
"loss": 0.0885,
|
| 1796 |
+
"step": 143500
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 6.33,
|
| 1800 |
+
"learning_rate": 7.803896802563562e-06,
|
| 1801 |
+
"loss": 0.0895,
|
| 1802 |
+
"step": 144000
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 6.35,
|
| 1806 |
+
"learning_rate": 7.75711645966365e-06,
|
| 1807 |
+
"loss": 0.0869,
|
| 1808 |
+
"step": 144500
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 6.38,
|
| 1812 |
+
"learning_rate": 7.710336116763737e-06,
|
| 1813 |
+
"loss": 0.0933,
|
| 1814 |
+
"step": 145000
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 6.4,
|
| 1818 |
+
"learning_rate": 7.663555773863823e-06,
|
| 1819 |
+
"loss": 0.0841,
|
| 1820 |
+
"step": 145500
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 6.42,
|
| 1824 |
+
"learning_rate": 7.61677543096391e-06,
|
| 1825 |
+
"loss": 0.0908,
|
| 1826 |
+
"step": 146000
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 6.44,
|
| 1830 |
+
"learning_rate": 7.569995088063996e-06,
|
| 1831 |
+
"loss": 0.0942,
|
| 1832 |
+
"step": 146500
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 6.46,
|
| 1836 |
+
"learning_rate": 7.523214745164083e-06,
|
| 1837 |
+
"loss": 0.0872,
|
| 1838 |
+
"step": 147000
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 6.49,
|
| 1842 |
+
"learning_rate": 7.476434402264169e-06,
|
| 1843 |
+
"loss": 0.0894,
|
| 1844 |
+
"step": 147500
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 6.51,
|
| 1848 |
+
"learning_rate": 7.429654059364255e-06,
|
| 1849 |
+
"loss": 0.0888,
|
| 1850 |
+
"step": 148000
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 6.53,
|
| 1854 |
+
"learning_rate": 7.382873716464343e-06,
|
| 1855 |
+
"loss": 0.093,
|
| 1856 |
+
"step": 148500
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 6.55,
|
| 1860 |
+
"learning_rate": 7.336093373564429e-06,
|
| 1861 |
+
"loss": 0.0885,
|
| 1862 |
+
"step": 149000
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 6.57,
|
| 1866 |
+
"learning_rate": 7.289313030664516e-06,
|
| 1867 |
+
"loss": 0.092,
|
| 1868 |
+
"step": 149500
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 6.6,
|
| 1872 |
+
"learning_rate": 7.242532687764602e-06,
|
| 1873 |
+
"loss": 0.0956,
|
| 1874 |
+
"step": 150000
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 6.62,
|
| 1878 |
+
"learning_rate": 7.195752344864688e-06,
|
| 1879 |
+
"loss": 0.1009,
|
| 1880 |
+
"step": 150500
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 6.64,
|
| 1884 |
+
"learning_rate": 7.148972001964775e-06,
|
| 1885 |
+
"loss": 0.0956,
|
| 1886 |
+
"step": 151000
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 6.66,
|
| 1890 |
+
"learning_rate": 7.102191659064862e-06,
|
| 1891 |
+
"loss": 0.0908,
|
| 1892 |
+
"step": 151500
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 6.68,
|
| 1896 |
+
"learning_rate": 7.055411316164949e-06,
|
| 1897 |
+
"loss": 0.0878,
|
| 1898 |
+
"step": 152000
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 6.71,
|
| 1902 |
+
"learning_rate": 7.008630973265035e-06,
|
| 1903 |
+
"loss": 0.1011,
|
| 1904 |
+
"step": 152500
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 6.73,
|
| 1908 |
+
"learning_rate": 6.961850630365121e-06,
|
| 1909 |
+
"loss": 0.0898,
|
| 1910 |
+
"step": 153000
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 6.75,
|
| 1914 |
+
"learning_rate": 6.915070287465208e-06,
|
| 1915 |
+
"loss": 0.0948,
|
| 1916 |
+
"step": 153500
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 6.77,
|
| 1920 |
+
"learning_rate": 6.868289944565294e-06,
|
| 1921 |
+
"loss": 0.0908,
|
| 1922 |
+
"step": 154000
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 6.79,
|
| 1926 |
+
"learning_rate": 6.82150960166538e-06,
|
| 1927 |
+
"loss": 0.0935,
|
| 1928 |
+
"step": 154500
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 6.82,
