open-llm-leaderboard-old/details_abdulrahman-nuzha__belal-finetuned-llama2-1024-v2.2
收藏数据集概述
数据集简介
该数据集是在模型abdulrahman-nuzha/belal-finetuned-llama2-1024-v2.2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。
- "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_abdulrahman-nuzha__belal-finetuned-llama2-1024-v2.2", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自2024-01-19T15:11:16.361884的运行： python { "all": { "acc": 0.4487446353511138, "acc_stderr": 0.034504979440505464, "acc_norm": 0.4534744253247318, "acc_norm_stderr": 0.03530926751067455, "mc1": 0.2460220318237454, "mc1_stderr": 0.015077219200662592, "mc2": 0.40020648111023094, "mc2_stderr": 0.01385589773587115 }, "harness|arc:challenge|25": { "acc": 0.49146757679180886, "acc_stderr": 0.014609263165632186, "acc_norm": 0.5264505119453925, "acc_norm_stderr": 0.014590931358120172 }, "harness|hellaswag|10": { "acc": 0.5850428201553476, "acc_stderr": 0.004917076726623795, "acc_norm": 0.7781318462457678, "acc_norm_stderr": 0.004146537488135697 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.48148148148148145, "acc_stderr": 0.043163785995113245, "acc_norm": 0.48148148148148145, "acc_norm_stderr": 0.043163785995113245 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.3881578947368421, "acc_stderr": 0.03965842097512744, "acc_norm": 0.3881578947368421, "acc_norm_stderr": 0.03965842097512744 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.4679245283018868, "acc_stderr": 0.03070948699255655, "acc_norm": 0.4679245283018868, "acc_norm_stderr": 0.03070948699255655 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4375, "acc_stderr": 0.04148415739394154, "acc_norm": 0.4375, "acc_norm_stderr": 0.04148415739394154 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.34, "acc_stderr": 0.047609522856952344, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952344 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.42196531791907516, "acc_stderr": 0.0376574669386515, "acc_norm": 0.42196531791907516, "acc_norm_stderr": 0.0376574669386515 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.1568627450980392, "acc_stderr": 0.03618664819936245, "acc_norm": 0.1568627450980392, "acc_norm_stderr": 0.03618664819936245 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4340425531914894, "acc_stderr": 0.03240038086792747, "acc_norm": 0.4340425531914894, "acc_norm_stderr": 0.03240038086792747 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.30701754385964913, "acc_stderr": 0.04339138322579861, "acc_norm": 0.30701754385964913, "acc_norm_stderr": 0.04339138322579861 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.496551724137931, "acc_stderr": 0.041665675771015785, "acc_norm": 0.496551724137931, "acc_norm_stderr": 0.041665675771015785 }, "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": 0.25396825396825395, "acc_stderr": 0.03893259610604675, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.03893259610604675 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.47419354838709676, "acc_stderr": 0.028406095057653315, "acc_norm": 0.47419354838709676, "acc_norm_stderr": 0.028406095057653315 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3399014778325123, "acc_stderr": 0.0333276906841079, "acc_norm": 0.3399014778325123, "acc_norm_stderr": 0.0333276906841079 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.42, "acc_stderr": 0.04960449637488584, "acc_norm": 0.42, "acc_norm_stderr": 0.04960449637488584 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5696969696969697, "acc_stderr": 0.03866225962879077, "acc_norm": 0.5696969696969697, "acc_norm_stderr": 0.03866225962879077 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5353535353535354, "acc_stderr": 0.03553436368828061, "acc_norm": 0.5353535353535354, "acc_norm_stderr": 0.03553436368828061 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6528497409326425, "acc_stderr": 0.03435696168361355, "acc_norm": 0.6528497409326425, "acc_norm_stderr": 0.03435696168361355 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4076923076923077, "acc_stderr": 0.024915243985987844, "acc_norm": 0.4076923076923077, "acc_norm_stderr": 0.024915243985987844 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.25555555555555554, "acc_stderr": 0.02659393910184408, "acc_norm": 0.25555555555555554, "acc_norm_stderr": 0.02659393910184408 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.3
