davanstrien's picture
davanstrien HF Staff
Release selected document-purpose classifier and inference example
3055b70 verified
Raw History Blame Contribute Delete
62.3 kB
{
"source_repo": "HuggingFaceFW/finepdfs-edu",
"source_revision": "66d9c1cc13ac934468e580442ee9e6d386dd1749",
"source_rows": 23023372,
"target_rows": 230234,
"seed": 20260909,
"sampling_method": "Exact rounded 1% eng_Latn source-row target, allocated across all 100 files proportionally to footer row counts using integer largest remainders (path breaks ties). Per file, seed=20260909+sorted_file_index; shuffle all row groups with random.Random(seed) and retain groups until their pooled rows meet the quota. Runtime reads selected groups, then random.Random(seed).sample(pooled_rows, quota), sorting retained rows by file_row_number. No historical exclusions or ID/text deduplication. One output per sampled source position; eligibility is applied afterward. A clustered sample, not IID or uniform document inclusion.",
"files": [
{
"path": "eng_Latn/train/0000.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0000.parquet",
"source_rows": 236144,
"quota": 2361,
"groups": [
{
"row_group_id": 89,
"start": 89000,
"end": 90000
},
{
"row_group_id": 95,
"start": 95000,
"end": 96000
},
{
"row_group_id": 134,
"start": 134000,
"end": 135000
}
],
"seed": 20260909
},
{
"path": "eng_Latn/train/0001.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0001.parquet",
"source_rows": 239573,
"quota": 2396,
"groups": [
{
"row_group_id": 176,
"start": 176000,
"end": 177000
},
{
"row_group_id": 194,
"start": 194000,
"end": 195000
},
{
"row_group_id": 212,
"start": 212000,
"end": 213000
}
],
"seed": 20260910
},
{
"path": "eng_Latn/train/0002.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0002.parquet",
"source_rows": 236024,
"quota": 2360,
"groups": [
{
"row_group_id": 147,
"start": 147000,
"end": 148000
},
{
"row_group_id": 232,
"start": 232000,
"end": 233000
},
{
"row_group_id": 131,
"start": 131000,
"end": 132000
}
],
"seed": 20260911
},
{
"path": "eng_Latn/train/0003.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0003.parquet",
"source_rows": 236753,
"quota": 2368,
"groups": [
{
"row_group_id": 96,
"start": 96000,
"end": 97000
},
{
"row_group_id": 46,
"start": 46000,
"end": 47000
},
{
"row_group_id": 88,
"start": 88000,
"end": 89000
}
],
"seed": 20260912
},
{
"path": "eng_Latn/train/0004.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0004.parquet",
"source_rows": 236594,
"quota": 2366,
"groups": [
{
"row_group_id": 191,
"start": 191000,
"end": 192000
},
{
"row_group_id": 227,
"start": 227000,
"end": 228000
},
{
"row_group_id": 28,
"start": 28000,
"end": 29000
}
],
"seed": 20260913
},
{
"path": "eng_Latn/train/0005.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0005.parquet",
"source_rows": 235500,
"quota": 2355,
"groups": [
{
"row_group_id": 143,
"start": 143000,
"end": 144000
},
{
"row_group_id": 226,
"start": 226000,
"end": 227000
},
{
"row_group_id": 126,
"start": 126000,
"end": 127000
}
],
"seed": 20260914
},
{
"path": "eng_Latn/train/0006.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0006.parquet",
"source_rows": 237979,
"quota": 2380,
"groups": [
{
"row_group_id": 56,
"start": 56000,
"end": 57000
},
{
"row_group_id": 225,
"start": 225000,
"end": 226000
},
{
"row_group_id": 205,
"start": 205000,
"end": 206000
}
],
"seed": 20260915
},
{
"path": "eng_Latn/train/0007.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0007.parquet",
"source_rows": 236429,
"quota": 2364,
"groups": [
{
"row_group_id": 20,
"start": 20000,
"end": 21000
},
{
"row_group_id": 107,
"start": 107000,
"end": 108000
},
{
"row_group_id": 54,
"start": 54000,
"end": 55000
}
],
"seed": 20260916
},
{
"path": "eng_Latn/train/0008.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0008.parquet",
"source_rows": 237139,
"quota": 2371,
"groups": [
{
"row_group_id": 43,
"start": 43000,
"end": 44000
},
{
"row_group_id": 168,
"start": 168000,
"end": 169000
},
{
"row_group_id": 131,
"start": 131000,
"end": 132000
}
],
"seed": 20260917
},
{
"path": "eng_Latn/train/0009.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0009.parquet",
"source_rows": 237447,
"quota": 2374,
"groups": [
{
"row_group_id": 79,
"start": 79000,
"end": 80000
},
{
"row_group_id": 145,
"start": 145000,
"end": 146000
},
{
"row_group_id": 112,
"start": 112000,
"end": 113000
