open-llm-leaderboard-old/details_maywell__koOpenChat-sft
收藏数据集概述
数据集摘要
该数据集是在对模型 maywell/koOpenChat-sft 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 64 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。"train" 分割始终指向最新的结果。
附加配置
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_maywell__koOpenChat-sft_public", "harness_winogrande_5", split="train")
最新结果
以下是 2023-11-20T08:36:25.253046 运行的最新结果：
python { "all": { "acc": 0.6084632908836825, "acc_stderr": 0.03295483776577676, "acc_norm": 0.6158685044863811, "acc_norm_stderr": 0.03365334045258809, "mc1": 0.3378212974296206, "mc1_stderr": 0.01655716732251688, "mc2": 0.5124049209846685, "mc2_stderr": 0.014984310875510325, "em": 0.005138422818791947, "em_stderr": 0.0007322104102794216, "f1": 0.07822776845637572, "f1_stderr": 0.0016538004844235878 }, "harness|arc:challenge|25": { "acc": 0.568259385665529, "acc_stderr": 0.014474591427196202, "acc_norm": 0.5981228668941979, "acc_norm_stderr": 0.014327268614578273 }, "harness|hellaswag|10": { "acc": 0.5913164708225453, "acc_stderr": 0.004905859114942294, "acc_norm": 0.7872933678550089, "acc_norm_stderr": 0.004083855139469325 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.37, "acc_stderr": 0.04852365870939098, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939098 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5481481481481482, "acc_stderr": 0.042992689054808644, "acc_norm": 0.5481481481481482, "acc_norm_stderr": 0.042992689054808644 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6578947368421053, "acc_stderr": 0.038607315993160904, "acc_norm": 0.6578947368421053, "acc_norm_stderr": 0.038607315993160904 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6943396226415094, "acc_stderr": 0.028353298073322666, "acc_norm": 0.6943396226415094, "acc_norm_stderr": 0.028353298073322666 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6527777777777778, "acc_stderr": 0.039812405437178615, "acc_norm": 0.6527777777777778, "acc_norm_stderr": 0.039812405437178615 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.49, "acc_stderr": 0.05024183937956913, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956913 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6416184971098265, "acc_stderr": 0.03656343653353159, "acc_norm": 0.6416184971098265, "acc_norm_stderr": 0.03656343653353159 }, "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": 0.76, "acc_stderr": 0.042923469599092816, "acc_norm": 0.76, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5617021276595745, "acc_stderr": 0.03243618636108102, "acc_norm": 0.5617021276595745, "acc_norm_stderr": 0.03243618636108102 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.43859649122807015, "acc_stderr": 0.04668000738510455, "acc_norm": 0.43859649122807015, "acc_norm_stderr": 0.04668000738510455 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5448275862068965, "acc_stderr": 0.04149886942192118, "acc_norm": 0.5448275862068965, "acc_norm_stderr": 0.04149886942192118 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3888888888888889, "acc_stderr": 0.025107425481137285, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.025107425481137285 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42063492063492064, "acc_stderr": 0.04415438226743744, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.04415438226743744 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7451612903225806, "acc_stderr": 0.024790118459332208, "acc_norm": 0.7451612903225806, "acc_norm_stderr": 0.024790118459332208 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.458128078817734, "acc_stderr": 0.03505630140785741, "acc_norm": 0.458128078817734, "acc_norm_stderr": 0.03505630140785741 }, "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": 0.7333333333333333, "acc_stderr": 0.03453131801885417, "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.03453131801885417 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7525252525252525, "acc_stderr": 0.030746300742124484, "acc_norm": 0.7525252525252525, "acc_norm_stderr": 0.030746300742124484 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8808290155440415, "acc_stderr": 0.023381935348121434, "acc_norm": 0.8808290155440415, "acc_norm_stderr": 0.023381935348121434 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6256410256410256, "acc_stderr": 0.0245375915728305, "acc_norm": 0.6256410256410256, "acc_norm_stderr": 0.0245375915728305 }, "harness|hendry
