End of training
Browse files- all_results.json +25 -0
- eval_results.json +12 -0
- predict_results.json +10 -0
- predictions.txt +0 -0
- train_results.json +8 -0
- trainer_state.json +1639 -0
all_results.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 120.0,
|
| 3 |
+
"eval_accuracy": 0.8046732017950711,
|
| 4 |
+
"eval_f1": 0.6398059560706104,
|
| 5 |
+
"eval_loss": 1.7624890804290771,
|
| 6 |
+
"eval_precision": 0.6042249936370577,
|
| 7 |
+
"eval_recall": 0.6798396334478809,
|
| 8 |
+
"eval_runtime": 2.8827,
|
| 9 |
+
"eval_samples": 1112,
|
| 10 |
+
"eval_samples_per_second": 385.751,
|
| 11 |
+
"eval_steps_per_second": 6.244,
|
| 12 |
+
"predict_accuracy": 0.8020527140897511,
|
| 13 |
+
"predict_f1": 0.6292738631020353,
|
| 14 |
+
"predict_loss": 1.8004062175750732,
|
| 15 |
+
"predict_precision": 0.5881466599698644,
|
| 16 |
+
"predict_recall": 0.676585295392171,
|
| 17 |
+
"predict_runtime": 5.922,
|
| 18 |
+
"predict_samples_per_second": 375.715,
|
| 19 |
+
"predict_steps_per_second": 5.91,
|
| 20 |
+
"train_loss": 0.10161643302465072,
|
| 21 |
+
"train_runtime": 6791.1484,
|
| 22 |
+
"train_samples": 7785,
|
| 23 |
+
"train_samples_per_second": 137.561,
|
| 24 |
+
"train_steps_per_second": 2.156
|
| 25 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 120.0,
|
| 3 |
+
"eval_accuracy": 0.8046732017950711,
|
| 4 |
+
"eval_f1": 0.6398059560706104,
|
| 5 |
+
"eval_loss": 1.7624890804290771,
|
| 6 |
+
"eval_precision": 0.6042249936370577,
|
| 7 |
+
"eval_recall": 0.6798396334478809,
|
| 8 |
+
"eval_runtime": 2.8827,
|
| 9 |
+
"eval_samples": 1112,
|
| 10 |
+
"eval_samples_per_second": 385.751,
|
| 11 |
+
"eval_steps_per_second": 6.244
|
| 12 |
+
}
|
predict_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_accuracy": 0.8020527140897511,
|
| 3 |
+
"predict_f1": 0.6292738631020353,
|
| 4 |
+
"predict_loss": 1.8004062175750732,
|
| 5 |
+
"predict_precision": 0.5881466599698644,
|
| 6 |
+
"predict_recall": 0.676585295392171,
|
| 7 |
+
"predict_runtime": 5.922,
|
| 8 |
+
"predict_samples_per_second": 375.715,
|
| 9 |
+
"predict_steps_per_second": 5.91
|
| 10 |
+
}
|
predictions.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 120.0,
|
| 3 |
+
"train_loss": 0.10161643302465072,
|
| 4 |
+
"train_runtime": 6791.1484,
|
| 5 |
+
"train_samples": 7785,
|
| 6 |
+
"train_samples_per_second": 137.561,
|
| 7 |
+
"train_steps_per_second": 2.156
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1639 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6398059560706104,
|
| 3 |
+
"best_model_checkpoint": "/tmp/test-ner1_roberta/checkpoint-13786",
|
| 4 |
+
"epoch": 120.0,
|
| 5 |
+
"global_step": 14640,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_accuracy": 0.6466768621355329,
|
| 13 |
+
"eval_f1": 0.2566238574569015,
|
| 14 |
+
"eval_loss": 1.1791669130325317,
|
| 15 |
+
"eval_precision": 0.21529800038827412,
|
| 16 |
+
"eval_recall": 0.31758304696449025,
|
| 17 |
+
"eval_runtime": 2.9054,
|
| 18 |
+
"eval_samples_per_second": 382.73,
|
| 19 |
+
"eval_steps_per_second": 6.195,
|
| 20 |
+
"step": 122
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 2.0,
|
| 24 |
+
"eval_accuracy": 0.7298117181036428,
|
| 25 |
+
"eval_f1": 0.40685328185328185,
|
| 26 |
+
"eval_loss": 0.9055529236793518,
|
| 27 |
+
"eval_precision": 0.35154295246038364,
|
| 28 |
+
"eval_recall": 0.48281786941580757,
|
| 29 |
+
"eval_runtime": 2.852,
|
| 30 |
+
"eval_samples_per_second": 389.9,
|
| 31 |
+
"eval_steps_per_second": 6.311,
|
| 32 |
+
"step": 244
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 3.0,
|
| 36 |
+
"eval_accuracy": 0.7447037882016697,
|
| 37 |
+
"eval_f1": 0.4581746714162879,
|
| 38 |
+
"eval_loss": 0.8212449550628662,
|
| 39 |
+
"eval_precision": 0.401161540116154,
|
| 40 |
+
"eval_recall": 0.534077892325315,
|
| 41 |
+
"eval_runtime": 2.8628,
|
| 42 |
+
"eval_samples_per_second": 388.43,
|
| 43 |
+
"eval_steps_per_second": 6.288,
|
| 44 |
+
"step": 366
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.0,
|
| 48 |
+
"eval_accuracy": 0.7637576152631184,
|
| 49 |
+
"eval_f1": 0.48680641183723805,
|
| 50 |
+
"eval_loss": 0.7602469325065613,
|
| 51 |
+
"eval_precision": 0.4274577739281074,
|
| 52 |
+
"eval_recall": 0.5652920962199313,
|
| 53 |
+
"eval_runtime": 2.8995,
|
| 54 |
+
"eval_samples_per_second": 383.518,
|
| 55 |
+
"eval_steps_per_second": 6.208,
|
| 56 |
+
"step": 488
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.1,
|
| 60 |
+
"learning_rate": 2.8975409836065577e-05,
|
| 61 |
+
"loss": 1.0934,
|
| 62 |
+
"step": 500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 5.0,
|
| 66 |
+
"eval_accuracy": 0.7645849524907865,
|
| 67 |
+
"eval_f1": 0.49326599326599335,
|
| 68 |
+
"eval_loss": 0.7660626769065857,
|
| 69 |
+
"eval_precision": 0.42516583747927034,
|
| 70 |
+
"eval_recall": 0.5873424971363116,
|
| 71 |
+
"eval_runtime": 2.8913,
|
| 72 |
+
"eval_samples_per_second": 384.608,
|
| 73 |
+
"eval_steps_per_second": 6.226,
|
| 74 |
+
"step": 610
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 6.0,
|
| 78 |
+
"eval_accuracy": 0.7731090330182766,
|
| 79 |
+
"eval_f1": 0.5357728706624606,
|
| 80 |
+
"eval_loss": 0.7474268674850464,
|
| 81 |
+
"eval_precision": 0.47890818858560796,
|
| 82 |
+
"eval_recall": 0.6079610538373424,
|
| 83 |
+
"eval_runtime": 2.8539,
|
| 84 |
+
"eval_samples_per_second": 389.638,
|
| 85 |
+
"eval_steps_per_second": 6.307,
|
| 86 |
+
"step": 732
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 7.0,
|
| 90 |
+
"eval_accuracy": 0.7785494020608218,
|
| 91 |
+
"eval_f1": 0.5398138572905895,
|
| 92 |
+
"eval_loss": 0.7386994957923889,
|
| 93 |
+
"eval_precision": 0.49198868991517436,
|
| 94 |
+
"eval_recall": 0.5979381443298969,
|
| 95 |
+
"eval_runtime": 2.8557,
|
| 96 |
+
"eval_samples_per_second": 389.403,
|
| 97 |
+
"eval_steps_per_second": 6.303,
|
| 98 |
+
"step": 854
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 8.0,
|
| 102 |
+
"eval_accuracy": 0.7813573344698774,
|
| 103 |
+
"eval_f1": 0.547186587069732,
|
| 104 |
+
"eval_loss": 0.7481865882873535,
|
| 105 |
+
"eval_precision": 0.4916685688199041,
|
| 106 |
+
"eval_recall": 0.6168384879725086,
|
| 107 |
+
"eval_runtime": 2.8531,
|
| 108 |
+
"eval_samples_per_second": 389.752,
|
| 109 |
+
"eval_steps_per_second": 6.309,
|
| 110 |
+
"step": 976
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 8.2,
|
| 114 |
+
"learning_rate": 2.795081967213115e-05,
|
| 115 |
+
"loss": 0.5404,
|
| 116 |
+
"step": 1000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 9.0,
|
| 120 |
+
"eval_accuracy": 0.7782234813347707,
|
| 121 |
+
"eval_f1": 0.5538539425389192,
|
| 122 |
+
"eval_loss": 0.7774013876914978,
|
| 123 |
+
"eval_precision": 0.4962576547970061,
|
| 124 |
+
"eval_recall": 0.6265750286368843,
|
| 125 |
+
"eval_runtime": 3.061,
|
| 126 |
+
"eval_samples_per_second": 363.279,
|
| 127 |
+
"eval_steps_per_second": 5.88,
|
| 128 |
+
"step": 1098
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 10.0,
|
| 132 |
+
"eval_accuracy": 0.7801790056910773,
|
| 133 |
+
"eval_f1": 0.5599486521181001,
|
| 134 |
+
"eval_loss": 0.7820373177528381,
|
| 135 |
+
"eval_precision": 0.5074453234062355,
|
| 136 |
+
"eval_recall": 0.6245704467353952,
|
| 137 |
+
"eval_runtime": 2.9062,
|
| 138 |
+
"eval_samples_per_second": 382.636,
|
| 139 |
+
"eval_steps_per_second": 6.194,
|
| 140 |
+
"step": 1220
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 11.0,
|
| 144 |
+
"eval_accuracy": 0.7816832551959285,
|
| 145 |
+
"eval_f1": 0.5656822810590632,
|
| 146 |
+
"eval_loss": 0.7769992351531982,
|
| 147 |
+
"eval_precision": 0.5091659028414299,
|
| 148 |
+
"eval_recall": 0.63631156930126,
|
| 149 |
+
"eval_runtime": 2.8301,
|
| 150 |
+
"eval_samples_per_second": 392.925,
|
| 151 |
+
