glirel_config.json

{
  "lr_encoder": "1e-5",
  "lr_others": "1e-4",
  "weight_decay_encoder": 0.01,
  "weight_decay_other": 0.01,
  "num_steps": 500000,
  "warmup_ratio": 0.1,
  "train_batch_size": 8,
  "eval_every": 15000,
  "gradient_accumulation": 8,
  "eval_batch_size": 32,
  "num_layers_freeze": null,
  "early_stopping_patience": null,
  "early_stopping_delta": 0.0,
  "save_at": [
    15000,
    30000,
    45000,
    60000,
    75000,
    90000,
    105000,
    120000,
    135000,
    150000,
    165000,
    180000,
    195000,
    210000,
    225000,
    240000,
    255000,
    270000,
    285000,
    300000,
    315000,
    330000,
    345000,
    360000,
    375000,
    390000,
    405000,
    420000,
    435000,
    450000,
    465000,
    480000,
    495000,
    500000
  ],
  "max_saves": 8,
  "max_width": 6,
  "model_name": "microsoft/deberta-v3-large",
  "fine_tune": true,
  "subtoken_pooling": "first",
  "hidden_size": 768,
  "scorer": "dot",
  "rel_mode": "marker",
  "span_marker_mode": "markerv1",
  "refine_prompt": false,
  "refine_relation": false,
  "ffn_mul": 4,
  "dropout": 0.4,
  "scheduler": "cosine_with_warmup",
  "loss_func": "binary_cross_entropy_loss",
  "alpha": 0.6,
  "gamma": 3,
  "label_embed_strategy": "both",
  "use_typed_relations": true,
  "consistency_loss_weight": 0.1,
  "enable_ner_module": true,
  "ner_threshold": 0.5,
  "ner_fn_loss_weight": 1.5,
  "ner_loss_weight": 100.0,
  "rel_loss_weight": 1.0,
  "ner_threshold_offset": -0.02,
  "training_phase": "ner_only",
  "span_f1_target": 0.7,
  "relation_f1_target": 0.7,
  "coref_classifier": false,
  "coref_loss_weight": 10.0,
  "coreference_label": null,
  "dataset_name": "custom",
  "root_dir": "multi_domain",
  "train_data": [
    "data/multi_domain_train_processed.jsonl"
  ],
  "eval_data": [
    "data/multi_domain_test_processed.jsonl"
  ],
  "prev_path": "./ner-glirel-log/saved_at/model_60000",
  "size_sup": -1,
  "num_train_rel_types": 40,
  "num_unseen_rel_types": 15,
  "top_k": 1,
  "random_drop": false,
  "max_len": 512,
  "eval_threshold": [
    0.1,
    0.2,
    0.3,
    0.5,
    0.6,
    0.7
  ],
  "max_entity_pair_distance": null,
  "fixed_relation_types": false,
  "name": "large",
  "log_dir": "ner-glirel-log-2/"
}