Files
l20-edu-135m/eval/comparison.json
ModelHub XC 9e2ca78a06 初始化项目,由ModelHub XC社区提供模型
Model: AliceYin/l20-edu-135m
Source: Original Platform
2026-06-10 18:43:03 +08:00

213 lines
4.9 KiB
JSON

{
"candidate": "l20-edu-135m-deepthin",
"tasks": {
"lambada_openai": {
"metric": "acc,none",
"value": 0.25402678051620414
},
"hellaswag": {
"metric": "acc_norm,none",
"value": 0.3272256522605059
},
"piqa": {
"metric": "acc_norm,none",
"value": 0.6224156692056583
},
"arc_easy": {
"metric": "acc_norm,none",
"value": 0.5058922558922558
},
"arc_challenge": {
"metric": "acc_norm,none",
"value": 0.2764505119453925
},
"winogrande": {
"metric": "acc,none",
"value": 0.5098658247829518
}
},
"baselines": {
"gpt2-small": {
"lambada_openai": {
"metric": "acc,none",
"value": 0.30758781292451
},
"hellaswag": {
"metric": "acc_norm,none",
"value": 0.31378211511651066
},
"piqa": {
"metric": "acc_norm,none",
"value": 0.6207834602829162
},
"arc_easy": {
"metric": "acc_norm,none",
"value": 0.39730639730639733
},
"arc_challenge": {
"metric": "acc_norm,none",
"value": 0.22610921501706485
},
"winogrande": {
"metric": "acc,none",
"value": 0.5067087608524072
}
},
"opt-125m": {
"lambada_openai": {
"metric": "acc,none",
"value": 0.3856006209974772
},
"hellaswag": {
"metric": "acc_norm,none",
"value": 0.31597291376219877
},
"piqa": {
"metric": "acc_norm,none",
"value": 0.6202393906420022
},
"arc_easy": {
"metric": "acc_norm,none",
"value": 0.398989898989899
},
"arc_challenge": {
"metric": "acc_norm,none",
"value": 0.22098976109215018
},
"winogrande": {
"metric": "acc,none",
"value": 0.5177584846093133
}
},
"gpt-neo-125m": {
"lambada_openai": {
"metric": "acc,none",
"value": 0.37647972055113527
},
"hellaswag": {
"metric": "acc_norm,none",
"value": 0.30551682931686913
},
"piqa": {
"metric": "acc_norm,none",
"value": 0.6213275299238302
},
"arc_easy": {
"metric": "acc_norm,none",
"value": 0.39646464646464646
},
"arc_challenge": {
"metric": "acc_norm,none",
"value": 0.23208191126279865
},
"winogrande": {
"metric": "acc,none",
"value": 0.5098658247829518
}
},
"cerebras-gpt-111m": {
"lambada_openai": {
"metric": "acc,none",
"value": 0.19115078594993207
},
"hellaswag": {
"metric": "acc_norm,none",
"value": 0.2719577773351922
},
"piqa": {
"metric": "acc_norm,none",
"value": 0.5810663764961915
},
"arc_easy": {
"metric": "acc_norm,none",
"value": 0.35058922558922556
},
"arc_challenge": {
"metric": "acc_norm,none",
"value": 0.2098976109215017
},
"winogrande": {
"metric": "acc,none",
"value": 0.49013417521704816
}
},
"pythia-160m": {
"lambada_openai": {
"metric": "acc,none",
"value": 0.12245294003493111
},
"hellaswag": {
"metric": "acc_norm,none",
"value": 0.30302728540131446
},
"piqa": {
"metric": "acc_norm,none",
"value": 0.5979325353645266
},
"arc_easy": {
"metric": "acc_norm,none",
"value": 0.3640572390572391
},
"arc_challenge": {
"metric": "acc_norm,none",
"value": 0.23122866894197952
},
"winogrande": {
"metric": "acc,none",
"value": 0.5074980268350434
}
},
"smollm-135m": {
"lambada_openai": {
"metric": "acc,none",
"value": 0.3757034737046381
},
"hellaswag": {
"metric": "acc_norm,none",
"value": 0.42650866361282613
},
"piqa": {
"metric": "acc_norm,none",
"value": 0.6822633297062024
},
"arc_easy": {
"metric": "acc_norm,none",
"value": 0.561026936026936
},
"arc_challenge": {
"metric": "acc_norm,none",
"value": 0.28754266211604096
},
"winogrande": {
"metric": "acc,none",
"value": 0.5272296764009471
}
},
"smollm2-135m": {
"lambada_openai": {
"metric": "acc,none",
"value": 0.4288763826896953
},
"hellaswag": {
"metric": "acc_norm,none",
"value": 0.43009360685122483
},
"piqa": {
"metric": "acc_norm,none",
"value": 0.6838955386289445
},
"arc_easy": {
"metric": "acc_norm,none",
"value": 0.5854377104377104
},
"arc_challenge": {
"metric": "acc_norm,none",
"value": 0.29692832764505117
},
"winogrande": {
"metric": "acc,none",
"value": 0.5248618784530387
}
}
}
}