gwlms
/

span-marker-token-dropping-bert-germeval14

Token Classification

named-entity-recognition

Model card Files Files and versions Community

stefan-it commited on Aug 18, 2023

Commit

a29a2d8

·

1 Parent(s): c1b2bdc

readme: minor markdown tweaks

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -59,11 +59,11 @@ Evaluation is performed with SpanMarkers internal evaluation code that uses `seq
 We fine-tune 5 models and upload the model with best F1-Score on development set. Results on development set are
 in brackets:
-| Model                                 | Run 1           | Run 2 (This)          | Run 3           | Run 4     | Run 5           | Avg.
-| ------------------------------------- | --------------- | --------------- | --------------- | --------------- | --------------- | ---------------
-| GWLMS Token Dropping BERT (5e-05, 3e) | (87.85) / 87.28 | (88.09) / 87.44 | (87.59) / 87.26 | (87.71) / 87.43 | (87.83) / 87.24 | (87.81) / 87.33
-The best model achieves a final test score of 87.44%:
 Scripts for [training](trainer.py) and [evaluation](evaluator.py) are also available.

 We fine-tune 5 models and upload the model with best F1-Score on development set. Results on development set are
 in brackets:
+| Model                                 | Run 1           | Run 2               | Run 3           | Run 4     | Run 5           | Avg.
+| ------------------------------------- | --------------- | ------------------- | --------------- | --------------- | --------------- | ---------------
+| GWLMS Token Dropping BERT (5e-05, 3e) | (87.85) / 87.28 | (**88.09**) / 87.44 | (87.59) / 87.26 | (87.71) / 87.43 | (87.83) / 87.24 | (87.81) / 87.33
+The best model achieves a final test score of 87.44%.
 Scripts for [training](trainer.py) and [evaluation](evaluator.py) are also available.