open-llm-leaderboard-old/details_PSanni__MPOMixtral-8x7B-Instruct-v0.1
收藏数据集概述
数据集简介
该数据集是在对模型 PSanni/MPOMixtral-8x7B-Instruct-v0.1 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。
- 额外的 "results" 配置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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_PSanni__MPOMixtral-8x7B-Instruct-v0.1", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-14T14:23:30.207507 运行的最新结果：
python { "all": { "acc": 0.7021378898937154, "acc_stderr": 0.03050401556178155, "acc_norm": 0.7057392541812927, "acc_norm_stderr": 0.031097861836160572, "mc1": 0.5152998776009792, "mc1_stderr": 0.017495304473187902, "mc2": 0.665216588266765, "mc2_stderr": 0.014619883028401507 }, "harness|arc:challenge|25": { "acc": 0.6800341296928327, "acc_stderr": 0.013631345807016193, "acc_norm": 0.7098976109215017, "acc_norm_stderr": 0.013261573677520764 }, "harness|hellaswag|10": { "acc": 0.690300736904999, "acc_stderr": 0.004614246282055377, "acc_norm": 0.8795060744871539, "acc_norm_stderr": 0.0032487292211528865 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6888888888888889, "acc_stderr": 0.0399926287661772, "acc_norm": 0.6888888888888889, "acc_norm_stderr": 0.0399926287661772 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7960526315789473, "acc_stderr": 0.0327900040631005, "acc_norm": 0.7960526315789473, "acc_norm_stderr": 0.0327900040631005 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7622641509433963, "acc_stderr": 0.02619980880756193, "acc_norm": 0.7622641509433963, "acc_norm_stderr": 0.02619980880756193 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8055555555555556, "acc_stderr": 0.03309615177059006, "acc_norm": 0.8055555555555556, "acc_norm_stderr": 0.03309615177059006 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.62, "acc_stderr": 0.04878317312145633, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7398843930635838, "acc_stderr": 0.033450369167889904, "acc_norm": 0.7398843930635838, "acc_norm_stderr": 0.033450369167889904 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4215686274509804, "acc_stderr": 0.04913595201274498, "acc_norm": 0.4215686274509804, "acc_norm_stderr": 0.04913595201274498 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.8, "acc_stderr": 0.04020151261036846, "acc_norm": 0.8, "acc_norm_stderr": 0.04020151261036846 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6851063829787234, "acc_stderr": 0.03036358219723817, "acc_norm": 0.6851063829787234, "acc_norm_stderr": 0.03036358219723817 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5877192982456141, "acc_stderr": 0.04630653203366596, "acc_norm": 0.5877192982456141, "acc_norm_stderr": 0.04630653203366596 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6275862068965518, "acc_stderr": 0.04028731532947558, "acc_norm": 0.6275862068965518, "acc_norm_stderr": 0.04028731532947558 }, "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": 0.47619047619047616, "acc_stderr": 0.04467062628403273, "acc_norm": 0.47619047619047616, "acc_norm_stderr": 0.04467062628403273 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8387096774193549, "acc_stderr": 0.020923327006423294, "acc_norm": 0.8387096774193549, "acc_norm_stderr": 0.020923327006423294 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5960591133004927, "acc_stderr": 0.03452453903822033, "acc_norm": 0.5960591133004927, "acc_norm_stderr": 0.03452453903822033 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7818181818181819, "acc_stderr": 0.03225078108306289, "acc_norm": 0.7818181818181819, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8585858585858586, "acc_stderr": 0.024825909793343336, "acc_norm": 0.8585858585858586, "acc_norm_stderr": 0.024825909793343336 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9585492227979274, "acc_stderr": 0.01438543285747646, "acc_norm": 0.9585492227979274, "acc_norm_stderr": 0.01438543285747646 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7205128205128205, "acc_stderr": 0.022752388839776823, "acc_norm": 0.7205128205128205, "acc_norm_stderr": 0.022752388839776823 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4, "acc_stderr": 0.029869605095316908, "acc_norm": 0.4, "acc_norm_stderr": 0.029869
