open-llm-leaderboard-old/details_Abhaykoul__qwen1.5-vortex
收藏数据集概述
该数据集是在对模型 Abhaykoul/qwen1.5-vortex 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 63 个配置，每个配置对应一个评估任务。
- 数据集从 2 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。
- 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 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_Abhaykoul__qwen1.5-vortex", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2024-03-11T02:27:12.145497 的运行：
python { "all": { "acc": 0.3817203865676145, "acc_stderr": 0.034089822227601395, "acc_norm": 0.3848469655600226, "acc_norm_stderr": 0.0348511286935856, "mc1": 0.2252141982864137, "mc1_stderr": 0.014623240768023496, "mc2": 0.38916482019581305, "mc2_stderr": 0.014419624366247177 }, "harness|arc:challenge|25": { "acc": 0.2790102389078498, "acc_stderr": 0.013106784883601353, "acc_norm": 0.3174061433447099, "acc_norm_stderr": 0.013602239088038169 }, "harness|hellaswag|10": { "acc": 0.3746265684126668, "acc_stderr": 0.004830371317841069, "acc_norm": 0.47779326827325236, "acc_norm_stderr": 0.004984857671187102 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3037037037037037, "acc_stderr": 0.039725528847851375, "acc_norm": 0.3037037037037037, "acc_norm_stderr": 0.039725528847851375 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.39473684210526316, "acc_stderr": 0.039777499346220734, "acc_norm": 0.39473684210526316, "acc_norm_stderr": 0.039777499346220734 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.3886792452830189, "acc_stderr": 0.030000485448675986, "acc_norm": 0.3886792452830189, "acc_norm_stderr": 0.030000485448675986 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3541666666666667, "acc_stderr": 0.039994111357535424, "acc_norm": 0.3541666666666667, "acc_norm_stderr": 0.039994111357535424 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3699421965317919, "acc_stderr": 0.036812296333943194, "acc_norm": 0.3699421965317919, "acc_norm_stderr": 0.036812296333943194 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2647058823529412, "acc_stderr": 0.043898699568087785, "acc_norm": 0.2647058823529412, "acc_norm_stderr": 0.043898699568087785 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3276595744680851, "acc_stderr": 0.030683020843231004, "acc_norm": 0.3276595744680851, "acc_norm_stderr": 0.030683020843231004 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2982456140350877, "acc_stderr": 0.04303684033537315, "acc_norm": 0.2982456140350877, "acc_norm_stderr": 0.04303684033537315 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4, "acc_stderr": 0.040824829046386284, "acc_norm": 0.4, "acc_norm_stderr": 0.040824829046386284 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.31746031746031744, "acc_stderr": 0.023973861998992062, "acc_norm": 0.31746031746031744, "acc_norm_stderr": 0.023973861998992062 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.24603174603174602, "acc_stderr": 0.03852273364924315, "acc_norm": 0.24603174603174602, "acc_norm_stderr": 0.03852273364924315 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.4032258064516129, "acc_stderr": 0.02790615082604114, "acc_norm": 0.4032258064516129, "acc_norm_stderr": 0.02790615082604114 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.29064039408866993, "acc_stderr": 0.03194740072265541, "acc_norm": 0.29064039408866993, "acc_norm_stderr": 0.03194740072265541 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.4909090909090909, "acc_stderr": 0.0390369864774844, "acc_norm": 0.4909090909090909, "acc_norm_stderr": 0.0390369864774844 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.4595959595959596, "acc_stderr": 0.035507024651313425, "acc_norm": 0.4595959595959596, "acc_norm_stderr": 0.035507024651313425 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.48186528497409326, "acc_stderr": 0.036060650018329185, "acc_norm": 0.48186528497409326, "acc_norm_stderr": 0.036060650018329185 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3487179487179487, "acc_stderr": 0.024162780284017717, "acc_norm": 0.3487179487179487, "acc_norm_stderr": 0.024162780284017717 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2740740740740741, "acc_stderr": 0.027195934804085622, "acc_norm": 0.2740740740740741, "acc_norm_stderr": 0.027195934804085622 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.40336134453781514, "acc_stderr": 0.0
