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 +2161 -0
all_results.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 120.0,
|
| 3 |
+
"eval_accuracy": 0.8296796355048782,
|
| 4 |
+
"eval_f1": 0.7018599562363238,
|
| 5 |
+
"eval_loss": 1.8209294080734253,
|
| 6 |
+
"eval_precision": 0.6879356568364611,
|
| 7 |
+
"eval_recall": 0.7163595756560581,
|
| 8 |
+
"eval_runtime": 7.2233,
|
| 9 |
+
"eval_samples": 1112,
|
| 10 |
+
"eval_samples_per_second": 153.946,
|
| 11 |
+
"eval_steps_per_second": 9.691,
|
| 12 |
+
"predict_accuracy": 0.8337691270446151,
|
| 13 |
+
"predict_f1": 0.6978635423845624,
|
| 14 |
+
"predict_loss": 1.762173056602478,
|
| 15 |
+
"predict_precision": 0.6780500870496853,
|
| 16 |
+
"predict_recall": 0.7188697998012211,
|
| 17 |
+
"predict_runtime": 14.232,
|
| 18 |
+
"predict_samples_per_second": 156.338,
|
| 19 |
+
"predict_steps_per_second": 9.837,
|
| 20 |
+
"train_loss": 0.033376370980433,
|
| 21 |
+
"train_runtime": 20083.166,
|
| 22 |
+
"train_samples": 7785,
|
| 23 |
+
"train_samples_per_second": 46.517,
|
| 24 |
+
"train_steps_per_second": 2.91
|
| 25 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 120.0,
|
| 3 |
+
"eval_accuracy": 0.8296796355048782,
|
| 4 |
+
"eval_f1": 0.7018599562363238,
|
| 5 |
+
"eval_loss": 1.8209294080734253,
|
| 6 |
+
"eval_precision": 0.6879356568364611,
|
| 7 |
+
"eval_recall": 0.7163595756560581,
|
| 8 |
+
"eval_runtime": 7.2233,
|
| 9 |
+
"eval_samples": 1112,
|
| 10 |
+
"eval_samples_per_second": 153.946,
|
| 11 |
+
"eval_steps_per_second": 9.691
|
| 12 |
+
}
|
predict_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_accuracy": 0.8337691270446151,
|
| 3 |
+
"predict_f1": 0.6978635423845624,
|
| 4 |
+
"predict_loss": 1.762173056602478,
|
| 5 |
+
"predict_precision": 0.6780500870496853,
|
| 6 |
+
"predict_recall": 0.7188697998012211,
|
| 7 |
+
"predict_runtime": 14.232,
|
| 8 |
+
"predict_samples_per_second": 156.338,
|
| 9 |
+
"predict_steps_per_second": 9.837
|
| 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": 0.033376370980433,
|
| 4 |
+
"train_runtime": 20083.166,
|
| 5 |
+
"train_samples": 7785,
|
| 6 |
+
"train_samples_per_second": 46.517,
|
| 7 |
+
"train_steps_per_second": 2.91
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7018599562363238,
|
| 3 |
+
"best_model_checkpoint": "/tmp/test-ner1_/checkpoint-52109",
|
| 4 |
+
"epoch": 120.0,
|
| 5 |
+
"global_step": 58440,
|
| 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": 0.7978578755277784,
|
| 13 |
+
"eval_f1": 0.5672056594239515,
|
| 14 |
+
"eval_loss": 0.6516662240028381,
|
| 15 |
+
"eval_precision": 0.5179972311952007,
|
| 16 |
+
"eval_recall": 0.6267448352875489,
|
| 17 |
+
"eval_runtime": 6.9697,
|
| 18 |
+
"eval_samples_per_second": 159.549,
|
| 19 |
+
"eval_steps_per_second": 10.044,
|
| 20 |
+
"step": 487
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.03,
|
| 24 |
+
"learning_rate": 2.9743326488706367e-05,
|
| 25 |
+
"loss": 1.0091,
|
| 26 |
+
"step": 500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.0,
|
| 30 |
+
"eval_accuracy": 0.8116457145583359,
|
| 31 |
+
"eval_f1": 0.5956049507451376,
|
| 32 |
+
"eval_loss": 0.6197972893714905,
|
| 33 |
+
"eval_precision": 0.5438191881918819,
|
| 34 |
+
"eval_recall": 0.6582914572864321,
|
| 35 |
+
"eval_runtime": 6.8446,
|
| 36 |
+
"eval_samples_per_second": 162.464,
|
| 37 |
+
"eval_steps_per_second": 10.227,
|
| 38 |
+
"step": 974
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.05,
|
| 42 |
+
"learning_rate": 2.9486652977412733e-05,
|
| 43 |
+
"loss": 0.5042,
|
| 44 |
+
"step": 1000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"eval_accuracy": 0.8094272560291977,
|
| 49 |
+
"eval_f1": 0.616483796886961,
|
| 50 |
+
"eval_loss": 0.6614459753036499,
|
| 51 |
+
"eval_precision": 0.5676691729323309,
|
| 52 |
+
"eval_recall": 0.6744835287548855,
|
| 53 |
+
"eval_runtime": 6.7608,
|
| 54 |
+
"eval_samples_per_second": 164.478,
|
| 55 |
+
"eval_steps_per_second": 10.354,
|
| 56 |
+
"step": 1461
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.08,
|
| 60 |
+
"learning_rate": 2.9229979466119096e-05,
|
| 61 |
+
"loss": 0.3543,
|
| 62 |
+
"step": 1500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"eval_accuracy": 0.8230719687030367,
|
| 67 |
+
"eval_f1": 0.6266820453671665,
|
| 68 |
+
"eval_loss": 0.6793712377548218,
|
| 69 |
+
"eval_precision": 0.5792466240227434,
|
| 70 |
+
"eval_recall": 0.6825795644891123,
|
| 71 |
+
"eval_runtime": 7.0887,
|
| 72 |
+
"eval_samples_per_second": 156.869,
|
| 73 |
+
"eval_steps_per_second": 9.875,
|
| 74 |
+
"step": 1948
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 4.11,
|
| 78 |
+
"learning_rate": 2.8973305954825462e-05,
|
| 79 |
+
"loss": 0.2476,
|
| 80 |
+
"step": 2000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 5.0,
|
| 84 |
+
"eval_accuracy": 0.8249326113403783,
|
| 85 |
+
"eval_f1": 0.653114074841383,
|
| 86 |
+
"eval_loss": 0.7132434248924255,
|
| 87 |
+
"eval_precision": 0.6090316348708041,
|
| 88 |
+
"eval_recall": 0.7040759352317141,
|
| 89 |
+
"eval_runtime": 6.8077,
|
| 90 |
+
"eval_samples_per_second": 163.344,
|
| 91 |
+
"eval_steps_per_second": 10.282,
|
| 92 |
+
"step": 2435
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.13,
|
| 96 |
+
"learning_rate": 2.8716632443531828e-05,
|
| 97 |
+
"loss": 0.1849,
|
| 98 |
+
"step": 2500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.0,
|
| 102 |
+
"eval_accuracy": 0.8218553946709286,
|
| 103 |
+
"eval_f1": 0.6443319049474094,
|
| 104 |
+
"eval_loss": 0.776131272315979,
|
| 105 |
+
"eval_precision": 0.6023306627822287,
|
| 106 |
+
"eval_recall": 0.6926298157453936,
|
| 107 |
+
"eval_runtime": 6.8192,
|
| 108 |
+
"eval_samples_per_second": 163.07,
|
| 109 |
+
"eval_steps_per_second": 10.265,
|
| 110 |
+
"step": 2922
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 6.16,
|
| 114 |
+
"learning_rate": 2.8459958932238194e-05,
|
| 115 |
+
"loss": 0.1465,
|
| 116 |
+
"step": 3000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 7.0,
|
| 120 |
+
"eval_accuracy": 0.8172992056487202,
|
| 121 |
+
"eval_f1": 0.6444159178433889,
|
| 122 |
+
"eval_loss": 0.8293828368186951,
|
| 123 |
+
"eval_precision": 0.5964828897338403,
|
| 124 |
+
"eval_recall": 0.7007258514796203,
|
| 125 |
+
"eval_runtime": 6.7817,
|
| 126 |
+
"eval_samples_per_second": 163.971,
|
| 127 |
+
"eval_steps_per_second": 10.322,
|
| 128 |
+
"step": 3409
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 7.19,
|
| 132 |
+
"learning_rate": 2.8203285420944557e-05,
|
| 133 |
+
"loss": 0.1176,
|
| 134 |
+
"step": 3500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 8.0,
|
| 138 |
+
"eval_accuracy": 0.8229765511318909,
|
| 139 |
+
"eval_f1": 0.6518829549927831,
|
| 140 |
+
"eval_loss": 0.8652628064155579,
|
| 141 |
+
"eval_precision": 0.6150037137905422,
|
| 142 |
+
"eval_recall": 0.6934673366834171,
|
| 143 |
+
"eval_runtime": 6.8373,
|
| 144 |
+
"eval_samples_per_second": 162.638,
|
| 145 |
+
"eval_steps_per_second": 10.238,
|
| 146 |
+
"step": 3896
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 8.21,
|
| 150 |
+
"learning_rate": 2.7946611909650923e-05,
|
| 151 |
+
"loss": 0.1023,
|
| 152 |
+
"step": 4000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 9.0,
|
| 156 |
+
"eval_accuracy": 0.822642589632881,
|
| 157 |
+
"eval_f1": 0.6499869007073618,
|
| 158 |
+
"eval_loss": 0.8613839745521545,
|
| 159 |
+
"eval_precision": 0.6122902270483712,
|
| 160 |
+
"eval_recall": 0.6926298157453936,
|
| 161 |
+
"eval_runtime": 6.8784,
|
| 162 |
+
"eval_samples_per_second": 161.665,
|
| 163 |
+
"eval_steps_per_second": 10.177,
|
| 164 |
+
"step": 4383
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 9.24,
|
| 168 |
+
"learning_rate": 2.7689938398357292e-05,
|
| 169 |
+
"loss": 0.0823,
|
| 170 |
+
"step": 4500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 10.0,
|
| 174 |
+
"eval_accuracy": 0.8216168507430643,
|
| 175 |
+
"eval_f1": 0.6437475396929537,
|
| 176 |
+
"eval_loss": 0.9824637174606323,
|
| 177 |
+
"eval_precision": 0.6073285466699678,
|
| 178 |
+
"eval_recall": 0.6848129536571748,
|
| 179 |
+
"eval_runtime": 6.8843,
|
| 180 |
+
"eval_samples_per_second": 161.527,
|
| 181 |
+
"eval_steps_per_second": 10.168,
|
| 182 |
+
"step": 4870
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 10.27,
|
| 186 |
+
"learning_rate": 2.743326488706366e-05,
|
| 187 |
+
"loss": 0.069,
|
| 188 |
+
"step": 5000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 11.0,
|
| 192 |
+
"eval_accuracy": 0.8247894849836598,
|
| 193 |
+
"eval_f1": 0.6582144743792923,
|
| 194 |
+
"eval_loss": 0.9782905578613281,
|
| 195 |
+
"eval_precision": 0.624561403508772,
|
| 196 |
+
"eval_recall": 0.6957007258514796,
|
| 197 |
+
"eval_runtime": 6.9683,
|
| 198 |
+
"eval_samples_per_second": 159.58,
|
| 199 |
+
"eval_steps_per_second": 10.046,
|
| 200 |
+
"step": 5357
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 11.29,
|
| 204 |
+
"learning_rate": 2.717659137577002e-05,
|
| 205 |
+
"loss": 0.0578,
|
| 206 |
+
"step": 5500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 12.0,
|
| 210 |
+
"eval_accuracy": 0.8224040457050166,
|
| 211 |
+
"eval_f1": 0.654025974025974,
|
| 212 |
+
"eval_loss": 1.003711462020874,
|
| 213 |
+
"eval_precision": 0.6114618746964546,
|
| 214 |
+
"eval_recall": 0.7029592406476829,
|
| 215 |
+
"eval_runtime": 7.0443,
|
| 216 |
+
"eval_samples_per_second": 157.859,
|
| 217 |
+
"eval_steps_per_second": 9.937,
|
| 218 |
+
"step": 5844
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 12.32,
|
| 222 |
+
"learning_rate": 2.6919917864476387e-05,
|
| 223 |
+
"loss": 0.0522,