}
],
"seed": 20260918
},
{
"path": "eng_Latn/train/0010.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0010.parquet",
"source_rows": 235406,
"quota": 2354,
"groups": [
{
"row_group_id": 78,
"start": 78000,
"end": 79000
},
{
"row_group_id": 62,
"start": 62000,
"end": 63000
},
{
"row_group_id": 181,
"start": 181000,
"end": 182000
}
],
"seed": 20260919
},
{
"path": "eng_Latn/train/0011.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0011.parquet",
"source_rows": 236241,
"quota": 2362,
"groups": [
{
"row_group_id": 60,
"start": 60000,
"end": 61000
},
{
"row_group_id": 221,
"start": 221000,
"end": 222000
},
{
"row_group_id": 0,
"start": 0,
"end": 1000
}
],
"seed": 20260920
},
{
"path": "eng_Latn/train/0012.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0012.parquet",
"source_rows": 237278,
"quota": 2373,
"groups": [
{
"row_group_id": 29,
"start": 29000,
"end": 30000
},
{
"row_group_id": 20,
"start": 20000,
"end": 21000
},
{
"row_group_id": 132,
"start": 132000,
"end": 133000
}
],
"seed": 20260921
},
{
"path": "eng_Latn/train/0013.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0013.parquet",
"source_rows": 235160,
"quota": 2352,
"groups": [
{
"row_group_id": 179,
"start": 179000,
"end": 180000
},
{
"row_group_id": 0,
"start": 0,
"end": 1000
},
{
"row_group_id": 3,
"start": 3000,
"end": 4000
}
],
"seed": 20260922
},
{
"path": "eng_Latn/train/0014.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0014.parquet",
"source_rows": 234293,
"quota": 2343,
"groups": [
{
"row_group_id": 225,
"start": 225000,
"end": 226000
},
{
"row_group_id": 190,
"start": 190000,
"end": 191000
},
{
"row_group_id": 49,
"start": 49000,
"end": 50000
}
],
"seed": 20260923
},
{
"path": "eng_Latn/train/0015.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0015.parquet",
"source_rows": 235147,
"quota": 2351,
"groups": [
{
"row_group_id": 97,
"start": 97000,
"end": 98000
},
{
"row_group_id": 23,
"start": 23000,
"end": 24000
},
{
"row_group_id": 45,
"start": 45000,
"end": 46000
}
],
"seed": 20260924
},
{
"path": "eng_Latn/train/0016.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0016.parquet",
"source_rows": 234821,
"quota": 2348,
"groups": [
{
"row_group_id": 142,
"start": 142000,
"end": 143000
},
{
"row_group_id": 166,
"start": 166000,
"end": 167000
},
{
"row_group_id": 50,
"start": 50000,
"end": 51000
}
],
"seed": 20260925
},
{
"path": "eng_Latn/train/0017.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0017.parquet",
"source_rows": 233195,
"quota": 2332,
"groups": [
{
"row_group_id": 81,
"start": 81000,
"end": 82000
},
{
"row_group_id": 233,
"start": 233000,
"end": 233195
},
{
"row_group_id": 151,
"start": 151000,
"end": 152000
},
{
"row_group_id": 98,
"start": 98000,
"end": 99000
}
],
"seed": 20260926
},
{
"path": "eng_Latn/train/0018.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0018.parquet",
"source_rows": 236800,
"quota": 2368,
"groups": [
{
"row_group_id": 75,
"start": 75000,
"end": 76000
},
{
"row_group_id": 113,
"start": 113000,
"end": 114000
},
{
"row_group_id": 164,
"start": 164000,
"end": 165000
}
],
"seed": 20260927
},
{
"path": "eng_Latn/train/0019.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0019.parquet",
"source_rows": 233399,
"quota": 2334,
"groups": [
{
"row_group_id": 31,
"start": 31000,
"end": 32000
},
{
"row_group_id": 127,
"start": 127000,
"end": 128000
},
{
"row_group_id": 74,
"start": 74000,
"end": 75000
}
],
"seed": 20260928
},
{
"path": "eng_Latn/train/0020.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0020.parquet",
"source_rows": 236750,
"quota": 2368,
"groups": [
{
"row_group_id": 130,
"start": 130000,
"end": 131000
},
{
"row_group_id": 72,
"start": 72000,
"end": 73000
},
{
"row_group_id": 138,
"start": 138000,
"end": 139000
}
],
"seed": 20260929
},
{
"path": "eng_Latn/train/0021.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0021.parquet",
"source_rows": 235882,
"quota": 2359,
"groups": [
{
"row_group_id": 202,
"start": 202000,
"end": 203000
},
{
"row_group_id": 86,
"start": 86000,
"end": 87000
},
{
"row_group_id": 198,
"start": 198000,
"end": 199000
}
],
"seed": 20260930
},
{
"path": "eng_Latn/train/0022.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0022.parquet",
"source_rows": 234423,
"quota": 2344,
"groups": [
{
"row_group_id": 54,
"start": 54000,
"end": 55000
},
{
"row_group_id": 57,
"start": 57000,
