rubert-base-srl / config.json
Daniil Larionov
Training in progress, epoch 1
e45f954
raw
history blame
1.36 kB
{
"_name_or_path": "./ruBert-base/",
"architectures": [
"BertForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"directionality": "bidi",
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "\u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442",
"1": "\u043a\u0430\u0443\u0437\u0430\u0442\u043e\u0440",
"2": "\u044d\u043a\u0441\u043f\u0435\u0440\u0438\u0435\u043d\u0446\u0435\u0440"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"\u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442": 0,
"\u043a\u0430\u0443\u0437\u0430\u0442\u043e\u0440": 1,
"\u044d\u043a\u0441\u043f\u0435\u0440\u0438\u0435\u043d\u0446\u0435\u0440": 2
},
"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",
"torch_dtype": "float32",
"transformers_version": "4.13.0.dev0",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 120138
}