open-llm-leaderboard-old/details_decruz07__llama-2-7b-miniguanaco
收藏数据集概述
数据集摘要
该数据集是在评估模型decruz07/llama-2-7b-miniguanaco在Open LLM Leaderboard上的自动创建的。
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_decruz07__llama-2-7b-miniguanaco", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自2024-01-10T16:23:25.560074的运行： python { "all": { "acc": 0.4622895077291068, "acc_stderr": 0.03447917370505138, "acc_norm": 0.4668682561630037, "acc_norm_stderr": 0.03525354072650985, "mc1": 0.28151774785801714, "mc1_stderr": 0.01574402724825605, "mc2": 0.43733395896519406, "mc2_stderr": 0.01449344801677889 }, "harness|arc:challenge|25": { "acc": 0.4522184300341297, "acc_stderr": 0.014544519880633832, "acc_norm": 0.4906143344709898, "acc_norm_stderr": 0.014608816322065 }, "harness|hellaswag|10": { "acc": 0.5611431985660227, "acc_stderr": 0.004952332378120329, "acc_norm": 0.7559251145190201, "acc_norm_stderr": 0.004286594977390901 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.04605661864718381, "acc_norm": 0.3, "acc_norm_stderr": 0.04605661864718381 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.45185185185185184, "acc_stderr": 0.04299268905480864, "acc_norm": 0.45185185185185184, "acc_norm_stderr": 0.04299268905480864 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.46710526315789475, "acc_stderr": 0.040601270352363966, "acc_norm": 0.46710526315789475, "acc_norm_stderr": 0.040601270352363966 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5132075471698113, "acc_stderr": 0.030762134874500482, "acc_norm": 0.5132075471698113, "acc_norm_stderr": 0.030762134874500482 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4930555555555556, "acc_stderr": 0.04180806750294938, "acc_norm": 0.4930555555555556, "acc_norm_stderr": 0.04180806750294938 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3815028901734104, "acc_stderr": 0.03703851193099521, "acc_norm": 0.3815028901734104, "acc_norm_stderr": 0.03703851193099521 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.22549019607843138, "acc_stderr": 0.04158307533083286, "acc_norm": 0.22549019607843138, "acc_norm_stderr": 0.04158307533083286 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.39574468085106385, "acc_stderr": 0.03196758697835362, "acc_norm": 0.39574468085106385, "acc_norm_stderr": 0.03196758697835362 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3684210526315789, "acc_stderr": 0.04537815354939392, "acc_norm": 0.3684210526315789, "acc_norm_stderr": 0.04537815354939392 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4482758620689655, "acc_stderr": 0.04144311810878151, "acc_norm": 0.4482758620689655, "acc_norm_stderr": 0.04144311810878151 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2777777777777778, "acc_stderr": 0.023068188848261128, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.023068188848261128 }, "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": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5225806451612903, "acc_stderr": 0.02841498501970786, "acc_norm": 0.5225806451612903, "acc_norm_stderr": 0.02841498501970786 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3891625615763547, "acc_stderr": 0.03430462416103872, "acc_norm": 0.3891625615763547, "acc_norm_stderr": 0.03430462416103872 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5636363636363636, "acc_stderr": 0.03872592983524754, "acc_norm": 0.5636363636363636, "acc_norm_stderr": 0.03872592983524754 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5505050505050505, "acc_stderr": 0.035441324919479704, "acc_norm": 0.5505050505050505, "acc_norm_stderr": 0.035441324919479704 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6994818652849741, "acc_stderr": 0.0330881859441575, "acc_norm": 0.6994818652849741, "acc_norm_stderr": 0.0330881859441575 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.38974358974358975, "acc_stderr": 0.024726967886647078, "acc_norm": 0.38974358974358975, "acc_norm_stderr": 0.024726967886647078 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.27037037037037037, "acc_stderr": 0.02708037281514568, "acc_norm": 0.27037037037037037, "acc_norm_stderr": 0.02708037281514568 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.3907563025
