Spaces:
Sleeping
Sleeping
| { | |
| "metrics": { | |
| "model": "CodeWraith-8b-v5 (Llama-3.1-8B-Instruct)", | |
| "num_examples": 37, | |
| "num_valid": 36, | |
| "avg_structural_score": 0.9877113373947525, | |
| "perfect_scores": 29, | |
| "good_scores": 36, | |
| "avg_inference_time": 25.293824969111263, | |
| "total_time": 935.8715238571167, | |
| "avg_function_coverage": 0.965521978021978, | |
| "avg_class_coverage": 1.0, | |
| "avg_argument_coverage": 0.9894483794265929, | |
| "avg_return_type_coverage": 1.0 | |
| }, | |
| "per_example": [ | |
| { | |
| "source_file": "clean/4600f935ed1d.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 3039, | |
| "reference_length": 2880, | |
| "inference_time": 18.591609954833984 | |
| }, | |
| { | |
| "source_file": "clean/71e2ec05a4ce.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "argument_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 4092, | |
| "reference_length": 3616, | |
| "inference_time": 21.81563091278076 | |
| }, | |
| { | |
| "source_file": "messy/e444a542540d.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": 7575, | |
| "reference_length": 4374, | |
| "inference_time": 47.71123433113098 | |
| }, | |
| { | |
| "source_file": "clean/cdb08f4d273a.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "argument_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 3446, | |
| "reference_length": 3614, | |
| "inference_time": 21.064913511276245 | |
| }, | |
| { | |
| "source_file": "clean/ca94c5502737.py", | |
| "scores": { | |
| "function_coverage": 0.6153846153846154, | |
| "argument_coverage": 0.9523809523809523, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 0.8559218559218559 | |
| }, | |
| "prediction_length": 8648, | |
| "reference_length": 6735, | |
| "inference_time": 54.13129162788391 | |
| }, | |
| { | |
| "source_file": "messy/1c73481ac309.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 3096, | |
| "reference_length": 1718, | |
| "inference_time": 15.332524538040161 | |
| }, | |
| { | |
| "source_file": "clean/12581ac99721.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "argument_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 4418, | |
| "reference_length": 4130, | |
| "inference_time": 38.43903708457947 | |
| }, | |
| { | |
| "source_file": "clean/a2576bff34ae.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 2490, | |
| "reference_length": 2440, | |
| "inference_time": 14.69094467163086 | |
| }, | |
| { | |
| "source_file": "messy/666f4c354670.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": 4816, | |
| "reference_length": 4536, | |
| "inference_time": 29.665302991867065 | |
| }, | |
| { | |
| "source_file": "clean/bf74c86796e4.py", | |
| "scores": { | |
| "overall": 0.5, | |
| "parseable": false | |
| }, | |
| "prediction_length": 3227, | |
| "reference_length": 4026, | |
| "inference_time": 20.119393587112427 | |
| }, | |
| { | |
| "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": 6493, | |
| "reference_length": 5133, | |
| "inference_time": 36.57983469963074 | |
| }, | |
| { | |
| "source_file": "clean/4e132b54cd4a.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": 3174, | |
| "reference_length": 4065, | |
| "inference_time": 20.479403257369995 | |
| }, | |
| { | |
| "source_file": "clean/7645f390c515.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "class_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 3679, | |
| "reference_length": 2559, | |
| "inference_time": 18.84472107887268 | |
| }, | |
| { | |
| "source_file": "messy/9c892371385d.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": 4995, | |
| "reference_length": 5041, | |
| "inference_time": 35.20069479942322 | |
| }, | |
| { | |
| "source_file": "messy/98c5f29240b9.py", | |
| "scores": { | |
| "function_coverage": 0.875, | |
| "class_coverage": 1.0, | |
| "argument_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 0.96875 | |
| }, | |
| "prediction_length": 5949, | |
| "reference_length": 6841, | |
| "inference_time": 34.81227779388428 | |
| }, | |
| { | |
| "source_file": "clean/88b8d70f4fe4.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": 3785, | |
| "reference_length": 3958, | |
| "inference_time": 21.514402627944946 | |
| }, | |
| { | |
| "source_file": "messy/73c72bfbe73b.py", | |
| "scores": { | |
| "function_coverage": 0.8076923076923077, | |
| "class_coverage": 1.0, | |
| "argument_coverage": 0.9411764705882353, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 0.9372171945701357 | |
| }, | |
| "prediction_length": 4787, | |
| "reference_length": 5624, | |
| "inference_time": 28.55956482887268 | |
| }, | |
| { | |
| "source_file": "clean/23b30f008578.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 3345, | |
