open-llm-leaderboard-old/details_alignment-handbook__zephyr-7b-dpo-qlora
收藏数据集概述
数据集简介
该数据集是在评估模型 alignment-handbook/zephyr-7b-dpo-qlora 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，每个运行的详细信息可以在每个配置中找到，并以运行的时间戳命名的特定分片形式存储。"train" 分片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，用于计算并在 Open LLM Leaderboard 上显示聚合指标。
数据加载示例
以下是一个加载运行详细信息的示例代码： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_alignment-handbook__zephyr-7b-dpo-qlora", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-26T21:27:47.387655 运行 的最新结果： python { "all": { "acc": 0.6369766338808557, "acc_stderr": 0.03238152491968989, "acc_norm": 0.641831921094304, "acc_norm_stderr": 0.033030780304730514, "mc1": 0.31701346389228885, "mc1_stderr": 0.016289203374403385, "mc2": 0.4714491532888518, "mc2_stderr": 0.014683410665396914 }, "harness|arc:challenge|25": { "acc": 0.6083617747440273, "acc_stderr": 0.014264122124938217, "acc_norm": 0.636518771331058, "acc_norm_stderr": 0.014056207319068285 }, "harness|hellaswag|10": { "acc": 0.658334993029277, "acc_stderr": 0.004732986187325878, "acc_norm": 0.8535152360087632, "acc_norm_stderr": 0.0035286889976580533 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542129, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542129 }, "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": 0.6578947368421053, "acc_stderr": 0.03860731599316091, "acc_norm": 0.6578947368421053, "acc_norm_stderr": 0.03860731599316091 }, "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": 0.7056603773584905, "acc_stderr": 0.02804918631569525, "acc_norm": 0.7056603773584905, "acc_norm_stderr": 0.02804918631569525 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7291666666666666, "acc_stderr": 0.03716177437566017, "acc_norm": 0.7291666666666666, "acc_norm_stderr": 0.03716177437566017 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6647398843930635, "acc_stderr": 0.03599586301247077, "acc_norm": 0.6647398843930635, "acc_norm_stderr": 0.03599586301247077 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4019607843137255, "acc_stderr": 0.048786087144669955, "acc_norm": 0.4019607843137255, "acc_norm_stderr": 0.048786087144669955 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932263, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932263 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5446808510638298, "acc_stderr": 0.03255525359340355, "acc_norm": 0.5446808510638298, "acc_norm_stderr": 0.03255525359340355 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.49122807017543857, "acc_stderr": 0.04702880432049615, "acc_norm": 0.49122807017543857, "acc_norm_stderr": 0.04702880432049615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5862068965517241, "acc_stderr": 0.04104269211806232, "acc_norm": 0.5862068965517241, "acc_norm_stderr": 0.04104269211806232 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.40476190476190477, "acc_stderr": 0.0252798503974049, "acc_norm": 0.40476190476190477, "acc_norm_stderr": 0.0252798503974049 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42857142857142855, "acc_stderr": 0.04426266681379909, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.04426266681379909 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7548387096774194, "acc_stderr": 0.024472243840895525, "acc_norm": 0.7548387096774194, "acc_norm_stderr": 0.024472243840895525 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5221674876847291, "acc_stderr": 0.03514528562175008, "acc_norm": 0.5221674876847291, "acc_norm_stderr": 0.03514528562175008 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.65, "acc_stderr": 0.04793724854411019, "acc_norm": 0.65, "acc_norm_stderr": 0.04793724854411019 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7515151515151515, "acc_stderr": 0.03374402644139403, "acc_norm": 0.7515151515151515, "acc_norm_stderr": 0.03374402644139403 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7676767676767676, "acc_stderr": 0.030088629490217487, "acc_norm": 0.7676767676767676, "acc_norm_stderr": 0.030088629490217487 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8756476683937824, "acc_stderr": 0.023814477086593542, "acc_norm": 0.8756476683937824, "acc_norm_stderr": 0.023814477086593542 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6461538461538462, "acc_stderr": 0.024243783994062153, "acc_norm": 0.6461538461538462, "acc_norm_stderr": 0.024243783994062153 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.36666666666666664, "acc_stderr": 0.029381620726465076, "acc_norm": 0.36666666666666664, "acc_
