bileldh's picture
Training in progress epoch 0
9dfe991
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-MET",
"2": "I-MET",
"3": "B-CONT",
"4": "I-CONT",
"5": "B-EDU",
"6": "I-EDU",
"7": "B-CER",
"8": "I-CER",
"9": "B-EXP",
"10": "I-EXP",
"11": "B-SAL",
"12": "I-SAL",
"13": "B-LOC",
"14": "I-LOC",
"15": "B-ORG",
"16": "I-ORG"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B-CER": 7,
"B-CONT": 3,
"B-EDU": 5,
"B-EXP": 9,
"B-LOC": 13,
"B-MET": 1,
"B-ORG": 15,
"B-SAL": 11,
"I-CER": 8,
"I-CONT": 4,
"I-EDU": 6,
"I-EXP": 10,
"I-LOC": 14,
"I-MET": 2,
"I-ORG": 16,
"I-SAL": 12,
"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",
"torch_dtype": "float32",
"transformers_version": "4.25.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 28996
}