{
  "dataset": "oneryalcin/financial-filings-sparse-retrieval-training",
  "config": "combined",
  "split": "test",
  "rows": 1000,
  "base_model": "opensearch-project/opensearch-neural-sparse-encoding-doc-v2-distill",
  "constant_settings": {
    "steps": 500,
    "train_size_requested": 20000,
    "usable_train_rows": 18247,
    "batch_size": 8,
    "query_regularizer_weight": 0.0001,
    "loss": "SpladeLoss(SparseMultipleNegativesRankingLoss)",
    "sampler": "BatchSamplers.NO_DUPLICATES"
  },
  "results": [
    {"document_regularizer_weight": 0.00008, "accuracy": 0.738, "positive_doc_active_dims": 4204.911, "negative_doc_active_dims": 3784.729, "note": "High score but too dense for practical sparse indexing."},
    {"document_regularizer_weight": 0.00015, "accuracy": 0.748, "positive_doc_active_dims": 3214.797, "negative_doc_active_dims": 2956.645, "note": "Best raw 500-step triplet accuracy but still too dense."},
    {"document_regularizer_weight": 0.0003, "accuracy": 0.734, "positive_doc_active_dims": 2101.448, "negative_doc_active_dims": 1875.179},
    {"document_regularizer_weight": 0.001, "accuracy": 0.727, "positive_doc_active_dims": 1340.540, "negative_doc_active_dims": 1136.954},
    {"document_regularizer_weight": 0.003, "accuracy": 0.734, "positive_doc_active_dims": 657.067, "negative_doc_active_dims": 563.964},
    {"document_regularizer_weight": 0.01, "accuracy": 0.732, "positive_doc_active_dims": 296.654, "negative_doc_active_dims": 261.160, "note": "Chosen for longer run because quality stayed strong while native vectors became much more indexable."},
    {"document_regularizer_weight": 0.03, "accuracy": 0.723, "positive_doc_active_dims": 160.887, "negative_doc_active_dims": 143.986, "note": "Compact but lower quality than 0.01."}
  ]
}