open-llm-leaderboard-old/details_llmixer__BigWeave-v12-90b
收藏数据集概述
该数据集是在对模型 llmixer/BigWeave-v12-90b 进行评估运行时自动创建的，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
- 创建来源：从 1 次运行中创建
- 分割方式：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_llmixer__BigWeave-v12-90b", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-10T04:50:33.456486 运行的最新结果：
python { "all": { "acc": 0.6915101661412839, "acc_stderr": 0.03080691396047242, "acc_norm": 0.6970185048770328, "acc_norm_stderr": 0.031402488490329186, "mc1": 0.4112607099143207, "mc1_stderr": 0.01722562708366086, "mc2": 0.6135320199051351, "mc2_stderr": 0.014869013157104283 }, "harness|arc:challenge|25": { "acc": 0.6399317406143344, "acc_stderr": 0.014027516814585188, "acc_norm": 0.6808873720136519, "acc_norm_stderr": 0.013621696119173304 }, "harness|hellaswag|10": { "acc": 0.6900019916351324, "acc_stderr": 0.004615472210316039, "acc_norm": 0.8770165305715992, "acc_norm_stderr": 0.0032774703870227274 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6222222222222222, "acc_stderr": 0.04188307537595853, "acc_norm": 0.6222222222222222, "acc_norm_stderr": 0.04188307537595853 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8289473684210527, "acc_stderr": 0.030643607071677088, "acc_norm": 0.8289473684210527, "acc_norm_stderr": 0.030643607071677088 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.73, "acc_stderr": 0.04461960433384741, "acc_norm": 0.73, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7358490566037735, "acc_stderr": 0.0271342916287417, "acc_norm": 0.7358490566037735, "acc_norm_stderr": 0.0271342916287417 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7847222222222222, "acc_stderr": 0.03437079344106135, "acc_norm": 0.7847222222222222, "acc_norm_stderr": 0.03437079344106135 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.630057803468208, "acc_stderr": 0.0368122963339432, "acc_norm": 0.630057803468208, "acc_norm_stderr": 0.0368122963339432 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.04784060704105653, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.04784060704105653 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.042923469599092816, "acc_norm": 0.76, "acc_norm_stderr": 0.042923469599092816 }, "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": 0.5087719298245614, "acc_stderr": 0.04702880432049615, "acc_norm": 0.5087719298245614, "acc_norm_stderr": 0.04702880432049615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6137931034482759, "acc_stderr": 0.04057324734419035, "acc_norm": 0.6137931034482759, "acc_norm_stderr": 0.04057324734419035 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.46296296296296297, "acc_stderr": 0.025680564640056882, "acc_norm": 0.46296296296296297, "acc_norm_stderr": 0.025680564640056882 }, "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": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8064516129032258, "acc_stderr": 0.022475258525536057, "acc_norm": 0.8064516129032258, "acc_norm_stderr": 0.022475258525536057 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5665024630541872, "acc_stderr": 0.034867317274198714, "acc_norm": 0.5665024630541872, "acc_norm_stderr": 0.034867317274198714 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.77, "acc_stderr": 0.04229525846816506, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8484848484848485, "acc_stderr": 0.027998073798781685, "acc_norm": 0.8484848484848485, "acc_norm_stderr": 0.027998073798781685 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8787878787878788, "acc_stderr": 0.023253157951942084, "acc_norm": 0.8787878787878788, "acc_norm_stderr": 0.023253157951942084 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.927461139896373, "acc_stderr": 0.018718998520678178, "acc_norm": 0.927461139896373, "acc_norm_stderr": 0.018718998520678178 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6846153846153846, "acc_stderr": 0.023559646983189946, "acc_norm": 0.6846153846153846, "acc_norm_stderr": 0.023559646983189946 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.34074074074074073, "acc_stderr": 0.028897748741131137, "acc_norm": 0.34074074074074073, "acc_norm_stderr": 0.028897748741131137 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.7310924369747899, "acc_stderr": 0.028801392193631276, "acc_norm": 0.7310924369747899, "acc_norm_stderr": 0.028801392193631276
