metadata
language:
- en
tags:
- QA
- Question Answering
- SQuAD
license: mit
datasets:
- squad
metrics:
- squad
model-index:
- name: distilroberta-base
results:
- task:
type: question-answering
name: Question Answering
dataset:
type: squad
name: SQuAD
split: validation
metrics:
- type: squad
value: 76.37653736991486
name: SQuAD EM
config: exact_match
- type: squad
value: 84.5528918750732
name: SQuAD F1
config: F1
distilroberta-base fined-tuned on SQuAD (https://huggingface.co/datasets/squad)
Hyperparameters:
- epochs: 1
- lr: 1e-5
- train batch sie: 16
- optimizer: adamW
- lr_scheduler: linear
- num warming steps: 0
- max_length: 512
Results on the dev set:
- 'exact_match': 76.37653736991486
- 'f1': 84.5528918750732
It took 1h 20 min to train on Colab.