open-llm-leaderboard-old/details_jisukim8873__mistralai-case-1-1
收藏数据集概述
数据集来源
该数据集是在对模型 jisukim8873/mistralai-case-1-1 进行评估运行期间自动创建的，评估结果发布在 Open LLM Leaderboard 上。
数据集结构
数据集包含 63 个配置，每个配置对应一个评估任务。数据集是从 1 次运行中创建的，每次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 Open LLM Leaderboard 上的聚合指标。
数据加载示例
以下是加载特定运行详细信息的示例代码： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_jisukim8873__mistralai-case-1-1", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-22T05:25:09.752096 运行的最新结果： python { "all": { "acc": 0.6256111715138245, "acc_stderr": 0.032674427804334064, "acc_norm": 0.6317806220170934, "acc_norm_stderr": 0.033343028946711, "mc1": 0.2913096695226438, "mc1_stderr": 0.015905987048184828, "mc2": 0.411007042760005, "mc2_stderr": 0.01432538694569347 }, "harness|arc:challenge|25": { "acc": 0.5725255972696246, "acc_stderr": 0.014456862944650647, "acc_norm": 0.6092150170648464, "acc_norm_stderr": 0.01425856388051378 }, "harness|hellaswag|10": { "acc": 0.6269667396932882, "acc_stderr": 0.004826224784850442, "acc_norm": 0.8287193786098387, "acc_norm_stderr": 0.0037598401271507036 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6074074074074074, "acc_stderr": 0.0421850621536888, "acc_norm": 0.6074074074074074, "acc_norm_stderr": 0.0421850621536888 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6447368421052632, "acc_stderr": 0.038947344870133176, "acc_norm": 0.6447368421052632, "acc_norm_stderr": 0.038947344870133176 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6716981132075471, "acc_stderr": 0.02890159361241178, "acc_norm": 0.6716981132075471, "acc_norm_stderr": 0.02890159361241178 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6944444444444444, "acc_stderr": 0.03852084696008534, "acc_norm": 0.6944444444444444, "acc_norm_stderr": 0.03852084696008534 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "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": 0.39215686274509803, "acc_stderr": 0.048580835742663454, "acc_norm": 0.39215686274509803, "acc_norm_stderr": 0.048580835742663454 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.574468085106383, "acc_stderr": 0.032321469162244675, "acc_norm": 0.574468085106383, "acc_norm_stderr": 0.032321469162244675 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.49122807017543857, "acc_stderr": 0.047028804320496165, "acc_norm": 0.49122807017543857, "acc_norm_stderr": 0.047028804320496165 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5586206896551724, "acc_stderr": 0.04137931034482758, "acc_norm": 0.5586206896551724, "acc_norm_stderr": 0.04137931034482758 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3968253968253968, "acc_stderr": 0.025197101074246487, "acc_norm": 0.3968253968253968, "acc_norm_stderr": 0.025197101074246487 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.40476190476190477, "acc_stderr": 0.04390259265377562, "acc_norm": 0.40476190476190477, "acc_norm_stderr": 0.04390259265377562 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7225806451612903, "acc_stderr": 0.025470196835900055, "acc_norm": 0.7225806451612903, "acc_norm_stderr": 0.025470196835900055 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5270935960591133, "acc_stderr": 0.03512819077876106, "acc_norm": 0.5270935960591133, "acc_norm_stderr": 0.03512819077876106 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7696969696969697, "acc_stderr": 0.032876667586034906, "acc_norm": 0.7696969696969697, "acc_norm_stderr": 0.032876667586034906 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7828282828282829, "acc_stderr": 0.029376616484945627, "acc_norm": 0.7828282828282829, "acc_norm_stderr": 0.029376616484945627 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8341968911917098, "acc_stderr": 0.026839845022314415, "acc_norm": 0.8341968911917098, "acc_norm_stderr": 0.026839845022314415 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6256410256410256, "acc_stderr": 0.024537591572830506, "acc_norm": 0.6256410256410256, "acc_norm_stderr": 0.024537591572830506 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3296296296296296, "acc_stderr": 0.0286612011
