open-llm-leaderboard-old/details_ToastyPigeon__SmolPlatypus-1.5B
收藏数据集概述
数据集简介
该数据集是在对模型 ToastyPigeon/SmolPlatypus-1.5B 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
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，每个运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。"train" 分片始终指向最新的结果。
额外配置
一个额外的配置 "results" 存储了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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_ToastyPigeon__SmolPlatypus-1.5B", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-21T20:25:46.815999 运行的最新结果：
python { "all": { "acc": 0.2538186191475448, "acc_stderr": 0.030621979660797015, "acc_norm": 0.25480932045056165, "acc_norm_stderr": 0.03138466683113775, "mc1": 0.2215422276621787, "mc1_stderr": 0.014537867601301145, "mc2": 0.36819500250290743, "mc2_stderr": 0.013885002767282889 }, "harness|arc:challenge|25": { "acc": 0.31399317406143346, "acc_stderr": 0.013562691224726295, "acc_norm": 0.3395904436860068, "acc_norm_stderr": 0.01383903976282016 }, "harness|hellaswag|10": { "acc": 0.45688109938259314, "acc_stderr": 0.004971192387202445, "acc_norm": 0.6004779924317865, "acc_norm_stderr": 0.004887991225950264 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.04408440022768081, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768081 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2518518518518518, "acc_stderr": 0.037498507091740206, "acc_norm": 0.2518518518518518, "acc_norm_stderr": 0.037498507091740206 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.19736842105263158, "acc_stderr": 0.03238981601699397, "acc_norm": 0.19736842105263158, "acc_norm_stderr": 0.03238981601699397 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.22, "acc_stderr": 0.041633319989322695, "acc_norm": 0.22, "acc_norm_stderr": 0.041633319989322695 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2679245283018868, "acc_stderr": 0.027257260322494845, "acc_norm": 0.2679245283018868, "acc_norm_stderr": 0.027257260322494845 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2222222222222222, "acc_stderr": 0.03476590104304134, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.03476590104304134 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.19653179190751446, "acc_stderr": 0.030299574664788147, "acc_norm": 0.19653179190751446, "acc_norm_stderr": 0.030299574664788147 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.19607843137254902, "acc_stderr": 0.03950581861179961, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.03950581861179961 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.32340425531914896, "acc_stderr": 0.030579442773610334, "acc_norm": 0.32340425531914896, "acc_norm_stderr": 0.030579442773610334 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.0414243971948936, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.0414243971948936 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2206896551724138, "acc_stderr": 0.03455930201924811, "acc_norm": 0.2206896551724138, "acc_norm_stderr": 0.03455930201924811 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2671957671957672, "acc_stderr": 0.02278967314577657, "acc_norm": 0.2671957671957672, "acc_norm_stderr": 0.02278967314577657 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.16666666666666666, "acc_stderr": 0.03333333333333338, "acc_norm": 0.16666666666666666, "acc_norm_stderr": 0.03333333333333338 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.25806451612903225, "acc_stderr": 0.02489246917246284, "acc_norm": 0.25806451612903225, "acc_norm_stderr": 0.02489246917246284 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.27586206896551724, "acc_stderr": 0.031447125816782405, "acc_norm": 0.27586206896551724, "acc_norm_stderr": 0.031447125816782405 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.23030303030303031, "acc_stderr": 0.032876667586034886, "acc_norm": 0.23030303030303031, "acc_norm_stderr": 0.032876667586034886 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.23232323232323232, "acc_stderr": 0.030088629490217483, "acc_norm": 0.23232323232323232, "acc_norm_stderr": 0.030088629490217483 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.20725388601036268, "acc_stderr": 0.02925282329180362, "acc_norm": 0.20725388601036268, "acc_norm_stderr": 0.02925282329180362 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2282051282051282, "acc_stderr": 0.021278393863586282, "acc_norm": 0.2282051282051282, "acc_norm_stderr": 0.021278393863586282 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26296296296296295, "acc_stderr": 0.0268420578738337
