Update README.md

README.md

@@ -36,6 +36,7 @@ widget:
   - [Licensing information](#licensing-information)
   - [Funding](#funding)
   - [Disclaimer](#disclaimer)
+</details>
 
 ## Model description
 The longformer-base-4096-bne-es is the [Longformer](https://huggingface.co/allenai/longformer-base-4096) version of the [roberta-base-bne](https://https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne) masked language model for the Spanish language. The model started from the **roberta-base-bne** checkpoint and was pretrained for MLM on long documents from our biomedical and clinical corpora.
@@ -84,6 +85,19 @@ For this Longformer, we have used a small random partition of 7,2GB containing d
 ### Tokenization and pre-training 
 The training corpus has been tokenized using a byte version of Byte-Pair Encoding (BPE) used in the original [RoBERTA](https://arxiv.org/abs/1907.11692) model with a vocabulary size of 50,262 tokens. The RoBERTa-base-bne pre-training consists of a masked language model training that follows the approach employed for the RoBERTa base. The training lasted a total of 40 hours with 8 computing nodes each one with 2 AMD MI50 GPUs of 32GB VRAM.
 
+## Evaluation
+
+When fine-tuned on downstream tasks, this model achieved the following performance:
+| Dataset      | Metric   | [**Longformer-base**](https://huggingface.co/PlanTL-GOB-ES/longformer-base-4096-bne-es)   |
+|--------------|----------|------------|
+| MLDoc        | F1       |     0.9608 |
+| CoNLL-NERC   | F1       |     0.8757 |
+| CAPITEL-NERC | F1       |     0.8985 |
+| PAWS-X       | F1       |     0.8878 |
+| UD-POS       | F1       |     0.9903 |
+| CAPITEL-POS  | F1       |     0.9853 |
+| SQAC         | F1       |     0.8026 |
+| STS          | Combined |     0.8338 |
 
 ## Additional information