gayanin/kaggle-native-v8-noise-op-wise

---
dataset_info:
- config_name: del-0.1
features:
- name: refs
dtype: string
- name: trans
dtype: string
splits:
- name: train
num_bytes: 527540
num_examples: 5140
- name: test
num_bytes: 66797
num_examples: 643
- name: validation
num_bytes: 65940
num_examples: 643
download_size: 283539
dataset_size: 660277
- config_name: del-0.2
features:
- name: refs
dtype: string
- name: trans
dtype: string
splits:
- name: train
num_bytes: 501145
num_examples: 5140
- name: test
num_bytes: 63543
num_examples: 643
- name: validation
num_bytes: 62810
num_examples: 643
download_size: 283130
dataset_size: 627498
- config_name: del-0.3
features:
- name: refs
dtype: string
- name: trans
dtype: string
splits:
- name: train
num_bytes: 475012
num_examples: 5140
- name: test
num_bytes: 60480
num_examples: 643
- name: validation
num_bytes: 59354
num_examples: 643
download_size: 272846
dataset_size: 594846
- config_name: del-0.4
features:
- name: refs
dtype: string
- name: trans
dtype: string
splits:
- name: train
num_bytes: 448513
num_examples: 5140
- name: test
num_bytes: 57015
num_examples: 643
- name: validation
num_bytes: 56555
num_examples: 643
download_size: 260210
dataset_size: 562083
- config_name: del-0.5
features:
- name: refs
dtype: string
- name: trans
dtype: string
splits:
- name: train
num_bytes: 423140
num_examples: 5140
- name: test
num_bytes: 53586
num_examples: 643
- name: validation
num_bytes: 52599
num_examples: 643
download_size: 244485
dataset_size: 529325
- config_name: ins-0.1
features:
- name: refs
dtype: string
- name: trans
dtype: string
splits:
- name: train
num_bytes: 582442
num_examples: 5140
- name: test
num_bytes: 73780
num_examples: 643
- name: validation
num_bytes: 72873
num_examples: 643
download_size: 321990
dataset_size: 729095
- config_name: ins-0.2
features:
- name: refs
dtype: string
- name: trans
dtype: string
splits:
- name: train
num_bytes: 610811
num_examples: 5140
- name: test
num_bytes: 77727
num_examples: 643
- name: validation
num_bytes: 76309
num_examples: 643
download_size: 359996
dataset_size: 764847
- config_name: ins-0.3
features:
- name: refs
dtype: string
- name: trans
dtype: string
splits:
- name: train
num_bytes: 639753
num_examples: 5140
- name: test
num_bytes: 81417
num_examples: 643
- name: validation
num_bytes: 79886
num_examples: 643
download_size: 392528
dataset_size: 801056
- config_name: ins-0.4
features:
- name: refs
dtype: string
- name: trans
dtype: string
splits:
- name: train
num_bytes: 667786
num_examples: 5140
- name: test
num_bytes: 85414
num_examples: 643
- name: validation
num_bytes: 83579
num_examples: 643
download_size: 418436
dataset_size: 836779
- config_name: ins-0.5
features:
- name: refs
dtype: string
- name: trans
dtype: string
splits:
- name: train
num_bytes: 696825
num_examples: 5140
- name: test
num_bytes: 88845
num_examples: 643
- name: validation
num_bytes: 87333
num_examples: 643
download_size: 442720
dataset_size: 873003
- config_name: sub-0.1
features:
- name: refs
dtype: string
- name: trans
dtype: string
splits:
- name: train
num_bytes: 554228
num_examples: 5140
- name: test
num_bytes: 70343
num_examples: 643
- name: validation
num_bytes: 69451
num_examples: 643
download_size: 300467
dataset_size: 694022
- config_name: sub-0.2
features:
- name: refs
dtype: string
- name: trans
dtype: string
splits:
- name: train
