open-llm-leaderboard-old/details_tricktreat__Llama-2-7b-chat-hf-guanaco-freeze-embed-tokens-q-v-proj
收藏数据集概述
数据集摘要
该数据集是在评估模型tricktreat/Llama-2-7b-chat-hf-guanaco-freeze-embed-tokens-q-v-proj在Open LLM Leaderboard上的运行过程中自动创建的。
数据集组成
- 该数据集包含63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。
- 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_tricktreat__Llama-2-7b-chat-hf-guanaco-freeze-embed-tokens-q-v-proj", "harness_winogrande_5", split="train")
最新结果
以下是2024-04-16T04:02:45.165972运行的最新结果：
python { "all": { "acc": 0.47119617088878807, "acc_stderr": 0.03446747326117775, "acc_norm": 0.47711994927683626, "acc_norm_stderr": 0.035254004485849776, "mc1": 0.29008567931456547, "mc1_stderr": 0.01588623687420952, "mc2": 0.4315330091327328, "mc2_stderr": 0.015209088465437729 }, "harness|arc:challenge|25": { "acc": 0.48208191126279865, "acc_stderr": 0.014602005585490978, "acc_norm": 0.514505119453925, "acc_norm_stderr": 0.014605241081370056 }, "harness|hellaswag|10": { "acc": 0.5862378012348137, "acc_stderr": 0.00491500349951783, "acc_norm": 0.7698665604461262, "acc_norm_stderr": 0.004200578535056529 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.37777777777777777, "acc_stderr": 0.04188307537595853, "acc_norm": 0.37777777777777777, "acc_norm_stderr": 0.04188307537595853 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.46710526315789475, "acc_stderr": 0.040601270352363966, "acc_norm": 0.46710526315789475, "acc_norm_stderr": 0.040601270352363966 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.45, "acc_stderr": 0.049999999999999996, "acc_norm": 0.45, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.4490566037735849, "acc_stderr": 0.030612730713641092, "acc_norm": 0.4490566037735849, "acc_norm_stderr": 0.030612730713641092 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5, "acc_stderr": 0.04181210050035455, "acc_norm": 0.5, "acc_norm_stderr": 0.04181210050035455 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4161849710982659, "acc_stderr": 0.03758517775404947, "acc_norm": 0.4161849710982659, "acc_norm_stderr": 0.03758517775404947 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.27450980392156865, "acc_stderr": 0.04440521906179327, "acc_norm": 0.27450980392156865, "acc_norm_stderr": 0.04440521906179327 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.43829787234042555, "acc_stderr": 0.03243618636108101, "acc_norm": 0.43829787234042555, "acc_norm_stderr": 0.03243618636108101 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.30701754385964913, "acc_stderr": 0.043391383225798615, "acc_norm": 0.30701754385964913, "acc_norm_stderr": 0.043391383225798615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4206896551724138, "acc_stderr": 0.0411391498118926, "acc_norm": 0.4206896551724138, "acc_norm_stderr": 0.0411391498118926 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.28835978835978837, "acc_stderr": 0.023330654054535892, "acc_norm": 0.28835978835978837, "acc_norm_stderr": 0.023330654054535892 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.23809523809523808, "acc_stderr": 0.03809523809523812, "acc_norm": 0.23809523809523808, "acc_norm_stderr": 0.03809523809523812 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5225806451612903, "acc_stderr": 0.028414985019707868, "acc_norm": 0.5225806451612903, "acc_norm_stderr": 0.028414985019707868 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3793103448275862, "acc_stderr": 0.034139638059062345, "acc_norm": 0.3793103448275862, "acc_norm_stderr": 0.034139638059062345 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.44, "acc_stderr": 0.049888765156985884, "acc_norm": 0.44, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5757575757575758, "acc_stderr": 0.03859268142070264, "acc_norm": 0.5757575757575758, "acc_norm_stderr": 0.03859268142070264 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5808080808080808, "acc_stderr": 0.03515520728670417, "acc_norm": 0.5808080808080808, "acc_norm_stderr": 0.03515520728670417 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7150259067357513, "acc_stderr": 0.032577140777096614, "acc_norm": 0.7150259067357513, "acc_norm_stderr": 0.032577140777096614 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4641025641025641, "acc_stderr": 0.025285585990017838, "acc_norm": 0.4641025641025641, "acc_norm_stderr": 0.025285585990017838 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26666666666666666, "acc_stderr": 0.026962
