open-llm-leaderboard-old/details_openbmb__MiniCPM-2B-dpo-bf16-llama-format
收藏数据集概述
该数据集是在对模型 openbmb/MiniCPM-2B-dpo-bf16-llama-format 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
- 配置数量：63 个配置
- 数据来源：从 1 次运行中创建，每个运行在每个配置中都有一个特定的分割，分割名称使用运行的时间戳。
- 最新结果："train" 分割始终指向最新结果。
- 结果汇总：一个额外的配置 "results" 存储所有运行的汇总结果，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_openbmb__MiniCPM-2B-dpo-bf16-llama-format", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-01T00:57:47.291949 运行的最新结果：
python { "all": { "acc": 0.24243627953377195, "acc_stderr": 0.030393209336527886, "acc_norm": 0.24231819242542613, "acc_norm_stderr": 0.031196508272985448, "mc1": 0.22888616891064872, "mc1_stderr": 0.014706994909055027, "mc2": NaN, "mc2_stderr": NaN }, "harness|arc:challenge|25": { "acc": 0.2150170648464164, "acc_stderr": 0.012005717634133611, "acc_norm": 0.25597269624573377, "acc_norm_stderr": 0.012753013241244508 }, "harness|hellaswag|10": { "acc": 0.23919537940649274, "acc_stderr": 0.004257204183396424, "acc_norm": 0.22415853415654252, "acc_norm_stderr": 0.004161746750401135 }, "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": 0.2518518518518518, "acc_stderr": 0.03749850709174021, "acc_norm": 0.2518518518518518, "acc_norm_stderr": 0.03749850709174021 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.25, "acc_stderr": 0.03523807393012047, "acc_norm": 0.25, "acc_norm_stderr": 0.03523807393012047 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.3132075471698113, "acc_stderr": 0.028544793319055326, "acc_norm": 0.3132075471698113, "acc_norm_stderr": 0.028544793319055326 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.1875, "acc_stderr": 0.032639560491693344, "acc_norm": 0.1875, "acc_norm_stderr": 0.032639560491693344 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.24, "acc_stderr": 0.04292346959909282, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.16, "acc_stderr": 0.0368452949177471, "acc_norm": 0.16, "acc_norm_stderr": 0.0368452949177471 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.23699421965317918, "acc_stderr": 0.03242414757483098, "acc_norm": 0.23699421965317918, "acc_norm_stderr": 0.03242414757483098 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.23529411764705882, "acc_stderr": 0.04220773659171452, "acc_norm": 0.23529411764705882, "acc_norm_stderr": 0.04220773659171452 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2553191489361702, "acc_stderr": 0.028504856470514196, "acc_norm": 0.2553191489361702, "acc_norm_stderr": 0.028504856470514196 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.22807017543859648, "acc_stderr": 0.03947152782669415, "acc_norm": 0.22807017543859648, "acc_norm_stderr": 0.03947152782669415 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.27586206896551724, "acc_stderr": 0.037245636197746325, "acc_norm": 0.27586206896551724, "acc_norm_stderr": 0.037245636197746325 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.21693121693121692, "acc_stderr": 0.02122708244944505, "acc_norm": 0.21693121693121692, "acc_norm_stderr": 0.02122708244944505 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.15873015873015872, "acc_stderr": 0.03268454013011744, "acc_norm": 0.15873015873015872, "acc_norm_stderr": 0.03268454013011744 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.1935483870967742, "acc_stderr": 0.022475258525536057, "acc_norm": 0.1935483870967742, "acc_norm_stderr": 0.022475258525536057 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.19704433497536947, "acc_stderr": 0.027986724666736226, "acc_norm": 0.19704433497536947, "acc_norm_stderr": 0.027986724666736226 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.2, "acc_stderr": 0.040201512610368445, "acc_norm": 0.2, "acc_norm_stderr": 0.040201512610368445 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.3090909090909091, "acc_stderr": 0.036085410115739666, "acc_norm": 0.3090909090909091, "acc_norm_stderr": 0.036085410115739666 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.26262626262626265, "acc_stderr": 0.031353050095330855, "acc_norm": 0.26262626262626265, "acc_norm_stderr": 0.031353050095330855 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.17616580310880828, "acc_stderr": 0.027493504244548047, "acc_norm": 0.17616580310880828, "acc_norm_stderr": 0.027493504244548047 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2692307692307692, "acc_stderr": 0.02248938979365483, "acc_norm": 0.2692307692307692, "acc_norm_stderr": 0.02248938979365483 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.23703703703703705, "acc_stderr": 0.025928876132766104, "acc_norm": 0.23703703703703705, "acc_norm_stderr": 0.025928876132766104 }, "harness|hendrycksTest-high_school_micro
