Task Adapters

SQuAD 1.1

Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage, or the question might be unanswerable.

qa/squad1@ukp bert-base-uncased

1 version Architecture: pfeiffer Head:

Adapter for bert-base in Pfeiffer architecture trained on the SQuAD 1.1 dataset for 15 epochs with early stopping and a learning rate of 3e-4.

qa/squad1@ukp distilbert-base-uncased

1 version Architecture: pfeiffer Head:

Adapter for distilbert-base-uncased in Pfeiffer architecture trained on the SQuAD 1.1 dataset for 15 epochs with early stopping and a learning rate of 1e-4.

qa/squad1@ukp distilbert-base-uncased

1 version Architecture: houlsby Head:

Adapter for distilbert-base-uncased in Houlsby architecture trained on the SQuAD 1.1 dataset for 15 epochs with early stopping and a learning rate of 1e-4.

qa/squad1@ukp roberta-base

1 version Architecture: houlsby Head:

Adapter for roberta-base in Houlsby architecture trained on the SQuAD 1.1 dataset for 15 epochs with early stopping and a learning rate of 1e-4.

qa/squad1@ukp bert-base-uncased

1 version Architecture: houlsby Head:

Adapter for bert-base in Houlsby architecture trained on the SQuAD 1.1 dataset for 15 epochs with early stopping and a learning rate of 3e-4.

qa/squad1@ukp roberta-base

1 version Architecture: pfeiffer Head:

Adapter for roberta-base in Pfeiffer architecture trained on the SQuAD 1.1 dataset for 15 epochs with early stopping and a learning rate of 1e-4.