|
| 1932 |
+
"learning_rate": 6.774729258765468e-06,
|
| 1933 |
+
"loss": 0.0987,
|
| 1934 |
+
"step": 155000
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 6.84,
|
| 1938 |
+
"learning_rate": 6.727948915865554e-06,
|
| 1939 |
+
"loss": 0.0971,
|
| 1940 |
+
"step": 155500
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 6.86,
|
| 1944 |
+
"learning_rate": 6.681168572965641e-06,
|
| 1945 |
+
"loss": 0.0894,
|
| 1946 |
+
"step": 156000
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 6.88,
|
| 1950 |
+
"learning_rate": 6.634388230065727e-06,
|
| 1951 |
+
"loss": 0.0925,
|
| 1952 |
+
"step": 156500
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 6.9,
|
| 1956 |
+
"learning_rate": 6.587607887165813e-06,
|
| 1957 |
+
"loss": 0.0831,
|
| 1958 |
+
"step": 157000
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 6.93,
|
| 1962 |
+
"learning_rate": 6.5408275442659e-06,
|
| 1963 |
+
"loss": 0.1021,
|
| 1964 |
+
"step": 157500
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 6.95,
|
| 1968 |
+
"learning_rate": 6.4940472013659864e-06,
|
| 1969 |
+
"loss": 0.0974,
|
| 1970 |
+
"step": 158000
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 6.97,
|
| 1974 |
+
"learning_rate": 6.447266858466074e-06,
|
| 1975 |
+
"loss": 0.0993,
|
| 1976 |
+
"step": 158500
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 6.99,
|
| 1980 |
+
"learning_rate": 6.40048651556616e-06,
|
| 1981 |
+
"loss": 0.0867,
|
| 1982 |
+
"step": 159000
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 7.0,
|
| 1986 |
+
"eval_accuracy": 0.9152609448429384,
|
| 1987 |
+
"eval_combined_score": 0.9009873932600381,
|
| 1988 |
+
"eval_f1": 0.8867138416771377,
|
| 1989 |
+
"eval_loss": 0.44352227449417114,
|
| 1990 |
+
"eval_runtime": 71.6368,
|
| 1991 |
+
"eval_samples_per_second": 564.374,
|
| 1992 |
+
"eval_steps_per_second": 70.55,
|
| 1993 |
+
"step": 159187
|
| 1994 |
+
},
|
| 1995 |
+
{
|
| 1996 |
+
"epoch": 7.01,
|
| 1997 |
+
"learning_rate": 6.353706172666246e-06,
|
| 1998 |
+
"loss": 0.0648,
|
| 1999 |
+
"step": 159500
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 7.04,
|
| 2003 |
+
"learning_rate": 6.306925829766333e-06,
|
| 2004 |
+
"loss": 0.0651,
|
| 2005 |
+
"step": 160000
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 7.06,
|
| 2009 |
+
"learning_rate": 6.2601454868664195e-06,
|
| 2010 |
+
"loss": 0.0692,
|
| 2011 |
+
"step": 160500
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 7.08,
|
| 2015 |
+
"learning_rate": 6.213365143966505e-06,
|
| 2016 |
+
"loss": 0.0699,
|
| 2017 |
+
"step": 161000
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 7.1,
|
| 2021 |
+
"learning_rate": 6.166584801066592e-06,
|
| 2022 |
+
"loss": 0.0668,
|
| 2023 |
+
"step": 161500
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 7.12,
|
| 2027 |
+
"learning_rate": 6.119804458166679e-06,
|
| 2028 |
+
"loss": 0.0606,
|
| 2029 |
+
"step": 162000
|
| 2030 |
+
},
|
| 2031 |
+
{
|
| 2032 |
+
"epoch": 7.15,
|
| 2033 |
+
"learning_rate": 6.073024115266766e-06,
|
| 2034 |
+
"loss": 0.0728,
|
| 2035 |
+
"step": 162500
|
| 2036 |
+
},
|
| 2037 |
+
{
|
| 2038 |
+
"epoch": 7.17,
|
| 2039 |
+
"learning_rate": 6.0262437723668525e-06,
|
| 2040 |
+
"loss": 0.0627,
|
| 2041 |
+
"step": 163000
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 7.19,
|
| 2045 |
+
"learning_rate": 5.979463429466938e-06,
|
| 2046 |
+
"loss": 0.0691,
|
| 2047 |
+
"step": 163500
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 7.21,
|
| 2051 |
+
"learning_rate": 5.932683086567025e-06,
|
| 2052 |
+
"loss": 0.0653,
|
| 2053 |
+
"step": 164000
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 7.23,
|
| 2057 |
+
"learning_rate": 5.8859027436671114e-06,
|
| 2058 |
+
"loss": 0.0659,
|
| 2059 |
+
"step": 164500
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 7.26,
|