|
| 224 |
+
"step": 6000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 13.0,
|
| 228 |
+
"eval_accuracy": 0.8160826316166122,
|
| 229 |
+
"eval_f1": 0.6486343145054362,
|
| 230 |
+
"eval_loss": 1.0798953771591187,
|
| 231 |
+
"eval_precision": 0.6176767676767677,
|
| 232 |
+
"eval_recall": 0.68285873813512,
|
| 233 |
+
"eval_runtime": 6.9483,
|
| 234 |
+
"eval_samples_per_second": 160.039,
|
| 235 |
+
"eval_steps_per_second": 10.074,
|
| 236 |
+
"step": 6331
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 13.35,
|
| 240 |
+
"learning_rate": 2.6663244353182754e-05,
|
| 241 |
+
"loss": 0.0461,
|
| 242 |
+
"step": 6500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 14.0,
|
| 246 |
+
"eval_accuracy": 0.8203048591398105,
|
| 247 |
+
"eval_f1": 0.651880674448768,
|
| 248 |
+
"eval_loss": 1.0693352222442627,
|
| 249 |
+
"eval_precision": 0.6087693798449613,
|
| 250 |
+
"eval_recall": 0.7015633724176438,
|
| 251 |
+
"eval_runtime": 7.0475,
|
| 252 |
+
"eval_samples_per_second": 157.787,
|
| 253 |
+
"eval_steps_per_second": 9.933,
|
| 254 |
+
"step": 6818
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 14.37,
|
| 258 |
+
"learning_rate": 2.640657084188912e-05,
|
| 259 |
+
"loss": 0.0402,
|
| 260 |
+
"step": 7000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 15.0,
|
| 264 |
+
"eval_accuracy": 0.8230242599174638,
|
| 265 |
+
"eval_f1": 0.6548117154811716,
|
| 266 |
+
"eval_loss": 1.055952548980713,
|
| 267 |
+
"eval_precision": 0.6158386620757501,
|
| 268 |
+
"eval_recall": 0.6990508096035735,
|
| 269 |
+
"eval_runtime": 6.7343,
|
| 270 |
+
"eval_samples_per_second": 165.125,
|
| 271 |
+
"eval_steps_per_second": 10.395,
|
| 272 |
+
"step": 7305
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 15.4,
|
| 276 |
+
"learning_rate": 2.6149897330595482e-05,
|
| 277 |
+
"loss": 0.0369,
|
| 278 |
+
"step": 7500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 16.0,
|
| 282 |
+
"eval_accuracy": 0.819660790534577,
|
| 283 |
+
"eval_f1": 0.6594724220623501,
|
| 284 |
+
"eval_loss": 1.104617714881897,
|
| 285 |
+
"eval_precision": 0.6307339449541285,
|
| 286 |
+
"eval_recall": 0.6909547738693468,
|
| 287 |
+
"eval_runtime": 6.9981,
|
| 288 |
+
"eval_samples_per_second": 158.901,
|
| 289 |
+
"eval_steps_per_second": 10.003,
|
| 290 |
+
"step": 7792
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 16.43,
|
| 294 |
+
"learning_rate": 2.589322381930185e-05,
|
| 295 |
+
"loss": 0.0391,
|
| 296 |
+
"step": 8000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 17.0,
|
| 300 |
+
"eval_accuracy": 0.8232628038453281,
|
| 301 |
+
"eval_f1": 0.6534837425348374,
|
| 302 |
+
"eval_loss": 1.1480329036712646,
|
| 303 |
+
"eval_precision": 0.622818112825702,
|
| 304 |
+
"eval_recall": 0.6873255164712451,
|
| 305 |
+
"eval_runtime": 6.8282,
|
| 306 |
+
"eval_samples_per_second": 162.854,
|
| 307 |
+
"eval_steps_per_second": 10.252,
|
| 308 |
+
"step": 8279
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 17.45,
|
| 312 |
+
"learning_rate": 2.5636550308008215e-05,
|
| 313 |
+
"loss": 0.0537,
|
| 314 |
+
"step": 8500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 18.0,
|
| 318 |
+
"eval_accuracy": 0.8203764223181699,
|
| 319 |
+
"eval_f1": 0.6538308325587572,
|
| 320 |
+
"eval_loss": 1.2140594720840454,
|
| 321 |
+
"eval_precision": 0.6234489744239048,
|
| 322 |
+
"eval_recall": 0.6873255164712451,
|
| 323 |
+
"eval_runtime": 6.8978,
|
| 324 |
+
"eval_samples_per_second": 161.212,
|
| 325 |
+
"eval_steps_per_second": 10.148,
|
| 326 |
+
"step": 8766
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 18.48,
|
| 330 |
+
"learning_rate": 2.537987679671458e-05,
|
| 331 |
+
"loss": 0.0497,
|
| 332 |
+
"step": 9000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 19.0,
|
| 336 |
+
"eval_accuracy": 0.818945158750984,
|
| 337 |
+
"eval_f1": 0.6579537953795379,
|
| 338 |
+
"eval_loss": 1.222991943359375,
|
| 339 |
+
"eval_precision": 0.6240921612822439,
|
| 340 |
+
"eval_recall": 0.6957007258514796,
|
| 341 |
+
"eval_runtime": 6.7892,
|
| 342 |
+
"eval_samples_per_second": 163.791,
|
| 343 |
+
"eval_steps_per_second": 10.311,
|
| 344 |
+
"step": 9253
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 19.51,
|
| 348 |
+
"learning_rate": 2.5123203285420943e-05,
|
| 349 |
+
"loss": 0.0512,
|
| 350 |
+
"step": 9500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 20.0,
|
| 354 |
+
"eval_accuracy": 0.8268171083705065,
|
| 355 |
+
"eval_f1": 0.6670205706702057,
|
| 356 |
+
"eval_loss": 1.207837462425232,
|
| 357 |
+
"eval_precision": 0.6357197065519858,
|
| 358 |
+
"eval_recall": 0.7015633724176438,
|
| 359 |
+
"eval_runtime": 6.7858,
|
| 360 |
+
"eval_samples_per_second": 163.871,
|
| 361 |
+
"eval_steps_per_second": 10.316,
|
| 362 |
+
"step": 9740
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 20.53,
|
| 366 |
+
"learning_rate": 2.486652977412731e-05,
|
| 367 |
+
"loss": 0.0508,
|
| 368 |
+
"step": 10000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 21.0,
|
| 372 |
+
"eval_accuracy": 0.8178240022900217,
|
| 373 |
+
"eval_f1": 0.6514255682564709,
|
| 374 |
+
"eval_loss": 1.1940995454788208,
|
| 375 |
+
"eval_precision": 0.615289153636138,
|
| 376 |
+
"eval_recall": 0.692071468453378,
|
| 377 |
+
"eval_runtime": 6.9352,
|
| 378 |
+
"eval_samples_per_second": 160.342,
|
| 379 |
+
"eval_steps_per_second": 10.093,
|
| 380 |
+
"step": 10227
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 21.56,
|
| 384 |
+
"learning_rate": 2.4609856262833676e-05,
|
| 385 |
+
"loss": 0.044,
|
| 386 |
+
"step": 10500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 22.0,
|
| 390 |
+
"eval_accuracy": 0.8161064860093986,
|
| 391 |
+
"eval_f1": 0.6639004149377594,
|
| 392 |
+
"eval_loss": 1.311377763748169,
|
| 393 |
+
"eval_precision": 0.6376960658266907,
|
| 394 |
+
"eval_recall": 0.6923506420993858,
|
| 395 |
+
"eval_runtime": 6.93,
|
| 396 |
+
"eval_samples_per_second": 160.462,
|
| 397 |
+
"eval_steps_per_second": 10.101,
|
| 398 |
+
"step": 10714
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 22.59,
|
| 402 |
+
"learning_rate": 2.4353182751540042e-05,
|
| 403 |
+
"loss": 0.041,
|
| 404 |
+
"step": 11000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 23.0,
|
| 408 |
+
"eval_accuracy": 0.8165120106867679,
|
| 409 |
+
"eval_f1": 0.6519497686715136,
|
| 410 |
+
"eval_loss": 1.2640310525894165,
|
| 411 |
+
"eval_precision": 0.6191313080592519,
|
| 412 |
+
"eval_recall": 0.6884422110552764,
|
| 413 |
+
"eval_runtime": 6.7498,
|
| 414 |
+
"eval_samples_per_second": 164.745,
|
| 415 |
+
"eval_steps_per_second": 10.371,
|
| 416 |
+
"step": 11201
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 23.61,
|
| 420 |
+
"learning_rate": 2.4096509240246405e-05,
|
| 421 |
+
"loss": 0.0216,
|
| 422 |
+
"step": 11500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 24.0,
|
| 426 |
+
"eval_accuracy": 0.824026144414494,
|
| 427 |
+
"eval_f1": 0.6626618608997463,
|
| 428 |
+
"eval_loss": 1.3126922845840454,
|
| 429 |
+
"eval_precision": 0.6349449987209005,
|
| 430 |
+
"eval_recall": 0.6929089893914014,
|
| 431 |
+
"eval_runtime": 6.9538,
|
| 432 |
+
"eval_samples_per_second": 159.913,
|
| 433 |
+
"eval_steps_per_second": 10.066,
|
| 434 |
+
"step": 11688
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 24.64,
|
| 438 |
+
"learning_rate": 2.383983572895277e-05,
|
| 439 |
+
"loss": 0.0187,
|
| 440 |
+
"step": 12000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 25.0,
|
| 444 |
+
"eval_accuracy": 0.8228572791679588,
|
| 445 |
+
"eval_f1": 0.6716637665640476,
|
| 446 |
+
"eval_loss": 1.3328564167022705,
|
| 447 |
+
"eval_precision": 0.6451529956286963,
|
| 448 |
+
"eval_recall": 0.7004466778336125,
|
| 449 |
+
"eval_runtime": 6.8192,
|
| 450 |
+
"eval_samples_per_second": 163.069,
|
| 451 |
+
"eval_steps_per_second": 10.265,
|
| 452 |
+
"step": 12175
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 25.67,
|
| 456 |
+
"learning_rate": 2.3583162217659137e-05,
|
| 457 |
+
"loss": 0.0158,
|
| 458 |
+
"step": 12500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 26.0,
|
| 462 |
+
"eval_accuracy": 0.8177047303260896,
|
| 463 |
+
"eval_f1": 0.6601762925930797,
|
| 464 |
+
"eval_loss": 1.2958290576934814,
|
| 465 |
+
"eval_precision": 0.6242846479223687,
|
| 466 |
+
"eval_recall": 0.7004466778336125,
|
| 467 |
+
"eval_runtime": 6.9466,
|
| 468 |
+
"eval_samples_per_second": 160.077,
|
| 469 |
+
"eval_steps_per_second": 10.077,
|
| 470 |
+
"step": 12662
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 26.69,
|
| 474 |
+
"learning_rate": 2.3326488706365506e-05,
|
| 475 |
+
"loss": 0.0151,
|
| 476 |
+
"step": 13000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 27.0,
|
| 480 |
+
"eval_accuracy": 0.818062546217886,
|
| 481 |
+
"eval_f1": 0.6571240971766251,
|
| 482 |
+
"eval_loss": 1.3275514841079712,
|
| 483 |
+
"eval_precision": 0.6203818497396479,
|
| 484 |
+
"eval_recall": 0.6984924623115578,
|
| 485 |
+
"eval_runtime": 6.7421,
|
| 486 |
+
"eval_samples_per_second": 164.934,
|
| 487 |
+
"eval_steps_per_second": 10.383,
|
| 488 |
+
"step": 13149
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 27.72,
|
| 492 |
+
"learning_rate": 2.306981519507187e-05,
|
| 493 |
+
"loss": 0.016,
|
| 494 |
+
"step": 13500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 28.0,
|
| 498 |
+
"eval_accuracy": 0.8251473008754562,
|
| 499 |
+
"eval_f1": 0.6730201342281878,
|
| 500 |
+
"eval_loss": 1.2671375274658203,
|
| 501 |
+
"eval_precision": 0.6481385729058945,
|
| 502 |
+
"eval_recall": 0.6998883305415968,
|
| 503 |
+
"eval_runtime": 6.8365,
|
| 504 |
+
