I use 'bert-base-cased' pre-trained model for encoding a dataset of text that was labeled to labels 0, 1. Then the encoded dataset is trained using BERT model imported from Transformer library. Does it supervised learning or semi-supervised?
The process you described is an example of supervised learning. In supervised learning, a model is trained using labeled data, where both the input (text in this case) and the corresponding output (labels 0 or 1) are provided. The pre-trained BERT model is used for encoding the text, and then the encoded dataset is used to train the BERT model from the Transformer library. Since the labels are provided during training, it falls under the category of supervised learning.