| 2063 |
+
"learning_rate": 5.839122400767197e-06,
|
| 2064 |
+
"loss": 0.0613,
|
| 2065 |
+
"step": 165000
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 7.28,
|
| 2069 |
+
"learning_rate": 5.7923420578672855e-06,
|
| 2070 |
+
"loss": 0.0599,
|
| 2071 |
+
"step": 165500
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 7.3,
|
| 2075 |
+
"learning_rate": 5.745561714967371e-06,
|
| 2076 |
+
"loss": 0.0723,
|
| 2077 |
+
"step": 166000
|
| 2078 |
+
},
|
| 2079 |
+
{
|
| 2080 |
+
"epoch": 7.32,
|
| 2081 |
+
"learning_rate": 5.698781372067458e-06,
|
| 2082 |
+
"loss": 0.0709,
|
| 2083 |
+
"step": 166500
|
| 2084 |
+
},
|
| 2085 |
+
{
|
| 2086 |
+
"epoch": 7.34,
|
| 2087 |
+
"learning_rate": 5.6520010291675445e-06,
|
| 2088 |
+
"loss": 0.0714,
|
| 2089 |
+
"step": 167000
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 7.37,
|
| 2093 |
+
"learning_rate": 5.60522068626763e-06,
|
| 2094 |
+
"loss": 0.0637,
|
| 2095 |
+
"step": 167500
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 7.39,
|
| 2099 |
+
"learning_rate": 5.558440343367717e-06,
|
| 2100 |
+
"loss": 0.0726,
|
| 2101 |
+
"step": 168000
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 7.41,
|
| 2105 |
+
"learning_rate": 5.5116600004678034e-06,
|
| 2106 |
+
"loss": 0.0632,
|
| 2107 |
+
"step": 168500
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"epoch": 7.43,
|
| 2111 |
+
"learning_rate": 5.464879657567891e-06,
|
| 2112 |
+
"loss": 0.0735,
|
| 2113 |
+
"step": 169000
|
| 2114 |
+
},
|
| 2115 |
+
{
|
| 2116 |
+
"epoch": 7.45,
|
| 2117 |
+
"learning_rate": 5.4180993146679775e-06,
|
| 2118 |
+
"loss": 0.0693,
|
| 2119 |
+
"step": 169500
|
| 2120 |
+
},
|
| 2121 |
+
{
|
| 2122 |
+
"epoch": 7.48,
|
| 2123 |
+
"learning_rate": 5.371318971768063e-06,
|
| 2124 |
+
"loss": 0.07,
|
| 2125 |
+
"step": 170000
|
| 2126 |
+
},
|
| 2127 |
+
{
|
| 2128 |
+
"epoch": 7.5,
|
| 2129 |
+
"learning_rate": 5.32453862886815e-06,
|
| 2130 |
+
"loss": 0.0699,
|
| 2131 |
+
"step": 170500
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 7.52,
|
| 2135 |
+
"learning_rate": 5.2777582859682365e-06,
|
| 2136 |
+
"loss": 0.0617,
|
| 2137 |
+
"step": 171000
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 7.54,
|
| 2141 |
+
"learning_rate": 5.230977943068323e-06,
|
| 2142 |
+
"loss": 0.056,
|
| 2143 |
+
"step": 171500
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 7.56,
|
| 2147 |
+
"learning_rate": 5.184197600168409e-06,
|
| 2148 |
+
"loss": 0.0644,
|
| 2149 |
+
"step": 172000
|
| 2150 |
+
},
|
| 2151 |
+
{
|
| 2152 |
+
"epoch": 7.59,
|
| 2153 |
+
"learning_rate": 5.137417257268496e-06,
|
| 2154 |
+
"loss": 0.0694,
|
| 2155 |
+
"step": 172500
|
| 2156 |
+
},
|
| 2157 |
+
{
|
| 2158 |
+
"epoch": 7.61,
|
| 2159 |
+
"learning_rate": 5.090636914368583e-06,
|
| 2160 |
+
"loss": 0.0642,
|
| 2161 |
+
"step": 173000
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 7.63,
|
| 2165 |
+
"learning_rate": 5.0438565714686695e-06,
|
| 2166 |
+
"loss": 0.0673,
|
| 2167 |
+
"step": 173500
|
| 2168 |
+
},
|
| 2169 |
+
{
|
| 2170 |
+
"epoch": 7.65,
|
| 2171 |
+
"learning_rate": 4.997076228568756e-06,
|
| 2172 |
+
"loss": 0.0682,
|
| 2173 |
+
"step": 174000
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 7.67,
|
| 2177 |
+
"learning_rate": 4.950295885668842e-06,
|
| 2178 |
+
"loss": 0.0671,
|
| 2179 |
+
"step": 174500
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 7.7,
|
| 2183 |
+
"learning_rate": 4.903515542768929e-06,
|
| 2184 |
+
"loss": 0.0734,
|
| 2185 |
+
"step": 175000
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 7.72,
|
| 2189 |
+
"learning_rate": 4.856735199869015e-06,
|
| 2190 |
+
"loss": 0.0665,
|
| 2191 |
+
"step": 175500
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 7.74,
|
| 2195 |
+
"learning_rate": 4.809954856969102e-06,
|
| 2196 |
+
"loss": 0.0644,
|
| 2197 |
+