"end": 58000
},
{
"row_group_id": 231,
"start": 231000,
"end": 232000
}
],
"seed": 20260931
},
{
"path": "eng_Latn/train/0023.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0023.parquet",
"source_rows": 233702,
"quota": 2337,
"groups": [
{
"row_group_id": 63,
"start": 63000,
"end": 64000
},
{
"row_group_id": 233,
"start": 233000,
"end": 233702
},
{
"row_group_id": 11,
"start": 11000,
"end": 12000
}
],
"seed": 20260932
},
{
"path": "eng_Latn/train/0024.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0024.parquet",
"source_rows": 235755,
"quota": 2358,
"groups": [
{
"row_group_id": 44,
"start": 44000,
"end": 45000
},
{
"row_group_id": 164,
"start": 164000,
"end": 165000
},
{
"row_group_id": 222,
"start": 222000,
"end": 223000
}
],
"seed": 20260933
},
{
"path": "eng_Latn/train/0025.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0025.parquet",
"source_rows": 234439,
"quota": 2344,
"groups": [
{
"row_group_id": 175,
"start": 175000,
"end": 176000
},
{
"row_group_id": 157,
"start": 157000,
"end": 158000
},
{
"row_group_id": 204,
"start": 204000,
"end": 205000
}
],
"seed": 20260934
},
{
"path": "eng_Latn/train/0026.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0026.parquet",
"source_rows": 232456,
"quota": 2325,
"groups": [
{
"row_group_id": 159,
"start": 159000,
"end": 160000
},
{
"row_group_id": 69,
"start": 69000,
"end": 70000
},
{
"row_group_id": 90,
"start": 90000,
"end": 91000
}
],
"seed": 20260935
},
{
"path": "eng_Latn/train/0027.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0027.parquet",
"source_rows": 233655,
"quota": 2337,
"groups": [
{
"row_group_id": 215,
"start": 215000,
"end": 216000
},
{
"row_group_id": 91,
"start": 91000,
"end": 92000
},
{
"row_group_id": 16,
"start": 16000,
"end": 17000
}
],
"seed": 20260936
},
{
"path": "eng_Latn/train/0028.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0028.parquet",
"source_rows": 233542,
"quota": 2335,
"groups": [
{
"row_group_id": 229,
"start": 229000,
"end": 230000
},
{
"row_group_id": 218,
"start": 218000,
"end": 219000
},
{
"row_group_id": 186,
"start": 186000,
"end": 187000
}
],
"seed": 20260937
},
{
"path": "eng_Latn/train/0029.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0029.parquet",
"source_rows": 233072,
"quota": 2331,
"groups": [
{
"row_group_id": 100,
"start": 100000,
"end": 101000
},
{
"row_group_id": 73,
"start": 73000,
"end": 74000
},
{
"row_group_id": 38,
"start": 38000,
"end": 39000
}
],
"seed": 20260938
},
{
"path": "eng_Latn/train/0030.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0030.parquet",
"source_rows": 232051,
"quota": 2321,
"groups": [
{
"row_group_id": 42,
"start": 42000,
"end": 43000
},
{
"row_group_id": 146,
"start": 146000,
"end": 147000
},
{
"row_group_id": 223,
"start": 223000,
"end": 224000
}
],
"seed": 20260939
},
{
"path": "eng_Latn/train/0031.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0031.parquet",
"source_rows": 235338,
"quota": 2353,
"groups": [
{
"row_group_id": 75,
"start": 75000,
"end": 76000
},
{
"row_group_id": 215,
"start": 215000,
"end": 216000
},
{
"row_group_id": 182,
"start": 182000,
"end": 183000
}
],
"seed": 20260940
},
{
"path": "eng_Latn/train/0032.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0032.parquet",
"source_rows": 232434,
"quota": 2324,
"groups": [
{
"row_group_id": 12,
"start": 12000,
"end": 13000
},
{
"row_group_id": 106,
"start": 106000,
"end": 107000
},
{
"row_group_id": 222,
"start": 222000,
"end": 223000
}
],
"seed": 20260941
},
{
"path": "eng_Latn/train/0033.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0033.parquet",
"source_rows": 230504,
"quota": 2305,
"groups": [
{
"row_group_id": 67,
"start": 67000,
"end": 68000
},
{
"row_group_id": 43,
"start": 43000,
"end": 44000
},
{
"row_group_id": 48,
"start": 48000,
"end": 49000
}
],
"seed": 20260942
},
{
"path": "eng_Latn/train/0034.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0034.parquet",
"source_rows": 233591,
"quota": 2336,
"groups": [
{
"row_group_id": 215,
"start": 215000,
"end": 216000
},
{
"row_group_id": 185,
"start": 185000,
"end": 186000
},
{
"row_group_id": 89,
"start": 89000,
"end": 90000
}
],
"seed": 20260943
},
{
"path": "eng_Latn/train/0035.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0035.parquet",
"source_rows": 232872,
"quota": 2329,
"groups": [
{
"row_group_id": 59,
"start": 59000,
"end": 60000
},
{
