class CustomDataset(Dataset):
 def __init__(self, tokenizer, sentences, labels, max_len):
 self.len = len(sentences)
 self.sentences = sentences
 self.labels = labels
 self.tokenizer = tokenizer
 self.max_len = max_len
 
 def __getitem__(self, index):
 sentence = str(self.sentences[index])
 inputs = self.tokenizer.encode_plus(
 sentence,
 None,
 add_special_tokens=True,
 max_length=self.max_len,
 pad_to_max_length=True,
 return_token_type_ids=True
 )
 ids = inputs['input_ids']
 mask = inputs['attention_mask']
 label = self.labels[index]
 label.extend([4]*200)
 label=label[:200]
 return {
 'ids': torch.tensor(ids, dtype=torch.long),
 'mask': torch.tensor(mask, dtype=torch.long),
 'tags': torch.tensor(label, dtype=torch.long)
 } 
 
 def __len__(self):
 return self.len