Qev-9B / evaluation.json
AustinFu's picture
Release Qev-9B v0.3.0 with 4K web-action and rule-reasoning training
34e1dd0 verified
Raw History Blame Contribute Delete
1.6 kB
{
"model": "Qev-9B",
"revision": "v0.3.0",
"full_suite": {
"decision_dev": {
"correct": 1296,
"total": 1468,
"accuracy": 0.8828337874659401,
"rejected": 0
},
"transfer_dev": {
"correct": 629,
"total": 764,
"accuracy": 0.8232984293193717,
"rejected": 0
},
"mmlupro": {
"correct": 565,
"total": 1000,
"accuracy": 0.565,
"rejected": 0
},
"semif": {
"correct": 243,
"total": 252,
"accuracy": 0.9642857142857143,
"rejected": 0
},
"scienthoon": {
"correct": 653,
"total": 873,
"accuracy": 0.7479954180985109,
"rejected": 0
},
"wanli": {
"correct": 192,
"total": 256,
"accuracy": 0.75,
"rejected": 0
},
"public": {
"correct": 187,
"total": 231,
"accuracy": 0.8095238095238095,
"rejected": 0
}
},
"matched_subsets": {
"decision_dev_all": {
"correct": 1296,
"total": 1468
},
"decision_dev_clean": {
"correct": 1107,
"total": 1264
},
"transfer_dev_all": {
"correct": 629,
"total": 764
},
"transfer_dev_clean": {
"correct": 549,
"total": 656
},
"mmlupro": {
"correct": 565,
"total": 1000
},
"scienthoon": {
"correct": 653,
"total": 873
},
"wanli": {
"correct": 192,
"total": 256
},
"semif_handwritten": {
"correct": 135,
"total": 144
},
"jevbench_public": {
"correct": 187,
"total": 231
}
}
}