open-llm-leaderboard-old/details_Nhoodie__Meta-Llama-3-8B-Uninstruct-function-calling-json-mode-model_stock-v0.1
收藏数据集概述
数据集摘要
该数据集是在对模型 Nhoodie/Meta-Llama-3-8B-Uninstruct-function-calling-json-mode-model_stock-v0.1 进行评估运行期间自动创建的，评估结果发布在 Open LLM Leaderboard 上。
数据集组成
- 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" 配置存储所有运行结果的聚合，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_Nhoodie__Meta-Llama-3-8B-Uninstruct-function-calling-json-mode-model_stock-v0.1", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-24T16:51:51.098371 运行的最新结果：
python { "all": { "acc": 0.6692027667552859, "acc_stderr": 0.03174231905766657, "acc_norm": 0.6715873187546587, "acc_norm_stderr": 0.032376462952646554, "mc1": 0.36107711138310894, "mc1_stderr": 0.016814312844836886, "mc2": 0.5169207909411342, "mc2_stderr": 0.015200397234696131 }, "harness|arc:challenge|25": { "acc": 0.5733788395904437, "acc_stderr": 0.014453185592920293, "acc_norm": 0.6109215017064846, "acc_norm_stderr": 0.014247309976045607 }, "harness|hellaswag|10": { "acc": 0.5899223262298346, "acc_stderr": 0.0049084231471620225, "acc_norm": 0.785700059749054, "acc_norm_stderr": 0.0040949719808920804 }, "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": 0.6592592592592592, "acc_stderr": 0.04094376269996793, "acc_norm": 0.6592592592592592, "acc_norm_stderr": 0.04094376269996793 }, "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": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7509433962264151, "acc_stderr": 0.026616482980501704, "acc_norm": 0.7509433962264151, "acc_norm_stderr": 0.026616482980501704 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7847222222222222, "acc_stderr": 0.034370793441061344, "acc_norm": 0.7847222222222222, "acc_norm_stderr": 0.034370793441061344 }, "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": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6358381502890174, "acc_stderr": 0.03669072477416907, "acc_norm": 0.6358381502890174, "acc_norm_stderr": 0.03669072477416907 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5, "acc_stderr": 0.04975185951049946, "acc_norm": 0.5, "acc_norm_stderr": 0.04975185951049946 }, "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": 0.5957446808510638, "acc_stderr": 0.032081157507886836, "acc_norm": 0.5957446808510638, "acc_norm_stderr": 0.032081157507886836 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6052631578947368, "acc_stderr": 0.04598188057816542, "acc_norm": 0.6052631578947368, "acc_norm_stderr": 0.04598188057816542 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6482758620689655, "acc_stderr": 0.0397923663749741, "acc_norm": 0.6482758620689655, "acc_norm_stderr": 0.0397923663749741 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4365079365079365, "acc_stderr": 0.0255428468174005, "acc_norm": 0.4365079365079365, "acc_norm_stderr": 0.0255428468174005 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.49206349206349204, "acc_stderr": 0.044715725362943486, "acc_norm": 0.49206349206349204, "acc_norm_stderr": 0.044715725362943486 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7870967741935484, "acc_stderr": 0.023287665127268563, "acc_norm": 0.7870967741935484, "acc_norm_stderr": 0.023287665127268563 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5172413793103449, "acc_stderr": 0.035158955511656986, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.035158955511656986 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7515151515151515, "acc_stderr": 0.03374402644139404, "acc_norm": 0.7515151515151515, "acc_norm_stderr": 0.03374402644139404 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8434343434343434, "acc_stderr": 0.025890520358141454, "acc_norm": 0.8434343434343434, "acc_norm_stderr": 0.025890520358141454 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9119170984455959, "acc_stderr": 0.02045374660160103, "acc_norm": 0.9119170984455959, "acc_norm_stderr": 0.02045374660160103 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6615384615384615, "acc_stderr": 0.02399150050031303, "acc_norm": 0.6615384615384615, "acc_norm_stderr": 0.02399150050031303 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3925925925925926, "acc_stderr": 0
