diff --git a/scripts/data_prep/convert_text_to_mds.py b/scripts/data_prep/convert_text_to_mds.py index b196ed2fd5..d28c38a704 100644 --- a/scripts/data_prep/convert_text_to_mds.py +++ b/scripts/data_prep/convert_text_to_mds.py @@ -88,7 +88,7 @@ def parse_args() -> Namespace: '--processes', type=int, required=False, - default=min(max(psutil.cpu_count() - 2, 1), 16), + default=min(max(psutil.cpu_count() - 2, 1), 32), help= 'The number of processes to use to download and convert the dataset', )