test / config.json
matsudatkm's picture
Training in progress, step 500
c9f10b4 verified
{
"_name_or_path": "rinna/japanese-roberta-base",
"architectures": [
"RobertaForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 1,
"classifier_dropout": null,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "I-\u6750\u8cea",
"1": "I-\u30d5\u30eb\u30fc\u30c8",
"2": "I-\u5bf8\u6cd5",
"3": "I-\u30b7\u30fc\u30c8\u306e\u30ab\u30c3\u30c8\u5bf8\u6cd5",
"4": "I-\u6570\u91cf",
"5": "I-\u7d0d\u671f",
"6": "O"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"I-\u30b7\u30fc\u30c8\u306e\u30ab\u30c3\u30c8\u5bf8\u6cd5": 3,
"I-\u30d5\u30eb\u30fc\u30c8": 1,
"I-\u5bf8\u6cd5": 2,
"I-\u6570\u91cf": 4,
"I-\u6750\u8cea": 0,
"I-\u7d0d\u671f": 5,
"O": 6
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "roberta",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 3,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.38.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 32000
}