"eval_samples_per_second": 162.657,
|
| 505 |
+
"eval_steps_per_second": 10.239,
|
| 506 |
+
"step": 13636
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 28.75,
|
| 510 |
+
"learning_rate": 2.2813141683778235e-05,
|
| 511 |
+
"loss": 0.0157,
|
| 512 |
+
"step": 14000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 29.0,
|
| 516 |
+
"eval_accuracy": 0.8204241311037428,
|
| 517 |
+
"eval_f1": 0.654650703854756,
|
| 518 |
+
"eval_loss": 1.3373730182647705,
|
| 519 |
+
"eval_precision": 0.6190594675292361,
|
| 520 |
+
"eval_recall": 0.6945840312674484,
|
| 521 |
+
"eval_runtime": 7.169,
|
| 522 |
+
"eval_samples_per_second": 155.113,
|
| 523 |
+
"eval_steps_per_second": 9.764,
|
| 524 |
+
"step": 14123
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 29.77,
|
| 528 |
+
"learning_rate": 2.25564681724846e-05,
|
| 529 |
+
"loss": 0.0146,
|
| 530 |
+
"step": 14500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 30.0,
|
| 534 |
+
"eval_accuracy": 0.8191598482860619,
|
| 535 |
+
"eval_f1": 0.6739956568946797,
|
| 536 |
+
"eval_loss": 1.394074559211731,
|
| 537 |
+
"eval_precision": 0.655837295298468,
|
| 538 |
+
"eval_recall": 0.6931881630374093,
|
| 539 |
+
"eval_runtime": 6.8998,
|
| 540 |
+
"eval_samples_per_second": 161.164,
|
| 541 |
+
"eval_steps_per_second": 10.145,
|
| 542 |
+
"step": 14610
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 30.8,
|
| 546 |
+
"learning_rate": 2.2299794661190967e-05,
|
| 547 |
+
"loss": 0.0134,
|
| 548 |
+
"step": 15000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 31.0,
|
| 552 |
+
"eval_accuracy": 0.8163927387228358,
|
| 553 |
+
"eval_f1": 0.6588835212023617,
|
| 554 |
+
"eval_loss": 1.4215149879455566,
|
| 555 |
+
"eval_precision": 0.6343669250645995,
|
| 556 |
+
"eval_recall": 0.6853713009491904,
|
| 557 |
+
"eval_runtime": 6.8752,
|
| 558 |
+
"eval_samples_per_second": 161.741,
|
| 559 |
+
"eval_steps_per_second": 10.182,
|
| 560 |
+
"step": 15097
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 31.83,
|
| 564 |
+
"learning_rate": 2.204312114989733e-05,
|
| 565 |
+
"loss": 0.0146,
|
| 566 |
+
"step": 15500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 32.0,
|
| 570 |
+
"eval_accuracy": 0.8197562081057227,
|
| 571 |
+
"eval_f1": 0.6717123935666982,
|
| 572 |
+
"eval_loss": 1.4602118730545044,
|
| 573 |
+
"eval_precision": 0.6510348441184176,
|
| 574 |
+
"eval_recall": 0.6937465103294249,
|
| 575 |
+
"eval_runtime": 6.8475,
|
| 576 |
+
"eval_samples_per_second": 162.396,
|
| 577 |
+
"eval_steps_per_second": 10.223,
|
| 578 |
+
"step": 15584
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 32.85,
|
| 582 |
+
"learning_rate": 2.1786447638603696e-05,
|
| 583 |
+
"loss": 0.0105,
|
| 584 |
+
"step": 16000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 33.0,
|
| 588 |
+
"eval_accuracy": 0.823978435628921,
|
| 589 |
+
"eval_f1": 0.6736138944555778,
|
| 590 |
+
"eval_loss": 1.4084781408309937,
|
| 591 |
+
"eval_precision": 0.6459133999487574,
|
| 592 |
+
"eval_recall": 0.7037967615857063,
|
| 593 |
+
"eval_runtime": 6.812,
|
| 594 |
+
"eval_samples_per_second": 163.241,
|
| 595 |
+
"eval_steps_per_second": 10.276,
|
| 596 |
+
"step": 16071
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 33.88,
|
| 600 |
+
"learning_rate": 2.1529774127310062e-05,
|
| 601 |
+
"loss": 0.0135,
|
| 602 |
+
"step": 16500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 34.0,
|
| 606 |
+
"eval_accuracy": 0.8166312826507002,
|
| 607 |
+
"eval_f1": 0.6652519893899204,
|
| 608 |
+
"eval_loss": 1.3592619895935059,
|
| 609 |
+
"eval_precision": 0.6336533602829711,
|
| 610 |
+
"eval_recall": 0.7001675041876047,
|
| 611 |
+
"eval_runtime": 6.8441,
|
| 612 |
+
"eval_samples_per_second": 162.475,
|
| 613 |
+
"eval_steps_per_second": 10.228,
|
| 614 |
+
"step": 16558
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 34.91,
|
| 618 |
+
"learning_rate": 2.127310061601643e-05,
|
| 619 |
+
"loss": 0.0155,
|
| 620 |
+
"step": 17000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 35.0,
|
| 624 |
+
"eval_accuracy": 0.8221893561699387,
|
| 625 |
+
"eval_f1": 0.6724347708530485,
|
| 626 |
+
"eval_loss": 1.3412460088729858,
|
| 627 |
+
"eval_precision": 0.6519003931847969,
|
| 628 |
+
"eval_recall": 0.6943048576214406,
|
| 629 |
+
"eval_runtime": 6.8473,
|
| 630 |
+
"eval_samples_per_second": 162.4,
|
| 631 |
+
"eval_steps_per_second": 10.223,
|
| 632 |
+
"step": 17045
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 35.93,
|
| 636 |
+
"learning_rate": 2.1016427104722795e-05,
|
| 637 |
+
"loss": 0.0141,
|
| 638 |
+
"step": 17500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 36.0,
|
| 642 |
+
"eval_accuracy": 0.8219031034565015,
|
| 643 |
+
"eval_f1": 0.6687940433452998,
|
| 644 |
+
"eval_loss": 1.3676053285598755,
|
| 645 |
+
"eval_precision": 0.6384869256156385,
|
| 646 |
+
"eval_recall": 0.7021217197096594,
|
| 647 |
+
"eval_runtime": 6.9597,
|
| 648 |
+
"eval_samples_per_second": 159.777,
|
| 649 |
+
"eval_steps_per_second": 10.058,
|
| 650 |
+
"step": 17532
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 36.96,
|
| 654 |
+
"learning_rate": 2.0759753593429157e-05,
|
| 655 |
+
"loss": 0.0145,
|
| 656 |
+
"step": 18000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 37.0,
|
| 660 |
+
"eval_accuracy": 0.825075737697097,
|
| 661 |
+
"eval_f1": 0.6776680643852293,
|
| 662 |
+
"eval_loss": 1.3878055810928345,
|
| 663 |
+
"eval_precision": 0.6573077932301233,
|
| 664 |
+
"eval_recall": 0.6993299832495813,
|
| 665 |
+
"eval_runtime": 6.8928,
|
| 666 |
+
"eval_samples_per_second": 161.328,
|
| 667 |
+
"eval_steps_per_second": 10.156,
|
| 668 |
+
"step": 18019
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 37.99,
|
| 672 |
+
"learning_rate": 2.0503080082135523e-05,
|
| 673 |
+
"loss": 0.0106,
|
| 674 |
+
"step": 18500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 38.0,
|
| 678 |
+
"eval_accuracy": 0.8239307268433482,
|
| 679 |
+
"eval_f1": 0.6637612255678816,
|
| 680 |
+
"eval_loss": 1.4313843250274658,
|
| 681 |
+
"eval_precision": 0.6298245614035087,
|
| 682 |
+
"eval_recall": 0.7015633724176438,
|
| 683 |
+
"eval_runtime": 6.9946,
|
| 684 |
+
"eval_samples_per_second": 158.98,
|
| 685 |
+
"eval_steps_per_second": 10.008,
|
| 686 |
+
"step": 18506
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 39.0,
|
| 690 |
+
"eval_accuracy": 0.8281529543665466,
|
| 691 |
+
"eval_f1": 0.6862638851259821,
|
| 692 |
+
"eval_loss": 1.3729307651519775,
|
| 693 |
+
"eval_precision": 0.666578947368421,
|
| 694 |
+
"eval_recall": 0.7071468453378001,
|
| 695 |
+
"eval_runtime": 6.8415,
|
| 696 |
+
"eval_samples_per_second": 162.538,
|
| 697 |
+
"eval_steps_per_second": 10.232,
|
| 698 |
+
"step": 18993
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 39.01,
|
| 702 |
+
"learning_rate": 2.024640657084189e-05,
|
| 703 |
+
"loss": 0.0112,
|
| 704 |
+
"step": 19000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 40.0,
|
| 708 |
+
"eval_accuracy": 0.8282960807232652,
|
| 709 |
+
"eval_f1": 0.6758787228333781,
|
| 710 |
+
"eval_loss": 1.3454548120498657,
|
| 711 |
+
"eval_precision": 0.6505681818181818,
|
| 712 |
+
"eval_recall": 0.7032384142936907,
|
| 713 |
+
"eval_runtime": 6.9483,
|
| 714 |
+
"eval_samples_per_second": 160.038,
|
| 715 |
+
"eval_steps_per_second": 10.074,
|
| 716 |
+
"step": 19480
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 40.04,
|
| 720 |
+
"learning_rate": 1.9989733059548256e-05,
|
| 721 |
+
"loss": 0.0109,
|
| 722 |
+
"step": 19500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 41.0,
|
| 726 |
+
"eval_accuracy": 0.8278189928675366,
|
| 727 |
+
"eval_f1": 0.6729643427354975,
|
| 728 |
+
"eval_loss": 1.3883967399597168,
|
| 729 |
+
"eval_precision": 0.6428571428571429,
|
| 730 |
+
"eval_recall": 0.7060301507537688,
|
| 731 |
+
"eval_runtime": 6.8639,
|
| 732 |
+
"eval_samples_per_second": 162.007,
|
| 733 |
+
"eval_steps_per_second": 10.198,
|
| 734 |
+
"step": 19967
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 41.07,
|
| 738 |
+
"learning_rate": 1.973305954825462e-05,
|
| 739 |
+
"loss": 0.0084,
|
| 740 |
+
"step": 20000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 42.0,
|
| 744 |
+
"eval_accuracy": 0.8254812623744663,
|
| 745 |
+
"eval_f1": 0.6738408396439485,
|
| 746 |
+
"eval_loss": 1.4240161180496216,
|
| 747 |
+
"eval_precision": 0.6428390367553866,
|
| 748 |
+
"eval_recall": 0.7079843662758235,
|
| 749 |
+
"eval_runtime": 6.8987,
|
| 750 |
+
"eval_samples_per_second": 161.191,
|
| 751 |
+
"eval_steps_per_second": 10.147,
|
| 752 |
+
"step": 20454
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 42.09,
|
| 756 |
+
"learning_rate": 1.9476386036960984e-05,
|
| 757 |
+
"loss": 0.0082,
|
| 758 |
+
"step": 20500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 43.0,
|
| 762 |
+
"eval_accuracy": 0.8176331671477303,
|
| 763 |
+
"eval_f1": 0.6438536456962358,
|
| 764 |
+
"eval_loss": 1.4279741048812866,
|
| 765 |
+
"eval_precision": 0.6090637450199203,
|
| 766 |
+
"eval_recall": 0.68285873813512,
|
| 767 |
+
"eval_runtime": 6.884,
|
| 768 |
+
"eval_samples_per_second": 161.533,
|
| 769 |
+
"eval_steps_per_second": 10.168,
|
| 770 |
+
"step": 20941
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 43.12,
|
| 774 |
+
"learning_rate": 1.921971252566735e-05,
|
| 775 |
+
"loss": 0.0122,
|
| 776 |
+
"step": 21000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 44.0,
|
| 780 |
+
"eval_accuracy": 0.8239068724505618,
|
| 781 |
+
"eval_f1": 0.6773326162947029,
|
| 782 |
+
"eval_loss": 1.4722952842712402,
|
| 783 |
+
"eval_precision": 0.6532676348547718,
|
| 784 |
+
