open-llm-leaderboard-old/details_AIGym__TinyLlama-1.1B-2.5T-chat-and-function-calling
收藏数据集概述
数据集简介
该数据集是在模型 AIGym/TinyLlama-1.1B-2.5T-chat-and-function-calling 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 数据来源：数据集由1次运行创建，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。
- 分割类型：每个配置包含多个分割，其中“train”分割指向最新的结果。
- 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_AIGym__TinyLlama-1.1B-2.5T-chat-and-function-calling", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-04T23:43:15.860527 运行的最新结果：
python { "all": { "acc": 0.26912346478859156, "acc_stderr": 0.03120091714101033, "acc_norm": 0.27025742576226947, "acc_norm_stderr": 0.03196861086820363, "mc1": 0.22766217870257038, "mc1_stderr": 0.01467925503211107, "mc2": 0.38916106981756643, "mc2_stderr": 0.014160770891106955 }, "harness|arc:challenge|25": { "acc": 0.32337883959044367, "acc_stderr": 0.013669421630012136, "acc_norm": 0.3438566552901024, "acc_norm_stderr": 0.013880644570156217 }, "harness|hellaswag|10": { "acc": 0.4509061939852619, "acc_stderr": 0.004965670398127352, "acc_norm": 0.5960963951404102, "acc_norm_stderr": 0.004896757857022549 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.041633319989322716, "acc_norm": 0.22, "acc_norm_stderr": 0.041633319989322716 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.26666666666666666, "acc_stderr": 0.038201699145179055, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.038201699145179055 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.21052631578947367, "acc_stderr": 0.03317672787533157, "acc_norm": 0.21052631578947367, "acc_norm_stderr": 0.03317672787533157 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.23, "acc_stderr": 0.042295258468165065, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165065 }, "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": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2023121387283237, "acc_stderr": 0.03063114553919882, "acc_norm": 0.2023121387283237, "acc_norm_stderr": 0.03063114553919882 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.23529411764705882, "acc_stderr": 0.04220773659171452, "acc_norm": 0.23529411764705882, "acc_norm_stderr": 0.04220773659171452 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.26, "acc_stderr": 0.04408440022768078, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.31063829787234043, "acc_stderr": 0.03025123757921317, "acc_norm": 0.31063829787234043, "acc_norm_stderr": 0.03025123757921317 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2719298245614035, "acc_stderr": 0.04185774424022056, "acc_norm": 0.2719298245614035, "acc_norm_stderr": 0.04185774424022056 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2413793103448276, "acc_stderr": 0.03565998174135302, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03565998174135302 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.26455026455026454, "acc_stderr": 0.022717467897708614, "acc_norm": 0.26455026455026454, "acc_norm_stderr": 0.022717467897708614 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.23015873015873015, "acc_stderr": 0.03764950879790606, "acc_norm": 0.23015873015873015, "acc_norm_stderr": 0.03764950879790606 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.29, "acc_stderr": 0.04560480215720683, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720683 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.25483870967741934, "acc_stderr": 0.024790118459332208, "acc_norm": 0.25483870967741934, "acc_norm_stderr": 0.024790118459332208 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.24630541871921183, "acc_stderr": 0.03031509928561773, "acc_norm": 0.24630541871921183, "acc_norm_stderr": 0.03031509928561773 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.32727272727272727, "acc_stderr": 0.036639749943912434, "acc_norm": 0.32727272727272727, "acc_norm_stderr": 0.036639749943912434 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.25252525252525254, "acc_stderr": 0.030954055470365914, "acc_norm": 0.25252525252525254, "acc_norm_stderr": 0.030954055470365914 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.27461139896373055, "acc_stderr": 0.03221024508041156, "acc_norm": 0.27461139896373055, "acc_norm_stderr": 0.03221024508041156 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.31025641025641026, "acc_stderr": 0.02345467488940429, "acc_norm": 0.31025641025641026, "acc_norm_stderr": 0.02345467488940429 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc
