open-llm-leaderboard-old/details_ArianAskari__NeuralHermes-2.5-Mistral-7B
收藏数据集概述
数据集摘要
该数据集是在对模型 ArianAskari/NeuralHermes-2.5-Mistral-7B 进行评估运行期间自动创建的，评估结果发布在 Open LLM Leaderboard 上。
数据集组成
数据集由 63 个配置组成，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。
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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_ArianAskari__NeuralHermes-2.5-Mistral-7B", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-02T00:23:23.624416 运行的最新结果： python { "all": { "acc": 0.6381118013498635, "acc_stderr": 0.03228022346468125, "acc_norm": 0.6407857748626177, "acc_norm_stderr": 0.032921741406603505, "mc1": 0.3598531211750306, "mc1_stderr": 0.016801860466677157, "mc2": 0.5223229691481044, "mc2_stderr": 0.015242725441292206 }, "harness|arc:challenge|25": { "acc": 0.6075085324232082, "acc_stderr": 0.014269634635670733, "acc_norm": 0.6467576791808873, "acc_norm_stderr": 0.013967822714840055 }, "harness|hellaswag|10": { "acc": 0.6520613423620792, "acc_stderr": 0.00475342980664544, "acc_norm": 0.842760406293567, "acc_norm_stderr": 0.003632825479128597 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5851851851851851, "acc_stderr": 0.04256193767901408, "acc_norm": 0.5851851851851851, "acc_norm_stderr": 0.04256193767901408 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6973684210526315, "acc_stderr": 0.037385206761196686, "acc_norm": 0.6973684210526315, "acc_norm_stderr": 0.037385206761196686 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6792452830188679, "acc_stderr": 0.028727502957880267, "acc_norm": 0.6792452830188679, "acc_norm_stderr": 0.028727502957880267 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7569444444444444, "acc_stderr": 0.03586879280080341, "acc_norm": 0.7569444444444444, "acc_norm_stderr": 0.03586879280080341 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "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": 0.4019607843137255, "acc_stderr": 0.04878608714466996, "acc_norm": 0.4019607843137255, "acc_norm_stderr": 0.04878608714466996 }, "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": 0.5617021276595745, "acc_stderr": 0.03243618636108101, "acc_norm": 0.5617021276595745, "acc_norm_stderr": 0.03243618636108101 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.49122807017543857, "acc_stderr": 0.04702880432049615, "acc_norm": 0.49122807017543857, "acc_norm_stderr": 0.04702880432049615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5241379310344828, "acc_stderr": 0.0416180850350153, "acc_norm": 0.5241379310344828, "acc_norm_stderr": 0.0416180850350153 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4312169312169312, "acc_stderr": 0.025506481698138215, "acc_norm": 0.4312169312169312, "acc_norm_stderr": 0.025506481698138215 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4603174603174603, "acc_stderr": 0.04458029125470973, "acc_norm": 0.4603174603174603, "acc_norm_stderr": 0.04458029125470973 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7903225806451613, "acc_stderr": 0.023157879349083525, "acc_norm": 0.7903225806451613, "acc_norm_stderr": 0.023157879349083525 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5123152709359606, "acc_stderr": 0.035169204442208966, "acc_norm": 0.5123152709359606, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.67, "acc_stderr": 0.047258156262526066, "acc_norm": 0.67, "acc_norm_stderr": 0.047258156262526066 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.793939393939394, "acc_stderr": 0.031584153240477114, "acc_norm": 0.793939393939394, "acc_norm_stderr": 0.031584153240477114 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.803030303030303, "acc_stderr": 0.02833560973246336, "acc_norm": 0.803030303030303, "acc_norm_stderr": 0.02833560973246336 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8860103626943006, "acc_stderr": 0.022935144053919443, "acc_norm": 0.8860103626943006, "acc_norm_stderr": 0.022935144053919443 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6076923076923076, "acc_stderr": 0.024756000382130956, "acc_norm": 0.6076923076923076, "acc_norm_stderr": 0.024756000382130956 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2962962962962963, "acc_stderr": 0.02784081149587193, "acc_norm": 0.296
