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 +1813 -0
all_results.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 120.0,
|
3 |
+
"eval_accuracy": 0.8276281577252451,
|
4 |
+
"eval_f1": 0.6784613322610911,
|
5 |
+
"eval_loss": 1.6160385608673096,
|
6 |
+
"eval_precision": 0.6524877545759217,
|
7 |
+
"eval_recall": 0.7065884980457845,
|
8 |
+
"eval_runtime": 2.9494,
|
9 |
+
"eval_samples": 1112,
|
10 |
+
"eval_samples_per_second": 377.029,
|
11 |
+
"eval_steps_per_second": 11.867,
|
12 |
+
"predict_accuracy": 0.8316702819956616,
|
13 |
+
"predict_f1": 0.6882613133718952,
|
14 |
+
"predict_loss": 1.5868676900863647,
|
15 |
+
"predict_precision": 0.6608729743857815,
|
16 |
+
"predict_recall": 0.718017890103649,
|
17 |
+
"predict_runtime": 5.983,
|
18 |
+
"predict_samples_per_second": 371.884,
|
19 |
+
"predict_steps_per_second": 11.7,
|
20 |
+
"train_loss": 0.045685164459416124,
|
21 |
+
"train_runtime": 6878.0479,
|
22 |
+
"train_samples": 7785,
|
23 |
+
"train_samples_per_second": 135.823,
|
24 |
+
"train_steps_per_second": 4.257
|
25 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 120.0,
|
3 |
+
"eval_accuracy": 0.8276281577252451,
|
4 |
+
"eval_f1": 0.6784613322610911,
|
5 |
+
"eval_loss": 1.6160385608673096,
|
6 |
+
"eval_precision": 0.6524877545759217,
|
7 |
+
"eval_recall": 0.7065884980457845,
|
8 |
+
"eval_runtime": 2.9494,
|
9 |
+
"eval_samples": 1112,
|
10 |
+
"eval_samples_per_second": 377.029,
|
11 |
+
"eval_steps_per_second": 11.867
|
12 |
+
}
|
predict_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"predict_accuracy": 0.8316702819956616,
|
3 |
+
"predict_f1": 0.6882613133718952,
|
4 |
+
"predict_loss": 1.5868676900863647,
|
5 |
+
"predict_precision": 0.6608729743857815,
|
6 |
+
"predict_recall": 0.718017890103649,
|
7 |
+
"predict_runtime": 5.983,
|
8 |
+
"predict_samples_per_second": 371.884,
|
9 |
+
"predict_steps_per_second": 11.7
|
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": 0.045685164459416124,
|
4 |
+
"train_runtime": 6878.0479,
|
5 |
+
"train_samples": 7785,
|
6 |
+
"train_samples_per_second": 135.823,
|
7 |
+
"train_steps_per_second": 4.257
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1813 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6784613322610911,
|
3 |
+
"best_model_checkpoint": "/tmp/test-ner1_base/checkpoint-26840",
|
4 |
+
"epoch": 120.0,
|
5 |
+
"global_step": 29280,
|
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": 0.7635791130936762,
|
13 |
+
"eval_f1": 0.4809298946603705,
|
14 |
+
"eval_loss": 0.8214002847671509,
|
15 |
+
"eval_precision": 0.4246311738293778,
|
16 |
+
"eval_recall": 0.5544388609715243,
|
17 |
+
"eval_runtime": 2.9656,
|
18 |
+
"eval_samples_per_second": 374.972,
|
19 |
+
"eval_steps_per_second": 11.802,
|
20 |
+
"step": 244
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.0,
|
24 |
+
"eval_accuracy": 0.8022709381932683,
|
25 |
+
"eval_f1": 0.5700258397932816,
|
26 |
+
"eval_loss": 0.6734200119972229,
|
27 |
+
"eval_precision": 0.5305435305435305,
|
28 |
+
"eval_recall": 0.615857063093244,
|
29 |
+
"eval_runtime": 2.95,
|
30 |
+
"eval_samples_per_second": 376.943,
|
31 |
+
"eval_steps_per_second": 11.864,
|
32 |
+
"step": 488
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.05,
|
36 |
+
"learning_rate": 2.9487704918032787e-05,
|
37 |
+
"loss": 0.9764,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"eval_accuracy": 0.8072087975000596,
|
43 |
+
"eval_f1": 0.6019592678525393,
|
44 |
+
"eval_loss": 0.6425491571426392,
|
45 |
+
"eval_precision": 0.5591475095785441,
|
46 |
+
"eval_recall": 0.6518704634282524,
|
47 |
+
"eval_runtime": 2.9986,
|
48 |
+
"eval_samples_per_second": 370.843,
|
49 |
+
"eval_steps_per_second": 11.672,
|
50 |
+
"step": 732
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"eval_accuracy": 0.8214737243863457,
|
55 |
+
"eval_f1": 0.6151294808011226,
|
56 |
+
"eval_loss": 0.6202793121337891,
|
57 |
+
"eval_precision": 0.5663612872915198,
|
58 |
+
"eval_recall": 0.6730876605248465,
|
59 |
+
"eval_runtime": 2.9638,
|
60 |
+
"eval_samples_per_second": 375.198,
|
61 |
+
"eval_steps_per_second": 11.809,
|
62 |
+
"step": 976
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 4.1,
|
66 |
+
"learning_rate": 2.8975409836065577e-05,
|
67 |
+
"loss": 0.4504,
|
68 |
+
"step": 1000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 5.0,
|
72 |
+
"eval_accuracy": 0.8170606617208559,
|
73 |
+
"eval_f1": 0.6304066304066305,
|
74 |
+
"eval_loss": 0.6483346223831177,
|
75 |
+
"eval_precision": 0.5879227053140097,
|
76 |
+
"eval_recall": 0.6795086543830262,
|
77 |
+
"eval_runtime": 2.9472,
|
78 |
+
"eval_samples_per_second": 377.302,
|
79 |
+
"eval_steps_per_second": 11.876,
|
80 |
+
"step": 1220
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 6.0,
|
84 |
+
"eval_accuracy": 0.8137687555163283,
|
85 |
+
"eval_f1": 0.607830950901181,
|
86 |
+
"eval_loss": 0.6827735900878906,
|
87 |
+
"eval_precision": 0.5478377772798566,
|
88 |
+
"eval_recall": 0.6825795644891123,
|
89 |
+
"eval_runtime": 2.9631,
|
90 |
+
"eval_samples_per_second": 375.283,
|
91 |
+
"eval_steps_per_second": 11.812,
|
92 |
+
"step": 1464
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 6.15,
|
96 |
+
"learning_rate": 2.846311475409836e-05,
|
97 |
+
"loss": 0.2877,
|
98 |
+
"step": 1500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"eval_accuracy": 0.8115025882016174,
|
103 |
+
"eval_f1": 0.6301228183581126,
|
104 |
+
"eval_loss": 0.709669828414917,
|
105 |
+
"eval_precision": 0.5868047194798941,
|
106 |
+
"eval_recall": 0.6803461753210497,
|
107 |
+
"eval_runtime": 2.9712,
|
108 |
+
"eval_samples_per_second": 374.266,
|
109 |
+
"eval_steps_per_second": 11.78,
|
110 |
+
"step": 1708
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 8.0,
|
114 |
+
"eval_accuracy": 0.8133393764461726,
|
115 |
+
"eval_f1": 0.6333632978040324,
|
116 |
+
"eval_loss": 0.7538309097290039,
|
117 |
+
"eval_precision": 0.5864447086801426,
|
118 |
+
"eval_recall": 0.6884422110552764,
|
119 |
+
"eval_runtime": 2.99,
|
120 |
+
"eval_samples_per_second": 371.902,
|
121 |
+
"eval_steps_per_second": 11.706,
|
122 |
+
"step": 1952
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 8.2,
|
126 |
+
"learning_rate": 2.795081967213115e-05,
|
127 |
+
"loss": 0.1968,
|
128 |
+
"step": 2000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 9.0,
|
132 |
+
"eval_accuracy": 0.812862288590444,
|
133 |
+
"eval_f1": 0.6361865177295752,
|
134 |
+
"eval_loss": 0.7852667570114136,
|
135 |
+
"eval_precision": 0.594850619383046,
|
136 |
+
"eval_recall": 0.6836962590731435,
|
137 |
+
"eval_runtime": 2.9647,
|
138 |
+
"eval_samples_per_second": 375.08,
|
139 |
+
"eval_steps_per_second": 11.806,
|
140 |
+
"step": 2196
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 10.0,
|
144 |
+
"eval_accuracy": 0.8093556928508385,
|
145 |
+
"eval_f1": 0.6372536222425271,
|
146 |
+
"eval_loss": 0.8311049938201904,
|
147 |
+
"eval_precision": 0.5984309879872518,
|
148 |
+
"eval_recall": 0.681462869905081,
|
149 |
+
"eval_runtime": 3.0899,
|
150 |
+
"eval_samples_per_second": 359.881,
|
151 |
+
"eval_steps_per_second": 11.327,
|
152 |
+
"step": 2440
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 10.25,
|
156 |
+
"learning_rate": 2.7438524590163935e-05,
|
157 |
+
"loss": 0.1443,
|
158 |
+
"step": 2500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 11.0,
|
162 |
+
"eval_accuracy": 0.8189928675365569,
|
163 |
+
"eval_f1": 0.6475366876310273,
|
164 |
+
"eval_loss": 0.790969967842102,
|
165 |
+
"eval_precision": 0.6101234567901235,
|
166 |
+
"eval_recall": 0.6898380792853155,
|
167 |
+
"eval_runtime": 2.9631,
|
168 |
+
"eval_samples_per_second": 375.284,
|
169 |
+
"eval_steps_per_second": 11.812,
|
170 |
+
"step": 2684
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 12.0,
|
174 |
+
"eval_accuracy": 0.8147229312277856,
|
175 |
+
"eval_f1": 0.6334806342604627,
|
176 |
+
"eval_loss": 0.8414269089698792,
|
177 |
+
"eval_precision": 0.5926556420233463,
|
178 |
+
"eval_recall": 0.6803461753210497,
|
179 |
