open-llm-leaderboard-old/details_Felladrin__Llama-160M-Chat-v1

该数据集是在Open LLM Leaderboard上对模型Felladrin/Llama-160M-Chat-v1进行评估时自动创建的。它包含63个配置，每个配置对应一个被评估的任务。数据集由2次运行生成，每次运行在每个配置中表示为特定的分割。train分割始终指向最新的结果。一个额外的配置results存储了所有运行的聚合结果，这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。可以使用`datasets`库中的`load_dataset`函数加载该数据集。

原始信息汇总

数据集概述

该数据集是在对模型 Felladrin/Llama-160M-Chat-v1 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。
• 数据集从 2 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。

最新结果

以下是 2024-03-03T13:55:54.641624 运行的最新结果：

python { "all": { "acc": 0.2613731865232815, "acc_stderr": 0.030843779992125668, "acc_norm": 0.2627506225927332, "acc_norm_stderr": 0.0316633522449165, "mc1": 0.24357405140758873, "mc1_stderr": 0.015026354824910782, "mc2": 0.4416088801457481, "mc2_stderr": 0.01524734599791119 }, "harness|arc:challenge|25": { "acc": 0.2167235494880546, "acc_stderr": 0.01204015671348119, "acc_norm": 0.24744027303754265, "acc_norm_stderr": 0.012610352663292673 }, "harness|hellaswag|10": { "acc": 0.3123879705238, "acc_stderr": 0.004625198756710239, "acc_norm": 0.35321649073889666, "acc_norm_stderr": 0.004769924131304643 }, "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": 0.2518518518518518, "acc_stderr": 0.03749850709174023, "acc_norm": 0.2518518518518518, "acc_norm_stderr": 0.03749850709174023 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.031103182383123398, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.031103182383123398 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.19, "acc_stderr": 0.03942772444036624, "acc_norm": 0.19, "acc_norm_stderr": 0.03942772444036624 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2339622641509434, "acc_stderr": 0.02605529690115292, "acc_norm": 0.2339622641509434, "acc_norm_stderr": 0.02605529690115292 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2847222222222222, "acc_stderr": 0.037738099906869355, "acc_norm": 0.2847222222222222, "acc_norm_stderr": 0.037738099906869355 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.17, "acc_stderr": 0.03775251680686371, "acc_norm": 0.17, "acc_norm_stderr": 0.03775251680686371 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.20809248554913296, "acc_stderr": 0.030952890217749898, "acc_norm": 0.20809248554913296, "acc_norm_stderr": 0.030952890217749898 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2549019607843137, "acc_stderr": 0.04336432707993178, "acc_norm": 0.2549019607843137, "acc_norm_stderr": 0.04336432707993178 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2425531914893617, "acc_stderr": 0.028020226271200217, "acc_norm": 0.2425531914893617, "acc_norm_stderr": 0.028020226271200217 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2543859649122807, "acc_stderr": 0.040969851398436695, "acc_norm": 0.2543859649122807, "acc_norm_stderr": 0.040969851398436695 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2206896551724138, "acc_stderr": 0.0345593020192481, "acc_norm": 0.2206896551724138, "acc_norm_stderr": 0.0345593020192481 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2619047619047619, "acc_stderr": 0.02264421261552521, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.02264421261552521 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.15079365079365079, "acc_stderr": 0.03200686497287392, "acc_norm": 0.15079365079365079, "acc_norm_stderr": 0.03200686497287392 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.17, "acc_stderr": 0.0377525168068637, "acc_norm": 0.17, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3096774193548387, "acc_stderr": 0.026302774983517414, "acc_norm": 0.3096774193548387, "acc_norm_stderr": 0.026302774983517414 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2955665024630542, "acc_stderr": 0.032104944337514575, "acc_norm": 0.2955665024630542, "acc_norm_stderr": 0.032104944337514575 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.18787878787878787, "acc_stderr": 0.03050193405942914, "acc_norm": 0.18787878787878787, "acc_norm_stderr": 0.03050193405942914 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.26262626262626265, "acc_stderr": 0.031353050095330855, "acc_norm": 0.26262626262626265, "acc_norm_stderr": 0.031353050095330855 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.3160621761658031, "acc_stderr": 0.03355397369686173, "acc_norm": 0.3160621761658031, "acc_norm_stderr": 0.03355397369686173 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3435897435897436, "acc_stderr": 0.024078696580635477, "acc_norm": 0.3435897435897436, "acc_norm_stderr": 0.024078696580635477 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.29259259259259257, "acc_stderr": 0.027738969632176088, "acc_norm": 0.29259259259259257, "acc_norm_stderr": 0.027738969632176088 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.