metadata
language: es
tags:
- biomedical
- clinical
- spanish
- bsc-bio-ehr-es
license: apache-2.0
datasets:
- IIC/livingner1
metrics:
- f1
model-index:
- name: IIC/bsc-bio-ehr-es-livingner1
results:
- task:
type: token-classification
dataset:
name: livingner1
type: IIC/livingner1
split: test
metrics:
- name: f1
type: f1
value: 0.938
pipeline_tag: token-classification
bsc-bio-ehr-es-livingner1
This model is a finetuned version of bsc-bio-ehr-es for the livingner1 dataset used in a benchmark in the paper TODO. The model has a F1 of 0.938
Please refer to the original publication for more information TODO LINK
Parameters used
| parameter | Value |
|---|---|
| batch size | 16 |
| learning rate | 4e-05 |
| classifier dropout | 0.1 |
| warmup ratio | 0 |
| warmup steps | 0 |
| weight decay | 0 |
| optimizer | AdamW |
| epochs | 10 |
| early stopping patience | 3 |
BibTeX entry and citation info
TODO