open-llm-leaderboard-old/details_OpenBuddy__openbuddy-mixtral-7bx8-v17.1-32k
收藏数据集概述
数据集简介
该数据集是在模型OpenBuddy/openbuddy-mixtral-7bx8-v17.1-32k在Open LLM Leaderboard上的评估运行期间自动创建的。
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。
- 数据集从1次运行中创建，每个运行可以在每个配置中作为一个特定的分割找到，分割名称使用运行的时间戳。
- "train"分割总是指向最新的结果。
- 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_OpenBuddy__openbuddy-mixtral-7bx8-v17.1-32k", "harness_winogrande_5", split="train")
最新结果
以下是2024-01-24T10:48:34.323714运行的最新结果：
python { "all": { "acc": 0.6959391076316241, "acc_stderr": 0.03060969376377179, "acc_norm": 0.7004357595579067, "acc_norm_stderr": 0.031196750430346164, "mc1": 0.2717258261933905, "mc1_stderr": 0.01557284045287583, "mc2": 0.42136704852768436, "mc2_stderr": 0.014220364088765812 }, "harness|arc:challenge|25": { "acc": 0.6168941979522184, "acc_stderr": 0.014206472661672876, "acc_norm": 0.6552901023890785, "acc_norm_stderr": 0.01388881628678211 }, "harness|hellaswag|10": { "acc": 0.5769766978689504, "acc_stderr": 0.004930293787545623, "acc_norm": 0.7595100577574189, "acc_norm_stderr": 0.0042650756644566235 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6518518518518519, "acc_stderr": 0.041153246103369526, "acc_norm": 0.6518518518518519, "acc_norm_stderr": 0.041153246103369526 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7828947368421053, "acc_stderr": 0.03355045304882924, "acc_norm": 0.7828947368421053, "acc_norm_stderr": 0.03355045304882924 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7886792452830189, "acc_stderr": 0.02512576648482785, "acc_norm": 0.7886792452830189, "acc_norm_stderr": 0.02512576648482785 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8263888888888888, "acc_stderr": 0.03167473383795718, "acc_norm": 0.8263888888888888, "acc_norm_stderr": 0.03167473383795718 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.43, "acc_stderr": 0.04975698519562428, "acc_norm": 0.43, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6647398843930635, "acc_stderr": 0.03599586301247077, "acc_norm": 0.6647398843930635, "acc_norm_stderr": 0.03599586301247077 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.45098039215686275, "acc_stderr": 0.04951218252396264, "acc_norm": 0.45098039215686275, "acc_norm_stderr": 0.04951218252396264 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932263, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932263 }, "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": 0.5614035087719298, "acc_stderr": 0.04668000738510455, "acc_norm": 0.5614035087719298, "acc_norm_stderr": 0.04668000738510455 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6344827586206897, "acc_stderr": 0.04013124195424386, "acc_norm": 0.6344827586206897, "acc_norm_stderr": 0.04013124195424386 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4576719576719577, "acc_stderr": 0.02565886886205833, "acc_norm": 0.4576719576719577, "acc_norm_stderr": 0.02565886886205833 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5, "acc_stderr": 0.04472135954999579, "acc_norm": 0.5, "acc_norm_stderr": 0.04472135954999579 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8548387096774194, "acc_stderr": 0.020039563628053286, "acc_norm": 0.8548387096774194, "acc_norm_stderr": 0.020039563628053286 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5665024630541872, "acc_stderr": 0.03486731727419872, "acc_norm": 0.5665024630541872, "acc_norm_stderr": 0.03486731727419872 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.74, "acc_stderr": 0.0440844002276808, "acc_norm": 0.74, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8242424242424242, "acc_stderr": 0.02972094300622445, "acc_norm": 0.8242424242424242, "acc_norm_stderr": 0.02972094300622445 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8535353535353535, "acc_stderr": 0.025190921114603915, "acc_norm": 0.8535353535353535, "acc_norm_stderr": 0.025190921114603915 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9222797927461139, "acc_stderr": 0.01932180555722315, "acc_norm": 0.9222797927461139, "acc_norm_stderr": 0.01932180555722315 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6871794871794872, "acc_stderr": 0.023507579020645358, "acc_norm": 0.6871794871794872, "acc_norm_stderr": 0.023507579020645358 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3296296296296296, "acc_stderr": 0.028661201116524593, "acc_norm": 0.3296296296296296, "acc_norm_stderr": 0
