testmodel / config.json
rkenji's picture
Training 20251210_140203 - 6 classes with metrics
a790bc6 verified
Raw
History Blame
1.31 kB
{
"architectures": [
"BertForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"directionality": "bidi",
"dtype": "float32",
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "646bb41b351734d0a39bb557",
"1": "652026c3798f7600075f9d40",
"2": "646bc57bc7605185f40b4263",
"3": "646b78c3dc761bc8c743a0c6",
"4": "645d42ebbacbc7baba32624d",
"5": "64ac68185fe31ca8ad57a822"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"645d42ebbacbc7baba32624d": 4,
"646b78c3dc761bc8c743a0c6": 3,
"646bb41b351734d0a39bb557": 0,
"646bc57bc7605185f40b4263": 2,
"64ac68185fe31ca8ad57a822": 5,
"652026c3798f7600075f9d40": 1
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"pooler_fc_size": 768,
"pooler_num_attention_heads": 12,
"pooler_num_fc_layers": 3,
"pooler_size_per_head": 128,
"pooler_type": "first_token_transform",
"position_embedding_type": "absolute",
"problem_type": "single_label_classification",
"transformers_version": "4.57.3",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 119547
}