open-llm-leaderboard-old/details_paulilioaica__Collin-7B-dare
收藏数据集概述
数据集描述
该数据集是在对模型 paulilioaica/Collin-7B-dare 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 63 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一个特定的分割，分割名称使用运行的时间戳。
- "train" 分割始终指向最新的结果。
- 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_paulilioaica__Collin-7B-dare", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2024-01-28T19:04:00.761394 的运行： python { "all": { "acc": 0.5209951850139622, "acc_stderr": 0.034255506033106245, "acc_norm": 0.5260738190060968, "acc_norm_stderr": 0.035005434358067744, "mc1": 0.5177478580171359, "mc1_stderr": 0.01749247084307536, "mc2": 0.6520234737027234, "mc2_stderr": 0.015553743495889045 }, "harness|arc:challenge|25": { "acc": 0.6151877133105802, "acc_stderr": 0.014218371065251104, "acc_norm": 0.658703071672355, "acc_norm_stderr": 0.013855831287497726 }, "harness|hellaswag|10": { "acc": 0.6176060545708026, "acc_stderr": 0.004849788423944363, "acc_norm": 0.8207528380800637, "acc_norm_stderr": 0.003827752572770012 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4740740740740741, "acc_stderr": 0.04313531696750574, "acc_norm": 0.4740740740740741, "acc_norm_stderr": 0.04313531696750574 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5921052631578947, "acc_stderr": 0.039993097127774734, "acc_norm": 0.5921052631578947, "acc_norm_stderr": 0.039993097127774734 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.569811320754717, "acc_stderr": 0.030471445867183238, "acc_norm": 0.569811320754717, "acc_norm_stderr": 0.030471445867183238 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5972222222222222, "acc_stderr": 0.041014055198424264, "acc_norm": 0.5972222222222222, "acc_norm_stderr": 0.041014055198424264 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5433526011560693, "acc_stderr": 0.03798106566014498, "acc_norm": 0.5433526011560693, "acc_norm_stderr": 0.03798106566014498 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04690650298201942, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04690650298201942 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.42127659574468085, "acc_stderr": 0.032278345101462665, "acc_norm": 0.42127659574468085, "acc_norm_stderr": 0.032278345101462665 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.38596491228070173, "acc_stderr": 0.04579639422070434, "acc_norm": 0.38596491228070173, "acc_norm_stderr": 0.04579639422070434 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4689655172413793, "acc_stderr": 0.04158632762097828, "acc_norm": 0.4689655172413793, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.335978835978836, "acc_stderr": 0.02432631052914913, "acc_norm": 0.335978835978836, "acc_norm_stderr": 0.02432631052914913 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.30952380952380953, "acc_stderr": 0.04134913018303316, "acc_norm": 0.30952380952380953, "acc_norm_stderr": 0.04134913018303316 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.4774193548387097, "acc_stderr": 0.02841498501970786, "acc_norm": 0.4774193548387097, "acc_norm_stderr": 0.02841498501970786 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3497536945812808, "acc_stderr": 0.03355400904969566, "acc_norm": 0.3497536945812808, "acc_norm_stderr": 0.03355400904969566 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5212121212121212, "acc_stderr": 0.03900828913737301, "acc_norm": 0.5212121212121212, "acc_norm_stderr": 0.03900828913737301 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6717171717171717, "acc_stderr": 0.03345678422756775, "acc_norm": 0.6717171717171717, "acc_norm_stderr": 0.03345678422756775 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7823834196891192, "acc_stderr": 0.029778663037752954, "acc_norm": 0.7823834196891192, "acc_norm_stderr": 0.029778663037752954 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4948717948717949, "acc_stderr": 0.025349672906838653, "acc_norm": 0.4948717948717949, "acc_norm_stderr": 0.025349672906838653 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2814814814814815, "acc_stderr": 0.027420019350945284, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.027420019350945284 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.5, "acc_
