open-llm-leaderboard-old/details_rufjdk5480__mixtral-ko-qna-merged
收藏数据集概述
数据集摘要
该数据集是在评估模型 rufjdk5480/mixtral-ko-qna-merged 在 Open LLM Leaderboard 上的自动创建的。
数据集组成
- 该数据集包含 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，用于计算和显示在 Open LLM Leaderboard 上的聚合指标。
加载数据集示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_rufjdk5480__mixtral-ko-qna-merged", "harness_winogrande_5", split="train")
最新结果
这些是最新结果，来自 2024-01-05T04:40:43.464052 的运行： python { "all": { "acc": 0.6966669201907558, "acc_stderr": 0.03014874135400622, "acc_norm": 0.7075970828086718, "acc_norm_stderr": 0.03073409651050876, "mc1": 0.2178702570379437, "mc1_stderr": 0.014450846714123892, "mc2": 0.48607139277849154, "mc2_stderr": 0.01710096370379909 }, "harness|arc:challenge|25": { "acc": 0.3506825938566553, "acc_stderr": 0.013944635930726089, "acc_norm": 0.39505119453924914, "acc_norm_stderr": 0.014285898292938165 }, "harness|hellaswag|10": { "acc": 0.33917546305516827, "acc_stderr": 0.004724619193427588, "acc_norm": 0.39055964947221666, "acc_norm_stderr": 0.004868787333436588 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6888888888888889, "acc_stderr": 0.039992628766177214, "acc_norm": 0.6888888888888889, "acc_norm_stderr": 0.039992628766177214 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8355263157894737, "acc_stderr": 0.03016753346863271, "acc_norm": 0.8355263157894737, "acc_norm_stderr": 0.03016753346863271 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.71, "acc_stderr": 0.04560480215720683, "acc_norm": 0.71, "acc_norm_stderr": 0.04560480215720683 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7811320754716982, "acc_stderr": 0.0254478638251086, "acc_norm": 0.7811320754716982, "acc_norm_stderr": 0.0254478638251086 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8680555555555556, "acc_stderr": 0.02830096838204443, "acc_norm": 0.8680555555555556, "acc_norm_stderr": 0.02830096838204443 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.61, "acc_stderr": 0.04902071300001974, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6994219653179191, "acc_stderr": 0.034961014811911786, "acc_norm": 0.6994219653179191, "acc_norm_stderr": 0.034961014811911786 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5, "acc_stderr": 0.04975185951049946, "acc_norm": 0.5, "acc_norm_stderr": 0.04975185951049946 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6680851063829787, "acc_stderr": 0.030783736757745636, "acc_norm": 0.6680851063829787, "acc_norm_stderr": 0.030783736757745636 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6403508771929824, "acc_stderr": 0.04514496132873633, "acc_norm": 0.6403508771929824, "acc_norm_stderr": 0.04514496132873633 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6896551724137931, "acc_stderr": 0.038552896163789485, "acc_norm": 0.6896551724137931, "acc_norm_stderr": 0.038552896163789485 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.47883597883597884, "acc_stderr": 0.025728230952130726, "acc_norm": 0.47883597883597884, "acc_norm_stderr": 0.025728230952130726 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5238095238095238, "acc_stderr": 0.04467062628403273, "acc_norm": 0.5238095238095238, "acc_norm_stderr": 0.04467062628403273 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8451612903225807, "acc_stderr": 0.020579287326583227, "acc_norm": 0.8451612903225807, "acc_norm_stderr": 0.020579287326583227 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6354679802955665, "acc_stderr": 0.0338640574606209, "acc_norm": 0.6354679802955665, "acc_norm_stderr": 0.0338640574606209 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.72, "acc_stderr": 0.04512608598542128, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8121212121212121, "acc_stderr": 0.03050193405942914, "acc_norm": 0.8121212121212121, "acc_norm_stderr": 0.03050193405942914 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8737373737373737, "acc_stderr": 0.023664359402880236, "acc_norm": 0.8737373737373737, "acc_norm_stderr": 0.023664359402880236 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9378238341968912, "acc_stderr": 0.017426974154240524, "acc_norm": 0.9378238341968912, "acc_norm_stderr": 0.017426974154240524 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7076923076923077, "acc_stderr": 0.023060438380857726, "acc_norm": 0.7076923076923077, "acc_norm_stderr": 0.023060438380857726 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.37037037037037035, "acc_stderr": 0.02944316932303154, "acc_norm": 0.37037037037037035, "acc_norm_stderr": 0.02944316932303154 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.7899159663865546, "acc_stderr": 0.02
