From 8b5da9fc6e22a9250691bab688e1465da922176a Mon Sep 17 00:00:00 2001 From: Phuc Van Phan Date: Mon, 18 Sep 2023 22:47:57 +0700 Subject: [PATCH] refactor: change default block_size in block size > max position embeddings (#26069) * refactor: change default block_size when not initialize * reformat: add the min of block size --- examples/flax/language-modeling/run_clm_flax.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/examples/flax/language-modeling/run_clm_flax.py b/examples/flax/language-modeling/run_clm_flax.py index 2d33053e95..b740dfcffe 100755 --- a/examples/flax/language-modeling/run_clm_flax.py +++ b/examples/flax/language-modeling/run_clm_flax.py @@ -574,9 +574,9 @@ def main(): if block_size > config.max_position_embeddings: logger.warning( f"The tokenizer picked seems to have a very large `model_max_length` ({tokenizer.model_max_length}). " - "Picking 1024 instead. You can change that default value by passing --block_size xxx." + f"Using block_size={min(1024, config.max_position_embeddings)} instead. You can change that default value by passing --block_size xxx." ) - block_size = 1024 + block_size = min(1024, config.max_position_embeddings) else: if data_args.block_size > tokenizer.model_max_length: logger.warning(