"step": 176000
|
| 2198 |
+
},
|
| 2199 |
+
{
|
| 2200 |
+
"epoch": 7.76,
|
| 2201 |
+
"learning_rate": 4.763174514069189e-06,
|
| 2202 |
+
"loss": 0.0681,
|
| 2203 |
+
"step": 176500
|
| 2204 |
+
},
|
| 2205 |
+
{
|
| 2206 |
+
"epoch": 7.78,
|
| 2207 |
+
"learning_rate": 4.716394171169275e-06,
|
| 2208 |
+
"loss": 0.0755,
|
| 2209 |
+
"step": 177000
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 7.81,
|
| 2213 |
+
"learning_rate": 4.6696138282693615e-06,
|
| 2214 |
+
"loss": 0.0758,
|
| 2215 |
+
"step": 177500
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 7.83,
|
| 2219 |
+
"learning_rate": 4.622833485369448e-06,
|
| 2220 |
+
"loss": 0.0633,
|
| 2221 |
+
"step": 178000
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 7.85,
|
| 2225 |
+
"learning_rate": 4.576053142469535e-06,
|
| 2226 |
+
"loss": 0.0603,
|
| 2227 |
+
"step": 178500
|
| 2228 |
+
},
|
| 2229 |
+
{
|
| 2230 |
+
"epoch": 7.87,
|
| 2231 |
+
"learning_rate": 4.529272799569621e-06,
|
| 2232 |
+
"loss": 0.0703,
|
| 2233 |
+
"step": 179000
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 7.89,
|
| 2237 |
+
"learning_rate": 4.482492456669708e-06,
|
| 2238 |
+
"loss": 0.062,
|
| 2239 |
+
"step": 179500
|
| 2240 |
+
},
|
| 2241 |
+
{
|
| 2242 |
+
"epoch": 7.92,
|
| 2243 |
+
"learning_rate": 4.4357121137697945e-06,
|
| 2244 |
+
"loss": 0.0733,
|
| 2245 |
+
"step": 180000
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 7.94,
|
| 2249 |
+
"learning_rate": 4.388931770869881e-06,
|
| 2250 |
+
"loss": 0.0717,
|
| 2251 |
+
"step": 180500
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 7.96,
|
| 2255 |
+
"learning_rate": 4.342151427969967e-06,
|
| 2256 |
+
"loss": 0.0612,
|
| 2257 |
+
"step": 181000
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 7.98,
|
| 2261 |
+
"learning_rate": 4.295371085070054e-06,
|
| 2262 |
+
"loss": 0.0757,
|
| 2263 |
+
"step": 181500
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 8.0,
|
| 2267 |
+
"eval_accuracy": 0.9147415285678951,
|
| 2268 |
+
"eval_combined_score": 0.8995565346371729,
|
| 2269 |
+
"eval_f1": 0.8843715407064506,
|
| 2270 |
+
"eval_loss": 0.4811749756336212,
|
| 2271 |
+
"eval_runtime": 72.7906,
|
| 2272 |
+
"eval_samples_per_second": 555.429,
|
| 2273 |
+
"eval_steps_per_second": 69.432,
|
| 2274 |
+
"step": 181928
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 8.0,
|
| 2278 |
+
"learning_rate": 4.248590742170141e-06,
|
| 2279 |
+
"loss": 0.0629,
|
| 2280 |
+
"step": 182000
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 8.03,
|
| 2284 |
+
"learning_rate": 4.201810399270227e-06,
|
| 2285 |
+
"loss": 0.0438,
|
| 2286 |
+
"step": 182500
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 8.05,
|
| 2290 |
+
"learning_rate": 4.155030056370313e-06,
|
| 2291 |
+
"loss": 0.0419,
|
| 2292 |
+
"step": 183000
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 8.07,
|
| 2296 |
+
"learning_rate": 4.1082497134704e-06,
|
| 2297 |
+
"loss": 0.0343,
|
| 2298 |
+
"step": 183500
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 8.09,
|
| 2302 |
+
"learning_rate": 4.0614693705704865e-06,
|
| 2303 |
+
"loss": 0.0557,
|
| 2304 |
+
"step": 184000
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 8.11,
|
| 2308 |
+
"learning_rate": 4.014689027670573e-06,
|
| 2309 |
+
"loss": 0.052,
|
| 2310 |
+
"step": 184500
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 8.14,
|
| 2314 |
+
"learning_rate": 3.96790868477066e-06,
|
| 2315 |
+
"loss": 0.0446,
|
| 2316 |
+
"step": 185000
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 8.16,
|
| 2320 |
+
"learning_rate": 3.921128341870746e-06,
|
| 2321 |
+
"loss": 0.0473,
|
| 2322 |
+
"step": 185500
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 8.18,
|
| 2326 |
+
"learning_rate": 3.874347998970833e-06,
|
| 2327 |
+
"loss": 0.0455,
|
| 2328 |
+
"step": 186000
