open-llm-leaderboard-old/details_YeungNLP__firefly-mixtral-8x7b-v0.1
收藏数据集概述
数据集简介
该数据集是在评估模型YeungNLP/firefly-mixtral-8x7b-v0.1在Open LLM Leaderboard上的运行过程中自动创建的。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 运行次数：数据集从1次运行中创建。每个运行在每个配置中作为一个特定的分片存在，分片名称使用运行的时间戳。
- 训练分片："train"分片始终指向最新的结果。
- 结果配置：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_YeungNLP__firefly-mixtral-8x7b-v0.1", "harness_winogrande_5", split="train")
最新结果
以下是2023-12-23T21:17:56.230718运行的最新结果：
python { "all": { "acc": 0.7128522987523449, "acc_stderr": 0.030245263140979715, "acc_norm": 0.7167785241964734, "acc_norm_stderr": 0.03083288189023405, "mc1": 0.40269277845777235, "mc1_stderr": 0.017168830935187222, "mc2": 0.553071814559571, "mc2_stderr": 0.0151346546936277 }, "harness|arc:challenge|25": { "acc": 0.6527303754266212, "acc_stderr": 0.013913034529620448, "acc_norm": 0.6808873720136519, "acc_norm_stderr": 0.013621696119173306 }, "harness|hellaswag|10": { "acc": 0.6661023700458076, "acc_stderr": 0.0047063982523824635, "acc_norm": 0.8575980880302728, "acc_norm_stderr": 0.0034874768122805247 }, "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": 0.6814814814814815, "acc_stderr": 0.04024778401977109, "acc_norm": 0.6814814814814815, "acc_norm_stderr": 0.04024778401977109 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8092105263157895, "acc_stderr": 0.031975658210325, "acc_norm": 0.8092105263157895, "acc_norm_stderr": 0.031975658210325 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.72, "acc_stderr": 0.04512608598542127, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7849056603773585, "acc_stderr": 0.02528839450289137, "acc_norm": 0.7849056603773585, "acc_norm_stderr": 0.02528839450289137 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8541666666666666, "acc_stderr": 0.029514245964291766, "acc_norm": 0.8541666666666666, "acc_norm_stderr": 0.029514245964291766 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.63, "acc_stderr": 0.048523658709391, "acc_norm": 0.63, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7052023121387283, "acc_stderr": 0.03476599607516478, "acc_norm": 0.7052023121387283, "acc_norm_stderr": 0.03476599607516478 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.43137254901960786, "acc_stderr": 0.04928099597287534, "acc_norm": 0.43137254901960786, "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": 0.6808510638297872, "acc_stderr": 0.030472973363380042, "acc_norm": 0.6808510638297872, "acc_norm_stderr": 0.030472973363380042 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6403508771929824, "acc_stderr": 0.04514496132873633, "acc_norm": 0.6403508771929824, "acc_norm_stderr": 0.04514496132873633 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6689655172413793, "acc_stderr": 0.039215453124671215, "acc_norm": 0.6689655172413793, "acc_norm_stderr": 0.039215453124671215 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.48677248677248675, "acc_stderr": 0.025742297289575142, "acc_norm": 0.48677248677248675, "acc_norm_stderr": 0.025742297289575142 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5714285714285714, "acc_stderr": 0.0442626668137991, "acc_norm": 0.5714285714285714, "acc_norm_stderr": 0.0442626668137991 }, "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": 0.8193548387096774, "acc_stderr": 0.02188617856717253, "acc_norm": 0.8193548387096774, "acc_norm_stderr": 0.02188617856717253 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6403940886699507, "acc_stderr": 0.03376458246509567, "acc_norm": 0.6403940886699507, "acc_norm_stderr": 0.03376458246509567 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.72, "acc_stderr": 0.04512608598542127, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7878787878787878, "acc_stderr": 0.031922715695483, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.031922715695483 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8737373737373737, "acc_stderr": 0.023664359402880232, "acc_norm": 0.8737373737373737, "acc_norm_stderr": 0.023664359402880232 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9378238341968912, "acc_stderr": 0.017426974154240528, "acc_norm": 0.9378238341968912, "acc_norm_stderr": 0.017426974154240528 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7076923076923077, "acc_stderr": 0.023060438380857744, "acc_norm": 0.7076923076923077, "acc_norm_stderr": 0.023060438380857744 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3925925925925926, "acc_stderr": 0.029773847012532967,
