open-llm-leaderboard-old/details_liuchanghf__bloomz3b-winogrande-pretrain
收藏数据集概述
该数据集是在评估模型 liuchanghf/bloomz3b-winogrande-pretrain 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。
额外配置
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 Open LLM Leaderboard 上的聚合指标。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_liuchanghf__bloomz3b-winogrande-pretrain", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 来自 2024-04-24T14:32:20.496429 的运行结果：
python { "all": { "acc": 0.30785866030699127, "acc_stderr": 0.03240975777498835, "acc_norm": 0.310460733911264, "acc_norm_stderr": 0.03328616765839484, "mc1": 0.20685434516523868, "mc1_stderr": 0.014179591496728343, "mc2": 0.3944147057427699, "mc2_stderr": 0.014800664324782834 }, "harness|arc:challenge|25": { "acc": 0.30631399317406144, "acc_stderr": 0.013470584417276513, "acc_norm": 0.34044368600682595, "acc_norm_stderr": 0.013847460518892976 }, "harness|hellaswag|10": { "acc": 0.39464250149372637, "acc_stderr": 0.004877748536428437, "acc_norm": 0.5249950209121689, "acc_norm_stderr": 0.0049835427688535465 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.26666666666666666, "acc_stderr": 0.03820169914517905, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.03820169914517905 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.2236842105263158, "acc_stderr": 0.03391160934343601, "acc_norm": 0.2236842105263158, "acc_norm_stderr": 0.03391160934343601 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.33584905660377357, "acc_stderr": 0.029067220146644823, "acc_norm": 0.33584905660377357, "acc_norm_stderr": 0.029067220146644823 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2777777777777778, "acc_stderr": 0.03745554791462458, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.03745554791462458 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.21, "acc_stderr": 0.04093601807403326, "acc_norm": 0.21, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.35260115606936415, "acc_stderr": 0.036430371689585475, "acc_norm": 0.35260115606936415, "acc_norm_stderr": 0.036430371689585475 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.27450980392156865, "acc_stderr": 0.04440521906179327, "acc_norm": 0.27450980392156865, "acc_norm_stderr": 0.04440521906179327 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.28936170212765955, "acc_stderr": 0.029644006577009618, "acc_norm": 0.28936170212765955, "acc_norm_stderr": 0.029644006577009618 }, "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": 0.3310344827586207, "acc_stderr": 0.03921545312467122, "acc_norm": 0.3310344827586207, "acc_norm_stderr": 0.03921545312467122 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.24603174603174602, "acc_stderr": 0.02218203720294836, "acc_norm": 0.24603174603174602, "acc_norm_stderr": 0.02218203720294836 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.16666666666666666, "acc_stderr": 0.03333333333333337, "acc_norm": 0.16666666666666666, "acc_norm_stderr": 0.03333333333333337 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.2, "acc_stderr": 0.04020151261036846, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036846 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.29354838709677417, "acc_stderr": 0.0259060870213193, "acc_norm": 0.29354838709677417, "acc_norm_stderr": 0.0259060870213193 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.26108374384236455, "acc_stderr": 0.030903796952114485, "acc_norm": 0.26108374384236455, "acc_norm_stderr": 0.030903796952114485 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.22424242424242424, "acc_stderr": 0.03256866661681102, "acc_norm": 0.22424242424242424, "acc_norm_stderr": 0.03256866661681102 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.31313131313131315, "acc_stderr": 0.033042050878136525, "acc_norm": 0.31313131313131315, "acc_norm_stderr": 0.033042050878136525 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.30569948186528495, "acc_stderr": 0.033248379397581594, "acc_norm": 0.30569948186528495, "acc_norm_stderr": 0.033248379397581594 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.31025641025641026, "acc_stderr": 0.023454674889404288, "acc_norm": 0.31025641025641026, "acc_norm_stderr": 0.023454674889404288 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.27037037037037037, "acc_stderr": 0.027080372815145658, "acc_norm": 0.27037037
