open-llm-leaderboard-old/details_BFauber__lora_llama2-13b_10e5_r8_a256
收藏数据集概述
数据集来源
该数据集是在模型 BFauber/lora_llama2-13b_10e5_r8_a256 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
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，每个运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。"train" 分片始终指向最新的结果。
额外配置
一个额外的配置 "results" 存储了所有运行结果的聚合，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_BFauber__lora_llama2-13b_10e5_r8_a256", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-10T01:23:39.833062 运行的最新结果：
python { "all": { "acc": 0.5324938577915043, "acc_stderr": 0.03380835687493485, "acc_norm": 0.5381763134612871, "acc_norm_stderr": 0.0345444080771251, "mc1": 0.2594859241126071, "mc1_stderr": 0.015345409485557982, "mc2": 0.38036691779076676, "mc2_stderr": 0.013738800535587169 }, "harness|arc:challenge|25": { "acc": 0.5699658703071673, "acc_stderr": 0.014467631559137994, "acc_norm": 0.5981228668941979, "acc_norm_stderr": 0.014327268614578278 }, "harness|hellaswag|10": { "acc": 0.6132244572794264, "acc_stderr": 0.004860162076330988, "acc_norm": 0.8178649671380203, "acc_norm_stderr": 0.0038516699346338897 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.562962962962963, "acc_stderr": 0.04284958639753401, "acc_norm": 0.562962962962963, "acc_norm_stderr": 0.04284958639753401 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5263157894736842, "acc_stderr": 0.04063302731486671, "acc_norm": 0.5263157894736842, "acc_norm_stderr": 0.04063302731486671 }, "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": 0.5358490566037736, "acc_stderr": 0.030693675018458, "acc_norm": 0.5358490566037736, "acc_norm_stderr": 0.030693675018458 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5416666666666666, "acc_stderr": 0.04166666666666665, "acc_norm": 0.5416666666666666, "acc_norm_stderr": 0.04166666666666665 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.45, "acc_stderr": 0.049999999999999996, "acc_norm": 0.45, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5144508670520231, "acc_stderr": 0.03810871630454764, "acc_norm": 0.5144508670520231, "acc_norm_stderr": 0.03810871630454764 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3431372549019608, "acc_stderr": 0.047240073523838876, "acc_norm": 0.3431372549019608, "acc_norm_stderr": 0.047240073523838876 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.39574468085106385, "acc_stderr": 0.03196758697835363, "acc_norm": 0.39574468085106385, "acc_norm_stderr": 0.03196758697835363 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.30701754385964913, "acc_stderr": 0.04339138322579861, "acc_norm": 0.30701754385964913, "acc_norm_stderr": 0.04339138322579861 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5241379310344828, "acc_stderr": 0.0416180850350153, "acc_norm": 0.5241379310344828, "acc_norm_stderr": 0.0416180850350153 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3439153439153439, "acc_stderr": 0.024464426625596437, "acc_norm": 0.3439153439153439, "acc_norm_stderr": 0.024464426625596437 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.31746031746031744, "acc_stderr": 0.04163453031302859, "acc_norm": 0.31746031746031744, "acc_norm_stderr": 0.04163453031302859 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6548387096774193, "acc_stderr": 0.027045746573534327, "acc_norm": 0.6548387096774193, "acc_norm_stderr": 0.027045746573534327 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4039408866995074, "acc_stderr": 0.0345245390382204, "acc_norm": 0.4039408866995074, "acc_norm_stderr": 0.0345245390382204 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6484848484848484, "acc_stderr": 0.037282069986826503, "acc_norm": 0.6484848484848484, "acc_norm_stderr": 0.037282069986826503 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6868686868686869, "acc_stderr": 0.033042050878136525, "acc_norm": 0.6868686868686869, "acc_norm_stderr": 0.033042050878136525 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8082901554404145, "acc_stderr": 0.02840895362624527, "acc_norm": 0.8082901554404145, "acc_norm_stderr": 0.02840895362624527 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4794871794871795, "acc_stderr": 0.02532966316348994, "acc_norm": 0.4794871794871795, "acc_norm_stderr": 0.02532966316348994 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3, "acc_stderr": 0.0279404571362284
