open-llm-leaderboard-old/details_TomGrc__FusionNet_34Bx2_MoE
收藏数据集概述
数据集组成
- 该数据集包含63个配置，每个配置对应一个评估任务。
- 数据集由1次运行创建，每个运行的详细结果存储在特定的分割中，分割名称使用运行的时间戳。
- 每个配置的“train”分割指向最新的结果。
额外配置
- 一个名为“results”的额外配置存储了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_TomGrc__FusionNet_34Bx2_MoE", "harness_winogrande_5", split="train")
最新结果
- 最新结果来自2024-01-22T11:29:51.974520的运行，包含多个任务的评估结果，具体结果如下：
python { "all": { "acc": 0.7677884016423521, "acc_stderr": 0.028039750027124166, "acc_norm": 0.7713984723671282, "acc_norm_stderr": 0.028574402204719553, "mc1": 0.5520195838433293, "mc1_stderr": 0.017408513063422906, "mc2": 0.7131206524056665, "mc2_stderr": 0.014366676245195859 }, "harness|arc:challenge|25": { "acc": 0.6962457337883959, "acc_stderr": 0.01343890918477876, "acc_norm": 0.7295221843003413, "acc_norm_stderr": 0.012980954547659556 }, "harness|hellaswag|10": { "acc": 0.6693885680143398, "acc_stderr": 0.004694718918225755, "acc_norm": 0.8621788488348935, "acc_norm_stderr": 0.003440076775300576 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7333333333333333, "acc_stderr": 0.038201699145179055, "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.038201699145179055 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.881578947368421, "acc_stderr": 0.026293995855474938, "acc_norm": 0.881578947368421, "acc_norm_stderr": 0.026293995855474938 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.77, "acc_stderr": 0.04229525846816506, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8075471698113208, "acc_stderr": 0.024262979839372274, "acc_norm": 0.8075471698113208, "acc_norm_stderr": 0.024262979839372274 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8680555555555556, "acc_stderr": 0.02830096838204443, "acc_norm": 0.8680555555555556, "acc_norm_stderr": 0.02830096838204443 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.59, "acc_stderr": 0.04943110704237101, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237101 }, "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": 0.7456647398843931, "acc_stderr": 0.0332055644308557, "acc_norm": 0.7456647398843931, "acc_norm_stderr": 0.0332055644308557 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5686274509803921, "acc_stderr": 0.04928099597287534, "acc_norm": 0.5686274509803921, "acc_norm_stderr": 0.04928099597287534 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.81, "acc_stderr": 0.039427724440366234, "acc_norm": 0.81, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7829787234042553, "acc_stderr": 0.02694748312149622, "acc_norm": 0.7829787234042553, "acc_norm_stderr": 0.02694748312149622 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6140350877192983, "acc_stderr": 0.04579639422070434, "acc_norm": 0.6140350877192983, "acc_norm_stderr": 0.04579639422070434 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7517241379310344, "acc_stderr": 0.036001056927277696, "acc_norm": 0.7517241379310344, "acc_norm_stderr": 0.036001056927277696 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.7222222222222222, "acc_stderr": 0.02306818884826112, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.02306818884826112 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5555555555555556, "acc_stderr": 0.044444444444444495, "acc_norm": 0.5555555555555556, "acc_norm_stderr": 0.044444444444444495 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9161290322580645, "acc_stderr": 0.015769027496775664, "acc_norm": 0.9161290322580645, "acc_norm_stderr": 0.015769027496775664 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6502463054187192, "acc_stderr": 0.03355400904969566, "acc_norm": 0.6502463054187192, "acc_norm_stderr": 0.03355400904969566 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.83, "acc_stderr": 0.03775251680686371, "acc_norm": 0.83, "acc_norm_stderr": 0.03775251680686371 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8727272727272727, "acc_stderr": 0.026024657651656177, "acc_norm": 0.8727272727272727, "acc_norm_stderr": 0.026024657651656177 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9191919191919192, "acc_stderr": 0.019417681889724536, "acc_norm": 0.9191919191919192, "acc_norm_stderr": 0.019417681889724536 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9740932642487047, "acc_stderr": 0.011464523356953162, "acc_norm": 0.9740932642487047, "acc_norm_stderr": 0.011464523356953162 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8179487179487179, "acc_stderr": 0.019565236782930893, "acc_norm": 0.8179487179487179, "acc_norm_stderr": 0.019565236782930893 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.45925925925925926, "acc_stderr": 0.03038416923235083, "acc_norm": 0.45925925925925926, "acc_norm_stderr": 0.03038416923235083 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.8487394957983193, "acc_stderr": 0.023274255898707946, "acc_norm": 0.8487394957983193, "acc_norm_stderr": 0.023
