open-llm-leaderboard/details_oh-yeontaek__llama-2-70B-LoRA-assemble-v3

该数据集是在模型 oh-yeontaek/llama-2-70B-LoRA-assemble-v3 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集由 61 个配置组成，每个配置对应一个被评估的任务。数据集是从一次或多次运行中生成的，每次运行在每个配置中表示为特定的拆分，train 拆分始终指向最新的结果。此外，还有一个 results 配置，用于存储所有运行的聚合结果，这些结果用于计算和显示 Open LLM Leaderboard 上的聚合指标。README 还提供了如何使用 Hugging Face datasets 库加载数据集的示例。

This dataset was automatically created during the evaluation run of the model oh-yeontaek/llama-2-70B-LoRA-assemble-v3 on the Open LLM Leaderboard. The dataset consists of 61 configurations, each corresponding to one evaluated task. The dataset is generated from one or multiple runs, where each run is represented as a specific split under each configuration, and the `train` split always points to the most recent results. In addition, there is a `results` configuration used to store the aggregated results from all runs, which are utilized to calculate and display the aggregate metrics on the Open LLM Leaderboard. The README also provides examples of how to load the dataset using the Hugging Face datasets library.

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 oh-yeontaek/llama-2-70B-LoRA-assemble-v3 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。

数据集组成

• 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。

最新结果

以下是 2023-09-15T17:36:30.757691 运行的最新结果：

python { "all": { "acc": 0.6985803552112708, "acc_stderr": 0.03118492094070661, "acc_norm": 0.7024274155828159, "acc_norm_stderr": 0.031154550420018332, "mc1": 0.47980416156670747, "mc1_stderr": 0.01748921684973705, "mc2": 0.658093697491632, "mc2_stderr": 0.014747866760131165 }, "harness|arc:challenge|25": { "acc": 0.6860068259385665, "acc_stderr": 0.013562691224726291, "acc_norm": 0.7209897610921502, "acc_norm_stderr": 0.013106784883601334 }, "harness|hellaswag|10": { "acc": 0.6820354511053575, "acc_stderr": 0.004647338877642188, "acc_norm": 0.8740290778729337, "acc_norm_stderr": 0.0033113844981586464 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6370370370370371, "acc_stderr": 0.041539484047424, "acc_norm": 0.6370370370370371, "acc_norm_stderr": 0.041539484047424 }, "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": 0.76, "acc_stderr": 0.04292346959909284, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7547169811320755, "acc_stderr": 0.026480357179895695, "acc_norm": 0.7547169811320755, "acc_norm_stderr": 0.026480357179895695 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8194444444444444, "acc_stderr": 0.03216600808802267, "acc_norm": 0.8194444444444444, "acc_norm_stderr": 0.03216600808802267 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.62, "acc_stderr": 0.04878317312145632, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145632 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "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": 0.3431372549019608, "acc_stderr": 0.04724007352383888, "acc_norm": 0.3431372549019608, "acc_norm_stderr": 0.04724007352383888 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.04408440022768078, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.676595744680851, "acc_stderr": 0.03057944277361034, "acc_norm": 0.676595744680851, "acc_norm_stderr": 0.03057944277361034 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4649122807017544, "acc_stderr": 0.04692008381368909, "acc_norm": 0.4649122807017544, "acc_norm_stderr": 0.04692008381368909 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6413793103448275, "acc_stderr": 0.03996629574876719, "acc_norm": 0.6413793103448275, "acc_norm_stderr": 0.03996629574876719 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.47354497354497355, "acc_stderr": 0.025715239811346758, "acc_norm": 0.47354497354497355, "acc_norm_stderr": 0.025715239811346758 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.49206349206349204, "acc_stderr": 0.044715725362943486, "acc_norm": 0.49206349206349204, "acc_norm_stderr": 0.044715725362943486 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "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": 0.541871921182266, "acc_stderr": 0.03505630140785741, "acc_norm": 0.541871921182266, "acc_norm_stderr": 0.03505630140785741 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8484848484848485, "acc_stderr": 0.027998073798781675, "acc_norm": 0.8484848484848485, "acc_norm_stderr": 0.027998073798781675 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8888888888888888, "acc_stderr": 0.022390787638216763, "acc_norm": 0.8888888888888888, "acc_norm_stderr": 0.022390787638216763 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.927461139896373, "acc_stderr": 0.018718998520678178, "acc_norm": 0.927461139896373, "acc_norm_stderr": 0.018718998520678178 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6974358974358974, "acc_stderr": 0.02329088805377272, "acc_norm": 0.6974358974358974, "acc_norm_stderr": 0.02329088805377272 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32592592592592595, "acc_stderr": 0.028578348365473072, "acc_norm": 0.32592592592592595, "acc_norm_stderr": 0.028578348365473072 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.773109243697479, "acc_stderr