num_bytes: 554953
num_examples: 5140
- name: test
num_bytes: 70426
num_examples: 643
- name: validation
num_bytes: 69553
num_examples: 643
download_size: 319710
dataset_size: 694932
- config_name: sub-0.3
features:
- name: refs
dtype: string
- name: trans
dtype: string
splits:
- name: train
num_bytes: 555471
num_examples: 5140
- name: test
num_bytes: 70508
num_examples: 643
- name: validation
num_bytes: 69628
num_examples: 643
download_size: 329627
dataset_size: 695607
- config_name: sub-0.4
features:
- name: refs
dtype: string
- name: trans
dtype: string
splits:
- name: train
num_bytes: 556271
num_examples: 5140
- name: test
num_bytes: 70623
num_examples: 643
- name: validation
num_bytes: 69755
num_examples: 643
download_size: 333112
dataset_size: 696649
- config_name: sub-0.5
features:
- name: refs
dtype: string
- name: trans
dtype: string
splits:
- name: train
num_bytes: 556947
num_examples: 5140
- name: test
num_bytes: 70715
num_examples: 643
- name: validation
num_bytes: 69833
num_examples: 643
download_size: 334630
dataset_size: 697495
configs:
- config_name: del-0.1
data_files:
- split: train
path: del-0.1/train-*
- split: test
path: del-0.1/test-*
- split: validation
path: del-0.1/validation-*
- config_name: del-0.2
data_files:
- split: train
path: del-0.2/train-*
- split: test
path: del-0.2/test-*
- split: validation
path: del-0.2/validation-*
- config_name: del-0.3
data_files:
- split: train
path: del-0.3/train-*
- split: test
path: del-0.3/test-*
- split: validation
path: del-0.3/validation-*
- config_name: del-0.4
data_files:
- split: train
path: del-0.4/train-*
- split: test
path: del-0.4/test-*
- split: validation
path: del-0.4/validation-*
- config_name: del-0.5
data_files:
- split: train
path: del-0.5/train-*
- split: test
path: del-0.5/test-*
- split: validation
path: del-0.5/validation-*
- config_name: ins-0.1
data_files:
- split: train
path: ins-0.1/train-*
- split: test
path: ins-0.1/test-*
- split: validation
path: ins-0.1/validation-*
- config_name: ins-0.2
data_files:
- split: train
path: ins-0.2/train-*
- split: test
path: ins-0.2/test-*
- split: validation
path: ins-0.2/validation-*
- config_name: ins-0.3
data_files:
- split: train
path: ins-0.3/train-*
- split: test
path: ins-0.3/test-*
- split: validation
path: ins-0.3/validation-*
- config_name: ins-0.4
data_files:
- split: train
path: ins-0.4/train-*
- split: test
path: ins-0.4/test-*
- split: validation
path: ins-0.4/validation-*
- config_name: ins-0.5
data_files:
- split: train
path: ins-0.5/train-*
- split: test
path: ins-0.5/test-*
- split: validation
path: ins-0.5/validation-*
- config_name: sub-0.1
data_files:
- split: train
path: sub-0.1/train-*
- split: test
path: sub-0.1/test-*
- split: validation
path: sub-0.1/validation-*
- config_name: sub-0.2
data_files:
- split: train
path: sub-0.2/train-*
- split: test
path: sub-0.2/test-*
- split: validation
path: sub-0.2/validation-*
- config_name: sub-0.3
data_files:
- split: train
path: sub-0.3/train-*
- split: test
path: sub-0.3/test-*
- split: validation
path: sub-0.3/validation-*
- config_name: sub-0.4
data_files:
- split: train
path: sub-0.4/train-*
- split: test
path: sub-0.4/test-*
- split: validation
path: sub-0.4/validation-*
- config_name: sub-0.5
data_files:
- split: train
path: sub-0.5/train-*
- split: test
path: sub-0.5/test-*
- split: validation
path: sub-0.5/validation-*
---

