open-llm-leaderboard/details_invalid-coder__TinyLlama-1.1B-intermediate-step-1431k-3T-laser-dpo
收藏Hugging Face2024-03-30 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_invalid-coder__TinyLlama-1.1B-intermediate-step-1431k-3T-laser-dpo
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invalid-coder/TinyLlama-1.1B-intermediate-step-1431k-3T-laser-dpo在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成,每个配置对应一个被评估的任务。数据集是从1次运行中创建的,每次运行作为每个配置中的一个特定分割,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存储了运行的所有聚合结果,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,并包含了特定运行的最新结果。
该数据集是在模型invalid-coder/TinyLlama-1.1B-intermediate-step-1431k-3T-laser-dpo在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成,每个配置对应一个被评估的任务。数据集是从1次运行中创建的,每次运行作为每个配置中的一个特定分割,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存储了运行的所有聚合结果,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,并包含了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
- pretty_name: Evaluation run of invalid-coder/TinyLlama-1.1B-intermediate-step-1431k-3T-laser-dpo
数据集描述
- dataset_summary: 该数据集是在评估模型invalid-coder/TinyLlama-1.1B-intermediate-step-1431k-3T-laser-dpo的过程中自动创建的。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次运行创建,每次运行都有特定的分割,分割名称使用运行的时间戳命名。"train"分割始终指向最新的结果。此外,还有一个名为"results"的配置,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。
数据集加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_invalid-coder__TinyLlama-1.1B-intermediate-step-1431k-3T-laser-dpo", "harness_winogrande_5", split="train")
最新结果
数据集配置
- config_name: harness_arc_challenge_25
- data_files:
- split: 2024_03_30T15_13_38.324226
- path: **/details_harness|arc:challenge|25_2024-03-30T15-13-38.324226.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2024-03-30T15-13-38.324226.parquet
- split: 2024_03_30T15_13_38.324226
- data_files:
- config_name: harness_gsm8k_5
- data_files:
- split: 2024_03_30T15_13_38.324226
- path: **/details_harness|gsm8k|5_2024-03-30T15-13-38.324226.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2024-03-30T15-13-38.324226.parquet
- split: 2024_03_30T15_13_38.324226
- data_files:
- config_name: harness_hellaswag_10
- data_files:
- split: 2024_03_30T15_13_38.324226
- path: **/details_harness|hellaswag|10_2024-03-30T15-13-38.324226.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2024-03-30T15-13-38.324226.parquet
- split: 2024_03_30T15_13_38.324226
- data_files:
- config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_03_30T15_13_38.324226
- path: **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-anatomy|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-astronomy|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-business_ethics|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-college_biology|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-college_chemistry|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-college_computer_science|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-college_mathematics|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-college_medicine|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-college_physics|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-computer_security|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-econometrics|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-human_aging|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-human_sexuality|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-international_law|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-jurisprudence|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-logical_fallacies|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-machine_learning|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-management|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-marketing|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-medical_genetics|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-miscellaneous|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-moral_disputes|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-moral_scenarios|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-nutrition|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-philosophy|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-prehistory|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-professional_accounting|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-professional_law|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-professional_medicine|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-professional_psychology|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-public_relations|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-security_studies|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-sociology|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-us_foreign_policy|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-virology|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-world_religions|5_2024-03-30T15-13-38.324226.parquet
- split: latest
- path: **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-anatomy|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-astronomy|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-business_ethics|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-college_biology|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-college_chemistry|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-college_computer_science|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-college_mathematics|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-college_medicine|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-college_physics|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-computer_security|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-econometrics|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-30T15-13-38.324226.parquet
- path: **/details_harness|hendrycksTest-human_aging|5_2024-03-30T
- split: 2024_03_30T15_13_38.324226
- data_files:



