Raise error when using an mlm flag for a clm model + correct TextDataset

examples/run_language_modeling.py

@@ -86,6 +86,9 @@ MODEL_CLASSES = {
 class TextDataset(Dataset):
     def __init__(self, tokenizer: PreTrainedTokenizer, args, file_path: str, block_size=512):
         assert os.path.isfile(file_path)
+
+        block_size = block_size - (tokenizer.max_len - tokenizer.max_len_single_sentence)
+
         directory, filename = os.path.split(file_path)
         cached_features_file = os.path.join(
             directory, args.model_type + "_cached_lm_" + str(block_size) + "_" + filename
@@ -195,6 +198,12 @@ def _rotate_checkpoints(args, checkpoint_prefix="checkpoint", use_mtime=False) -
 
 def mask_tokens(inputs: torch.Tensor, tokenizer: PreTrainedTokenizer, args) -> Tuple[torch.Tensor, torch.Tensor]:
     """ Prepare masked tokens inputs/labels for masked language modeling: 80% MASK, 10% random, 10% original. """
+
+    if tokenizer.mask_token is None:
+        raise ValueError(
+            "This tokenizer does not have a mask token which is necessary for masked language modeling. Remove the --mlm flag if you want to use this tokenizer."
+        )
+
     labels = inputs.clone()
     # We sample a few tokens in each sequence for masked-LM training (with probability args.mlm_probability defaults to 0.15 in Bert/RoBERTa)
     probability_matrix = torch.full(labels.shape, args.mlm_probability)