open-llm-leaderboard-old/details_chargoddard__SmolLlamix-8x101M
收藏数据集概述
数据集简介
该数据集是在评估模型 chargoddard/SmolLlamix-8x101M 在 Open LLM Leaderboard 上的运行过程中自动创建的。
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。数据集是从 1 次运行中创建的，每次运行可以在每个配置中找到一个特定的拆分，拆分名称使用运行的时间戳。"train" 拆分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_chargoddard__SmolLlamix-8x101M", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-04T12:29:56.794531 运行的最新结果：
python { "all": { "acc": 0.24665141008843472, "acc_stderr": 0.030422170490043785, "acc_norm": 0.24716769398389823, "acc_norm_stderr": 0.031197299482121136, "mc1": 0.26193390452876375, "mc1_stderr": 0.015392118805015021, "mc2": 0.4608972262894305, "mc2_stderr": 0.015343271963572871 }, "harness|arc:challenge|25": { "acc": 0.17918088737201365, "acc_stderr": 0.011207045216615667, "acc_norm": 0.22696245733788395, "acc_norm_stderr": 0.012240491536132866 }, "harness|hellaswag|10": { "acc": 0.2765385381398128, "acc_stderr": 0.0044637210713190986, "acc_norm": 0.28500298745269864, "acc_norm_stderr": 0.004504932999736393 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.26666666666666666, "acc_stderr": 0.03820169914517904, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.03820169914517904 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.18421052631578946, "acc_stderr": 0.0315469804508223, "acc_norm": 0.18421052631578946, "acc_norm_stderr": 0.0315469804508223 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.22, "acc_stderr": 0.04163331998932268, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932268 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.22264150943396227, "acc_stderr": 0.0256042334708991, "acc_norm": 0.22264150943396227, "acc_norm_stderr": 0.0256042334708991 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.22916666666666666, "acc_stderr": 0.035146974678623884, "acc_norm": 0.22916666666666666, "acc_norm_stderr": 0.035146974678623884 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.15, "acc_stderr": 0.035887028128263714, "acc_norm": 0.15, "acc_norm_stderr": 0.035887028128263714 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.19653179190751446, "acc_stderr": 0.03029957466478814, "acc_norm": 0.19653179190751446, "acc_norm_stderr": 0.03029957466478814 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237654, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.27, "acc_stderr": 0.04461960433384741, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.22127659574468084, "acc_stderr": 0.027136349602424063, "acc_norm": 0.22127659574468084, "acc_norm_stderr": 0.027136349602424063 }, "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": 0.20689655172413793, "acc_stderr": 0.03375672449560553, "acc_norm": 0.20689655172413793, "acc_norm_stderr": 0.03375672449560553 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.24338624338624337, "acc_stderr": 0.022101128787415433, "acc_norm": 0.24338624338624337, "acc_norm_stderr": 0.022101128787415433 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.1746031746031746, "acc_stderr": 0.03395490020856113, "acc_norm": 0.1746031746031746, "acc_norm_stderr": 0.03395490020856113 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.31290322580645163, "acc_stderr": 0.02637756702864586, "acc_norm": 0.31290322580645163, "acc_norm_stderr": 0.02637756702864586 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.30049261083743845, "acc_stderr": 0.03225799476233483, "acc_norm": 0.30049261083743845, "acc_norm_stderr": 0.03225799476233483 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2, "acc_stderr": 0.031234752377721175, "acc_norm": 0.2, "acc_norm_stderr": 0.031234752377721175 }, "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": 0.34196891191709844, "acc_stderr": 0.03423465100104281, "acc_norm": 0.34196891191709844, "acc_norm_stderr": 0.03423465100104281 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2641025641025641, "acc_stderr": 0.022352193737453285, "acc_norm": 0.2641025641025641, "acc_norm_stderr": 0.022352193737453285 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2777777777777778, "acc_stderr": 0.027309140588230182, "acc_norm": 0.2777777777
