Update README.md
Browse files
README.md
CHANGED
|
@@ -207,8 +207,9 @@ Due to time constraints, there is no official benchmarking done yet.
|
|
| 207 |
|
| 208 |
However, the evaluation on a test dataset is the following:
|
| 209 |
|
| 210 |
-
Evaluation results:
|
| 211 |
|
|
|
|
| 212 |
|
| 213 |
'eval_loss': 0.0322,
|
| 214 |
|
|
@@ -220,7 +221,7 @@ Evaluation results:
|
|
| 220 |
|
| 221 |
'eval_recall': 0.9133,
|
| 222 |
|
| 223 |
-
|
| 224 |
|
| 225 |
|
| 226 |
Enjoy!
|
|
|
|
| 207 |
|
| 208 |
However, the evaluation on a test dataset is the following:
|
| 209 |
|
| 210 |
+
Evaluation results for emotion classification:
|
| 211 |
|
| 212 |
+
'eval_f1': 0.9448,
|
| 213 |
|
| 214 |
'eval_loss': 0.0322,
|
| 215 |
|
|
|
|
| 221 |
|
| 222 |
'eval_recall': 0.9133,
|
| 223 |
|
| 224 |
+
|
| 225 |
|
| 226 |
|
| 227 |
Enjoy!
|