sts/sts-b@ukp gpt2
1 version Architecture: houlsby non-linearity: swish reduction factor: 16 Head: 

Adapter for gpt2 in Houlsby architecture trained on the STS-B dataset for 10 epochs with a learning rate of 1e-4.

sts/sts-b@ukp roberta-base
1 version Architecture: houlsby Head: 

STS-B adapter (with head) trained using the `run_glue.py` script with an extension that retains the best checkpoint (out of 30 epochs).

sts/sts-b@ukp gpt2
1 version Architecture: pfeiffer non-linearity: relu reduction factor: 16 Head: 

Adapter for gpt2 in Pfeiffer architecture trained on the STS-B dataset for 10 epochs with a learning rate of 1e-4.

sts/sts-b@ukp roberta-large
1 version Architecture: pfeiffer Head: 

STS-B adapter (with head) trained using the `run_glue.py` script with an extension that retains the best checkpoint (out of 30 epochs).

sts/sts-b@ukp bert-base-uncased
1 version Architecture: pfeiffer Head: 

Adapter in Pfeiffer architecture trained on the STS-Benchmark task for 20 epochs with early stopping and a learning rate of 1e-4. See https://arxiv.org/pdf/2007.07779.pdf.

sts/sts-b@ukp roberta-base
1 version Architecture: pfeiffer Head: 

STS-B adapter (with head) trained using the `run_glue.py` script with an extension that retains the best checkpoint (out of 30 epochs).

sts/sts-b@ukp bert-base-uncased
1 version Architecture: houlsby Head: 

Adapter in Houlsby architecture trained on the STS-Benchmark task for 20 epochs with early stopping and a learning rate of 1e-4. See https://arxiv.org/pdf/2007.07779.pdf.

sts/sts-b@ukp facebook/bart-base
1 version Architecture: pfeiffer non-linearity: relu reduction factor: 16 Head: 

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

sts/sts-b@ukp roberta-large
1 version Architecture: houlsby Head: 

STS-B adapter (with head) trained using the `run_glue.py` script with an extension that retains the best checkpoint (out of 30 epochs).

sts/sts-b@ukp facebook/bart-base
1 version Architecture: houlsby non-linearity: swish reduction factor: 16 Head: 

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

sts/sts-b@ukp distilbert-base-uncased
1 version Architecture: houlsby Head: 

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

sts/sts-b@ukp distilbert-base-uncased
1 version Architecture: pfeiffer Head: 

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