open-llm-leaderboard-old/details_Josephgflowers__TinyLlama-748M-Reason-With-Cinder-Test-2
收藏数据集概述
数据集简介
该数据集是在评估模型 Josephgflowers/TinyLlama-748M-Reason-With-Cinder-Test-2 在 Open LLM Leaderboard 上的运行过程中自动创建的。
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。数据集从 1 次运行中创建，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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Josephgflowers__TinyLlama-748M-Reason-With-Cinder-Test-2", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-16T18:21:24.569209 运行的最新结果：
python { "all": { "acc": 0.2521207309170715, "acc_stderr": 0.030556259826906736, "acc_norm": 0.2529609814071766, "acc_norm_stderr": 0.03131972311648323, "mc1": 0.2558139534883721, "mc1_stderr": 0.015274176219283352, "mc2": 0.42762316543412854, "mc2_stderr": 0.015330016474026912 }, "harness|arc:challenge|25": { "acc": 0.22781569965870307, "acc_stderr": 0.012256708602326912, "acc_norm": 0.24658703071672355, "acc_norm_stderr": 0.012595726268790134 }, "harness|hellaswag|10": { "acc": 0.304919338777136, "acc_stderr": 0.004594323838650341, "acc_norm": 0.34495120493925513, "acc_norm_stderr": 0.004743808792037872 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.19, "acc_stderr": 0.039427724440366234, "acc_norm": 0.19, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3037037037037037, "acc_stderr": 0.039725528847851375, "acc_norm": 0.3037037037037037, "acc_norm_stderr": 0.039725528847851375 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.03110318238312337, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.03110318238312337 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.21132075471698114, "acc_stderr": 0.025125766484827842, "acc_norm": 0.21132075471698114, "acc_norm_stderr": 0.025125766484827842 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.24305555555555555, "acc_stderr": 0.03586879280080342, "acc_norm": 0.24305555555555555, "acc_norm_stderr": 0.03586879280080342 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.27, "acc_stderr": 0.0446196043338474, "acc_norm": 0.27, "acc_norm_stderr": 0.0446196043338474 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2543352601156069, "acc_stderr": 0.0332055644308557, "acc_norm": 0.2543352601156069, "acc_norm_stderr": 0.0332055644308557 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.28431372549019607, "acc_stderr": 0.04488482852329017, "acc_norm": 0.28431372549019607, "acc_norm_stderr": 0.04488482852329017 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.17, "acc_stderr": 0.0377525168068637, "acc_norm": 0.17, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.23829787234042554, "acc_stderr": 0.027851252973889778, "acc_norm": 0.23829787234042554, "acc_norm_stderr": 0.027851252973889778 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2543859649122807, "acc_stderr": 0.040969851398436695, "acc_norm": 0.2543859649122807, "acc_norm_stderr": 0.040969851398436695 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.22758620689655173, "acc_stderr": 0.03493950380131184, "acc_norm": 0.22758620689655173, "acc_norm_stderr": 0.03493950380131184 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.23015873015873015, "acc_stderr": 0.02167921966369314, "acc_norm": 0.23015873015873015, "acc_norm_stderr": 0.02167921966369314 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.16666666666666666, "acc_stderr": 0.03333333333333337, "acc_norm": 0.16666666666666666, "acc_norm_stderr": 0.03333333333333337 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.18, "acc_stderr": 0.038612291966536934, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536934 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3161290322580645, "acc_stderr": 0.02645087448904277, "acc_norm": 0.3161290322580645, "acc_norm_stderr": 0.02645087448904277 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.29064039408866993, "acc_stderr": 0.0319474007226554, "acc_norm": 0.29064039408866993, "acc_norm_stderr": 0.0319474007226554 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.23, "acc_stderr": 0.042295258468165065, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2606060606060606, "acc_stderr": 0.034277431758165236, "acc_norm": 0.2606060606060606, "acc_norm_stderr": 0.034277431758165236 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2676767676767677, "acc_stderr": 0.03154449888270285, "acc_norm": 0.2676767676767677, "acc_norm_stderr": 0.03154449888270285 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.27979274611398963, "acc_stderr": 0.03239637046735703, "acc_norm": 0.27979274611398963, "acc_norm_stderr": 0.03239637046735703 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2692307692307692, "acc_stderr": 0.022489389793654845, "acc_norm": 0.2692307692307692, "acc_norm_stderr": 0.022489389793654845 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24074074074074073, "acc_
