open-llm-leaderboard/details_bongchoi__test-llama-2-7b
收藏数据集概述
该数据集是在对模型 bongchoi/test-llama-2-7b 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
- 数据集由 61 个配置组成，每个配置对应一个评估任务。
- 数据集从 1 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_bongchoi__test-llama-2-7b", "harness_truthfulqa_mc_0", split="train")
最新结果
以下是 2023-09-12T23:02:34.518107 运行的最新结果：
python { "all": { "acc": 0.471008753299703, "acc_stderr": 0.03528088196519964, "acc_norm": 0.4749886536723232, "acc_norm_stderr": 0.035266604173246285, "mc1": 0.2484700122399021, "mc1_stderr": 0.01512742709652068, "mc2": 0.3875084099562216, "mc2_stderr": 0.013510147651392562 }, "harness|arc:challenge|25": { "acc": 0.4931740614334471, "acc_stderr": 0.014610029151379813, "acc_norm": 0.5307167235494881, "acc_norm_stderr": 0.014583792546304037 }, "harness|hellaswag|10": { "acc": 0.5884285998805019, "acc_stderr": 0.0049111251010646425, "acc_norm": 0.785700059749054, "acc_norm_stderr": 0.004094971980892084 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "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": 0.40789473684210525, "acc_stderr": 0.03999309712777471, "acc_norm": 0.40789473684210525, "acc_norm_stderr": 0.03999309712777471 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.4641509433962264, "acc_stderr": 0.030693675018458003, "acc_norm": 0.4641509433962264, "acc_norm_stderr": 0.030693675018458003 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4652777777777778, "acc_stderr": 0.04171115858181618, "acc_norm": 0.4652777777777778, "acc_norm_stderr": 0.04171115858181618 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "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": 0.24509803921568626, "acc_stderr": 0.04280105837364395, "acc_norm": 0.24509803921568626, "acc_norm_stderr": 0.04280105837364395 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.42127659574468085, "acc_stderr": 0.03227834510146267, "acc_norm": 0.42127659574468085, "acc_norm_stderr": 0.03227834510146267 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2807017543859649, "acc_stderr": 0.042270544512322004, "acc_norm": 0.2807017543859649, "acc_norm_stderr": 0.042270544512322004 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.47586206896551725, "acc_stderr": 0.041618085035015295, "acc_norm": 0.47586206896551725, "acc_norm_stderr": 0.041618085035015295 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2671957671957672, "acc_stderr": 0.02278967314577656, "acc_norm": 0.2671957671957672, "acc_norm_stderr": 0.02278967314577656 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2857142857142857, "acc_stderr": 0.0404061017820884, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.0404061017820884 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.32, "acc_stderr": 0.04688261722621503, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621503 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5, "acc_stderr": 0.028444006199428714, "acc_norm": 0.5, "acc_norm_stderr": 0.028444006199428714 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3645320197044335, "acc_stderr": 0.033864057460620905, "acc_norm": 0.3645320197044335, "acc_norm_stderr": 0.033864057460620905 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6363636363636364, "acc_stderr": 0.03756335775187899, "acc_norm": 0.6363636363636364, "acc_norm_stderr": 0.03756335775187899 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.4898989898989899, "acc_stderr": 0.03561625488673745, "acc_norm": 0.4898989898989899, "acc_norm_stderr": 0.03561625488673745 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6787564766839378, "acc_stderr": 0.033699508685490674, "acc_norm": 0.6787564766839378, "acc_norm_stderr": 0.033699508685490674 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.45897435897435895, "acc_stderr": 0.025265525491284295, "acc_norm": 0.45897435897435895, "acc_norm_stderr": 0.025265525491284295 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3, "acc_stderr": 0.027940457136228416, "acc_norm": 0.3, "acc_norm_stderr": 0.027940457136228416 }, "harness|hendrycksTest-high_school_microeconomics|5": { "