"eval_steps_per_second": 6.36,
|
| 152 |
+
"step": 1342
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 12.0,
|
| 156 |
+
"eval_accuracy": 0.7849173916313585,
|
| 157 |
+
"eval_f1": 0.5781455214079328,
|
| 158 |
+
"eval_loss": 0.8044845461845398,
|
| 159 |
+
"eval_precision": 0.5339640950994663,
|
| 160 |
+
"eval_recall": 0.6302978235967927,
|
| 161 |
+
"eval_runtime": 2.9058,
|
| 162 |
+
"eval_samples_per_second": 382.688,
|
| 163 |
+
"eval_steps_per_second": 6.195,
|
| 164 |
+
"step": 1464
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 12.3,
|
| 168 |
+
"learning_rate": 2.6926229508196725e-05,
|
| 169 |
+
"loss": 0.3509,
|
| 170 |
+
"step": 1500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 13.0,
|
| 174 |
+
"eval_accuracy": 0.7871486950635546,
|
| 175 |
+
"eval_f1": 0.585631067961165,
|
| 176 |
+
"eval_loss": 0.8087980151176453,
|
| 177 |
+
"eval_precision": 0.5343727852586818,
|
| 178 |
+
"eval_recall": 0.647766323024055,
|
| 179 |
+
"eval_runtime": 2.8915,
|
| 180 |
+
"eval_samples_per_second": 384.581,
|
| 181 |
+
"eval_steps_per_second": 6.225,
|
| 182 |
+
"step": 1586
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 14.0,
|
| 186 |
+
"eval_accuracy": 0.7768195151302429,
|
| 187 |
+
"eval_f1": 0.565743073047859,
|
| 188 |
+
"eval_loss": 0.84703528881073,
|
| 189 |
+
"eval_precision": 0.5049460431654677,
|
| 190 |
+
"eval_recall": 0.643184421534937,
|
| 191 |
+
"eval_runtime": 2.8567,
|
| 192 |
+
"eval_samples_per_second": 389.267,
|
| 193 |
+
"eval_steps_per_second": 6.301,
|
| 194 |
+
"step": 1708
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 15.0,
|
| 198 |
+
"eval_accuracy": 0.7845914709053075,
|
| 199 |
+
"eval_f1": 0.5803108808290157,
|
| 200 |
+
"eval_loss": 0.835796058177948,
|
| 201 |
+
"eval_precision": 0.5298013245033113,
|
| 202 |
+
"eval_recall": 0.6414662084765178,
|
| 203 |
+
"eval_runtime": 2.9498,
|
| 204 |
+
"eval_samples_per_second": 376.98,
|
| 205 |
+
"eval_steps_per_second": 6.102,
|
| 206 |
+
"step": 1830
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 16.0,
|
| 210 |
+
"eval_accuracy": 0.7889287236442951,
|
| 211 |
+
"eval_f1": 0.5734914904589995,
|
| 212 |
+
"eval_loss": 0.8826290369033813,
|
| 213 |
+
"eval_precision": 0.5215759849906192,
|
| 214 |
+
"eval_recall": 0.6368843069873997,
|
| 215 |
+
"eval_runtime": 2.818,
|
| 216 |
+
"eval_samples_per_second": 394.606,
|
| 217 |
+
"eval_steps_per_second": 6.388,
|
| 218 |
+
"step": 1952
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 16.39,
|
| 222 |
+
"learning_rate": 2.5901639344262294e-05,
|
| 223 |
+
"loss": 0.2458,
|
| 224 |
+
"step": 2000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 17.0,
|
| 228 |
+
"eval_accuracy": 0.7903577606739037,
|
| 229 |
+
"eval_f1": 0.590254852766407,
|
| 230 |
+
"eval_loss": 0.8949980735778809,
|
| 231 |
+
"eval_precision": 0.5476598872825288,
|
| 232 |
+
"eval_recall": 0.6400343642611683,
|
| 233 |
+
"eval_runtime": 2.8918,
|
| 234 |
+
"eval_samples_per_second": 384.538,
|
| 235 |
+
"eval_steps_per_second": 6.225,
|
| 236 |
+
"step": 2074
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 18.0,
|
| 240 |
+
"eval_accuracy": 0.7900067691227718,
|
| 241 |
+
"eval_f1": 0.5787797732772896,
|
| 242 |
+
"eval_loss": 0.8845651745796204,
|
| 243 |
+
"eval_precision": 0.5212204634090388,
|
| 244 |
+
"eval_recall": 0.6506300114547537,
|
| 245 |
+
"eval_runtime": 2.8519,
|
| 246 |
+
"eval_samples_per_second": 389.916,
|
| 247 |
+
"eval_steps_per_second": 6.312,
|
| 248 |
+
"step": 2196
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 19.0,
|
| 252 |
+
"eval_accuracy": 0.7903577606739037,
|
| 253 |
+
"eval_f1": 0.5841648308928341,
|
| 254 |
+
"eval_loss": 0.88877934217453,
|
| 255 |
+
"eval_precision": 0.533491124260355,
|
| 256 |
+
"eval_recall": 0.645475372279496,
|
| 257 |
+
"eval_runtime": 2.9333,
|
| 258 |
+
"eval_samples_per_second": 379.09,
|
| 259 |
+
"eval_steps_per_second": 6.136,
|
| 260 |
+
"step": 2318
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 20.0,
|
| 264 |
+
"eval_accuracy": 0.7915360894527039,
|
| 265 |
+
"eval_f1": 0.5802566116784498,
|
| 266 |
+
"eval_loss": 0.893390953540802,
|
| 267 |
+
"eval_precision": 0.5344910757356488,
|
| 268 |
+
"eval_recall": 0.6345933562428407,
|
| 269 |
+
"eval_runtime": 2.8278,
|
| 270 |
+
"eval_samples_per_second": 393.243,
|
| 271 |
+
"eval_steps_per_second": 6.365,
|
| 272 |
+
"step": 2440
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 20.49,
|
| 276 |
+
"learning_rate": 2.487704918032787e-05,
|
| 277 |
+
"loss": 0.1765,
|
| 278 |
+
"step": 2500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 21.0,
|
| 282 |
+
"eval_accuracy": 0.7933411888585253,
|
| 283 |
+
"eval_f1": 0.5913089142707102,
|
| 284 |
+
"eval_loss": 0.9481694102287292,
|
| 285 |
+
"eval_precision": 0.545939393939394,
|
| 286 |
+
"eval_recall": 0.6449026345933563,
|
| 287 |
+
"eval_runtime": 2.8849,
|
| 288 |
+
"eval_samples_per_second": 385.458,
|
| 289 |
+
"eval_steps_per_second": 6.239,
|
| 290 |
+
"step": 2562
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 22.0,
|
| 294 |
+
"eval_accuracy": 0.7958984130167723,
|
| 295 |
+
"eval_f1": 0.5927963326784546,
|
| 296 |
+
"eval_loss": 0.9498738646507263,
|
| 297 |
+
"eval_precision": 0.5462225440502052,
|
| 298 |
+
"eval_recall": 0.6480526918671249,
|
| 299 |
+
"eval_runtime": 2.8695,
|
| 300 |
+
"eval_samples_per_second": 387.521,
|
| 301 |
+
"eval_steps_per_second": 6.273,
|
| 302 |
+
"step": 2684
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 23.0,
|
| 306 |
+
"eval_accuracy": 0.7868729159876652,
|
| 307 |
+
"eval_f1": 0.5899986735641332,
|
| 308 |
+
"eval_loss": 0.9826343059539795,
|
| 309 |
+
"eval_precision": 0.5495428712626637,
|
| 310 |
+
"eval_recall": 0.6368843069873997,
|
| 311 |
+
"eval_runtime": 2.8977,
|
| 312 |
+
"eval_samples_per_second": 383.754,
|
| 313 |
+
"eval_steps_per_second": 6.212,
|
| 314 |
+
"step": 2806
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 24.0,
|
| 318 |
+
"eval_accuracy": 0.7972522375711385,
|
| 319 |
+
"eval_f1": 0.607061350516848,
|
| 320 |
+
"eval_loss": 0.9814818501472473,
|
| 321 |
+
"eval_precision": 0.5713924690422036,
|
| 322 |
+
"eval_recall": 0.6474799541809851,
|
| 323 |
+
"eval_runtime": 2.8607,
|
| 324 |
+
"eval_samples_per_second": 388.722,
|
| 325 |
+
"eval_steps_per_second": 6.292,
|
| 326 |
+
"step": 2928
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 24.59,
|
| 330 |
+
"learning_rate": 2.3852459016393442e-05,
|
| 331 |
+
"loss": 0.1273,
|
| 332 |
+
"step": 3000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 25.0,
|
| 336 |
+
"eval_accuracy": 0.7970516709704917,
|
| 337 |
+
"eval_f1": 0.6025760191209667,
|
| 338 |
+
"eval_loss": 1.007980227470398,
|
| 339 |
+
"eval_precision": 0.5617727160188165,
|
| 340 |
+
"eval_recall": 0.6497709049255441,
|
| 341 |
+
"eval_runtime": 2.9873,
|
| 342 |
+
"eval_samples_per_second": 372.236,
|
| 343 |
+
"eval_steps_per_second": 6.025,
|
| 344 |
+
"step": 3050
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 26.0,
|
| 348 |
+
"eval_accuracy": 0.7940431719607892,
|
| 349 |
+
"eval_f1": 0.5959833072509129,
|
| 350 |
+
"eval_loss": 1.0463485717773438,
|
| 351 |
+
"eval_precision": 0.5471743295019157,
|
| 352 |
+
"eval_recall": 0.6543528064146621,
|
| 353 |
+
"eval_runtime": 2.8597,
|
| 354 |
+
"eval_samples_per_second": 388.851,
|
| 355 |
+
"eval_steps_per_second": 6.294,
|
| 356 |
+
"step": 3172
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 27.0,
|
| 360 |
+
"eval_accuracy": 0.7965753252939555,
|
| 361 |
+
"eval_f1": 0.5990990990990992,
|
| 362 |
+
"eval_loss": 1.0348948240280151,
|
| 363 |
+
"eval_precision": 0.5574457593688363,
|
| 364 |
+
"eval_recall": 0.6474799541809851,
|
| 365 |
+
"eval_runtime": 2.8692,
|
| 366 |
+
