Skip to main content

Table 1 Hyperparameters of fine-tuning of CTPubMedBERT + SAPBERT + VO.

From: Mapping vaccine names in clinical trials to vaccine ontology using cascaded fine-tuned domain-specific language models

Hyperparameters

Value

fine-tuning epochs

1

train batch size

256

learning rate

2e-5

max_seq_length of BERT tokenizer

25

Back to article page

Journal of Biomedical Semantics

ISSN: 2041-1480