"eval_recall": 0.7032384142936907,
|
| 785 |
+
"eval_runtime": 6.8269,
|
| 786 |
+
"eval_samples_per_second": 162.886,
|
| 787 |
+
"eval_steps_per_second": 10.254,
|
| 788 |
+
"step": 21428
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 44.15,
|
| 792 |
+
"learning_rate": 1.896303901437372e-05,
|
| 793 |
+
"loss": 0.0082,
|
| 794 |
+
"step": 21500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 45.0,
|
| 798 |
+
"eval_accuracy": 0.8180386918250996,
|
| 799 |
+
"eval_f1": 0.6551905387647833,
|
| 800 |
+
"eval_loss": 1.5150511264801025,
|
| 801 |
+
"eval_precision": 0.6189175769612711,
|
| 802 |
+
"eval_recall": 0.6959798994974874,
|
| 803 |
+
"eval_runtime": 6.807,
|
| 804 |
+
"eval_samples_per_second": 163.361,
|
| 805 |
+
"eval_steps_per_second": 10.284,
|
| 806 |
+
"step": 21915
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 45.17,
|
| 810 |
+
"learning_rate": 1.8706365503080083e-05,
|
| 811 |
+
"loss": 0.0068,
|
| 812 |
+
"step": 22000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 46.0,
|
| 816 |
+
"eval_accuracy": 0.8210681997089764,
|
| 817 |
+
"eval_f1": 0.6669309023649095,
|
| 818 |
+
"eval_loss": 1.4440630674362183,
|
| 819 |
+
"eval_precision": 0.6330574366691748,
|
| 820 |
+
"eval_recall": 0.7046342825237297,
|
| 821 |
+
"eval_runtime": 6.8346,
|
| 822 |
+
"eval_samples_per_second": 162.702,
|
| 823 |
+
"eval_steps_per_second": 10.242,
|
| 824 |
+
"step": 22402
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 46.2,
|
| 828 |
+
"learning_rate": 1.844969199178645e-05,
|
| 829 |
+
"loss": 0.0074,
|
| 830 |
+
"step": 22500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 47.0,
|
| 834 |
+
"eval_accuracy": 0.8202571503542377,
|
| 835 |
+
"eval_f1": 0.6726807593914097,
|
| 836 |
+
"eval_loss": 1.4752631187438965,
|
| 837 |
+
"eval_precision": 0.6496749024707412,
|
| 838 |
+
"eval_recall": 0.6973757677275265,
|
| 839 |
+
"eval_runtime": 6.7986,
|
| 840 |
+
"eval_samples_per_second": 163.564,
|
| 841 |
+
"eval_steps_per_second": 10.296,
|
| 842 |
+
"step": 22889
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 47.23,
|
| 846 |
+
"learning_rate": 1.8193018480492815e-05,
|
| 847 |
+
"loss": 0.0076,
|
| 848 |
+
"step": 23000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 48.0,
|
| 852 |
+
"eval_accuracy": 0.8214975787791322,
|
| 853 |
+
"eval_f1": 0.6728770082354529,
|
| 854 |
+
"eval_loss": 1.5147960186004639,
|
| 855 |
+
"eval_precision": 0.6515032679738562,
|
| 856 |
+
"eval_recall": 0.6957007258514796,
|
| 857 |
+
"eval_runtime": 6.8796,
|
| 858 |
+
"eval_samples_per_second": 161.637,
|
| 859 |
+
"eval_steps_per_second": 10.175,
|
| 860 |
+
"step": 23376
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 48.25,
|
| 864 |
+
"learning_rate": 1.793634496919918e-05,
|
| 865 |
+
"loss": 0.0098,
|
| 866 |
+
"step": 23500
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 49.0,
|
| 870 |
+
"eval_accuracy": 0.8233343670236875,
|
| 871 |
+
"eval_f1": 0.6630391506303915,
|
| 872 |
+
"eval_loss": 1.4481282234191895,
|
| 873 |
+
"eval_precision": 0.6319251201619024,
|
| 874 |
+
"eval_recall": 0.6973757677275265,
|
| 875 |
+
"eval_runtime": 6.9541,
|
| 876 |
+
"eval_samples_per_second": 159.906,
|
| 877 |
+
"eval_steps_per_second": 10.066,
|
| 878 |
+
"step": 23863
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 49.28,
|
| 882 |
+
"learning_rate": 1.7679671457905544e-05,
|
| 883 |
+
"loss": 0.0104,
|
| 884 |
+
"step": 24000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 50.0,
|
| 888 |
+
"eval_accuracy": 0.823477493380406,
|
| 889 |
+
"eval_f1": 0.682099596231494,
|
| 890 |
+
"eval_loss": 1.4813882112503052,
|
| 891 |
+
"eval_precision": 0.6585239085239085,
|
| 892 |
+
"eval_recall": 0.707426018983808,
|
| 893 |
+
"eval_runtime": 7.0699,
|
| 894 |
+
"eval_samples_per_second": 157.287,
|
| 895 |
+
"eval_steps_per_second": 9.901,
|
| 896 |
+
"step": 24350
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 50.31,
|
| 900 |
+
"learning_rate": 1.742299794661191e-05,
|
| 901 |
+
"loss": 0.0119,
|
| 902 |
+
"step": 24500
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 51.0,
|
| 906 |
+
"eval_accuracy": 0.8263638749075642,
|
| 907 |
+
"eval_f1": 0.6831550802139038,
|
| 908 |
+
"eval_loss": 1.4050037860870361,
|
| 909 |
+
"eval_precision": 0.6554643406875321,
|
| 910 |
+
"eval_recall": 0.7132886655499721,
|
| 911 |
+
"eval_runtime": 6.9082,
|
| 912 |
+
"eval_samples_per_second": 160.968,
|
| 913 |
+
"eval_steps_per_second": 10.133,
|
| 914 |
+
"step": 24837
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 51.33,
|
| 918 |
+
"learning_rate": 1.7166324435318276e-05,
|
| 919 |
+
"loss": 0.0078,
|
| 920 |
+
"step": 25000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 52.0,
|
| 924 |
+
"eval_accuracy": 0.8233582214164739,
|
| 925 |
+
"eval_f1": 0.6825246654953372,
|
| 926 |
+
"eval_loss": 1.4853544235229492,
|
| 927 |
+
"eval_precision": 0.6615142782289757,
|
| 928 |
+
"eval_recall": 0.7049134561697376,
|
| 929 |
+
"eval_runtime": 6.9587,
|
| 930 |
+
"eval_samples_per_second": 159.8,
|
| 931 |
+
"eval_steps_per_second": 10.059,
|
| 932 |
+
"step": 25324
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 52.36,
|
| 936 |
+
"learning_rate": 1.6909650924024642e-05,
|
| 937 |
+
"loss": 0.007,
|
| 938 |
+
"step": 25500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 53.0,
|
| 942 |
+
"eval_accuracy": 0.8203764223181699,
|
| 943 |
+
"eval_f1": 0.6733681812089531,
|
| 944 |
+
"eval_loss": 1.4941233396530151,
|
| 945 |
+
"eval_precision": 0.6475895849445733,
|
| 946 |
+
"eval_recall": 0.701284198771636,
|
| 947 |
+
"eval_runtime": 6.8301,
|
| 948 |
+
"eval_samples_per_second": 162.81,
|
| 949 |
+
"eval_steps_per_second": 10.249,
|
| 950 |
+
"step": 25811
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 53.39,
|
| 954 |
+
"learning_rate": 1.6652977412731005e-05,
|
| 955 |
+
"loss": 0.0079,
|
| 956 |
+
"step": 26000
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 54.0,
|
| 960 |
+
"eval_accuracy": 0.8228095703823859,
|
| 961 |
+
"eval_f1": 0.6796948199705528,
|
| 962 |
+
"eval_loss": 1.4137930870056152,
|
| 963 |
+
"eval_precision": 0.652867060941116,
|
| 964 |
+
"eval_recall": 0.708821887213847,
|
| 965 |
+
"eval_runtime": 7.1554,
|
| 966 |
+
"eval_samples_per_second": 155.406,
|
| 967 |
+
"eval_steps_per_second": 9.783,
|
| 968 |
+
"step": 26298
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 54.41,
|
| 972 |
+
"learning_rate": 1.639630390143737e-05,
|
| 973 |
+
"loss": 0.0092,
|
| 974 |
+
"step": 26500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 55.0,
|
| 978 |
+
"eval_accuracy": 0.8217599770997829,
|
| 979 |
+
"eval_f1": 0.6887671232876712,
|
| 980 |
+
"eval_loss": 1.4301496744155884,
|
| 981 |
+
"eval_precision": 0.6761699838622915,
|
| 982 |
+
"eval_recall": 0.7018425460636516,
|
| 983 |
+
"eval_runtime": 7.1182,
|
| 984 |
+
"eval_samples_per_second": 156.219,
|
| 985 |
+
"eval_steps_per_second": 9.834,
|
| 986 |
+
"step": 26785
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 55.44,
|
| 990 |
+
"learning_rate": 1.6139630390143737e-05,
|
| 991 |
+
"loss": 0.0097,
|
| 992 |
+
"step": 27000
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 56.0,
|
| 996 |
+
"eval_accuracy": 0.8181579637890317,
|
| 997 |
+
"eval_f1": 0.6752263819435058,
|
| 998 |
+
"eval_loss": 1.5275614261627197,
|
| 999 |
+
"eval_precision": 0.654440660204349,
|
| 1000 |
+
"eval_recall": 0.6973757677275265,
|
| 1001 |
+
"eval_runtime": 7.0427,
|
| 1002 |
+
"eval_samples_per_second": 157.894,
|
| 1003 |
+
"eval_steps_per_second": 9.939,
|
| 1004 |
+
"step": 27272
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 56.47,
|
| 1008 |
+
"learning_rate": 1.5882956878850103e-05,
|
| 1009 |
+
"loss": 0.0076,
|
| 1010 |
+
"step": 27500
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 57.0,
|
| 1014 |
+
"eval_accuracy": 0.8257913694806899,
|
| 1015 |
+
"eval_f1": 0.6765140324963074,
|
| 1016 |
+
"eval_loss": 1.430177927017212,
|
| 1017 |
+
"eval_precision": 0.6517464424320828,
|
| 1018 |
+
"eval_recall": 0.7032384142936907,
|
| 1019 |
+
"eval_runtime": 6.9201,
|
| 1020 |
+
"eval_samples_per_second": 160.691,
|
| 1021 |
+
"eval_steps_per_second": 10.115,
|
| 1022 |
+
"step": 27759
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 57.49,
|
| 1026 |
+
"learning_rate": 1.5626283367556466e-05,
|
| 1027 |
+
"loss": 0.0056,
|
| 1028 |
+
"step": 28000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 58.0,
|
| 1032 |
+
"eval_accuracy": 0.8264831468714964,
|
| 1033 |
+
"eval_f1": 0.6855901127257911,
|
| 1034 |
+
"eval_loss": 1.4996072053909302,
|
| 1035 |
+
"eval_precision": 0.6675482676540597,
|
| 1036 |
+
"eval_recall": 0.7046342825237297,
|
| 1037 |
+
"eval_runtime": 6.8256,
|
| 1038 |
+
"eval_samples_per_second": 162.916,
|
| 1039 |
+
"eval_steps_per_second": 10.256,
|
| 1040 |
+
"step": 28246
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 58.52,
|
| 1044 |
+
"learning_rate": 1.5369609856262832e-05,
|
| 1045 |
+
"loss": 0.0047,
|
| 1046 |
+
"step": 28500
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 59.0,
|
| 1050 |
+
"eval_accuracy": 0.8240977075928533,
|
| 1051 |
+
"eval_f1": 0.6822860238353197,
|
| 1052 |
+
"eval_loss": 1.4308714866638184,
|
| 1053 |
+
"eval_precision": 0.6625460284061021,
|
| 1054 |
+
"eval_recall": 0.7032384142936907,
|
| 1055 |
+
"eval_runtime": 6.8106,
|
| 1056 |
+
"eval_samples_per_second": 163.274,
|
| 1057 |
+
"eval_steps_per_second": 10.278,
|
| 1058 |
+
"step": 28733
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 59.55,
|
| 1062 |
+
"learning_rate": 1.5112936344969198e-05,
|
| 1063 |
+
"loss": 0.0126,