"eval_samples_per_second": 387.57,
|
| 367 |
+
"eval_steps_per_second": 6.274,
|
| 368 |
+
"step": 3294
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 28.0,
|
| 372 |
+
"eval_accuracy": 0.7898312733472058,
|
| 373 |
+
"eval_f1": 0.596569333507922,
|
| 374 |
+
"eval_loss": 1.0559194087982178,
|
| 375 |
+
"eval_precision": 0.549577804583836,
|
| 376 |
+
"eval_recall": 0.652348224513173,
|
| 377 |
+
"eval_runtime": 2.8607,
|
| 378 |
+
"eval_samples_per_second": 388.718,
|
| 379 |
+
"eval_steps_per_second": 6.292,
|
| 380 |
+
"step": 3416
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 28.69,
|
| 384 |
+
"learning_rate": 2.2827868852459018e-05,
|
| 385 |
+
"loss": 0.0951,
|
| 386 |
+
"step": 3500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 29.0,
|
| 390 |
+
"eval_accuracy": 0.7917867977035125,
|
| 391 |
+
"eval_f1": 0.592843201040989,
|
| 392 |
+
"eval_loss": 1.0900899171829224,
|
| 393 |
+
"eval_precision": 0.5432864297638922,
|
| 394 |
+
"eval_recall": 0.652348224513173,
|
| 395 |
+
"eval_runtime": 2.9162,
|
| 396 |
+
"eval_samples_per_second": 381.323,
|
| 397 |
+
"eval_steps_per_second": 6.173,
|
| 398 |
+
"step": 3538
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 30.0,
|
| 402 |
+
"eval_accuracy": 0.7840649835786095,
|
| 403 |
+
"eval_f1": 0.5850218004616569,
|
| 404 |
+
"eval_loss": 1.1399974822998047,
|
| 405 |
+
"eval_precision": 0.5297259637714816,
|
| 406 |
+
"eval_recall": 0.6532073310423826,
|
| 407 |
+
"eval_runtime": 2.8324,
|
| 408 |
+
"eval_samples_per_second": 392.593,
|
| 409 |
+
"eval_steps_per_second": 6.355,
|
| 410 |
+
"step": 3660
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 31.0,
|
| 414 |
+
"eval_accuracy": 0.7916113019279465,
|
| 415 |
+
"eval_f1": 0.59593375521745,
|
| 416 |
+
"eval_loss": 1.1601282358169556,
|
| 417 |
+
"eval_precision": 0.5623888182973317,
|
| 418 |
+
"eval_recall": 0.6337342497136311,
|
| 419 |
+
"eval_runtime": 2.8109,
|
| 420 |
+
"eval_samples_per_second": 395.6,
|
| 421 |
+
"eval_steps_per_second": 6.404,
|
| 422 |
+
"step": 3782
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 32.0,
|
| 426 |
+
"eval_accuracy": 0.7882768821921929,
|
| 427 |
+
"eval_f1": 0.5970422719539328,
|
| 428 |
+
"eval_loss": 1.135899305343628,
|
| 429 |
+
"eval_precision": 0.549771029163654,
|
| 430 |
+
"eval_recall": 0.6532073310423826,
|
| 431 |
+
"eval_runtime": 2.8146,
|
| 432 |
+
"eval_samples_per_second": 395.088,
|
| 433 |
+
"eval_steps_per_second": 6.395,
|
| 434 |
+
"step": 3904
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 32.79,
|
| 438 |
+
"learning_rate": 2.180327868852459e-05,
|
| 439 |
+
"loss": 0.0717,
|
| 440 |
+
"step": 4000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 33.0,
|
| 444 |
+
"eval_accuracy": 0.7965001128187129,
|
| 445 |
+
"eval_f1": 0.6057882912647021,
|
| 446 |
+
"eval_loss": 1.1268887519836426,
|
| 447 |
+
"eval_precision": 0.5624539877300614,
|
| 448 |
+
"eval_recall": 0.6563573883161512,
|
| 449 |
+
"eval_runtime": 2.8737,
|
| 450 |
+
"eval_samples_per_second": 386.952,
|
| 451 |
+
"eval_steps_per_second": 6.264,
|
| 452 |
+
"step": 4026
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 34.0,
|
| 456 |
+
"eval_accuracy": 0.7966756085942789,
|
| 457 |
+
"eval_f1": 0.6037027099543869,
|
| 458 |
+
"eval_loss": 1.1757946014404297,
|
| 459 |
+
"eval_precision": 0.5678950025239778,
|
| 460 |
+
"eval_recall": 0.6443298969072165,
|
| 461 |
+
"eval_runtime": 2.8674,
|
| 462 |
+
"eval_samples_per_second": 387.814,
|
| 463 |
+
"eval_steps_per_second": 6.278,
|
| 464 |
+
"step": 4148
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 35.0,
|
| 468 |
+
"eval_accuracy": 0.7897811316970441,
|
| 469 |
+
"eval_f1": 0.5957000524383849,
|
| 470 |
+
"eval_loss": 1.1870158910751343,
|
| 471 |
+
"eval_precision": 0.5493230174081238,
|
| 472 |
+
"eval_recall": 0.6506300114547537,
|
| 473 |
+
"eval_runtime": 2.9346,
|
| 474 |
+
"eval_samples_per_second": 378.932,
|
| 475 |
+
"eval_steps_per_second": 6.134,
|
| 476 |
+
"step": 4270
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 36.0,
|
| 480 |
+
"eval_accuracy": 0.7928397723569083,
|
| 481 |
+
"eval_f1": 0.5987710811870832,
|
| 482 |
+
"eval_loss": 1.129560947418213,
|
| 483 |
+
"eval_precision": 0.5508780370459466,
|
| 484 |
+
"eval_recall": 0.6557846506300115,
|
| 485 |
+
"eval_runtime": 2.9245,
|
| 486 |
+
"eval_samples_per_second": 380.236,
|
| 487 |
+
"eval_steps_per_second": 6.155,
|
| 488 |
+
"step": 4392
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 36.89,
|
| 492 |
+
"learning_rate": 2.0778688524590166e-05,
|
| 493 |
+
"loss": 0.0552,
|
| 494 |
+
"step": 4500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 37.0,
|
| 498 |
+
"eval_accuracy": 0.790307619023742,
|
| 499 |
+
"eval_f1": 0.5933980582524273,
|
| 500 |
+
"eval_loss": 1.2164160013198853,
|
| 501 |
+
"eval_precision": 0.5414599574769667,
|
| 502 |
+
"eval_recall": 0.6563573883161512,
|
| 503 |
+
"eval_runtime": 2.8667,
|
| 504 |
+
"eval_samples_per_second": 387.897,
|
| 505 |
+
"eval_steps_per_second": 6.279,
|
| 506 |
+
"step": 4514
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 38.0,
|
| 510 |
+
"eval_accuracy": 0.7943440218617595,
|
| 511 |
+
"eval_f1": 0.6001566988769914,
|
| 512 |
+
"eval_loss": 1.2046586275100708,
|
| 513 |
+
"eval_precision": 0.5516082573211714,
|
| 514 |
+
"eval_recall": 0.6580756013745704,
|
| 515 |
+
"eval_runtime": 2.8635,
|
| 516 |
+
"eval_samples_per_second": 388.332,
|
| 517 |
+
"eval_steps_per_second": 6.286,
|
| 518 |
+
"step": 4636
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 39.0,
|
| 522 |
+
"eval_accuracy": 0.7949206508386191,
|
| 523 |
+
"eval_f1": 0.6084432717678101,
|
| 524 |
+
"eval_loss": 1.2363812923431396,
|
| 525 |
+
"eval_precision": 0.5640900195694716,
|
| 526 |
+
"eval_recall": 0.6603665521191294,
|
| 527 |
+
"eval_runtime": 2.8842,
|
| 528 |
+
"eval_samples_per_second": 385.555,
|
| 529 |
+
"eval_steps_per_second": 6.241,
|
| 530 |
+
"step": 4758
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 40.0,
|
| 534 |
+
"eval_accuracy": 0.7944693759871637,
|
| 535 |
+
"eval_f1": 0.6042486231313926,
|
| 536 |
+
"eval_loss": 1.248107671737671,
|
| 537 |
+
"eval_precision": 0.5573294629898403,
|
| 538 |
+
"eval_recall": 0.6597938144329897,
|
| 539 |
+
"eval_runtime": 2.9808,
|
| 540 |
+
"eval_samples_per_second": 373.05,
|
| 541 |
+
"eval_steps_per_second": 6.039,
|
| 542 |
+
"step": 4880
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 40.98,
|
| 546 |
+
"learning_rate": 1.975409836065574e-05,
|
| 547 |
+
"loss": 0.0432,
|
| 548 |
+
"step": 5000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 41.0,
|
| 552 |
+
"eval_accuracy": 0.7926141349311806,
|
| 553 |
+
"eval_f1": 0.6043454935622318,
|
| 554 |
+
"eval_loss": 1.276792287826538,
|
| 555 |
+
"eval_precision": 0.5683652875882946,
|
| 556 |
+
"eval_recall": 0.6451890034364262,
|
| 557 |
+
"eval_runtime": 2.8846,
|
| 558 |
+
"eval_samples_per_second": 385.494,
|
| 559 |
+
"eval_steps_per_second": 6.24,
|
| 560 |
+
"step": 5002
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 42.0,
|
| 564 |
+
"eval_accuracy": 0.7957981297164489,
|
| 565 |
+
"eval_f1": 0.6079725448785638,
|
| 566 |
+
"eval_loss": 1.2605416774749756,
|
| 567 |
+
"eval_precision": 0.5639079333986288,
|
| 568 |
+
"eval_recall": 0.6595074455899198,
|
| 569 |
+
"eval_runtime": 2.8333,
|
| 570 |
+
"eval_samples_per_second": 392.474,
|
| 571 |
+
"eval_steps_per_second": 6.353,
|
| 572 |
+
"step": 5124
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 43.0,
|
| 576 |
+
"eval_accuracy": 0.7974528041717853,
|
| 577 |
+
"eval_f1": 0.6125862984599043,
|
| 578 |
+
"eval_loss": 1.249541163444519,
|
| 579 |
+
"eval_precision": 0.571039603960396,
|
| 580 |
+
"eval_recall": 0.6606529209621993,
|
| 581 |
