open-llm-leaderboard-old/details_nisten__smaugzilla-77b
收藏数据集概述
数据集简介
该数据集是在评估模型 nisten/smaugzilla-77b 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1次运行创建，每个运行可以在每个配置中找到特定的分割，分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。
结果配置
一个额外的配置 "results" 存储了所有运行的聚合结果，用于计算和显示在 Open LLM Leaderboard 上的聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_nisten__smaugzilla-77b", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-25T09:11:08.117569 运行的最新结果：
python { "all": { "acc": 0.2313959419192546, "acc_stderr": 0.02980559001033843, "acc_norm": 0.2311889182949315, "acc_norm_stderr": 0.030586104532219726, "mc1": 0.23011015911872704, "mc1_stderr": 0.01473455795980776, "mc2": 0.4822114510622401, "mc2_stderr": 0.0164164994827405 }, "harness|arc:challenge|25": { "acc": 0.21928327645051193, "acc_stderr": 0.012091245787615725, "acc_norm": 0.24829351535836178, "acc_norm_stderr": 0.01262491286808976 }, "harness|hellaswag|10": { "acc": 0.2592113124875523, "acc_stderr": 0.004373062283376514, "acc_norm": 0.25164309898426607, "acc_norm_stderr": 0.004330703120137954 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.19, "acc_stderr": 0.03942772444036625, "acc_norm": 0.19, "acc_norm_stderr": 0.03942772444036625 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.26666666666666666, "acc_stderr": 0.03820169914517907, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.03820169914517907 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.031103182383123398, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.031103182383123398 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2490566037735849, "acc_stderr": 0.026616482980501715, "acc_norm": 0.2490566037735849, "acc_norm_stderr": 0.026616482980501715 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2569444444444444, "acc_stderr": 0.03653946969442099, "acc_norm": 0.2569444444444444, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.17, "acc_stderr": 0.0377525168068637, "acc_norm": 0.17, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.23699421965317918, "acc_stderr": 0.03242414757483098, "acc_norm": 0.23699421965317918, "acc_norm_stderr": 0.03242414757483098 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237654, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2553191489361702, "acc_stderr": 0.0285048564705142, "acc_norm": 0.2553191489361702, "acc_norm_stderr": 0.0285048564705142 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.22807017543859648, "acc_stderr": 0.03947152782669415, "acc_norm": 0.22807017543859648, "acc_norm_stderr": 0.03947152782669415 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2482758620689655, "acc_stderr": 0.036001056927277716, "acc_norm": 0.2482758620689655, "acc_norm_stderr": 0.036001056927277716 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.20899470899470898, "acc_stderr": 0.02094048156533486, "acc_norm": 0.20899470899470898, "acc_norm_stderr": 0.02094048156533486 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.1984126984126984, "acc_stderr": 0.03567016675276864, "acc_norm": 0.1984126984126984, "acc_norm_stderr": 0.03567016675276864 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.18, "acc_stderr": 0.038612291966536934, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536934 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.18064516129032257, "acc_stderr": 0.021886178567172548, "acc_norm": 0.18064516129032257, "acc_norm_stderr": 0.021886178567172548 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.15270935960591134, "acc_stderr": 0.02530890453938063, "acc_norm": 0.15270935960591134, "acc_norm_stderr": 0.02530890453938063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.26, "acc_stderr": 0.04408440022768078, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.22424242424242424, "acc_stderr": 0.032568666616811015, "acc_norm": 0.22424242424242424, "acc_norm_stderr": 0.032568666616811015 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.17676767676767677, "acc_stderr": 0.027178752639044915, "acc_norm": 0.17676767676767677, "acc_norm_stderr": 0.027178752639044915 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.19689119170984457, "acc_stderr": 0.028697873971860667, "acc_norm": 0.19689119170984457, "acc_norm_stderr": 0.028697873971860667 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.30256410256410254, "acc_stderr": 0.02329088805377274, "acc_norm": 0.30256410256410254, "acc_norm_stderr": 0.02329088805377274 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2111111111111111, "acc_stderr": 0.024882116857655075, "acc_norm": 0.2111111111111111, "acc_norm_stderr": 0.024882116
