diff --git a/examples/run_lm_finetuning.py b/examples/run_lm_finetuning.py
index c37af5ef..e7a09abd 100644
--- a/examples/run_lm_finetuning.py
+++ b/examples/run_lm_finetuning.py
@@ -195,6 +195,7 @@ 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. """
+    inputs = inputs.clone().type(dtype=torch.long)
     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)