+
"eval_runtime": 2.8379,
|
| 582 |
+
"eval_samples_per_second": 391.839,
|
| 583 |
+
"eval_steps_per_second": 6.343,
|
| 584 |
+
"step": 5246
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 44.0,
|
| 588 |
+
"eval_accuracy": 0.7954722089903978,
|
| 589 |
+
"eval_f1": 0.6102653913512056,
|
| 590 |
+
"eval_loss": 1.2717816829681396,
|
| 591 |
+
"eval_precision": 0.5761892648181124,
|
| 592 |
+
"eval_recall": 0.6486254295532646,
|
| 593 |
+
"eval_runtime": 2.8387,
|
| 594 |
+
"eval_samples_per_second": 391.732,
|
| 595 |
+
"eval_steps_per_second": 6.341,
|
| 596 |
+
"step": 5368
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 45.0,
|
| 600 |
+
"eval_accuracy": 0.8003108782310026,
|
| 601 |
+
"eval_f1": 0.6093247588424437,
|
| 602 |
+
"eval_loss": 1.2998257875442505,
|
| 603 |
+
"eval_precision": 0.5725075528700906,
|
| 604 |
+
"eval_recall": 0.6512027491408935,
|
| 605 |
+
"eval_runtime": 2.8997,
|
| 606 |
+
"eval_samples_per_second": 383.49,
|
| 607 |
+
"eval_steps_per_second": 6.208,
|
| 608 |
+
"step": 5490
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 45.08,
|
| 612 |
+
"learning_rate": 1.872950819672131e-05,
|
| 613 |
+
"loss": 0.0331,
|
| 614 |
+
"step": 5500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 46.0,
|
| 618 |
+
"eval_accuracy": 0.7945696592874871,
|
| 619 |
+
"eval_f1": 0.6008263361322138,
|
| 620 |
+
"eval_loss": 1.3468672037124634,
|
| 621 |
+
"eval_precision": 0.5619546247818499,
|
| 622 |
+
"eval_recall": 0.645475372279496,
|
| 623 |
+
"eval_runtime": 2.896,
|
| 624 |
+
"eval_samples_per_second": 383.974,
|
| 625 |
+
"eval_steps_per_second": 6.215,
|
| 626 |
+
"step": 5612
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 47.0,
|
| 630 |
+
"eval_accuracy": 0.8010128613332664,
|
| 631 |
+
"eval_f1": 0.6131348045732518,
|
| 632 |
+
"eval_loss": 1.3357452154159546,
|
| 633 |
+
"eval_precision": 0.5722084367245658,
|
| 634 |
+
"eval_recall": 0.6603665521191294,
|
| 635 |
+
"eval_runtime": 2.8883,
|
| 636 |
+
"eval_samples_per_second": 384.996,
|
| 637 |
+
"eval_steps_per_second": 6.232,
|
| 638 |
+
"step": 5734
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 48.0,
|
| 642 |
+
"eval_accuracy": 0.7936420387594956,
|
| 643 |
+
"eval_f1": 0.6039968445963714,
|
| 644 |
+
"eval_loss": 1.3576422929763794,
|
| 645 |
+
"eval_precision": 0.5583373845405931,
|
| 646 |
+
"eval_recall": 0.6577892325315006,
|
| 647 |
+
"eval_runtime": 2.8265,
|
| 648 |
+
"eval_samples_per_second": 393.421,
|
| 649 |
+
"eval_steps_per_second": 6.368,
|
| 650 |
+
"step": 5856
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 49.0,
|
| 654 |
+
"eval_accuracy": 0.7985057788251811,
|
| 655 |
+
"eval_f1": 0.6147880732718278,
|
| 656 |
+
"eval_loss": 1.3396836519241333,
|
| 657 |
+
"eval_precision": 0.5766240280912968,
|
| 658 |
+
"eval_recall": 0.6583619702176403,
|
| 659 |
+
"eval_runtime": 2.908,
|
| 660 |
+
"eval_samples_per_second": 382.397,
|
| 661 |
+
"eval_steps_per_second": 6.19,
|
| 662 |
+
"step": 5978
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 49.18,
|
| 666 |
+
"learning_rate": 1.7704918032786887e-05,
|
| 667 |
+
"loss": 0.0265,
|
| 668 |
+
"step": 6000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 50.0,
|
| 672 |
+
"eval_accuracy": 0.7961240504425,
|
| 673 |
+
"eval_f1": 0.6078405315614618,
|
| 674 |
+
"eval_loss": 1.3641352653503418,
|
| 675 |
+
"eval_precision": 0.5670716588147781,
|
| 676 |
+
"eval_recall": 0.6549255441008018,
|
| 677 |
+
"eval_runtime": 2.9731,
|
| 678 |
+
"eval_samples_per_second": 374.026,
|
| 679 |
+
"eval_steps_per_second": 6.054,
|
| 680 |
+
"step": 6100
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 51.0,
|
| 684 |
+
"eval_accuracy": 0.7937924637099807,
|
| 685 |
+
"eval_f1": 0.6058036305816881,
|
| 686 |
+
"eval_loss": 1.3726739883422852,
|
| 687 |
+
"eval_precision": 0.5637484586929716,
|
| 688 |
+
"eval_recall": 0.654639175257732,
|
| 689 |
+
"eval_runtime": 2.8737,
|
| 690 |
+
"eval_samples_per_second": 386.957,
|
| 691 |
+
"eval_steps_per_second": 6.264,
|
| 692 |
+
"step": 6222
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 52.0,
|
| 696 |
+
"eval_accuracy": 0.7926642765813423,
|
| 697 |
+
"eval_f1": 0.6081809811916349,
|
| 698 |
+
"eval_loss": 1.4024547338485718,
|
| 699 |
+
"eval_precision": 0.5623935782048164,
|
| 700 |
+
"eval_recall": 0.6620847651775487,
|
| 701 |
+
"eval_runtime": 2.8503,
|
| 702 |
+
"eval_samples_per_second": 390.136,
|
| 703 |
+
"eval_steps_per_second": 6.315,
|
| 704 |
+
"step": 6344
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 53.0,
|
| 708 |
+
"eval_accuracy": 0.7915862311028656,
|
| 709 |
+
"eval_f1": 0.6084185367149118,
|
| 710 |
+
"eval_loss": 1.399110198020935,
|
| 711 |
+
"eval_precision": 0.5672196088140629,
|
| 712 |
+
"eval_recall": 0.6560710194730813,
|
| 713 |
+
"eval_runtime": 2.9033,
|
| 714 |
+
"eval_samples_per_second": 383.006,
|
| 715 |
+
"eval_steps_per_second": 6.2,
|
| 716 |
+
"step": 6466
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 53.28,
|
| 720 |
+
"learning_rate": 1.668032786885246e-05,
|
| 721 |
+
"loss": 0.0212,
|
| 722 |
+
"step": 6500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 54.0,
|
| 726 |
+
"eval_accuracy": 0.7953217840399127,
|
| 727 |
+
"eval_f1": 0.6119815668202765,
|
| 728 |
+
"eval_loss": 1.4267858266830444,
|
| 729 |
+
"eval_precision": 0.5664148184255423,
|
| 730 |
+
"eval_recall": 0.6655211912943871,
|
| 731 |
+
"eval_runtime": 2.9191,
|
| 732 |
+
"eval_samples_per_second": 380.935,
|
| 733 |
+
"eval_steps_per_second": 6.166,
|
| 734 |
+
"step": 6588
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 55.0,
|
| 738 |
+
"eval_accuracy": 0.7943690926868403,
|
| 739 |
+
"eval_f1": 0.6073173953242637,
|
| 740 |
+
"eval_loss": 1.4376713037490845,
|
| 741 |
+
"eval_precision": 0.5636185339544005,
|
| 742 |
+
"eval_recall": 0.6583619702176403,
|
| 743 |
+
"eval_runtime": 3.0593,
|
| 744 |
+
"eval_samples_per_second": 363.477,
|
| 745 |
+
"eval_steps_per_second": 5.884,
|
| 746 |
+
"step": 6710
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 56.0,
|
| 750 |
+
"eval_accuracy": 0.795271642389751,
|
| 751 |
+
"eval_f1": 0.6113687557970054,
|
| 752 |
+
"eval_loss": 1.4307470321655273,
|
| 753 |
+
"eval_precision": 0.5689272503082614,
|
| 754 |
+
"eval_recall": 0.6606529209621993,
|
| 755 |
+
"eval_runtime": 2.9231,
|
| 756 |
+
"eval_samples_per_second": 380.418,
|
| 757 |
+
"eval_steps_per_second": 6.158,
|
| 758 |
+
"step": 6832
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 57.0,
|
| 762 |
+
"eval_accuracy": 0.7917115852282699,
|
| 763 |
+
"eval_f1": 0.6049250535331906,
|
| 764 |
+
"eval_loss": 1.4772576093673706,
|
| 765 |
+
"eval_precision": 0.5678391959798995,
|
| 766 |
+
"eval_recall": 0.6471935853379153,
|
| 767 |
+
"eval_runtime": 2.9801,
|
| 768 |
+
"eval_samples_per_second": 373.136,
|
| 769 |
+
"eval_steps_per_second": 6.04,
|
| 770 |
+
"step": 6954
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 57.38,
|
| 774 |
+
"learning_rate": 1.5655737704918035e-05,
|
| 775 |
+
"loss": 0.0171,
|
| 776 |
+
"step": 7000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 58.0,
|
| 780 |
+
"eval_accuracy": 0.7976032291222704,
|
| 781 |
+
"eval_f1": 0.6215258855585831,
|
| 782 |
+
"eval_loss": 1.46255362033844,
|
| 783 |
+
"eval_precision": 0.5927754677754677,
|
| 784 |
+
"eval_recall": 0.6532073310423826,
|
| 785 |
+
"eval_runtime": 2.8727,
|
| 786 |
+
"eval_samples_per_second": 387.093,
|
| 787 |
+
"eval_steps_per_second": 6.266,
|
| 788 |
+
"step": 7076
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 59.0,
|
| 792 |
+
"eval_accuracy": 0.7991074786271216,
|
| 793 |
+
"eval_f1": 0.6118965057348627,
|
| 794 |
+
"eval_loss": 1.4488873481750488,
|
| 795 |
+
"eval_precision": 0.5726410384423365,
|
