temp_model_roberta / config.json
daiki7069's picture
Training in progress, epoch 1
403c3ec
{
"_name_or_path": "rinna/japanese-roberta-base",
"architectures": [
"RobertaForSequenceClassification"
],
"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": 3.0,
"1": 7.0,
"2": 6.0,
"3": 0.0,
"4": 2.0,
"5": 4.0,
"6": 1.0,
"7": 5.0,
"8": 8.0
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"0.0": 3,
"1.0": 6,
"2.0": 4,
"3.0": 0,
"4.0": 5,
"5.0": 7,
"6.0": 2,
"7.0": 1,
"8.0": 8
},
"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",
"problem_type": "single_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.26.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 32000
}