open-llm-leaderboard-old/details_BFauber__lora_llama2-13b_10e5_r2_a256
收藏数据集概述
数据集摘要
该数据集是在模型BFauber/lora_llama2-13b_10e5_r2_a256在Open LLM Leaderboard上的评估运行期间自动创建的。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一个特定的分割，分割名称使用运行的时间戳。"train"分割始终指向最新的结果。
数据集结构
数据集包含以下配置：
- results: 存储所有运行结果的聚合结果，用于计算和显示Open LLM Leaderboard上的聚合指标。
最新结果
以下是最新结果的摘要： python { "all": { "acc": 0.5262381600832391, "acc_stderr": 0.03391157572673184, "acc_norm": 0.5327872286671618, "acc_norm_stderr": 0.03466267483741011, "mc1": 0.2460220318237454, "mc1_stderr": 0.015077219200662597, "mc2": 0.3636128598306004, "mc2_stderr": 0.013371503900824411 }, "harness|arc:challenge|25": { "acc": 0.5435153583617748, "acc_stderr": 0.01455594976049644, "acc_norm": 0.5802047781569966, "acc_norm_stderr": 0.014422181226303028 }, "harness|hellaswag|10": { "acc": 0.6014738099980084, "acc_stderr": 0.004885942040894563, "acc_norm": 0.8098984266082454, "acc_norm_stderr": 0.003915792315457796 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5185185185185185, "acc_stderr": 0.043163785995113245, "acc_norm": 0.5185185185185185, "acc_norm_stderr": 0.043163785995113245 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5131578947368421, "acc_stderr": 0.04067533136309174, "acc_norm": 0.5131578947368421, "acc_norm_stderr": 0.04067533136309174 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.51, "acc_stderr": 0.05024183937956913, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956913 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5358490566037736, "acc_stderr": 0.030693675018458003, "acc_norm": 0.5358490566037736, "acc_norm_stderr": 0.030693675018458003 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5833333333333334, "acc_stderr": 0.04122728707651282, "acc_norm": 0.5833333333333334, "acc_norm_stderr": 0.04122728707651282 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5028901734104047, "acc_stderr": 0.038124005659748335, "acc_norm": 0.5028901734104047, "acc_norm_stderr": 0.038124005659748335 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.28431372549019607, "acc_stderr": 0.04488482852329017, "acc_norm": 0.28431372549019607, "acc_norm_stderr": 0.04488482852329017 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.67, "acc_stderr": 0.04725815626252609, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252609 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4085106382978723, "acc_stderr": 0.03213418026701576, "acc_norm": 0.4085106382978723, "acc_norm_stderr": 0.03213418026701576 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2543859649122807, "acc_stderr": 0.040969851398436716, "acc_norm": 0.2543859649122807, "acc_norm_stderr": 0.040969851398436716 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4689655172413793, "acc_stderr": 0.04158632762097828, "acc_norm": 0.4689655172413793, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3148148148148148, "acc_stderr": 0.023919984164047732, "acc_norm": 0.3148148148148148, "acc_norm_stderr": 0.023919984164047732 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3253968253968254, "acc_stderr": 0.041905964388711366, "acc_norm": 0.3253968253968254, "acc_norm_stderr": 0.041905964388711366 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6096774193548387, "acc_stderr": 0.027751256636969576, "acc_norm": 0.6096774193548387, "acc_norm_stderr": 0.027751256636969576 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3891625615763547, "acc_stderr": 0.034304624161038716, "acc_norm": 0.3891625615763547, "acc_norm_stderr": 0.034304624161038716 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6606060606060606, "acc_stderr": 0.03697442205031595, "acc_norm": 0.6606060606060606, "acc_norm_stderr": 0.03697442205031595 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6363636363636364, "acc_stderr": 0.03427308652999933, "acc_norm": 0.6363636363636364, "acc_norm_stderr": 0.03427308652999933 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7979274611398963, "acc_stderr": 0.02897908979429673, "acc_norm": 0.7979274611398963, "acc_norm_stderr": 0.02897908979429673 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4897435897435897, "acc_stderr": 0.025345672221942374, "acc_norm": 0.4897435897435897, "acc_norm_stderr": 0.025345672221942374 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2814814814814815, "acc_stderr": 0.027420019350945273, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.027420019350945273 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.5, "acc_