| 796 |
+
"eval_recall": 0.656930126002291,
|
| 797 |
+
"eval_runtime": 2.9083,
|
| 798 |
+
"eval_samples_per_second": 382.356,
|
| 799 |
+
"eval_steps_per_second": 6.189,
|
| 800 |
+
"step": 7198
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 60.0,
|
| 804 |
+
"eval_accuracy": 0.8010379321583473,
|
| 805 |
+
"eval_f1": 0.6189835977413283,
|
| 806 |
+
"eval_loss": 1.447924017906189,
|
| 807 |
+
"eval_precision": 0.5833755701976685,
|
| 808 |
+
"eval_recall": 0.6592210767468499,
|
| 809 |
+
"eval_runtime": 2.8818,
|
| 810 |
+
"eval_samples_per_second": 385.865,
|
| 811 |
+
"eval_steps_per_second": 6.246,
|
| 812 |
+
"step": 7320
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 61.0,
|
| 816 |
+
"eval_accuracy": 0.7975530874721087,
|
| 817 |
+
"eval_f1": 0.6155924875016889,
|
| 818 |
+
"eval_loss": 1.464934229850769,
|
| 819 |
+
"eval_precision": 0.5827577385520594,
|
| 820 |
+
"eval_recall": 0.652348224513173,
|
| 821 |
+
"eval_runtime": 3.0162,
|
| 822 |
+
"eval_samples_per_second": 368.671,
|
| 823 |
+
"eval_steps_per_second": 5.968,
|
| 824 |
+
"step": 7442
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 61.48,
|
| 828 |
+
"learning_rate": 1.4631147540983607e-05,
|
| 829 |
+
"loss": 0.0142,
|
| 830 |
+
"step": 7500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 62.0,
|
| 834 |
+
"eval_accuracy": 0.8005866573068919,
|
| 835 |
+
"eval_f1": 0.617394747261449,
|
| 836 |
+
"eval_loss": 1.5170141458511353,
|
| 837 |
+
"eval_precision": 0.5725826193390453,
|
| 838 |
+
"eval_recall": 0.6698167239404352,
|
| 839 |
+
"eval_runtime": 2.8537,
|
| 840 |
+
"eval_samples_per_second": 389.666,
|
| 841 |
+
"eval_steps_per_second": 6.308,
|
| 842 |
+
"step": 7564
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 63.0,
|
| 846 |
+
"eval_accuracy": 0.798530849650262,
|
| 847 |
+
"eval_f1": 0.6186992951190318,
|
| 848 |
+
"eval_loss": 1.486588478088379,
|
| 849 |
+
"eval_precision": 0.5776011919543084,
|
| 850 |
+
"eval_recall": 0.6660939289805269,
|
| 851 |
+
"eval_runtime": 2.9317,
|
| 852 |
+
"eval_samples_per_second": 379.306,
|
| 853 |
+
"eval_steps_per_second": 6.14,
|
| 854 |
+
"step": 7686
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 64.0,
|
| 858 |
+
"eval_accuracy": 0.8009877905081856,
|
| 859 |
+
"eval_f1": 0.6169074371321562,
|
| 860 |
+
"eval_loss": 1.544573426246643,
|
| 861 |
+
"eval_precision": 0.5788152610441767,
|
| 862 |
+
"eval_recall": 0.6603665521191294,
|
| 863 |
+
"eval_runtime": 2.9763,
|
| 864 |
+
"eval_samples_per_second": 373.624,
|
| 865 |
+
"eval_steps_per_second": 6.048,
|
| 866 |
+
"step": 7808
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 65.0,
|
| 870 |
+
"eval_accuracy": 0.7935166846340913,
|
| 871 |
+
"eval_f1": 0.6111037498343711,
|
| 872 |
+
"eval_loss": 1.5565959215164185,
|
| 873 |
+
"eval_precision": 0.5686806411837237,
|
| 874 |
+
"eval_recall": 0.6603665521191294,
|
| 875 |
+
"eval_runtime": 2.8561,
|
| 876 |
+
"eval_samples_per_second": 389.345,
|
| 877 |
+
"eval_steps_per_second": 6.302,
|
| 878 |
+
"step": 7930
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 65.57,
|
| 882 |
+
"learning_rate": 1.3606557377049181e-05,
|
| 883 |
+
"loss": 0.0114,
|
| 884 |
+
"step": 8000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 66.0,
|
| 888 |
+
"eval_accuracy": 0.795948554666934,
|
| 889 |
+
"eval_f1": 0.6242587601078167,
|
| 890 |
+
"eval_loss": 1.5454256534576416,
|
| 891 |
+
"eval_precision": 0.5896130346232179,
|
| 892 |
+
"eval_recall": 0.6632302405498282,
|
| 893 |
+
"eval_runtime": 2.9632,
|
| 894 |
+
"eval_samples_per_second": 375.274,
|
| 895 |
+
"eval_steps_per_second": 6.075,
|
| 896 |
+
"step": 8052
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 67.0,
|
| 900 |
+
"eval_accuracy": 0.7998345325544663,
|
| 901 |
+
"eval_f1": 0.6325366648560564,
|
| 902 |
+
"eval_loss": 1.5341241359710693,
|
| 903 |
+
"eval_precision": 0.6014979338842975,
|
| 904 |
+
"eval_recall": 0.6669530355097365,
|
| 905 |
+
"eval_runtime": 2.8476,
|
| 906 |
+
"eval_samples_per_second": 390.501,
|
| 907 |
+
"eval_steps_per_second": 6.321,
|
| 908 |
+
"step": 8174
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 68.0,
|
| 912 |
+
"eval_accuracy": 0.7963246170431469,
|
| 913 |
+
"eval_f1": 0.6196650459211237,
|
| 914 |
+
"eval_loss": 1.5298110246658325,
|
| 915 |
+
"eval_precision": 0.58640081799591,
|
| 916 |
+
"eval_recall": 0.656930126002291,
|
| 917 |
+
"eval_runtime": 2.9457,
|
| 918 |
+
"eval_samples_per_second": 377.495,
|
| 919 |
+
"eval_steps_per_second": 6.111,
|
| 920 |
+
"step": 8296
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 69.0,
|
| 924 |
+
"eval_accuracy": 0.7943941635119212,
|
| 925 |
+
"eval_f1": 0.617556946849607,
|
| 926 |
+
"eval_loss": 1.5693646669387817,
|
| 927 |
+
"eval_precision": 0.57733499377335,
|
| 928 |
+
"eval_recall": 0.6638029782359679,
|
| 929 |
+
"eval_runtime": 2.8694,
|
| 930 |
+
"eval_samples_per_second": 387.533,
|
| 931 |
+
"eval_steps_per_second": 6.273,
|
| 932 |
+
"step": 8418
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 69.67,
|
| 936 |
+
"learning_rate": 1.2581967213114756e-05,
|
| 937 |
+
"loss": 0.0101,
|
| 938 |
+
"step": 8500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 70.0,
|
| 942 |
+
"eval_accuracy": 0.7977285832476747,
|
| 943 |
+
"eval_f1": 0.6197596795727636,
|
| 944 |
+
"eval_loss": 1.591435432434082,
|
| 945 |
+
"eval_precision": 0.5805402701350675,
|
| 946 |
+
"eval_recall": 0.6646620847651775,
|
| 947 |
+
"eval_runtime": 2.9323,
|
| 948 |
+
"eval_samples_per_second": 379.23,
|
| 949 |
+
"eval_steps_per_second": 6.139,
|
| 950 |
+
"step": 8540
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 71.0,
|
| 954 |
+
"eval_accuracy": 0.7956978464161255,
|
| 955 |
+
"eval_f1": 0.6129676474504061,
|
| 956 |
+
"eval_loss": 1.568572998046875,
|
| 957 |
+
"eval_precision": 0.5727792983329186,
|
| 958 |
+
"eval_recall": 0.6592210767468499,
|
| 959 |
+
"eval_runtime": 2.9544,
|
| 960 |
+
"eval_samples_per_second": 376.394,
|
| 961 |
+
"eval_steps_per_second": 6.093,
|
| 962 |
+
"step": 8662
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 72.0,
|
| 966 |
+
"eval_accuracy": 0.7949206508386191,
|
| 967 |
+
"eval_f1": 0.6126834381551364,
|
| 968 |
+
"eval_loss": 1.6199277639389038,
|
| 969 |
+
"eval_precision": 0.5647342995169082,
|
| 970 |
+
"eval_recall": 0.6695303550973654,
|
| 971 |
+
"eval_runtime": 2.9153,
|
| 972 |
+
"eval_samples_per_second": 381.436,
|
| 973 |
+
"eval_steps_per_second": 6.174,
|
| 974 |
+
"step": 8784
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 73.0,
|
| 978 |
+
"eval_accuracy": 0.7943941635119212,
|
| 979 |
+
"eval_f1": 0.623042954636692,
|
| 980 |
+
"eval_loss": 1.634416103363037,
|
| 981 |
+
"eval_precision": 0.584777694046722,
|
| 982 |
+
"eval_recall": 0.6666666666666666,
|
| 983 |
+
"eval_runtime": 2.8778,
|
| 984 |
+
"eval_samples_per_second": 386.41,
|
| 985 |
+
"eval_steps_per_second": 6.255,
|
| 986 |
+
"step": 8906
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 73.77,
|
| 990 |
+
"learning_rate": 1.1557377049180328e-05,
|
| 991 |
+
"loss": 0.0079,
|
| 992 |
+
"step": 9000
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 74.0,
|
| 996 |
+
"eval_accuracy": 0.7969513876701683,
|
| 997 |
+
"eval_f1": 0.6292225201072386,
|
| 998 |
+
"eval_loss": 1.557986855506897,
|
| 999 |
+
"eval_precision": 0.5914818548387096,
|
| 1000 |
+
"eval_recall": 0.6721076746849943,
|
| 1001 |
+
"eval_runtime": 2.8737,
|
| 1002 |
+
"eval_samples_per_second": 386.956,
|
| 1003 |
+
"eval_steps_per_second": 6.264,
|
| 1004 |
+
"step": 9028
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 75.0,
|
| 1008 |
+
"eval_accuracy": 0.8006117281319728,
|
| 1009 |
+
"eval_f1": 0.6340199154276359,
|
| 1010 |
+
"eval_loss": 1.6272269487380981,