+
"eval_runtime": 2.9571,
|
180 |
+
"eval_samples_per_second": 376.042,
|
181 |
+
"eval_steps_per_second": 11.836,
|
182 |
+
"step": 2928
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 12.3,
|
186 |
+
"learning_rate": 2.6926229508196725e-05,
|
187 |
+
"loss": 0.1118,
|
188 |
+
"step": 3000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 13.0,
|
192 |
+
"eval_accuracy": 0.8069225447866225,
|
193 |
+
"eval_f1": 0.6412532637075719,
|
194 |
+
"eval_loss": 0.8946433067321777,
|
195 |
+
"eval_precision": 0.6022560078469839,
|
196 |
+
"eval_recall": 0.6856504745951982,
|
197 |
+
"eval_runtime": 2.9859,
|
198 |
+
"eval_samples_per_second": 372.42,
|
199 |
+
"eval_steps_per_second": 11.722,
|
200 |
+
"step": 3172
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 14.0,
|
204 |
+
"eval_accuracy": 0.8129815605543761,
|
205 |
+
"eval_f1": 0.6424639580602883,
|
206 |
+
"eval_loss": 0.9194995760917664,
|
207 |
+
"eval_precision": 0.6054841897233202,
|
208 |
+
"eval_recall": 0.6842546063651591,
|
209 |
+
"eval_runtime": 2.9708,
|
210 |
+
"eval_samples_per_second": 374.309,
|
211 |
+
"eval_steps_per_second": 11.781,
|
212 |
+
"step": 3416
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 14.34,
|
216 |
+
"learning_rate": 2.6413934426229508e-05,
|
217 |
+
"loss": 0.0838,
|
218 |
+
"step": 3500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 15.0,
|
222 |
+
"eval_accuracy": 0.8192314114644211,
|
223 |
+
"eval_f1": 0.6421779340888367,
|
224 |
+
"eval_loss": 0.9149069786071777,
|
225 |
+
"eval_precision": 0.6019536019536019,
|
226 |
+
"eval_recall": 0.6881630374092685,
|
227 |
+
"eval_runtime": 2.9929,
|
228 |
+
"eval_samples_per_second": 371.552,
|
229 |
+
"eval_steps_per_second": 11.695,
|
230 |
+
"step": 3660
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 16.0,
|
234 |
+
"eval_accuracy": 0.8201140239975191,
|
235 |
+
"eval_f1": 0.6456589958158997,
|
236 |
+
"eval_loss": 0.9356908798217773,
|
237 |
+
"eval_precision": 0.6072306935563208,
|
238 |
+
"eval_recall": 0.6892797319932998,
|
239 |
+
"eval_runtime": 2.9882,
|
240 |
+
"eval_samples_per_second": 372.132,
|
241 |
+
"eval_steps_per_second": 11.713,
|
242 |
+
"step": 3904
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 16.39,
|
246 |
+
"learning_rate": 2.5901639344262294e-05,
|
247 |
+
"loss": 0.0661,
|
248 |
+
"step": 4000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 17.0,
|
252 |
+
"eval_accuracy": 0.8172514968631474,
|
253 |
+
"eval_f1": 0.6432016686220832,
|
254 |
+
"eval_loss": 0.9784498810768127,
|
255 |
+
"eval_precision": 0.60332599657618,
|
256 |
+
"eval_recall": 0.6887213847012842,
|
257 |
+
"eval_runtime": 2.968,
|
258 |
+
"eval_samples_per_second": 374.663,
|
259 |
+
"eval_steps_per_second": 11.792,
|
260 |
+
"step": 4148
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 18.0,
|
264 |
+
"eval_accuracy": 0.8184442165024689,
|
265 |
+
"eval_f1": 0.6472832522036575,
|
266 |
+
"eval_loss": 0.9842237234115601,
|
267 |
+
"eval_precision": 0.6120925603383927,
|
268 |
+
"eval_recall": 0.6867671691792295,
|
269 |
+
"eval_runtime": 2.981,
|
270 |
+
"eval_samples_per_second": 373.035,
|
271 |
+
"eval_steps_per_second": 11.741,
|
272 |
+
"step": 4392
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 18.44,
|
276 |
+
"learning_rate": 2.5389344262295083e-05,
|
277 |
+
"loss": 0.0514,
|
278 |
+
"step": 4500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 19.0,
|
282 |
+
"eval_accuracy": 0.8163688843300494,
|
283 |
+
"eval_f1": 0.6476140534871526,
|
284 |
+
"eval_loss": 1.0097302198410034,
|
285 |
+
"eval_precision": 0.6104794859120118,
|
286 |
+
"eval_recall": 0.6895589056393077,
|
287 |
+
"eval_runtime": 2.9667,
|
288 |
+
"eval_samples_per_second": 374.823,
|
289 |
+
"eval_steps_per_second": 11.797,
|
290 |
+
"step": 4636
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 20.0,
|
294 |
+
"eval_accuracy": 0.8167028458290594,
|
295 |
+
"eval_f1": 0.648761408083442,
|
296 |
+
"eval_loss": 1.0300242900848389,
|
297 |
+
"eval_precision": 0.6086105675146771,
|
298 |
+
"eval_recall": 0.6945840312674484,
|
299 |
+
"eval_runtime": 3.032,
|
300 |
+
"eval_samples_per_second": 366.754,
|
301 |
+
"eval_steps_per_second": 11.544,
|
302 |
+
"step": 4880
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 20.49,
|
306 |
+
"learning_rate": 2.487704918032787e-05,
|
307 |
+
"loss": 0.0416,
|
308 |
+
"step": 5000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 21.0,
|
312 |
+
"eval_accuracy": 0.8204718398893156,
|
313 |
+
"eval_f1": 0.652764946548766,
|
314 |
+
"eval_loss": 1.0250210762023926,
|
315 |
+
"eval_precision": 0.6190237797246558,
|
316 |
+
"eval_recall": 0.6903964265773311,
|
317 |
+
"eval_runtime": 2.9697,
|
318 |
+
"eval_samples_per_second": 374.455,
|
319 |
+
"eval_steps_per_second": 11.786,
|
320 |
+
"step": 5124
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 22.0,
|
324 |
+
"eval_accuracy": 0.8167267002218459,
|
325 |
+
"eval_f1": 0.6531738730450781,
|
326 |
+
"eval_loss": 1.087920069694519,
|
327 |
+
"eval_precision": 0.6170846784206605,
|
328 |
+
"eval_recall": 0.6937465103294249,
|
329 |
+
"eval_runtime": 2.983,
|
330 |
+
"eval_samples_per_second": 372.773,
|
331 |
+
"eval_steps_per_second": 11.733,
|
332 |
+
"step": 5368
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 22.54,
|
336 |
+
"learning_rate": 2.436475409836066e-05,
|
337 |
+
"loss": 0.0324,
|
338 |
+
"step": 5500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 23.0,
|
342 |
+
"eval_accuracy": 0.8127191622337253,
|
343 |
+
"eval_f1": 0.6434782608695652,
|
344 |
+
"eval_loss": 1.134914755821228,
|
345 |
+
"eval_precision": 0.6092814371257484,
|
346 |
+
"eval_recall": 0.6817420435510888,
|
347 |
+
"eval_runtime": 2.9583,
|
348 |
+
"eval_samples_per_second": 375.891,
|
349 |
+
"eval_steps_per_second": 11.831,
|
350 |
+
"step": 5612
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 24.0,
|
354 |
+
"eval_accuracy": 0.8181102550034589,
|
355 |
+
"eval_f1": 0.6542006847511194,
|
356 |
+
"eval_loss": 1.0993841886520386,
|
357 |
+
"eval_precision": 0.6191425722831505,
|
358 |
+
"eval_recall": 0.6934673366834171,
|
359 |
+
"eval_runtime": 2.985,
|
360 |
+
"eval_samples_per_second": 372.527,
|
361 |
+
"eval_steps_per_second": 11.725,
|
362 |
+
"step": 5856
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 24.59,
|
366 |
+
"learning_rate": 2.3852459016393442e-05,
|
367 |
+
"loss": 0.0277,
|
368 |
+
"step": 6000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 25.0,
|
372 |
+
"eval_accuracy": 0.8152715822618736,
|
373 |
+
"eval_f1": 0.6543161214032323,
|
374 |
+
"eval_loss": 1.1400500535964966,
|
375 |
+
"eval_precision": 0.6180193596425912,
|
376 |
+
"eval_recall": 0.695142378559464,
|
377 |
+
"eval_runtime": 3.0938,
|
378 |
+
"eval_samples_per_second": 359.431,
|
379 |
+
"eval_steps_per_second": 11.313,
|
380 |
+
"step": 6100
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 26.0,
|
384 |
+
"eval_accuracy": 0.808449225924954,
|
385 |
+
"eval_f1": 0.6410887880751782,
|
386 |
+
"eval_loss": 1.1867998838424683,
|
387 |
+
"eval_precision": 0.5983547060246794,
|
388 |
+
"eval_recall": 0.6903964265773311,
|
389 |
+
"eval_runtime": 2.9903,
|
390 |
+
"eval_samples_per_second": 371.869,
|
391 |
+
"eval_steps_per_second": 11.704,
|
392 |
+
"step": 6344
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 26.64,
|
396 |
+
"learning_rate": 2.3340163934426228e-05,
|
397 |
+
"loss": 0.0223,
|
398 |
+
"step": 6500
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 27.0,
|
402 |
+
"eval_accuracy": 0.8138880274802605,
|
403 |
+
"eval_f1": 0.6558120912851995,
|
404 |
+
"eval_loss": 1.205185890197754,
|
405 |
+
"eval_precision": 0.628228074661212,
|
406 |
+
"eval_recall": 0.6859296482412061,
|
407 |
+
"eval_runtime": 2.9746,
|
408 |
+
"eval_samples_per_second": 373.828,
|
409 |
+
"eval_steps_per_second": 11.766,
|
410 |
+
"step": 6588
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 28.0,
|
414 |
+
"eval_accuracy": 0.81529543665466,
|
415 |
+
"eval_f1": 0.6529110264160862,
|
416 |
+
