open-llm-leaderboard-old/details_Unbabel__TowerBase-7B-v0.1
收藏Hugging Face2024-01-13 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Unbabel__TowerBase-7B-v0.1
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在评估模型Unbabel/TowerBase-7B-v0.1时自动创建的,用于在Open LLM Leaderboard上进行评估。数据集由63个配置组成,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。此外,results配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。
该数据集是在评估模型Unbabel/TowerBase-7B-v0.1时自动创建的,用于在Open LLM Leaderboard上进行评估。数据集由63个配置组成,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。此外,results配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。
提供机构:
open-llm-leaderboard-old
原始信息汇总
数据集概述
数据集信息
- 名称: Evaluation run of Unbabel/TowerBase-7B-v0.1
- 来源: 自动创建于模型 Unbabel/TowerBase-7B-v0.1 在 Open LLM Leaderboard 的评估运行中。
- 配置数量: 63 个配置,每个配置对应一个评估任务。
- 创建次数: 1 次运行。每个运行在每个配置中有一个特定的分割,分割名称使用运行的时间戳。"train" 分割始终指向最新结果。
- 额外配置: "results" 配置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_Unbabel__TowerBase-7B-v0.1", "harness_winogrande_5", split="train")
最新结果
- 最新结果时间戳: 2024-01-13T18:50:27.460863
- 聚合结果: python { "all": { "acc": 0.4376530652603909, "acc_stderr": 0.03443246082169724, "acc_norm": 0.4418549088967034, "acc_norm_stderr": 0.035215274463337505, "mc1": 0.23745410036719705, "mc1_stderr": 0.014896277441041843, "mc2": 0.3729251403943506, "mc2_stderr": 0.013360710032144346 }, "harness|arc:challenge|25": { "acc": 0.48464163822525597, "acc_stderr": 0.014604496129394906, "acc_norm": 0.5102389078498294, "acc_norm_stderr": 0.014608326906285012 }, "harness|hellaswag|10": { "acc": 0.5780720971917944, "acc_stderr": 0.004928578106026371, "acc_norm": 0.7768372834096794, "acc_norm_stderr": 0.0041551563175093375 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, # 其他任务的结果... }
配置详情
-
配置名称: harness_arc_challenge_25
- 分割: 2024_01_13T18_50_27.460863, latest
- 路径:
- **/details_harness|arc:challenge|25_2024-01-13T18-50-27.460863.parquet
-
配置名称: harness_gsm8k_5
- 分割: 2024_01_13T18_50_27.460863, latest
- 路径:
- **/details_harness|gsm8k|5_2024-01-13T18-50-27.460863.parquet
-
配置名称: harness_hellaswag_10
- 分割: 2024_01_13T18_50_27.460863, latest
- 路径:
- **/details_harness|hellaswag|10_2024-01-13T18-50-27.460863.parquet
-
配置名称: harness_hendrycksTest_5
- 分割: 2024_01_13T18_50_27.460863, latest
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-management|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-public_relations|5_2024-01-13T18-50-27.460863.parquet
- **/details_harness|hendrycksTest-security_studies|5_2024-01-13T18-50