"row_group_id": 27,
"start": 27000,
"end": 28000
},
{
"row_group_id": 144,
"start": 144000,
"end": 145000
}
],
"seed": 20260944
},
{
"path": "eng_Latn/train/0036.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0036.parquet",
"source_rows": 233138,
"quota": 2331,
"groups": [
{
"row_group_id": 91,
"start": 91000,
"end": 92000
},
{
"row_group_id": 39,
"start": 39000,
"end": 40000
},
{
"row_group_id": 228,
"start": 228000,
"end": 229000
}
],
"seed": 20260945
},
{
"path": "eng_Latn/train/0037.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0037.parquet",
"source_rows": 232820,
"quota": 2328,
"groups": [
{
"row_group_id": 172,
"start": 172000,
"end": 173000
},
{
"row_group_id": 58,
"start": 58000,
"end": 59000
},
{
"row_group_id": 114,
"start": 114000,
"end": 115000
}
],
"seed": 20260946
},
{
"path": "eng_Latn/train/0038.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0038.parquet",
"source_rows": 231984,
"quota": 2320,
"groups": [
{
"row_group_id": 31,
"start": 31000,
"end": 32000
},
{
"row_group_id": 33,
"start": 33000,
"end": 34000
},
{
"row_group_id": 212,
"start": 212000,
"end": 213000
}
],
"seed": 20260947
},
{
"path": "eng_Latn/train/0039.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0039.parquet",
"source_rows": 235387,
"quota": 2354,
"groups": [
{
"row_group_id": 157,
"start": 157000,
"end": 158000
},
{
"row_group_id": 177,
"start": 177000,
"end": 178000
},
{
"row_group_id": 78,
"start": 78000,
"end": 79000
}
],
"seed": 20260948
},
{
"path": "eng_Latn/train/0040.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0040.parquet",
"source_rows": 232320,
"quota": 2323,
"groups": [
{
"row_group_id": 34,
"start": 34000,
"end": 35000
},
{
"row_group_id": 184,
"start": 184000,
"end": 185000
},
{
"row_group_id": 16,
"start": 16000,
"end": 17000
}
],
"seed": 20260949
},
{
"path": "eng_Latn/train/0041.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0041.parquet",
"source_rows": 233810,
"quota": 2338,
"groups": [
{
"row_group_id": 172,
"start": 172000,
"end": 173000
},
{
"row_group_id": 31,
"start": 31000,
"end": 32000
},
{
"row_group_id": 216,
"start": 216000,
"end": 217000
}
],
"seed": 20260950
},
{
"path": "eng_Latn/train/0042.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0042.parquet",
"source_rows": 231187,
"quota": 2312,
"groups": [
{
"row_group_id": 150,
"start": 150000,
"end": 151000
},
{
"row_group_id": 176,
"start": 176000,
"end": 177000
},
{
"row_group_id": 45,
"start": 45000,
"end": 46000
}
],
"seed": 20260951
},
{
"path": "eng_Latn/train/0043.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0043.parquet",
"source_rows": 233533,
"quota": 2335,
"groups": [
{
"row_group_id": 175,
"start": 175000,
"end": 176000
},
{
"row_group_id": 54,
"start": 54000,
"end": 55000
},
{
"row_group_id": 42,
"start": 42000,
"end": 43000
}
],
"seed": 20260952
},
{
"path": "eng_Latn/train/0044.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0044.parquet",
"source_rows": 231543,
"quota": 2315,
"groups": [
{
"row_group_id": 105,
"start": 105000,
"end": 106000
},
{
"row_group_id": 154,
"start": 154000,
"end": 155000
},
{
"row_group_id": 181,
"start": 181000,
"end": 182000
}
],
"seed": 20260953
},
{
"path": "eng_Latn/train/0045.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0045.parquet",
"source_rows": 232079,
"quota": 2321,
"groups": [
{
"row_group_id": 182,
"start": 182000,
"end": 183000
},
{
"row_group_id": 21,
"start": 21000,
"end": 22000
},
{
"row_group_id": 34,
"start": 34000,
"end": 35000
}
],
"seed": 20260954
},
{
"path": "eng_Latn/train/0046.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0046.parquet",
"source_rows": 232372,
"quota": 2324,
"groups": [
{
"row_group_id": 198,
"start": 198000,
"end": 199000
},
{
"row_group_id": 11,
"start": 11000,
"end": 12000
},
{
"row_group_id": 214,
"start": 214000,
"end": 215000
}
],
"seed": 20260955
},
{
"path": "eng_Latn/train/0047.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0047.parquet",
"source_rows": 233217,
"quota": 2332,
"groups": [
{
"row_group_id": 2,
"start": 2000,
"end": 3000
},
{
"row_group_id": 59,
"start": 59000,
"end": 60000
},
{
"row_group_id": 159,
"start": 159000,
"end": 160000
}
],
"seed": 20260956
},
{
"path": "eng_Latn/train/0048.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0048.parquet",
"source_rows": 231000,
"quota": 2310,
"groups": [
{
"row_group_id": 208,
"start": 208000,
