metadata

tags:
  - multilingual
datasets:
  - xquad

xlm-roberta-large for multilingual QA

Overview

Language Model: xlm-roberta-large
Downstream task: Extractive QA
Training data: XQuAD
Testing Data: XQuAD

batch_size = 48
n_epochs = 13
max_seq_len = 384
doc_stride = 128
learning_rate = 3e-5

Evaluated on held-out test set from XQuAD

"exact_match": 87.12546816479401,
"f1": 94.77703248802527,
"test_samples": 2307