UKP-SQuARE
/

distilroberta-squad

Question Answering Transformers PyTorch

English roberta QA Question Answering SQuAD Eval Results Inference Endpoints

Model card Files Files and versions Community

Edit model card

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.

Downloads last month: 13

Dataset used to train UKP-SQuARE/distilroberta-squad

Evaluation results

SQuAD EM on SQuAD
validation set self-reported

76.377
SQuAD F1 on SQuAD
validation set self-reported

84.553

View on Papers With Code