open-llm-leaderboard-old/details_aevalone__Pengland-Merge
收藏数据集概述
该数据集是在对模型 aevalone/Pengland-Merge 进行评估运行时自动创建的，用于 Open LLM Leaderboard。
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。
- 数据集从 1 次运行中创建，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。
- 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_aevalone__Pengland-Merge", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-25T06:50:36.319568 运行 的最新结果：
python { "all": { "acc": 0.4951138346481346, "acc_stderr": 0.03407816807613722, "acc_norm": 0.5048451795300618, "acc_norm_stderr": 0.03500738607918216, "mc1": 0.2215422276621787, "mc1_stderr": 0.014537867601301145, "mc2": 0.47030169673148503, "mc2_stderr": 0.016478296846766455 }, "harness|arc:challenge|25": { "acc": 0.37627986348122866, "acc_stderr": 0.014157022555407172, "acc_norm": 0.4052901023890785, "acc_norm_stderr": 0.014346869060229325 }, "harness|hellaswag|10": { "acc": 0.32613025293766185, "acc_stderr": 0.004678375103797975, "acc_norm": 0.4706233817964549, "acc_norm_stderr": 0.004981161746388227 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.27, "acc_stderr": 0.04461960433384741, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.48148148148148145, "acc_stderr": 0.043163785995113245, "acc_norm": 0.48148148148148145, "acc_norm_stderr": 0.043163785995113245 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6052631578947368, "acc_stderr": 0.039777499346220734, "acc_norm": 0.6052631578947368, "acc_norm_stderr": 0.039777499346220734 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6150943396226415, "acc_stderr": 0.02994649856769995, "acc_norm": 0.6150943396226415, "acc_norm_stderr": 0.02994649856769995 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5972222222222222, "acc_stderr": 0.04101405519842426, "acc_norm": 0.5972222222222222, "acc_norm_stderr": 0.04101405519842426 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "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": 0.5202312138728323, "acc_stderr": 0.03809342081273957, "acc_norm": 0.5202312138728323, "acc_norm_stderr": 0.03809342081273957 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3431372549019608, "acc_stderr": 0.047240073523838876, "acc_norm": 0.3431372549019608, "acc_norm_stderr": 0.047240073523838876 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4765957446808511, "acc_stderr": 0.032650194750335815, "acc_norm": 0.4765957446808511, "acc_norm_stderr": 0.032650194750335815 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.41228070175438597, "acc_stderr": 0.04630653203366595, "acc_norm": 0.41228070175438597, "acc_norm_stderr": 0.04630653203366595 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5172413793103449, "acc_stderr": 0.04164188720169375, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.04164188720169375 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3915343915343915, "acc_stderr": 0.025138091388851112, "acc_norm": 0.3915343915343915, "acc_norm_stderr": 0.025138091388851112 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2619047619047619, "acc_stderr": 0.039325376803928704, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.039325376803928704 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5064516129032258, "acc_stderr": 0.02844163823354051, "acc_norm": 0.5064516129032258, "acc_norm_stderr": 0.02844163823354051 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3793103448275862, "acc_stderr": 0.034139638059062345, "acc_norm": 0.3793103448275862, "acc_norm_stderr": 0.034139638059062345 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.3515151515151515, "acc_stderr": 0.0372820699868265, "acc_norm": 0.3515151515151515, "acc_norm_stderr": 0.0372820699868265 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6616161616161617, "acc_stderr": 0.03371124142626302, "acc_norm": 0.6616161616161617, "acc_norm_stderr": 0.03371124142626302 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7927461139896373, "acc_stderr": 0.02925282329180363, "acc_norm": 0.7927461139896373, "acc_norm_stderr": 0.02925282329180363 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4897435897435897, "acc_stderr": 0.025345672221942374, "acc_norm": 0.4897435897435897, "acc_norm_stderr": 0.025345672221942374 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.23333333333333334, "acc_stderr": 0.025787874220959316, "acc_norm": 0.23333333333333334, "acc_norm_stderr": 0.0257878
