open-llm-leaderboard/details_AGI-inc__lora_moe_7b_baseline

该数据集是在模型[AGI-inc/lora_moe_7b_baseline](https://huggingface.co/AGI-inc/lora_moe_7b_baseline)评估运行期间自动创建的，用于[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)。数据集由61个配置组成，每个配置对应一个评估任务。数据集来源于一次运行，每次运行作为一个特定分割，以运行的时间戳命名。train分割始终指向最新结果，而额外的results配置存储了运行的聚合结果，用于在Leaderboard上计算和显示聚合指标。

原始信息汇总

数据集概述

数据集摘要

该数据集是在对模型 AGI-inc/lora_moe_7b_baseline 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。

数据集组成

• 该数据集包含 61 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" 分割始终指向最新的结果。
• 额外的 "results" 配置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_AGI-inc__lora_moe_7b_baseline", "harness_truthfulqa_mc_0", split="train")

最新结果

以下是 2023-07-24T11:38:46.147581 运行的最新结果：

python { "all": { "acc": 0.3624349655819883, "acc_stderr": 0.03457932037185986, "acc_norm": 0.36641755034742307, "acc_norm_stderr": 0.03456622803809125, "mc1": 0.22031823745410037, "mc1_stderr": 0.014509045171487291, "mc2": 0.3433554241758255, "mc2_stderr": 0.01319092242364727 }, "harness|arc:challenge|25": { "acc": 0.47696245733788395, "acc_stderr": 0.014595873205358267, "acc_norm": 0.5093856655290102, "acc_norm_stderr": 0.014608816322065 }, "harness|hellaswag|10": { "acc": 0.5754829715196176, "acc_stderr": 0.004932593348813628, "acc_norm": 0.7780322644891456, "acc_norm_stderr": 0.004147202539759587 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.04408440022768081, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768081 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3851851851851852, "acc_stderr": 0.042039210401562783, "acc_norm": 0.3851851851851852, "acc_norm_stderr": 0.042039210401562783 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.34210526315789475, "acc_stderr": 0.03860731599316092, "acc_norm": 0.34210526315789475, "acc_norm_stderr": 0.03860731599316092 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.3622641509433962, "acc_stderr": 0.0295822451283843, "acc_norm": 0.3622641509433962, "acc_norm_stderr": 0.0295822451283843 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3819444444444444, "acc_stderr": 0.040629907841466674, "acc_norm": 0.3819444444444444, "acc_norm_stderr": 0.040629907841466674 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3236994219653179, "acc_stderr": 0.035676037996391685, "acc_norm": 0.3236994219653179, "acc_norm_stderr": 0.035676037996391685 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.23529411764705882, "acc_stderr": 0.04220773659171451, "acc_norm": 0.23529411764705882, "acc_norm_stderr": 0.04220773659171451 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.37446808510638296, "acc_stderr": 0.03163910665367291, "acc_norm": 0.37446808510638296, "acc_norm_stderr": 0.03163910665367291 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.04142439719489362, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.04142439719489362 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.22758620689655173, "acc_stderr": 0.03493950380131184, "acc_norm": 0.22758620689655173, "acc_norm_stderr": 0.03493950380131184 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2619047619047619, "acc_stderr": 0.022644212615525214, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.022644212615525214 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.25396825396825395, "acc_stderr": 0.038932596106046734, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.038932596106046734 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.33548387096774196, "acc_stderr": 0.02686020644472435, "acc_norm": 0.33548387096774196, "acc_norm_stderr": 0.02686020644472435 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2857142857142857, "acc_stderr": 0.031785297106427496, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.031785297106427496 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.43636363636363634, "acc_stderr": 0.03872592983524754, "acc_norm": 0.43636363636363634, "acc_norm_stderr": 0.03872592983524754 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.3333333333333333, "acc_stderr": 0.03358618145732522, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.03358618145732522 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.45077720207253885, "acc_stderr": 0.03590910952235525, "acc_norm": 0.45077720207253885, "acc_norm_stderr": 0.03590910952235525 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.34102564102564104, "acc_stderr": 0.024035489676335065, "acc_norm": 0.34102564102564104, "acc_norm_stderr": 0.024035489676335065 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.25925925925925924, "acc_stderr": 0.026719240783712173, "acc_norm": 0.25925925925925924, "acc_norm_stderr":