open-llm-leaderboard-old/details_abacusai__Smaug-34B-v0.1
收藏数据集概述
数据集简介
该数据集是在评估模型 abacusai/Smaug-34B-v0.1 在 Open LLM Leaderboard 上的自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
- 配置数量：63 个配置
- 数据来源：从 1 次运行中创建
- 数据分割：每个配置包含特定分割，分割名称使用运行的时间戳。"train" 分割始终指向最新结果。
- 结果汇总：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_abacusai__Smaug-34B-v0.1", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-28T00:47:50.241075 运行的最新结果：
python { "all": { "acc": 0.764755210936867, "acc_stderr": 0.02827091348156039, "acc_norm": 0.7679456916750921, "acc_norm_stderr": 0.02881630413388168, "mc1": 0.5299877600979193, "mc1_stderr": 0.017471992091697534, "mc2": 0.7022329988948236, "mc2_stderr": 0.014217101642120922 }, "harness|arc:challenge|25": { "acc": 0.7209897610921502, "acc_stderr": 0.013106784883601341, "acc_norm": 0.742320819112628, "acc_norm_stderr": 0.012780770562768412 }, "harness|hellaswag|10": { "acc": 0.6717785301732723, "acc_stderr": 0.0046860624211581495, "acc_norm": 0.8675562636924915, "acc_norm_stderr": 0.003382797907523026 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.49, "acc_stderr": 0.05024183937956911, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7407407407407407, "acc_stderr": 0.03785714465066653, "acc_norm": 0.7407407407407407, "acc_norm_stderr": 0.03785714465066653 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.881578947368421, "acc_stderr": 0.02629399585547494, "acc_norm": 0.881578947368421, "acc_norm_stderr": 0.02629399585547494 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.77, "acc_stderr": 0.04229525846816505, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8037735849056604, "acc_stderr": 0.024442388131100813, "acc_norm": 0.8037735849056604, "acc_norm_stderr": 0.024442388131100813 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9166666666666666, "acc_stderr": 0.023112508176051236, "acc_norm": 0.9166666666666666, "acc_norm_stderr": 0.023112508176051236 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7225433526011561, "acc_stderr": 0.034140140070440354, "acc_norm": 0.7225433526011561, "acc_norm_stderr": 0.034140140070440354 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5392156862745098, "acc_stderr": 0.04959859966384181, "acc_norm": 0.5392156862745098, "acc_norm_stderr": 0.04959859966384181 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.79, "acc_stderr": 0.04093601807403326, "acc_norm": 0.79, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7702127659574468, "acc_stderr": 0.027501752944412417, "acc_norm": 0.7702127659574468, "acc_norm_stderr": 0.027501752944412417 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5789473684210527, "acc_stderr": 0.046446020912223177, "acc_norm": 0.5789473684210527, "acc_norm_stderr": 0.046446020912223177 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7586206896551724, "acc_stderr": 0.03565998174135302, "acc_norm": 0.7586206896551724, "acc_norm_stderr": 0.03565998174135302 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.7354497354497355, "acc_stderr": 0.022717467897708614, "acc_norm": 0.7354497354497355, "acc_norm_stderr": 0.022717467897708614 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5476190476190477, "acc_stderr": 0.044518079590553275, "acc_norm": 0.5476190476190477, "acc_norm_stderr": 0.044518079590553275 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9064516129032258, "acc_stderr": 0.016565754668270982, "acc_norm": 0.9064516129032258, "acc_norm_stderr": 0.016565754668270982 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6798029556650246, "acc_stderr": 0.03282649385304151, "acc_norm": 0.6798029556650246, "acc_norm_stderr": 0.03282649385304151 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.77, "acc_stderr": 0.042295258468165044, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8727272727272727, "acc_stderr": 0.02602465765165619, "acc_norm": 0.8727272727272727, "acc_norm_stderr": 0.02602465765165619 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9292929292929293, "acc_stderr": 0.018263105420199488, "acc_norm": 0.9292929292929293, "acc_norm_stderr": 0.018263105420199488 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9792746113989638, "acc_stderr": 0.010281417011909025, "acc_norm": 0.9792746113989638, "acc_norm_stderr": 0.010281417011909025 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8128205128205128, "acc_stderr": 0.019776601086550036, "acc_norm": 0.8128205128205128, "acc_norm_stderr": 0.019776601086550036 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.44814814814814813, "acc_stderr": 0.030321167196316293, "acc
