README.md

metadata

language: es
tags:
  - biomedical
  - clinical
  - spanish
  - bsc-bio-ehr-es
license: apache-2.0
datasets:
  - IIC/livingner3
metrics:
  - f1
model-index:
  - name: IIC/bsc-bio-ehr-es-livingner3
    results:
      - task:
          type: multi-label-classification
        dataset:
          name: livingner3
          type: IIC/livingner3
          split: test
        metrics:
          - name: f1
            type: f1
            value: 0.604
pipeline_tag: text-classification

bsc-bio-ehr-es-livingner3

This model is a finetuned version of bsc-bio-ehr-es for the livingner3 dataset used in a benchmark in the paper TODO. The model has a F1 of 0.604

Please refer to the original publication for more information TODO LINK

Parameters used

parameter	Value
batch size	16
learning rate	3e-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