Fine-Tuning of a Sentiment Analysis Task with Transformers-TensorFlow on Apple M1 Chip

A simple guide to fine-tuning a Transformers DistilBert Model using Tensorflow on Apple M1 Chip for a Sentiment Analysis Task. During the execution of the model.fit() After investigation, I found this solution that works for TF2.6 and forces the GPU as the only device available to run the network Read the CSV file and apply a lambda function to convert labels from text to numbers. Label positive is 1 and label negative is 0. The dataset will be split into training, validation, and testing, according to the percentages of 70, 15, and 15. For this copy-paste tutorial, the distilbert-base-uncased has been used, so the DistilBertTokenizerFast is used to tokenize the dataset, the output is in numpy form.