"eval_loss": 1.1963977813720703,
|
417 |
+
"eval_precision": 0.6168363546064067,
|
418 |
+
"eval_recall": 0.6934673366834171,
|
419 |
+
"eval_runtime": 2.9694,
|
420 |
+
"eval_samples_per_second": 374.481,
|
421 |
+
"eval_steps_per_second": 11.787,
|
422 |
+
"step": 6832
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 28.69,
|
426 |
+
"learning_rate": 2.2827868852459018e-05,
|
427 |
+
"loss": 0.019,
|
428 |
+
"step": 7000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 29.0,
|
432 |
+
"eval_accuracy": 0.820161732783092,
|
433 |
+
"eval_f1": 0.6533368644067797,
|
434 |
+
"eval_loss": 1.1897813081741333,
|
435 |
+
"eval_precision": 0.6214105793450881,
|
436 |
+
"eval_recall": 0.6887213847012842,
|
437 |
+
"eval_runtime": 2.9761,
|
438 |
+
"eval_samples_per_second": 373.647,
|
439 |
+
"eval_steps_per_second": 11.76,
|
440 |
+
"step": 7076
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 30.0,
|
444 |
+
"eval_accuracy": 0.8134586484101047,
|
445 |
+
"eval_f1": 0.6515647505565013,
|
446 |
+
"eval_loss": 1.2819464206695557,
|
447 |
+
"eval_precision": 0.6135635018495684,
|
448 |
+
"eval_recall": 0.6945840312674484,
|
449 |
+
"eval_runtime": 2.9771,
|
450 |
+
"eval_samples_per_second": 373.523,
|
451 |
+
"eval_steps_per_second": 11.757,
|
452 |
+
"step": 7320
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 30.74,
|
456 |
+
"learning_rate": 2.2315573770491804e-05,
|
457 |
+
"loss": 0.0159,
|
458 |
+
"step": 7500
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 31.0,
|
462 |
+
"eval_accuracy": 0.8127907254120846,
|
463 |
+
"eval_f1": 0.6476589066178393,
|
464 |
+
"eval_loss": 1.2686526775360107,
|
465 |
+
"eval_precision": 0.609251968503937,
|
466 |
+
"eval_recall": 0.6912339475153545,
|
467 |
+
"eval_runtime": 3.0513,
|
468 |
+
"eval_samples_per_second": 364.436,
|
469 |
+
"eval_steps_per_second": 11.471,
|
470 |
+
"step": 7564
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 32.0,
|
474 |
+
"eval_accuracy": 0.8158917964743208,
|
475 |
+
"eval_f1": 0.6522136607026251,
|
476 |
+
"eval_loss": 1.2997089624404907,
|
477 |
+
"eval_precision": 0.612760736196319,
|
478 |
+
"eval_recall": 0.6970965940815187,
|
479 |
+
"eval_runtime": 3.0022,
|
480 |
+
"eval_samples_per_second": 370.396,
|
481 |
+
"eval_steps_per_second": 11.658,
|
482 |
+
"step": 7808
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 32.79,
|
486 |
+
"learning_rate": 2.180327868852459e-05,
|
487 |
+
"loss": 0.0141,
|
488 |
+
"step": 8000
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 33.0,
|
492 |
+
"eval_accuracy": 0.8157248157248157,
|
493 |
+
"eval_f1": 0.6490136369654441,
|
494 |
+
"eval_loss": 1.2799758911132812,
|
495 |
+
"eval_precision": 0.6172248803827751,
|
496 |
+
"eval_recall": 0.6842546063651591,
|
497 |
+
"eval_runtime": 2.9595,
|
498 |
+
"eval_samples_per_second": 375.745,
|
499 |
+
"eval_steps_per_second": 11.827,
|
500 |
+
"step": 8052
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 34.0,
|
504 |
+
"eval_accuracy": 0.8141265714081248,
|
505 |
+
"eval_f1": 0.6543144520910535,
|
506 |
+
"eval_loss": 1.3110435009002686,
|
507 |
+
"eval_precision": 0.6220432813286362,
|
508 |
+
"eval_recall": 0.6901172529313233,
|
509 |
+
"eval_runtime": 2.9482,
|
510 |
+
"eval_samples_per_second": 377.185,
|
511 |
+
"eval_steps_per_second": 11.872,
|
512 |
+
"step": 8296
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 34.84,
|
516 |
+
"learning_rate": 2.1290983606557376e-05,
|
517 |
+
"loss": 0.0107,
|
518 |
+
"step": 8500
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 35.0,
|
522 |
+
"eval_accuracy": 0.8159633596526801,
|
523 |
+
"eval_f1": 0.6468897020386828,
|
524 |
+
"eval_loss": 1.3342597484588623,
|
525 |
+
"eval_precision": 0.6081081081081081,
|
526 |
+
"eval_recall": 0.6909547738693468,
|
527 |
+
"eval_runtime": 2.9541,
|
528 |
+
"eval_samples_per_second": 376.43,
|
529 |
+
"eval_steps_per_second": 11.848,
|
530 |
+
"step": 8540
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 36.0,
|
534 |
+
"eval_accuracy": 0.8130292693399489,
|
535 |
+
"eval_f1": 0.6493064642763675,
|
536 |
+
"eval_loss": 1.3406134843826294,
|
537 |
+
"eval_precision": 0.6110837438423645,
|
538 |
+
"eval_recall": 0.6926298157453936,
|
539 |
+
"eval_runtime": 2.9685,
|
540 |
+
"eval_samples_per_second": 374.606,
|
541 |
+
"eval_steps_per_second": 11.791,
|
542 |
+
"step": 8784
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 36.89,
|
546 |
+
"learning_rate": 2.0778688524590166e-05,
|
547 |
+
"loss": 0.0106,
|
548 |
+
"step": 9000
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 37.0,
|
552 |
+
"eval_accuracy": 0.8127430166265118,
|
553 |
+
"eval_f1": 0.6453556923883139,
|
554 |
+
"eval_loss": 1.3921236991882324,
|
555 |
+
"eval_precision": 0.6079980251789682,
|
556 |
+
"eval_recall": 0.6876046901172529,
|
557 |
+
"eval_runtime": 2.9551,
|
558 |
+
"eval_samples_per_second": 376.302,
|
559 |
+
"eval_steps_per_second": 11.844,
|
560 |
+
"step": 9028
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 38.0,
|
564 |
+
"eval_accuracy": 0.8099997614560721,
|
565 |
+
"eval_f1": 0.6453305351521511,
|
566 |
+
"eval_loss": 1.4060559272766113,
|
567 |
+
"eval_precision": 0.6086095992083127,
|
568 |
+
"eval_recall": 0.6867671691792295,
|
569 |
+
"eval_runtime": 2.9714,
|
570 |
+
"eval_samples_per_second": 374.231,
|
571 |
+
"eval_steps_per_second": 11.779,
|
572 |
+
"step": 9272
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 38.93,
|
576 |
+
"learning_rate": 2.0266393442622952e-05,
|
577 |
+
"loss": 0.0088,
|
578 |
+
"step": 9500
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 39.0,
|
582 |
+
"eval_accuracy": 0.8165835738651273,
|
583 |
+
"eval_f1": 0.6592208482914507,
|
584 |
+
"eval_loss": 1.382816195487976,
|
585 |
+
"eval_precision": 0.6293475501396294,
|
586 |
+
"eval_recall": 0.692071468453378,
|
587 |
+
"eval_runtime": 2.9744,
|
588 |
+
"eval_samples_per_second": 373.857,
|
589 |
+
"eval_steps_per_second": 11.767,
|
590 |
+
"step": 9516
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 40.0,
|
594 |
+
"eval_accuracy": 0.8129577061615897,
|
595 |
+
"eval_f1": 0.6572372769332453,
|
596 |
+
"eval_loss": 1.42629873752594,
|
597 |
+
"eval_precision": 0.6241526487572182,
|
598 |
+
"eval_recall": 0.6940256839754327,
|
599 |
+
"eval_runtime": 3.0851,
|
600 |
+
"eval_samples_per_second": 360.448,
|
601 |
+
"eval_steps_per_second": 11.345,
|
602 |
+
"step": 9760
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 40.98,
|
606 |
+
"learning_rate": 1.975409836065574e-05,
|
607 |
+
"loss": 0.0086,
|
608 |
+
"step": 10000
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 41.0,
|
612 |
+
"eval_accuracy": 0.8185157796808282,
|
613 |
+
"eval_f1": 0.6573940427765386,
|
614 |
+
"eval_loss": 1.3521106243133545,
|
615 |
+
"eval_precision": 0.620203020549641,
|
616 |
+
"eval_recall": 0.6993299832495813,
|
617 |
+
"eval_runtime": 2.9673,
|
618 |
+
"eval_samples_per_second": 374.747,
|
619 |
+
"eval_steps_per_second": 11.795,
|
620 |
+
"step": 10004
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 42.0,
|
624 |
+
"eval_accuracy": 0.8196369361417906,
|
625 |
+
"eval_f1": 0.6713979646491698,
|
626 |
+
"eval_loss": 1.372209072113037,
|
627 |
+
"eval_precision": 0.6451363870303655,
|
628 |
+
"eval_recall": 0.6998883305415968,
|
629 |
+
"eval_runtime": 2.9625,
|
630 |
+
"eval_samples_per_second": 375.361,
|
631 |
+
"eval_steps_per_second": 11.814,
|
632 |
+
"step": 10248
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 43.0,
|
636 |
+
"eval_accuracy": 0.822594880847308,
|
637 |
+
"eval_f1": 0.6647074539139727,
|
638 |
+
"eval_loss": 1.3783916234970093,
|
639 |
+
"eval_precision": 0.6372950819672131,
|
640 |
+
"eval_recall": 0.6945840312674484,
|
641 |
+
"eval_runtime": 2.9632,
|
642 |
+
"eval_samples_per_second": 375.273,
|
643 |
+
"eval_steps_per_second": 11.812,
|
644 |
+
"step": 10492
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 43.03,
|
648 |
+
"learning_rate": 1.9241803278688525e-05,
|
649 |
+
"loss": 0.0075,
|
650 |
+
"step": 10500
