open-llm-leaderboard/details_EleutherAI__pythia-410m

该数据集是在评估模型EleutherAI/pythia-410m时自动创建的，主要用于在Open LLM Leaderboard上进行评估。数据集包含64个配置，每个配置对应一个评估任务。数据集由1次运行生成，每次运行的结果可以在每个配置的特定分割中找到，分割名称使用运行的时间戳命名。train分割始终指向最新的结果。此外，还有一个名为results的配置，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

数据集名称

Evaluation run of EleutherAI/pythia-410m

数据集描述

该数据集是在评估模型 EleutherAI/pythia-410m 在 Open LLM Leaderboard 上的运行过程中自动创建的。

数据集组成

• 该数据集包含 64 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，用于计算并在 Open LLM Leaderboard 上显示聚合指标。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_EleutherAI__pythia-410m_public", "harness_winogrande_5", split="train")

最新结果

以下是 2023-11-13T14:11:57.049362 运行的最新结果：

python { "all": { "acc": 0.27276461407760977, "acc_stderr": 0.03137987193481735, "acc_norm": 0.27458252512347847, "acc_norm_stderr": 0.032179450217890426, "mc1": 0.23745410036719705, "mc1_stderr": 0.01489627744104184, "mc2": 0.4121958367286861, "mc2_stderr": 0.014564451157949564, "em": 0.0018875838926174498, "em_stderr": 0.00044451099905590827, "f1": 0.044600461409396115, "f1_stderr": 0.0012188499729627125 }, "harness|arc:challenge|25": { "acc": 0.23122866894197952, "acc_stderr": 0.012320858834772283, "acc_norm": 0.2619453924914676, "acc_norm_stderr": 0.012849054826858115 }, "harness|hellaswag|10": { "acc": 0.33947420832503483, "acc_stderr": 0.004725630911520322, "acc_norm": 0.4084843656642103, "acc_norm_stderr": 0.00490548949400508 }, "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": 0.2814814814814815, "acc_stderr": 0.03885004245800255, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.03885004245800255 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.21710526315789475, "acc_stderr": 0.03355045304882924, "acc_norm": 0.21710526315789475, "acc_norm_stderr": 0.03355045304882924 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "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": 0.2777777777777778, "acc_stderr": 0.03745554791462457, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.03745554791462457 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.047609522856952365, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952365 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.20809248554913296, "acc_stderr": 0.03095289021774988, "acc_norm": 0.20809248554913296, "acc_norm_stderr": 0.03095289021774988 }, "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": 0.2, "acc_stderr": 0.04020151261036843, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036843 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.28936170212765955, "acc_stderr": 0.029644006577009618, "acc_norm": 0.28936170212765955, "acc_norm_stderr": 0.029644006577009618 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.22807017543859648, "acc_stderr": 0.03947152782669415, "acc_norm": 0.22807017543859648, "acc_norm_stderr": 0.03947152782669415 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.22758620689655173, "acc_stderr": 0.03493950380131183, "acc_norm": 0.22758620689655173, "acc_norm_stderr": 0.03493950380131183 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.23809523809523808, "acc_stderr": 0.021935878081184756, "acc_norm": 0.23809523809523808, "acc_norm_stderr": 0.021935878081184756 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.29365079365079366, "acc_stderr": 0.04073524322147125, "acc_norm": 0.29365079365079366, "acc_norm_stderr": 0.04073524322147125 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.17, "acc_stderr": 0.03775251680686371, "acc_norm": 0.17, "acc_norm_stderr": 0.03775251680686371 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.29354838709677417, "acc_stderr": 0.025906087021319288, "acc_norm": 0.29354838709677417, "acc_norm_stderr": 0.025906087021319288 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.26108374384236455, "acc_stderr": 0.030903796952114475, "acc_norm": 0.26108374384236455, "acc_norm_stderr": 0.030903796952114475 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.23636363636363636, "acc_stderr": 0.033175059300091805, "acc_norm": 0.23636363636363636, "acc_norm_stderr": 0.033175059300091805 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.30303030303030304, "acc_stderr": 0.032742879140268674, "acc_norm": 0.30303030303030304, "acc_norm_stderr": 0.032742879140268674 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.23316062176165803, "acc_stderr": 0.030516111371476008, "acc_norm": 0.23316062176165803, "acc_norm_stderr": 0.030516111371476008 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.358974358974359, "acc_stderr": 0.024321738484602364, "acc