open-llm-leaderboard-old/details_hon9kon9ize__CantoneseLLMChat-preview20240326
收藏数据集概述
该数据集是在对模型 hon9kon9ize/CantoneseLLMChat-preview20240326 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 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。
- 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。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_hon9kon9ize__CantoneseLLMChat-preview20240326", "harness_winogrande_5", split="train")
最新结果
以下是来自 2024-04-06T21:09:18.139662 运行的最新结果：
python { "all": { "acc": 0.5852867980696239, "acc_stderr": 0.0332442920433603, "acc_norm": 0.5924742418958416, "acc_norm_stderr": 0.03394324011157871, "mc1": 0.2802937576499388, "mc1_stderr": 0.015723139524608763, "mc2": 0.4186523322493673, "mc2_stderr": 0.014508189130743358 }, "harness|arc:challenge|25": { "acc": 0.4854948805460751, "acc_stderr": 0.01460524108137006, "acc_norm": 0.5255972696245734, "acc_norm_stderr": 0.014592230885298967 }, "harness|hellaswag|10": { "acc": 0.517625970922127, "acc_stderr": 0.004986680048438308, "acc_norm": 0.6904999004182434, "acc_norm_stderr": 0.004613427745209508 }, "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": 0.5259259259259259, "acc_stderr": 0.04313531696750575, "acc_norm": 0.5259259259259259, "acc_norm_stderr": 0.04313531696750575 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6381578947368421, "acc_stderr": 0.03910525752849724, "acc_norm": 0.6381578947368421, "acc_norm_stderr": 0.03910525752849724 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.63, "acc_stderr": 0.04852365870939099, "acc_norm": 0.63, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.660377358490566, "acc_stderr": 0.029146904747798325, "acc_norm": 0.660377358490566, "acc_norm_stderr": 0.029146904747798325 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6041666666666666, "acc_stderr": 0.04089465449325582, "acc_norm": 0.6041666666666666, "acc_norm_stderr": 0.04089465449325582 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.39, "acc_stderr": 0.049020713000019756, "acc_norm": 0.39, "acc_norm_stderr": 0.049020713000019756 }, "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": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6011560693641619, "acc_stderr": 0.037336266553835096, "acc_norm": 0.6011560693641619, "acc_norm_stderr": 0.037336266553835096 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3431372549019608, "acc_stderr": 0.04724007352383887, "acc_norm": 0.3431372549019608, "acc_norm_stderr": 0.04724007352383887 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5574468085106383, "acc_stderr": 0.032469569197899575, "acc_norm": 0.5574468085106383, "acc_norm_stderr": 0.032469569197899575 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.37719298245614036, "acc_stderr": 0.04559522141958216, "acc_norm": 0.37719298245614036, "acc_norm_stderr": 0.04559522141958216 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6068965517241379, "acc_stderr": 0.0407032901370707, "acc_norm": 0.6068965517241379, "acc_norm_stderr": 0.0407032901370707 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42063492063492064, "acc_stderr": 0.025424835086923992, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.025424835086923992 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.38095238095238093, "acc_stderr": 0.04343525428949097, "acc_norm": 0.38095238095238093, "acc_norm_stderr": 0.04343525428949097 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7483870967741936, "acc_stderr": 0.024685979286239976, "acc_norm": 0.7483870967741936, "acc_norm_stderr": 0.024685979286239976 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.43349753694581283, "acc_stderr": 0.034867317274198714, "acc_norm": 0.43349753694581283, "acc_norm_stderr": 0.034867317274198714 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7212121212121212, "acc_stderr": 0.03501438706296781, "acc_norm": 0.7212121212121212, "acc_norm_stderr": 0.03501438706296781 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7878787878787878, "acc_stderr": 0.0291265228345868, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.0291265228345868 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7979274611398963, "acc_stderr": 0.02897908979429673, "acc_norm": 0.7979274611398963, "acc_norm_stderr": 0.02897908979429673 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5512820512820513, "acc_stderr": 0.025217315184846482, "acc_norm": 0.5512820512820513, "acc_norm_stderr": 0.025217315184846482 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.25925925925925924, "acc_stderr": 0.026719240783712166, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.026719240783712166 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6554621848739496,
