{ "metrics": { "model": "CodeWraith-3b-v2 (Llama-3.2-3B-Instruct)", "num_examples": 31, "num_valid": 28, "avg_structural_score": 0.9349173785126699, "perfect_scores": 15, "good_scores": 25, "avg_inference_time": 20.007101074341804, "total_time": 620.220133304596, "avg_function_coverage": 0.8438498225377107, "avg_class_coverage": 0.9736842105263158, "avg_argument_coverage": 0.9082270670505964, "avg_return_type_coverage": 0.9714285714285713 }, "per_example": [ { "source_file": "clean/4bc9509376c0.py", "scores": { "function_coverage": 1.0, "argument_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 1.0 }, "prediction_length": 2844, "reference_length": 3384, "inference_time": 18.0885272026062 }, { "source_file": "clean/1e7e10bc6571.py", "scores": { "function_coverage": 0.8, "argument_coverage": 1.0, "return_type_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 0.95 }, "prediction_length": 4926, "reference_length": 2578, "inference_time": 29.220056772232056 }, { "source_file": "clean/03a9ee616ef3.py", "scores": { "function_coverage": 0.4444444444444444, "class_coverage": 1.0, "argument_coverage": 0.16666666666666666, "has_structure": 1.0, "parseable": true, "overall": 0.6527777777777778 }, "prediction_length": 3503, "reference_length": 6998, "inference_time": 20.247114658355713 }, { "source_file": "messy/0ccd89c328c2.py", "scores": { "overall": 0.5, "parseable": false }, "prediction_length": 2863, "reference_length": 2655, "inference_time": 14.904531478881836 }, { "source_file": "clean/83b5f3fff612.py", "scores": { "function_coverage": 0.4, "class_coverage": 1.0, "argument_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 0.85 }, "prediction_length": 3495, "reference_length": 2520, "inference_time": 23.264450073242188 }, { "source_file": "clean/0f721ae1b9ad.py", "scores": { "function_coverage": 1.0, "argument_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 1.0 }, "prediction_length": 3473, "reference_length": 3470, "inference_time": 23.27858591079712 }, { "source_file": "clean/859980c575e3.py", "scores": { "function_coverage": 0.5, "class_coverage": 1.0, "return_type_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 0.875 }, "prediction_length": 3255, "reference_length": 2112, "inference_time": 13.077555179595947 }, { "source_file": "clean/3dcb1d7b4a12.py", "scores": { "function_coverage": 0.875, "class_coverage": 0.5, "argument_coverage": 1.0, "return_type_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 0.875 }, "prediction_length": 5091, "reference_length": 3288, "inference_time": 29.730497360229492 }, { "source_file": "clean/6bc6fb7ee908.py", "scores": { "function_coverage": 0.5, "class_coverage": 1.0, "argument_coverage": 0.7333333333333333, "has_structure": 1.0, "parseable": true, "overall": 0.8083333333333333 }, "prediction_length": 4773, "reference_length": 2824, "inference_time": 28.070369243621826 }, { "source_file": "messy/1ea06667316a.py", "scores": { "function_coverage": 1.0, "class_coverage": 1.0, "argument_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 1.0 }, "prediction_length": 2857, "reference_length": 2513, "inference_time": 16.786190271377563 }, { "source_file": "clean/830d0ef964f3.py", "scores": { "function_coverage": 0.5555555555555556, "class_coverage": 1.0, "argument_coverage": 0.9411764705882353, "has_structure": 1.0, "parseable": true, "overall": 0.8741830065359477 }, "prediction_length": 4630, "reference_length": 5902, "inference_time": 24.956990003585815 }, { "source_file": "clean/9dc2299143fb.py", "scores": { "function_coverage": 1.0, "argument_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 1.0 }, "prediction_length": 3830, "reference_length": 2788, "inference_time": 21.43935513496399 }, { "source_file": "clean/bf74c86796e4.py", "scores": { "overall": 0.5, "parseable": false }, "prediction_length": 3348, "reference_length": 2904, "inference_time": 15.760165691375732 }, { "source_file": "messy/e74dec1c1520.py", "scores": { "function_coverage": 1.0, "class_coverage": 1.0, "argument_coverage": 1.0, "return_type_coverage": 0.8571428571428571, "has_structure": 1.0, "parseable": true, "overall": 0.9714285714285713 }, "prediction_length": 5344, "reference_length": 3551, "inference_time": 29.408547401428223 }, { "source_file": "clean/4df191fa5942.py", "scores": { "overall": 0.5, "parseable": false }, "prediction_length": 