Spaces:
Sleeping
Sleeping
| { | |
| "metrics": { | |
| "model": "CodeWraith-8b-v2 (Llama-3.1-8B-Instruct)", | |
| "num_examples": 31, | |
| "num_valid": 28, | |
| "avg_structural_score": 0.9199616404532828, | |
| "perfect_scores": 15, | |
| "good_scores": 24, | |
| "avg_inference_time": 21.908129569022886, | |
| "total_time": 679.1520166397095, | |
| "avg_function_coverage": 0.8487331164349798, | |
| "avg_class_coverage": 0.8421052631578947, | |
| "avg_argument_coverage": 0.9281404869640164, | |
| "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": 5858, | |
| "reference_length": 3384, | |
| "inference_time": 27.2649405002594 | |
| }, | |
| { | |
| "source_file": "clean/1e7e10bc6571.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "argument_coverage": 1.0, | |
| "return_type_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 3479, | |
| "reference_length": 2578, | |
| "inference_time": 23.819497108459473 | |
| }, | |
| { | |
| "source_file": "clean/03a9ee616ef3.py", | |
| "scores": { | |
| "function_coverage": 0.5555555555555556, | |
| "class_coverage": 0.0, | |
| "argument_coverage": 0.5, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 0.5138888888888888 | |
| }, | |
| "prediction_length": 2609, | |
| "reference_length": 6998, | |
| "inference_time": 17.608966827392578 | |
| }, | |
| { | |
| "source_file": "messy/0ccd89c328c2.py", | |
| "scores": { | |
| "overall": 0.5, | |
| "parseable": false | |
| }, | |
| "prediction_length": 2239, | |
| "reference_length": 2655, | |
| "inference_time": 15.687925338745117 | |
| }, | |
| { | |
| "source_file": "clean/83b5f3fff612.py", | |
| "scores": { | |
| "function_coverage": 0.4, | |
| "class_coverage": 1.0, | |
| "argument_coverage": 0.8333333333333334, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 0.8083333333333333 | |
| }, | |
| "prediction_length": 4949, | |
| "reference_length": 2520, | |
| "inference_time": 24.682470560073853 | |
| }, | |
| { | |
| "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": 2880, | |
| "reference_length": 3470, | |
| "inference_time": 20.674485683441162 | |
| }, | |
| { | |
| "source_file": "clean/859980c575e3.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "class_coverage": 1.0, | |
| "return_type_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 2612, | |
| "reference_length": 2112, | |
| "inference_time": 17.795993089675903 | |
| }, | |
| { | |
| "source_file": "clean/3dcb1d7b4a12.py", | |
| "scores": { | |
| "function_coverage": 0.875, | |
| "class_coverage": 0.1, | |
| "argument_coverage": 0.8571428571428571, | |
| "return_type_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 0.7664285714285715 | |
| }, | |
| "prediction_length": 2927, | |
| "reference_length": 3288, | |
| "inference_time": 19.569356203079224 | |
| }, | |
| { | |
| "source_file": "clean/6bc6fb7ee908.py", | |
| "scores": { | |
| "function_coverage": 0.6, | |
| "class_coverage": 1.0, | |
| "argument_coverage": 0.6666666666666666, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 0.8166666666666667 | |
| }, | |
| "prediction_length": 3505, | |
| "reference_length": 2824, | |
| "inference_time": 20.122586011886597 | |
| }, | |
| { | |
| "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": 3162, | |
| "reference_length": 2513, | |
| "inference_time": 19.400817394256592 | |
| }, | |
| { | |
| "source_file": "clean/830d0ef964f3.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "class_coverage": 1.0, | |
| "argument_coverage": 0.9411764705882353, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 0.9852941176470589 | |
| }, | |
| "prediction_length": 3115, | |
| "reference_length": 5902, | |
| "inference_time": 21.291579246520996 | |
| }, | |
| { | |
| "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": 2591, | |
| "reference_length": 2788, | |
| "inference_time": 16.241718769073486 | |
| }, | |
| { | |
| "source_file": "clean/bf74c86796e4.py", | |
| "scores": { | |
| "overall": 0.5, | |
| "parseable": false | |
| }, | |
| "prediction_length": 3653, | |
| "reference_length": 2904, | |
| "inference_time": 20.073659896850586 | |
| }, | |
| { | |
| "source_file": "messy/e74dec1c1520.py", | |
| "scores": { | |
