mbzuai-ugrip-statement-tuning/massive

---
dataset_info:
- config_name: af
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1109678
num_examples: 11514
- name: validation
num_bytes: 194946
num_examples: 2033
download_size: 452635
dataset_size: 1304624
- config_name: am
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1394162
num_examples: 11514
- name: validation
num_bytes: 246557
num_examples: 2033
download_size: 572604
dataset_size: 1640719
- config_name: ar
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1234663
num_examples: 11514
- name: validation
num_bytes: 218735
num_examples: 2033
download_size: 497064
dataset_size: 1453398
- config_name: az
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1168998
num_examples: 11514
- name: validation
num_bytes: 205086
num_examples: 2033
download_size: 466948
dataset_size: 1374084
- config_name: bn
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1745554
num_examples: 11514
- name: validation
num_bytes: 306045
num_examples: 2033
download_size: 619285
dataset_size: 2051599
- config_name: ca
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1137106
num_examples: 11514
- name: validation
num_bytes: 200287
num_examples: 2033
download_size: 459837
dataset_size: 1337393
- config_name: cy
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1126063
num_examples: 11514
- name: validation
num_bytes: 198193
num_examples: 2033
download_size: 463573
dataset_size: 1324256
- config_name: da
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1086468
num_examples: 11514
- name: validation
num_bytes: 191371
num_examples: 2033
download_size: 439422
dataset_size: 1277839
- config_name: de
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1136675
num_examples: 11514
- name: validation
num_bytes: 200820
num_examples: 2033
download_size: 471920
dataset_size: 1337495
- config_name: el
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1541312
num_examples: 11514
- name: validation
num_bytes: 270881
num_examples: 2033
download_size: 617657
dataset_size: 1812193
- config_name: en
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1080913
num_examples: 11514
- name: validation
num_bytes: 190813
num_examples: 2033
download_size: 432014
dataset_size: 1271726
- config_name: es
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1143140
num_examples: 11514
- name: validation
num_bytes: 201112
num_examples: 2033
download_size: 468903
dataset_size: 1344252
- config_name: fa
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1377230
num_examples: 11514
- name: validation
num_bytes: 241262
num_examples: 2033
download_size: 531007
dataset_size: 1618492
- config_name: fi
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1124055
num_examples: 11514
- name: validation
num_bytes: 197892
num_examples: 2033
download_size: 459957
dataset_size: 1321947
- config_name: fr
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1180442
num_examples: 11514
- name: validation
num_bytes: 208054
num_examples: 2033
download_size: 484562
dataset_size: 1388496
- config_name: he
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1276756
num_examples: 11514
- name: validation
num_bytes: 223898
num_examples: 2033
download_size: 501370
dataset_size: 1500654
- config_name: hi
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1744363
num_examples: 11514
- name: validation
num_bytes: 304622
num_examples: 2033
download_size: 630394
dataset_size: 2048985
- config_name: hu
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1142165
num_examples: 11514
- name: validation
num_bytes: 200096
num_examples: 2033
download_size: 481633
dataset_size: 1342261
- config_name: hy
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1474892
num_examples: 11514
- name: validation
num_bytes: 257249
num_examples: 2033
download_size: 575589
dataset_size: 1732141
- config_name: id
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1116139
num_examples: 11514
- name: validation
num_bytes: 196204
num_examples: 2033
download_size: 436382
dataset_size: 1312343
- config_name: is
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1155592
num_examples: 11514
- name: validation
num_bytes: 202818
num_examples: 2033
download_size: 474230
dataset_size: 1358410
- config_name: it
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1122823
num_examples: 11514
- name: validation
num_bytes: 197339
num_examples: 2033
download_size: 451912
dataset_size: 1320162
- config_name: ja
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1197285
num_examples: 11514
- name: validation
num_bytes: 211534
num_examples: 2033
download_size: 479002
dataset_size: 1408819
- config_name: jv
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1080906
num_examples: 11514
- name: validation
num_bytes: 189180
num_examples: 2033
download_size: 435160
dataset_size: 1270086
- config_name: ka
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1683984
num_examples: 11514
- name: validation
num_bytes: 294672
num_examples: 2033
download_size: 578561
dataset_size: 1978656
- config_name: km
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1718683
num_examples: 11514
- name: validation
num_bytes: 304631
num_examples: 2033
