Merge pull request nomic-ai#174 from waybarrios/fixing_data_bug

DatasetDict to dataset object.
w6et · Apr 3, 2023 · 846f4cd · 846f4cd
2 parents c62312f + 1a45144
commit 846f4cd
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/data.py b/data.py
@@ -68,7 +68,7 @@ def load_data(config, tokenizer):
         dataset = load_dataset("json", data_files=files, split="train")
 
     else:
-        dataset = load_dataset(dataset_path)
+        dataset = load_dataset(dataset_path,split='train')
 
     dataset = dataset.train_test_split(test_size=.05, seed=config["seed"])