open-llm-leaderboard-old/details_llm-agents__tora-70b-v1.0
收藏数据集概述
数据集简介
该数据集是在对模型 llm-agents/tora-70b-v1.0 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集结构
- 配置数量：64个配置，每个配置对应一个评估任务。
- 运行次数：数据集从3次运行中创建，每个运行在每个配置中作为一个特定的分割存在，分割名称使用运行的时间戳。
- 训练分割："train" 分割始终指向最新的结果。
- 结果配置：一个额外的配置 "results" 存储所有运行的聚合结果，用于计算和显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_llm-agents__tora-70b-v1.0", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-05T04:40:35.452468 运行的最新结果：
python { "all": { "acc": 0.686642645967617, "acc_stderr": 0.03047283426707121, "acc_norm": 0.6938580939473421, "acc_norm_stderr": 0.031073735621803395, "mc1": 0.3561811505507956, "mc1_stderr": 0.01676379072844633, "mc2": 0.5176388218057985, "mc2_stderr": 0.01472999313037203 }, "harness|arc:challenge|25": { "acc": 0.6390784982935154, "acc_stderr": 0.014034761386175452, "acc_norm": 0.6757679180887372, "acc_norm_stderr": 0.013678810399518819 }, "harness|hellaswag|10": { "acc": 0.6682931686914957, "acc_stderr": 0.004698640688271201, "acc_norm": 0.858195578570006, "acc_norm_stderr": 0.003481364840770977 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6296296296296297, "acc_stderr": 0.04171654161354543, "acc_norm": 0.6296296296296297, "acc_norm_stderr": 0.04171654161354543 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8026315789473685, "acc_stderr": 0.03238981601699397, "acc_norm": 0.8026315789473685, "acc_norm_stderr": 0.03238981601699397 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.73, "acc_stderr": 0.04461960433384741, "acc_norm": 0.73, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7094339622641509, "acc_stderr": 0.027943219989337142, "acc_norm": 0.7094339622641509, "acc_norm_stderr": 0.027943219989337142 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8194444444444444, "acc_stderr": 0.03216600808802267, "acc_norm": 0.8194444444444444, "acc_norm_stderr": 0.03216600808802267 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6416184971098265, "acc_stderr": 0.03656343653353159, "acc_norm": 0.6416184971098265, "acc_norm_stderr": 0.03656343653353159 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.38235294117647056, "acc_stderr": 0.04835503696107223, "acc_norm": 0.38235294117647056, "acc_norm_stderr": 0.04835503696107223 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932262, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932262 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6680851063829787, "acc_stderr": 0.030783736757745643, "acc_norm": 0.6680851063829787, "acc_norm_stderr": 0.030783736757745643 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.41228070175438597, "acc_stderr": 0.04630653203366595, "acc_norm": 0.41228070175438597, "acc_norm_stderr": 0.04630653203366595 }, "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": 0.41534391534391535, "acc_stderr": 0.025379524910778394, "acc_norm": 0.41534391534391535, "acc_norm_stderr": 0.025379524910778394 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5158730158730159, "acc_stderr": 0.044698818540726076, "acc_norm": 0.5158730158730159, "acc_norm_stderr": 0.044698818540726076 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8161290322580645, "acc_stderr": 0.022037217340267826, "acc_norm": 0.8161290322580645, "acc_norm_stderr": 0.022037217340267826 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.541871921182266, "acc_stderr": 0.03505630140785741, "acc_norm": 0.541871921182266, "acc_norm_stderr": 0.03505630140785741 }, "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": 0.8363636363636363, "acc_stderr": 0.02888787239548795, "acc_norm": 0.8363636363636363, "acc_norm_stderr": 0.02888787239548795 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8888888888888888, "acc_stderr": 0.022390787638216763, "acc_norm": 0.8888888888888888, "acc_norm_stderr": 0.022390787638216763 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9378238341968912, "acc_stderr": 0.01742697415424052, "acc_norm": 0.9378238341968912, "acc_norm_stderr": 0.01742697415424052 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7102564102564103, "acc_stderr": 0.023000628243687964, "acc_norm": 0.7102564102564103, "acc_norm_stderr": 0.023000628243687964 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32592592592592595, "acc_stderr": 0.028578348365473075, "acc_norm": 0.32592592592592595, "acc_norm_stderr": 0.02
