Hello - hoping you can help me out here: for uni i need to fine tune BERT german for text classification.
-
would like to know how to split my training data into 70 training, 20 validation and 10 test with the dataloader
-
would like some tips on how to use Trainer class with arguments to monitor the loss function for each of training, validation and test phases.
-
what are most common ways to tune hyperparameters in BERT? is # epochs enough?
Any help much appreciated.
DB