sileod/deberta-v3-base-tasksource-paraphrase

Dataset Name	Test Accuracy
glue/mrpc	0.856
glue/qqp	0.876
hlgd	0.898
paws/labeled_final	0.952
paws/labeled_swap	0.968
medical_questions_pairs	0.8562
parade	0.732
apt	0.824

@article{sileo2023tasksource,
  title={tasksource: A Dataset Harmonization Framework for Streamlined NLP Multi-Task Learning and Evaluation},
  author={Sileo, Damien},
  journal={arXiv preprint arXiv:2301.05948},
  year={2023}
}

(Accepted at LREC-COLING 2024)