|
| 1011 |
+
"eval_precision": 0.6053659807241469,
|
| 1012 |
+
"eval_recall": 0.6655211912943871,
|
| 1013 |
+
"eval_runtime": 2.8776,
|
| 1014 |
+
"eval_samples_per_second": 386.439,
|
| 1015 |
+
"eval_steps_per_second": 6.255,
|
| 1016 |
+
"step": 9150
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 76.0,
|
| 1020 |
+
"eval_accuracy": 0.7967758918946023,
|
| 1021 |
+
"eval_f1": 0.6184052357419527,
|
| 1022 |
+
"eval_loss": 1.6266722679138184,
|
| 1023 |
+
"eval_precision": 0.5794743429286608,
|
| 1024 |
+
"eval_recall": 0.6629438717067583,
|
| 1025 |
+
"eval_runtime": 2.9302,
|
| 1026 |
+
"eval_samples_per_second": 379.493,
|
| 1027 |
+
"eval_steps_per_second": 6.143,
|
| 1028 |
+
"step": 9272
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 77.0,
|
| 1032 |
+
"eval_accuracy": 0.7958984130167723,
|
| 1033 |
+
"eval_f1": 0.6194760518655729,
|
| 1034 |
+
"eval_loss": 1.6500694751739502,
|
| 1035 |
+
"eval_precision": 0.5757501229709788,
|
| 1036 |
+
"eval_recall": 0.670389461626575,
|
| 1037 |
+
"eval_runtime": 2.8781,
|
| 1038 |
+
"eval_samples_per_second": 386.368,
|
| 1039 |
+
"eval_steps_per_second": 6.254,
|
| 1040 |
+
"step": 9394
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 77.87,
|
| 1044 |
+
"learning_rate": 1.0532786885245902e-05,
|
| 1045 |
+
"loss": 0.0065,
|
| 1046 |
+
"step": 9500
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 78.0,
|
| 1050 |
+
"eval_accuracy": 0.7995336826534961,
|
| 1051 |
+
"eval_f1": 0.630329195898543,
|
| 1052 |
+
"eval_loss": 1.6222110986709595,
|
| 1053 |
+
"eval_precision": 0.5959183673469388,
|
| 1054 |
+
"eval_recall": 0.6689576174112256,
|
| 1055 |
+
"eval_runtime": 2.9051,
|
| 1056 |
+
"eval_samples_per_second": 382.773,
|
| 1057 |
+
"eval_steps_per_second": 6.196,
|
| 1058 |
+
"step": 9516
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 79.0,
|
| 1062 |
+
"eval_accuracy": 0.7965502544688746,
|
| 1063 |
+
"eval_f1": 0.6257701580498258,
|
| 1064 |
+
"eval_loss": 1.6543381214141846,
|
| 1065 |
+
"eval_precision": 0.587820835430297,
|
| 1066 |
+
"eval_recall": 0.6689576174112256,
|
| 1067 |
+
"eval_runtime": 2.9225,
|
| 1068 |
+
"eval_samples_per_second": 380.492,
|
| 1069 |
+
"eval_steps_per_second": 6.159,
|
| 1070 |
+
"step": 9638
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 80.0,
|
| 1074 |
+
"eval_accuracy": 0.8008875072078622,
|
| 1075 |
+
"eval_f1": 0.6276252019386107,
|
| 1076 |
+
"eval_loss": 1.605409026145935,
|
| 1077 |
+
"eval_precision": 0.5922256097560976,
|
| 1078 |
+
"eval_recall": 0.6675257731958762,
|
| 1079 |
+
"eval_runtime": 2.8935,
|
| 1080 |
+
"eval_samples_per_second": 384.305,
|
| 1081 |
+
"eval_steps_per_second": 6.221,
|
| 1082 |
+
"step": 9760
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 81.0,
|
| 1086 |
+
"eval_accuracy": 0.8007872239075388,
|
| 1087 |
+
"eval_f1": 0.6293103448275862,
|
| 1088 |
+
"eval_loss": 1.6386600732803345,
|
| 1089 |
+
"eval_precision": 0.5940996948118006,
|
| 1090 |
+
"eval_recall": 0.6689576174112256,
|
| 1091 |
+
"eval_runtime": 2.9359,
|
| 1092 |
+
"eval_samples_per_second": 378.763,
|
| 1093 |
+
"eval_steps_per_second": 6.131,
|
| 1094 |
+
"step": 9882
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 81.97,
|
| 1098 |
+
"learning_rate": 9.508196721311476e-06,
|
| 1099 |
+
"loss": 0.0053,
|
| 1100 |
+
"step": 10000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 82.0,
|
| 1104 |
+
"eval_accuracy": 0.8047233434452328,
|
| 1105 |
+
"eval_f1": 0.6390403489640131,
|
| 1106 |
+
"eval_loss": 1.6452571153640747,
|
| 1107 |
+
"eval_precision": 0.6097814776274714,
|
| 1108 |
+
"eval_recall": 0.6712485681557846,
|
| 1109 |
+
"eval_runtime": 2.9102,
|
| 1110 |
+
"eval_samples_per_second": 382.104,
|
| 1111 |
+
"eval_steps_per_second": 6.185,
|
| 1112 |
+
"step": 10004
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 83.0,
|
| 1116 |
+
"eval_accuracy": 0.8004613031814877,
|
| 1117 |
+
"eval_f1": 0.6212403513441574,
|
| 1118 |
+
"eval_loss": 1.679402232170105,
|
| 1119 |
+
"eval_precision": 0.5803083043262058,
|
| 1120 |
+
"eval_recall": 0.6683848797250859,
|
| 1121 |
+
"eval_runtime": 2.9425,
|
| 1122 |
+
"eval_samples_per_second": 377.908,
|
| 1123 |
+
"eval_steps_per_second": 6.117,
|
| 1124 |
+
"step": 10126
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 84.0,
|
| 1128 |
+
"eval_accuracy": 0.7990322661518791,
|
| 1129 |
+
"eval_f1": 0.6314366806325179,
|
| 1130 |
+
"eval_loss": 1.700645923614502,
|
| 1131 |
+
"eval_precision": 0.5979012029690299,
|
| 1132 |
+
"eval_recall": 0.6689576174112256,
|
| 1133 |
+
"eval_runtime": 2.8808,
|
| 1134 |
+
"eval_samples_per_second": 386.008,
|
| 1135 |
+
"eval_steps_per_second": 6.248,
|
| 1136 |
+
"step": 10248
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 85.0,
|
| 1140 |
+
"eval_accuracy": 0.7989069120264748,
|
| 1141 |
+
"eval_f1": 0.6296992481203008,
|
| 1142 |
+
"eval_loss": 1.682008147239685,
|
| 1143 |
+
"eval_precision": 0.5927704752275025,
|
| 1144 |
+
"eval_recall": 0.6715349369988545,
|
| 1145 |
+
"eval_runtime": 2.8543,
|
| 1146 |
+
"eval_samples_per_second": 389.584,
|
| 1147 |
+
"eval_steps_per_second": 6.306,
|
| 1148 |
+
"step": 10370
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 86.0,
|
| 1152 |
+
"eval_accuracy": 0.7983052122245343,
|
| 1153 |
+
"eval_f1": 0.6285100094048098,
|
| 1154 |
+
"eval_loss": 1.6995329856872559,
|
| 1155 |
+
"eval_precision": 0.5920020248038471,
|
| 1156 |
+
"eval_recall": 0.6698167239404352,
|
| 1157 |
+
"eval_runtime": 3.0037,
|
| 1158 |
+
"eval_samples_per_second": 370.211,
|
| 1159 |
+
"eval_steps_per_second": 5.993,
|
| 1160 |
+
"step": 10492
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 86.07,
|
| 1164 |
+
"learning_rate": 8.483606557377049e-06,
|
| 1165 |
+
"loss": 0.0045,
|
| 1166 |
+
"step": 10500
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 87.0,
|
| 1170 |
+
"eval_accuracy": 0.8004863740065685,
|
| 1171 |
+
"eval_f1": 0.6253886710828714,
|
| 1172 |
+
"eval_loss": 1.6652146577835083,
|
| 1173 |
+
"eval_precision": 0.5923175416133163,
|
| 1174 |
+
"eval_recall": 0.6623711340206185,
|
| 1175 |
+
"eval_runtime": 2.9086,
|
| 1176 |
+
"eval_samples_per_second": 382.312,
|
| 1177 |
+
"eval_steps_per_second": 6.189,
|
| 1178 |
+
"step": 10614
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 88.0,
|
| 1182 |
+
"eval_accuracy": 0.7990824078020408,
|
| 1183 |
+
"eval_f1": 0.6266846361185983,
|
| 1184 |
+
"eval_loss": 1.7196266651153564,
|
| 1185 |
+
"eval_precision": 0.5919042769857433,
|
| 1186 |
+
"eval_recall": 0.665807560137457,
|
| 1187 |
+
"eval_runtime": 2.8941,
|
| 1188 |
+
"eval_samples_per_second": 384.232,
|
| 1189 |
+
"eval_steps_per_second": 6.22,
|
| 1190 |
+
"step": 10736
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 89.0,
|
| 1194 |
+
"eval_accuracy": 0.805375184897335,
|
| 1195 |
+
"eval_f1": 0.6272862755724156,
|
| 1196 |
+
"eval_loss": 1.6730009317398071,
|
| 1197 |
+
"eval_precision": 0.5952687066083826,
|
| 1198 |
+
"eval_recall": 0.6629438717067583,
|
| 1199 |
+
"eval_runtime": 2.9839,
|
| 1200 |
+
"eval_samples_per_second": 372.672,
|
| 1201 |
+
"eval_steps_per_second": 6.032,
|
| 1202 |
+
"step": 10858
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 90.0,
|
| 1206 |
+
"eval_accuracy": 0.8023165442374709,
|
| 1207 |
+
"eval_f1": 0.6332482193253596,
|
| 1208 |
+
"eval_loss": 1.709200143814087,
|
| 1209 |
+
"eval_precision": 0.5966067358825019,
|
| 1210 |
+
"eval_recall": 0.6746849942726232,
|
| 1211 |
+
"eval_runtime": 2.9784,
|
| 1212 |
+
"eval_samples_per_second": 373.352,
|
| 1213 |
+
"eval_steps_per_second": 6.043,
|
| 1214 |
+
"step": 10980
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 90.16,
|
| 1218 |
+
"learning_rate": 7.459016393442623e-06,
|
| 1219 |
+
"loss": 0.0037,