|
| 1064 |
+
"step": 29000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 60.0,
|
| 1068 |
+
"eval_accuracy": 0.817179933684788,
|
| 1069 |
+
"eval_f1": 0.671845700508974,
|
| 1070 |
+
"eval_loss": 1.490278720855713,
|
| 1071 |
+
"eval_precision": 0.6457260556127703,
|
| 1072 |
+
"eval_recall": 0.7001675041876047,
|
| 1073 |
+
"eval_runtime": 6.8728,
|
| 1074 |
+
"eval_samples_per_second": 161.798,
|
| 1075 |
+
"eval_steps_per_second": 10.185,
|
| 1076 |
+
"step": 29220
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 60.57,
|
| 1080 |
+
"learning_rate": 1.4856262833675564e-05,
|
| 1081 |
+
"loss": 0.0054,
|
| 1082 |
+
"step": 29500
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 61.0,
|
| 1086 |
+
"eval_accuracy": 0.8218315402781422,
|
| 1087 |
+
"eval_f1": 0.6701236537694455,
|
| 1088 |
+
"eval_loss": 1.4318019151687622,
|
| 1089 |
+
"eval_precision": 0.6397562833206397,
|
| 1090 |
+
"eval_recall": 0.7035175879396985,
|
| 1091 |
+
"eval_runtime": 6.8056,
|
| 1092 |
+
"eval_samples_per_second": 163.394,
|
| 1093 |
+
"eval_steps_per_second": 10.286,
|
| 1094 |
+
"step": 29707
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 61.6,
|
| 1098 |
+
"learning_rate": 1.459958932238193e-05,
|
| 1099 |
+
"loss": 0.0076,
|
| 1100 |
+
"step": 30000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 62.0,
|
| 1104 |
+
"eval_accuracy": 0.8196369361417906,
|
| 1105 |
+
"eval_f1": 0.6820163487738419,
|
| 1106 |
+
"eval_loss": 1.574474811553955,
|
| 1107 |
+
"eval_precision": 0.6660457690260777,
|
| 1108 |
+
"eval_recall": 0.6987716359575656,
|
| 1109 |
+
"eval_runtime": 6.995,
|
| 1110 |
+
"eval_samples_per_second": 158.97,
|
| 1111 |
+
"eval_steps_per_second": 10.007,
|
| 1112 |
+
"step": 30194
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 62.63,
|
| 1116 |
+
"learning_rate": 1.4342915811088295e-05,
|
| 1117 |
+
"loss": 0.0043,
|
| 1118 |
+
"step": 30500
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 63.0,
|
| 1122 |
+
"eval_accuracy": 0.82679325397772,
|
| 1123 |
+
"eval_f1": 0.6825053995680346,
|
| 1124 |
+
"eval_loss": 1.5101566314697266,
|
| 1125 |
+
"eval_precision": 0.6607422895974908,
|
| 1126 |
+
"eval_recall": 0.705750977107761,
|
| 1127 |
+
"eval_runtime": 6.9716,
|
| 1128 |
+
"eval_samples_per_second": 159.503,
|
| 1129 |
+
"eval_steps_per_second": 10.041,
|
| 1130 |
+
"step": 30681
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 63.66,
|
| 1134 |
+
"learning_rate": 1.4086242299794661e-05,
|
| 1135 |
+
"loss": 0.0046,
|
| 1136 |
+
"step": 31000
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 64.0,
|
| 1140 |
+
"eval_accuracy": 0.8252427184466019,
|
| 1141 |
+
"eval_f1": 0.6798688882818902,
|
| 1142 |
+
"eval_loss": 1.5499790906906128,
|
| 1143 |
+
"eval_precision": 0.6655080213903743,
|
| 1144 |
+
"eval_recall": 0.6948632049134562,
|
| 1145 |
+
"eval_runtime": 6.9216,
|
| 1146 |
+
"eval_samples_per_second": 160.656,
|
| 1147 |
+
"eval_steps_per_second": 10.113,
|
| 1148 |
+
"step": 31168
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 64.68,
|
| 1152 |
+
"learning_rate": 1.3829568788501027e-05,
|
| 1153 |
+
"loss": 0.0042,
|
| 1154 |
+
"step": 31500
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 65.0,
|
| 1158 |
+
"eval_accuracy": 0.8273896137973807,
|
| 1159 |
+
"eval_f1": 0.6834157423493251,
|
| 1160 |
+
"eval_loss": 1.5357410907745361,
|
| 1161 |
+
"eval_precision": 0.6554729556523968,
|
| 1162 |
+
"eval_recall": 0.7138470128419877,
|
| 1163 |
+
"eval_runtime": 6.9877,
|
| 1164 |
+
"eval_samples_per_second": 159.137,
|
| 1165 |
+
"eval_steps_per_second": 10.018,
|
| 1166 |
+
"step": 31655
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 65.71,
|
| 1170 |
+
"learning_rate": 1.3572895277207393e-05,
|
| 1171 |
+
"loss": 0.0039,
|
| 1172 |
+
"step": 32000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 66.0,
|
| 1176 |
+
"eval_accuracy": 0.8219985210276473,
|
| 1177 |
+
"eval_f1": 0.6870022945066812,
|
| 1178 |
+
"eval_loss": 1.5469226837158203,
|
| 1179 |
+
"eval_precision": 0.665011758557617,
|
| 1180 |
+
"eval_recall": 0.7104969290898939,
|
| 1181 |
+
"eval_runtime": 6.9394,
|
| 1182 |
+
"eval_samples_per_second": 160.243,
|
| 1183 |
+
"eval_steps_per_second": 10.087,
|
| 1184 |
+
"step": 32142
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 66.74,
|
| 1188 |
+
"learning_rate": 1.331622176591376e-05,
|
| 1189 |
+
"loss": 0.004,
|
| 1190 |
+
"step": 32500
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 67.0,
|
| 1194 |
+
"eval_accuracy": 0.8289162949357124,
|
| 1195 |
+
"eval_f1": 0.6831220813875917,
|
| 1196 |
+
"eval_loss": 1.481360673904419,
|
| 1197 |
+
"eval_precision": 0.6542294914387937,
|
| 1198 |
+
"eval_recall": 0.7146845337800112,
|
| 1199 |
+
"eval_runtime": 6.9709,
|
| 1200 |
+
"eval_samples_per_second": 159.521,
|
| 1201 |
+
"eval_steps_per_second": 10.042,
|
| 1202 |
+
"step": 32629
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 67.76,
|
| 1206 |
+
"learning_rate": 1.3059548254620124e-05,
|
| 1207 |
+
"loss": 0.0031,
|
| 1208 |
+
"step": 33000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 68.0,
|
| 1212 |
+
"eval_accuracy": 0.825028028911524,
|
| 1213 |
+
"eval_f1": 0.68095365657648,
|
| 1214 |
+
"eval_loss": 1.5209916830062866,
|
| 1215 |
+
"eval_precision": 0.6544799176107106,
|
| 1216 |
+
"eval_recall": 0.7096594081518705,
|
| 1217 |
+
"eval_runtime": 7.0091,
|
| 1218 |
+
"eval_samples_per_second": 158.65,
|
| 1219 |
+
"eval_steps_per_second": 9.987,
|
| 1220 |
+
"step": 33116
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 68.79,
|
| 1224 |
+
"learning_rate": 1.280287474332649e-05,
|
| 1225 |
+
"loss": 0.0047,
|
| 1226 |
+
"step": 33500
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 69.0,
|
| 1230 |
+
"eval_accuracy": 0.8271510698695165,
|
| 1231 |
+
"eval_f1": 0.6805257510729614,
|
| 1232 |
+
"eval_loss": 1.5326005220413208,
|
| 1233 |
+
"eval_precision": 0.6548786783686112,
|
| 1234 |
+
"eval_recall": 0.7082635399218313,
|
| 1235 |
+
"eval_runtime": 6.9749,
|
| 1236 |
+
"eval_samples_per_second": 159.429,
|
| 1237 |
+
"eval_steps_per_second": 10.036,
|
| 1238 |
+
"step": 33603
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 69.82,
|
| 1242 |
+
"learning_rate": 1.2546201232032854e-05,
|
| 1243 |
+
"loss": 0.0029,
|
| 1244 |
+
"step": 34000
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 70.0,
|
| 1248 |
+
"eval_accuracy": 0.8225710264545216,
|
| 1249 |
+
"eval_f1": 0.6829466829466829,
|
| 1250 |
+
"eval_loss": 1.6056736707687378,
|
| 1251 |
+
"eval_precision": 0.6642913697545526,
|
| 1252 |
+
"eval_recall": 0.7026800670016751,
|
| 1253 |
+
"eval_runtime": 7.4038,
|
| 1254 |
+
"eval_samples_per_second": 150.193,
|
| 1255 |
+
"eval_steps_per_second": 9.455,
|
| 1256 |
+
"step": 34090
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 70.84,
|
| 1260 |
+
"learning_rate": 1.228952772073922e-05,
|
| 1261 |
+
"loss": 0.0027,
|
| 1262 |
+
"step": 34500
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 71.0,
|
| 1266 |
+
"eval_accuracy": 0.8255289711600391,
|
| 1267 |
+
"eval_f1": 0.6856989679667604,
|
| 1268 |
+
"eval_loss": 1.5919586420059204,
|
| 1269 |
+
"eval_precision": 0.6594483114204692,
|
| 1270 |
+
"eval_recall": 0.7141261864879955,
|
| 1271 |
+
"eval_runtime": 6.9324,
|
| 1272 |
+
"eval_samples_per_second": 160.406,
|
| 1273 |
+
"eval_steps_per_second": 10.098,
|
| 1274 |
+
"step": 34577
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 71.87,
|
| 1278 |
+
"learning_rate": 1.2032854209445585e-05,
|
| 1279 |
+
"loss": 0.0016,
|
| 1280 |
+
"step": 35000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 72.0,
|
| 1284 |
+
"eval_accuracy": 0.8255051167672527,
|
| 1285 |
+
"eval_f1": 0.6841604350781781,
|
| 1286 |
+
"eval_loss": 1.6220448017120361,
|
| 1287 |
+
"eval_precision": 0.6668433607209118,
|
| 1288 |
+
"eval_recall": 0.7024008933556672,
|
| 1289 |
+
"eval_runtime": 6.9179,
|
| 1290 |
+
"eval_samples_per_second": 160.743,
|
| 1291 |
+
"eval_steps_per_second": 10.119,
|
| 1292 |
+
"step": 35064
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 72.9,
|
| 1296 |
+
"learning_rate": 1.1776180698151951e-05,
|
| 1297 |
+
"loss": 0.0025,
|
| 1298 |
+
"step": 35500
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 73.0,
|
| 1302 |
+
"eval_accuracy": 0.8238591636649889,
|
| 1303 |
+
"eval_f1": 0.6912936006591596,
|
| 1304 |
+
"eval_loss": 1.626072645187378,
|
| 1305 |
+
"eval_precision": 0.6802702702702703,
|
| 1306 |
+
"eval_recall": 0.7026800670016751,
|
| 1307 |
+
"eval_runtime": 7.3201,
|
| 1308 |
+
"eval_samples_per_second": 151.911,
|
| 1309 |
+
"eval_steps_per_second": 9.563,
|
| 1310 |
+
"step": 35551
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 73.92,
|
| 1314 |
+
"learning_rate": 1.1519507186858315e-05,
|
| 1315 |
+
"loss": 0.0037,
|
| 1316 |
+
"step": 36000
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 74.0,
|
| 1320 |
+
"eval_accuracy": 0.8206865294243935,
|
| 1321 |
+
"eval_f1": 0.6906455142231948,
|
| 1322 |
+
"eval_loss": 1.6439733505249023,
|
| 1323 |
+
"eval_precision": 0.6769436997319035,
|
| 1324 |
+
"eval_recall": 0.7049134561697376,
|
| 1325 |
+
"eval_runtime": 6.8715,
|
| 1326 |
+
"eval_samples_per_second": 161.827,
|
| 1327 |
+
"eval_steps_per_second": 10.187,
|
| 1328 |
+
"step": 36038
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 74.95,
|
| 1332 |
+
"learning_rate": 1.1262833675564683e-05,
|
| 1333 |
+
"loss": 0.003,
|
| 1334 |
+
"step": 36500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 75.0,
|
| 1338 |
+
"eval_accuracy": 0.8263400205147778,
|
| 1339 |
+
"eval_f1": 0.6881282260255366,