"end": 209000
},
{
"row_group_id": 113,
"start": 113000,
"end": 114000
},
{
"row_group_id": 209,
"start": 209000,
"end": 210000
}
],
"seed": 20260957
},
{
"path": "eng_Latn/train/0049.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0049.parquet",
"source_rows": 230367,
"quota": 2304,
"groups": [
{
"row_group_id": 50,
"start": 50000,
"end": 51000
},
{
"row_group_id": 20,
"start": 20000,
"end": 21000
},
{
"row_group_id": 136,
"start": 136000,
"end": 137000
}
],
"seed": 20260958
},
{
"path": "eng_Latn/train/0050.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0050.parquet",
"source_rows": 232297,
"quota": 2323,
"groups": [
{
"row_group_id": 97,
"start": 97000,
"end": 98000
},
{
"row_group_id": 102,
"start": 102000,
"end": 103000
},
{
"row_group_id": 119,
"start": 119000,
"end": 120000
}
],
"seed": 20260959
},
{
"path": "eng_Latn/train/0051.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0051.parquet",
"source_rows": 232381,
"quota": 2324,
"groups": [
{
"row_group_id": 151,
"start": 151000,
"end": 152000
},
{
"row_group_id": 85,
"start": 85000,
"end": 86000
},
{
"row_group_id": 99,
"start": 99000,
"end": 100000
}
],
"seed": 20260960
},
{
"path": "eng_Latn/train/0052.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0052.parquet",
"source_rows": 230294,
"quota": 2303,
"groups": [
{
"row_group_id": 13,
"start": 13000,
"end": 14000
},
{
"row_group_id": 226,
"start": 226000,
"end": 227000
},
{
"row_group_id": 150,
"start": 150000,
"end": 151000
}
],
"seed": 20260961
},
{
"path": "eng_Latn/train/0053.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0053.parquet",
"source_rows": 234418,
"quota": 2344,
"groups": [
{
"row_group_id": 79,
"start": 79000,
"end": 80000
},
{
"row_group_id": 234,
"start": 234000,
"end": 234418
},
{
"row_group_id": 142,
"start": 142000,
"end": 143000
}
],
"seed": 20260962
},
{
"path": "eng_Latn/train/0054.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0054.parquet",
"source_rows": 232489,
"quota": 2325,
"groups": [
{
"row_group_id": 81,
"start": 81000,
"end": 82000
},
{
"row_group_id": 112,
"start": 112000,
"end": 113000
},
{
"row_group_id": 197,
"start": 197000,
"end": 198000
}
],
"seed": 20260963
},
{
"path": "eng_Latn/train/0055.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0055.parquet",
"source_rows": 230166,
"quota": 2302,
"groups": [
{
"row_group_id": 29,
"start": 29000,
"end": 30000
},
{
"row_group_id": 104,
"start": 104000,
"end": 105000
},
{
"row_group_id": 103,
"start": 103000,
"end": 104000
}
],
"seed": 20260964
},
{
"path": "eng_Latn/train/0056.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0056.parquet",
"source_rows": 231394,
"quota": 2314,
"groups": [
{
"row_group_id": 79,
"start": 79000,
"end": 80000
},
{
"row_group_id": 18,
"start": 18000,
"end": 19000
},
{
"row_group_id": 165,
"start": 165000,
"end": 166000
}
],
"seed": 20260965
},
{
"path": "eng_Latn/train/0057.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0057.parquet",
"source_rows": 231546,
"quota": 2315,
"groups": [
{
"row_group_id": 31,
"start": 31000,
"end": 32000
},
{
"row_group_id": 159,
"start": 159000,
"end": 160000
},
{
"row_group_id": 162,
"start": 162000,
"end": 163000
}
],
"seed": 20260966
},
{
"path": "eng_Latn/train/0058.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0058.parquet",
"source_rows": 233613,
"quota": 2336,
"groups": [
{
"row_group_id": 200,
"start": 200000,
"end": 201000
},
{
"row_group_id": 71,
"start": 71000,
"end": 72000
},
{
"row_group_id": 191,
"start": 191000,
"end": 192000
}
],
"seed": 20260967
},
{
"path": "eng_Latn/train/0059.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0059.parquet",
"source_rows": 232475,
"quota": 2325,
"groups": [
{
"row_group_id": 178,
"start": 178000,
"end": 179000
},
{
"row_group_id": 117,
"start": 117000,
"end": 118000
},
{
"row_group_id": 121,
"start": 121000,
"end": 122000
}
],
"seed": 20260968
},
{
"path": "eng_Latn/train/0060.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0060.parquet",
"source_rows": 230236,
"quota": 2302,
"groups": [
{
"row_group_id": 118,
"start": 118000,
"end": 119000
},
{
"row_group_id": 194,
"start": 194000,
"end": 195000
},
{
"row_group_id": 64,
"start": 64000,
"end": 65000
}
],
"seed": 20260969
},
{
"path": "eng_Latn/train/0061.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0061.parquet",
"source_rows": 228267,
"quota": 2283,
"groups": [
