evaluate.py

from sentence_transformers import SentenceTransformer, util

def evaluate_model(model_name,dataset):
    try:
        model = SentenceTransformer(model_name)

        scores = []
        for row in dataset:
            emb1 = model.encode(row["instruction"], convert_to_tensor=True)
            emb2 = model.encode(row["output"], convert_to_tensor=True)
            sim_score = float(util.cos_sim(emb1, emb2)[0])
            scores.append(sim_score)

        return sum(scores) / len(scores)
    except Exception as e:
        print(f"Evaluation failed: {e}")
        return None