download_size: 609001
dataset_size: 2023314
- config_name: kn
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1906568
num_examples: 11514
- name: validation
num_bytes: 333532
num_examples: 2033
download_size: 667729
dataset_size: 2240100
- config_name: ko
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1123574
num_examples: 11514
- name: validation
num_bytes: 198034
num_examples: 2033
download_size: 454881
dataset_size: 1321608
- config_name: lv
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1138666
num_examples: 11514
- name: validation
num_bytes: 200013
num_examples: 2033
download_size: 471652
dataset_size: 1338679
- config_name: ml
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 2073281
num_examples: 11514
- name: validation
num_bytes: 363546
num_examples: 2033
download_size: 710476
dataset_size: 2436827
- config_name: mn
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1497928
num_examples: 11514
- name: validation
num_bytes: 264903
num_examples: 2033
download_size: 580653
dataset_size: 1762831
- config_name: ms
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1137681
num_examples: 11514
- name: validation
num_bytes: 199651
num_examples: 2033
download_size: 445132
dataset_size: 1337332
- config_name: my
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 2017787
num_examples: 11514
- name: validation
num_bytes: 351475
num_examples: 2033
download_size: 702009
dataset_size: 2369262
- config_name: nb
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1089702
num_examples: 11514
- name: validation
num_bytes: 191895
num_examples: 2033
download_size: 442418
dataset_size: 1281597
- config_name: nl
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1135536
num_examples: 11514
- name: validation
num_bytes: 199906
num_examples: 2033
download_size: 464776
dataset_size: 1335442
- config_name: pl
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1120033
num_examples: 11514
- name: validation
num_bytes: 197122
num_examples: 2033
download_size: 462681
dataset_size: 1317155
- config_name: pt
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1134461
num_examples: 11514
- name: validation
num_bytes: 199018
num_examples: 2033
download_size: 462950
dataset_size: 1333479
- config_name: ro
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1118842
num_examples: 11514
- name: validation
num_bytes: 196492
num_examples: 2033
download_size: 471338
dataset_size: 1315334
- config_name: ru
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1463069
num_examples: 11514
- name: validation
num_bytes: 257460
num_examples: 2033
download_size: 592187
dataset_size: 1720529
- config_name: sl
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1098532
num_examples: 11514
- name: validation
num_bytes: 193098
num_examples: 2033
download_size: 454072
dataset_size: 1291630
- config_name: sq
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1150187
num_examples: 11514
- name: validation
num_bytes: 202371
num_examples: 2033
download_size: 464347
dataset_size: 1352558
- config_name: sv
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1102727
num_examples: 11514
- name: validation
num_bytes: 194944
num_examples: 2033
download_size: 443326
dataset_size: 1297671
- config_name: sw
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1119426
num_examples: 11514
- name: validation
num_bytes: 197525
num_examples: 2033
download_size: 445321
dataset_size: 1316951
- config_name: ta
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 2049351
num_examples: 11514
- name: validation
num_bytes: 360128
num_examples: 2033
download_size: 695231
dataset_size: 2409479
- config_name: te
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1889870
num_examples: 11514
- name: validation
num_bytes: 330871
num_examples: 2033
download_size: 686919
dataset_size: 2220741
- config_name: th
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1693456
num_examples: 11514
- name: validation
num_bytes: 299044
num_examples: 2033
download_size: 623773
dataset_size: 1992500
- config_name: tl
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1194061
num_examples: 11514
- name: validation
num_bytes: 208325
num_examples: 2033
download_size: 475408
dataset_size: 1402386
- config_name: tr
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1113859
num_examples: 11514
- name: validation
num_bytes: 195302
num_examples: 2033
download_size: 456796
dataset_size: 1309161
- config_name: ur
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1404468
num_examples: 11514
- name: validation
num_bytes: 246502
num_examples: 2033
download_size: 554250
dataset_size: 1650970
- config_name: vi
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1257367
num_examples: 11514
- name: validation
num_bytes: 221431
num_examples: 2033
download_size: 501700
dataset_size: 1478798
- config_name: zh
features:
- name: is_true
dtype: int64
- name: statement
dtype: string
splits:
- name: train
num_bytes: 1003514
num_examples: 11514
- name: validation
num_bytes: 176309
num_examples: 2033
download_size: 470045
dataset_size: 1179823
configs:
- config_name: af
data_files:
- split: train
path: af/train-*
- split: validation
path: af/validation-*
- config_name: am
