open-llm-leaderboard-old/details_migtissera__SynthIA-70B-v1.5
收藏数据集概述
数据集摘要
该数据集是在对模型 migtissera/SynthIA-70B-v1.5 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
- 配置数量：63 个配置
- 数据来源：从 1 次运行中创建
- 数据分割：每个配置包含特定分割，分割名称使用运行的时间戳。"train" 分割始终指向最新结果。
- 额外配置："results" 配置存储所有运行的聚合结果，用于计算和显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_migtissera__SynthIA-70B-v1.5", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-08T03:41:45.134305 运行的最新结果：
python { "all": { "acc": 0.6908264640585592, "acc_stderr": 0.03059066166329622, "acc_norm": 0.6946757184916225, "acc_norm_stderr": 0.031189654753338784, "mc1": 0.40758873929008566, "mc1_stderr": 0.017201949234553107, "mc2": 0.5740125787335826, "mc2_stderr": 0.015069171807224776 }, "harness|arc:challenge|25": { "acc": 0.6518771331058021, "acc_stderr": 0.013921008595179349, "acc_norm": 0.6936860068259386, "acc_norm_stderr": 0.013470584417276513 }, "harness|hellaswag|10": { "acc": 0.6813383788090022, "acc_stderr": 0.0046500521500943935, "acc_norm": 0.8697470623381797, "acc_norm_stderr": 0.00335893627986726 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6148148148148148, "acc_stderr": 0.042039210401562783, "acc_norm": 0.6148148148148148, "acc_norm_stderr": 0.042039210401562783 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7960526315789473, "acc_stderr": 0.03279000406310051, "acc_norm": 0.7960526315789473, "acc_norm_stderr": 0.03279000406310051 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.72, "acc_stderr": 0.04512608598542127, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7056603773584905, "acc_stderr": 0.028049186315695248, "acc_norm": 0.7056603773584905, "acc_norm_stderr": 0.028049186315695248 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8125, "acc_stderr": 0.032639560491693344, "acc_norm": 0.8125, "acc_norm_stderr": 0.032639560491693344 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "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": 0.6763005780346821, "acc_stderr": 0.0356760379963917, "acc_norm": 0.6763005780346821, "acc_norm_stderr": 0.0356760379963917 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.39215686274509803, "acc_stderr": 0.048580835742663434, "acc_norm": 0.39215686274509803, "acc_norm_stderr": 0.048580835742663434 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.73, "acc_stderr": 0.04461960433384739, "acc_norm": 0.73, "acc_norm_stderr": 0.04461960433384739 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.676595744680851, "acc_stderr": 0.030579442773610337, "acc_norm": 0.676595744680851, "acc_norm_stderr": 0.030579442773610337 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.40350877192982454, "acc_stderr": 0.04615186962583703, "acc_norm": 0.40350877192982454, "acc_norm_stderr": 0.04615186962583703 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6068965517241379, "acc_stderr": 0.040703290137070705, "acc_norm": 0.6068965517241379, "acc_norm_stderr": 0.040703290137070705 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.43386243386243384, "acc_stderr": 0.025525034382474894, "acc_norm": 0.43386243386243384, "acc_norm_stderr": 0.025525034382474894 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.46825396825396826, "acc_stderr": 0.04463112720677172, "acc_norm": 0.46825396825396826, "acc_norm_stderr": 0.04463112720677172 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8290322580645161, "acc_stderr": 0.021417242936321582, "acc_norm": 0.8290322580645161, "acc_norm_stderr": 0.021417242936321582 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5123152709359606, "acc_stderr": 0.035169204442208966, "acc_norm": 0.5123152709359606, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.73, "acc_stderr": 0.044619604333847394, "acc_norm": 0.73, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8242424242424242, "acc_stderr": 0.02972094300622445, "acc_norm": 0.8242424242424242, "acc_norm_stderr": 0.02972094300622445 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8939393939393939, "acc_stderr": 0.021938047738853106, "acc_norm": 0.8939393939393939, "acc_norm_stderr": 0.021938047738853106 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9378238341968912, "acc_stderr": 0.017426974154240528, "acc_norm": 0.9378238341968912, "acc_norm_stderr": 0.017426974154240528 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7307692307692307, "acc_stderr": 0.022489389793654817, "acc_norm": 0.7307692307692307, "acc_norm_stderr": 0.022489389793654817 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3111111111111111, "acc_stderr": 0.02822644674968352, "acc_norm": 0.3111111111111111, "acc_norm_stderr": 0.02822644674968352 }, "harness|hendrycksTest-high_school_microeconomics
