diff --git a/local_evaluation.py b/local_evaluation.py index 2f01cbf26c2644b18fbf702305b7804b939c1378..2f040284cae069eb8716621acfa75aff99348a34 100644 --- a/local_evaluation.py +++ b/local_evaluation.py @@ -112,7 +112,7 @@ def evaluate_predictions(predictions, evaluation_model_name, openai_client): "content": f"Question: {query}\n Ground truth: {ground_truth}\n Prediction: {prediction}\n", }, ] - if prediction == "i don't know..": + if prediction == "i don't know": n_miss += 1 continue if prediction == ground_truth: