mschwab/va_bert_classification

1{2  "_name_or_path": "bert-base-cased",3  "architectures": [4    "BertForSequenceClassification"5  ],6  "attention_probs_dropout_prob": 0.1,7  "gradient_checkpointing": false,8  "hidden_act": "gelu",9  "hidden_dropout_prob": 0.1,10  "hidden_size": 768,11   "id2label": {12    "0": "no VA",13    "1": "VA"14  },15  "initializer_range": 0.02,16  "intermediate_size": 3072,17  "label2id": {18    "VA": "1",19    "no VA": "0"20  },21  "layer_norm_eps": 1e-12,22  "max_position_embeddings": 512,23  "model_type": "bert",24  "num_attention_heads": 12,25  "num_hidden_layers": 12,26  "pad_token_id": 0,27  "position_embedding_type": "absolute",28  "transformers_version": "4.5.0.dev0",29  "type_vocab_size": 2,30  "use_cache": true,31  "vocab_size": 2899632}33