open-llm-leaderboard-old/details_leonarad__hope_for_7b_1.0v
收藏数据集概述
数据集摘要
该数据集是在对模型 leonarad/hope_for_7b_1.0v 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。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。
数据集结构
数据集包含多个配置，每个配置对应不同的评估任务。每个配置包含多个分割，包括特定运行的时间戳分割和 "latest" 分割。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_leonarad__hope_for_7b_1.0v", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的摘要： python { "all": { "acc": 0.49625763833263636, "acc_stderr": 0.03432748690410699, "acc_norm": 0.501465304135971, "acc_norm_stderr": 0.03510035831107398, "mc1": 0.2423500611995104, "mc1_stderr": 0.015000674373570342, "mc2": 0.38661424040991893, "mc2_stderr": 0.013834126560159537 }, "harness|arc:challenge|25": { "acc": 0.4718430034129693, "acc_stderr": 0.014588204105102205, "acc_norm": 0.5042662116040956, "acc_norm_stderr": 0.014610858923956952 }, "harness|hellaswag|10": { "acc": 0.5646285600477993, "acc_stderr": 0.0049479226926888355, "acc_norm": 0.764389563831906, "acc_norm_stderr": 0.004235124215120109 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "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": 0.4605263157894737, "acc_stderr": 0.04056242252249034, "acc_norm": 0.4605263157894737, "acc_norm_stderr": 0.04056242252249034 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.4867924528301887, "acc_stderr": 0.030762134874500482, "acc_norm": 0.4867924528301887, "acc_norm_stderr": 0.030762134874500482 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5208333333333334, "acc_stderr": 0.041775789507399935, "acc_norm": 0.5208333333333334, "acc_norm_stderr": 0.041775789507399935 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.43, "acc_stderr": 0.04975698519562428, "acc_norm": 0.43, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.36416184971098264, "acc_stderr": 0.036690724774169084, "acc_norm": 0.36416184971098264, "acc_norm_stderr": 0.036690724774169084 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.24509803921568626, "acc_stderr": 0.04280105837364395, "acc_norm": 0.24509803921568626, "acc_norm_stderr": 0.04280105837364395 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.67, "acc_stderr": 0.04725815626252609, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252609 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3829787234042553, "acc_stderr": 0.03177821250236922, "acc_norm": 0.3829787234042553, "acc_norm_stderr": 0.03177821250236922 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.34210526315789475, "acc_stderr": 0.04462917535336936, "acc_norm": 0.34210526315789475, "acc_norm_stderr": 0.04462917535336936 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4827586206896552, "acc_stderr": 0.04164188720169377, "acc_norm": 0.4827586206896552, "acc_norm_stderr": 0.04164188720169377 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3253968253968254, "acc_stderr": 0.024130158299762616, "acc_norm": 0.3253968253968254, "acc_norm_stderr": 0.024130158299762616 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.35714285714285715, "acc_stderr": 0.042857142857142816, "acc_norm": 0.35714285714285715, "acc_norm_stderr": 0.042857142857142816 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.26, "acc_stderr": 0.04408440022768078, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5483870967741935, "acc_stderr": 0.02831050034856839, "acc_norm": 0.5483870967741935, "acc_norm_stderr": 0.02831050034856839 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3399014778325123, "acc_stderr": 0.033327690684107895, "acc_norm": 0.3399014778325123, "acc_norm_stderr": 0.033327690684107895 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6545454545454545, "acc_stderr": 0.0371315806748191, "acc_norm": 0.6545454545454545, "acc_norm_stderr": 0.0371315806748191 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6363636363636364, "acc_stderr": 0.03427308652999934, "acc_norm": 0.6363636363636364, "acc_norm_stderr": 0.03427308652999934 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.689119170984456, "acc_stderr": 0.03340361906276586, "acc_norm": 0.689119170984456, "acc_norm_stderr": 0.03340361906276586 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4153846153846154, "acc_stderr": 0.024985354923102325, "acc_norm": 0.4153846153846154, "acc_norm_stderr": 0.024985354923102325 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2740740740740741, "acc_stderr": 0.027195934804085622, "acc_norm": 0.2740740740740741, "acc_norm_stderr": 0.027195934804085622 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.43697478991