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 44.0,
|
654 |
+
"eval_accuracy": 0.8140072994441927,
|
655 |
+
"eval_f1": 0.6623151725056613,
|
656 |
+
"eval_loss": 1.433977484703064,
|
657 |
+
"eval_precision": 0.6333757961783439,
|
658 |
+
"eval_recall": 0.6940256839754327,
|
659 |
+
"eval_runtime": 2.9882,
|
660 |
+
"eval_samples_per_second": 372.133,
|
661 |
+
"eval_steps_per_second": 11.713,
|
662 |
+
"step": 10736
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 45.0,
|
666 |
+
"eval_accuracy": 0.816130340402185,
|
667 |
+
"eval_f1": 0.6643708609271523,
|
668 |
+
"eval_loss": 1.390194058418274,
|
669 |
+
"eval_precision": 0.6320564516129032,
|
670 |
+
"eval_recall": 0.7001675041876047,
|
671 |
+
"eval_runtime": 2.9941,
|
672 |
+
"eval_samples_per_second": 371.401,
|
673 |
+
"eval_steps_per_second": 11.69,
|
674 |
+
"step": 10980
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 45.08,
|
678 |
+
"learning_rate": 1.872950819672131e-05,
|
679 |
+
"loss": 0.0066,
|
680 |
+
"step": 11000
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 46.0,
|
684 |
+
"eval_accuracy": 0.8162496123661173,
|
685 |
+
"eval_f1": 0.6585943669386681,
|
686 |
+
"eval_loss": 1.401918888092041,
|
687 |
+
"eval_precision": 0.62300796812749,
|
688 |
+
"eval_recall": 0.6984924623115578,
|
689 |
+
"eval_runtime": 2.9812,
|
690 |
+
"eval_samples_per_second": 373.006,
|
691 |
+
"eval_steps_per_second": 11.74,
|
692 |
+
"step": 11224
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 47.0,
|
696 |
+
"eval_accuracy": 0.816130340402185,
|
697 |
+
"eval_f1": 0.6548463356973996,
|
698 |
+
"eval_loss": 1.431990623474121,
|
699 |
+
"eval_precision": 0.6183035714285714,
|
700 |
+
"eval_recall": 0.6959798994974874,
|
701 |
+
"eval_runtime": 2.9274,
|
702 |
+
"eval_samples_per_second": 379.864,
|
703 |
+
"eval_steps_per_second": 11.956,
|
704 |
+
"step": 11468
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 47.13,
|
708 |
+
"learning_rate": 1.82172131147541e-05,
|
709 |
+
"loss": 0.0067,
|
710 |
+
"step": 11500
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 48.0,
|
714 |
+
"eval_accuracy": 0.8200424608191599,
|
715 |
+
"eval_f1": 0.6645460569913849,
|
716 |
+
"eval_loss": 1.4461051225662231,
|
717 |
+
"eval_precision": 0.6326015644713601,
|
718 |
+
"eval_recall": 0.6998883305415968,
|
719 |
+
"eval_runtime": 3.0764,
|
720 |
+
"eval_samples_per_second": 361.458,
|
721 |
+
"eval_steps_per_second": 11.377,
|
722 |
+
"step": 11712
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 49.0,
|
726 |
+
"eval_accuracy": 0.8202332959614513,
|
727 |
+
"eval_f1": 0.6595464135021096,
|
728 |
+
"eval_loss": 1.432677984237671,
|
729 |
+
"eval_precision": 0.6249375312343828,
|
730 |
+
"eval_recall": 0.69821328866555,
|
731 |
+
"eval_runtime": 3.0963,
|
732 |
+
"eval_samples_per_second": 359.141,
|
733 |
+
"eval_steps_per_second": 11.304,
|
734 |
+
"step": 11956
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 49.18,
|
738 |
+
"learning_rate": 1.7704918032786887e-05,
|
739 |
+
"loss": 0.0054,
|
740 |
+
"step": 12000
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 50.0,
|
744 |
+
"eval_accuracy": 0.8176331671477303,
|
745 |
+
"eval_f1": 0.6632,
|
746 |
+
"eval_loss": 1.4615715742111206,
|
747 |
+
"eval_precision": 0.6347626339969372,
|
748 |
+
"eval_recall": 0.6943048576214406,
|
749 |
+
"eval_runtime": 3.0477,
|
750 |
+
"eval_samples_per_second": 364.866,
|
751 |
+
"eval_steps_per_second": 11.484,
|
752 |
+
"step": 12200
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 51.0,
|
756 |
+
"eval_accuracy": 0.8177047303260896,
|
757 |
+
"eval_f1": 0.6543322475570033,
|
758 |
+
"eval_loss": 1.4536991119384766,
|
759 |
+
"eval_precision": 0.6134864402638651,
|
760 |
+
"eval_recall": 0.7010050251256281,
|
761 |
+
"eval_runtime": 2.9579,
|
762 |
+
"eval_samples_per_second": 375.937,
|
763 |
+
"eval_steps_per_second": 11.833,
|
764 |
+
"step": 12444
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 51.23,
|
768 |
+
"learning_rate": 1.7192622950819673e-05,
|
769 |
+
"loss": 0.0052,
|
770 |
+
"step": 12500
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 52.0,
|
774 |
+
"eval_accuracy": 0.8095703823859164,
|
775 |
+
"eval_f1": 0.6560255387071029,
|
776 |
+
"eval_loss": 1.5621511936187744,
|
777 |
+
"eval_precision": 0.6265243902439024,
|
778 |
+
"eval_recall": 0.6884422110552764,
|
779 |
+
"eval_runtime": 3.0041,
|
780 |
+
"eval_samples_per_second": 370.165,
|
781 |
+
"eval_steps_per_second": 11.651,
|
782 |
+
"step": 12688
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 53.0,
|
786 |
+
"eval_accuracy": 0.8235967653443381,
|
787 |
+
"eval_f1": 0.6670200079501789,
|
788 |
+
"eval_loss": 1.4217201471328735,
|
789 |
+
"eval_precision": 0.6348045397225726,
|
790 |
+
"eval_recall": 0.7026800670016751,
|
791 |
+
"eval_runtime": 3.0478,
|
792 |
+
"eval_samples_per_second": 364.848,
|
793 |
+
"eval_steps_per_second": 11.484,
|
794 |
+
"step": 12932
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 53.28,
|
798 |
+
"learning_rate": 1.668032786885246e-05,
|
799 |
+
"loss": 0.0051,
|
800 |
+
"step": 13000
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 54.0,
|
804 |
+
"eval_accuracy": 0.8217361227069965,
|
805 |
+
"eval_f1": 0.6597038603913273,
|
806 |
+
"eval_loss": 1.4624608755111694,
|
807 |
+
"eval_precision": 0.6265695630336514,
|
808 |
+
"eval_recall": 0.696538246789503,
|
809 |
+
"eval_runtime": 3.0888,
|
810 |
+
"eval_samples_per_second": 360.016,
|
811 |
+
"eval_steps_per_second": 11.331,
|
812 |
+
"step": 13176
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 55.0,
|
816 |
+
"eval_accuracy": 0.8257198063023306,
|
817 |
+
"eval_f1": 0.6645213193885761,
|
818 |
+
"eval_loss": 1.4358925819396973,
|
819 |
+
"eval_precision": 0.6393188854489165,
|
820 |
+
"eval_recall": 0.6917922948073701,
|
821 |
+
"eval_runtime": 3.0221,
|
822 |
+
"eval_samples_per_second": 367.953,
|
823 |
+
"eval_steps_per_second": 11.581,
|
824 |
+
"step": 13420
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 55.33,
|
828 |
+
"learning_rate": 1.6168032786885245e-05,
|
829 |
+
"loss": 0.0049,
|
830 |
+
"step": 13500
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 56.0,
|
834 |
+
"eval_accuracy": 0.8230719687030367,
|
835 |
+
"eval_f1": 0.6701528559935639,
|
836 |
+
"eval_loss": 1.4616944789886475,
|
837 |
+
"eval_precision": 0.6447368421052632,
|
838 |
+
"eval_recall": 0.6976549413735343,
|
839 |
+
"eval_runtime": 3.0092,
|
840 |
+
"eval_samples_per_second": 369.528,
|
841 |
+
"eval_steps_per_second": 11.631,
|
842 |
+
"step": 13664
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 57.0,
|
846 |
+
"eval_accuracy": 0.8181102550034589,
|
847 |
+
"eval_f1": 0.6630275595792837,
|
848 |
+
"eval_loss": 1.5170940160751343,
|
849 |
+
"eval_precision": 0.6337490455586663,
|
850 |
+
"eval_recall": 0.695142378559464,
|
851 |
+
"eval_runtime": 2.9576,
|
852 |
+
"eval_samples_per_second": 375.979,
|
853 |
+
"eval_steps_per_second": 11.834,
|
854 |
+
"step": 13908
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 57.38,
|
858 |
+
"learning_rate": 1.5655737704918035e-05,
|
859 |
+
"loss": 0.0037,
|
860 |
+
"step": 14000
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 58.0,
|
864 |
+
"eval_accuracy": 0.8205672574604613,
|
865 |
+
"eval_f1": 0.6667548967707781,
|
866 |
+
"eval_loss": 1.4998589754104614,
|
867 |
+
"eval_precision": 0.6338701560140916,
|
868 |
+
"eval_recall": 0.7032384142936907,
|
869 |
+
"eval_runtime": 2.9519,
|
870 |
+
"eval_samples_per_second": 376.709,
|
871 |
+
"eval_steps_per_second": 11.857,
|
872 |
+
"step": 14152
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 59.0,
|
876 |
+
"eval_accuracy": 0.8208296557811121,
|
877 |
+
"eval_f1": 0.6617453203269179,
|
878 |
+
"eval_loss": 1.484113335609436,
|
879 |
+
"eval_precision": 0.6268731268731269,
|
880 |
+
"eval_recall": 0.7007258514796203,
|
881 |
+
"eval_runtime": 2.9535,
|
882 |
+
"eval_samples_per_second": 376.498,
|
883 |
+
"eval_steps_per_second": 11.85,
|
884 |
+
"step": 14396
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 59.43,
