open-llm-leaderboard-old/details_TinyLlama__TinyLlama-1.1B-intermediate-step-1195k-token-2.5T
收藏数据集概述
数据集简介
该数据集是在对模型 TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T 进行评估运行期间自动创建的。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
- 数据来源：1 次运行（每个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）
- 分割：每个配置包含多个分割，其中 "train" 分割指向最新的结果
- 额外配置："results" 配置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_TinyLlama__TinyLlama-1.1B-intermediate-step-1195k-token-2.5T", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-12T02:53:47.167196 运行的最新结果：
python { "all": { "acc": 0.2675448542417715, "acc_stderr": 0.03118011664128985, "acc_norm": 0.2690761116467705, "acc_norm_stderr": 0.03195175927273723, "mc1": 0.20930232558139536, "mc1_stderr": 0.014241219434785828, "mc2": 0.3678523017186956, "mc2_stderr": 0.013764237138063459 }, "harness|arc:challenge|25": { "acc": 0.31143344709897613, "acc_stderr": 0.013532472099850942, "acc_norm": 0.33532423208191126, "acc_norm_stderr": 0.013796182947785562 }, "harness|hellaswag|10": { "acc": 0.4458275243975304, "acc_stderr": 0.004960408362133243, "acc_norm": 0.5938060147381, "acc_norm_stderr": 0.00490117891790085 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.26666666666666666, "acc_stderr": 0.03820169914517905, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.03820169914517905 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.1513157894736842, "acc_stderr": 0.029162631596843975, "acc_norm": 0.1513157894736842, "acc_norm_stderr": 0.029162631596843975 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2641509433962264, "acc_stderr": 0.02713429162874171, "acc_norm": 0.2641509433962264, "acc_norm_stderr": 0.02713429162874171 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2222222222222222, "acc_stderr": 0.03476590104304134, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.03476590104304134 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.23699421965317918, "acc_stderr": 0.03242414757483098, "acc_norm": 0.23699421965317918, "acc_norm_stderr": 0.03242414757483098 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237656, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237656 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.23, "acc_stderr": 0.042295258468165065, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2936170212765957, "acc_stderr": 0.029771642712491227, "acc_norm": 0.2936170212765957, "acc_norm_stderr": 0.029771642712491227 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2543859649122807, "acc_stderr": 0.04096985139843672, "acc_norm": 0.2543859649122807, "acc_norm_stderr": 0.04096985139843672 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2413793103448276, "acc_stderr": 0.03565998174135303, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03565998174135303 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2777777777777778, "acc_stderr": 0.023068188848261114, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.023068188848261114 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2222222222222222, "acc_stderr": 0.037184890068181146, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.037184890068181146 }, "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": 0.2161290322580645, "acc_stderr": 0.02341529343356852, "acc_norm": 0.2161290322580645, "acc_norm_stderr": 0.02341529343356852 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2512315270935961, "acc_stderr": 0.030516530732694433, "acc_norm": 0.2512315270935961, "acc_norm_stderr": 0.030516530732694433 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.26, "acc_stderr": 0.044084400227680794, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2727272727272727, "acc_stderr": 0.03477691162163659, "acc_norm": 0.2727272727272727, "acc_norm_stderr": 0.03477691162163659 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2222222222222222, "acc_stderr": 0.02962022787479049, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.02962022787479049 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.23834196891191708, "acc_stderr": 0.03074890536390988, "acc_norm": 0.23834196891191708, "acc_norm_stderr": 0.03074890536390988 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.28205128205128205, "acc_stderr": 0.0228158130988966, "acc_norm": 0.28205128205128205, "acc_norm_stderr": 0.0228158130988966 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24074074074074073, "acc_stderr": 0.0260
