This example demonstrates how to retrain a BERT (Bidirectional Encoder Representations from Transformers) model on the CoLA (Corpus of Linguistic Acceptability) dataset.
To begin, you'll need the latest version of Swift for
TensorFlow
installed. Make sure you've added the correct version of swift to your path.
To train the model, run:
cd swift-models
swift run -c release BERT-CoLA