open-llm-leaderboard/details_quantumaikr__QuantumLM-llama2-70B-Korean-LoRA
收藏数据集概述
数据集摘要
该数据集是在评估模型 quantumaikr/QuantumLM-llama2-70B-Korean-LoRA 在 Open LLM Leaderboard 上的运行过程中自动创建的。数据集包含61个配置，每个配置对应一个评估任务。
数据集结构
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。
额外配置
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_quantumaikr__QuantumLM-llama2-70B-Korean-LoRA", "harness_truthfulqa_mc_0", split="train")
最新结果
以下是 最新结果 的摘要： python { "all": { "acc": 0.6934168799483462, "acc_stderr": 0.03115919348812645, "acc_norm": 0.6971494359890498, "acc_norm_stderr": 0.031131669600877022, "mc1": 0.401468788249694, "mc1_stderr": 0.017160273901693654, "mc2": 0.5608488880093394, "mc2_stderr": 0.014874770245335572 }, "harness|arc:challenge|25": { "acc": 0.6749146757679181, "acc_stderr": 0.013688147309729119, "acc_norm": 0.7056313993174061, "acc_norm_stderr": 0.013318528460539422 }, "harness|hellaswag|10": { "acc": 0.6743676558454491, "acc_stderr": 0.004676529200753001, "acc_norm": 0.8638717386974706, "acc_norm_stderr": 0.0034222387022263645 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5925925925925926, "acc_stderr": 0.04244633238353228, "acc_norm": 0.5925925925925926, "acc_norm_stderr": 0.04244633238353228 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8289473684210527, "acc_stderr": 0.03064360707167709, "acc_norm": 0.8289473684210527, "acc_norm_stderr": 0.03064360707167709 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7245283018867924, "acc_stderr": 0.027495663683724057, "acc_norm": 0.7245283018867924, "acc_norm_stderr": 0.027495663683724057 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8333333333333334, "acc_stderr": 0.031164899666948617, "acc_norm": 0.8333333333333334, "acc_norm_stderr": 0.031164899666948617 }, "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": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6705202312138728, "acc_stderr": 0.03583901754736412, "acc_norm": 0.6705202312138728, "acc_norm_stderr": 0.03583901754736412 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.04810840148082635, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.04810840148082635 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.73, "acc_stderr": 0.04461960433384739, "acc_norm": 0.73, "acc_norm_stderr": 0.04461960433384739 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6808510638297872, "acc_stderr": 0.030472973363380045, "acc_norm": 0.6808510638297872, "acc_norm_stderr": 0.030472973363380045 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4473684210526316, "acc_stderr": 0.04677473004491199, "acc_norm": 0.4473684210526316, "acc_norm_stderr": 0.04677473004491199 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5862068965517241, "acc_stderr": 0.04104269211806232, "acc_norm": 0.5862068965517241, "acc_norm_stderr": 0.04104269211806232 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.43915343915343913, "acc_stderr": 0.02555992055053101, "acc_norm": 0.43915343915343913, "acc_norm_stderr": 0.02555992055053101 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.46825396825396826, "acc_stderr": 0.04463112720677172, "acc_norm": 0.46825396825396826, "acc_norm_stderr": 0.04463112720677172 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8451612903225807, "acc_stderr": 0.020579287326583227, "acc_norm": 0.8451612903225807, "acc_norm_stderr": 0.020579287326583227 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5320197044334976, "acc_stderr": 0.03510766597959217, "acc_norm": 0.5320197044334976, "acc_norm_stderr": 0.03510766597959217 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.73, "acc_stderr": 0.044619604333847394, "acc_norm": 0.73, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8242424242424242, "acc_stderr": 0.02972094300622445, "acc_norm": 0.8242424242424242, "acc_norm_stderr": 0.02972094300622445 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8636363636363636, "acc_stderr": 0.024450155973189835, "acc_norm": 0.8636363636363636, "acc_norm_stderr": 0.024450155973189835 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9430051813471503, "acc_stderr": 0.01673108529360756, "acc_norm": 0.9430051813471503, "acc_norm_stderr": 0.01673108529360756 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7256410256410256, "acc_stderr": 0.022622765767493225, "acc_norm": 0.7256410256410256, "acc_norm_stderr": 0.022622765767493225 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.35185185185185186, "acc_stderr": 0.029116617606083015, "acc_norm": 0.35185185185185186, "acc_norm_stderr": 0.029116617606083015
