open-llm-leaderboard-old/details_eren23__slerp-test-turdus-beagle
收藏数据集概述
数据集简介
该数据集是在评估模型 eren23/slerp-test-turdus-beagle 在 Open LLM Leaderboard 上的运行过程中自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
数据集由 1 次运行创建，每个运行可以在每个配置中找到特定的拆分，拆分名称使用运行的时间戳。"train" 拆分始终指向最新的结果。
结果配置
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。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_eren23__slerp-test-turdus-beagle", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-16T22:46:06.877584 运行的最新结果：
python { "all": { "acc": 0.6526065017579354, "acc_stderr": 0.03210475190383045, "acc_norm": 0.6518375747763883, "acc_norm_stderr": 0.03277592690440463, "mc1": 0.576499388004896, "mc1_stderr": 0.01729742144853475, "mc2": 0.6969379766281721, "mc2_stderr": 0.015098794143768114 }, "harness|arc:challenge|25": { "acc": 0.712457337883959, "acc_stderr": 0.013226719056266129, "acc_norm": 0.735494880546075, "acc_norm_stderr": 0.012889272949313368 }, "harness|hellaswag|10": { "acc": 0.7225652260505875, "acc_stderr": 0.004468178273665674, "acc_norm": 0.8884684325831508, "acc_norm_stderr": 0.0031414591751392704 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6370370370370371, "acc_stderr": 0.04153948404742398, "acc_norm": 0.6370370370370371, "acc_norm_stderr": 0.04153948404742398 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7171052631578947, "acc_stderr": 0.03665349695640767, "acc_norm": 0.7171052631578947, "acc_norm_stderr": 0.03665349695640767 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.65, "acc_stderr": 0.0479372485441102, "acc_norm": 0.65, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7132075471698113, "acc_stderr": 0.02783491252754407, "acc_norm": 0.7132075471698113, "acc_norm_stderr": 0.02783491252754407 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7638888888888888, "acc_stderr": 0.03551446610810826, "acc_norm": 0.7638888888888888, "acc_norm_stderr": 0.03551446610810826 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6589595375722543, "acc_stderr": 0.036146654241808254, "acc_norm": 0.6589595375722543, "acc_norm_stderr": 0.036146654241808254 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4411764705882353, "acc_stderr": 0.049406356306056595, "acc_norm": 0.4411764705882353, "acc_norm_stderr": 0.049406356306056595 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.04292346959909283, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5617021276595745, "acc_stderr": 0.03243618636108102, "acc_norm": 0.5617021276595745, "acc_norm_stderr": 0.03243618636108102 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4649122807017544, "acc_stderr": 0.046920083813689104, "acc_norm": 0.4649122807017544, "acc_norm_stderr": 0.046920083813689104 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5724137931034483, "acc_stderr": 0.04122737111370333, "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.04122737111370333 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4074074074074074, "acc_stderr": 0.02530590624159063, "acc_norm": 0.4074074074074074, "acc_norm_stderr": 0.02530590624159063 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4603174603174603, "acc_stderr": 0.04458029125470973, "acc_norm": 0.4603174603174603, "acc_norm_stderr": 0.04458029125470973 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7870967741935484, "acc_stderr": 0.023287665127268545, "acc_norm": 0.7870967741935484, "acc_norm_stderr": 0.023287665127268545 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5024630541871922, "acc_stderr": 0.035179450386910616, "acc_norm": 0.5024630541871922, "acc_norm_stderr": 0.035179450386910616 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7696969696969697, "acc_stderr": 0.0328766675860349, "acc_norm": 0.7696969696969697, "acc_norm_stderr": 0.0328766675860349 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.797979797979798, "acc_stderr": 0.028606204289229872, "acc_norm": 0.797979797979798, "acc_norm_stderr": 0.028606204289229872 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9015544041450777, "acc_stderr": 0.02150024957603348, "acc_norm": 0.9015544041450777, "acc_norm_stderr": 0.02150024957603348 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6666666666666666, "acc_stderr": 0.023901157979402534, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.023901157979402534 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.028742040903948482, "acc_norm": 0.3333333333333333, "acc_norm_
