README.md

---
language:
- es
tags:
- question-answering
datasets:
- squad_es
metrics:
- f1
- em

# Optional. Add this if you want to encode your eval results in a structured way.
model-index:
- name: beto-base-spanish-squades2
  results:
  - task: 
      type: question-answering # Required. Example: automatic-speech-recognition
      name: question-answering  # Optional. Example: Speech Recognition
    dataset:
      type: squad_es # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
      name: squad_es v2.0.0   # Required. Example: Common Voice zh-CN
      args: es         # Optional. Example: zh-CN
    metrics:
      - type: f1
        value: 62.70
        name: f1
      - type: exact match
        value: 54.60
        name: exact match
---

The model has been trained on the second version of the [SQuAD_es](https://huggingface.co/datasets/squad_es) database. It is a question-answering dataset automatically translated from SQUAD to Spanish. This version includes the possibility that the answer does not exist within the context.

The pretrained model used is ["dccuchile/bert-base-spanish-wwm-cased"](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased), also called as BETO, pretrained on a [big spanish corpus](https://github.com/josecannete/spanish-corpora).

**METRICS**

**F1:** 62.70
**EM:** 54.60