diff --git a/data.py b/data.py
index ff79924c..72dc4574 100644
--- a/data.py
+++ b/data.py
@@ -57,7 +57,6 @@ def load_data(config, tokenizer):
     dataset_path = config["dataset_path"]
 
     if os.path.exists(dataset_path):
-        # check if path is a directory
         if os.path.isdir(dataset_path):
             files = glob.glob(os.path.join(dataset_path, "*_clean.jsonl"))
         else:
@@ -68,7 +67,7 @@ def load_data(config, tokenizer):
         dataset = load_dataset("json", data_files=files, split="train")
 
     else:
-        dataset = load_dataset(dataset_path,split='train')
+        dataset = load_dataset(dataset_path, split='train')
 
     dataset = dataset.train_test_split(test_size=.05, seed=config["seed"])