open-llm-leaderboard-old/details_zelus82__Obelix-Phi2
收藏数据集概述
该数据集是在评估模型 zelus82/Obelix-Phi2 在 Open LLM Leaderboard 上的运行过程中自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
数据集由 2 次运行结果组成，每次运行的详细结果可以在每个配置中找到，并以运行的时间戳命名。每个配置中的 "train" 分割始终指向最新的结果。
加载数据
可以通过以下代码加载特定运行的详细信息：
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_zelus82__Obelix-Phi2", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-27T18:35:12.191328 运行的最新结果：
python { "all": { "acc": 0.5853924359239346, "acc_stderr": 0.03378364174710213, "acc_norm": 0.5856717116958013, "acc_norm_stderr": 0.03448015035691927, "mc1": 0.3659730722154223, "mc1_stderr": 0.01686294168408837, "mc2": 0.512857705990862, "mc2_stderr": 0.015743075492404626 }, "harness|arc:challenge|25": { "acc": 0.5870307167235495, "acc_stderr": 0.014388344935398326, "acc_norm": 0.6177474402730375, "acc_norm_stderr": 0.014200454049979288 }, "harness|hellaswag|10": { "acc": 0.5887273451503684, "acc_stderr": 0.004910588449330018, "acc_norm": 0.767576180043816, "acc_norm_stderr": 0.004215145576745956 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.045126085985421296, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421296 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4888888888888889, "acc_stderr": 0.04318275491977976, "acc_norm": 0.4888888888888889, "acc_norm_stderr": 0.04318275491977976 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.625, "acc_stderr": 0.039397364351956274, "acc_norm": 0.625, "acc_norm_stderr": 0.039397364351956274 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5886792452830188, "acc_stderr": 0.030285009259009794, "acc_norm": 0.5886792452830188, "acc_norm_stderr": 0.030285009259009794 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6458333333333334, "acc_stderr": 0.039994111357535424, "acc_norm": 0.6458333333333334, "acc_norm_stderr": 0.039994111357535424 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.39, "acc_stderr": 0.049020713000019756, "acc_norm": 0.39, "acc_norm_stderr": 0.049020713000019756 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.42, "acc_stderr": 0.04960449637488584, "acc_norm": 0.42, "acc_norm_stderr": 0.04960449637488584 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6184971098265896, "acc_stderr": 0.03703851193099521, "acc_norm": 0.6184971098265896, "acc_norm_stderr": 0.03703851193099521 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4019607843137255, "acc_stderr": 0.04878608714466996, "acc_norm": 0.4019607843137255, "acc_norm_stderr": 0.04878608714466996 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.04408440022768078, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4765957446808511, "acc_stderr": 0.03265019475033582, "acc_norm": 0.4765957446808511, "acc_norm_stderr": 0.03265019475033582 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3684210526315789, "acc_stderr": 0.04537815354939392, "acc_norm": 0.3684210526315789, "acc_norm_stderr": 0.04537815354939392 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5103448275862069, "acc_stderr": 0.04165774775728763, "acc_norm": 0.5103448275862069, "acc_norm_stderr": 0.04165774775728763 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42857142857142855, "acc_stderr": 0.025487187147859375, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.025487187147859375 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.38095238095238093, "acc_stderr": 0.04343525428949097, "acc_norm": 0.38095238095238093, "acc_norm_stderr": 0.04343525428949097 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6838709677419355, "acc_stderr": 0.02645087448904277, "acc_norm": 0.6838709677419355, "acc_norm_stderr": 0.02645087448904277 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4975369458128079, "acc_stderr": 0.03517945038691063, "acc_norm": 0.4975369458128079, "acc_norm_stderr": 0.03517945038691063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.65, "acc_stderr": 0.047937248544110196, "acc_norm": 0.65, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6848484848484848, "acc_stderr": 0.0362773057502241, "acc_norm": 0.6848484848484848, "acc_norm_stderr": 0.0362773057502241 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7323232323232324, "acc_stderr": 0.03154449888270285, "acc_norm": 0.7323232323232324, "acc_norm_stderr": 0.03154449888270285 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7927461139896373, "acc_stderr": 0.029252823291803624, "acc_norm": 0.7927461139896373, "acc_norm_stderr": 0.029252823291803624 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6, "acc_stderr": 0.02483881198803316, "acc_norm": 0.6, "acc_norm_stderr": 0.02483881198803316 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32592592592592595, "acc_stderr": 0.028578348365473065, "acc_norm": 0.32592592592592595, "acc_norm_stderr": 0.028578348365473065 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.634453781512605, "acc_stderr": 0.03128217706368461, "acc_norm": 0.634453781512605, "acc_norm_stderr": 0.031
