{ "blank_prompt_rep_layer": true, "class_token_index": -1, "dropout": 0.36, "embed_ent_token": true, "encoder_config": { "_name_or_path": "microsoft/deberta-v3-base", "add_cross_attention": false, "architectures": null, "attention_probs_dropout_prob": 0.1, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 3072, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-07, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 512, "max_relative_positions": -1, "min_length": 0, "model_type": "deberta-v2", "no_repeat_ngram_size": 0, "norm_rel_ebd": "layer_norm", "num_attention_heads": 12, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 12, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 0, "pooler_dropout": 0, "pooler_hidden_act": "gelu", "pooler_hidden_size": 768, "pos_att_type": [ "p2c", "c2p" ], "position_biased_input": false, "position_buckets": 256, "prefix": null, "problem_type": null, "pruned_heads": {}, "relative_attention": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "share_att_key": true, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "type_vocab_size": 0, "typical_p": 1.0, "use_bfloat16": false, "vocab_size": 128100 }, "ent_token": "<>", "entity_linking": null, "eval_every": 4000, "fine_tune": true, "freeze_labels_encoder": true, "freeze_token_rep": true, "fuse_layers": false, "has_rnn": true, "hidden_size": 768, "label_smoothing": 0, "labels_encoder": "BAAI/bge-base-en-v1.5", "labels_encoder_config": { "_name_or_path": "BAAI/bge-base-en-v1.5", "add_cross_attention": false, "architectures": [ "BertModel" ], "attention_probs_dropout_prob": 0.1, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "classifier_dropout": null, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "LABEL_0" }, "initializer_range": 0.02, "intermediate_size": 3072, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0 }, "layer_norm_eps": 1e-12, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 512, "min_length": 0, "model_type": "bert", "no_repeat_ngram_size": 0, "num_attention_heads": 12, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 12, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 0, "position_embedding_type": "absolute", "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "float32", "torchscript": false, "type_vocab_size": 2, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 30522 }, "log_dir": "models-base-2/", "loss_alpha": 0.8, "loss_gamma": 2, "loss_reduction": "sum", "lr_encoder": "1e-5", "lr_others": "4e-5", "max_grad_norm": 10.0, "max_len": 768, "max_neg_type_ratio": 5, "max_types": 256, "max_width": 12, "model_name": "microsoft/deberta-v3-base", "model_type": "gliner", "name": "span level gliner for entity linking", "num_post_fusion_layers": 1, "num_steps": 250000, "post_fusion_schema": "", "prev_path": null, "random_drop": true, "root_dir": "gliner_logs", "save_total_limit": 20, "scheduler_type": "cosine", "sep_token": "<>", "shuffle_types": true, "size_sup": -1, "span_mode": "markerV0", "subtoken_pooling": "first", "train_batch_size": 4, "train_data": "final_dataset_1m.json", "transformers_version": "4.45.2", "val_data_dir": null, "vocab_size": -1, "warmup_ratio": 0.1, "weight_decay_encoder": 0.01, "weight_decay_other": 0.02, "words_splitter_type": "whitespace" }