|
888 |
+
"learning_rate": 1.514344262295082e-05,
|
889 |
+
"loss": 0.004,
|
890 |
+
"step": 14500
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 60.0,
|
894 |
+
"eval_accuracy": 0.8244316690918633,
|
895 |
+
"eval_f1": 0.6695859872611465,
|
896 |
+
"eval_loss": 1.436055302619934,
|
897 |
+
"eval_precision": 0.6380880121396054,
|
898 |
+
"eval_recall": 0.7043551088777219,
|
899 |
+
"eval_runtime": 2.9713,
|
900 |
+
"eval_samples_per_second": 374.253,
|
901 |
+
"eval_steps_per_second": 11.78,
|
902 |
+
"step": 14640
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 61.0,
|
906 |
+
"eval_accuracy": 0.8235252021659789,
|
907 |
+
"eval_f1": 0.6716417910447762,
|
908 |
+
"eval_loss": 1.4800474643707275,
|
909 |
+
"eval_precision": 0.6425293217746048,
|
910 |
+
"eval_recall": 0.7035175879396985,
|
911 |
+
"eval_runtime": 2.9663,
|
912 |
+
"eval_samples_per_second": 374.881,
|
913 |
+
"eval_steps_per_second": 11.799,
|
914 |
+
"step": 14884
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 61.48,
|
918 |
+
"learning_rate": 1.4631147540983607e-05,
|
919 |
+
"loss": 0.004,
|
920 |
+
"step": 15000
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 62.0,
|
924 |
+
"eval_accuracy": 0.8240977075928533,
|
925 |
+
"eval_f1": 0.664367206155479,
|
926 |
+
"eval_loss": 1.4699968099594116,
|
927 |
+
"eval_precision": 0.6329625884732053,
|
928 |
+
"eval_recall": 0.6990508096035735,
|
929 |
+
"eval_runtime": 2.9625,
|
930 |
+
"eval_samples_per_second": 375.361,
|
931 |
+
"eval_steps_per_second": 11.814,
|
932 |
+
"step": 15128
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 63.0,
|
936 |
+
"eval_accuracy": 0.821211326065695,
|
937 |
+
"eval_f1": 0.6643754130865829,
|
938 |
+
"eval_loss": 1.5107179880142212,
|
939 |
+
"eval_precision": 0.6309314586994728,
|
940 |
+
"eval_recall": 0.7015633724176438,
|
941 |
+
"eval_runtime": 2.9695,
|
942 |
+
"eval_samples_per_second": 374.47,
|
943 |
+
"eval_steps_per_second": 11.786,
|
944 |
+
"step": 15372
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 63.52,
|
948 |
+
"learning_rate": 1.4118852459016394e-05,
|
949 |
+
"loss": 0.0037,
|
950 |
+
"step": 15500
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 64.0,
|
954 |
+
"eval_accuracy": 0.8227141528112402,
|
955 |
+
"eval_f1": 0.6691489361702128,
|
956 |
+
"eval_loss": 1.5131914615631104,
|
957 |
+
"eval_precision": 0.6389029964448959,
|
958 |
+
"eval_recall": 0.7024008933556672,
|
959 |
+
"eval_runtime": 2.9514,
|
960 |
+
"eval_samples_per_second": 376.769,
|
961 |
+
"eval_steps_per_second": 11.859,
|
962 |
+
"step": 15616
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 65.0,
|
966 |
+
"eval_accuracy": 0.8239307268433482,
|
967 |
+
"eval_f1": 0.6631481725821349,
|
968 |
+
"eval_loss": 1.5229130983352661,
|
969 |
+
"eval_precision": 0.6287215411558669,
|
970 |
+
"eval_recall": 0.7015633724176438,
|
971 |
+
"eval_runtime": 3.0184,
|
972 |
+
"eval_samples_per_second": 368.409,
|
973 |
+
"eval_steps_per_second": 11.596,
|
974 |
+
"step": 15860
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 65.57,
|
978 |
+
"learning_rate": 1.3606557377049181e-05,
|
979 |
+
"loss": 0.0033,
|
980 |
+
"step": 16000
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 66.0,
|
984 |
+
"eval_accuracy": 0.8242408339495718,
|
985 |
+
"eval_f1": 0.6695929768555469,
|
986 |
+
"eval_loss": 1.5573978424072266,
|
987 |
+
"eval_precision": 0.6394817073170732,
|
988 |
+
"eval_recall": 0.7026800670016751,
|
989 |
+
"eval_runtime": 2.9796,
|
990 |
+
"eval_samples_per_second": 373.204,
|
991 |
+
"eval_steps_per_second": 11.747,
|
992 |
+
"step": 16104
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 67.0,
|
996 |
+
"eval_accuracy": 0.8195892273562176,
|
997 |
+
"eval_f1": 0.6637761135199055,
|
998 |
+
"eval_loss": 1.5216217041015625,
|
999 |
+
"eval_precision": 0.6269545793000745,
|
1000 |
+
"eval_recall": 0.7051926298157454,
|
1001 |
+
"eval_runtime": 2.9602,
|
1002 |
+
"eval_samples_per_second": 375.655,
|
1003 |
+
"eval_steps_per_second": 11.824,
|
1004 |
+
"step": 16348
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 67.62,
|
1008 |
+
"learning_rate": 1.3094262295081968e-05,
|
1009 |
+
"loss": 0.0033,
|
1010 |
+
"step": 16500
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 68.0,
|
1014 |
+
"eval_accuracy": 0.8242169795567854,
|
1015 |
+
"eval_f1": 0.6635576282478347,
|
1016 |
+
"eval_loss": 1.4876649379730225,
|
1017 |
+
"eval_precision": 0.6347183278103492,
|
1018 |
+
"eval_recall": 0.695142378559464,
|
1019 |
+
"eval_runtime": 2.9571,
|
1020 |
+
"eval_samples_per_second": 376.04,
|
1021 |
+
"eval_steps_per_second": 11.836,
|
1022 |
+
"step": 16592
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 69.0,
|
1026 |
+
"eval_accuracy": 0.8194699553922855,
|
1027 |
+
"eval_f1": 0.6630635380964935,
|
1028 |
+
"eval_loss": 1.5372997522354126,
|
1029 |
+
"eval_precision": 0.6281218781218781,
|
1030 |
+
"eval_recall": 0.7021217197096594,
|
1031 |
+
"eval_runtime": 3.0929,
|
1032 |
+
"eval_samples_per_second": 359.536,
|
1033 |
+
"eval_steps_per_second": 11.316,
|
1034 |
+
"step": 16836
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 69.67,
|
1038 |
+
"learning_rate": 1.2581967213114756e-05,
|
1039 |
+
"loss": 0.0026,
|
1040 |
+
"step": 17000
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 70.0,
|
1044 |
+
"eval_accuracy": 0.8200663152119463,
|
1045 |
+
"eval_f1": 0.6651637713831056,
|
1046 |
+
"eval_loss": 1.5521858930587769,
|
1047 |
+
"eval_precision": 0.6334933063905026,
|
1048 |
+
"eval_recall": 0.7001675041876047,
|
1049 |
+
"eval_runtime": 3.0082,
|
1050 |
+
"eval_samples_per_second": 369.652,
|
1051 |
+
"eval_steps_per_second": 11.635,
|
1052 |
+
"step": 17080
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 71.0,
|
1056 |
+
"eval_accuracy": 0.8226902984184538,
|
1057 |
+
"eval_f1": 0.6691449814126393,
|
1058 |
+
"eval_loss": 1.5180128812789917,
|
1059 |
+
"eval_precision": 0.6379746835443038,
|
1060 |
+
"eval_recall": 0.7035175879396985,
|
1061 |
+
"eval_runtime": 2.9978,
|
1062 |
+
"eval_samples_per_second": 370.939,
|
1063 |
+
"eval_steps_per_second": 11.675,
|
1064 |
+
"step": 17324
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 71.72,
|
1068 |
+
"learning_rate": 1.206967213114754e-05,
|
1069 |
+
"loss": 0.0024,
|
1070 |
+
"step": 17500
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 72.0,
|
1074 |
+
"eval_accuracy": 0.8218076858853558,
|
1075 |
+
"eval_f1": 0.67304324397144,
|
1076 |
+
"eval_loss": 1.5517120361328125,
|
1077 |
+
"eval_precision": 0.6503514709711012,
|
1078 |
+
"eval_recall": 0.6973757677275265,
|
1079 |
+
"eval_runtime": 2.9567,
|
1080 |
+
"eval_samples_per_second": 376.089,
|
1081 |
+
"eval_steps_per_second": 11.837,
|
1082 |
+
"step": 17568
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 73.0,
|
1086 |
+
"eval_accuracy": 0.8206388206388207,
|
1087 |
+
"eval_f1": 0.6658723854911305,
|
1088 |
+
"eval_loss": 1.539225697517395,
|
1089 |
+
"eval_precision": 0.6331822759315207,
|
1090 |
+
"eval_recall": 0.7021217197096594,
|
1091 |
+
"eval_runtime": 2.9669,
|
1092 |
+
"eval_samples_per_second": 374.796,
|
1093 |
+
"eval_steps_per_second": 11.797,
|
1094 |
+
"step": 17812
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 73.77,
|
1098 |
+
"learning_rate": 1.1557377049180328e-05,
|
1099 |
+
"loss": 0.0026,
|
1100 |
+
"step": 18000
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 74.0,
|
1104 |
+
"eval_accuracy": 0.8245986498413683,
|
1105 |
+
"eval_f1": 0.669957310565635,
|
1106 |
+
"eval_loss": 1.5395687818527222,
|
1107 |
+
"eval_precision": 0.641543178334185,
|
1108 |
+
"eval_recall": 0.7010050251256281,
|
1109 |
+
"eval_runtime": 2.9773,
|
1110 |
+
"eval_samples_per_second": 373.49,
|
1111 |
+
"eval_steps_per_second": 11.756,
|
1112 |
+
"step": 18056
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 75.0,
|
1116 |
+
"eval_accuracy": 0.8233343670236875,
|
1117 |
+
"eval_f1": 0.6740153246404087,
|
1118 |
+
"eval_loss": 1.5637731552124023,
|
1119 |
+
"eval_precision": 0.6499870365569095,
