open-llm-leaderboard-old/details_indischepartij__TinyUltra-4x1.1B-Base-Alpha
收藏数据集概述
该数据集是在对模型 indischepartij/TinyUltra-4x1.1B-Base-Alpha 进行评估运行时自动创建的，用于 Open LLM Leaderboard。
数据集组成
- 数据集包含 63 个配置，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。
加载数据集示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_indischepartij__TinyUltra-4x1.1B-Base-Alpha", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-01T23:08:05.664341 运行的最新结果：
python { "all": { "acc": 0.26201452650295837, "acc_stderr": 0.030950575098959248, "acc_norm": 0.26190159146597486, "acc_norm_stderr": 0.03169834440202644, "mc1": 0.2350061199510404, "mc1_stderr": 0.014843061507731618, "mc2": 0.3758799861882878, "mc2_stderr": 0.014070883279660485 }, "harness|arc:challenge|25": { "acc": 0.3447098976109215, "acc_stderr": 0.01388881628678211, "acc_norm": 0.34897610921501704, "acc_norm_stderr": 0.013928933461382504 }, "harness|hellaswag|10": { "acc": 0.46594303923521213, "acc_stderr": 0.004978192893406287, "acc_norm": 0.6142202748456482, "acc_norm_stderr": 0.004857840934549174 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2222222222222222, "acc_stderr": 0.035914440841969694, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.035914440841969694 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.03110318238312338, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.03110318238312338 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.26, "acc_stderr": 0.04408440022768079, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.27169811320754716, "acc_stderr": 0.027377706624670713, "acc_norm": 0.27169811320754716, "acc_norm_stderr": 0.027377706624670713 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2569444444444444, "acc_stderr": 0.03653946969442099, "acc_norm": 0.2569444444444444, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.24, "acc_stderr": 0.04292346959909282, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2138728323699422, "acc_stderr": 0.03126511206173043, "acc_norm": 0.2138728323699422, "acc_norm_stderr": 0.03126511206173043 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.19607843137254902, "acc_stderr": 0.03950581861179961, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.03950581861179961 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.32340425531914896, "acc_stderr": 0.030579442773610334, "acc_norm": 0.32340425531914896, "acc_norm_stderr": 0.030579442773610334 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.0414243971948936, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.0414243971948936 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.23448275862068965, "acc_stderr": 0.035306258743465914, "acc_norm": 0.23448275862068965, "acc_norm_stderr": 0.035306258743465914 }, "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": 0.20634920634920634, "acc_stderr": 0.036196045241242515, "acc_norm": 0.20634920634920634, "acc_norm_stderr": 0.036196045241242515 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.26129032258064516, "acc_stderr": 0.024993053397764826, "acc_norm": 0.26129032258064516, "acc_norm_stderr": 0.024993053397764826 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.27586206896551724, "acc_stderr": 0.031447125816782405, "acc_norm": 0.27586206896551724, "acc_norm_stderr": 0.031447125816782405 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.24848484848484848, "acc_stderr": 0.03374402644139404, "acc_norm": 0.24848484848484848, "acc_norm_stderr": 0.03374402644139404 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.21717171717171718, "acc_stderr": 0.029376616484945637, "acc_norm": 0.21717171717171718, "acc_norm_stderr": 0.029376616484945637 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.22279792746113988, "acc_stderr": 0.03003114797764154, "acc_norm": 0.22279792746113988, "acc_norm_stderr": 0.03003114797764154 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.23333333333333334, "acc_stderr": 0.021444547301560486, "acc_norm": 0.23333333333333334, "acc_norm_stderr": 0.021444547301560486 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26296296296296295, "acc_stderr": 0.026842057873833706, "acc_norm": 0.2629