|
| 1340 |
+
"eval_loss": 1.6027307510375977,
|
| 1341 |
+
"eval_precision": 0.6701058201058201,
|
| 1342 |
+
"eval_recall": 0.7071468453378001,
|
| 1343 |
+
"eval_runtime": 7.2528,
|
| 1344 |
+
"eval_samples_per_second": 153.321,
|
| 1345 |
+
"eval_steps_per_second": 9.651,
|
| 1346 |
+
"step": 36525
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 75.98,
|
| 1350 |
+
"learning_rate": 1.1006160164271048e-05,
|
| 1351 |
+
"loss": 0.0031,
|
| 1352 |
+
"step": 37000
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 76.0,
|
| 1356 |
+
"eval_accuracy": 0.8261730397652728,
|
| 1357 |
+
"eval_f1": 0.6897667520560874,
|
| 1358 |
+
"eval_loss": 1.6012972593307495,
|
| 1359 |
+
"eval_precision": 0.6670143415906128,
|
| 1360 |
+
"eval_recall": 0.7141261864879955,
|
| 1361 |
+
"eval_runtime": 6.9267,
|
| 1362 |
+
"eval_samples_per_second": 160.539,
|
| 1363 |
+
"eval_steps_per_second": 10.106,
|
| 1364 |
+
"step": 37012
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 77.0,
|
| 1368 |
+
"eval_accuracy": 0.8184919252880418,
|
| 1369 |
+
"eval_f1": 0.6771591059383678,
|
| 1370 |
+
"eval_loss": 1.6714273691177368,
|
| 1371 |
+
"eval_precision": 0.6433777330987686,
|
| 1372 |
+
"eval_recall": 0.7146845337800112,
|
| 1373 |
+
"eval_runtime": 7.0081,
|
| 1374 |
+
"eval_samples_per_second": 158.674,
|
| 1375 |
+
"eval_steps_per_second": 9.988,
|
| 1376 |
+
"step": 37499
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 77.0,
|
| 1380 |
+
"learning_rate": 1.0749486652977414e-05,
|
| 1381 |
+
"loss": 0.002,
|
| 1382 |
+
"step": 37500
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 78.0,
|
| 1386 |
+
"eval_accuracy": 0.8266501276210014,
|
| 1387 |
+
"eval_f1": 0.6862638851259821,
|
| 1388 |
+
"eval_loss": 1.6293165683746338,
|
| 1389 |
+
"eval_precision": 0.666578947368421,
|
| 1390 |
+
"eval_recall": 0.7071468453378001,
|
| 1391 |
+
"eval_runtime": 6.9855,
|
| 1392 |
+
"eval_samples_per_second": 159.186,
|
| 1393 |
+
"eval_steps_per_second": 10.021,
|
| 1394 |
+
"step": 37986
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 78.03,
|
| 1398 |
+
"learning_rate": 1.0492813141683778e-05,
|
| 1399 |
+
"loss": 0.0024,
|
| 1400 |
+
"step": 38000
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 79.0,
|
| 1404 |
+
"eval_accuracy": 0.8221893561699387,
|
| 1405 |
+
"eval_f1": 0.6826057756883814,
|
| 1406 |
+
"eval_loss": 1.679621934890747,
|
| 1407 |
+
"eval_precision": 0.6577789282940719,
|
| 1408 |
+
"eval_recall": 0.7093802345058626,
|
| 1409 |
+
"eval_runtime": 7.0739,
|
| 1410 |
+
"eval_samples_per_second": 157.199,
|
| 1411 |
+
"eval_steps_per_second": 9.896,
|
| 1412 |
+
"step": 38473
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 79.06,
|
| 1416 |
+
"learning_rate": 1.0236139630390144e-05,
|
| 1417 |
+
"loss": 0.003,
|
| 1418 |
+
"step": 38500
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 80.0,
|
| 1422 |
+
"eval_accuracy": 0.828343789508838,
|
| 1423 |
+
"eval_f1": 0.6891781936533767,
|
| 1424 |
+
"eval_loss": 1.6462854146957397,
|
| 1425 |
+
"eval_precision": 0.6700949367088608,
|
| 1426 |
+
"eval_recall": 0.7093802345058626,
|
| 1427 |
+
"eval_runtime": 6.9376,
|
| 1428 |
+
"eval_samples_per_second": 160.285,
|
| 1429 |
+
"eval_steps_per_second": 10.09,
|
| 1430 |
+
"step": 38960
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 80.08,
|
| 1434 |
+
"learning_rate": 9.979466119096509e-06,
|
| 1435 |
+
"loss": 0.0015,
|
| 1436 |
+
"step": 39000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 81.0,
|
| 1440 |
+
"eval_accuracy": 0.826626273228215,
|
| 1441 |
+
"eval_f1": 0.6915938864628821,
|
| 1442 |
+
"eval_loss": 1.6634407043457031,
|
| 1443 |
+
"eval_precision": 0.6764548852108916,
|
| 1444 |
+
"eval_recall": 0.707426018983808,
|
| 1445 |
+
"eval_runtime": 6.9101,
|
| 1446 |
+
"eval_samples_per_second": 160.923,
|
| 1447 |
+
"eval_steps_per_second": 10.13,
|
| 1448 |
+
"step": 39447
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 81.11,
|
| 1452 |
+
"learning_rate": 9.722792607802875e-06,
|
| 1453 |
+
"loss": 0.003,
|
| 1454 |
+
"step": 39500
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 82.0,
|
| 1458 |
+
"eval_accuracy": 0.8255051167672527,
|
| 1459 |
+
"eval_f1": 0.6838971583220568,
|
| 1460 |
+
"eval_loss": 1.6947256326675415,
|
| 1461 |
+
"eval_precision": 0.6636029411764706,
|
| 1462 |
+
"eval_recall": 0.7054718034617532,
|
| 1463 |
+
"eval_runtime": 6.9976,
|
| 1464 |
+
"eval_samples_per_second": 158.913,
|
| 1465 |
+
"eval_steps_per_second": 10.003,
|
| 1466 |
+
"step": 39934
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 82.14,
|
| 1470 |
+
"learning_rate": 9.46611909650924e-06,
|
| 1471 |
+
"loss": 0.0036,
|
| 1472 |
+
"step": 40000
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 83.0,
|
| 1476 |
+
"eval_accuracy": 0.8227141528112402,
|
| 1477 |
+
"eval_f1": 0.6791335934346832,
|
| 1478 |
+
"eval_loss": 1.651548981666565,
|
| 1479 |
+
"eval_precision": 0.6554141781355493,
|
| 1480 |
+
"eval_recall": 0.7046342825237297,
|
| 1481 |
+
"eval_runtime": 7.0674,
|
| 1482 |
+
"eval_samples_per_second": 157.343,
|
| 1483 |
+
"eval_steps_per_second": 9.905,
|
| 1484 |
+
"step": 40421
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 83.16,
|
| 1488 |
+
"learning_rate": 9.209445585215607e-06,
|
| 1489 |
+
"loss": 0.0018,
|
| 1490 |
+
"step": 40500
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 84.0,
|
| 1494 |
+
"eval_accuracy": 0.8266024188354285,
|
| 1495 |
+
"eval_f1": 0.6863617968433833,
|
| 1496 |
+
"eval_loss": 1.6855460405349731,
|
| 1497 |
+
"eval_precision": 0.6640563821456539,
|
| 1498 |
+
"eval_recall": 0.7102177554438861,
|
| 1499 |
+
"eval_runtime": 7.0529,
|
| 1500 |
+
"eval_samples_per_second": 157.667,
|
| 1501 |
+
"eval_steps_per_second": 9.925,
|
| 1502 |
+
"step": 40908
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 84.19,
|
| 1506 |
+
"learning_rate": 8.952772073921972e-06,
|
| 1507 |
+
"loss": 0.0012,
|
| 1508 |
+
"step": 41000
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 85.0,
|
| 1512 |
+
"eval_accuracy": 0.8240738532000668,
|
| 1513 |
+
"eval_f1": 0.6814775160599572,
|
| 1514 |
+
"eval_loss": 1.6966240406036377,
|
| 1515 |
+
"eval_precision": 0.6544987146529563,
|
| 1516 |
+
"eval_recall": 0.7107761027359017,
|
| 1517 |
+
"eval_runtime": 6.8863,
|
| 1518 |
+
"eval_samples_per_second": 161.48,
|
| 1519 |
+
"eval_steps_per_second": 10.165,
|
| 1520 |
+
"step": 41395
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 85.22,
|
| 1524 |
+
"learning_rate": 8.696098562628338e-06,
|
| 1525 |
+
"loss": 0.0019,
|
| 1526 |
+
"step": 41500
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 86.0,
|
| 1530 |
+
"eval_accuracy": 0.8255051167672527,
|
| 1531 |
+
"eval_f1": 0.6833355858899851,
|
| 1532 |
+
"eval_loss": 1.656359314918518,
|
| 1533 |
+
"eval_precision": 0.6623002357872675,
|
| 1534 |
+
"eval_recall": 0.705750977107761,
|
| 1535 |
+
"eval_runtime": 6.9513,
|
| 1536 |
+
"eval_samples_per_second": 159.971,
|
| 1537 |
+
"eval_steps_per_second": 10.07,
|
| 1538 |
+
"step": 41882
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 86.24,
|
| 1542 |
+
"learning_rate": 8.439425051334702e-06,
|
| 1543 |
+
"loss": 0.0015,
|
| 1544 |
+
"step": 42000
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 87.0,
|
| 1548 |
+
"eval_accuracy": 0.8239307268433482,
|
| 1549 |
+
"eval_f1": 0.6778030201790726,
|
| 1550 |
+
"eval_loss": 1.6362555027008057,
|
| 1551 |
+
"eval_precision": 0.6500897205844656,
|
| 1552 |
+
"eval_recall": 0.7079843662758235,
|
| 1553 |
+
"eval_runtime": 7.2734,
|
| 1554 |
+
"eval_samples_per_second": 152.885,
|
| 1555 |
+
"eval_steps_per_second": 9.624,
|
| 1556 |
+
"step": 42369
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 87.27,
|
| 1560 |
+
"learning_rate": 8.182751540041068e-06,
|
| 1561 |
+
"loss": 0.0022,
|
| 1562 |
+
"step": 42500
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 88.0,
|
| 1566 |
+
"eval_accuracy": 0.8260299134085541,
|
| 1567 |
+
"eval_f1": 0.6931833767658757,
|
| 1568 |
+
"eval_loss": 1.6878582239151,
|
| 1569 |
+
"eval_precision": 0.6813157185225128,
|
| 1570 |
+
"eval_recall": 0.7054718034617532,
|
| 1571 |
+
"eval_runtime": 7.1154,
|
| 1572 |
+
"eval_samples_per_second": 156.28,
|
| 1573 |
+
"eval_steps_per_second": 9.838,
|
| 1574 |
+
"step": 42856
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 88.3,
|
| 1578 |
+
"learning_rate": 7.926078028747433e-06,
|
| 1579 |
+
"loss": 0.0011,
|
| 1580 |
+
"step": 43000
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 89.0,
|
| 1584 |
+
"eval_accuracy": 0.829441091577014,
|
| 1585 |
+
"eval_f1": 0.6879049676025918,
|
| 1586 |
+
"eval_loss": 1.686987042427063,
|
| 1587 |
+
"eval_precision": 0.6659696811291166,
|
| 1588 |
+
"eval_recall": 0.7113344500279174,
|
| 1589 |
+
"eval_runtime": 6.9712,
|
| 1590 |
+
"eval_samples_per_second": 159.514,
|
| 1591 |
+
"eval_steps_per_second": 10.041,
|
| 1592 |
+
"step": 43343
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 89.32,
|
| 1596 |
+
"learning_rate": 7.669404517453799e-06,
|
| 1597 |
+
"loss": 0.0017,
|
| 1598 |
+
"step": 43500
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 90.0,
|
| 1602 |
+
"eval_accuracy": 0.8275804489396722,
|
| 1603 |
+
"eval_f1": 0.6870062653228004,
|
| 1604 |
+
"eval_loss": 1.7017887830734253,
|
| 1605 |
+
"eval_precision": 0.6707446808510639,
|
| 1606 |
+
"eval_recall": 0.7040759352317141,
|
| 1607 |
+
"eval_runtime": 6.9862,
|
| 1608 |
+
"eval_samples_per_second": 159.17,
|
| 1609 |
+
"eval_steps_per_second": 10.02,
|
| 1610 |
+
"step": 43830
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 90.35,
