open-llm-leaderboard-old/details_kodonho__Solar-OrcaDPO-Solar-Instruct-SLERP
收藏数据集概述
该数据集是在对模型 kodonho/Solar-OrcaDPO-Solar-Instruct-SLERP 进行评估运行期间自动创建的，评估结果发布在 Open LLM Leaderboard 上。
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。
- 数据集由 1 次运行创建，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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_kodonho__Solar-OrcaDPO-Solar-Instruct-SLERP", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-13T17:32:35.779900 运行的最新结果：
python { "all": { "acc": 0.6659359197324706, "acc_stderr": 0.03167249441105516, "acc_norm": 0.6667077779566729, "acc_norm_stderr": 0.032318448519432046, "mc1": 0.5679314565483476, "mc1_stderr": 0.017341202394988327, "mc2": 0.7195437123974021, "mc2_stderr": 0.01500878766115849 }, "harness|arc:challenge|25": { "acc": 0.6808873720136519, "acc_stderr": 0.013621696119173306, "acc_norm": 0.7098976109215017, "acc_norm_stderr": 0.013261573677520766 }, "harness|hellaswag|10": { "acc": 0.7105158334993029, "acc_stderr": 0.004525960965551707, "acc_norm": 0.882194781915953, "acc_norm_stderr": 0.003217184906847944 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6148148148148148, "acc_stderr": 0.04203921040156279, "acc_norm": 0.6148148148148148, "acc_norm_stderr": 0.04203921040156279 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7302631578947368, "acc_stderr": 0.03611780560284898, "acc_norm": 0.7302631578947368, "acc_norm_stderr": 0.03611780560284898 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.74, "acc_stderr": 0.0440844002276808, "acc_norm": 0.74, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6830188679245283, "acc_stderr": 0.02863723563980089, "acc_norm": 0.6830188679245283, "acc_norm_stderr": 0.02863723563980089 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7569444444444444, "acc_stderr": 0.03586879280080341, "acc_norm": 0.7569444444444444, "acc_norm_stderr": 0.03586879280080341 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6647398843930635, "acc_stderr": 0.03599586301247077, "acc_norm": 0.6647398843930635, "acc_norm_stderr": 0.03599586301247077 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.04810840148082636, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.04810840148082636 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.04229525846816507, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816507 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6340425531914894, "acc_stderr": 0.031489558297455304, "acc_norm": 0.6340425531914894, "acc_norm_stderr": 0.031489558297455304 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5087719298245614, "acc_stderr": 0.04702880432049615, "acc_norm": 0.5087719298245614, "acc_norm_stderr": 0.04702880432049615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6137931034482759, "acc_stderr": 0.04057324734419036, "acc_norm": 0.6137931034482759, "acc_norm_stderr": 0.04057324734419036 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.47354497354497355, "acc_stderr": 0.025715239811346758, "acc_norm": 0.47354497354497355, "acc_norm_stderr": 0.025715239811346758 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4444444444444444, "acc_stderr": 0.044444444444444495, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.044444444444444495 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8096774193548387, "acc_stderr": 0.022331707611823078, "acc_norm": 0.8096774193548387, "acc_norm_stderr": 0.022331707611823078 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5024630541871922, "acc_stderr": 0.03517945038691063, "acc_norm": 0.5024630541871922, "acc_norm_stderr": 0.03517945038691063 }, "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": 0.806060606060606, "acc_stderr": 0.03087414513656209, "acc_norm": 0.806060606060606, "acc_norm_stderr": 0.03087414513656209 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8737373737373737, "acc_stderr": 0.02366435940288023, "acc_norm": 0.8737373737373737, "acc_norm_stderr": 0.02366435940288023 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9067357512953368, "acc_stderr": 0.02098685459328973, "acc_norm": 0.9067357512953368, "acc_norm_stderr": 0.02098685459328973 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6641025641025641, "acc_stderr": 0.023946724741563976, "acc_norm": 0.6641025641025641, "acc_norm_stderr": 0.023946724741563976 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.35555555555555557, "acc_stderr": 0.029185714949857406, "acc_norm": 0.35555555555555557, "acc_norm_stderr": 0.02918
