bert-ner-nsm1 / config.json
aalogan's picture
Training in progress epoch 0
02201f4
raw
history blame
1.3 kB
{
"_name_or_path": "bert-base-cased",
"architectures": [
"BertForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "O",
"1": "B-ORG",
"10": "I-PER",
"11": "B-ORT",
"12": "I-ORT",
"13": "B-DTR",
"14": "I-DTR",
"15": "B-ACL",
"16": "I-ACL",
"2": "I-ORG",
"3": "B-DTA",
"4": "I-DTA",
"5": "B-ACJ",
"6": "I-ACJ",
"7": "B-ROL",
"8": "I-ROL",
"9": "B-PER"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B-ACJ": "5",
"B-ACL": "15",
"B-DTA": "3",
"B-DTR": "13",
"B-ORG": "1",
"B-ORT": "11",
"B-PER": "9",
"B-ROL": "7",
"I-ACJ": "6",
"I-ACL": "16",
"I-DTA": "4",
"I-DTR": "14",
"I-ORG": "2",
"I-ORT": "12",
"I-PER": "10",
"I-ROL": "8",
"O": "0"
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"transformers_version": "4.18.0",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 28996
}