open-llm-leaderboard-old/details_Mihaiii__Pallas-0.4
收藏数据集概述
该数据集是在对模型 Mihaiii/Pallas-0.4 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
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 2 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_Mihaiii__Pallas-0.4", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-24T22:40:47.293518 运行的最新结果：
python { "all": { "acc": 0.7456868749897599, "acc_stderr": 0.0291121349888231, "acc_norm": 0.7505483434369399, "acc_norm_stderr": 0.029662136004319276, "mc1": 0.42717258261933905, "mc1_stderr": 0.017316834410963933, "mc2": 0.5729286090488297, "mc2_stderr": 0.015803191112374947 }, "harness|arc:challenge|25": { "acc": 0.6203071672354948, "acc_stderr": 0.014182119866974872, "acc_norm": 0.636518771331058, "acc_norm_stderr": 0.014056207319068283 }, "harness|hellaswag|10": { "acc": 0.6451902011551484, "acc_stderr": 0.004774778180345196, "acc_norm": 0.8330013941445927, "acc_norm_stderr": 0.003722123709610458 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7037037037037037, "acc_stderr": 0.03944624162501116, "acc_norm": 0.7037037037037037, "acc_norm_stderr": 0.03944624162501116 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8618421052631579, "acc_stderr": 0.028081042939576552, "acc_norm": 0.8618421052631579, "acc_norm_stderr": 0.028081042939576552 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.77, "acc_stderr": 0.042295258468165044, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8037735849056604, "acc_stderr": 0.024442388131100824, "acc_norm": 0.8037735849056604, "acc_norm_stderr": 0.024442388131100824 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8611111111111112, "acc_stderr": 0.0289198029561349, "acc_norm": 0.8611111111111112, "acc_norm_stderr": 0.0289198029561349 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.64, "acc_stderr": 0.048241815132442176, "acc_norm": 0.64, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7341040462427746, "acc_stderr": 0.03368762932259431, "acc_norm": 0.7341040462427746, "acc_norm_stderr": 0.03368762932259431 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5784313725490197, "acc_stderr": 0.04913595201274504, "acc_norm": 0.5784313725490197, "acc_norm_stderr": 0.04913595201274504 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.8, "acc_stderr": 0.04020151261036845, "acc_norm": 0.8, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7702127659574468, "acc_stderr": 0.02750175294441242, "acc_norm": 0.7702127659574468, "acc_norm_stderr": 0.02750175294441242 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5877192982456141, "acc_stderr": 0.04630653203366596, "acc_norm": 0.5877192982456141, "acc_norm_stderr": 0.04630653203366596 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7034482758620689, "acc_stderr": 0.03806142687309993, "acc_norm": 0.7034482758620689, "acc_norm_stderr": 0.03806142687309993 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6851851851851852, "acc_stderr": 0.023919984164047736, "acc_norm": 0.6851851851851852, "acc_norm_stderr": 0.023919984164047736 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5714285714285714, "acc_stderr": 0.04426266681379909, "acc_norm": 0.5714285714285714, "acc_norm_stderr": 0.04426266681379909 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.896774193548387, "acc_stderr": 0.017308381281034516, "acc_norm": 0.896774193548387, "acc_norm_stderr": 0.017308381281034516 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6748768472906403, "acc_stderr": 0.032957975663112704, "acc_norm": 0.6748768472906403, "acc_norm_stderr": 0.032957975663112704 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.84, "acc_stderr": 0.03684529491774709, "acc_norm": 0.84, "acc_norm_stderr": 0.03684529491774709 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8424242424242424, "acc_stderr": 0.028450388805284332, "acc_norm": 0.8424242424242424, "acc_norm_stderr": 0.028450388805284332 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9090909090909091, "acc_stderr": 0.020482086775424218, "acc_norm": 0.9090909090909091, "acc_norm_stderr": 0.020482086775424218 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9689119170984456, "acc_stderr": 0.012525310625527041, "acc_norm": 0.9689119170984456, "acc_norm_stderr": 0.012525310625527041 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7897435897435897, "acc_stderr": 0.02066059748502692, "acc_norm": 0.7897435897435897, "acc_norm_stderr": 0.02066059748502692 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.43703703703703706, "acc_stderr": 0.030242862397654002, "acc_norm": 0.43703703703703706, "acc_norm_stderr": 0.030242862397654002 }, "harness|hendrycksTest-high_school_microeconomics|