|
| 1220 |
+
"step": 11000
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 91.0,
|
| 1224 |
+
"eval_accuracy": 0.8009627196831047,
|
| 1225 |
+
"eval_f1": 0.6340402392604676,
|
| 1226 |
+
"eval_loss": 1.7260353565216064,
|
| 1227 |
+
"eval_precision": 0.6035196687370601,
|
| 1228 |
+
"eval_recall": 0.6678121420389461,
|
| 1229 |
+
"eval_runtime": 2.8928,
|
| 1230 |
+
"eval_samples_per_second": 384.405,
|
| 1231 |
+
"eval_steps_per_second": 6.222,
|
| 1232 |
+
"step": 11102
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 92.0,
|
| 1236 |
+
"eval_accuracy": 0.8030185273397348,
|
| 1237 |
+
"eval_f1": 0.631593220338983,
|
| 1238 |
+
"eval_loss": 1.71060311794281,
|
| 1239 |
+
"eval_precision": 0.5997939737316508,
|
| 1240 |
+
"eval_recall": 0.6669530355097365,
|
| 1241 |
+
"eval_runtime": 2.9325,
|
| 1242 |
+
"eval_samples_per_second": 379.201,
|
| 1243 |
+
"eval_steps_per_second": 6.138,
|
| 1244 |
+
"step": 11224
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 93.0,
|
| 1248 |
+
"eval_accuracy": 0.8027928899140071,
|
| 1249 |
+
"eval_f1": 0.6377910124526259,
|
| 1250 |
+
"eval_loss": 1.709562063217163,
|
| 1251 |
+
"eval_precision": 0.6047227926078029,
|
| 1252 |
+
"eval_recall": 0.6746849942726232,
|
| 1253 |
+
"eval_runtime": 2.929,
|
| 1254 |
+
"eval_samples_per_second": 379.651,
|
| 1255 |
+
"eval_steps_per_second": 6.145,
|
| 1256 |
+
"step": 11346
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 94.0,
|
| 1260 |
+
"eval_accuracy": 0.8009627196831047,
|
| 1261 |
+
"eval_f1": 0.6353984679478566,
|
| 1262 |
+
"eval_loss": 1.721982717514038,
|
| 1263 |
+
"eval_precision": 0.5986325652063814,
|
| 1264 |
+
"eval_recall": 0.6769759450171822,
|
| 1265 |
+
"eval_runtime": 2.8786,
|
| 1266 |
+
"eval_samples_per_second": 386.296,
|
| 1267 |
+
"eval_steps_per_second": 6.253,
|
| 1268 |
+
"step": 11468
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 94.26,
|
| 1272 |
+
"learning_rate": 6.434426229508197e-06,
|
| 1273 |
+
"loss": 0.0032,
|
| 1274 |
+
"step": 11500
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 95.0,
|
| 1278 |
+
"eval_accuracy": 0.7994333993531727,
|
| 1279 |
+
"eval_f1": 0.6351459951781409,
|
| 1280 |
+
"eval_loss": 1.7394192218780518,
|
| 1281 |
+
"eval_precision": 0.5966280825364871,
|
| 1282 |
+
"eval_recall": 0.6789805269186713,
|
| 1283 |
+
"eval_runtime": 2.9637,
|
| 1284 |
+
"eval_samples_per_second": 375.209,
|
| 1285 |
+
"eval_steps_per_second": 6.074,
|
| 1286 |
+
"step": 11590
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 96.0,
|
| 1290 |
+
"eval_accuracy": 0.8004613031814877,
|
| 1291 |
+
"eval_f1": 0.6391640656805537,
|
| 1292 |
+
"eval_loss": 1.7256627082824707,
|
| 1293 |
+
"eval_precision": 0.6074284240392056,
|
| 1294 |
+
"eval_recall": 0.6743986254295533,
|
| 1295 |
+
"eval_runtime": 2.9246,
|
| 1296 |
+
"eval_samples_per_second": 380.221,
|
| 1297 |
+
"eval_steps_per_second": 6.155,
|
| 1298 |
+
"step": 11712
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 97.0,
|
| 1302 |
+
"eval_accuracy": 0.8039461478677263,
|
| 1303 |
+
"eval_f1": 0.635028555887952,
|
| 1304 |
+
"eval_loss": 1.700808048248291,
|
| 1305 |
+
"eval_precision": 0.6046090108751943,
|
| 1306 |
+
"eval_recall": 0.6686712485681557,
|
| 1307 |
+
"eval_runtime": 2.8758,
|
| 1308 |
+
"eval_samples_per_second": 386.673,
|
| 1309 |
+
"eval_steps_per_second": 6.259,
|
| 1310 |
+
"step": 11834
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 98.0,
|
| 1314 |
+
"eval_accuracy": 0.8032190939403816,
|
| 1315 |
+
"eval_f1": 0.6355140186915889,
|
| 1316 |
+
"eval_loss": 1.7482486963272095,
|
| 1317 |
+
"eval_precision": 0.6029298380878951,
|
| 1318 |
+
"eval_recall": 0.6718213058419243,
|
| 1319 |
+
"eval_runtime": 2.927,
|
| 1320 |
+
"eval_samples_per_second": 379.912,
|
| 1321 |
+
"eval_steps_per_second": 6.15,
|
| 1322 |
+
"step": 11956
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 98.36,
|
| 1326 |
+
"learning_rate": 5.409836065573771e-06,
|
| 1327 |
+
"loss": 0.0028,
|
| 1328 |
+
"step": 12000
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 99.0,
|
| 1332 |
+
"eval_accuracy": 0.8030435981648156,
|
| 1333 |
+
"eval_f1": 0.6319491410793994,
|
| 1334 |
+
"eval_loss": 1.7569934129714966,
|
| 1335 |
+
"eval_precision": 0.598820815175596,
|
| 1336 |
+
"eval_recall": 0.6689576174112256,
|
| 1337 |
+
"eval_runtime": 2.8862,
|
| 1338 |
+
"eval_samples_per_second": 385.277,
|
| 1339 |
+
"eval_steps_per_second": 6.236,
|
| 1340 |
+
"step": 12078
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 100.0,
|
| 1344 |
+
"eval_accuracy": 0.8026173941384411,
|
| 1345 |
+
"eval_f1": 0.6335353535353535,
|
| 1346 |
+
"eval_loss": 1.733221411705017,
|
| 1347 |
+
"eval_precision": 0.5980167810831426,
|
| 1348 |
+
"eval_recall": 0.6735395189003437,
|
| 1349 |
+
"eval_runtime": 2.9532,
|
| 1350 |
+
"eval_samples_per_second": 376.543,
|
| 1351 |
+
"eval_steps_per_second": 6.095,
|
| 1352 |
+
"step": 12200
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 101.0,
|
| 1356 |
+
"eval_accuracy": 0.8011131446335898,
|
| 1357 |
+
"eval_f1": 0.6279817743232377,
|
| 1358 |
+
"eval_loss": 1.749053955078125,
|
| 1359 |
+
"eval_precision": 0.590176322418136,
|
| 1360 |
+
"eval_recall": 0.6709621993127147,
|
| 1361 |
+
"eval_runtime": 2.8456,
|
| 1362 |
+
"eval_samples_per_second": 390.774,
|
| 1363 |
+
"eval_steps_per_second": 6.325,
|
| 1364 |
+
"step": 12322
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 102.0,
|
| 1368 |
+
"eval_accuracy": 0.8033444480657859,
|
| 1369 |
+
"eval_f1": 0.6348178137651822,
|
| 1370 |
+
"eval_loss": 1.754211664199829,
|
| 1371 |
+
"eval_precision": 0.6003062787136294,
|
| 1372 |
+
"eval_recall": 0.6735395189003437,
|
| 1373 |
+
"eval_runtime": 3.0603,
|
| 1374 |
+
"eval_samples_per_second": 363.358,
|
| 1375 |
+
"eval_steps_per_second": 5.882,
|
| 1376 |
+
"step": 12444
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 102.46,
|
| 1380 |
+
"learning_rate": 4.385245901639344e-06,
|
| 1381 |
+
"loss": 0.0021,
|
| 1382 |
+
"step": 12500
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 103.0,
|
| 1386 |
+
"eval_accuracy": 0.8040464311680497,
|
| 1387 |
+
"eval_f1": 0.6305431998921687,
|
| 1388 |
+
"eval_loss": 1.7371126413345337,
|
| 1389 |
+
"eval_precision": 0.5956200662083015,
|
| 1390 |
+
"eval_recall": 0.6698167239404352,
|
| 1391 |
+
"eval_runtime": 2.9206,
|
| 1392 |
+
"eval_samples_per_second": 380.743,
|
| 1393 |
+
"eval_steps_per_second": 6.163,
|
| 1394 |
+
"step": 12566
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 104.0,
|
| 1398 |
+
"eval_accuracy": 0.800737082257377,
|
| 1399 |
+
"eval_f1": 0.6273032952252858,
|
| 1400 |
+
"eval_loss": 1.771882176399231,
|
| 1401 |
+
"eval_precision": 0.5914278468171443,
|
| 1402 |
+
"eval_recall": 0.6678121420389461,
|
| 1403 |
+
"eval_runtime": 2.9022,
|
| 1404 |
+
"eval_samples_per_second": 383.156,
|
| 1405 |
+
"eval_steps_per_second": 6.202,
|
| 1406 |
+
"step": 12688
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 105.0,
|
| 1410 |
+
"eval_accuracy": 0.804522776844586,
|
| 1411 |
+
"eval_f1": 0.6305525460455038,
|
| 1412 |
+
"eval_loss": 1.7473387718200684,
|
| 1413 |
+
"eval_precision": 0.5981500513874615,
|
| 1414 |
+
"eval_recall": 0.6666666666666666,
|
| 1415 |
+
"eval_runtime": 2.8767,
|
| 1416 |
+
"eval_samples_per_second": 386.556,
|
| 1417 |
+
"eval_steps_per_second": 6.257,
|
| 1418 |
+
"step": 12810
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 106.0,
|
| 1422 |
+
"eval_accuracy": 0.803996289517888,
|
| 1423 |
+
"eval_f1": 0.6361556064073227,
|
| 1424 |
+
"eval_loss": 1.7518253326416016,
|
| 1425 |
+
"eval_precision": 0.6002032004064008,
|
| 1426 |
+
"eval_recall": 0.6766895761741123,
|
| 1427 |
+
"eval_runtime": 2.9045,
|
| 1428 |
+
