101 lines
2.7 KiB
JSON
101 lines
2.7 KiB
JSON
{
|
|
"name": "Qwen2.5-0.5B-Instruct_ifeval",
|
|
"dataset_name": "ifeval",
|
|
"model_name": "Qwen2.5-0.5B-Instruct",
|
|
"score": 0.3055,
|
|
"metrics": [
|
|
{
|
|
"name": "inst_level_loose_acc",
|
|
"num": 10,
|
|
"score": 0.3889,
|
|
"macro_score": 0.3889,
|
|
"categories": [
|
|
{
|
|
"name": [
|
|
"default"
|
|
],
|
|
"num": 10,
|
|
"score": 0.3889,
|
|
"macro_score": 0.3889,
|
|
"subsets": [
|
|
{
|
|
"name": "default",
|
|
"score": 0.3889,
|
|
"num": 10
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"name": "inst_level_strict_acc",
|
|
"num": 10,
|
|
"score": 0.3333,
|
|
"macro_score": 0.3333,
|
|
"categories": [
|
|
{
|
|
"name": [
|
|
"default"
|
|
],
|
|
"num": 10,
|
|
"score": 0.3333,
|
|
"macro_score": 0.3333,
|
|
"subsets": [
|
|
{
|
|
"name": "default",
|
|
"score": 0.3333,
|
|
"num": 10
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"name": "prompt_level_loose_acc",
|
|
"num": 10,
|
|
"score": 0.3,
|
|
"macro_score": 0.3,
|
|
"categories": [
|
|
{
|
|
"name": [
|
|
"default"
|
|
],
|
|
"num": 10,
|
|
"score": 0.3,
|
|
"macro_score": 0.3,
|
|
"subsets": [
|
|
{
|
|
"name": "default",
|
|
"score": 0.3,
|
|
"num": 10
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"name": "prompt_level_strict_acc",
|
|
"num": 10,
|
|
"score": 0.2,
|
|
"macro_score": 0.2,
|
|
"categories": [
|
|
{
|
|
"name": [
|
|
"default"
|
|
],
|
|
"num": 10,
|
|
"score": 0.2,
|
|
"macro_score": 0.2,
|
|
"subsets": [
|
|
{
|
|
"name": "default",
|
|
"score": 0.2,
|
|
"num": 10
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|