open-llm-leaderboard-old/details_nnpy__Nape-0
收藏数据集概述
数据集简介
该数据集是在对模型 nnpy/Nape-0 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
数据集包含 64 个配置，每个配置对应一个评估任务。数据集从 1 次运行中创建，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" 分割始终指向最新结果。
额外配置
一个额外的配置 "results" 存储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
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_nnpy__Nape-0_public", "harness_winogrande_5", split="train")
最新结果
以下是 2023-11-18T20:32:43.776654 运行 的最新结果：
python { "all": { "acc": 0.2543128094432495, "acc_stderr": 0.03062072612679358, "acc_norm": 0.2558387672983551, "acc_norm_stderr": 0.031412385111215566, "mc1": 0.23745410036719705, "mc1_stderr": 0.014896277441041836, "mc2": 0.3899188336745711, "mc2_stderr": 0.014581462986356814, "em": 0.0017827181208053692, "em_stderr": 0.0004320097346039005, "f1": 0.03894714765100676, "f1_stderr": 0.0011174860838397392 }, "harness|arc:challenge|25": { "acc": 0.31143344709897613, "acc_stderr": 0.013532472099850939, "acc_norm": 0.3267918088737201, "acc_norm_stderr": 0.013706665975587331 }, "harness|hellaswag|10": { "acc": 0.4470225054769966, "acc_stderr": 0.004961693567208816, "acc_norm": 0.5868352917745469, "acc_norm_stderr": 0.004913955705080124 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.34074074074074073, "acc_stderr": 0.04094376269996793, "acc_norm": 0.34074074074074073, "acc_norm_stderr": 0.04094376269996793 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.23684210526315788, "acc_stderr": 0.034597776068105365, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.034597776068105365 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.2, "acc_stderr": 0.040201512610368445, "acc_norm": 0.2, "acc_norm_stderr": 0.040201512610368445 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.26037735849056604, "acc_stderr": 0.027008766090708097, "acc_norm": 0.26037735849056604, "acc_norm_stderr": 0.027008766090708097 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2152777777777778, "acc_stderr": 0.03437079344106132, "acc_norm": 0.2152777777777778, "acc_norm_stderr": 0.03437079344106132 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.18, "acc_stderr": 0.038612291966536955, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536955 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.16, "acc_stderr": 0.03684529491774709, "acc_norm": 0.16, "acc_norm_stderr": 0.03684529491774709 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.24, "acc_stderr": 0.04292346959909284, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909284 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.23121387283236994, "acc_stderr": 0.03214737302029471, "acc_norm": 0.23121387283236994, "acc_norm_stderr": 0.03214737302029471 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.24509803921568626, "acc_stderr": 0.04280105837364396, "acc_norm": 0.24509803921568626, "acc_norm_stderr": 0.04280105837364396 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.24, "acc_stderr": 0.04292346959909282, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.251063829787234, "acc_stderr": 0.028346963777162452, "acc_norm": 0.251063829787234, "acc_norm_stderr": 0.028346963777162452 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2719298245614035, "acc_stderr": 0.041857744240220575, "acc_norm": 0.2719298245614035, "acc_norm_stderr": 0.041857744240220575 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2896551724137931, "acc_stderr": 0.03780019230438014, "acc_norm": 0.2896551724137931, "acc_norm_stderr": 0.03780019230438014 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2671957671957672, "acc_stderr": 0.02278967314577656, "acc_norm": 0.2671957671957672, "acc_norm_stderr": 0.02278967314577656 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.14285714285714285, "acc_stderr": 0.0312984318574381, "acc_norm": 0.14285714285714285, "acc_norm_stderr": 0.0312984318574381 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.24838709677419354, "acc_stderr": 0.02458002892148101, "acc_norm": 0.24838709677419354, "acc_norm_stderr": 0.02458002892148101 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2561576354679803, "acc_stderr": 0.0307127300709826, "acc_norm": 0.2561576354679803, "acc_norm_stderr": 0.0307127300709826 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.296969696969697, "acc_stderr": 0.035679697722680474, "acc_norm": 0.296969696969697, "acc_norm_stderr": 0.035679697722680474 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.25252525252525254, "acc_stderr": 0.030954055470365904, "acc_norm": 0.25252525252525254, "acc_norm_stderr": 0.030954055470365904 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.22279792746113988, "acc_stderr": 0.030031147977641545, "acc_norm": 0.22279792746113988, "acc_norm_stderr": 0.030031147977641545 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.23076923076923078, "acc_stderr": 0.02136202772522271, "acc_norm": 0.23076923076923078, "acc_norm_stderr": 0.02136202772522271 }, "harness