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 8.2,
|
| 2332 |
+
"learning_rate": 3.827567656070919e-06,
|
| 2333 |
+
"loss": 0.0486,
|
| 2334 |
+
"step": 186500
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 8.22,
|
| 2338 |
+
"learning_rate": 3.780787313171006e-06,
|
| 2339 |
+
"loss": 0.0412,
|
| 2340 |
+
"step": 187000
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 8.25,
|
| 2344 |
+
"learning_rate": 3.7340069702710923e-06,
|
| 2345 |
+
"loss": 0.0502,
|
| 2346 |
+
"step": 187500
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 8.27,
|
| 2350 |
+
"learning_rate": 3.687226627371179e-06,
|
| 2351 |
+
"loss": 0.0435,
|
| 2352 |
+
"step": 188000
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 8.29,
|
| 2356 |
+
"learning_rate": 3.6404462844712655e-06,
|
| 2357 |
+
"loss": 0.0391,
|
| 2358 |
+
"step": 188500
|
| 2359 |
+
},
|
| 2360 |
+
{
|
| 2361 |
+
"epoch": 8.31,
|
| 2362 |
+
"learning_rate": 3.593665941571352e-06,
|
| 2363 |
+
"loss": 0.0476,
|
| 2364 |
+
"step": 189000
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 8.33,
|
| 2368 |
+
"learning_rate": 3.5468855986714383e-06,
|
| 2369 |
+
"loss": 0.0468,
|
| 2370 |
+
"step": 189500
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 8.35,
|
| 2374 |
+
"learning_rate": 3.500105255771525e-06,
|
| 2375 |
+
"loss": 0.043,
|
| 2376 |
+
"step": 190000
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 8.38,
|
| 2380 |
+
"learning_rate": 3.453324912871612e-06,
|
| 2381 |
+
"loss": 0.0457,
|
| 2382 |
+
"step": 190500
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 8.4,
|
| 2386 |
+
"learning_rate": 3.406544569971698e-06,
|
| 2387 |
+
"loss": 0.0445,
|
| 2388 |
+
"step": 191000
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 8.42,
|
| 2392 |
+
"learning_rate": 3.3597642270717847e-06,
|
| 2393 |
+
"loss": 0.0532,
|
| 2394 |
+
"step": 191500
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 8.44,
|
| 2398 |
+
"learning_rate": 3.3129838841718713e-06,
|
| 2399 |
+
"loss": 0.049,
|
| 2400 |
+
"step": 192000
|
| 2401 |
+
},
|
| 2402 |
+
{
|
| 2403 |
+
"epoch": 8.46,
|
| 2404 |
+
"learning_rate": 3.266203541271958e-06,
|
| 2405 |
+
"loss": 0.0451,
|
| 2406 |
+
"step": 192500
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 8.49,
|
| 2410 |
+
"learning_rate": 3.219423198372044e-06,
|
| 2411 |
+
"loss": 0.0493,
|
| 2412 |
+
"step": 193000
|
| 2413 |
+
},
|
| 2414 |
+
{
|
| 2415 |
+
"epoch": 8.51,
|
| 2416 |
+
"learning_rate": 3.172642855472131e-06,
|
| 2417 |
+
"loss": 0.0387,
|
| 2418 |
+
"step": 193500
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 8.53,
|
| 2422 |
+
"learning_rate": 3.1258625125722173e-06,
|
| 2423 |
+
"loss": 0.0597,
|
| 2424 |
+
"step": 194000
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 8.55,
|
| 2428 |
+
"learning_rate": 3.079082169672304e-06,
|
| 2429 |
+
"loss": 0.0549,
|
| 2430 |
+
"step": 194500
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 8.57,
|
| 2434 |
+
"learning_rate": 3.03230182677239e-06,
|
| 2435 |
+
"loss": 0.0455,
|
| 2436 |
+
"step": 195000
|
| 2437 |
+
},
|
| 2438 |
+
{
|
| 2439 |
+
"epoch": 8.6,
|
| 2440 |
+
"learning_rate": 2.985521483872477e-06,
|
| 2441 |
+
"loss": 0.0487,
|
| 2442 |
+
"step": 195500
|
| 2443 |
+
},
|
| 2444 |
+
{
|
| 2445 |
+
"epoch": 8.62,
|
| 2446 |
+
"learning_rate": 2.9387411409725637e-06,
|
| 2447 |
+
"loss": 0.0485,
|
| 2448 |
+
"step": 196000
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 8.64,
|
| 2452 |
+
"learning_rate": 2.89196079807265e-06,
|
| 2453 |
+
"loss": 0.0471,
|
| 2454 |
+
"step": 196500
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"epoch": 8.66,
|
| 2458 |
+
"learning_rate": 2.845180455172737e-06,
|
| 2459 |
+
"loss": 0.0508,
|
| 2460 |
+
"step": 197000
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 8.68,
|
| 2464 |
+