|
1120 |
+
"eval_recall": 0.6998883305415968,
|
1121 |
+
"eval_runtime": 2.9662,
|
1122 |
+
"eval_samples_per_second": 374.894,
|
1123 |
+
"eval_steps_per_second": 11.8,
|
1124 |
+
"step": 18300
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 75.82,
|
1128 |
+
"learning_rate": 1.1045081967213114e-05,
|
1129 |
+
"loss": 0.0019,
|
1130 |
+
"step": 18500
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 76.0,
|
1134 |
+
"eval_accuracy": 0.8201855871758784,
|
1135 |
+
"eval_f1": 0.6666666666666666,
|
1136 |
+
"eval_loss": 1.5789735317230225,
|
1137 |
+
"eval_precision": 0.6437857514300572,
|
1138 |
+
"eval_recall": 0.6912339475153545,
|
1139 |
+
"eval_runtime": 2.9784,
|
1140 |
+
"eval_samples_per_second": 373.357,
|
1141 |
+
"eval_steps_per_second": 11.751,
|
1142 |
+
"step": 18544
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 77.0,
|
1146 |
+
"eval_accuracy": 0.8216168507430643,
|
1147 |
+
"eval_f1": 0.676486341724692,
|
1148 |
+
"eval_loss": 1.5545753240585327,
|
1149 |
+
"eval_precision": 0.6500257334019557,
|
1150 |
+
"eval_recall": 0.7051926298157454,
|
1151 |
+
"eval_runtime": 2.9887,
|
1152 |
+
"eval_samples_per_second": 372.065,
|
1153 |
+
"eval_steps_per_second": 11.711,
|
1154 |
+
"step": 18788
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 77.87,
|
1158 |
+
"learning_rate": 1.0532786885245902e-05,
|
1159 |
+
"loss": 0.0029,
|
1160 |
+
"step": 19000
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 78.0,
|
1164 |
+
"eval_accuracy": 0.8236206197371246,
|
1165 |
+
"eval_f1": 0.6684357171288311,
|
1166 |
+
"eval_loss": 1.5374187231063843,
|
1167 |
+
"eval_precision": 0.6369152970922882,
|
1168 |
+
"eval_recall": 0.7032384142936907,
|
1169 |
+
"eval_runtime": 2.9659,
|
1170 |
+
"eval_samples_per_second": 374.933,
|
1171 |
+
"eval_steps_per_second": 11.801,
|
1172 |
+
"step": 19032
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 79.0,
|
1176 |
+
"eval_accuracy": 0.8180148374323132,
|
1177 |
+
"eval_f1": 0.6651595744680852,
|
1178 |
+
"eval_loss": 1.5923025608062744,
|
1179 |
+
"eval_precision": 0.6350939563230066,
|
1180 |
+
"eval_recall": 0.69821328866555,
|
1181 |
+
"eval_runtime": 2.9684,
|
1182 |
+
"eval_samples_per_second": 374.615,
|
1183 |
+
"eval_steps_per_second": 11.791,
|
1184 |
+
"step": 19276
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 79.92,
|
1188 |
+
"learning_rate": 1.0020491803278688e-05,
|
1189 |
+
"loss": 0.0015,
|
1190 |
+
"step": 19500
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 80.0,
|
1194 |
+
"eval_accuracy": 0.8245986498413683,
|
1195 |
+
"eval_f1": 0.6673737239825004,
|
1196 |
+
"eval_loss": 1.5727756023406982,
|
1197 |
+
"eval_precision": 0.6354455945468316,
|
1198 |
+
"eval_recall": 0.7026800670016751,
|
1199 |
+
"eval_runtime": 2.9791,
|
1200 |
+
"eval_samples_per_second": 373.261,
|
1201 |
+
"eval_steps_per_second": 11.748,
|
1202 |
+
"step": 19520
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 81.0,
|
1206 |
+
"eval_accuracy": 0.8228811335607452,
|
1207 |
+
"eval_f1": 0.6686279753944906,
|
1208 |
+
"eval_loss": 1.564627766609192,
|
1209 |
+
"eval_precision": 0.6416837782340863,
|
1210 |
+
"eval_recall": 0.6979341150195422,
|
1211 |
+
"eval_runtime": 2.9678,
|
1212 |
+
"eval_samples_per_second": 374.693,
|
1213 |
+
"eval_steps_per_second": 11.793,
|
1214 |
+
"step": 19764
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 81.97,
|
1218 |
+
"learning_rate": 9.508196721311476e-06,
|
1219 |
+
"loss": 0.0019,
|
1220 |
+
"step": 20000
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 82.0,
|
1224 |
+
"eval_accuracy": 0.8210920541017629,
|
1225 |
+
"eval_f1": 0.6615000656771313,
|
1226 |
+
"eval_loss": 1.5844708681106567,
|
1227 |
+
"eval_precision": 0.6246588935747953,
|
1228 |
+
"eval_recall": 0.7029592406476829,
|
1229 |
+
"eval_runtime": 2.9641,
|
1230 |
+
"eval_samples_per_second": 375.15,
|
1231 |
+
"eval_steps_per_second": 11.808,
|
1232 |
+
"step": 20008
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 83.0,
|
1236 |
+
"eval_accuracy": 0.819279120249994,
|
1237 |
+
"eval_f1": 0.666935159081756,
|
1238 |
+
"eval_loss": 1.589419960975647,
|
1239 |
+
"eval_precision": 0.6423584173778123,
|
1240 |
+
"eval_recall": 0.6934673366834171,
|
1241 |
+
"eval_runtime": 2.9637,
|
1242 |
+
"eval_samples_per_second": 375.21,
|
1243 |
+
"eval_steps_per_second": 11.81,
|
1244 |
+
"step": 20252
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 84.0,
|
1248 |
+
"eval_accuracy": 0.8169175353641374,
|
1249 |
+
"eval_f1": 0.665859238325932,
|
1250 |
+
"eval_loss": 1.6702436208724976,
|
1251 |
+
"eval_precision": 0.6427643543777605,
|
1252 |
+
"eval_recall": 0.690675600223339,
|
1253 |
+
"eval_runtime": 2.99,
|
1254 |
+
"eval_samples_per_second": 371.906,
|
1255 |
+
"eval_steps_per_second": 11.706,
|
1256 |
+
"step": 20496
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 84.02,
|
1260 |
+
"learning_rate": 8.995901639344264e-06,
|
1261 |
+
"loss": 0.0012,
|
1262 |
+
"step": 20500
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 85.0,
|
1266 |
+
"eval_accuracy": 0.8188974499654111,
|
1267 |
+
"eval_f1": 0.6666666666666667,
|
1268 |
+
"eval_loss": 1.6313210725784302,
|
1269 |
+
"eval_precision": 0.6341647770219199,
|
1270 |
+
"eval_recall": 0.7026800670016751,
|
1271 |
+
"eval_runtime": 3.0786,
|
1272 |
+
"eval_samples_per_second": 361.198,
|
1273 |
+
"eval_steps_per_second": 11.369,
|
1274 |
+
"step": 20740
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 86.0,
|
1278 |
+
"eval_accuracy": 0.8231912406669688,
|
1279 |
+
"eval_f1": 0.6679915209326974,
|
1280 |
+
"eval_loss": 1.5829322338104248,
|
1281 |
+
"eval_precision": 0.6356530509329299,
|
1282 |
+
"eval_recall": 0.7037967615857063,
|
1283 |
+
"eval_runtime": 2.9543,
|
1284 |
+
"eval_samples_per_second": 376.397,
|
1285 |
+
"eval_steps_per_second": 11.847,
|
1286 |
+
"step": 20984
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 86.07,
|
1290 |
+
"learning_rate": 8.483606557377049e-06,
|
1291 |
+
"loss": 0.0015,
|
1292 |
+
"step": 21000
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 87.0,
|
1296 |
+
"eval_accuracy": 0.8209966365306172,
|
1297 |
+
"eval_f1": 0.672317880794702,
|
1298 |
+
"eval_loss": 1.605576753616333,
|
1299 |
+
"eval_precision": 0.639616935483871,
|
1300 |
+
"eval_recall": 0.7085427135678392,
|
1301 |
+
"eval_runtime": 2.9894,
|
1302 |
+
"eval_samples_per_second": 371.983,
|
1303 |
+
"eval_steps_per_second": 11.708,
|
1304 |
+
"step": 21228
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 88.0,
|
1308 |
+
"eval_accuracy": 0.8224994632761623,
|
1309 |
+
"eval_f1": 0.6773120425815037,
|
1310 |
+
"eval_loss": 1.5823140144348145,
|
1311 |
+
"eval_precision": 0.6470887363335875,
|
1312 |
+
"eval_recall": 0.7104969290898939,
|
1313 |
+
"eval_runtime": 2.973,
|
1314 |
+
"eval_samples_per_second": 374.028,
|
1315 |
+
"eval_steps_per_second": 11.772,
|
1316 |
+
"step": 21472
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"epoch": 88.11,
|
1320 |
+
"learning_rate": 7.971311475409837e-06,
|
1321 |
+
"loss": 0.0015,
|
1322 |
+
"step": 21500
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 89.0,
|
1326 |
+
"eval_accuracy": 0.8249326113403783,
|
1327 |
+
"eval_f1": 0.6675521317572054,
|
1328 |
+
"eval_loss": 1.573556661605835,
|
1329 |
+
"eval_precision": 0.6366860907017988,
|
1330 |
+
"eval_recall": 0.7015633724176438,
|
1331 |
+
"eval_runtime": 2.9619,
|
1332 |
+
"eval_samples_per_second": 375.438,
|
1333 |
+
"eval_steps_per_second": 11.817,
|
1334 |
+
"step": 21716
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 90.0,
|
1338 |
+
"eval_accuracy": 0.823644474129911,
|
1339 |
+
"eval_f1": 0.6724645437516724,
|
1340 |
+
"eval_loss": 1.5920721292495728,
|
1341 |
+
"eval_precision": 0.64568345323741,
|
1342 |
+
"eval_recall": 0.7015633724176438,
|
1343 |
+
"eval_runtime": 2.9692,
|
1344 |
+
"eval_samples_per_second": 374.506,
|
1345 |
+
"eval_steps_per_second": 11.788,
|
1346 |
+
"step": 21960
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 90.16,
|
1350 |
+