{
"row_group_id": 71,
"start": 71000,
"end": 72000
},
{
"row_group_id": 181,
"start": 181000,
"end": 182000
},
{
"row_group_id": 108,
"start": 108000,
"end": 109000
}
],
"seed": 20260970
},
{
"path": "eng_Latn/train/0062.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0062.parquet",
"source_rows": 228466,
"quota": 2285,
"groups": [
{
"row_group_id": 43,
"start": 43000,
"end": 44000
},
{
"row_group_id": 154,
"start": 154000,
"end": 155000
},
{
"row_group_id": 129,
"start": 129000,
"end": 130000
}
],
"seed": 20260971
},
{
"path": "eng_Latn/train/0063.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0063.parquet",
"source_rows": 228549,
"quota": 2285,
"groups": [
{
"row_group_id": 155,
"start": 155000,
"end": 156000
},
{
"row_group_id": 75,
"start": 75000,
"end": 76000
},
{
"row_group_id": 202,
"start": 202000,
"end": 203000
}
],
"seed": 20260972
},
{
"path": "eng_Latn/train/0064.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0064.parquet",
"source_rows": 228683,
"quota": 2287,
"groups": [
{
"row_group_id": 211,
"start": 211000,
"end": 212000
},
{
"row_group_id": 16,
"start": 16000,
"end": 17000
},
{
"row_group_id": 31,
"start": 31000,
"end": 32000
}
],
"seed": 20260973
},
{
"path": "eng_Latn/train/0065.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0065.parquet",
"source_rows": 229880,
"quota": 2299,
"groups": [
{
"row_group_id": 141,
"start": 141000,
"end": 142000
},
{
"row_group_id": 18,
"start": 18000,
"end": 19000
},
{
"row_group_id": 43,
"start": 43000,
"end": 44000
}
],
"seed": 20260974
},
{
"path": "eng_Latn/train/0066.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0066.parquet",
"source_rows": 225676,
"quota": 2257,
"groups": [
{
"row_group_id": 96,
"start": 96000,
"end": 97000
},
{
"row_group_id": 91,
"start": 91000,
"end": 92000
},
{
"row_group_id": 43,
"start": 43000,
"end": 44000
}
],
"seed": 20260975
},
{
"path": "eng_Latn/train/0067.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0067.parquet",
"source_rows": 230712,
"quota": 2307,
"groups": [
{
"row_group_id": 43,
"start": 43000,
"end": 44000
},
{
"row_group_id": 22,
"start": 22000,
"end": 23000
},
{
"row_group_id": 80,
"start": 80000,
"end": 81000
}
],
"seed": 20260976
},
{
"path": "eng_Latn/train/0068.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0068.parquet",
"source_rows": 230408,
"quota": 2304,
"groups": [
{
"row_group_id": 157,
"start": 157000,
"end": 158000
},
{
"row_group_id": 201,
"start": 201000,
"end": 202000
},
{
"row_group_id": 33,
"start": 33000,
"end": 34000
}
],
"seed": 20260977
},
{
"path": "eng_Latn/train/0069.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0069.parquet",
"source_rows": 226672,
"quota": 2267,
"groups": [
{
"row_group_id": 198,
"start": 198000,
"end": 199000
},
{
"row_group_id": 88,
"start": 88000,
"end": 89000
},
{
"row_group_id": 169,
"start": 169000,
"end": 170000
}
],
"seed": 20260978
},
{
"path": "eng_Latn/train/0070.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0070.parquet",
"source_rows": 228656,
"quota": 2287,
"groups": [
{
"row_group_id": 58,
"start": 58000,
"end": 59000
},
{
"row_group_id": 195,
"start": 195000,
"end": 196000
},
{
"row_group_id": 159,
"start": 159000,
"end": 160000
}
],
"seed": 20260979
},
{
"path": "eng_Latn/train/0071.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0071.parquet",
"source_rows": 228428,
"quota": 2284,
"groups": [
{
"row_group_id": 68,
"start": 68000,
"end": 69000
},
{
"row_group_id": 81,
"start": 81000,
"end": 82000
},
{
"row_group_id": 48,
"start": 48000,
"end": 49000
}
],
"seed": 20260980
},
{
"path": "eng_Latn/train/0072.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0072.parquet",
"source_rows": 226836,
"quota": 2268,
"groups": [
{
"row_group_id": 198,
"start": 198000,
"end": 199000
},
{
"row_group_id": 98,
"start": 98000,
"end": 99000
},
{
"row_group_id": 18,
"start": 18000,
"end": 19000
}
],
"seed": 20260981
},
{
"path": "eng_Latn/train/0073.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0073.parquet",
"source_rows": 230552,
"quota": 2306,
"groups": [
{
"row_group_id": 137,
"start": 137000,
"end": 138000
},
{
"row_group_id": 109,
"start": 109000,
"end": 110000
},
{
"row_group_id": 118,
"start": 118000,
"end": 119000
}
],
"seed": 20260982
},
{
"path": "eng_Latn/train/0074.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0074.parquet",
"source_rows": 228387,
