| { |
| "class_token_index": 128002, |
| "dropout": 0.2, |
| "embed_ent_token": true, |
| "encoder_config": { |
| "_name_or_path": "microsoft/deberta-v3-base", |
| "architectures": null, |
| "attention_probs_dropout_prob": 0.1, |
| "bos_token_id": null, |
| "chunk_size_feed_forward": 0, |
| "dtype": null, |
| "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_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "layer_norm_eps": 1e-07, |
| "legacy": true, |
| "max_position_embeddings": 512, |
| "max_relative_positions": -1, |
| "model_type": "deberta-v2", |
| "norm_rel_ebd": "layer_norm", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "output_attentions": false, |
| "output_hidden_states": 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, |
| "problem_type": null, |
| "relative_attention": true, |
| "return_dict": true, |
| "share_att_key": true, |
| "tie_word_embeddings": true, |
| "type_vocab_size": 0, |
| "vocab_size": 128004 |
| }, |
| "ent_token": "<<ENT>>", |
| "eval_every": 5000, |
| "fine_tune": true, |
| "fuse_layers": false, |
| "gpu": "ohy@a100", |
| "hidden_size": 768, |
| "log_dir": "/gpfsdswork/projects/rech/bwq/upa43yu/GLiNER/log_main/deberta-v3-base_0", |
| "lr_encoder": "1e-5", |
| "lr_others": "5e-5", |
| "max_len": 384, |
| "max_neg_type_ratio": 1, |
| "max_types": 25, |
| "max_width": 12, |
| "model_name": "microsoft/deberta-v3-base", |
| "model_type": null, |
| "name": "abl", |
| "num_post_fusion_layers": 1, |
| "num_rnn_layers": 1, |
| "num_steps": 30000, |
| "post_fusion_schema": "", |
| "prev_path": "none", |
| "random_drop": true, |
| "root_dir": "log_main", |
| "run_time": "05:30:00", |
| "sep_token": "<<SEP>>", |
| "shuffle_types": true, |
| "size_sup": -1, |
| "span_mode": "marker", |
| "subtoken_pooling": "first", |
| "train_batch_size": 8, |
| "train_data": "/gpfswork/rech/ohy/upa43yu/instruct_ner/train_instruct.json", |
| "transformers_version": "5.3.0", |
| "vocab_size": 128004, |
| "warmup_ratio": 0.1, |
| "words_splitter_type": "whitespace" |
| } |
|
|
