Hugging Face's logo

classla
/
xlm-r-bertic

Fill-Mask
Transformers
PyTorch
Croatian
Bosnian
Serbian
xlm-roberta
Model card Files
xet
 Community
1
5roop commited on
Commit
843fcf7
·
verified ·
1 Parent(s): 18597f6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ In all cases, this model was finetuned for specific downstream tasks.
22
 
23
  ## NER
24
 
25
- 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).
26
 
27
  | system | dataset | F1 score |
28
  |:-----------------------------------------------------------------------|:--------|---------:|
 
22
 
23
  ## NER
24
 
25
+ 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).
26
 
27
  | system | dataset | F1 score |
28
  |:-----------------------------------------------------------------------|:--------|---------:|