typo fix in train_tokenizer

delphi-suite · May 23, 2024 · 48f2222 · 48f2222
1 parent b3899b1
commit 48f2222
Show file tree

Hide file tree

Showing 2 changed files with 1 addition and 3 deletions.
diff --git a/scripts/tokenize_dataset.py b/scripts/tokenize_dataset.py
@@ -80,7 +80,6 @@
         args.out_repo_id or args.out_dir
     ), "You need to provide --out-repo-id or --out-dir"
 
-    print(f"Loading dataset '{args.in_repo_id}'...")
     in_dataset_split = utils.load_dataset_split_string_feature(
         args.in_repo_id, args.split, args.feature
     )

diff --git a/scripts/train_tokenizer.py b/scripts/train_tokenizer.py
@@ -76,9 +76,8 @@ def train_byte_level_bpe(
         args.out_repo_id or args.out_dir
     ), "You need to provide out_repo_id or out_dir"
 
-    print(f"Loading dataset '{args.in_repo_id}'...")
     in_dataset_split = utils.load_dataset_split_string_feature(
-        args.repo_id, args.split, args.feature
+        args.in_repo_id, args.split, args.feature
     )
     assert isinstance(in_dataset_split, Dataset)
     tokenizer = train_byte_level_bpe(