dolma3-mix-07/_aggregate.json

{
  "engine": "tokforge",
  "prefix": "dolma3-mix-07",
  "corpus": "dolma3",
  "version": "mix",
  "shards": 4,
  "docs": 1101584,
  "tokens": 424240467,
  "bytes": 848480934,
  "files": [
    "data-00000-of-00004.npy",
    "data-00001-of-00004.npy",
    "data-00002-of-00004.npy",
    "data-00003-of-00004.npy"
  ],
  "source_range": [
    0,
    16
  ],
  "source_dataset": "allenai/dolma3_pool",
  "source_config": "common_crawl-food_and_dining",
  "created_at": "2026-08-18T11:14:28Z"
}