"learning_rate": 7.459016393442623e-06,
|
1351 |
+
"loss": 0.0012,
|
1352 |
+
"step": 22000
|
1353 |
+
},
|
1354 |
+
{
|
1355 |
+
"epoch": 91.0,
|
1356 |
+
"eval_accuracy": 0.8230958230958231,
|
1357 |
+
"eval_f1": 0.6684364215556146,
|
1358 |
+
"eval_loss": 1.6113594770431519,
|
1359 |
+
"eval_precision": 0.6371457489878543,
|
1360 |
+
"eval_recall": 0.7029592406476829,
|
1361 |
+
"eval_runtime": 2.9681,
|
1362 |
+
"eval_samples_per_second": 374.651,
|
1363 |
+
"eval_steps_per_second": 11.792,
|
1364 |
+
"step": 22204
|
1365 |
+
},
|
1366 |
+
{
|
1367 |
+
"epoch": 92.0,
|
1368 |
+
"eval_accuracy": 0.824527086663009,
|
1369 |
+
"eval_f1": 0.6708355508249069,
|
1370 |
+
"eval_loss": 1.5752336978912354,
|
1371 |
+
"eval_precision": 0.6408235892221658,
|
1372 |
+
"eval_recall": 0.7037967615857063,
|
1373 |
+
"eval_runtime": 2.9615,
|
1374 |
+
"eval_samples_per_second": 375.482,
|
1375 |
+
"eval_steps_per_second": 11.818,
|
1376 |
+
"step": 22448
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"epoch": 92.21,
|
1380 |
+
"learning_rate": 6.946721311475411e-06,
|
1381 |
+
"loss": 0.0014,
|
1382 |
+
"step": 22500
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 93.0,
|
1386 |
+
"eval_accuracy": 0.8216884139214237,
|
1387 |
+
"eval_f1": 0.6672859986728599,
|
1388 |
+
"eval_loss": 1.6123404502868652,
|
1389 |
+
"eval_precision": 0.6359726789779914,
|
1390 |
+
"eval_recall": 0.7018425460636516,
|
1391 |
+
"eval_runtime": 3.0214,
|
1392 |
+
"eval_samples_per_second": 368.046,
|
1393 |
+
"eval_steps_per_second": 11.584,
|
1394 |
+
"step": 22692
|
1395 |
+
},
|
1396 |
+
{
|
1397 |
+
"epoch": 94.0,
|
1398 |
+
"eval_accuracy": 0.8221177929915794,
|
1399 |
+
"eval_f1": 0.6681721572794899,
|
1400 |
+
"eval_loss": 1.618289589881897,
|
1401 |
+
"eval_precision": 0.6373542828180436,
|
1402 |
+
"eval_recall": 0.7021217197096594,
|
1403 |
+
"eval_runtime": 2.9574,
|
1404 |
+
"eval_samples_per_second": 376.01,
|
1405 |
+
"eval_steps_per_second": 11.835,
|
1406 |
+
"step": 22936
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"epoch": 94.26,
|
1410 |
+
"learning_rate": 6.434426229508197e-06,
|
1411 |
+
"loss": 0.0009,
|
1412 |
+
"step": 23000
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 95.0,
|
1416 |
+
"eval_accuracy": 0.8274611769757401,
|
1417 |
+
"eval_f1": 0.6721267454350162,
|
1418 |
+
"eval_loss": 1.6077880859375,
|
1419 |
+
"eval_precision": 0.6474392136575272,
|
1420 |
+
"eval_recall": 0.6987716359575656,
|
1421 |
+
"eval_runtime": 2.9598,
|
1422 |
+
"eval_samples_per_second": 375.703,
|
1423 |
+
"eval_steps_per_second": 11.825,
|
1424 |
+
"step": 23180
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 96.0,
|
1428 |
+
"eval_accuracy": 0.8245747954485818,
|
1429 |
+
"eval_f1": 0.6682679476914866,
|
1430 |
+
"eval_loss": 1.6201205253601074,
|
1431 |
+
"eval_precision": 0.6400817995910021,
|
1432 |
+
"eval_recall": 0.6990508096035735,
|
1433 |
+
"eval_runtime": 2.9623,
|
1434 |
+
"eval_samples_per_second": 375.385,
|
1435 |
+
"eval_steps_per_second": 11.815,
|
1436 |
+
"step": 23424
|
1437 |
+
},
|
1438 |
+
{
|
1439 |
+
"epoch": 96.31,
|
1440 |
+
"learning_rate": 5.922131147540984e-06,
|
1441 |
+
"loss": 0.0008,
|
1442 |
+
"step": 23500
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"epoch": 97.0,
|
1446 |
+
"eval_accuracy": 0.8238114548794161,
|
1447 |
+
"eval_f1": 0.6687067589143161,
|
1448 |
+
"eval_loss": 1.6216107606887817,
|
1449 |
+
"eval_precision": 0.6387900355871886,
|
1450 |
+
"eval_recall": 0.7015633724176438,
|
1451 |
+
"eval_runtime": 2.9859,
|
1452 |
+
"eval_samples_per_second": 372.411,
|
1453 |
+
"eval_steps_per_second": 11.722,
|
1454 |
+
"step": 23668
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"epoch": 98.0,
|
1458 |
+
"eval_accuracy": 0.8243839603062904,
|
1459 |
+
"eval_f1": 0.6703077128013853,
|
1460 |
+
"eval_loss": 1.6113009452819824,
|
1461 |
+
"eval_precision": 0.6410191082802548,
|
1462 |
+
"eval_recall": 0.7024008933556672,
|
1463 |
+
"eval_runtime": 2.9619,
|
1464 |
+
"eval_samples_per_second": 375.438,
|
1465 |
+
"eval_steps_per_second": 11.817,
|
1466 |
+
"step": 23912
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 98.36,
|
1470 |
+
"learning_rate": 5.409836065573771e-06,
|
1471 |
+
"loss": 0.0011,
|
1472 |
+
"step": 24000
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 99.0,
|
1476 |
+
"eval_accuracy": 0.824527086663009,
|
1477 |
+
"eval_f1": 0.6751609442060086,
|
1478 |
+
"eval_loss": 1.5995452404022217,
|
1479 |
+
"eval_precision": 0.6497160557563242,
|
1480 |
+
"eval_recall": 0.7026800670016751,
|
1481 |
+
"eval_runtime": 3.0743,
|
1482 |
+
"eval_samples_per_second": 361.705,
|
1483 |
+
"eval_steps_per_second": 11.385,
|
1484 |
+
"step": 24156
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"epoch": 100.0,
|
1488 |
+
"eval_accuracy": 0.8258629326590492,
|
1489 |
+
"eval_f1": 0.6711105185975204,
|
1490 |
+
"eval_loss": 1.5953351259231567,
|
1491 |
+
"eval_precision": 0.642255677468742,
|
1492 |
+
"eval_recall": 0.7026800670016751,
|
1493 |
+
"eval_runtime": 2.974,
|
1494 |
+
"eval_samples_per_second": 373.912,
|
1495 |
+
"eval_steps_per_second": 11.769,
|
1496 |
+
"step": 24400
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 100.41,
|
1500 |
+
"learning_rate": 4.897540983606557e-06,
|
1501 |
+
"loss": 0.0009,
|
1502 |
+
"step": 24500
|
1503 |
+
},
|
1504 |
+
{
|
1505 |
+
"epoch": 101.0,
|
1506 |
+
"eval_accuracy": 0.8247894849836598,
|
1507 |
+
"eval_f1": 0.6724552497996259,
|
1508 |
+
"eval_loss": 1.6178245544433594,
|
1509 |
+
"eval_precision": 0.6447233606557377,
|
1510 |
+
"eval_recall": 0.7026800670016751,
|
1511 |
+
"eval_runtime": 3.0886,
|
1512 |
+
"eval_samples_per_second": 360.031,
|
1513 |
+
"eval_steps_per_second": 11.332,
|
1514 |
+
"step": 24644
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 102.0,
|
1518 |
+
"eval_accuracy": 0.8256720975167577,
|
1519 |
+
"eval_f1": 0.67206585236325,
|
1520 |
+
"eval_loss": 1.6170806884765625,
|
1521 |
+
"eval_precision": 0.640759493670886,
|
1522 |
+
"eval_recall": 0.7065884980457845,
|
1523 |
+
"eval_runtime": 2.967,
|
1524 |
+
"eval_samples_per_second": 374.794,
|
1525 |
+
"eval_steps_per_second": 11.797,
|
1526 |
+
"step": 24888
|
1527 |
+
},
|
1528 |
+
{
|
1529 |
+
"epoch": 102.46,
|
1530 |
+
"learning_rate": 4.385245901639344e-06,
|
1531 |
+
"loss": 0.0006,
|
1532 |
+
"step": 25000
|
1533 |
+
},
|
1534 |
+
{
|
1535 |
+
"epoch": 103.0,
|
1536 |
+
"eval_accuracy": 0.8270795066911572,
|
1537 |
+
"eval_f1": 0.6780794436271232,
|
1538 |
+
"eval_loss": 1.6054375171661377,
|
1539 |
+
"eval_precision": 0.6508344030808729,
|
1540 |
+
"eval_recall": 0.7077051926298158,
|
1541 |
+
"eval_runtime": 2.9599,
|
1542 |
+
"eval_samples_per_second": 375.683,
|
1543 |
+
"eval_steps_per_second": 11.825,
|
1544 |
+
"step": 25132
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"epoch": 104.0,
|
1548 |
+
"eval_accuracy": 0.8251234464826698,
|
1549 |
+
"eval_f1": 0.6701319472211115,
|
1550 |
+
"eval_loss": 1.621781826019287,
|
1551 |
+
"eval_precision": 0.6411629686304514,
|
1552 |
+
"eval_recall": 0.7018425460636516,
|
1553 |
+
"eval_runtime": 3.0743,
|
1554 |
+
"eval_samples_per_second": 361.711,
|
1555 |
+
"eval_steps_per_second": 11.385,
|
1556 |
+
"step": 25376
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 104.51,
|
1560 |
+
"learning_rate": 3.872950819672131e-06,
|
1561 |
+
"loss": 0.0008,
|
1562 |
+
"step": 25500
|
1563 |
+
},
|
1564 |
+
{
|
1565 |
+
"epoch": 105.0,
|
1566 |
+
"eval_accuracy": 0.8244555234846497,
|
1567 |
+
"eval_f1": 0.6738082485270488,
|
1568 |
+
"eval_loss": 1.6307542324066162,
|
1569 |
+
"eval_precision": 0.6474523932063819,
|
1570 |
+
"eval_recall": 0.7024008933556672,
|
1571 |
+
"eval_runtime": 2.9786,
|
1572 |
+
"eval_samples_per_second": 373.327,
|
1573 |
+
"eval_steps_per_second": 11.75,
|
1574 |
+
"step": 25620
|
1575 |
+
},
|
1576 |
+
{
|
1577 |
+
"epoch": 106.0,
|
1578 |
+
"eval_accuracy": 0.8267216907993608,
|
1579 |
+
"eval_f1": 0.6755638596022955,
|
1580 |
+
"eval_loss": 1.6341726779937744,
|
1581 |