|
| 1614 |
+
"learning_rate": 7.412731006160165e-06,
|
| 1615 |
+
"loss": 0.0016,
|
| 1616 |
+
"step": 44000
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 91.0,
|
| 1620 |
+
"eval_accuracy": 0.8280813911881874,
|
| 1621 |
+
"eval_f1": 0.6910074374577416,
|
| 1622 |
+
"eval_loss": 1.6699299812316895,
|
| 1623 |
+
"eval_precision": 0.6700760555992656,
|
| 1624 |
+
"eval_recall": 0.7132886655499721,
|
| 1625 |
+
"eval_runtime": 6.9237,
|
| 1626 |
+
"eval_samples_per_second": 160.607,
|
| 1627 |
+
"eval_steps_per_second": 10.11,
|
| 1628 |
+
"step": 44317
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 91.38,
|
| 1632 |
+
"learning_rate": 7.15605749486653e-06,
|
| 1633 |
+
"loss": 0.0015,
|
| 1634 |
+
"step": 44500
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 92.0,
|
| 1638 |
+
"eval_accuracy": 0.8320412203907349,
|
| 1639 |
+
"eval_f1": 0.694421768707483,
|
| 1640 |
+
"eval_loss": 1.6736540794372559,
|
| 1641 |
+
"eval_precision": 0.6772823779193206,
|
| 1642 |
+
"eval_recall": 0.7124511446119486,
|
| 1643 |
+
"eval_runtime": 7.0271,
|
| 1644 |
+
"eval_samples_per_second": 158.244,
|
| 1645 |
+
"eval_steps_per_second": 9.961,
|
| 1646 |
+
"step": 44804
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 92.4,
|
| 1650 |
+
"learning_rate": 6.899383983572895e-06,
|
| 1651 |
+
"loss": 0.0017,
|
| 1652 |
+
"step": 45000
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 93.0,
|
| 1656 |
+
"eval_accuracy": 0.8280336824026144,
|
| 1657 |
+
"eval_f1": 0.6972650961278094,
|
| 1658 |
+
"eval_loss": 1.727142572402954,
|
| 1659 |
+
"eval_precision": 0.676919032597266,
|
| 1660 |
+
"eval_recall": 0.7188721384701284,
|
| 1661 |
+
"eval_runtime": 7.0065,
|
| 1662 |
+
"eval_samples_per_second": 158.709,
|
| 1663 |
+
"eval_steps_per_second": 9.991,
|
| 1664 |
+
"step": 45291
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 93.43,
|
| 1668 |
+
"learning_rate": 6.642710472279261e-06,
|
| 1669 |
+
"loss": 0.0005,
|
| 1670 |
+
"step": 45500
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 94.0,
|
| 1674 |
+
"eval_accuracy": 0.8260537678013407,
|
| 1675 |
+
"eval_f1": 0.6882329154872624,
|
| 1676 |
+
"eval_loss": 1.7245275974273682,
|
| 1677 |
+
"eval_precision": 0.6653635652853792,
|
| 1678 |
+
"eval_recall": 0.7127303182579564,
|
| 1679 |
+
"eval_runtime": 6.9585,
|
| 1680 |
+
"eval_samples_per_second": 159.804,
|
| 1681 |
+
"eval_steps_per_second": 10.06,
|
| 1682 |
+
"step": 45778
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 94.46,
|
| 1686 |
+
"learning_rate": 6.386036960985627e-06,
|
| 1687 |
+
"loss": 0.0013,
|
| 1688 |
+
"step": 46000
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 95.0,
|
| 1692 |
+
"eval_accuracy": 0.8235013477731924,
|
| 1693 |
+
"eval_f1": 0.6909190371991247,
|
| 1694 |
+
"eval_loss": 1.8143095970153809,
|
| 1695 |
+
"eval_precision": 0.6772117962466488,
|
| 1696 |
+
"eval_recall": 0.7051926298157454,
|
| 1697 |
+
"eval_runtime": 6.8559,
|
| 1698 |
+
"eval_samples_per_second": 162.196,
|
| 1699 |
+
"eval_steps_per_second": 10.21,
|
| 1700 |
+
"step": 46265
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 95.48,
|
| 1704 |
+
"learning_rate": 6.129363449691992e-06,
|
| 1705 |
+
"loss": 0.0012,
|
| 1706 |
+
"step": 46500
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 96.0,
|
| 1710 |
+
"eval_accuracy": 0.8262207485508456,
|
| 1711 |
+
"eval_f1": 0.6908744730042159,
|
| 1712 |
+
"eval_loss": 1.7299076318740845,
|
| 1713 |
+
"eval_precision": 0.673561389551843,
|
| 1714 |
+
"eval_recall": 0.7091010608598548,
|
| 1715 |
+
"eval_runtime": 7.0371,
|
| 1716 |
+
"eval_samples_per_second": 158.02,
|
| 1717 |
+
"eval_steps_per_second": 9.947,
|
| 1718 |
+
"step": 46752
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 96.51,
|
| 1722 |
+
"learning_rate": 5.872689938398357e-06,
|
| 1723 |
+
"loss": 0.002,
|
| 1724 |
+
"step": 47000
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 97.0,
|
| 1728 |
+
"eval_accuracy": 0.8272703418334486,
|
| 1729 |
+
"eval_f1": 0.6936667572709975,
|
| 1730 |
+
"eval_loss": 1.7251330614089966,
|
| 1731 |
+
"eval_precision": 0.6758474576271186,
|
| 1732 |
+
"eval_recall": 0.7124511446119486,
|
| 1733 |
+
"eval_runtime": 6.9526,
|
| 1734 |
+
"eval_samples_per_second": 159.94,
|
| 1735 |
+
"eval_steps_per_second": 10.068,
|
| 1736 |
+
"step": 47239
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 97.54,
|
| 1740 |
+
"learning_rate": 5.6160164271047226e-06,
|
| 1741 |
+
"loss": 0.0009,
|
| 1742 |
+
"step": 47500
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 98.0,
|
| 1746 |
+
"eval_accuracy": 0.8262207485508456,
|
| 1747 |
+
"eval_f1": 0.6860418610851887,
|
| 1748 |
+
"eval_loss": 1.718263864517212,
|
| 1749 |
+
"eval_precision": 0.6565450369992345,
|
| 1750 |
+
"eval_recall": 0.7183137911781128,
|
| 1751 |
+
"eval_runtime": 6.9474,
|
| 1752 |
+
"eval_samples_per_second": 160.059,
|
| 1753 |
+
"eval_steps_per_second": 10.076,
|
| 1754 |
+
"step": 47726
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 98.56,
|
| 1758 |
+
"learning_rate": 5.359342915811089e-06,
|
| 1759 |
+
"loss": 0.0009,
|
| 1760 |
+
"step": 48000
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 99.0,
|
| 1764 |
+
"eval_accuracy": 0.8278905560458959,
|
| 1765 |
+
"eval_f1": 0.6933224534203727,
|
| 1766 |
+
"eval_loss": 1.7801190614700317,
|
| 1767 |
+
"eval_precision": 0.6759480243967118,
|
| 1768 |
+
"eval_recall": 0.7116136236739252,
|
| 1769 |
+
"eval_runtime": 6.9784,
|
| 1770 |
+
"eval_samples_per_second": 159.35,
|
| 1771 |
+
"eval_steps_per_second": 10.031,
|
| 1772 |
+
"step": 48213
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 99.59,
|
| 1776 |
+
"learning_rate": 5.102669404517454e-06,
|
| 1777 |
+
"loss": 0.0008,
|
| 1778 |
+
"step": 48500
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 100.0,
|
| 1782 |
+
"eval_accuracy": 0.8263400205147778,
|
| 1783 |
+
"eval_f1": 0.6959136258029246,
|
| 1784 |
+
"eval_loss": 1.7749357223510742,
|
| 1785 |
+
"eval_precision": 0.6816599732262383,
|
| 1786 |
+
"eval_recall": 0.7107761027359017,
|
| 1787 |
+
"eval_runtime": 6.9549,
|
| 1788 |
+
"eval_samples_per_second": 159.888,
|
| 1789 |
+
"eval_steps_per_second": 10.065,
|
| 1790 |
+
"step": 48700
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 100.62,
|
| 1794 |
+
"learning_rate": 4.845995893223819e-06,
|
| 1795 |
+
"loss": 0.0006,
|
| 1796 |
+
"step": 49000
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 101.0,
|
| 1800 |
+
"eval_accuracy": 0.8272226330478758,
|
| 1801 |
+
"eval_f1": 0.6917334057282477,
|
| 1802 |
+
"eval_loss": 1.7413458824157715,
|
| 1803 |
+
"eval_precision": 0.6731836195508587,
|
| 1804 |
+
"eval_recall": 0.7113344500279174,
|
| 1805 |
+
"eval_runtime": 6.9416,
|
| 1806 |
+
"eval_samples_per_second": 160.194,
|
| 1807 |
+
"eval_steps_per_second": 10.084,
|
| 1808 |
+
"step": 49187
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 101.64,
|
| 1812 |
+
"learning_rate": 4.5893223819301845e-06,
|
| 1813 |
+
"loss": 0.0005,
|
| 1814 |
+
"step": 49500
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 102.0,
|
| 1818 |
+
"eval_accuracy": 0.826960234727225,
|
| 1819 |
+
"eval_f1": 0.6887363746467502,
|
| 1820 |
+
"eval_loss": 1.7939246892929077,
|
| 1821 |
+
"eval_precision": 0.6648480124707716,
|
| 1822 |
+
"eval_recall": 0.7144053601340034,
|
| 1823 |
+
"eval_runtime": 7.0029,
|
| 1824 |
+
"eval_samples_per_second": 158.792,
|
| 1825 |
+
"eval_steps_per_second": 9.996,
|
| 1826 |
+
"step": 49674
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 102.67,
|
| 1830 |
+
"learning_rate": 4.332648870636551e-06,
|
| 1831 |
+
"loss": 0.0008,
|
| 1832 |
+
"step": 50000
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 103.0,
|
| 1836 |
+
"eval_accuracy": 0.8237160373082704,
|
| 1837 |
+
"eval_f1": 0.6846774193548387,
|
| 1838 |
+
"eval_loss": 1.7955106496810913,
|
| 1839 |
+
"eval_precision": 0.6601866251944012,
|
| 1840 |
+
"eval_recall": 0.7110552763819096,
|
| 1841 |
+
"eval_runtime": 6.8701,
|
| 1842 |
+
"eval_samples_per_second": 161.86,
|
| 1843 |
+
"eval_steps_per_second": 10.189,
|
| 1844 |
+
"step": 50161
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 103.7,
|
| 1848 |
+
"learning_rate": 4.075975359342916e-06,
|
| 1849 |
+
"loss": 0.0007,
|
| 1850 |
+
"step": 50500
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 104.0,
|
| 1854 |
+
"eval_accuracy": 0.826626273228215,
|
| 1855 |
+
"eval_f1": 0.6900837611456363,
|
| 1856 |
+
"eval_loss": 1.78438401222229,
|
| 1857 |
+
"eval_precision": 0.668586387434555,
|
| 1858 |
+
"eval_recall": 0.7130094919039642,
|
| 1859 |
+
"eval_runtime": 7.0026,
|
| 1860 |
+
"eval_samples_per_second": 158.798,
|
| 1861 |
+
"eval_steps_per_second": 9.996,
|
| 1862 |
+
"step": 50648
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 104.72,
|
| 1866 |
+
"learning_rate": 3.819301848049281e-06,
|
| 1867 |
+
"loss": 0.0005,
|
| 1868 |
+
"step": 51000
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 105.0,
|
| 1872 |
+
"eval_accuracy": 0.8279382648314687,
|
| 1873 |
+
"eval_f1": 0.6963993453355155,
|
| 1874 |
+
"eval_loss": 1.798330307006836,
|
| 1875 |
+
"eval_precision": 0.6808,
|
| 1876 |
+
"eval_recall": 0.7127303182579564,
|
| 1877 |
+
"eval_runtime": 6.8685,
|
| 1878 |
+
"eval_samples_per_second": 161.899,
|
| 1879 |
+
"eval_steps_per_second": 10.191,
|
| 1880 |
+
"step": 51135
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 105.75,
|
| 1884 |
+
"learning_rate": 3.5626283367556473e-06,
|
| 1885 |
+
"loss": 0.0004,
|
| 1886 |
+
"step": 51500
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 106.0,
|
