open-llm-leaderboard-old/details_0-hero__Matter-0.1-Slim-7B
收藏数据集概述
数据集简介
该数据集是在对模型 0-hero/Matter-0.1-Slim-7B 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 运行次数：数据集由1次运行创建。每个运行在每个配置中作为一个特定的分割存在，分割名称使用运行的时间戳。
- 训练分割："train" 分割始终指向最新的结果。
- 结果配置：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。
最新结果
以下是 2024-03-13T22:23:44.167497 运行的最新结果：
python { "all": { "acc": 0.605490033884534, "acc_stderr": 0.03326571312658935, "acc_norm": 0.6102815752899539, "acc_norm_stderr": 0.0339481142869132, "mc1": 0.2778457772337821, "mc1_stderr": 0.015680929364024647, "mc2": 0.4178982620141241, "mc2_stderr": 0.014144240439100468 }, "harness|arc:challenge|25": { "acc": 0.5733788395904437, "acc_stderr": 0.014453185592920293, "acc_norm": 0.6049488054607508, "acc_norm_stderr": 0.014285898292938169 }, "harness|hellaswag|10": { "acc": 0.6183031268671579, "acc_stderr": 0.004848099661619697, "acc_norm": 0.8132842063333997, "acc_norm_stderr": 0.003888868099629071 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5851851851851851, "acc_stderr": 0.04256193767901408, "acc_norm": 0.5851851851851851, "acc_norm_stderr": 0.04256193767901408 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6644736842105263, "acc_stderr": 0.03842498559395269, "acc_norm": 0.6644736842105263, "acc_norm_stderr": 0.03842498559395269 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6943396226415094, "acc_stderr": 0.028353298073322663, "acc_norm": 0.6943396226415094, "acc_norm_stderr": 0.028353298073322663 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6944444444444444, "acc_stderr": 0.03852084696008534, "acc_norm": 0.6944444444444444, "acc_norm_stderr": 0.03852084696008534 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.630057803468208, "acc_stderr": 0.0368122963339432, "acc_norm": 0.630057803468208, "acc_norm_stderr": 0.0368122963339432 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.047840607041056527, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.047840607041056527 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.71, "acc_stderr": 0.04560480215720683, "acc_norm": 0.71, "acc_norm_stderr": 0.04560480215720683 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5234042553191489, "acc_stderr": 0.03265019475033582, "acc_norm": 0.5234042553191489, "acc_norm_stderr": 0.03265019475033582 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.47368421052631576, "acc_stderr": 0.04697085136647863, "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.04697085136647863 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5862068965517241, "acc_stderr": 0.04104269211806232, "acc_norm": 0.5862068965517241, "acc_norm_stderr": 0.04104269211806232 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3783068783068783, "acc_stderr": 0.024976954053155254, "acc_norm": 0.3783068783068783, "acc_norm_stderr": 0.024976954053155254 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3888888888888889, "acc_stderr": 0.04360314860077459, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.04360314860077459 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.667741935483871, "acc_stderr": 0.026795560848122794, "acc_norm": 0.667741935483871, "acc_norm_stderr": 0.026795560848122794 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5073891625615764, "acc_stderr": 0.035176035403610105, "acc_norm": 0.5073891625615764, "acc_norm_stderr": 0.035176035403610105 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7333333333333333, "acc_stderr": 0.03453131801885417, "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.03453131801885417 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.797979797979798, "acc_stderr": 0.028606204289229862, "acc_norm": 0.797979797979798, "acc_norm_stderr": 0.028606204289229862 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8186528497409327, "acc_stderr": 0.02780703236068609, "acc_norm": 0.8186528497409327, "acc_norm_stderr": 0.02780703236068609 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6102564102564103, "acc_stderr": 0.024726967886647074, "acc_norm": 0.6102564102564103, "acc_norm_stderr": 0.024726967886647074 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.028742040903948496, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.028742040903948496 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.605