+
"eval_precision": 0.6471490667348504,
|
1582 |
+
"eval_recall": 0.7065884980457845,
|
1583 |
+
"eval_runtime": 2.9836,
|
1584 |
+
"eval_samples_per_second": 372.709,
|
1585 |
+
"eval_steps_per_second": 11.731,
|
1586 |
+
"step": 25864
|
1587 |
+
},
|
1588 |
+
{
|
1589 |
+
"epoch": 106.56,
|
1590 |
+
"learning_rate": 3.3606557377049183e-06,
|
1591 |
+
"loss": 0.0004,
|
1592 |
+
"step": 26000
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 107.0,
|
1596 |
+
"eval_accuracy": 0.8253619904105342,
|
1597 |
+
"eval_f1": 0.673863787818206,
|
1598 |
+
"eval_loss": 1.634595274925232,
|
1599 |
+
"eval_precision": 0.6447334863555215,
|
1600 |
+
"eval_recall": 0.705750977107761,
|
1601 |
+
"eval_runtime": 2.9821,
|
1602 |
+
"eval_samples_per_second": 372.893,
|
1603 |
+
"eval_steps_per_second": 11.737,
|
1604 |
+
"step": 26108
|
1605 |
+
},
|
1606 |
+
{
|
1607 |
+
"epoch": 108.0,
|
1608 |
+
"eval_accuracy": 0.825743660695117,
|
1609 |
+
"eval_f1": 0.6736758051636944,
|
1610 |
+
"eval_loss": 1.6328423023223877,
|
1611 |
+
"eval_precision": 0.6436927772126144,
|
1612 |
+
"eval_recall": 0.7065884980457845,
|
1613 |
+
"eval_runtime": 2.998,
|
1614 |
+
"eval_samples_per_second": 370.912,
|
1615 |
+
"eval_steps_per_second": 11.674,
|
1616 |
+
"step": 26352
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 108.61,
|
1620 |
+
"learning_rate": 2.848360655737705e-06,
|
1621 |
+
"loss": 0.0008,
|
1622 |
+
"step": 26500
|
1623 |
+
},
|
1624 |
+
{
|
1625 |
+
"epoch": 109.0,
|
1626 |
+
"eval_accuracy": 0.8256720975167577,
|
1627 |
+
"eval_f1": 0.674515050167224,
|
1628 |
+
"eval_loss": 1.6220307350158691,
|
1629 |
+
"eval_precision": 0.6475725661443616,
|
1630 |
+
"eval_recall": 0.7037967615857063,
|
1631 |
+
"eval_runtime": 2.9865,
|
1632 |
+
"eval_samples_per_second": 372.341,
|
1633 |
+
"eval_steps_per_second": 11.719,
|
1634 |
+
"step": 26596
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 110.0,
|
1638 |
+
"eval_accuracy": 0.8276281577252451,
|
1639 |
+
"eval_f1": 0.6784613322610911,
|
1640 |
+
"eval_loss": 1.6160385608673096,
|
1641 |
+
"eval_precision": 0.6524877545759217,
|
1642 |
+
"eval_recall": 0.7065884980457845,
|
1643 |
+
"eval_runtime": 2.9726,
|
1644 |
+
"eval_samples_per_second": 374.081,
|
1645 |
+
"eval_steps_per_second": 11.774,
|
1646 |
+
"step": 26840
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"epoch": 110.66,
|
1650 |
+
"learning_rate": 2.336065573770492e-06,
|
1651 |
+
"loss": 0.0006,
|
1652 |
+
"step": 27000
|
1653 |
+
},
|
1654 |
+
{
|
1655 |
+
"epoch": 111.0,
|
1656 |
+
"eval_accuracy": 0.8270079435127978,
|
1657 |
+
"eval_f1": 0.6741363211951447,
|
1658 |
+
"eval_loss": 1.609981656074524,
|
1659 |
+
"eval_precision": 0.6454661558109834,
|
1660 |
+
"eval_recall": 0.7054718034617532,
|
1661 |
+
"eval_runtime": 2.9645,
|
1662 |
+
"eval_samples_per_second": 375.104,
|
1663 |
+
"eval_steps_per_second": 11.806,
|
1664 |
+
"step": 27084
|
1665 |
+
},
|
1666 |
+
{
|
1667 |
+
"epoch": 112.0,
|
1668 |
+
"eval_accuracy": 0.8246702130197275,
|
1669 |
+
"eval_f1": 0.6708255906556942,
|
1670 |
+
"eval_loss": 1.6269794702529907,
|
1671 |
+
"eval_precision": 0.6394230769230769,
|
1672 |
+
"eval_recall": 0.7054718034617532,
|
1673 |
+
"eval_runtime": 2.9668,
|
1674 |
+
"eval_samples_per_second": 374.813,
|
1675 |
+
"eval_steps_per_second": 11.797,
|
1676 |
+
"step": 27328
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 112.7,
|
1680 |
+
"learning_rate": 1.8237704918032786e-06,
|
1681 |
+
"loss": 0.0005,
|
1682 |
+
"step": 27500
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 113.0,
|
1686 |
+
"eval_accuracy": 0.8273180506190215,
|
1687 |
+
"eval_f1": 0.6754362416107383,
|
1688 |
+
"eval_loss": 1.6233818531036377,
|
1689 |
+
"eval_precision": 0.6504653567735263,
|
1690 |
+
"eval_recall": 0.7024008933556672,
|
1691 |
+
"eval_runtime": 2.9684,
|
1692 |
+
"eval_samples_per_second": 374.612,
|
1693 |
+
"eval_steps_per_second": 11.791,
|
1694 |
+
"step": 27572
|
1695 |
+
},
|
1696 |
+
{
|
1697 |
+
"epoch": 114.0,
|
1698 |
+
"eval_accuracy": 0.8252188640538155,
|
1699 |
+
"eval_f1": 0.6711945665201757,
|
1700 |
+
"eval_loss": 1.632752537727356,
|
1701 |
+
"eval_precision": 0.6417112299465241,
|
1702 |
+
"eval_recall": 0.7035175879396985,
|
1703 |
+
"eval_runtime": 2.9514,
|
1704 |
+
"eval_samples_per_second": 376.771,
|
1705 |
+
"eval_steps_per_second": 11.859,
|
1706 |
+
"step": 27816
|
1707 |
+
},
|
1708 |
+
{
|
1709 |
+
"epoch": 114.75,
|
1710 |
+
"learning_rate": 1.3114754098360657e-06,
|
1711 |
+
"loss": 0.0004,
|
1712 |
+
"step": 28000
|
1713 |
+
},
|
1714 |
+
{
|
1715 |
+
"epoch": 115.0,
|
1716 |
+
"eval_accuracy": 0.8251473008754562,
|
1717 |
+
"eval_f1": 0.6710262912051248,
|
1718 |
+
"eval_loss": 1.635224461555481,
|
1719 |
+
"eval_precision": 0.6428023523395551,
|
1720 |
+
"eval_recall": 0.7018425460636516,
|
1721 |
+
"eval_runtime": 2.9586,
|
1722 |
+
"eval_samples_per_second": 375.859,
|
1723 |
+
"eval_steps_per_second": 11.83,
|
1724 |
+
"step": 28060
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 116.0,
|
1728 |
+
"eval_accuracy": 0.8265308556570693,
|
1729 |
+
"eval_f1": 0.6743162108072048,
|
1730 |
+
"eval_loss": 1.6268539428710938,
|
1731 |
+
"eval_precision": 0.6457960644007156,
|
1732 |
+
"eval_recall": 0.7054718034617532,
|
1733 |
+
"eval_runtime": 3.1118,
|
1734 |
+
"eval_samples_per_second": 357.346,
|
1735 |
+
"eval_steps_per_second": 11.247,
|
1736 |
+
"step": 28304
|
1737 |
+
},
|
1738 |
+
{
|
1739 |
+
"epoch": 116.8,
|
1740 |
+
"learning_rate": 7.991803278688524e-07,
|
1741 |
+
"loss": 0.0005,
|
1742 |
+
"step": 28500
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 117.0,
|
1746 |
+
"eval_accuracy": 0.8253381360177476,
|
1747 |
+
"eval_f1": 0.6728024543150594,
|
1748 |
+
"eval_loss": 1.6376687288284302,
|
1749 |
+
"eval_precision": 0.6441890166028097,
|
1750 |
+
"eval_recall": 0.7040759352317141,
|
1751 |
+
"eval_runtime": 2.9567,
|
1752 |
+
"eval_samples_per_second": 376.091,
|
1753 |
+
"eval_steps_per_second": 11.837,
|
1754 |
+
"step": 28548
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 118.0,
|
1758 |
+
"eval_accuracy": 0.8256959519095441,
|
1759 |
+
"eval_f1": 0.6736027744431106,
|
1760 |
+
"eval_loss": 1.6352702379226685,
|
1761 |
+
"eval_precision": 0.644955300127714,
|
1762 |
+
"eval_recall": 0.7049134561697376,
|
1763 |
+
"eval_runtime": 2.977,
|
1764 |
+
"eval_samples_per_second": 373.528,
|
1765 |
+
"eval_steps_per_second": 11.757,
|
1766 |
+
"step": 28792
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 118.85,
|
1770 |
+
"learning_rate": 2.8688524590163937e-07,
|
1771 |
+
"loss": 0.0004,
|
1772 |
+
"step": 29000
|
1773 |
+
},
|
1774 |
+
{
|
1775 |
+
"epoch": 119.0,
|
1776 |
+
"eval_accuracy": 0.825743660695117,
|
1777 |
+
"eval_f1": 0.6747793527681197,
|
1778 |
+
"eval_loss": 1.6394999027252197,
|
1779 |
+
"eval_precision": 0.6475872689938398,
|
1780 |
+
"eval_recall": 0.7043551088777219,
|
1781 |
+
"eval_runtime": 2.9575,
|
1782 |
+
"eval_samples_per_second": 375.995,
|
1783 |
+
"eval_steps_per_second": 11.834,
|
1784 |
+
"step": 29036
|
1785 |
+
},
|
1786 |
+
{
|
1787 |
+
"epoch": 120.0,
|
1788 |
+
"eval_accuracy": 0.8256005343383984,
|
1789 |
+
"eval_f1": 0.6740641711229947,
|
1790 |
+
"eval_loss": 1.6384611129760742,
|
1791 |
+
"eval_precision": 0.6467419189327861,
|
1792 |
+
"eval_recall": 0.7037967615857063,
|
1793 |
+
"eval_runtime": 2.9942,
|
1794 |
+
"eval_samples_per_second": 371.386,
|
1795 |
+
"eval_steps_per_second": 11.689,
|
1796 |
+
"step": 29280
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 120.0,
|
1800 |
+
"step": 29280,
|
1801 |
+
"total_flos": 1.220726808511488e+17,
|
1802 |
+
"train_loss": 0.045685164459416124,
|
1803 |
+
"train_runtime": 6878.0479,
|
1804 |
+
"train_samples_per_second": 135.823,
|
1805 |
+
"train_steps_per_second": 4.257
|
1806 |
+
}
|
1807 |
+
],
|
1808 |
+
"max_steps": 29280,
|
1809 |
+
"num_train_epochs": 120,
|
1810 |
+
"total_flos": 1.220726808511488e+17,
|
1811 |
+
"trial_name": null,
|
1812 |
+
"trial_params": null
|
1813 |
+
}
|