| 1890 |
+
"eval_accuracy": 0.8256243887311848,
|
| 1891 |
+
"eval_f1": 0.696007630467366,
|
| 1892 |
+
"eval_loss": 1.7945122718811035,
|
| 1893 |
+
"eval_precision": 0.6797977109395794,
|
| 1894 |
+
"eval_recall": 0.7130094919039642,
|
| 1895 |
+
"eval_runtime": 6.9592,
|
| 1896 |
+
"eval_samples_per_second": 159.789,
|
| 1897 |
+
"eval_steps_per_second": 10.059,
|
| 1898 |
+
"step": 51622
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 106.78,
|
| 1902 |
+
"learning_rate": 3.3059548254620125e-06,
|
| 1903 |
+
"loss": 0.0005,
|
| 1904 |
+
"step": 52000
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 107.0,
|
| 1908 |
+
"eval_accuracy": 0.8296796355048782,
|
| 1909 |
+
"eval_f1": 0.7018599562363238,
|
| 1910 |
+
"eval_loss": 1.8209294080734253,
|
| 1911 |
+
"eval_precision": 0.6879356568364611,
|
| 1912 |
+
"eval_recall": 0.7163595756560581,
|
| 1913 |
+
"eval_runtime": 7.0252,
|
| 1914 |
+
"eval_samples_per_second": 158.287,
|
| 1915 |
+
"eval_steps_per_second": 9.964,
|
| 1916 |
+
"step": 52109
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 107.8,
|
| 1920 |
+
"learning_rate": 3.049281314168378e-06,
|
| 1921 |
+
"loss": 0.0004,
|
| 1922 |
+
"step": 52500
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 108.0,
|
| 1926 |
+
"eval_accuracy": 0.8281052455809738,
|
| 1927 |
+
"eval_f1": 0.6960098724804608,
|
| 1928 |
+
"eval_loss": 1.8149752616882324,
|
| 1929 |
+
"eval_precision": 0.6839126919967664,
|
| 1930 |
+
"eval_recall": 0.7085427135678392,
|
| 1931 |
+
"eval_runtime": 7.0444,
|
| 1932 |
+
"eval_samples_per_second": 157.855,
|
| 1933 |
+
"eval_steps_per_second": 9.937,
|
| 1934 |
+
"step": 52596
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 108.83,
|
| 1938 |
+
"learning_rate": 2.7926078028747435e-06,
|
| 1939 |
+
"loss": 0.0006,
|
| 1940 |
+
"step": 53000
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 109.0,
|
| 1944 |
+
"eval_accuracy": 0.8287016054006345,
|
| 1945 |
+
"eval_f1": 0.6967024019541321,
|
| 1946 |
+
"eval_loss": 1.7784167528152466,
|
| 1947 |
+
"eval_precision": 0.6778452601003433,
|
| 1948 |
+
"eval_recall": 0.7166387493020658,
|
| 1949 |
+
"eval_runtime": 6.8299,
|
| 1950 |
+
"eval_samples_per_second": 162.815,
|
| 1951 |
+
"eval_steps_per_second": 10.249,
|
| 1952 |
+
"step": 53083
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 109.86,
|
| 1956 |
+
"learning_rate": 2.5359342915811088e-06,
|
| 1957 |
+
"loss": 0.0009,
|
| 1958 |
+
"step": 53500
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 110.0,
|
| 1962 |
+
"eval_accuracy": 0.8292741108275089,
|
| 1963 |
+
"eval_f1": 0.6964527484430002,
|
| 1964 |
+
"eval_loss": 1.7941442728042603,
|
| 1965 |
+
"eval_precision": 0.676130389064143,
|
| 1966 |
+
"eval_recall": 0.718034617532105,
|
| 1967 |
+
"eval_runtime": 7.0109,
|
| 1968 |
+
"eval_samples_per_second": 158.61,
|
| 1969 |
+
"eval_steps_per_second": 9.984,
|
| 1970 |
+
"step": 53570
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 110.88,
|
| 1974 |
+
"learning_rate": 2.2792607802874745e-06,
|
| 1975 |
+
"loss": 0.0006,
|
| 1976 |
+
"step": 54000
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 111.0,
|
| 1980 |
+
"eval_accuracy": 0.828009828009828,
|
| 1981 |
+
"eval_f1": 0.6974040021633315,
|
| 1982 |
+
"eval_loss": 1.807924509048462,
|
| 1983 |
+
"eval_precision": 0.6761929732564237,
|
| 1984 |
+
"eval_recall": 0.7199888330541597,
|
| 1985 |
+
"eval_runtime": 6.9069,
|
| 1986 |
+
"eval_samples_per_second": 160.999,
|
| 1987 |
+
"eval_steps_per_second": 10.135,
|
| 1988 |
+
"step": 54057
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 111.91,
|
| 1992 |
+
"learning_rate": 2.0225872689938397e-06,
|
| 1993 |
+
"loss": 0.0006,
|
| 1994 |
+
"step": 54500
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 112.0,
|
| 1998 |
+
"eval_accuracy": 0.8276520121180315,
|
| 1999 |
+
"eval_f1": 0.6952871072589383,
|
| 2000 |
+
"eval_loss": 1.796797513961792,
|
| 2001 |
+
"eval_precision": 0.6751709626512362,
|
| 2002 |
+
"eval_recall": 0.7166387493020658,
|
| 2003 |
+
"eval_runtime": 6.9819,
|
| 2004 |
+
"eval_samples_per_second": 159.269,
|
| 2005 |
+
"eval_steps_per_second": 10.026,
|
| 2006 |
+
"step": 54544
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 112.94,
|
| 2010 |
+
"learning_rate": 1.7659137577002054e-06,
|
| 2011 |
+
"loss": 0.0003,
|
| 2012 |
+
"step": 55000
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 113.0,
|
| 2016 |
+
"eval_accuracy": 0.8284630614727702,
|
| 2017 |
+
"eval_f1": 0.6953812813219559,
|
| 2018 |
+
"eval_loss": 1.7971785068511963,
|
| 2019 |
+
"eval_precision": 0.6753485924756643,
|
| 2020 |
+
"eval_recall": 0.7166387493020658,
|
| 2021 |
+
"eval_runtime": 7.1267,
|
| 2022 |
+
"eval_samples_per_second": 156.032,
|
| 2023 |
+
"eval_steps_per_second": 9.822,
|
| 2024 |
+
"step": 55031
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 113.96,
|
| 2028 |
+
"learning_rate": 1.509240246406571e-06,
|
| 2029 |
+
"loss": 0.0003,
|
| 2030 |
+
"step": 55500
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 114.0,
|
| 2034 |
+
"eval_accuracy": 0.8297989074688104,
|
| 2035 |
+
"eval_f1": 0.6962059620596205,
|
| 2036 |
+
"eval_loss": 1.7985066175460815,
|
| 2037 |
+
"eval_precision": 0.6764086361242759,
|
| 2038 |
+
"eval_recall": 0.7171970965940815,
|
| 2039 |
+
"eval_runtime": 7.0596,
|
| 2040 |
+
"eval_samples_per_second": 157.517,
|
| 2041 |
+
"eval_steps_per_second": 9.916,
|
| 2042 |
+
"step": 55518
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 114.99,
|
| 2046 |
+
"learning_rate": 1.2525667351129362e-06,
|
| 2047 |
+
"loss": 0.0006,
|
| 2048 |
+
"step": 56000
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 115.0,
|
| 2052 |
+
"eval_accuracy": 0.8286777510078481,
|
| 2053 |
+
"eval_f1": 0.695923066504131,
|
| 2054 |
+
"eval_loss": 1.8047789335250854,
|
| 2055 |
+
"eval_precision": 0.6758747697974218,
|
| 2056 |
+
"eval_recall": 0.7171970965940815,
|
| 2057 |
+
"eval_runtime": 6.9955,
|
| 2058 |
+
"eval_samples_per_second": 158.959,
|
| 2059 |
+
"eval_steps_per_second": 10.006,
|
| 2060 |
+
"step": 56005
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 116.0,
|
| 2064 |
+
"eval_accuracy": 0.8298466162543833,
|
| 2065 |
+
"eval_f1": 0.6949681269496812,
|
| 2066 |
+
"eval_loss": 1.7985312938690186,
|
| 2067 |
+
"eval_precision": 0.6758111316275389,
|
| 2068 |
+
"eval_recall": 0.7152428810720268,
|
| 2069 |
+
"eval_runtime": 7.0552,
|
| 2070 |
+
"eval_samples_per_second": 157.615,
|
| 2071 |
+
"eval_steps_per_second": 9.922,
|
| 2072 |
+
"step": 56492
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 116.02,
|
| 2076 |
+
"learning_rate": 9.958932238193019e-07,
|
| 2077 |
+
"loss": 0.0004,
|
| 2078 |
+
"step": 56500
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 117.0,
|
| 2082 |
+
"eval_accuracy": 0.8314448605710741,
|
| 2083 |
+
"eval_f1": 0.6995637949836424,
|
| 2084 |
+
"eval_loss": 1.788254976272583,
|
| 2085 |
+
"eval_precision": 0.6835375599360682,
|
| 2086 |
+
"eval_recall": 0.7163595756560581,
|
| 2087 |
+
"eval_runtime": 7.0043,
|
| 2088 |
+
"eval_samples_per_second": 158.759,
|
| 2089 |
+
"eval_steps_per_second": 9.994,
|
| 2090 |
+
"step": 56979
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 117.04,
|
| 2094 |
+
"learning_rate": 7.392197125256674e-07,
|
| 2095 |
+
"loss": 0.0009,
|
| 2096 |
+
"step": 57000
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 118.0,
|
| 2100 |
+
"eval_accuracy": 0.8311347534648506,
|
| 2101 |
+
"eval_f1": 0.7000544365813827,
|
| 2102 |
+
"eval_loss": 1.785180687904358,
|
| 2103 |
+
"eval_precision": 0.6829527349973447,
|
| 2104 |
+
"eval_recall": 0.718034617532105,
|
| 2105 |
+
"eval_runtime": 6.9229,
|
| 2106 |
+
"eval_samples_per_second": 160.627,
|
| 2107 |
+
"eval_steps_per_second": 10.111,
|
| 2108 |
+
"step": 57466
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 118.07,
|
| 2112 |
+
"learning_rate": 4.82546201232033e-07,
|
| 2113 |
+
"loss": 0.0002,
|
| 2114 |
+
"step": 57500
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 119.0,
|
| 2118 |
+
"eval_accuracy": 0.8308962095369863,
|
| 2119 |
+
"eval_f1": 0.7012951601908658,
|
| 2120 |
+
"eval_loss": 1.7869131565093994,
|
| 2121 |
+
"eval_precision": 0.685318411937117,
|
| 2122 |
+
"eval_recall": 0.718034617532105,
|
| 2123 |
+
"eval_runtime": 7.1691,
|
| 2124 |
+
"eval_samples_per_second": 155.111,
|
| 2125 |
+
"eval_steps_per_second": 9.764,
|
| 2126 |
+
"step": 57953
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 119.1,
|
| 2130 |
+
"learning_rate": 2.2587268993839835e-07,
|
| 2131 |
+
"loss": 0.0003,
|
| 2132 |
+
"step": 58000
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 120.0,
|
| 2136 |
+
"eval_accuracy": 0.8312063166432099,
|
| 2137 |
+
"eval_f1": 0.7009129309170186,
|
| 2138 |
+
"eval_loss": 1.7865298986434937,
|
| 2139 |
+
"eval_precision": 0.6845887676337503,
|
| 2140 |
+
"eval_recall": 0.718034617532105,
|
| 2141 |
+
"eval_runtime": 7.0357,
|
| 2142 |
+
"eval_samples_per_second": 158.051,
|
| 2143 |
+
"eval_steps_per_second": 9.949,
|
| 2144 |
+
"step": 58440
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 120.0,
|
| 2148 |
+
"step": 58440,
|
| 2149 |
+
"total_flos": 4.338269813081088e+17,
|
| 2150 |
+
"train_loss": 0.033376370980433,
|
| 2151 |
+
"train_runtime": 20083.166,
|
| 2152 |
+
"train_samples_per_second": 46.517,
|
| 2153 |
+
"train_steps_per_second": 2.91
|
| 2154 |
+
}
|
| 2155 |
+
],
|
| 2156 |
+
"max_steps": 58440,
|
| 2157 |
+
"num_train_epochs": 120,
|
| 2158 |
+
"total_flos": 4.338269813081088e+17,
|
| 2159 |
+
"trial_name": null,
|
| 2160 |
+
"trial_params": null
|
| 2161 |
+
}
|