open-llm-leaderboard-old/details_Tensoic__Kan-Llama-SFT-v0.5
收藏Hugging Face2024-01-24 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Tensoic__Kan-Llama-SFT-v0.5
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在Open LLM Leaderboard上对模型Tensoic/Kan-Llama-SFT-v0.5进行评估时自动创建的。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果存储为特定配置中的一个分割,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,一个名为results的配置存储了所有运行的聚合结果,用于在Open LLM Leaderboard上计算和显示聚合指标。
该数据集是在Open LLM Leaderboard上对模型Tensoic/Kan-Llama-SFT-v0.5进行评估时自动创建的。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果存储为特定配置中的一个分割,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,一个名为results的配置存储了所有运行的聚合结果,用于在Open LLM Leaderboard上计算和显示聚合指标。
提供机构:
open-llm-leaderboard-old
原始信息汇总
数据集概述
数据集名称
- 名称: Evaluation run of Tensoic/Kan-Llama-SFT-v0.5
数据集组成
- 配置数量: 63个配置
- 每个配置对应: 一个评估任务
- 数据来源: 从1次运行中创建
- 分割命名: 使用运行的时间戳
- 训练分割: 总是指向最新的结果
额外配置
- 结果配置: 存储所有运行的聚合结果,用于计算和显示在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_Tensoic__Kan-Llama-SFT-v0.5", "harness_winogrande_5", split="train")
最新结果
- 最新结果来源: 2024-01-24T01:43:44.197286
- 结果示例: python { "all": { "acc": 0.4272736498001841, "acc_stderr": 0.03426594520244024, "acc_norm": 0.43301807406696846, "acc_norm_stderr": 0.03509638961981207, "mc1": 0.3157894736842105, "mc1_stderr": 0.016272287957916912, "mc2": 0.4744031768522622, "mc2_stderr": 0.015238059013971565 }, "harness|arc:challenge|25": { "acc": 0.42918088737201365, "acc_stderr": 0.014464085894870653, "acc_norm": 0.47440273037542663, "acc_norm_stderr": 0.01459223088529896 }, "harness|hellaswag|10": { "acc": 0.5372435769766979, "acc_stderr": 0.00497591966511654, "acc_norm": 0.7271459868552081, "acc_norm_stderr": 0.004445160997618376 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, # 其他任务的结果... }
配置详情
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_01_24T01_43_44.197286
- 路径: **/details_harness|arc:challenge|25_2024-01-24T01-43-44.197286.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-01-24T01-43-44.197286.parquet
- 分割: 2024_01_24T01_43_44.197286
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_01_24T01_43_44.197286
- 路径: **/details_harness|gsm8k|5_2024-01-24T01-43-44.197286.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-01-24T01-43-44.197286.parquet
- 分割: 2024_01_24T01_43_44.197286
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_01_24T01_43_44.197286
- 路径: **/details_harness|hellaswag|10_2024-01-24T01-43-44.197286.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-01-24T01-43-44.197286.parquet
- 分割: 2024_01_24T01_43_44.197286
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_01_24T01_43_44.197286
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-management|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2024-01-24T01-43-44.197286.parquet
- **/details_harness|hendrycksTest-public_
- 路径:
- 分割: 2024_01_24T01_43_44.197286
- 数据文件:



