open-llm-leaderboard-old/details_NbAiLab__nb-gpt-j-6B-alpaca
收藏数据集概述
数据集摘要
该数据集是在对模型 NbAiLab/nb-gpt-j-6B-alpaca 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
- 数据集包含 61 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。
- 额外的 "results" 配置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_NbAiLab__nb-gpt-j-6B-alpaca", "harness_truthfulqa_mc_0", split="train")
最新结果
这些是最新的结果，来自 2023-07-19T15:55:19.313530 的运行： python { "all": { "acc": 0.2793361324347659, "acc_stderr": 0.03229367242405252, "acc_norm": 0.2819200448548028, "acc_norm_stderr": 0.03229676260655511, "mc1": 0.23623011015911874, "mc1_stderr": 0.014869755015871114, "mc2": 0.3799804264451723, "mc2_stderr": 0.014771856203795355 }, "harness|arc:challenge|25": { "acc": 0.3447098976109215, "acc_stderr": 0.013888816286782114, "acc_norm": 0.36860068259385664, "acc_norm_stderr": 0.014097810678042184 }, "harness|hellaswag|10": { "acc": 0.44602668791077477, "acc_stderr": 0.004960624576987787, "acc_norm": 0.574586735710018, "acc_norm_stderr": 0.004933950953380902 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2962962962962963, "acc_stderr": 0.039446241625011175, "acc_norm": 0.2962962962962963, "acc_norm_stderr": 0.039446241625011175 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17105263157894737, "acc_stderr": 0.030643607071677088, "acc_norm": 0.17105263157894737, "acc_norm_stderr": 0.030643607071677088 }, "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": 0.23773584905660378, "acc_stderr": 0.02619980880756193, "acc_norm": 0.23773584905660378, "acc_norm_stderr": 0.02619980880756193 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3472222222222222, "acc_stderr": 0.039812405437178615, "acc_norm": 0.3472222222222222, "acc_norm_stderr": 0.039812405437178615 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.22, "acc_stderr": 0.04163331998932269, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932269 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2658959537572254, "acc_stderr": 0.0336876293225943, "acc_norm": 0.2658959537572254, "acc_norm_stderr": 0.0336876293225943 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3235294117647059, "acc_stderr": 0.04655010411319619, "acc_norm": 0.3235294117647059, "acc_norm_stderr": 0.04655010411319619 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.22, "acc_stderr": 0.041633319989322674, "acc_norm": 0.22, "acc_norm_stderr": 0.041633319989322674 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3148936170212766, "acc_stderr": 0.030363582197238156, "acc_norm": 0.3148936170212766, "acc_norm_stderr": 0.030363582197238156 }, "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": 0.2482758620689655, "acc_stderr": 0.03600105692727771, "acc_norm": 0.2482758620689655, "acc_norm_stderr": 0.03600105692727771 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25396825396825395, "acc_stderr": 0.022418042891113942, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.022418042891113942 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2222222222222222, "acc_stderr": 0.03718489006818115, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.03718489006818115 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.22, "acc_stderr": 0.04163331998932269, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932269 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.23548387096774193, "acc_stderr": 0.02413763242933772, "acc_norm": 0.23548387096774193, "acc_norm_stderr": 0.02413763242933772 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.270935960591133, "acc_stderr": 0.03127090713297698, "acc_norm": 0.270935960591133, "acc_norm_stderr": 0.03127090713297698 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.27, "acc_stderr": 0.04461960433384739, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384739 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2606060606060606, "acc_stderr": 0.034277431758165236, "acc_norm": 0.2606060606060606, "acc_norm_stderr": 0.034277431758165236 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.35858585858585856, "acc_stderr": 0.03416903640391521, "acc_norm": 0.35858585858585856, "acc_norm_stderr": 0.03416903640391521 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.35751295336787564, "acc_stderr": 0.034588160421810045, "acc_norm": 0.35751295336787564, "acc_norm_stderr": 0.034588160421810045 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.23846153846153847, "acc_stderr": 0.02160629449464773, "acc_norm": 0.23846153846153847, "acc_norm_stderr": 0.02160629449464773 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.22592592592592592, "acc_stderr": 0.025497532639609542, "acc_norm": 0.22592592592592592, "acc_norm_stderr": 0.025497532639609542 }, "harness|hendrycksTest-high_school_microeconomics|5":
