open-llm-leaderboard-old/details_grimjim__zephyr-beta-wizardLM-2-merge-7B
收藏数据集概述
该数据集是在评估模型 grimjim/zephyr-beta-wizardLM-2-merge-7B 在 Open LLM Leaderboard 上的运行过程中自动创建的。
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 2 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 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_grimjim__zephyr-beta-wizardLM-2-merge-7B", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果来自 run 2024-04-18T19:23:10.412079 的摘要：
python { "all": { "acc": 0.6340910723457099, "acc_stderr": 0.032643349211070934, "acc_norm": 0.6380814915677291, "acc_norm_stderr": 0.033295183192576565, "mc1": 0.4186046511627907, "mc1_stderr": 0.017270015284476855, "mc2": 0.5837624501502261, "mc2_stderr": 0.01558197159702437 }, "harness|arc:challenge|25": { "acc": 0.621160409556314, "acc_stderr": 0.014175915490000328, "acc_norm": 0.6467576791808873, "acc_norm_stderr": 0.013967822714840055 }, "harness|hellaswag|10": { "acc": 0.6734714200358495, "acc_stderr": 0.004679847503411343, "acc_norm": 0.853415654252141, "acc_norm_stderr": 0.003529682285857235 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "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": 0.6644736842105263, "acc_stderr": 0.03842498559395268, "acc_norm": 0.6644736842105263, "acc_norm_stderr": 0.03842498559395268 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.690566037735849, "acc_stderr": 0.028450154794118637, "acc_norm": 0.690566037735849, "acc_norm_stderr": 0.028450154794118637 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7291666666666666, "acc_stderr": 0.037161774375660164, "acc_norm": 0.7291666666666666, "acc_norm_stderr": 0.037161774375660164 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "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": 0.6416184971098265, "acc_stderr": 0.036563436533531585, "acc_norm": 0.6416184971098265, "acc_norm_stderr": 0.036563436533531585 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.39215686274509803, "acc_stderr": 0.04858083574266345, "acc_norm": 0.39215686274509803, "acc_norm_stderr": 0.04858083574266345 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.79, "acc_stderr": 0.04093601807403326, "acc_norm": 0.79, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5531914893617021, "acc_stderr": 0.032500536843658404, "acc_norm": 0.5531914893617021, "acc_norm_stderr": 0.032500536843658404 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5175438596491229, "acc_stderr": 0.04700708033551038, "acc_norm": 0.5175438596491229, "acc_norm_stderr": 0.04700708033551038 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5517241379310345, "acc_stderr": 0.04144311810878151, "acc_norm": 0.5517241379310345, "acc_norm_stderr": 0.04144311810878151 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3862433862433862, "acc_stderr": 0.025075981767601688, "acc_norm": 0.3862433862433862, "acc_norm_stderr": 0.025075981767601688 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4126984126984127, "acc_stderr": 0.04403438954768176, "acc_norm": 0.4126984126984127, "acc_norm_stderr": 0.04403438954768176 }, "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": 0.7870967741935484, "acc_stderr": 0.023287665127268552, "acc_norm": 0.7870967741935484, "acc_norm_stderr": 0.023287665127268552 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4876847290640394, "acc_stderr": 0.035169204442208966, "acc_norm": 0.4876847290640394, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7757575757575758, "acc_stderr": 0.03256866661681102, "acc_norm": 0.7757575757575758, "acc_norm_stderr": 0.03256866661681102 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7626262626262627, "acc_stderr": 0.030313710538198896, "acc_norm": 0.7626262626262627, "acc_norm_stderr": 0.030313710538198896 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8756476683937824, "acc_stderr": 0.02381447708659356, "acc_norm": 0.8756476683937824, "acc_norm_stderr": 0.02381447708659356 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6435897435897436, "acc_stderr": 0.02428314052946731, "acc_norm": 0.6435897435897436, "acc_norm_stderr": 0.02428314052946731 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.34814814814814815, "acc_stderr": 0.029045600290616255, "acc_norm": 0.348148148