data_files:
- split: train
path: am/train-*
- split: validation
path: am/validation-*
- config_name: ar
data_files:
- split: train
path: ar/train-*
- split: validation
path: ar/validation-*
- config_name: az
data_files:
- split: train
path: az/train-*
- split: validation
path: az/validation-*
- config_name: bn
data_files:
- split: train
path: bn/train-*
- split: validation
path: bn/validation-*
- config_name: ca
data_files:
- split: train
path: ca/train-*
- split: validation
path: ca/validation-*
- config_name: cy
data_files:
- split: train
path: cy/train-*
- split: validation
path: cy/validation-*
- config_name: da
data_files:
- split: train
path: da/train-*
- split: validation
path: da/validation-*
- config_name: de
data_files:
- split: train
path: de/train-*
- split: validation
path: de/validation-*
- config_name: el
data_files:
- split: train
path: el/train-*
- split: validation
path: el/validation-*
- config_name: en
data_files:
- split: train
path: en/train-*
- split: validation
path: en/validation-*
- config_name: es
data_files:
- split: train
path: es/train-*
- split: validation
path: es/validation-*
- config_name: fa
data_files:
- split: train
path: fa/train-*
- split: validation
path: fa/validation-*
- config_name: fi
data_files:
- split: train
path: fi/train-*
- split: validation
path: fi/validation-*
- config_name: fr
data_files:
- split: train
path: fr/train-*
- split: validation
path: fr/validation-*
- config_name: he
data_files:
- split: train
path: he/train-*
- split: validation
path: he/validation-*
- config_name: hi
data_files:
- split: train
path: hi/train-*
- split: validation
path: hi/validation-*
- config_name: hu
data_files:
- split: train
path: hu/train-*
- split: validation
path: hu/validation-*
- config_name: hy
data_files:
- split: train
path: hy/train-*
- split: validation
path: hy/validation-*
- config_name: id
data_files:
- split: train
path: id/train-*
- split: validation
path: id/validation-*
- config_name: is
data_files:
- split: train
path: is/train-*
- split: validation
path: is/validation-*
- config_name: it
data_files:
- split: train
path: it/train-*
- split: validation
path: it/validation-*
- config_name: ja
data_files:
- split: train
path: ja/train-*
- split: validation
path: ja/validation-*
- config_name: jv
data_files:
- split: train
path: jv/train-*
- split: validation
path: jv/validation-*
- config_name: ka
data_files:
- split: train
path: ka/train-*
- split: validation
path: ka/validation-*
- config_name: km
data_files:
- split: train
path: km/train-*
- split: validation
path: km/validation-*
- config_name: kn
data_files:
- split: train
path: kn/train-*
- split: validation
path: kn/validation-*
- config_name: ko
data_files:
- split: train
path: ko/train-*
- split: validation
path: ko/validation-*
- config_name: lv
data_files:
- split: train
path: lv/train-*
- split: validation
path: lv/validation-*
- config_name: ml
data_files:
- split: train
path: ml/train-*
- split: validation
path: ml/validation-*
- config_name: mn
data_files:
- split: train
path: mn/train-*
- split: validation
path: mn/validation-*
- config_name: ms
data_files:
- split: train
path: ms/train-*
- split: validation
path: ms/validation-*
- config_name: my
data_files:
- split: train
path: my/train-*
- split: validation
path: my/validation-*
- config_name: nb
data_files:
- split: train
path: nb/train-*
- split: validation
path: nb/validation-*
- config_name: nl
data_files:
- split: train
path: nl/train-*
- split: validation
path: nl/validation-*
- config_name: pl
data_files:
- split: train
path: pl/train-*
- split: validation
path: pl/validation-*
- config_name: pt
data_files:
- split: train
path: pt/train-*
- split: validation
path: pt/validation-*
- config_name: ro
data_files:
- split: train
path: ro/train-*
- split: validation
path: ro/validation-*
- config_name: ru
data_files:
- split: train
path: ru/train-*
- split: validation
path: ru/validation-*
- config_name: sl
data_files:
- split: train
path: sl/train-*
- split: validation
path: sl/validation-*
- config_name: sq
data_files:
- split: train
path: sq/train-*
- split: validation
path: sq/validation-*
- config_name: sv
data_files:
- split: train
path: sv/train-*
- split: validation
path: sv/validation-*
- config_name: sw
data_files:
- split: train
path: sw/train-*
- split: validation
path: sw/validation-*
- config_name: ta
data_files:
- split: train
path: ta/train-*
- split: validation
path: ta/validation-*
- config_name: te
data_files:
- split: train
path: te/train-*
- split: validation
path: te/validation-*
- config_name: th
data_files:
- split: train
path: th/train-*
- split: validation
path: th/validation-*
- config_name: tl
data_files:
- split: train
path: tl/train-*
- split: validation
path: tl/validation-*
- config_name: tr
data_files:
- split: train
path: tr/train-*
- split: validation
path: tr/validation-*
- config_name: ur
data_files:
- split: train
path: ur/train-*
- split: validation
path: ur/validation-*
- config_name: vi
data_files:
- split: train
path: vi/train-*
- split: validation
path: vi/validation-*
- config_name: zh
data_files:
- split: train
path: zh/train-*
- split: validation
path: zh/validation-*
---

