Pre-trained model:
Adapter for distilbert-base-uncased in Pfeiffer architecture trained on the MRPC dataset for 15 epochs with early stopping and a learning rate of 1e-4.
MRPC adapter (with head) trained using the `run_glue.py` script with an extension that retains the best checkpoint (out of 30 epochs).
Pfeiffer Adapter trained on the MRPC dataset.
Adapter in Pfeiffer architecture trained on the MRPC task for 20 epochs with early stopping and a learning rate of 1e-4. See https://arxiv.org/pdf/2007.07779.pdf.
Adapter for distilbert-base-uncased in Houlsby architecture trained on the MRPC dataset for 15 epochs with early stopping and a learning rate of 1e-4.
Adapter in Houlsby architecture trained on the MRPC task for 20 epochs with early stopping and a learning rate of 1e-4. See https://arxiv.org/pdf/2007.07779.pdf.