open-llm-leaderboard-old/details_Severian__ANIMA-Phi-Neptune-Mistral-LoRa
收藏数据集概述
该数据集是在模型Severian/ANIMA-Phi-Neptune-Mistral-LoRa的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"分割总是指向最新的结果。
- 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_Severian__ANIMA-Phi-Neptune-Mistral-LoRa", "harness_truthfulqa_mc_0", split="train")
最新结果
以下是2023-10-10T15:49:43.201517运行的最新结果： python { "all": { "acc": 0.5216421138363554, "acc_stderr": 0.034984720641748575, "acc_norm": 0.5252295168080844, "acc_norm_stderr": 0.03497398634134131, "mc1": 0.412484700122399, "mc1_stderr": 0.017233299399571227, "mc2": 0.5938354841447588, "mc2_stderr": 0.015090386269121684 }, "harness|arc:challenge|25": { "acc": 0.5, "acc_stderr": 0.014611390804670088, "acc_norm": 0.5307167235494881, "acc_norm_stderr": 0.014583792546304037 }, "harness|hellaswag|10": { "acc": 0.5656243776140211, "acc_stderr": 0.004946617138983521, "acc_norm": 0.7465644293965346, "acc_norm_stderr": 0.004340891673320502 }, "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": 0.4074074074074074, "acc_stderr": 0.042446332383532286, "acc_norm": 0.4074074074074074, "acc_norm_stderr": 0.042446332383532286 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.4868421052631579, "acc_stderr": 0.04067533136309174, "acc_norm": 0.4868421052631579, "acc_norm_stderr": 0.04067533136309174 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5849056603773585, "acc_stderr": 0.03032594578928611, "acc_norm": 0.5849056603773585, "acc_norm_stderr": 0.03032594578928611 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5277777777777778, "acc_stderr": 0.04174752578923185, "acc_norm": 0.5277777777777778, "acc_norm_stderr": 0.04174752578923185 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.45, "acc_stderr": 0.049999999999999996, "acc_norm": 0.45, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.23, "acc_stderr": 0.042295258468165065, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5375722543352601, "acc_stderr": 0.0380168510452446, "acc_norm": 0.5375722543352601, "acc_norm_stderr": 0.0380168510452446 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.29411764705882354, "acc_stderr": 0.04533838195929777, "acc_norm": 0.29411764705882354, "acc_norm_stderr": 0.04533838195929777 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4553191489361702, "acc_stderr": 0.03255525359340355, "acc_norm": 0.4553191489361702, "acc_norm_stderr": 0.03255525359340355 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.35964912280701755, "acc_stderr": 0.04514496132873633, "acc_norm": 0.35964912280701755, "acc_norm_stderr": 0.04514496132873633 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5586206896551724, "acc_stderr": 0.04137931034482758, "acc_norm": 0.5586206896551724, "acc_norm_stderr": 0.04137931034482758 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.35714285714285715, "acc_stderr": 0.024677862841332783, "acc_norm": 0.35714285714285715, "acc_norm_stderr": 0.024677862841332783 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.36507936507936506, "acc_stderr": 0.04306241259127153, "acc_norm": 0.36507936507936506, "acc_norm_stderr": 0.04306241259127153 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5838709677419355, "acc_stderr": 0.028040981380761547, "acc_norm": 0.5838709677419355, "acc_norm_stderr": 0.028040981380761547 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3448275862068966, "acc_stderr": 0.033442837442804574, "acc_norm": 0.3448275862068966, "acc_norm_stderr": 0.033442837442804574 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6727272727272727, "acc_stderr": 0.036639749943912434, "acc_norm": 0.6727272727272727, "acc_norm_stderr": 0.036639749943912434 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6212121212121212, "acc_stderr": 0.03456088731993747, "acc_norm": 0.6212121212121212, "acc_norm_stderr": 0.03456088731993747 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7202072538860104, "acc_stderr": 0.03239637046735704, "acc_norm": 0.7202072538860104, "acc_norm_stderr": 0.03239637046735704 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4641025641025641, "acc_stderr": 0.02528558599001784, "acc_norm": 0.4641025641025641, "acc_norm_stderr": 0.02528558599001784 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2740740740740741, "acc_stderr": 0.027195934804085626, "acc_norm": 0.2740740740740741, "acc_norm_stderr": 0.027195
