Update README.md

README.md

@@ -25,7 +25,7 @@ QLoRA adapter for `google/gemma-4-E4B-it`, trained on filtered benign coding ins
 
 ## Proof
 
-- HumanEval subset: first 8 tasks
+- HumanEval subset: first 8 tasks (ran out of GPU hours)
 - Executable pass count before: 5/8
 - Executable pass count after: 7/8
 - Heuristic score before: 0.7688