"quota": 2284,
"groups": [
{
"row_group_id": 89,
"start": 89000,
"end": 90000
},
{
"row_group_id": 125,
"start": 125000,
"end": 126000
},
{
"row_group_id": 117,
"start": 117000,
"end": 118000
}
],
"seed": 20260983
},
{
"path": "eng_Latn/train/0075.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0075.parquet",
"source_rows": 229906,
"quota": 2299,
"groups": [
{
"row_group_id": 132,
"start": 132000,
"end": 133000
},
{
"row_group_id": 155,
"start": 155000,
"end": 156000
},
{
"row_group_id": 50,
"start": 50000,
"end": 51000
}
],
"seed": 20260984
},
{
"path": "eng_Latn/train/0076.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0076.parquet",
"source_rows": 229750,
"quota": 2297,
"groups": [
{
"row_group_id": 44,
"start": 44000,
"end": 45000
},
{
"row_group_id": 60,
"start": 60000,
"end": 61000
},
{
"row_group_id": 223,
"start": 223000,
"end": 224000
}
],
"seed": 20260985
},
{
"path": "eng_Latn/train/0077.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0077.parquet",
"source_rows": 229125,
"quota": 2291,
"groups": [
{
"row_group_id": 3,
"start": 3000,
"end": 4000
},
{
"row_group_id": 65,
"start": 65000,
"end": 66000
},
{
"row_group_id": 53,
"start": 53000,
"end": 54000
}
],
"seed": 20260986
},
{
"path": "eng_Latn/train/0078.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0078.parquet",
"source_rows": 229809,
"quota": 2298,
"groups": [
{
"row_group_id": 81,
"start": 81000,
"end": 82000
},
{
"row_group_id": 94,
"start": 94000,
"end": 95000
},
{
"row_group_id": 154,
"start": 154000,
"end": 155000
}
],
"seed": 20260987
},
{
"path": "eng_Latn/train/0079.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0079.parquet",
"source_rows": 225165,
"quota": 2252,
"groups": [
{
"row_group_id": 144,
"start": 144000,
"end": 145000
},
{
"row_group_id": 92,
"start": 92000,
"end": 93000
},
{
"row_group_id": 60,
"start": 60000,
"end": 61000
}
],
"seed": 20260988
},
{
"path": "eng_Latn/train/0080.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0080.parquet",
"source_rows": 223794,
"quota": 2238,
"groups": [
{
"row_group_id": 116,
"start": 116000,
"end": 117000
},
{
"row_group_id": 126,
"start": 126000,
"end": 127000
},
{
"row_group_id": 167,
"start": 167000,
"end": 168000
}
],
"seed": 20260989
},
{
"path": "eng_Latn/train/0081.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0081.parquet",
"source_rows": 220500,
"quota": 2205,
"groups": [
{
"row_group_id": 28,
"start": 28000,
"end": 29000
},
{
"row_group_id": 66,
"start": 66000,
"end": 67000
},
{
"row_group_id": 27,
"start": 27000,
"end": 28000
}
],
"seed": 20260990
},
{
"path": "eng_Latn/train/0082.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0082.parquet",
"source_rows": 219914,
"quota": 2199,
"groups": [
{
"row_group_id": 22,
"start": 22000,
"end": 23000
},
{
"row_group_id": 197,
"start": 197000,
"end": 198000
},
{
"row_group_id": 191,
"start": 191000,
"end": 192000
}
],
"seed": 20260991
},
{
"path": "eng_Latn/train/0083.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0083.parquet",
"source_rows": 220407,
"quota": 2204,
"groups": [
{
"row_group_id": 71,
"start": 71000,
"end": 72000
},
{
"row_group_id": 216,
"start": 216000,
"end": 217000
},
{
"row_group_id": 61,
"start": 61000,
"end": 62000
}
],
"seed": 20260992
},
{
"path": "eng_Latn/train/0084.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0084.parquet",
"source_rows": 222046,
"quota": 2220,
"groups": [
{
"row_group_id": 23,
"start": 23000,
"end": 24000
},
{
"row_group_id": 160,
"start": 160000,
"end": 161000
},
{
"row_group_id": 58,
"start": 58000,
"end": 59000
}
],
"seed": 20260993
},
{
"path": "eng_Latn/train/0085.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0085.parquet",
"source_rows": 220780,
"quota": 2208,
"groups": [
{
"row_group_id": 154,
"start": 154000,
"end": 155000
},
{
"row_group_id": 165,
"start": 165000,
"end": 166000
},
{
"row_group_id": 12,
"start": 12000,
"end": 13000
}
],
"seed": 20260994
},
{
"path": "eng_Latn/train/0086.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0086.parquet",
"source_rows": 221064,
"quota": 2211,
"groups": [
{
"row_group_id": 215,
"start": 215000,
"end": 216000
},
{
"row_group_id": 148,
"start": 148000,
"end": 149000
},
{
"row_group_id": 58,
"start": 58000,
"end": 59000
}
],
"seed": 20260995
},
{
"path": "eng_Latn/train/0087.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0087.parquet",
