open-llm-leaderboard-old/details_Charlie911__vicuna-7b-v1.5-lora-temporal-without-mctaco-1
收藏数据集概述
数据集简介
该数据集是在对模型 Charlie911/vicuna-7b-v1.5-lora-temporal-without-mctaco-1 进行评估运行期间自动创建的,用于 Open LLM Leaderboard。
数据集结构
- 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,每个运行可以在每个配置中作为一个特定的分割找到,分割名称使用运行的时间戳。
- "train" 分割始终指向最新的结果。
- 额外的 "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_Charlie911__vicuna-7b-v1.5-lora-temporal-without-mctaco-1", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果来自 run 2024-01-24T22:38:44.232137 的摘要:
python { "all": { "acc": 0.47390153459197415, "acc_stderr": 0.034488650414693046, "acc_norm": 0.47990494504266334, "acc_norm_stderr": 0.03528061933639502, "mc1": 0.26193390452876375, "mc1_stderr": 0.015392118805015021, "mc2": 0.39945852317616254, "mc2_stderr": 0.01392826930362614 }, "harness|arc:challenge|25": { "acc": 0.4539249146757679, "acc_stderr": 0.014549221105171865, "acc_norm": 0.4948805460750853, "acc_norm_stderr": 0.01461062489030916 }, "harness|hellaswag|10": { "acc": 0.5613423620792671, "acc_stderr": 0.004952087083128905, "acc_norm": 0.7593108942441744, "acc_norm_stderr": 0.0042662819001443916 }, # 其他任务的结果... }
配置详情
-
config_name: harness_arc_challenge_25
- 数据文件:
- split: 2024_01_24T22_38_44.232137
- path: **/details_harness|arc:challenge|25_2024-01-24T22-38-44.232137.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2024-01-24T22-38-44.232137.parquet
- split: 2024_01_24T22_38_44.232137
- 数据文件:
-
config_name: harness_gsm8k_5
- 数据文件:
- split: 2024_01_24T22_38_44.232137
- path: **/details_harness|gsm8k|5_2024-01-24T22-38-44.232137.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2024-01-24T22-38-44.232137.parquet
- split: 2024_01_24T22_38_44.232137
- 数据文件:
-
config_name: harness_hellaswag_10
- 数据文件:
- split: 2024_01_24T22_38_44.232137
- path: **/details_harness|hellaswag|10_2024-01-24T22-38-44.232137.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2024-01-24T22-38-44.232137.parquet
- split: 2024_01_24T22_38_44.232137
- 数据文件:
-
config_name: harness_hendrycksTest_5
- 数据文件:
- split: 2024_01_24T22_38_44.232137
- path: **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-anatomy|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-astronomy|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-business_ethics|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-college_biology|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-college_chemistry|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-college_computer_science|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-college_mathematics|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-college_medicine|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-college_physics|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-computer_security|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-econometrics|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-formal_logic|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-global_facts|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-high_school_biology|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-high_school_geography|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-high_school_physics|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-human_aging|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-human_sexuality|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-international_law|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-jurisprudence|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-machine_learning|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-management|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-marketing|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-medical_genetics|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-miscellaneous|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-moral_disputes|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-nutrition|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-philosophy|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-prehistory|5_2024-01-24T22-38-44.232137.parquet
- path: **/details_harness|hendrycksTest-professional_accounting|5_2
- split: 2024_01_24T22_38_44.232137
- 数据文件:



