prepModel.py

# Load BertForSequenceClassification, the pretrained BERT model with a single linear classification layer on top. 
model = BertForSequenceClassification.from_pretrained("bert-base-uncased", num_labels=2).to(device)

# Parameters:
lr = 2e-5
adam_epsilon = 1e-8

# Number of training epochs (authors recommend between 2 and 4)
epochs = 3

num_warmup_steps = 0
num_training_steps = len(train_dataloader)*epochs

### In Transformers, optimizer and schedules are splitted and instantiated like this:
optimizer = AdamW(model.parameters(), lr=lr,eps=adam_epsilon,correct_bias=False)  # To reproduce BertAdam specific behavior set correct_bias=False
scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=num_warmup_steps, num_training_steps=num_training_steps)  # PyTorch scheduler