gsl22's picture
Training in progress, epoch 1
ca4cc0c verified
raw
history blame
1.29 kB
{
"_name_or_path": "microsoft/deberta-v3-small",
"architectures": [
"DebertaV2ForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "Autoconsci\u00eancia",
"1": "Autogerenciamento",
"2": "Autoresponsabilidade",
"3": "Automotiva\u00e7\u00e3o",
"4": "Comunica\u00e7\u00e3o"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"Autoconsci\u00eancia": 0,
"Autogerenciamento": 1,
"Automotiva\u00e7\u00e3o": 3,
"Autoresponsabilidade": 2,
"Comunica\u00e7\u00e3o": 4
},
"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": 6,
"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": "multi_label_classification",
"relative_attention": true,
"share_att_key": true,
"torch_dtype": "float32",
"transformers_version": "4.40.0",
"type_vocab_size": 0,
"vocab_size": 128100
}