open-llm-leaderboard-old/details_migtissera__Tess-34B-v1.4
收藏数据集概述
数据集描述
该数据集是在对模型 migtissera/Tess-34B-v1.4 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 1 次运行中创建，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。
- "train" 分割始终指向最新的结果。
- 额外的 "results" 配置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_migtissera__Tess-34B-v1.4", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-08T21:42:14.185157 运行的最新结果：
python { "all": { "acc": 0.744827149985735, "acc_stderr": 0.029006208191077444, "acc_norm": 0.7498384630409163, "acc_norm_stderr": 0.02955308381117489, "mc1": 0.412484700122399, "mc1_stderr": 0.01723329939957122, "mc2": 0.5679144363917273, "mc2_stderr": 0.01582118053131118 }, "harness|arc:challenge|25": { "acc": 0.6228668941979523, "acc_stderr": 0.0141633668961926, "acc_norm": 0.6459044368600683, "acc_norm_stderr": 0.01397545412275656 }, "harness|hellaswag|10": { "acc": 0.6419040031866162, "acc_stderr": 0.004784607222774645, "acc_norm": 0.833698466440948, "acc_norm_stderr": 0.0037159010850549854 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6962962962962963, "acc_stderr": 0.03972552884785136, "acc_norm": 0.6962962962962963, "acc_norm_stderr": 0.03972552884785136 }, "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": 0.02444238813110082, "acc_norm": 0.8037735849056604, "acc_norm_stderr": 0.02444238813110082 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.875, "acc_stderr": 0.02765610492929436, "acc_norm": 0.875, "acc_norm_stderr": 0.02765610492929436 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.45, "acc_stderr": 0.04999999999999999, "acc_norm": 0.45, "acc_norm_stderr": 0.04999999999999999 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7398843930635838, "acc_stderr": 0.033450369167889904, "acc_norm": 0.7398843930635838, "acc_norm_stderr": 0.033450369167889904 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5392156862745098, "acc_stderr": 0.04959859966384181, "acc_norm": 0.5392156862745098, "acc_norm_stderr": 0.04959859966384181 }, "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": 0.027501752944412417, "acc_norm": 0.7702127659574468, "acc_norm_stderr": 0.027501752944412417 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6228070175438597, "acc_stderr": 0.04559522141958216, "acc_norm": 0.6228070175438597, "acc_norm_stderr": 0.04559522141958216 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7379310344827587, "acc_stderr": 0.03664666337225257, "acc_norm": 0.7379310344827587, "acc_norm_stderr": 0.03664666337225257 }, "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": 0.5476190476190477, "acc_stderr": 0.044518079590553275, "acc_norm": 0.5476190476190477, "acc_norm_stderr": 0.044518079590553275 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.55, "acc_stderr": 0.049999999999999996, "acc_norm": 0.55, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9032258064516129, "acc_stderr": 0.016818943416345197, "acc_norm": 0.9032258064516129, "acc_norm_stderr": 0.016818943416345197 }, "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": 0.81, "acc_stderr": 0.03942772444036625, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036625 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8363636363636363, "acc_stderr": 0.028887872395487946, "acc_norm": 0.8363636363636363, "acc_norm_stderr": 0.028887872395487946 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9191919191919192, "acc_stderr": 0.019417681889724536, "acc_norm": 0.9191919191919192, "acc_norm_stderr": 0.019417681889724536 }, "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": 0.7974358974358975, "acc_stderr": 0.020377660970371393, "acc_norm": 0.7974358974358975, "acc_norm_stderr": 0.020377660970371393 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4148148148148148, "acc_stderr": 0.03003984245406929, "acc_norm": 0.4148148148148148, "acc_norm_stderr": 0.03003984245406
