gliner_config.json

{
  "class_token_index": 128001,
  "dropout": 0.4,
  "encoder_config": null,
  "ent_token": "<<ENT>>",
  "eval_every": 10000,
  "fine_tune": true,
  "freeze_token_rep": false,
  "has_rnn": true,
  "hidden_size": 768,
  "label_smoothing": 0,
  "log_dir": "GLINER_output",
  "loss_alpha": -1,
  "loss_gamma": 0,
  "loss_reduction": "sum",
  "lr_encoder": "1e-5",
  "lr_others": "5e-5",
  "max_grad_norm": 1.0,
  "max_len": 384,
  "max_neg_type_ratio": 1,
  "max_types": 25,
  "max_width": 12,
  "model_name": "microsoft/deberta-v3-large",
  "model_type": "gliner",
  "name": "GLiNER_WN_trained",
  "num_steps": 100000,
  "prev_path": "none",
  "random_drop": true,
  "root_dir": "gliner_logs",
  "save_total_limit": 3,
  "scheduler_type": "cosine",
  "sep_token": "<<SEP>>",
  "shuffle_types": true,
  "size_sup": -1,
  "span_mode": "markerV0",
  "subtoken_pooling": "first",
  "train_batch_size": 8,
  "train_data": "KIND_train_GLiNER_format.json",
  "transformers_version": "4.41.2",
  "val_data_dir": "KIND_validation_GLiNER_format.json",
  "vocab_size": 128003,
  "warmup_ratio": 0.1,
  "weight_decay_encoder": 0.01,
  "weight_decay_other": 0.01,
  "words_splitter_type": "whitespace"
}