"learning_rate": 2.798400112272823e-06,
|
| 2465 |
+
"loss": 0.0489,
|
| 2466 |
+
"step": 197500
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 8.71,
|
| 2470 |
+
"learning_rate": 2.7516197693729097e-06,
|
| 2471 |
+
"loss": 0.0498,
|
| 2472 |
+
"step": 198000
|
| 2473 |
+
},
|
| 2474 |
+
{
|
| 2475 |
+
"epoch": 8.73,
|
| 2476 |
+
"learning_rate": 2.704839426472996e-06,
|
| 2477 |
+
"loss": 0.0457,
|
| 2478 |
+
"step": 198500
|
| 2479 |
+
},
|
| 2480 |
+
{
|
| 2481 |
+
"epoch": 8.75,
|
| 2482 |
+
"learning_rate": 2.658059083573083e-06,
|
| 2483 |
+
"loss": 0.0434,
|
| 2484 |
+
"step": 199000
|
| 2485 |
+
},
|
| 2486 |
+
{
|
| 2487 |
+
"epoch": 8.77,
|
| 2488 |
+
"learning_rate": 2.6112787406731695e-06,
|
| 2489 |
+
"loss": 0.0394,
|
| 2490 |
+
"step": 199500
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"epoch": 8.79,
|
| 2494 |
+
"learning_rate": 2.5644983977732557e-06,
|
| 2495 |
+
"loss": 0.0422,
|
| 2496 |
+
"step": 200000
|
| 2497 |
+
},
|
| 2498 |
+
{
|
| 2499 |
+
"epoch": 8.82,
|
| 2500 |
+
"learning_rate": 2.5177180548733427e-06,
|
| 2501 |
+
"loss": 0.0505,
|
| 2502 |
+
"step": 200500
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 8.84,
|
| 2506 |
+
"learning_rate": 2.470937711973429e-06,
|
| 2507 |
+
"loss": 0.0574,
|
| 2508 |
+
"step": 201000
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 8.86,
|
| 2512 |
+
"learning_rate": 2.4241573690735155e-06,
|
| 2513 |
+
"loss": 0.0445,
|
| 2514 |
+
"step": 201500
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 8.88,
|
| 2518 |
+
"learning_rate": 2.377377026173602e-06,
|
| 2519 |
+
"loss": 0.0565,
|
| 2520 |
+
"step": 202000
|
| 2521 |
+
},
|
| 2522 |
+
{
|
| 2523 |
+
"epoch": 8.9,
|
| 2524 |
+
"learning_rate": 2.3305966832736887e-06,
|
| 2525 |
+
"loss": 0.0519,
|
| 2526 |
+
"step": 202500
|
| 2527 |
+
},
|
| 2528 |
+
{
|
| 2529 |
+
"epoch": 8.93,
|
| 2530 |
+
"learning_rate": 2.283816340373775e-06,
|
| 2531 |
+
"loss": 0.0508,
|
| 2532 |
+
"step": 203000
|
| 2533 |
+
},
|
| 2534 |
+
{
|
| 2535 |
+
"epoch": 8.95,
|
| 2536 |
+
"learning_rate": 2.237035997473862e-06,
|
| 2537 |
+
"loss": 0.0467,
|
| 2538 |
+
"step": 203500
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 8.97,
|
| 2542 |
+
"learning_rate": 2.190255654573948e-06,
|
| 2543 |
+
"loss": 0.0466,
|
| 2544 |
+
"step": 204000
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 8.99,
|
| 2548 |
+
"learning_rate": 2.1434753116740347e-06,
|
| 2549 |
+
"loss": 0.0479,
|
| 2550 |
+
"step": 204500
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 9.0,
|
| 2554 |
+
"eval_accuracy": 0.9150878060845906,
|
| 2555 |
+
"eval_combined_score": 0.9010856587900834,
|
| 2556 |
+
"eval_f1": 0.8870835114955762,
|
| 2557 |
+
"eval_loss": 0.5081153512001038,
|
| 2558 |
+
"eval_runtime": 92.6456,
|
| 2559 |
+
"eval_samples_per_second": 436.394,
|
| 2560 |
+
"eval_steps_per_second": 54.552,
|
| 2561 |
+
"step": 204669
|
| 2562 |
+
},
|
| 2563 |
+
{
|
| 2564 |
+
"epoch": 9.01,
|
| 2565 |
+
"learning_rate": 2.0966949687741213e-06,
|
| 2566 |
+
"loss": 0.0354,
|
| 2567 |
+
"step": 205000
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 9.04,
|
| 2571 |
+
"learning_rate": 2.049914625874208e-06,
|
| 2572 |
+
"loss": 0.037,
|
| 2573 |
+
"step": 205500
|
| 2574 |
+
},
|
| 2575 |
+
{
|
| 2576 |
+
"epoch": 9.06,
|
| 2577 |
+
"learning_rate": 2.0031342829742946e-06,
|
| 2578 |
+
"loss": 0.0354,
|
| 2579 |
+
"step": 206000
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 9.08,
|
| 2583 |
+
"learning_rate": 1.9563539400743807e-06,
|
| 2584 |
+
"loss": 0.029,
|
| 2585 |
+
"step": 206500
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 9.1,
|
| 2589 |
+
"learning_rate": 1.9095735971744673e-06,
|
| 2590 |
+
"loss": 0.0363,
|
| 2591 |
+
"step": 207000
|
| 2592 |
+
},
|
| 2593 |
+
{
|
| 2594 |
+
"epoch": 9.12,
|
| 2595 |
+
"learning_rate": 1.862793254274554e-06,
