evalscope/examples/viz/20250117_154856/reports/Qwen2.5-7B-Instruct/arc.json

37 lines
988 B
JSON

{
"name": "Qwen2.5-7B-Instruct_arc",
"dataset_name": "arc",
"model_name": "Qwen2.5-7B-Instruct",
"score": 0.85,
"metrics": [
{
"name": "AverageAccuracy",
"num": 20,
"score": 0.85,
"macro_score": 0.85,
"categories": [
{
"name": [
"default"
],
"num": 20,
"score": 0.85,
"macro_score": 0.85,
"subsets": [
{
"name": "ARC-Easy",
"score": 0.8,
"num": 10
},
{
"name": "ARC-Challenge",
"score": 0.9,
"num": 10
}
]
}
]
}
]
}