open-llm-leaderboard-old/details_quantumaikr__quantum-trinity-v0.1
收藏数据集概述
数据集是在对模型 quantumaikr/quantum-trinity-v0.1 进行评估运行期间自动创建的，该模型在 Open LLM Leaderboard 上进行评估。
数据集组成
- 数据集由 63 个配置组成，每个配置对应一个评估任务。
- 数据集是从 1 次运行中创建的。每个运行可以在每个配置中作为一个特定的分割找到，分割名称使用运行的时间戳。
- "train" 分割总是指向最新的结果。
- 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_quantumaikr__quantum-trinity-v0.1", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-18T03:19:56.363034 运行的最新结果：
python { "all": { "acc": 0.6572247685368219, "acc_stderr": 0.031992528267718985, "acc_norm": 0.657053972912952, "acc_norm_stderr": 0.032653378327314075, "mc1": 0.5495716034271726, "mc1_stderr": 0.01741726437196764, "mc2": 0.6927593169679473, "mc2_stderr": 0.01502938815172874 }, "harness|arc:challenge|25": { "acc": 0.6945392491467577, "acc_stderr": 0.013460080478002508, "acc_norm": 0.7252559726962458, "acc_norm_stderr": 0.013044617212771227 }, "harness|hellaswag|10": { "acc": 0.7104162517426807, "acc_stderr": 0.004526422125860672, "acc_norm": 0.8827922724556861, "acc_norm_stderr": 0.0032101025071772497 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6444444444444445, "acc_stderr": 0.04135176749720386, "acc_norm": 0.6444444444444445, "acc_norm_stderr": 0.04135176749720386 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6907894736842105, "acc_stderr": 0.037610708698674805, "acc_norm": 0.6907894736842105, "acc_norm_stderr": 0.037610708698674805 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.720754716981132, "acc_stderr": 0.027611163402399715, "acc_norm": 0.720754716981132, "acc_norm_stderr": 0.027611163402399715 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7708333333333334, "acc_stderr": 0.03514697467862388, "acc_norm": 0.7708333333333334, "acc_norm_stderr": 0.03514697467862388 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6936416184971098, "acc_stderr": 0.035149425512674394, "acc_norm": 0.6936416184971098, "acc_norm_stderr": 0.035149425512674394 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.46078431372549017, "acc_stderr": 0.04959859966384181, "acc_norm": 0.46078431372549017, "acc_norm_stderr": 0.04959859966384181 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.042295258468165065, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5829787234042553, "acc_stderr": 0.03223276266711712, "acc_norm": 0.5829787234042553, "acc_norm_stderr": 0.03223276266711712 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5, "acc_stderr": 0.047036043419179864, "acc_norm": 0.5, "acc_norm_stderr": 0.047036043419179864 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5793103448275863, "acc_stderr": 0.0411391498118926, "acc_norm": 0.5793103448275863, "acc_norm_stderr": 0.0411391498118926 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42063492063492064, "acc_stderr": 0.025424835086923996, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.025424835086923996 }, "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": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7838709677419354, "acc_stderr": 0.02341529343356853, "acc_norm": 0.7838709677419354, "acc_norm_stderr": 0.02341529343356853 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5221674876847291, "acc_stderr": 0.03514528562175007, "acc_norm": 0.5221674876847291, "acc_norm_stderr": 0.03514528562175007 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7757575757575758, "acc_stderr": 0.03256866661681102, "acc_norm": 0.7757575757575758, "acc_norm_stderr": 0.03256866661681102 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7929292929292929, "acc_stderr": 0.028869778460267042, "acc_norm": 0.7929292929292929, "acc_norm_stderr": 0.028869778460267042 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8963730569948186, "acc_stderr": 0.02199531196364424, "acc_norm": 0.8963730569948186, "acc_norm_stderr": 0.02199531196364424 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6692307692307692, "acc_stderr": 0.02385479568097112, "acc_norm": 0.6692307692307692, "acc_norm_stderr": 0.02385479568097112 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3296296296296296, "acc_stderr": 0.028661201116524565, "acc_norm": 0.3296296296296296, "acc_norm_stderr": 0.028661201116524565 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6680672268907563,