原始信息汇总

数据集概述

数据集配置

del-0.1

• 特征:
  • refs: 字符串类型
  • trans: 字符串类型
• 分割:
  • train: 5140个样本, 527540字节
  • test: 643个样本, 66797字节
  • validation: 643个样本, 65940字节
• 下载大小: 283539字节
• 数据集大小: 660277字节

del-0.2

• 特征:
  • refs: 字符串类型
  • trans: 字符串类型
• 分割:
  • train: 5140个样本, 501145字节
  • test: 643个样本, 63543字节
  • validation: 643个样本, 62810字节
• 下载大小: 283130字节
• 数据集大小: 627498字节

del-0.3

• 特征:
  • refs: 字符串类型
  • trans: 字符串类型
• 分割:
  • train: 5140个样本, 475012字节
  • test: 643个样本, 60480字节
  • validation: 643个样本, 59354字节
• 下载大小: 272846字节
• 数据集大小: 594846字节

del-0.4

• 特征:
  • refs: 字符串类型
  • trans: 字符串类型
• 分割:
  • train: 5140个样本, 448513字节
  • test: 643个样本, 57015字节
  • validation: 643个样本, 56555字节
• 下载大小: 260210字节
• 数据集大小: 562083字节

del-0.5

• 特征:
  • refs: 字符串类型
  • trans: 字符串类型
• 分割:
  • train: 5140个样本, 423140字节
  • test: 643个样本, 53586字节
  • validation: 643个样本, 52599字节
• 下载大小: 244485字节
• 数据集大小: 529325字节

ins-0.1

• 特征:
  • refs: 字符串类型
  • trans: 字符串类型
• 分割:
  • train: 5140个样本, 582442字节
  • test: 643个样本, 73780字节
  • validation: 643个样本, 72873字节
• 下载大小: 321990字节
• 数据集大小: 729095字节

ins-0.2

• 特征:
  • refs: 字符串类型
  • trans: 字符串类型
• 分割:
  • train: 5140个样本, 610811字节
  • test: 643个样本, 77727字节
  • validation: 643个样本, 76309字节
• 下载大小: 359996字节
• 数据集大小: 764847字节

ins-0.3

• 特征:
  • refs: 字符串类型
  • trans: 字符串类型
• 分割:
  • train: 5140个样本, 639753字节
  • test: 643个样本, 81417字节
  • validation: 643个样本, 79886字节
• 下载大小: 392528字节
• 数据集大小: 801056字节

ins-0.4

• 特征:
  • refs: 字符串类型
  • trans: 字符串类型
• 分割:
  • train: 5140个样本, 667786字节
  • test: 643个样本, 85414字节
  • validation: 643个样本, 83579字节
• 下载大小: 418436字节
• 数据集大小: 836779字节

ins-0.5

• 特征:
  • refs: 字符串类型
  • trans: 字符串类型
• 分割:
  • train: 5140个样本, 696825字节
  • test: 643个样本, 88845字节
  • validation: 643个样本, 87333字节
• 下载大小: 442720字节
• 数据集大小: 873003字节

sub-0.1

• 特征:
  • refs: 字符串类型
  • trans: 字符串类型
• 分割:
  • train: 5140个样本, 554228字节
  • test: 643个样本, 70343字节
  • validation: 643个样本, 69451字节
• 下载大小: 300467字节
• 数据集大小: 694022字节

sub-0.2

• 特征:
  • refs: 字符串类型
  • trans: 字符串类型
• 分割:
  • train: 5140个样本, 554953字节
  • test: 643个样本, 70426字节
  • validation: 643个样本, 69553字节
• 下载大小: 319710字节
• 数据集大小: 694932字节

sub-0.3

• 特征:
  • refs: 字符串类型
  • trans: 字符串类型
• 分割:
  • train: 5140个样本, 555471字节
  • test: 643个样本, 70508字节
  • validation: 643个样本, 69628字节
• 下载大小: 329627字节
• 数据集大小: 695607字节

sub-0.4

• 特征:
  • refs: 字符串类型
  • trans: 字符串类型
• 分割:
  • train: 5140个样本, 556271字节
  • test: 643个样本, 70623字节
  • validation: 643个样本, 69755字节
• 下载大小: 333112字节
• 数据集大小: 696649字节

sub-0.5

• 特征:
  • refs: 字符串类型
  • trans: 字符串类型
• 分割:
  • train: 5140个样本, 556947字节
  • test: 643个样本, 70715字节
  • validation: 643个样本, 69833字节
• 下载大小: 334630字节
• 数据集大小: 697495字节