data/processed/split_summary.json

{
 "seed": 42,
 "fractions": [
  0.8,
  0.1,
  0.1
 ],
 "images_total": 8091,
 "train": {
  "images": 6473,
  "captions_eng": 6473,
  "captions_ibo": 5943,
  "captions_hau": 6116,
  "captions_yor": 6083,
  "pairs_total": 24615
 },
 "val": {
  "images": 809,
  "captions_eng": 809,
  "captions_ibo": 742,
  "captions_hau": 770,
  "captions_yor": 764,
  "pairs_total": 3085
 },
 "test": {
  "images": 809,
  "captions_eng": 809,
  "captions_ibo": 751,
  "captions_hau": 769,
  "captions_yor": 764,
  "pairs_total": 3093
 },
 "test_unfiltered": {
  "images": 809
 },
 "leakage_check": "passed: no image_id in more than one split"
}