open-llm-leaderboard-old/details_ToastyPigeon__smolphin-test-stack
收藏数据集概述
数据集简介
该数据集是在模型 ToastyPigeon/smolphin-test-stack 的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_ToastyPigeon__smolphin-test-stack", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-25T03:16:22.374930 运行的最新结果：
python { "all": { "acc": 0.2576236542436733, "acc_stderr": 0.03071582201279267, "acc_norm": 0.2587962741606236, "acc_norm_stderr": 0.031490332830215, "mc1": 0.23255813953488372, "mc1_stderr": 0.0147891575310805, "mc2": 0.3664279625945466, "mc2_stderr": 0.013923552920892408 }, "harness|arc:challenge|25": { "acc": 0.2960750853242321, "acc_stderr": 0.013340916085246252, "acc_norm": 0.3267918088737201, "acc_norm_stderr": 0.013706665975587323 }, "harness|hellaswag|10": { "acc": 0.4482174865564629, "acc_stderr": 0.0049629497842360445, "acc_norm": 0.5993825931089425, "acc_norm_stderr": 0.00489022101201507 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.04229525846816508, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816508 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.25925925925925924, "acc_stderr": 0.03785714465066654, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.03785714465066654 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.18421052631578946, "acc_stderr": 0.0315469804508223, "acc_norm": 0.18421052631578946, "acc_norm_stderr": 0.0315469804508223 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.29, "acc_stderr": 0.04560480215720683, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720683 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.21132075471698114, "acc_stderr": 0.025125766484827845, "acc_norm": 0.21132075471698114, "acc_norm_stderr": 0.025125766484827845 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2638888888888889, "acc_stderr": 0.03685651095897532, "acc_norm": 0.2638888888888889, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.21, "acc_stderr": 0.04093601807403326, "acc_norm": 0.21, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.18497109826589594, "acc_stderr": 0.02960562398177122, "acc_norm": 0.18497109826589594, "acc_norm_stderr": 0.02960562398177122 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.28431372549019607, "acc_stderr": 0.04488482852329017, "acc_norm": 0.28431372549019607, "acc_norm_stderr": 0.04488482852329017 }, "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": 0.225531914893617, "acc_stderr": 0.02732107841738753, "acc_norm": 0.225531914893617, "acc_norm_stderr": 0.02732107841738753 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.23684210526315788, "acc_stderr": 0.039994238792813344, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.039994238792813344 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2482758620689655, "acc_stderr": 0.03600105692727772, "acc_norm": 0.2482758620689655, "acc_norm_stderr": 0.03600105692727772 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2566137566137566, "acc_stderr": 0.022494510767503154, "acc_norm": 0.2566137566137566, "acc_norm_stderr": 0.022494510767503154 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.1984126984126984, "acc_stderr": 0.03567016675276865, "acc_norm": 0.1984126984126984, "acc_norm_stderr": 0.03567016675276865 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.19, "acc_stderr": 0.039427724440366234, "acc_norm": 0.19, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.25483870967741934, "acc_stderr": 0.024790118459332204, "acc_norm": 0.25483870967741934, "acc_norm_stderr": 0.024790118459332204 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.270935960591133, "acc_stderr": 0.031270907132976984, "acc_norm": 0.270935960591133, "acc_norm_stderr": 0.031270907132976984 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.2, "acc_stderr": 0.04020151261036844, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036844 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2727272727272727, "acc_stderr": 0.0347769116216366, "acc_norm": 0.2727272727272727, "acc_norm_stderr": 0.0347769116216366 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.21212121212121213, "acc_stderr": 0.02912652283458682, "acc_norm": 0.21212121212121213, "acc_norm_stderr": 0.02912652283458682 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.32124352331606215, "acc_stderr": 0.033699508685490674, "acc_norm": 0.32124352331606215, "acc_norm_stderr": 0.033699508685490674 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3128205128205128, "acc_stderr": 0.02350757902064535, "acc_norm": 0.3128205128205128, "acc_norm_stderr": 0.02350757902064535 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.25925925925925924, "acc_stderr": 0.02671924078371217, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.02
