open-llm-leaderboard-old/details_mistral-community__Mixtral-8x22B-v0.1
收藏数据集概述
数据集摘要
该数据集是在评估模型mistral-community/Mixtral-8x22B-v0.1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"分割总是指向最新的结果。
- 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_mistral-community__Mixtral-8x22B-v0.1", "harness_winogrande_5", split="train")
最新结果
以下是2024-04-11T17:46:29.011968的最新结果：
python { "all": { "acc": 0.7755702218580992, "acc_stderr": 0.027802894465057237, "acc_norm": 0.7787346755663934, "acc_norm_stderr": 0.028337156466328183, "mc1": 0.33414932680538556, "mc1_stderr": 0.016512530677150535, "mc2": 0.5108062819806165, "mc2_stderr": 0.014560943713053241 }, "harness|arc:challenge|25": { "acc": 0.6646757679180887, "acc_stderr": 0.013796182947785562, "acc_norm": 0.7047781569965871, "acc_norm_stderr": 0.013329750293382316 }, "harness|hellaswag|10": { "acc": 0.7050388368850826, "acc_stderr": 0.004550933142528781, "acc_norm": 0.8872734515036845, "acc_norm_stderr": 0.003156118964752945 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.762962962962963, "acc_stderr": 0.03673731683969506, "acc_norm": 0.762962962962963, "acc_norm_stderr": 0.03673731683969506 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.881578947368421, "acc_stderr": 0.026293995855474924, "acc_norm": 0.881578947368421, "acc_norm_stderr": 0.026293995855474924 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.73, "acc_stderr": 0.044619604333847394, "acc_norm": 0.73, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8264150943396227, "acc_stderr": 0.02331058302600625, "acc_norm": 0.8264150943396227, "acc_norm_stderr": 0.02331058302600625 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8819444444444444, "acc_stderr": 0.026983346503309368, "acc_norm": 0.8819444444444444, "acc_norm_stderr": 0.026983346503309368 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.72, "acc_stderr": 0.045126085985421255, "acc_norm": 0.72, "acc_norm_stderr": 0.045126085985421255 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7861271676300579, "acc_stderr": 0.03126511206173044, "acc_norm": 0.7861271676300579, "acc_norm_stderr": 0.03126511206173044 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5392156862745098, "acc_stderr": 0.04959859966384181, "acc_norm": 0.5392156862745098, "acc_norm_stderr": 0.04959859966384181 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.82, "acc_stderr": 0.03861229196653694, "acc_norm": 0.82, "acc_norm_stderr": 0.03861229196653694 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.8085106382978723, "acc_stderr": 0.02572214999263779, "acc_norm": 0.8085106382978723, "acc_norm_stderr": 0.02572214999263779 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6842105263157895, "acc_stderr": 0.04372748290278007, "acc_norm": 0.6842105263157895, "acc_norm_stderr": 0.04372748290278007 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7724137931034483, "acc_stderr": 0.034939503801311826, "acc_norm": 0.7724137931034483, "acc_norm_stderr": 0.034939503801311826 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6190476190476191, "acc_stderr": 0.025010749116137595, "acc_norm": 0.6190476190476191, "acc_norm_stderr": 0.025010749116137595 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.6031746031746031, "acc_stderr": 0.043758884927270585, "acc_norm": 0.6031746031746031, "acc_norm_stderr": 0.043758884927270585 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9129032258064517, "acc_stderr": 0.01604110074169669, "acc_norm": 0.9129032258064517, "acc_norm_stderr": 0.01604110074169669 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6699507389162561, "acc_stderr": 0.03308530426228258, "acc_norm": 0.6699507389162561, "acc_norm_stderr": 0.03308530426228258 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.87, "acc_stderr": 0.03379976689896309, "acc_norm": 0.87, "acc_norm_stderr": 0.03379976689896309 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8545454545454545, "acc_stderr": 0.027530196355066584, "acc_norm": 0.8545454545454545, "acc_norm_stderr": 0.027530196355066584 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9141414141414141, "acc_stderr": 0.01996022556317289, "acc_norm": 0.9141414141414141, "acc_norm_stderr": 0.01996022556317289 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9689119170984456, "acc_stderr": 0.012525310625527041, "acc_norm": 0.9689119170984456, "acc_norm_stderr": 0.012525310625527041 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8051282051282052, "acc_stderr": 0.020083167595181393, "acc_norm": 0.8051282051282052, "acc_norm_stderr": 0.020083167595181393 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.45185185185185184, "acc_stderr": 0.030343862998512633, "acc_norm": 0.45185185185185184, "acc_norm_stderr": 0.030343862
