acul3 commited on
Commit
5002646
1 Parent(s): e92cbcf

add max_length

Browse files
Files changed (1) hide show
  1. run_mlm_flax_stream.py +1 -0
run_mlm_flax_stream.py CHANGED
@@ -504,6 +504,7 @@ if __name__ == "__main__":
504
  def tokenize_function(examples):
505
  return tokenizer(
506
  examples[data_args.text_column_name],
 
507
  return_special_tokens_mask=True
508
  )
509
 
 
504
  def tokenize_function(examples):
505
  return tokenizer(
506
  examples[data_args.text_column_name],
507
+ max_length=512,
508
  return_special_tokens_mask=True
509
  )
510