open-llm-leaderboard-old/details_dillfrescott__amadeus-v0.1

该数据集是在模型dillfrescott/amadeus-v0.1的评估运行期间自动创建的，用于在Open LLM Leaderboard上进行评估。数据集由63个配置组成，每个配置对应一个评估任务。数据集从1次运行中创建，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命名。"train"分割始终指向最新的结果。此外，"results"配置存储了所有运行的聚合结果，并用于计算和显示Open LLM Leaderboard上的聚合指标。

原始信息汇总

数据集概述

该数据集是在对模型dillfrescott/amadeus-v0.1进行评估运行期间自动创建的，用于Open LLM Leaderboard。

数据集组成

• 数据集由63个配置组成，每个配置对应一个评估任务。
• 数据集从1次运行中创建，每次运行的详细结果可以在每个配置中找到，以运行的时间戳命名的特定分割形式存储。
• "train"分割始终指向最新的结果。
• 一个额外的配置"results"存储所有运行的聚合结果，用于计算和显示在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_dillfrescott__amadeus-v0.1", "harness_winogrande_5", split="train")

最新结果

以下是2024-01-06T01:28:19.231223运行的最新结果： python { "all": { "acc": 0.6503116864878898, "acc_stderr": 0.03211845742165151, "acc_norm": 0.6514191578913137, "acc_norm_stderr": 0.032765902396781794, "mc1": 0.46266829865361075, "mc1_stderr": 0.017454645150970588, "mc2": 0.6382334765973684, "mc2_stderr": 0.01550846970253108 }, "harness|arc:challenge|25": { "acc": 0.6578498293515358, "acc_stderr": 0.013864152159177278, "acc_norm": 0.689419795221843, "acc_norm_stderr": 0.013522292098053069 }, "harness|hellaswag|10": { "acc": 0.6957777335192192, "acc_stderr": 0.004591369853276529, "acc_norm": 0.8698466440948018, "acc_norm_stderr": 0.0033578442491239546 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6296296296296297, "acc_stderr": 0.041716541613545426, "acc_norm": 0.6296296296296297, "acc_norm_stderr": 0.041716541613545426 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6907894736842105, "acc_stderr": 0.037610708698674805, "acc_norm": 0.6907894736842105, "acc_norm_stderr": 0.037610708698674805 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.59, "acc_stderr": 0.049431107042371025, "acc_norm": 0.59, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7018867924528301, "acc_stderr": 0.02815283794249386, "acc_norm": 0.7018867924528301, "acc_norm_stderr": 0.02815283794249386 }, "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": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.047609522856952344, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952344 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6705202312138728, "acc_stderr": 0.03583901754736412, "acc_norm": 0.6705202312138728, "acc_norm_stderr": 0.03583901754736412 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.43137254901960786, "acc_stderr": 0.04928099597287534, "acc_norm": 0.43137254901960786, "acc_norm_stderr": 0.04928099597287534 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.79, "acc_stderr": 0.04093601807403326, "acc_norm": 0.79, "acc_norm_stderr": 0.04093601807403326 }, "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": 0.5517241379310345, "acc_stderr": 0.04144311810878151, "acc_norm": 0.5517241379310345, "acc_norm_stderr": 0.04144311810878151 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4021164021164021, "acc_stderr": 0.025253032554997695, "acc_norm": 0.4021164021164021, "acc_norm_stderr": 0.025253032554997695 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.48412698412698413, "acc_stderr": 0.04469881854072606, "acc_norm": 0.48412698412698413, "acc_norm_stderr": 0.04469881854072606 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8, "acc_stderr": 0.022755204959542943, "acc_norm": 0.8, "acc_norm_stderr": 0.022755204959542943 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5123152709359606, "acc_stderr": 0.035169204442208966, "acc_norm": 0.5123152709359606, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.72, "acc_stderr": 0.04512608598542127, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7575757575757576, "acc_stderr": 0.03346409881055953, "acc_norm": 0.7575757575757576, "acc_norm_stderr": 0.03346409881055953 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7828282828282829, "acc_stderr": 0.02937661648494563, "acc_norm": 0.7828282828282829, "acc_norm_stderr": 0.02937661648494563 }, "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": 0.6743589743589744, "acc_stderr": 0.02375966576741229, "acc_norm": 0.6743589743589744, "acc_norm_stderr": 0.02375966576741229 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.02874204090394848, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.02874204090394848 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.71008403