open-llm-leaderboard-old/details_AtAndDev__Ogno-Monarch-Neurotic-9B-Passthrough
收藏数据集概述
该数据集是在模型 AtAndDev/Ogno-Monarch-Neurotic-9B-Passthrough 的评估运行期间自动创建的，用于 Open LLM Leaderboard。
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。
- 数据集由 1 次运行创建，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。
- 额外的 "results" 配置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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_AtAndDev__Ogno-Monarch-Neurotic-9B-Passthrough", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-01T17:09:32.814517 运行的最新结果：
python { "all": { "acc": 0.6122781802684721, "acc_stderr": 0.032268454851190724, "acc_norm": 0.625230553768112, "acc_norm_stderr": 0.03315794745802012, "mc1": 0.2582619339045288, "mc1_stderr": 0.015321821688476185, "mc2": 0.5102578228172799, "mc2_stderr": 0.01648564659078862 }, "harness|arc:challenge|25": { "acc": 0.3924914675767918, "acc_stderr": 0.014269634635670717, "acc_norm": 0.46245733788395904, "acc_norm_stderr": 0.014570144495075583 }, "harness|hellaswag|10": { "acc": 0.3632742481577375, "acc_stderr": 0.004799599840397383, "acc_norm": 0.5606452897829117, "acc_norm_stderr": 0.004952942072999274 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.04408440022768079, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6148148148148148, "acc_stderr": 0.04203921040156279, "acc_norm": 0.6148148148148148, "acc_norm_stderr": 0.04203921040156279 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6973684210526315, "acc_stderr": 0.0373852067611967, "acc_norm": 0.6973684210526315, "acc_norm_stderr": 0.0373852067611967 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.720754716981132, "acc_stderr": 0.027611163402399715, "acc_norm": 0.720754716981132, "acc_norm_stderr": 0.027611163402399715 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7430555555555556, "acc_stderr": 0.03653946969442099, "acc_norm": 0.7430555555555556, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6416184971098265, "acc_stderr": 0.036563436533531585, "acc_norm": 0.6416184971098265, "acc_norm_stderr": 0.036563436533531585 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4411764705882353, "acc_stderr": 0.04940635630605659, "acc_norm": 0.4411764705882353, "acc_norm_stderr": 0.04940635630605659 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.73, "acc_stderr": 0.044619604333847394, "acc_norm": 0.73, "acc_norm_stderr": 0.044619604333847394 }, "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": 0.4473684210526316, "acc_stderr": 0.046774730044911984, "acc_norm": 0.4473684210526316, "acc_norm_stderr": 0.046774730044911984 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5103448275862069, "acc_stderr": 0.04165774775728762, "acc_norm": 0.5103448275862069, "acc_norm_stderr": 0.04165774775728762 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.373015873015873, "acc_stderr": 0.02490699045899257, "acc_norm": 0.373015873015873, "acc_norm_stderr": 0.02490699045899257 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3968253968253968, "acc_stderr": 0.043758884927270605, "acc_norm": 0.3968253968253968, "acc_norm_stderr": 0.043758884927270605 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7516129032258064, "acc_stderr": 0.024580028921481003, "acc_norm": 0.7516129032258064, "acc_norm_stderr": 0.024580028921481003 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.49261083743842365, "acc_stderr": 0.035176035403610084, "acc_norm": 0.49261083743842365, "acc_norm_stderr": 0.035176035403610084 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.67, "acc_stderr": 0.04725815626252607, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252607 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7696969696969697, "acc_stderr": 0.03287666758603491, "acc_norm": 0.7696969696969697, "acc_norm_stderr": 0.03287666758603491 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7676767676767676, "acc_stderr": 0.030088629490217483, "acc_norm": 0.7676767676767676, "acc_norm_stderr": 0.030088629490217483 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8911917098445595, "acc_stderr": 0.022473253332768766, "acc_norm": 0.8911917098445595, "acc_norm_stderr": 0.022473253332768766 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6435897435897436, "acc_stderr": 0.024283140529467305, "acc_norm": 0.6435897435897436, "acc_norm_stderr": 0.024283140529467305 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.31851851851851853, "acc_stderr": 0.02840653309060846, "acc_norm": 0.31851851