原始信息汇总

数据集概述

数据集配置信息

配置名称	特征
af	- is_true: int64<br>- statement: string
am	- is_true: int64<br>- statement: string
ar	- is_true: int64<br>- statement: string
az	- is_true: int64<br>- statement: string
bn	- is_true: int64<br>- statement: string
ca	- is_true: int64<br>- statement: string
cy	- is_true: int64<br>- statement: string
da	- is_true: int64<br>- statement: string
de	- is_true: int64<br>- statement: string
el	- is_true: int64<br>- statement: string
en	- is_true: int64<br>- statement: string
es	- is_true: int64<br>- statement: string
fa	- is_true: int64<br>- statement: string
fi	- is_true: int64<br>- statement: string
fr	- is_true: int64<br>- statement: string
he	- is_true: int64<br>- statement: string
hi	- is_true: int64<br>- statement: string
hu	- is_true: int64<br>- statement: string
hy	- is_true: int64<br>- statement: string
id	- is_true: int64<br>- statement: string
is	- is_true: int64<br>- statement: string
it	- is_true: int64<br>- statement: string
ja	- is_true: int64<br>- statement: string
jv	- is_true: int64<br>- statement: string
ka	- is_true: int64<br>- statement: string
km	- is_true: int64<br>- statement: string
kn	- is_true: int64<br>- statement: string
ko	- is_true: int64<br>- statement: string
lv	- is_true: int64<br>- statement: string
ml	- is_true: int64<br>- statement: string
mn	- is_true: int64<br>- statement: string
ms	- is_true: int64<br>- statement: string
my	- is_true: int64<br>- statement: string
nb	- is_true: int64<br>- statement: string
nl	- is_true: int64<br>- statement: string
pl	- is_true: int64<br>- statement: string
pt	- is_true: int64<br>- statement: string
ro	- is_true: int64<br>- statement: string
ru	- is_true: int64<br>- statement: string
sl	- is_true: int64<br>- statement: string
sq	- is_true: int64<br>- statement: string
sv	- is_true: int64<br>- statement: string
sw	- is_true: int64<br>- statement: string
ta	- is_true: int64<br>- statement: string
te	- is_true: int64<br>- statement: string
th	- is_true: int64<br>- statement: string
tl	- is_true: int64<br>- statement: string
tr	- is_true: int64<br>- statement: string
ur	- is_true: int64<br>- statement: string
vi	- is_true: int64<br>- statement: string
zh	- is_true: int64<br>- statement: string

