MuneK's picture
Training in progress, epoch 1
908e8a1
{
"_name_or_path": "ku-nlp/deberta-v2-base-japanese",
"architectures": [
"DebertaV2ForSequenceClassification"
],
"attention_head_size": 64,
"attention_probs_dropout_prob": 0.1,
"conv_act": "gelu",
"conv_kernel_size": 3,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2",
"3": "LABEL_3",
"4": "LABEL_4",
"5": "LABEL_5",
"6": "LABEL_6",
"7": "LABEL_7"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2,
"LABEL_3": 3,
"LABEL_4": 4,
"LABEL_5": 5,
"LABEL_6": 6,
"LABEL_7": 7
},
"layer_norm_eps": 1e-07,
"max_position_embeddings": 512,
"max_relative_positions": -1,
"model_type": "deberta-v2",
"norm_rel_ebd": "layer_norm",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"pooler_dropout": 0,
"pooler_hidden_act": "gelu",
"pooler_hidden_size": 768,
"pos_att_type": [
"p2c",
"c2p"
],
"position_biased_input": false,
"position_buckets": 256,
"problem_type": "regression",
"relative_attention": true,
"share_att_key": true,
"torch_dtype": "float32",
"transformers_version": "4.31.0",
"type_vocab_size": 0,
"vocab_size": 32000
}