{ "metric_group": "json_validity", "model": "Code_analyze.1.0", "hf_model": "Vilyam888/Code_analyze.1.0", "evaluation_file": "prepared_data/code_analyze/test.jsonl", "evaluation_date": "2026-06-11", "samples_evaluated": 100, "generation_params": { "temperature": 0.2, "top_p": 0.95, "max_new_tokens": 2048, "seed": 42 }, "required_fields": [ "summary", "tags", "suggested_tags", "overall_score", "code_quality_score", "correctness", "task_compliance", "strengths", "weaknesses", "recommendations", "detailed_analysis" ], "metrics": { "valid_json_rate": 0.93, "required_fields_rate": 0.9, "tag_name_match_rate": 0.88 }, "metrics_counts": { "valid_json": 93, "required_fields_complete": 90, "tag_name_match": 88 } }