|
| 2596 |
+
"loss": 0.0331,
|
| 2597 |
+
"step": 207500
|
| 2598 |
+
},
|
| 2599 |
+
{
|
| 2600 |
+
"epoch": 9.15,
|
| 2601 |
+
"learning_rate": 1.8160129113746405e-06,
|
| 2602 |
+
"loss": 0.03,
|
| 2603 |
+
"step": 208000
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 9.17,
|
| 2607 |
+
"learning_rate": 1.7692325684747272e-06,
|
| 2608 |
+
"loss": 0.0314,
|
| 2609 |
+
"step": 208500
|
| 2610 |
+
},
|
| 2611 |
+
{
|
| 2612 |
+
"epoch": 9.19,
|
| 2613 |
+
"learning_rate": 1.7224522255748135e-06,
|
| 2614 |
+
"loss": 0.033,
|
| 2615 |
+
"step": 209000
|
| 2616 |
+
},
|
| 2617 |
+
{
|
| 2618 |
+
"epoch": 9.21,
|
| 2619 |
+
"learning_rate": 1.6756718826749001e-06,
|
| 2620 |
+
"loss": 0.0307,
|
| 2621 |
+
"step": 209500
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 9.23,
|
| 2625 |
+
"learning_rate": 1.6288915397749865e-06,
|
| 2626 |
+
"loss": 0.0284,
|
| 2627 |
+
"step": 210000
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 9.26,
|
| 2631 |
+
"learning_rate": 1.5821111968750731e-06,
|
| 2632 |
+
"loss": 0.0311,
|
| 2633 |
+
"step": 210500
|
| 2634 |
+
},
|
| 2635 |
+
{
|
| 2636 |
+
"epoch": 9.28,
|
| 2637 |
+
"learning_rate": 1.5353308539751595e-06,
|
| 2638 |
+
"loss": 0.036,
|
| 2639 |
+
"step": 211000
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 9.3,
|
| 2643 |
+
"learning_rate": 1.4885505110752464e-06,
|
| 2644 |
+
"loss": 0.0321,
|
| 2645 |
+
"step": 211500
|
| 2646 |
+
},
|
| 2647 |
+
{
|
| 2648 |
+
"epoch": 9.32,
|
| 2649 |
+
"learning_rate": 1.441770168175333e-06,
|
| 2650 |
+
"loss": 0.0303,
|
| 2651 |
+
"step": 212000
|
| 2652 |
+
},
|
| 2653 |
+
{
|
| 2654 |
+
"epoch": 9.34,
|
| 2655 |
+
"learning_rate": 1.3949898252754194e-06,
|
| 2656 |
+
"loss": 0.0326,
|
| 2657 |
+
"step": 212500
|
| 2658 |
+
},
|
| 2659 |
+
{
|
| 2660 |
+
"epoch": 9.37,
|
| 2661 |
+
"learning_rate": 1.348209482375506e-06,
|
| 2662 |
+
"loss": 0.03,
|
| 2663 |
+
"step": 213000
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 9.39,
|
| 2667 |
+
"learning_rate": 1.3014291394755924e-06,
|
| 2668 |
+
"loss": 0.0325,
|
| 2669 |
+
"step": 213500
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 9.41,
|
| 2673 |
+
"learning_rate": 1.254648796575679e-06,
|
| 2674 |
+
"loss": 0.034,
|
| 2675 |
+
"step": 214000
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 9.43,
|
| 2679 |
+
"learning_rate": 1.2078684536757656e-06,
|
| 2680 |
+
"loss": 0.0423,
|
| 2681 |
+
"step": 214500
|
| 2682 |
+
},
|
| 2683 |
+
{
|
| 2684 |
+
"epoch": 9.45,
|
| 2685 |
+
"learning_rate": 1.161088110775852e-06,
|
| 2686 |
+
"loss": 0.0353,
|
| 2687 |
+
"step": 215000
|
| 2688 |
+
},
|
| 2689 |
+
{
|
| 2690 |
+
"epoch": 9.48,
|
| 2691 |
+
"learning_rate": 1.1143077678759386e-06,
|
| 2692 |
+
"loss": 0.0301,
|
| 2693 |
+
"step": 215500
|
| 2694 |
+
},
|
| 2695 |
+
{
|
| 2696 |
+
"epoch": 9.5,
|
| 2697 |
+
"learning_rate": 1.0675274249760252e-06,
|
| 2698 |
+
"loss": 0.0315,
|
| 2699 |
+
"step": 216000
|
| 2700 |
+
},
|
| 2701 |
+
{
|
| 2702 |
+
"epoch": 9.52,
|
| 2703 |
+
"learning_rate": 1.0207470820761118e-06,
|
| 2704 |
+
"loss": 0.0361,
|
| 2705 |
+
"step": 216500
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 9.54,
|
| 2709 |
+
"learning_rate": 9.739667391761982e-07,
|
| 2710 |
+
"loss": 0.0388,
|
| 2711 |
+
"step": 217000
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 9.56,
|
| 2715 |
+
"learning_rate": 9.271863962762848e-07,
|
| 2716 |
+
"loss": 0.0309,
|
| 2717 |
+
"step": 217500
|
| 2718 |
+
},
|
| 2719 |
+
{
|
| 2720 |
+
"epoch": 9.59,
|
| 2721 |
+
"learning_rate": 8.804060533763713e-07,
|
| 2722 |
+
"loss": 0.0299,
|
| 2723 |
+
"step": 218000
|
| 2724 |
+
},
|
| 2725 |
+
{
|
| 2726 |
+
"epoch": 9.61,
|
| 2727 |
+
"learning_rate": 8.336257104764578e-07,
|
| 2728 |
+
"loss": 0.0357,
|
| 2729 |
+
"step": 218500
|
| 2730 |
+
},
|
| 2731 |
