open-llm-leaderboard-old/details_juhwanlee__gemma-7B-alpaca-case-2-3
收藏数据集概述
数据集摘要
该数据集是在对模型 juhwanlee/gemma-7B-alpaca-case-2-3 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。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_juhwanlee__gemma-7B-alpaca-case-2-3", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-27T18:29:11.869374 运行的最新结果：
python { "all": { "acc": 0.26908811376582065, "acc_stderr": 0.031454313335312636, "acc_norm": 0.2701685926335597, "acc_norm_stderr": 0.032293322700319135, "mc1": 0.21542227662178703, "mc1_stderr": 0.014391902652427678, "mc2": 0.4798747402340299, "mc2_stderr": 0.0170283180875269 }, "harness|arc:challenge|25": { "acc": 0.22013651877133106, "acc_stderr": 0.01210812488346098, "acc_norm": 0.25597269624573377, "acc_norm_stderr": 0.012753013241244518 }, "harness|hellaswag|10": { "acc": 0.2570205138418642, "acc_stderr": 0.004360977256058731, "acc_norm": 0.2566221868153754, "acc_norm_stderr": 0.004358764596401032 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.34814814814814815, "acc_stderr": 0.041153246103369526, "acc_norm": 0.34814814814814815, "acc_norm_stderr": 0.041153246103369526 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.34210526315789475, "acc_stderr": 0.03860731599316091, "acc_norm": 0.34210526315789475, "acc_norm_stderr": 0.03860731599316091 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2981132075471698, "acc_stderr": 0.028152837942493857, "acc_norm": 0.2981132075471698, "acc_norm_stderr": 0.028152837942493857 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.25, "acc_stderr": 0.03621034121889507, "acc_norm": 0.25, "acc_norm_stderr": 0.03621034121889507 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.24, "acc_stderr": 0.04292346959909282, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.24855491329479767, "acc_stderr": 0.03295304696818318, "acc_norm": 0.24855491329479767, "acc_norm_stderr": 0.03295304696818318 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.30392156862745096, "acc_stderr": 0.045766654032077636, "acc_norm": 0.30392156862745096, "acc_norm_stderr": 0.045766654032077636 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2, "acc_stderr": 0.026148818018424513, "acc_norm": 0.2, "acc_norm_stderr": 0.026148818018424513 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2543859649122807, "acc_stderr": 0.040969851398436695, "acc_norm": 0.2543859649122807, "acc_norm_stderr": 0.040969851398436695 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.30344827586206896, "acc_stderr": 0.038312260488503336, "acc_norm": 0.30344827586206896, "acc_norm_stderr": 0.038312260488503336 }, "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": 0.1746031746031746, "acc_stderr": 0.03395490020856113, "acc_norm": 0.1746031746031746, "acc_norm_stderr": 0.03395490020856113 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.25161290322580643, "acc_stderr": 0.024685979286239956, "acc_norm": 0.25161290322580643, "acc_norm_stderr": 0.024685979286239956 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.31527093596059114, "acc_stderr": 0.03269080871970187, "acc_norm": 0.31527093596059114, "acc_norm_stderr": 0.03269080871970187 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.32, "acc_stderr": 0.04688261722621505, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.28484848484848485, "acc_stderr": 0.035243908445117836, "acc_norm": 0.28484848484848485, "acc_norm_stderr": 0.035243908445117836 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.35858585858585856, "acc_stderr": 0.03416903640391521, "acc_norm": 0.35858585858585856, "acc_norm_stderr": 0.03416903640391521 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.3316062176165803, "acc_stderr": 0.03397636541089116, "acc_norm": 0.3316062176165803, "acc_norm_stderr": 0.03397636541089116 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.32051282051282054, "acc_stderr": 0.02366129639396428, "acc_norm": 0.32051282051282054, "acc_norm_stderr": 0.02366129639396428 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.22592592592592592, "acc_stderr": 0.025497532639609542, "acc_norm": 0.22592592592592592, "acc_norm_stderr": 0.0254
