import torch

token_ids = []
attention_masks = []

# Encode each review
for review in df['review_cleaned']:
    batch_encoder = tokenizer.encode_plus(
        review,
        max_length = 512,
        padding = 'max_length',
        truncation = True,
        return_tensors = 'pt')

    token_ids.append(batch_encoder['input_ids'])
    attention_masks.append(batch_encoder['attention_mask'])

# Convert token IDs and attention mask lists to PyTorch tensors
token_ids = torch.cat(token_ids, dim=0)
attention_masks = torch.cat(attention_masks, dim=0)