open-llm-leaderboard-old/details_martyn__llama-megamerge-dare-13b
收藏数据集概述
数据集简介
该数据集是在模型martyn/llama-megamerge-dare-13b在Open LLM Leaderboard上的评估运行期间自动创建的。
数据集组成
数据集由63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片，分片名称使用运行的时间戳。"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_martyn__llama-megamerge-dare-13b", "harness_winogrande_5", split="train")
最新结果
以下是2023-12-13T12:51:07.798960运行的最新结果：
python { "all": { "acc": 0.5501426946833134, "acc_stderr": 0.033816613061950815, "acc_norm": 0.5548026687947745, "acc_norm_stderr": 0.0345287472758958, "mc1": 0.3243574051407589, "mc1_stderr": 0.01638797677964794, "mc2": 0.4575555939890639, "mc2_stderr": 0.015024821972393557 }, "harness|arc:challenge|25": { "acc": 0.575938566552901, "acc_stderr": 0.014441889627464396, "acc_norm": 0.60580204778157, "acc_norm_stderr": 0.014280522667467325 }, "harness|hellaswag|10": { "acc": 0.6385182234614618, "acc_stderr": 0.004794478426382609, "acc_norm": 0.8300139414459271, "acc_norm_stderr": 0.0037485288878381204 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5037037037037037, "acc_stderr": 0.04319223625811331, "acc_norm": 0.5037037037037037, "acc_norm_stderr": 0.04319223625811331 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5394736842105263, "acc_stderr": 0.04056242252249034, "acc_norm": 0.5394736842105263, "acc_norm_stderr": 0.04056242252249034 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6113207547169811, "acc_stderr": 0.030000485448675986, "acc_norm": 0.6113207547169811, "acc_norm_stderr": 0.030000485448675986 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5902777777777778, "acc_stderr": 0.04112490974670787, "acc_norm": 0.5902777777777778, "acc_norm_stderr": 0.04112490974670787 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.04688261722621505, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5144508670520231, "acc_stderr": 0.03810871630454764, "acc_norm": 0.5144508670520231, "acc_norm_stderr": 0.03810871630454764 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.30392156862745096, "acc_stderr": 0.045766654032077615, "acc_norm": 0.30392156862745096, "acc_norm_stderr": 0.045766654032077615 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4553191489361702, "acc_stderr": 0.03255525359340355, "acc_norm": 0.4553191489361702, "acc_norm_stderr": 0.03255525359340355 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.35964912280701755, "acc_stderr": 0.045144961328736334, "acc_norm": 0.35964912280701755, "acc_norm_stderr": 0.045144961328736334 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.503448275862069, "acc_stderr": 0.04166567577101579, "acc_norm": 0.503448275862069, "acc_norm_stderr": 0.04166567577101579 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3492063492063492, "acc_stderr": 0.024552292209342654, "acc_norm": 0.3492063492063492, "acc_norm_stderr": 0.024552292209342654 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2857142857142857, "acc_stderr": 0.0404061017820884, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.0404061017820884 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6193548387096774, "acc_stderr": 0.027621717832907032, "acc_norm": 0.6193548387096774, "acc_norm_stderr": 0.027621717832907032 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4088669950738916, "acc_stderr": 0.034590588158832314, "acc_norm": 0.4088669950738916, "acc_norm_stderr": 0.034590588158832314 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.56, "acc_stderr": 0.049888765156985884, "acc_norm": 0.56, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6787878787878788, "acc_stderr": 0.0364620496325381, "acc_norm": 0.6787878787878788, "acc_norm_stderr": 0.0364620496325381 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7424242424242424, "acc_stderr": 0.03115626951964683, "acc_norm": 0.7424242424242424, "acc_norm_stderr": 0.03115626951964683 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7927461139896373, "acc_stderr": 0.02925282329180363, "acc_norm": 0.7927461139896373, "acc_norm_stderr": 0.02925282329180363 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5025641025641026, "acc_stderr": 0.025350672979412195, "acc_norm": 0.5025641025641026, "acc_norm_stderr": 0.025350672979412195 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2814814814814815, "acc_stderr": 0.02742001935094528, "acc_norm": 0.2814814814814815, "acc_norm_stderr
