TC_model / config.json
wgj0714's picture
Training in progress, epoch 1
24305ca verified
raw
history blame
1.08 kB
{
"_name_or_path": "klue/roberta-large",
"architectures": [
"RobertaForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"id2label": {
"0": "\ubb3c\ud488",
"1": "\ubd80\ub3d9\uc0b0",
"2": "\ucc28\uc6a9\uc6a9\ub3c4",
"3": "\ud22c\uc790"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"label2id": {
"\ubb3c\ud488": 0,
"\ubd80\ub3d9\uc0b0": 1,
"\ucc28\uc6a9\uc6a9\ub3c4": 2,
"\ud22c\uc790": 3
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "roberta",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"problem_type": "single_label_classification",
"tokenizer_class": "BertTokenizer",
"torch_dtype": "float32",
"transformers_version": "4.39.3",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 32000
}