open-llm-leaderboard-old/details_migtissera__Tess-10.7B-v1.5b
收藏数据集概述
数据集组成
该数据集是在对模型 migtissera/Tess-10.7B-v1.5b 进行评估运行期间自动创建的。数据集包含63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，每次运行的详细结果可以在每个配置中找到，并以运行的时间戳命名的特定分片存储。"train" 分片始终指向最新的结果。
数据集加载示例
以下是加载数据集详细信息的示例代码： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_migtissera__Tess-10.7B-v1.5b", "harness_winogrande_5", split="train")
最新结果
以下是2024年1月28日19:33:09.585454运行的最新结果： python { "all": { "acc": 0.6623790658470444, "acc_stderr": 0.03145433935990498, "acc_norm": 0.6654734598510913, "acc_norm_stderr": 0.0320818568417205, "mc1": 0.31946144430844553, "mc1_stderr": 0.0163226441829605, "mc2": 0.4738041625665458, "mc2_stderr": 0.0145592749388437 }, "harness|arc:challenge|25": { "acc": 0.5998293515358362, "acc_stderr": 0.014317197787809169, "acc_norm": 0.6535836177474402, "acc_norm_stderr": 0.013905011180063232 }, "harness|hellaswag|10": { "acc": 0.6595299741087433, "acc_stderr": 0.004728988167338548, "acc_norm": 0.8533160724955188, "acc_norm_stderr": 0.003530675014892316 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.046482319871173156, "acc_norm": 0.31, "acc_norm_stderr": 0.046482319871173156 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5851851851851851, "acc_stderr": 0.04256193767901408, "acc_norm": 0.5851851851851851, "acc_norm_stderr": 0.04256193767901408 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.756578947368421, "acc_stderr": 0.034923496688842384, "acc_norm": 0.756578947368421, "acc_norm_stderr": 0.034923496688842384 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7056603773584905, "acc_stderr": 0.02804918631569525, "acc_norm": 0.7056603773584905, "acc_norm_stderr": 0.02804918631569525 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7638888888888888, "acc_stderr": 0.03551446610810826, "acc_norm": 0.7638888888888888, "acc_norm_stderr": 0.03551446610810826 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6878612716763006, "acc_stderr": 0.035331333893236574, "acc_norm": 0.6878612716763006, "acc_norm_stderr": 0.035331333893236574 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4411764705882353, "acc_stderr": 0.049406356306056595, "acc_norm": 0.4411764705882353, "acc_norm_stderr": 0.049406356306056595 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.04229525846816506, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5787234042553191, "acc_stderr": 0.03227834510146268, "acc_norm": 0.5787234042553191, "acc_norm_stderr": 0.03227834510146268 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.45614035087719296, "acc_stderr": 0.04685473041907789, "acc_norm": 0.45614035087719296, "acc_norm_stderr": 0.04685473041907789 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6275862068965518, "acc_stderr": 0.04028731532947559, "acc_norm": 0.6275862068965518, "acc_norm_stderr": 0.04028731532947559 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4365079365079365, "acc_stderr": 0.025542846817400485, "acc_norm": 0.4365079365079365, "acc_norm_stderr": 0.025542846817400485 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4126984126984127, "acc_stderr": 0.04403438954768176, "acc_norm": 0.4126984126984127, "acc_norm_stderr": 0.04403438954768176 }, "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": 0.8096774193548387, "acc_stderr": 0.022331707611823078, "acc_norm": 0.8096774193548387, "acc_norm_stderr": 0.022331707611823078 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5073891625615764, "acc_stderr": 0.035176035403610105, "acc_norm": 0.5073891625615764, "acc_norm_stderr": 0.035176035403610105 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8181818181818182, "acc_stderr": 0.03011768892950357, "acc_norm": 0.8181818181818182, "acc_norm_stderr": 0.03011768892950357 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8585858585858586, "acc_stderr": 0.024825909793343343, "acc_norm": 0.8585858585858586, "acc_norm_stderr": 0.024825909793343343 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9326424870466321, "acc_stderr": 0.018088393839078912, "acc_norm": 0.9326424870466321, "acc_norm_stderr": 0.018088393839078912 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6666666666666666, "acc_stderr": 0.023901157979402538, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.023901157979402538 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.37037037037037035, "acc_stderr": 0.02944316932303154, "acc_norm": 0.37037037037037035, "acc_norm_stderr": 0.02944316932303154 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.7100840336134454, "acc_stderr": 0.029472485833136094, "acc_norm": 0.7100840336134454, "acc_norm_stderr": 0.029472485833136094 }, "harness|hendrycksTest-high_school
