open-llm-leaderboard-old/details_ArianAskari__SOLID-SFT-WoDPO-MixQV2-Zephyr-7b-beta
收藏数据集概述
数据集摘要
该数据集是在对模型 ArianAskari/SOLID-SFT-WoDPO-MixQV2-Zephyr-7b-beta 进行评估运行期间自动创建的。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作为一个特定的分片找到，分片名称使用运行的时间戳。"train" 分片总是指向最新的结果。
结果配置
一个额外的配置 "results" 存储所有运行的聚合结果，用于计算和显示在 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_ArianAskari__SOLID-SFT-WoDPO-MixQV2-Zephyr-7b-beta", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-11T14:20:18.392173 运行的最新结果：
python { "all": { "acc": 0.5989068889556914, "acc_stderr": 0.03306588865476634, "acc_norm": 0.6081578643232973, "acc_norm_stderr": 0.03380748896101241, "mc1": 0.3818849449204406, "mc1_stderr": 0.017008101939163495, "mc2": 0.5376745022515824, "mc2_stderr": 0.01602462184426783 }, "harness|arc:challenge|25": { "acc": 0.5631399317406144, "acc_stderr": 0.014494421584256522, "acc_norm": 0.5972696245733788, "acc_norm_stderr": 0.01433223630679014 }, "harness|hellaswag|10": { "acc": 0.6338378809002191, "acc_stderr": 0.004807699539973415, "acc_norm": 0.817167894841665, "acc_norm_stderr": 0.003857388613533091 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5333333333333333, "acc_stderr": 0.043097329010363554, "acc_norm": 0.5333333333333333, "acc_norm_stderr": 0.043097329010363554 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.618421052631579, "acc_stderr": 0.03953173377749194, "acc_norm": 0.618421052631579, "acc_norm_stderr": 0.03953173377749194 }, "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": 0.6377358490566037, "acc_stderr": 0.0295822451283843, "acc_norm": 0.6377358490566037, "acc_norm_stderr": 0.0295822451283843 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7222222222222222, "acc_stderr": 0.037455547914624555, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.037455547914624555 }, "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": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6242774566473989, "acc_stderr": 0.036928207672648664, "acc_norm": 0.6242774566473989, "acc_norm_stderr": 0.036928207672648664 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.04784060704105654, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.04784060704105654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.04229525846816506, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5361702127659574, "acc_stderr": 0.03260038511835772, "acc_norm": 0.5361702127659574, "acc_norm_stderr": 0.03260038511835772 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.45614035087719296, "acc_stderr": 0.04685473041907789, "acc_norm": 0.45614035087719296, "acc_norm_stderr": 0.04685473041907789 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5379310344827586, "acc_stderr": 0.04154659671707548, "acc_norm": 0.5379310344827586, "acc_norm_stderr": 0.04154659671707548 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3994708994708995, "acc_stderr": 0.025225450284067884, "acc_norm": 0.3994708994708995, "acc_norm_stderr": 0.025225450284067884 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3968253968253968, "acc_stderr": 0.043758884927270605, "acc_norm": 0.3968253968253968, "acc_norm_stderr": 0.043758884927270605 }, "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": 0.7483870967741936, "acc_stderr": 0.024685979286239966, "acc_norm": 0.7483870967741936, "acc_norm_stderr": 0.024685979286239966 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.47783251231527096, "acc_stderr": 0.03514528562175008, "acc_norm": 0.47783251231527096, "acc_norm_stderr": 0.03514528562175008 }, "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": 0.7515151515151515, "acc_stderr": 0.033744026441394036, "acc_norm": 0.7515151515151515, "acc_norm_stderr": 0.033744026441394036 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7373737373737373, "acc_stderr": 0.03135305009533086, "acc_norm": 0.7373737373737373, "acc_norm_stderr": 0.03135305009533086 }, "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": 0.6128205128205129, "acc_stderr": 0.024697216930878934, "acc_norm": 0.6128205128205129, "acc_norm_stderr": 0.024697216930878934 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.34074074074074073, "acc_stderr": 0.02889774874113115, "acc_norm": 0