"source_rows": 222490,
"quota": 2225,
"groups": [
{
"row_group_id": 60,
"start": 60000,
"end": 61000
},
{
"row_group_id": 175,
"start": 175000,
"end": 176000
},
{
"row_group_id": 92,
"start": 92000,
"end": 93000
}
],
"seed": 20260996
},
{
"path": "eng_Latn/train/0088.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0088.parquet",
"source_rows": 220672,
"quota": 2207,
"groups": [
{
"row_group_id": 1,
"start": 1000,
"end": 2000
},
{
"row_group_id": 36,
"start": 36000,
"end": 37000
},
{
"row_group_id": 116,
"start": 116000,
"end": 117000
}
],
"seed": 20260997
},
{
"path": "eng_Latn/train/0089.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0089.parquet",
"source_rows": 218663,
"quota": 2187,
"groups": [
{
"row_group_id": 109,
"start": 109000,
"end": 110000
},
{
"row_group_id": 133,
"start": 133000,
"end": 134000
},
{
"row_group_id": 49,
"start": 49000,
"end": 50000
}
],
"seed": 20260998
},
{
"path": "eng_Latn/train/0090.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0090.parquet",
"source_rows": 218461,
"quota": 2185,
"groups": [
{
"row_group_id": 173,
"start": 173000,
"end": 174000
},
{
"row_group_id": 23,
"start": 23000,
"end": 24000
},
{
"row_group_id": 67,
"start": 67000,
"end": 68000
}
],
"seed": 20260999
},
{
"path": "eng_Latn/train/0091.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0091.parquet",
"source_rows": 221692,
"quota": 2217,
"groups": [
{
"row_group_id": 136,
"start": 136000,
"end": 137000
},
{
"row_group_id": 20,
"start": 20000,
"end": 21000
},
{
"row_group_id": 81,
"start": 81000,
"end": 82000
}
],
"seed": 20261000
},
{
"path": "eng_Latn/train/0092.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0092.parquet",
"source_rows": 220420,
"quota": 2204,
"groups": [
{
"row_group_id": 176,
"start": 176000,
"end": 177000
},
{
"row_group_id": 170,
"start": 170000,
"end": 171000
},
{
"row_group_id": 85,
"start": 85000,
"end": 86000
}
],
"seed": 20261001
},
{
"path": "eng_Latn/train/0093.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0093.parquet",
"source_rows": 218688,
"quota": 2187,
"groups": [
{
"row_group_id": 211,
"start": 211000,
"end": 212000
},
{
"row_group_id": 45,
"start": 45000,
"end": 46000
},
{
"row_group_id": 87,
"start": 87000,
"end": 88000
}
],
"seed": 20261002
},
{
"path": "eng_Latn/train/0094.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0094.parquet",
"source_rows": 219204,
"quota": 2192,
"groups": [
{
"row_group_id": 110,
"start": 110000,
"end": 111000
},
{
"row_group_id": 83,
"start": 83000,
"end": 84000
},
{
"row_group_id": 52,
"start": 52000,
"end": 53000
}
],
"seed": 20261003
},
{
"path": "eng_Latn/train/0095.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0095.parquet",
"source_rows": 221135,
"quota": 2211,
"groups": [
{
"row_group_id": 161,
"start": 161000,
"end": 162000
},
{
"row_group_id": 178,
"start": 178000,
"end": 179000
},
{
"row_group_id": 36,
"start": 36000,
"end": 37000
}
],
"seed": 20261004
},
{
"path": "eng_Latn/train/0096.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0096.parquet",
"source_rows": 221741,
"quota": 2217,
"groups": [
{
"row_group_id": 8,
"start": 8000,
"end": 9000
},
{
"row_group_id": 196,
"start": 196000,
"end": 197000
},
{
"row_group_id": 100,
"start": 100000,
"end": 101000
}
],
"seed": 20261005
},
{
"path": "eng_Latn/train/0097.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0097.parquet",
"source_rows": 219432,
"quota": 2194,
"groups": [
{
"row_group_id": 197,
"start": 197000,
"end": 198000
},
{
"row_group_id": 82,
"start": 82000,
"end": 83000
},
{
"row_group_id": 176,
"start": 176000,
"end": 177000
}
],
"seed": 20261006
},
{
"path": "eng_Latn/train/0098.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0098.parquet",
"source_rows": 218862,
"quota": 2189,
"groups": [
{
"row_group_id": 36,
"start": 36000,
"end": 37000
},
{
"row_group_id": 51,
"start": 51000,
"end": 52000
},
{
"row_group_id": 179,
"start": 179000,
"end": 180000
}
],
"seed": 20261007
},
{
"path": "eng_Latn/train/0099.parquet",
"url": "https://huggingface.co/datasets/HuggingFaceFW/finepdfs-edu/resolve/66d9c1cc13ac934468e580442ee9e6d386dd1749/eng_Latn/train/0099.parquet",
"source_rows": 221626,
"quota": 2216,
"groups": [
{
"row_group_id": 98,
"start": 98000,
"end": 99000
},
{
"row_group_id": 161,
"start": 161000,
"end": 162000
},
{
"row_group_id": 66,
"start": 66000,
"end": 67000
}
],
"seed": 20261008
}
]
}