open-llm-leaderboard/details_lmsys__vicuna-7b-delta-v1.1
收藏Hugging Face2023-10-12 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_lmsys__vicuna-7b-delta-v1.1
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在模型 lmsys/vicuna-7b-delta-v1.1 在 Open LLM Leaderboard 上的评估过程中自动生成的。数据集由 64 个配置组成,每个配置对应一个被评估的任务。它由 3 次运行创建,每次运行在每个配置中表示为特定的拆分,并以运行的时间戳命名。train 拆分始终指向最新的结果。一个名为 results 的额外配置存储了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。README 还提供了如何使用 Python 代码加载运行中的详细信息的示例,并包含特定运行的最新结果。
提供机构:
open-llm-leaderboard
原始信息汇总
数据集概述
数据集名称
- Evaluation run of lmsys/vicuna-7b-delta-v1.1
数据集摘要
- 该数据集是在对模型 lmsys/vicuna-7b-delta-v1.1 进行评估运行期间自动创建的。
- 数据集由64个配置组成,每个配置对应一个评估任务。
- 数据集从3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。
数据集加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_lmsys__vicuna-7b-delta-v1.1", "harness_winogrande_5", split="train")
最新结果
- 这些是最新结果,来自2023-10-12T14:40:56.820234的运行。 python { "all": { "em": 0.11388422818791946, "em_stderr": 0.00325324428862373, "f1": 0.16976719798657605, "f1_stderr": 0.003380156230610554, "acc": 0.38244753834582057, "acc_stderr": 0.009528517622122097 }, "harness|drop|3": { "em": 0.11388422818791946, "em_stderr": 0.00325324428862373, "f1": 0.16976719798657605, "f1_stderr": 0.003380156230610554 }, "harness|gsm8k|5": { "acc": 0.05534495830174375, "acc_stderr": 0.006298221796179588 }, "harness|winogrande|5": { "acc": 0.7095501183898973, "acc_stderr": 0.012758813448064607 } }
配置详情
-
harness_arc_challenge_25
- 分割:2023_07_18T12_22_17.969682
- 路径:
**/details_harness|arc:challenge|25_2023-07-18T12:22:17.969682.parquet
- 路径:
- 分割:2023_08_03T12_35_58.134991
- 路径:
**/details_harness|arc:challenge|25_2023-08-03T12:35:58.134991.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|arc:challenge|25_2023-08-03T12:35:58.134991.parquet
- 路径:
- 分割:2023_07_18T12_22_17.969682
-
harness_drop_3
- 分割:2023_10_12T14_40_56.820234
- 路径:
**/details_harness|drop|3_2023-10-12T14-40-56.820234.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|drop|3_2023-10-12T14-40-56.820234.parquet
- 路径:
- 分割:2023_10_12T14_40_56.820234
-
harness_gsm8k_5
- 分割:2023_10_12T14_40_56.820234
- 路径:
**/details_harness|gsm8k|5_2023-10-12T14-40-56.820234.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|gsm8k|5_2023-10-12T14-40-56.820234.parquet
- 路径:
- 分割:2023_10_12T14_40_56.820234
-
harness_hellaswag_10
- 分割:2023_07_18T12_22_17.969682
- 路径:
**/details_harness|hellaswag|10_2023-07-18T12:22:17.969682.parquet
- 路径:
- 分割:2023_08_03T12_35_58.134991
- 路径:
**/details_harness|hellaswag|10_2023-08-03T12:35:58.134991.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|hellaswag|10_2023-08-03T12:35:58.134991.parquet
- 路径:
- 分割:2023_07_18T12_22_17.969682
-
harness_hendrycksTest_5
- 分割:2023_07_18T12_22_17.969682
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-anatomy|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-astronomy|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-business_ethics|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-college_biology|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-college_chemistry|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-college_computer_science|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-college_mathematics|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-college_medicine|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-college_physics|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-computer_security|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-econometrics|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-formal_logic|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-global_facts|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-high_school_biology|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-high_school_european_history|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-high_school_geography|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-high_school_physics|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-high_school_psychology|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-high_school_statistics|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-high_school_us_history|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-high_school_world_history|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-human_aging|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-human_sexuality|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-international_law|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-jurisprudence|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-logical_fallacies|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-machine_learning|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-management|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-marketing|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-medical_genetics|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-miscellaneous|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-moral_disputes|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-moral_scenarios|5_2023-07-18T12:22:17.969682.parquet - 路径:
**/details_harness|hendrycksTest-nutrition|5_2023-07-18T12:22:17.969682.parquet
- 路径:
- 分割:2023_07_18T12_22_17.969682



