{ "name": "Qwen2.5-0.5B-Instruct_gsm8k", "dataset_name": "gsm8k", "model_name": "Qwen2.5-0.5B-Instruct", "score": 0.4, "metrics": [ { "name": "AverageAccuracy", "num": 10, "score": 0.4, "macro_score": 0.4, "categories": [ { "name": [ "default" ], "num": 10, "score": 0.4, "macro_score": 0.4, "subsets": [ { "name": "main", "score": 0.4, "num": 10 } ] } ] } ] }