open-llm-leaderboard-old/details_BFauber__opt125m_10e5_lr2e-5
收藏数据集概述
数据集简介
该数据集是在对模型 BFauber/opt125m_10e5_lr2e-5 进行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 "results" 配置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_BFauber__opt125m_10e5_lr2e-5", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果,来自 2024-04-23T18:55:50.156124 的运行: python { "all": { "acc": 0.25637443680638616, "acc_stderr": 0.030729179774188004, "acc_norm": 0.2572610584746352, "acc_norm_stderr": 0.03154779331378521, "mc1": 0.2423500611995104, "mc1_stderr": 0.015000674373570338, "mc2": 0.45153644837461854, "mc2_stderr": 0.015273187384634465 }, "harness|arc:challenge|25": { "acc": 0.20648464163822525, "acc_stderr": 0.011828865619002316, "acc_norm": 0.24488054607508533, "acc_norm_stderr": 0.012566273985131354 }, "harness|hellaswag|10": { "acc": 0.28380800637323245, "acc_stderr": 0.00449923387442751, "acc_norm": 0.31378211511651066, "acc_norm_stderr": 0.004630806412067355 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2518518518518518, "acc_stderr": 0.03749850709174021, "acc_norm": 0.2518518518518518, "acc_norm_stderr": 0.03749850709174021 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.21052631578947367, "acc_stderr": 0.03317672787533157, "acc_norm": 0.21052631578947367, "acc_norm_stderr": 0.03317672787533157 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.19, "acc_stderr": 0.03942772444036623, "acc_norm": 0.19, "acc_norm_stderr": 0.03942772444036623 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2490566037735849, "acc_stderr": 0.02661648298050171, "acc_norm": 0.2490566037735849, "acc_norm_stderr": 0.02661648298050171 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2222222222222222, "acc_stderr": 0.03476590104304134, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.03476590104304134 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.2, "acc_stderr": 0.04020151261036845, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.2, "acc_stderr": 0.04020151261036845, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.19653179190751446, "acc_stderr": 0.030299574664788147, "acc_norm": 0.19653179190751446, "acc_norm_stderr": 0.030299574664788147 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.27450980392156865, "acc_stderr": 0.044405219061793275, "acc_norm": 0.27450980392156865, "acc_norm_stderr": 0.044405219061793275 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3148936170212766, "acc_stderr": 0.030363582197238167, "acc_norm": 0.3148936170212766, "acc_norm_stderr": 0.030363582197238167 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2719298245614035, "acc_stderr": 0.041857744240220575, "acc_norm": 0.2719298245614035, "acc_norm_stderr": 0.041857744240220575 }, "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": 0.19047619047619047, "acc_stderr": 0.03512207412302052, "acc_norm": 0.19047619047619047, "acc_norm_stderr": 0.03512207412302052 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3161290322580645, "acc_stderr": 0.02645087448904277, "acc_norm": 0.3161290322580645, "acc_norm_stderr": 0.02645087448904277 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2413793103448276, "acc_stderr": 0.03010833071801162, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03010833071801162 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2606060606060606, "acc_stderr": 0.03427743175816524, "acc_norm": 0.2606060606060606, "acc_norm_stderr": 0.03427743175816524 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2222222222222222, "acc_stderr": 0.02962022787479049, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.02962022787479049 }, "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": 0.25384615384615383, "acc_stderr": 0.022066054378726257, "acc_norm": 0.25384615384615383, "acc_norm_stderr": 0.022066054378726257 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.29259259259259257, "acc_stderr": 0.02773896963217609, "acc_norm": 0.29259259259259257, "acc_norm_stderr": 0.02773896963217609 }, "harness|hendrycksTest-high