| "function_coverage": 0.8571428571428571, | |
| "class_coverage": 1.0, | |
| "argument_coverage": 0.8333333333333334, | |
| "return_type_coverage": 0.8571428571428571, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 0.9095238095238095 | |
| }, | |
| "prediction_length": 4965, | |
| "reference_length": 3551, | |
| "inference_time": 36.057464361190796 | |
| }, | |
| { | |
| "source_file": "clean/4df191fa5942.py", | |
| "scores": { | |
| "overall": 0.5, | |
| "parseable": false | |
| }, | |
| "prediction_length": 1864, | |
| "reference_length": 1844, | |
| "inference_time": 12.269999504089355 | |
| }, | |
| { | |
| "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": 6880, | |
| "reference_length": 4189, | |
| "inference_time": 29.761359691619873 | |
| }, | |
| { | |
| "source_file": "clean/eecf4b89e18a.py", | |
| "scores": { | |
| "function_coverage": 0.7391304347826086, | |
| "class_coverage": 1.0, | |
| "argument_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 0.9347826086956521 | |
| }, | |
| "prediction_length": 4187, | |
| "reference_length": 3237, | |
| "inference_time": 26.844980716705322 | |
| }, | |
| { | |
| "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": 2321, | |
| "reference_length": 2284, | |
| "inference_time": 14.376977443695068 | |
| }, | |
| { | |
| "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": 2049, | |
| "reference_length": 2550, | |
| "inference_time": 13.274568796157837 | |
| }, | |
| { | |
| "source_file": "messy/fe6dc7d06e56.py", | |
| "scores": { | |
| "function_coverage": 0.0, | |
| "class_coverage": 1.0, | |
| "argument_coverage": 0.5, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 0.625 | |
| }, | |
| "prediction_length": 3919, | |
| "reference_length": 4839, | |
| "inference_time": 19.380743503570557 | |
| }, | |
| { | |
| "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": 3636, | |
| "reference_length": 2674, | |
| "inference_time": 19.849429607391357 | |
| }, | |
| { | |
| "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": 1914, | |
| "reference_length": 3253, | |
| "inference_time": 13.395134925842285 | |
| }, | |
| { | |
| "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": 3092, | |
| "reference_length": 3420, | |
| "inference_time": 20.314209938049316 | |
| }, | |
| { | |
| "source_file": "clean/569e9c198e62.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "class_coverage": 0.0, | |
| "argument_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 0.75 | |
| }, | |
| "prediction_length": 3506, | |
| "reference_length": 2881, | |
| "inference_time": 20.47663974761963 | |
| }, | |
| { | |
| "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": 3266, | |
| "reference_length": 4393, | |
| "inference_time": 26.921948671340942 | |
| }, | |
| { | |
| "source_file": "messy/8bf1ff66eee0.py", | |
| "scores": { | |
| "function_coverage": 0.5555555555555556, | |
| "class_coverage": 1.0, | |
| "argument_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 0.8888888888888888 | |
| }, | |
| "prediction_length": 2708, | |
| "reference_length": 4216, | |
| "inference_time": 18.472944974899292 | |
| }, | |
| { | |
| "source_file": "messy/a60733716488.py", | |
| "scores": { | |
| "function_coverage": 0.45, | |
| "class_coverage": 0.9, | |
| "argument_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 0.8375 | |
| }, | |
| "prediction_length": 7126, | |
| "reference_length": 2329, | |
| "inference_time": 56.12669610977173 | |
| }, | |
| { | |
| "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": 2170, | |
| "reference_length": 3840, | |
| "inference_time": 17.253268718719482 | |
| }, | |
| { | |
| "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": 3031, | |
| "reference_length": 2552, | |
| "inference_time": 21.40690016746521 | |
| }, | |
| { | |
| "source_file": "messy/acda636b4109.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": 3424, | |
| "reference_length": 3593, | |
| "inference_time": 25.26692247390747 | |
| }, | |
| { | |
| "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": 3132, | |
| "reference_length": 4991, | |
| "inference_time": 23.467830657958984 | |
| } | |
| ] | |
| } |