open-llm-leaderboard-old/details_Josephgflowers__Tinyllama-616M-Cinder-DPO-With-GGUF

该数据集是在模型Josephgflowers/Tinyllama-616M-Cinder-DPO-With-GGUF的评估运行期间自动创建的，用于在Open LLM Leaderboard上进行评估。数据集由63个配置组成，每个配置对应一个评估任务。数据集从1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分割始终指向最新结果。此外，results配置存储了所有运行的聚合结果，并用于计算和显示Open LLM Leaderboard上的聚合指标。

原始信息汇总

数据集概述

数据集简介

该数据集是在评估模型Josephgflowers/Tinyllama-616M-Cinder-DPO-With-GGUF在Open LLM Leaderboard上的运行过程中自动创建的。

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，用于计算和显示在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_Josephgflowers__Tinyllama-616M-Cinder-DPO-With-GGUF", "harness_winogrande_5", split="train")

最新结果

以下是2024-04-03T03:56:14.436511运行的最新结果：

python { "all": { "acc": 0.24993534212404958, "acc_stderr": 0.030646320343789935, "acc_norm": 0.2504292600079835, "acc_norm_stderr": 0.03143711945216173, "mc1": 0.23990208078335373, "mc1_stderr": 0.014948812679062133, "mc2": 0.4357570964400005, "mc2_stderr": 0.015481098716394607 }, "harness|arc:challenge|25": { "acc": 0.24488054607508533, "acc_stderr": 0.012566273985131356, "acc_norm": 0.2627986348122867, "acc_norm_stderr": 0.012862523175351333 }, "harness|hellaswag|10": { "acc": 0.3163712407886875, "acc_stderr": 0.004641092001425288, "acc_norm": 0.3635729934276041, "acc_norm_stderr": 0.0048004463976533416 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.2, "acc_stderr": 0.04020151261036845, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.28888888888888886, "acc_stderr": 0.03915450630414251, "acc_norm": 0.28888888888888886, "acc_norm_stderr": 0.03915450630414251 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.2236842105263158, "acc_stderr": 0.033911609343436025, "acc_norm": 0.2236842105263158, "acc_norm_stderr": 0.033911609343436025 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2188679245283019, "acc_stderr": 0.02544786382510861, "acc_norm": 0.2188679245283019, "acc_norm_stderr": 0.02544786382510861 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.22916666666666666, "acc_stderr": 0.03514697467862388, "acc_norm": 0.22916666666666666, "acc_norm_stderr": 0.03514697467862388 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.18, "acc_stderr": 0.03861229196653694, "acc_norm": 0.18, "acc_norm_stderr": 0.03861229196653694 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.26, "acc_stderr": 0.04408440022768078, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2543352601156069, "acc_stderr": 0.0332055644308557, "acc_norm": 0.2543352601156069, "acc_norm_stderr": 0.0332055644308557 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3137254901960784, "acc_stderr": 0.04617034827006718, "acc_norm": 0.3137254901960784, "acc_norm_stderr": 0.04617034827006718 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.20851063829787234, "acc_stderr": 0.02655698211783874, "acc_norm": 0.20851063829787234, "acc_norm_stderr": 0.02655698211783874 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.04049339297748141, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.04049339297748141 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2827586206896552, "acc_stderr": 0.03752833958003336, "acc_norm": 0.2827586206896552, "acc_norm_stderr": 0.03752833958003336 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.24338624338624337, "acc_stderr": 0.02210112878741543, "acc_norm": 0.24338624338624337, "acc_norm_stderr": 0.02210112878741543 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.1984126984126984, "acc_stderr": 0.03567016675276863, "acc_norm": 0.1984126984126984, "acc_norm_stderr": 0.03567016675276863 }, "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": 0.33548387096774196, "acc_stderr": 0.026860206444724356, "acc_norm": 0.33548387096774196, "acc_norm_stderr": 0.026860206444724356 }, "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": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.23030303030303031, "acc_stderr": 0.03287666758603489, "acc_norm": 0.23030303030303031, "acc_norm_stderr": 0.03287666758603489 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.25757575757575757, "acc_stderr": 0.031156269519646826, "acc_norm": 0.25757575757575757, "acc_norm_stderr": 0.031156269519646826 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.24870466321243523, "acc_stderr": 0.03119584087770029, "acc_norm": 0.24870466321243523, "acc_norm_stderr": 0.03119584087770029 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2076923076923077, "acc_stderr": 0.020567539567246808, "acc_norm": 0.2076923076923077, "acc_norm_stderr": 0.020567539567246808 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3037037037037037, "acc_stderr": 0.0280379299