diff --git a/create_pretraining_data.py b/create_pretraining_data.py index 5340d96ae..c4edf2a19 100644 --- a/create_pretraining_data.py +++ b/create_pretraining_data.py @@ -388,7 +388,6 @@ def create_masked_lm_predictions(tokens, masked_lm_prob, for index in index_set: covered_indexes.add(index) - masked_token = None # 80% of the time, replace with [MASK] if rng.random() < 0.8: masked_token = "[MASK]"