From 9cbf6549e538efb2770c907b6fd74a00b66d4413 Mon Sep 17 00:00:00 2001
From: Christian Medina <37550954+cmedinasoriano@users.noreply.github.com>
Date: Tue, 30 Jun 2026 21:54:05 -0400
Subject: [PATCH] fix: use output_file parameter in prepare_dataset

---
 training/scripts/prepare_dataset.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/training/scripts/prepare_dataset.py b/training/scripts/prepare_dataset.py
index c81fc4d..e4e24eb 100755
--- a/training/scripts/prepare_dataset.py
+++ b/training/scripts/prepare_dataset.py
@@ -66,17 +66,17 @@ def prepare_dataset(input_file, output_file, test_size=0.05):
     test_data = formatted[split_point:]
     
     # Save
-    with open(output_dir / "train.jsonl", "w") as f:
+    with open(output_file / "train.jsonl", "w") as f:
         for item in train_data:
             f.write(json.dumps(item) + "\n")
     
-    with open(output_dir / "test.jsonl", "w") as f:
+    with open(output_file / "test.jsonl", "w") as f:
         for item in test_data:
             f.write(json.dumps(item) + "\n")
     
     print(f"Train: {len(train_data)} examples")
     print(f"Test: {len(test_data)} examples")
-    print(f"Saved to {output_file.parent}")
+    print(f"Saved to {output_file}")
 
 
 def main():