1601, "reference_length": 1844, "inference_time": 10.143949031829834 }, { "source_file": "messy/a2d7a4633b12.py", "scores": { "function_coverage": 0.8571428571428571, "class_coverage": 1.0, "argument_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 0.9642857142857143 }, "prediction_length": 3715, "reference_length": 4189, "inference_time": 20.434860467910767 }, { "source_file": "clean/eecf4b89e18a.py", "scores": { "function_coverage": 0.6956521739130435, "class_coverage": 1.0, "argument_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 0.9239130434782609 }, "prediction_length": 3652, "reference_length": 3237, "inference_time": 23.721028327941895 }, { "source_file": "clean/5b0bb172c22d.py", "scores": { "function_coverage": 1.0, "argument_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 1.0 }, "prediction_length": 1728, "reference_length": 2284, "inference_time": 10.692550897598267 }, { "source_file": "clean/210e6fb50260.py", "scores": { "function_coverage": 1.0, "class_coverage": 1.0, "argument_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 1.0 }, "prediction_length": 2573, "reference_length": 2550, "inference_time": 16.10159707069397 }, { "source_file": "messy/fe6dc7d06e56.py", "scores": { "function_coverage": 0.5, "class_coverage": 1.0, "argument_coverage": 0.5, "has_structure": 1.0, "parseable": true, "overall": 0.75 }, "prediction_length": 3201, "reference_length": 4839, "inference_time": 17.795408964157104 }, { "source_file": "clean/07c7264a775f.py", "scores": { "function_coverage": 0.875, "argument_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 0.9583333333333334 }, "prediction_length": 2866, "reference_length": 2674, "inference_time": 14.786346435546875 }, { "source_file": "messy/273a3f8a3b29.py", "scores": { "function_coverage": 1.0, "class_coverage": 1.0, "argument_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 1.0 }, "prediction_length": 2540, "reference_length": 3253, "inference_time": 13.740688800811768 }, { "source_file": "messy/6f869b875813.py", "scores": { "function_coverage": 1.0, "class_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 1.0 }, "prediction_length": 3033, "reference_length": 3420, "inference_time": 16.89442777633667 }, { "source_file": "clean/569e9c198e62.py", "scores": { "function_coverage": 1.0, "class_coverage": 1.0, "argument_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 1.0 }, "prediction_length": 3779, "reference_length": 2881, "inference_time": 20.661334991455078 }, { "source_file": "messy/0bdbe88d7d1a.py", "scores": { "function_coverage": 1.0, "class_coverage": 1.0, "argument_coverage": 1.0, "return_type_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 1.0 }, "prediction_length": 3082, "reference_length": 4393, "inference_time": 18.825385332107544 }, { "source_file": "messy/8bf1ff66eee0.py", "scores": { "function_coverage": 1.0, "class_coverage": 1.0, "argument_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 1.0 }, "prediction_length": 3235, "reference_length": 4216, "inference_time": 18.384609699249268 }, { "source_file": "messy/a60733716488.py", "scores": { "function_coverage": 1.0, "class_coverage": 1.0, "argument_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 1.0 }, "prediction_length": 4713, "reference_length": 2329, "inference_time": 29.785675764083862 }, { "source_file": "messy/76c274773ccc.py", "scores": { "function_coverage": 1.0, "argument_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 1.0 }, "prediction_length": 2810, "reference_length": 3840, "inference_time": 17.719330310821533 }, { "source_file": "messy/1d8649714119.py", "scores": { "function_coverage": 1.0, "argument_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 1.0 }, "prediction_length": 4883, "reference_length": 2552, "inference_time": 25.8785502910614 }, { "source_file": "messy/acda636b4109.py", "scores": { "function_coverage": 0.625, "class_coverage": 1.0, "argument_coverage": 0.2727272727272727, "has_structure": 1.0, "parseable": true, "overall": 0.7244318181818181 }, "prediction_length": 2875, "reference_length": 3593, "inference_time": 16.34171986579895 }, { "source_file": "clean/08a5bdeb757f.py", "scores": { "function_coverage": 1.0, "argument_coverage": 1.0, "has_structure": 1.0, "parseable": true, "overall": 1.0 }, "prediction_length": 4286, "reference_length": 4991, "inference_time": 20.07973289489746 } ] }