数据集大小信息

配置名称	下载大小	数据集大小	训练集大小	验证集大小
af	452635	1304624	1109678	194946
am	572604	1640719	1394162	246557
ar	497064	1453398	1234663	218735
az	466948	1374084	1168998	205086
bn	619285	2051599	1745554	306045
ca	459837	1337393	1137106	200287
cy	463573	1324256	1126063	198193
da	439422	1277839	1086468	191371
de	471920	1337495	1136675	200820
el	617657	1812193	1541312	270881
en	432014	1271726	1080913	190813
es	468903	1344252	1143140	201112
fa	531007	1618492	1377230	241262
fi	459957	1321947	1124055	197892
fr	484562	1388496	1180442	208054
he	501370	1500654	1276756	223898
hi	630394	2048985	1744363	304622
hu	481633	1342261	1142165	200096
hy	575589	1732141	1474892	257249
id	436382	1312343	1116139	196204
is	474230	1358410	1155592	202818
it	451912	1320162	1122823	197339
ja	479002	1408819	1197285	211534
jv	435160	1270086	1080906	189180
ka	578561	1978656	1683984	294672
km	609001	2023314	1718683	304631
kn	667729	2240100	1906568	333532
ko	454881	1321608	1123574	198034
lv	471652	1338679	1138666	200013
ml	710476	2436827	2073281	363546
mn	580653	1762831	1497928	264903
ms	445132	1337332	1137681	199651
my	702009	2369262	2017787	351475
nb	442418	1281597	1089702	191895
nl	464776	1335442	1135536	199906
pl	462681	1317155	1120033	197122
pt	462950	1333479	1134461	199018
ro	471338	1315334	1118842	196492
ru	592187	1720529	1463069	257460
sl	454072	1291630	1098532	193098
sq	464347	1352558	1150187	202371
sv	443326	1297671	1102727	194944
sw	445321	1316951	1119426	197525
ta	695231	2409479	2049351	360128
te	686919	2220741	1889870	330871
th	623773	1992500	1693456	299044
tl	475408	1402386	1194061	208325
tr	456796	1309161	1113859	195302
ur	554250	1650970	1404468	246502
vi	501700	1478798	1257367	221431
zh	470045	1179823	1003514	176309

数据集分割信息

配置名称	训练集路径	验证集路径
af	af/train-*	af/validation-*
am	am/train-*	am/validation-*
ar	ar/train-*	ar/validation-*
az	az/train-*	az/validation-*
bn	bn/train-*	bn/validation-*
ca	ca/train-*	ca/validation-*
cy	cy/train-*	cy/validation-*
da	da/train-*	da/validation-*
de	de/train-*	de/validation-*
el	el/train-*	el/validation-*
en	en/train-*	en/validation-*
es	es/train-*	es/validation-*
fa	fa/train-*	fa/validation-*
fi	fi/train-*	fi/validation-*
fr	fr/train-*	fr/validation-*
he	he/train-*	he/validation-*
hi	hi/train-*	hi/validation-*
hu	hu/train-*	hu/validation-*
hy	hy/train-*	hy/validation-*
id	id/train-*	id/validation-*
is	is/train-*	is/validation-*
it	it/train-*	it/validation-*
ja	ja/train-*	ja/validation-*
jv	jv/train-*	jv/validation-*
ka	ka/train-*	ka/validation-*
km	km/train-*	km/validation-*
kn	kn/train-*	kn/validation-*
ko	ko/train-*	ko/validation-*
lv	lv/train-*	lv/validation-*
ml	ml/train-*	ml/validation-*
mn	mn/train-*	mn/validation-*
ms	ms/train-*	ms/validation-*
my	my/train-*	my/validation-*
nb	nb/train-*	nb/validation-*
nl	nl/train-*	nl/validation-*
pl	pl/train-*	pl/validation-*
pt	pt/train-*	pt/validation-*
ro	ro/train-*	ro/validation-*
ru	ru/train-*	ru/validation-*
sl	sl/train-*	sl/validation-*
sq	sq/train-*	sq/validation-*
sv	sv/train-*	sv/validation-*
sw	sw/train-*	sw/validation-*
ta	ta/train-*	ta/validation-*
te	te/train-*	te/validation-*
th	th/train-*	th/validation-*
tl	tl/train-*	tl/validation-*
tr	tr/train-*	tr/validation-*
ur	ur/train-*	ur/validation-*
vi	vi/train-*	vi/validation-*
zh	zh/train-*	zh/validation-*