| "reference_length": 3367, | |
| "inference_time": 20.1626718044281 | |
| }, | |
| { | |
| "source_file": "clean/d4a9d78d0281.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "argument_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 7764, | |
| "reference_length": 8236, | |
| "inference_time": 43.4171040058136 | |
| }, | |
| { | |
| "source_file": "clean/a3060596bc92.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "argument_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 2724, | |
| "reference_length": 3016, | |
| "inference_time": 15.7329843044281 | |
| }, | |
| { | |
| "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": 2930, | |
| "reference_length": 3217, | |
| "inference_time": 17.04488444328308 | |
| }, | |
| { | |
| "source_file": "messy/e8a7155bfbec.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "argument_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 4835, | |
| "reference_length": 4014, | |
| "inference_time": 28.13184118270874 | |
| }, | |
| { | |
| "source_file": "clean/5ffc696dc345.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 4035, | |
| "reference_length": 4605, | |
| "inference_time": 23.935144186019897 | |
| }, | |
| { | |
| "source_file": "clean/319db52d59c7.py", | |
| "scores": { | |
| "function_coverage": 0.9285714285714286, | |
| "class_coverage": 1.0, | |
| "argument_coverage": 0.8518518518518519, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 0.9451058201058201 | |
| }, | |
| "prediction_length": 4992, | |
| "reference_length": 7164, | |
| "inference_time": 29.12249255180359 | |
| }, | |
| { | |
| "source_file": "clean/d3728f31c0db.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": 3722, | |
| "reference_length": 3077, | |
| "inference_time": 23.72391390800476 | |
| }, | |
| { | |
| "source_file": "messy/1a534773f649.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "argument_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 3613, | |
| "reference_length": 2682, | |
| "inference_time": 21.959770441055298 | |
| }, | |
| { | |
| "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": 2903, | |
| "reference_length": 3326, | |
| "inference_time": 15.395075559616089 | |
| }, | |
| { | |
| "source_file": "clean/46e001660b82.py", | |
| "scores": { | |
| "function_coverage": 0.8571428571428571, | |
| "argument_coverage": 0.9696969696969697, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 0.9422799422799423 | |
| }, | |
| "prediction_length": 5109, | |
| "reference_length": 4027, | |
| "inference_time": 34.29022479057312 | |
| }, | |
| { | |
| "source_file": "messy/04e23b0b5d08.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": 4639, | |
| "reference_length": 4653, | |
| "inference_time": 25.926616668701172 | |
| }, | |
| { | |
| "source_file": "messy/afc593ff8c4c.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 5742, | |
| "reference_length": 4162, | |
| "inference_time": 36.24571490287781 | |
| }, | |
| { | |
| "source_file": "clean/60ccb349f496.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": 3714, | |
| "reference_length": 2891, | |
| "inference_time": 20.234167098999023 | |
| }, | |
| { | |
| "source_file": "clean/d199807b678d.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "argument_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 2547, | |
| "reference_length": 3783, | |
| "inference_time": 15.620551347732544 | |
| }, | |
| { | |
| "source_file": "clean/d2e8b7aa1e82.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": 3310, | |
| "reference_length": 3348, | |
| "inference_time": 18.21688151359558 | |
| }, | |
| { | |
| "source_file": "messy/20afb8e5092a.py", | |
| "scores": { | |
| "function_coverage": 1.0, | |
| "class_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 1.0 | |
| }, | |
| "prediction_length": 2232, | |
| "reference_length": 3277, | |
| "inference_time": 10.995202779769897 | |
| }, | |
| { | |
| "source_file": "clean/d3c7051a19d9.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": 3051, | |
| "reference_length": 3097, | |
| "inference_time": 19.41274380683899 | |
| }, | |
| { | |
| "source_file": "messy/6d62ae4e17f6.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": 2944, | |
| "reference_length": 3356, | |
| "inference_time": 17.790547370910645 | |
| }, | |
| { | |
| "source_file": "clean/83b5f3fff612.py", | |
| "scores": { | |
| "function_coverage": 0.8, | |
| "class_coverage": 1.0, | |
| "argument_coverage": 1.0, | |
| "has_structure": 1.0, | |
| "parseable": true, | |
| "overall": 0.95 | |
| }, | |
| "prediction_length": 3536, | |
| "reference_length": 4406, | |
| "inference_time": 20.960208892822266 | |
| } | |
| ] | |
| } | |