open-llm-leaderboard-old/details_decruz07__kellemar-DPO-Orca-Distilled-7B-SLERP
收藏数据集概述
数据集简介
该数据集是在评估模型 decruz07/kellemar-DPO-Orca-Distilled-7B-SLERP 在 Open LLM Leaderboard 上的自动创建的。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 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-Orca-Distilled-7B-SLERP", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-16T17:19:43.357839 运行的最新结果：
python { "all": { "acc": 0.6581904352779381, "acc_stderr": 0.03198559228658252, "acc_norm": 0.6579223801812178, "acc_norm_stderr": 0.03264927345286248, "mc1": 0.4944920440636475, "mc1_stderr": 0.01750243899045106, "mc2": 0.6497116450794354, "mc2_stderr": 0.015124463559805741 }, "harness|arc:challenge|25": { "acc": 0.6766211604095563, "acc_stderr": 0.013669421630012134, "acc_norm": 0.7047781569965871, "acc_norm_stderr": 0.013329750293382318 }, "harness|hellaswag|10": { "acc": 0.6964748058155746, "acc_stderr": 0.004588403419449666, "acc_norm": 0.8756223859788886, "acc_norm_stderr": 0.003293374019781595 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6888888888888889, "acc_stderr": 0.0399926287661772, "acc_norm": 0.6888888888888889, "acc_norm_stderr": 0.0399926287661772 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6973684210526315, "acc_stderr": 0.03738520676119669, "acc_norm": 0.6973684210526315, "acc_norm_stderr": 0.03738520676119669 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.66, "acc_stderr": 0.04760952285695238, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695238 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7169811320754716, "acc_stderr": 0.027724236492700914, "acc_norm": 0.7169811320754716, "acc_norm_stderr": 0.027724236492700914 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7777777777777778, "acc_stderr": 0.03476590104304134, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.03476590104304134 }, "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": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6820809248554913, "acc_stderr": 0.0355068398916558, "acc_norm": 0.6820809248554913, "acc_norm_stderr": 0.0355068398916558 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.45098039215686275, "acc_stderr": 0.049512182523962625, "acc_norm": 0.45098039215686275, "acc_norm_stderr": 0.049512182523962625 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.04292346959909284, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909284 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5957446808510638, "acc_stderr": 0.03208115750788684, "acc_norm": 0.5957446808510638, "acc_norm_stderr": 0.03208115750788684 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5, "acc_stderr": 0.047036043419179864, "acc_norm": 0.5, "acc_norm_stderr": 0.047036043419179864 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5724137931034483, "acc_stderr": 0.04122737111370332, "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.04122737111370332 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4312169312169312, "acc_stderr": 0.02550648169813821, "acc_norm": 0.4312169312169312, "acc_norm_stderr": 0.02550648169813821 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4365079365079365, "acc_stderr": 0.04435932892851466, "acc_norm": 0.4365079365079365, "acc_norm_stderr": 0.04435932892851466 }, "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": 0.7903225806451613, "acc_stderr": 0.023157879349083525, "acc_norm": 0.7903225806451613, "acc_norm_stderr": 0.023157879349083525 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4975369458128079, "acc_stderr": 0.03517945038691063, "acc_norm": 0.4975369458128079, "acc_norm_stderr": 0.03517945038691063 }, "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": 0.7636363636363637, "acc_stderr": 0.03317505930009181, "acc_norm": 0.7636363636363637, "acc_norm_stderr": 0.03317505930009181 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.797979797979798, "acc_stderr": 0.028606204289229865, "acc_norm": 0.797979797979798, "acc_norm_stderr": 0.028606204289229865 }, "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": 0.676923076923077, "acc_stderr": 0.02371088850197057, "acc_norm": 0.676923076923077, "acc_norm_stderr": 0.02371088850197057 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.362962962962963, "acc_stderr": 0.02931820364520686, "acc_norm": 0.362962962962963, "acc_norm_stderr": 0.0