+
{
|
| 2732 |
+
"epoch": 9.63,
|
| 2733 |
+
"learning_rate": 7.868453675765445e-07,
|
| 2734 |
+
"loss": 0.0285,
|
| 2735 |
+
"step": 219000
|
| 2736 |
+
},
|
| 2737 |
+
{
|
| 2738 |
+
"epoch": 9.65,
|
| 2739 |
+
"learning_rate": 7.40065024676631e-07,
|
| 2740 |
+
"loss": 0.0238,
|
| 2741 |
+
"step": 219500
|
| 2742 |
+
},
|
| 2743 |
+
{
|
| 2744 |
+
"epoch": 9.67,
|
| 2745 |
+
"learning_rate": 6.932846817767175e-07,
|
| 2746 |
+
"loss": 0.0284,
|
| 2747 |
+
"step": 220000
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 9.7,
|
| 2751 |
+
"learning_rate": 6.46504338876804e-07,
|
| 2752 |
+
"loss": 0.033,
|
| 2753 |
+
"step": 220500
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 9.72,
|
| 2757 |
+
"learning_rate": 5.997239959768906e-07,
|
| 2758 |
+
"loss": 0.031,
|
| 2759 |
+
"step": 221000
|
| 2760 |
+
},
|
| 2761 |
+
{
|
| 2762 |
+
"epoch": 9.74,
|
| 2763 |
+
"learning_rate": 5.529436530769771e-07,
|
| 2764 |
+
"loss": 0.028,
|
| 2765 |
+
"step": 221500
|
| 2766 |
+
},
|
| 2767 |
+
{
|
| 2768 |
+
"epoch": 9.76,
|
| 2769 |
+
"learning_rate": 5.061633101770636e-07,
|
| 2770 |
+
"loss": 0.0264,
|
| 2771 |
+
"step": 222000
|
| 2772 |
+
},
|
| 2773 |
+
{
|
| 2774 |
+
"epoch": 9.78,
|
| 2775 |
+
"learning_rate": 4.5938296727715023e-07,
|
| 2776 |
+
"loss": 0.0341,
|
| 2777 |
+
"step": 222500
|
| 2778 |
+
},
|
| 2779 |
+
{
|
| 2780 |
+
"epoch": 9.81,
|
| 2781 |
+
"learning_rate": 4.1260262437723673e-07,
|
| 2782 |
+
"loss": 0.0252,
|
| 2783 |
+
"step": 223000
|
| 2784 |
+
},
|
| 2785 |
+
{
|
| 2786 |
+
"epoch": 9.83,
|
| 2787 |
+
"learning_rate": 3.6582228147732323e-07,
|
| 2788 |
+
"loss": 0.0348,
|
| 2789 |
+
"step": 223500
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 9.85,
|
| 2793 |
+
"learning_rate": 3.1904193857740983e-07,
|
| 2794 |
+
"loss": 0.0315,
|
| 2795 |
+
"step": 224000
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 9.87,
|
| 2799 |
+
"learning_rate": 2.7226159567749633e-07,
|
| 2800 |
+
"loss": 0.0352,
|
| 2801 |
+
"step": 224500
|
| 2802 |
+
},
|
| 2803 |
+
{
|
| 2804 |
+
"epoch": 9.89,
|
| 2805 |
+
"learning_rate": 2.2548125277758288e-07,
|
| 2806 |
+
"loss": 0.0342,
|
| 2807 |
+
"step": 225000
|
| 2808 |
+
},
|
| 2809 |
+
{
|
| 2810 |
+
"epoch": 9.92,
|
| 2811 |
+
"learning_rate": 1.787009098776694e-07,
|
| 2812 |
+
"loss": 0.0313,
|
| 2813 |
+
"step": 225500
|
| 2814 |
+
},
|
| 2815 |
+
{
|
| 2816 |
+
"epoch": 9.94,
|
| 2817 |
+
"learning_rate": 1.3192056697775596e-07,
|
| 2818 |
+
"loss": 0.0324,
|
| 2819 |
+
"step": 226000
|
| 2820 |
+
},
|
| 2821 |
+
{
|
| 2822 |
+
"epoch": 9.96,
|
| 2823 |
+
"learning_rate": 8.51402240778425e-08,
|
| 2824 |
+
"loss": 0.0274,
|
| 2825 |
+
"step": 226500
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 9.98,
|
| 2829 |
+
"learning_rate": 3.835988117792904e-08,
|
| 2830 |
+
"loss": 0.0379,
|
| 2831 |
+
"step": 227000
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 10.0,
|
| 2835 |
+
"eval_accuracy": 0.9148899332179075,
|
| 2836 |
+
"eval_combined_score": 0.9003480960683503,
|
| 2837 |
+
"eval_f1": 0.8858062589187933,
|
| 2838 |
+
"eval_loss": 0.5646682977676392,
|
| 2839 |
+
"eval_runtime": 85.1463,
|
| 2840 |
+
"eval_samples_per_second": 474.83,
|
| 2841 |
+
"eval_steps_per_second": 59.357,
|
| 2842 |
+
"step": 227410
|
| 2843 |
+
},
|
| 2844 |
+
{
|
| 2845 |
+
"epoch": 10.0,
|
| 2846 |
+
"step": 227410,
|
| 2847 |
+
"total_flos": 2.393297626212864e+17,
|
| 2848 |
+
"train_loss": 0.1477880122620598,
|
| 2849 |
+
"train_runtime": 22868.2253,
|
| 2850 |
+
"train_samples_per_second": 159.105,
|
| 2851 |
+
"train_steps_per_second": 9.944
|
| 2852 |
+
}
|
| 2853 |
+
],
|
| 2854 |
+
"max_steps": 227410,
|
| 2855 |
+
"num_train_epochs": 10,
|
| 2856 |
+
"total_flos": 2.393297626212864e+17,
|
| 2857 |
+
"trial_name": null,
|
| 2858 |
+
"trial_params": null
|
| 2859 |
+
}
|