morganchen1007's picture
Training in progress, step 500
122cadd
raw
history blame
1.38 kB
{
"_name_or_path": "ckiplab/bert-base-chinese-ner",
"architectures": [
"BertForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"directionality": "bidi",
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "B-AUTHOR",
"1": "I-AUTHOR",
"2": "B-PUBYEAR",
"3": "I-PUBYEAR",
"4": "B-TITLE",
"5": "I-TITLE",
"6": "B-SOURCE",
"7": "I-SOURCE",
"8": "B-SPAGE",
"9": "I-SPAGE",
"10": "O"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B-AUTHOR": 0,
"B-PUBYEAR": 2,
"B-SOURCE": 6,
"B-SPAGE": 8,
"B-TITLE": 4,
"I-AUTHOR": 1,
"I-PUBYEAR": 3,
"I-SOURCE": 7,
"I-SPAGE": 9,
"I-TITLE": 5,
"O": 10
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"pooler_fc_size": 768,
"pooler_num_attention_heads": 12,
"pooler_num_fc_layers": 3,
"pooler_size_per_head": 128,
"pooler_type": "first_token_transform",
"position_embedding_type": "absolute",
"tokenizer_class": "BertTokenizerFast",
"torch_dtype": "float32",
"transformers_version": "4.20.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 21128
}