classla
/

xlm-r-bertic

Inference Endpoints

Model card Files Files and versions Community

5roop commited on May 27

Commit

843fcf7

•

1 Parent(s): 18597f6

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ In all cases, this model was finetuned for specific downstream tasks.
 ## NER
-Mean macro-F1 scores were used to evaluate performance. Datasets used: [hr500k](https://huggingface.co/datasets/classla/hr500k), [ReLDI-sr](https://huggingface.co/datasets/classla/reldi_sr), [ReLDI-hr](https://huggingface.co/datasets/classla/reldi_hr), and [SETimes.SR](https://huggingface.co/datasets/classla/setimes_sr).
 | system                                                                 | dataset | F1 score |
 |:-----------------------------------------------------------------------|:--------|---------:|

 ## NER
+Average macro-F1 scores from three runs were used to evaluate performance. Datasets used: [hr500k](https://huggingface.co/datasets/classla/hr500k), [ReLDI-sr](https://huggingface.co/datasets/classla/reldi_sr), [ReLDI-hr](https://huggingface.co/datasets/classla/reldi_hr), and [SETimes.SR](https://huggingface.co/datasets/classla/setimes_sr).
 | system                                                                 | dataset | F1 score |
 |:-----------------------------------------------------------------------|:--------|---------:|