open-llm-leaderboard-old/details_Undi95__Llama2-13B-no_robots-alpaca-lora
收藏数据集概述
数据集摘要
该数据集是在对模型 Undi95/Llama2-13B-no_robots-alpaca-lora 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
- 数据集包含 64 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。
- "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 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_Undi95__Llama2-13B-no_robots-alpaca-lora_public", "harness_winogrande_5", split="train")
最新结果
以下是 2023-11-15T08:15:04.836039 运行的最新结果：
python { "all": { "acc": 0.5288556443369928, "acc_stderr": 0.03390383953418472, "acc_norm": 0.5370018287535696, "acc_norm_stderr": 0.034712721572579625, "mc1": 0.28151774785801714, "mc1_stderr": 0.01574402724825605, "mc2": 0.4045559753787184, "mc2_stderr": 0.01423646056016957, "em": 0.031774328859060404, "em_stderr": 0.0017962473521312278, "f1": 0.09261220637583845, "f1_stderr": 0.0021550523797604715 }, "harness|arc:challenge|25": { "acc": 0.5418088737201365, "acc_stderr": 0.014560220308714695, "acc_norm": 0.5887372013651877, "acc_norm_stderr": 0.014379441068522082 }, "harness|hellaswag|10": { "acc": 0.6309500099581756, "acc_stderr": 0.004815613144385403, "acc_norm": 0.8243377813184625, "acc_norm_stderr": 0.003797548252851636 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.047609522856952365, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952365 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4888888888888889, "acc_stderr": 0.04318275491977976, "acc_norm": 0.4888888888888889, "acc_norm_stderr": 0.04318275491977976 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5328947368421053, "acc_stderr": 0.040601270352363966, "acc_norm": 0.5328947368421053, "acc_norm_stderr": 0.040601270352363966 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5660377358490566, "acc_stderr": 0.030503292013342592, "acc_norm": 0.5660377358490566, "acc_norm_stderr": 0.030503292013342592 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5625, "acc_stderr": 0.04148415739394154, "acc_norm": 0.5625, "acc_norm_stderr": 0.04148415739394154 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.28, "acc_stderr": 0.04512608598542129, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542129 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.49710982658959535, "acc_stderr": 0.038124005659748335, "acc_norm": 0.49710982658959535, "acc_norm_stderr": 0.038124005659748335 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.23529411764705882, "acc_stderr": 0.04220773659171452, "acc_norm": 0.23529411764705882, "acc_norm_stderr": 0.04220773659171452 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4127659574468085, "acc_stderr": 0.03218471141400351, "acc_norm": 0.4127659574468085, "acc_norm_stderr": 0.03218471141400351 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.32456140350877194, "acc_stderr": 0.04404556157374768, "acc_norm": 0.32456140350877194, "acc_norm_stderr": 0.04404556157374768 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5379310344827586, "acc_stderr": 0.04154659671707548, "acc_norm": 0.5379310344827586, "acc_norm_stderr": 0.04154659671707548 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3492063492063492, "acc_stderr": 0.024552292209342654, "acc_norm": 0.3492063492063492, "acc_norm_stderr": 0.024552292209342654 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2619047619047619, "acc_stderr": 0.039325376803928704, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.039325376803928704 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6258064516129033, "acc_stderr": 0.027528904299845704, "acc_norm": 0.6258064516129033, "acc_norm_stderr": 0.027528904299845704 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4630541871921182, "acc_stderr": 0.035083705204426656, "acc_norm": 0.4630541871921182, "acc_norm_stderr": 0.035083705204426656 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6242424242424243, "acc_stderr": 0.037818873532059816, "acc_norm": 0.6242424242424243, "acc_norm_stderr": 0.037818873532059816 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6464646464646465, "acc_stderr": 0.03406086723547155, "acc_norm": 0.6464646464646465, "acc_norm_stderr": 0.03406086723547155 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7564766839378239, "acc_stderr": 0.030975436386845454, "acc_norm": 0.7564766839378239, "acc_norm_stderr": 0.030975436386845454 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5205128205128206, "acc_stderr": 0.02532966316348994, "acc_norm": 0.5205128205128206,
