open-llm-leaderboard-old/details_robinsmits__Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit
收藏数据集概述
数据集简介
该数据集是在评估模型robinsmits/Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit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2次运行中创建。每个运行在每个配置中作为一个特定的分割存在，分割名称使用运行的时间戳。
- 最新结果："train"分割始终指向最新的结果。
- 汇总结果：一个额外的配置"results"存储所有运行的汇总结果，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_robinsmits__Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit", "harness_winogrande_5", split="train")
最新结果
以下是最新结果来自2024-02-12T16:17:26.640039的摘要：
python { "all": { "acc": 0.6063275626505344, "acc_stderr": 0.0332967902436461, "acc_norm": 0.6109376151305722, "acc_norm_stderr": 0.03397264723447794, "mc1": 0.5189718482252142, "mc1_stderr": 0.017490896405762357, "mc2": 0.6728616152193471, "mc2_stderr": 0.015267659398484597 }, "harness|arc:challenge|25": { "acc": 0.5750853242320819, "acc_stderr": 0.014445698968520763, "acc_norm": 0.621160409556314, "acc_norm_stderr": 0.014175915490000326 }, "harness|hellaswag|10": { "acc": 0.657837084246166, "acc_stderr": 0.004734642167493353, "acc_norm": 0.8455486954789883, "acc_norm_stderr": 0.003606422623639926 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.04793724854411021, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411021 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5925925925925926, "acc_stderr": 0.04244633238353228, "acc_norm": 0.5925925925925926, "acc_norm_stderr": 0.04244633238353228 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6052631578947368, "acc_stderr": 0.039777499346220734, "acc_norm": 0.6052631578947368, "acc_norm_stderr": 0.039777499346220734 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6830188679245283, "acc_stderr": 0.028637235639800893, "acc_norm": 0.6830188679245283, "acc_norm_stderr": 0.028637235639800893 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6805555555555556, "acc_stderr": 0.038990736873573344, "acc_norm": 0.6805555555555556, "acc_norm_stderr": 0.038990736873573344 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5780346820809249, "acc_stderr": 0.0376574669386515, "acc_norm": 0.5780346820809249, "acc_norm_stderr": 0.0376574669386515 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4411764705882353, "acc_stderr": 0.049406356306056595, "acc_norm": 0.4411764705882353, "acc_norm_stderr": 0.049406356306056595 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.72, "acc_stderr": 0.04512608598542128, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5319148936170213, "acc_stderr": 0.03261936918467382, "acc_norm": 0.5319148936170213, "acc_norm_stderr": 0.03261936918467382 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4298245614035088, "acc_stderr": 0.04657047260594963, "acc_norm": 0.4298245614035088, "acc_norm_stderr": 0.04657047260594963 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5793103448275863, "acc_stderr": 0.0411391498118926, "acc_norm": 0.5793103448275863, "acc_norm_stderr": 0.0411391498118926 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3835978835978836, "acc_stderr": 0.025043757318520193, "acc_norm": 0.3835978835978836, "acc_norm_stderr": 0.025043757318520193 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3888888888888889, "acc_stderr": 0.04360314860077459, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.04360314860077459 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.667741935483871, "acc_stderr": 0.0267955608481228, "acc_norm": 0.667741935483871, "acc_norm_stderr": 0.0267955608481228 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5123152709359606, "acc_stderr": 0.035169204442208966, "acc_norm": 0.5123152709359606, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.63, "acc_stderr": 0.04852365870939099, "acc_norm": 0.63, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7393939393939394, "acc_stderr": 0.034277431758165236, "acc_norm": 0.7393939393939394, "acc_norm_stderr": 0.034277431758165236 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7373737373737373, "acc_stderr": 0.031353050095330855, "acc_norm": 0.7373737373737373, "acc_norm_stderr": 0.031353050095330855 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.844559585492228, "acc_stderr": 0.026148483469153314, "acc_norm": 0.844559585492228, "acc_norm_stderr": 0.026148483469153314 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.558974358974359, "acc_stderr": 0.025174048384000745, "acc_norm": 0.558974358974359, "acc_norm_stderr": 0.025174048384000745 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.0287