"eval_samples_per_second": 382.852,
|
| 1429 |
+
"eval_steps_per_second": 6.197,
|
| 1430 |
+
"step": 12932
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 106.56,
|
| 1434 |
+
"learning_rate": 3.3606557377049183e-06,
|
| 1435 |
+
"loss": 0.0019,
|
| 1436 |
+
"step": 13000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 107.0,
|
| 1440 |
+
"eval_accuracy": 0.804848697570637,
|
| 1441 |
+
"eval_f1": 0.6358241165362828,
|
| 1442 |
+
"eval_loss": 1.7628158330917358,
|
| 1443 |
+
"eval_precision": 0.6009688934217237,
|
| 1444 |
+
"eval_recall": 0.6749713631156931,
|
| 1445 |
+
"eval_runtime": 2.8942,
|
| 1446 |
+
"eval_samples_per_second": 384.222,
|
| 1447 |
+
"eval_steps_per_second": 6.219,
|
| 1448 |
+
"step": 13054
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 108.0,
|
| 1452 |
+
"eval_accuracy": 0.7964750419936321,
|
| 1453 |
+
"eval_f1": 0.6344605475040258,
|
| 1454 |
+
"eval_loss": 1.8080339431762695,
|
| 1455 |
+
"eval_precision": 0.5969696969696969,
|
| 1456 |
+
"eval_recall": 0.6769759450171822,
|
| 1457 |
+
"eval_runtime": 2.9081,
|
| 1458 |
+
"eval_samples_per_second": 382.377,
|
| 1459 |
+
"eval_steps_per_second": 6.19,
|
| 1460 |
+
"step": 13176
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 109.0,
|
| 1464 |
+
"eval_accuracy": 0.7985809913004237,
|
| 1465 |
+
"eval_f1": 0.6338519313304721,
|
| 1466 |
+
"eval_loss": 1.8027576208114624,
|
| 1467 |
+
"eval_precision": 0.5961150353178607,
|
| 1468 |
+
"eval_recall": 0.6766895761741123,
|
| 1469 |
+
"eval_runtime": 2.8859,
|
| 1470 |
+
"eval_samples_per_second": 385.324,
|
| 1471 |
+
"eval_steps_per_second": 6.237,
|
| 1472 |
+
"step": 13298
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 110.0,
|
| 1476 |
+
"eval_accuracy": 0.8029683856895731,
|
| 1477 |
+
"eval_f1": 0.6342911102117901,
|
| 1478 |
+
"eval_loss": 1.781972050666809,
|
| 1479 |
+
"eval_precision": 0.5995919408314205,
|
| 1480 |
+
"eval_recall": 0.6732531500572738,
|
| 1481 |
+
"eval_runtime": 2.9186,
|
| 1482 |
+
"eval_samples_per_second": 380.999,
|
| 1483 |
+
"eval_steps_per_second": 6.167,
|
| 1484 |
+
"step": 13420
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 110.66,
|
| 1488 |
+
"learning_rate": 2.336065573770492e-06,
|
| 1489 |
+
"loss": 0.0015,
|
| 1490 |
+
"step": 13500
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 111.0,
|
| 1494 |
+
"eval_accuracy": 0.8029934565146539,
|
| 1495 |
+
"eval_f1": 0.6372588695534872,
|
| 1496 |
+
"eval_loss": 1.7890208959579468,
|
| 1497 |
+
"eval_precision": 0.6023973476154042,
|
| 1498 |
+
"eval_recall": 0.6764032073310424,
|
| 1499 |
+
"eval_runtime": 2.8911,
|
| 1500 |
+
"eval_samples_per_second": 384.624,
|
| 1501 |
+
"eval_steps_per_second": 6.226,
|
| 1502 |
+
"step": 13542
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 112.0,
|
| 1506 |
+
"eval_accuracy": 0.8039712186928072,
|
| 1507 |
+
"eval_f1": 0.6397507112857337,
|
| 1508 |
+
"eval_loss": 1.7686277627944946,
|
| 1509 |
+
"eval_precision": 0.6070969400874261,
|
| 1510 |
+
"eval_recall": 0.6761168384879725,
|
| 1511 |
+
"eval_runtime": 2.9181,
|
| 1512 |
+
"eval_samples_per_second": 381.073,
|
| 1513 |
+
"eval_steps_per_second": 6.168,
|
| 1514 |
+
"step": 13664
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 113.0,
|
| 1518 |
+
"eval_accuracy": 0.8046732017950711,
|
| 1519 |
+
"eval_f1": 0.6398059560706104,
|
| 1520 |
+
"eval_loss": 1.7624890804290771,
|
| 1521 |
+
"eval_precision": 0.6042249936370577,
|
| 1522 |
+
"eval_recall": 0.6798396334478809,
|
| 1523 |
+
"eval_runtime": 2.9383,
|
| 1524 |
+
"eval_samples_per_second": 378.455,
|
| 1525 |
+
"eval_steps_per_second": 6.126,
|
| 1526 |
+
"step": 13786
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 114.0,
|
| 1530 |
+
"eval_accuracy": 0.8038960062175646,
|
| 1531 |
+
"eval_f1": 0.637657584383896,
|
| 1532 |
+
"eval_loss": 1.7636594772338867,
|
| 1533 |
+
"eval_precision": 0.6054054054054054,
|
| 1534 |
+
"eval_recall": 0.6735395189003437,
|
| 1535 |
+
"eval_runtime": 2.886,
|
| 1536 |
+
"eval_samples_per_second": 385.312,
|
| 1537 |
+
"eval_steps_per_second": 6.237,
|
| 1538 |
+
"step": 13908
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 114.75,
|
| 1542 |
+
"learning_rate": 1.3114754098360657e-06,
|
| 1543 |
+
"loss": 0.0013,
|
| 1544 |
+
"step": 14000
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 115.0,
|
| 1548 |
+
"eval_accuracy": 0.8037957229172412,
|
| 1549 |
+
"eval_f1": 0.638487508440243,
|
| 1550 |
+
"eval_loss": 1.7679991722106934,
|
| 1551 |
+
"eval_precision": 0.6041400460005111,
|
| 1552 |
+
"eval_recall": 0.6769759450171822,
|
| 1553 |
+
"eval_runtime": 2.8755,
|
| 1554 |
+
"eval_samples_per_second": 386.709,
|
| 1555 |
+
"eval_steps_per_second": 6.26,
|
| 1556 |
+
"step": 14030
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 116.0,
|
| 1560 |
+
"eval_accuracy": 0.8028931732143305,
|
| 1561 |
+
"eval_f1": 0.6367303038451196,
|
| 1562 |
+
"eval_loss": 1.783056616783142,
|
| 1563 |
+
"eval_precision": 0.6001013684744044,
|
| 1564 |
+
"eval_recall": 0.6781214203894617,
|
| 1565 |
+
"eval_runtime": 2.9247,
|
| 1566 |
+
"eval_samples_per_second": 380.207,
|
| 1567 |
+
"eval_steps_per_second": 6.154,
|
| 1568 |
+
"step": 14152
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 117.0,
|
| 1572 |
+
"eval_accuracy": 0.8021159776368241,
|
| 1573 |
+
"eval_f1": 0.6353479606945753,
|
| 1574 |
+
"eval_loss": 1.7854276895523071,
|
| 1575 |
+
"eval_precision": 0.5994411988823978,
|
| 1576 |
+
"eval_recall": 0.6758304696449027,
|
| 1577 |
+
"eval_runtime": 2.8934,
|
| 1578 |
+
"eval_samples_per_second": 384.319,
|
| 1579 |
+
"eval_steps_per_second": 6.221,
|
| 1580 |
+
"step": 14274
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 118.0,
|
| 1584 |
+
"eval_accuracy": 0.8034447313661093,
|
| 1585 |
+
"eval_f1": 0.6355291576673866,
|
| 1586 |
+
"eval_loss": 1.7762141227722168,
|
| 1587 |
+
"eval_precision": 0.601123595505618,
|
| 1588 |
+
"eval_recall": 0.6741122565864834,
|
| 1589 |
+
"eval_runtime": 3.1021,
|
| 1590 |
+
"eval_samples_per_second": 358.473,
|
| 1591 |
+
"eval_steps_per_second": 5.803,
|
| 1592 |
+
"step": 14396
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 118.85,
|
| 1596 |
+
"learning_rate": 2.8688524590163937e-07,
|
| 1597 |
+
"loss": 0.0012,
|
| 1598 |
+
"step": 14500
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 119.0,
|
| 1602 |
+
"eval_accuracy": 0.8027928899140071,
|
| 1603 |
+
"eval_f1": 0.635909888034534,
|
| 1604 |
+
"eval_loss": 1.7778316736221313,
|
| 1605 |
+
"eval_precision": 0.6011221627135934,
|
| 1606 |
+
"eval_recall": 0.6749713631156931,
|
| 1607 |
+
"eval_runtime": 2.8654,
|
| 1608 |
+
"eval_samples_per_second": 388.078,
|
| 1609 |
+
"eval_steps_per_second": 6.282,
|
| 1610 |
+
"step": 14518
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 120.0,
|
| 1614 |
+
"eval_accuracy": 0.8029182440394114,
|
| 1615 |
+
"eval_f1": 0.6360691144708422,
|
| 1616 |
+
"eval_loss": 1.777363896369934,
|
| 1617 |
+
"eval_precision": 0.6016343207354443,
|
| 1618 |
+
"eval_recall": 0.6746849942726232,
|
| 1619 |
+
"eval_runtime": 2.9475,
|
| 1620 |
+
"eval_samples_per_second": 377.274,
|
| 1621 |
+
"eval_steps_per_second": 6.107,
|
| 1622 |
+
"step": 14640
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 120.0,
|
| 1626 |
+
"step": 14640,
|
| 1627 |
+
"total_flos": 1.220726808511488e+17,
|
| 1628 |
+
"train_loss": 0.10161643302465072,
|
| 1629 |
+
"train_runtime": 6791.1484,
|
| 1630 |
+
"train_samples_per_second": 137.561,
|
| 1631 |
+
"train_steps_per_second": 2.156
|
| 1632 |
+
}
|
| 1633 |
+
],
|
| 1634 |
+
"max_steps": 14640,
|
| 1635 |
+
"num_train_epochs": 120,
|
| 1636 |
+
"total_flos": 1.220726808511488e+17,
|
| 1637 |
+
"trial_name": null,
|
| 1638 |
+
"trial_params": null
|
| 1639 |
+
}
|