open-llm-leaderboard-old/details_decruz07__kellemar-DPO-7B-c
收藏数据集概述
该数据集是在评估模型 decruz07/kellemar-DPO-7B-c 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，用于计算和显示在 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_decruz07__kellemar-DPO-7B-c", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-11T11:35:01.176663 运行的最新结果：
python { "all": { "acc": 0.6384818948169925, "acc_stderr": 0.032244773650019175, "acc_norm": 0.6408980660124164, "acc_norm_stderr": 0.03288578301996733, "mc1": 0.3733170134638923, "mc1_stderr": 0.016932370557570634, "mc2": 0.5407842160887599, "mc2_stderr": 0.015285349287061248 }, "harness|arc:challenge|25": { "acc": 0.6168941979522184, "acc_stderr": 0.014206472661672876, "acc_norm": 0.6569965870307167, "acc_norm_stderr": 0.013872423223718164 }, "harness|hellaswag|10": { "acc": 0.6591316470822546, "acc_stderr": 0.00473032455662413, "acc_norm": 0.8498307110137423, "acc_norm_stderr": 0.0035650718701954478 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6074074074074074, "acc_stderr": 0.0421850621536888, "acc_norm": 0.6074074074074074, "acc_norm_stderr": 0.0421850621536888 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6973684210526315, "acc_stderr": 0.037385206761196686, "acc_norm": 0.6973684210526315, "acc_norm_stderr": 0.037385206761196686 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6943396226415094, "acc_stderr": 0.028353298073322666, "acc_norm": 0.6943396226415094, "acc_norm_stderr": 0.028353298073322666 }, "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": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "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": 0.6184971098265896, "acc_stderr": 0.03703851193099521, "acc_norm": 0.6184971098265896, "acc_norm_stderr": 0.03703851193099521 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.04784060704105653, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.04784060704105653 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.042295258468165065, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5702127659574469, "acc_stderr": 0.03236214467715564, "acc_norm": 0.5702127659574469, "acc_norm_stderr": 0.03236214467715564 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4824561403508772, "acc_stderr": 0.04700708033551038, "acc_norm": 0.4824561403508772, "acc_norm_stderr": 0.04700708033551038 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5310344827586206, "acc_stderr": 0.04158632762097828, "acc_norm": 0.5310344827586206, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42328042328042326, "acc_stderr": 0.02544636563440678, "acc_norm": 0.42328042328042326, "acc_norm_stderr": 0.02544636563440678 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.46825396825396826, "acc_stderr": 0.04463112720677172, "acc_norm": 0.46825396825396826, "acc_norm_stderr": 0.04463112720677172 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7870967741935484, "acc_stderr": 0.023287665127268552, "acc_norm": 0.7870967741935484, "acc_norm_stderr": 0.023287665127268552 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5172413793103449, "acc_stderr": 0.035158955511656986, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.035158955511656986 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7878787878787878, "acc_stderr": 0.03192271569548302, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.03192271569548302 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.797979797979798, "acc_stderr": 0.028606204289229862, "acc_norm": 0.797979797979798, "acc_norm_stderr": 0.028606204289229862 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8911917098445595, "acc_stderr": 0.02247325333276877, "acc_norm": 0.8911917098445595, "acc_norm_stderr": 0.02247325333276877 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.617948717948718, "acc_stderr": 0.024635549163908237, "acc_norm": 0.617948717948718, "acc_norm_stderr": 0.024635549163908237 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3111111111111111, "acc_stderr": 0.02822644674968352, "acc_norm": 0.3111111111111111, "acc_norm_stderr": 0.02822644674968352
