open-llm-leaderboard-old/details_AIGym__TinyLlama-1.1B-2.5T-chat
收藏数据集概述
数据集摘要
该数据集是在模型 AIGym/TinyLlama-1.1B-2.5T-chat 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，每个运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。
- "train" 分片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。
最新结果
以下是 2024-02-03T15:30:41.915912 运行的最新结果：
python { "all": { "acc": 0.27000171868537254, "acc_stderr": 0.031271197448198736, "acc_norm": 0.2714719344502093, "acc_norm_stderr": 0.032051933008136725, "mc1": 0.23133414932680538, "mc1_stderr": 0.014761945174862666, "mc2": 0.3879515338680291, "mc2_stderr": 0.014081119436170311 }, "harness|arc:challenge|25": { "acc": 0.32337883959044367, "acc_stderr": 0.013669421630012132, "acc_norm": 0.3447098976109215, "acc_norm_stderr": 0.01388881628678211 }, "harness|hellaswag|10": { "acc": 0.4502091216889066, "acc_stderr": 0.004964979120927575, "acc_norm": 0.5970922127066322, "acc_norm_stderr": 0.004894801119898594 }, "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": 0.2222222222222222, "acc_stderr": 0.03591444084196968, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.03591444084196968 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.031103182383123398, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.031103182383123398 }, "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": 0.2708333333333333, "acc_stderr": 0.03716177437566016, "acc_norm": 0.2708333333333333, "acc_norm_stderr": 0.03716177437566016 }, "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": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "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": 0.2138728323699422, "acc_stderr": 0.03126511206173043, "acc_norm": 0.2138728323699422, "acc_norm_stderr": 0.03126511206173043 }, "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": 0.24, "acc_stderr": 0.042923469599092816, "acc_norm": 0.24, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.30638297872340425, "acc_stderr": 0.030135906478517563, "acc_norm": 0.30638297872340425, "acc_norm_stderr": 0.030135906478517563 }, "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": 0.2206896551724138, "acc_stderr": 0.034559302019248124, "acc_norm": 0.2206896551724138, "acc_norm_stderr": 0.034559302019248124 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.291005291005291, "acc_stderr": 0.02339382650048488, "acc_norm": 0.291005291005291, "acc_norm_stderr": 0.02339382650048488 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.20634920634920634, "acc_stderr": 0.03619604524124251, "acc_norm": 0.20634920634920634, "acc_norm_stderr": 0.03619604524124251 }, "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": 0.24193548387096775, "acc_stderr": 0.024362599693031093, "acc_norm": 0.24193548387096775, "acc_norm_stderr": 0.024362599693031093 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2561576354679803, "acc_stderr": 0.0307127300709826, "acc_norm": 0.2561576354679803, "acc_norm_stderr": 0.0307127300709826 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.32, "acc_stderr": 0.04688261722621504, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2909090909090909, "acc_stderr": 0.03546563019624336, "acc_norm": 0.2909090909090909, "acc_norm_stderr": 0.03546563019624336 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.22727272727272727, "acc_stderr": 0.029857515673386407, "acc_norm": 0.22727272727272727, "acc_norm_stderr": 0.029857515673386407 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.26424870466321243, "acc_stderr": 0.03182155050916648, "acc_norm": 0.26424870466321243, "acc_norm_stderr": 0.03182155050916648 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2794871794871795, "acc_stderr": 0.022752388839776826, "acc_norm": 0.2794871794871795, "acc_norm_stderr": 0.022752388839776826 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24444444444444444, "acc_stderr": 0.02620276653465215, "acc_norm": 0.24444444444444444, "acc_norm_stderr": 0.02620276653465215 }, "harness|hendrycksTest-high_
