bert-eval-256 / config.json
AndrewDOrlov's picture
Training in progress, epoch 1
34c3ade
Raw
History Blame Contribute Delete
3.21 kB
{
"_name_or_path": "rubert_cased_L-12_H-768_A-12_pt",
"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": "\u0437\u0430\u043a\u043e\u043d\u044b_\u0438_\u043d\u0430\u0440\u0443\u0448\u0435\u043d\u0438\u044f",
"1": "\u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u043a\u0430",
"2": "\u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u043d\u0438\u044f",
"3": "\u0432\u0440\u0435\u0434\u043e\u043d\u043e\u0441\u044b",
"4": "\u0443\u044f\u0437\u0432\u0438\u043c\u043e\u0441\u0442\u0438",
"5": "\u0443\u0442\u0435\u0447\u043a\u0438",
"6": "\u043c\u043e\u0448\u0435\u043d\u043d\u0438\u0447\u0435\u0441\u0442\u0432\u0430",
"7": "\u0433\u043e\u0441\u0440\u0435\u0433\u0443\u043b\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435",
"8": "\u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u043d\u043e\u0435_\u043e\u0431\u0435\u0441\u043f\u0435\u0447\u0435\u043d\u0438\u0435",
"9": "\u0444\u0438\u043d\u0430\u043d\u0441\u044b_\u0438_\u0431\u0438\u0437\u043d\u0435\u0441",
"10": "\u0441\u043e\u0431\u044b\u0442\u0438\u044f_\u0438_\u043c\u0435\u0440\u043e\u043f\u0440\u0438\u044f\u0442\u0438\u044f",
"11": "\u043a\u0438\u0431\u0435\u0440\u0431\u0435\u0437\u043e\u043f\u0430\u0441\u043d\u043e\u0441\u0442\u044c"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"\u0432\u0440\u0435\u0434\u043e\u043d\u043e\u0441\u044b": 3,
"\u0433\u043e\u0441\u0440\u0435\u0433\u0443\u043b\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435": 7,
"\u0437\u0430\u043a\u043e\u043d\u044b_\u0438_\u043d\u0430\u0440\u0443\u0448\u0435\u043d\u0438\u044f": 0,
"\u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u043d\u0438\u044f": 2,
"\u043a\u0438\u0431\u0435\u0440\u0431\u0435\u0437\u043e\u043f\u0430\u0441\u043d\u043e\u0441\u0442\u044c": 11,
"\u043c\u043e\u0448\u0435\u043d\u043d\u0438\u0447\u0435\u0441\u0442\u0432\u0430": 6,
"\u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u043d\u043e\u0435_\u043e\u0431\u0435\u0441\u043f\u0435\u0447\u0435\u043d\u0438\u0435": 8,
"\u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u043a\u0430": 1,
"\u0441\u043e\u0431\u044b\u0442\u0438\u044f_\u0438_\u043c\u0435\u0440\u043e\u043f\u0440\u0438\u044f\u0442\u0438\u044f": 10,
"\u0443\u0442\u0435\u0447\u043a\u0438": 5,
"\u0443\u044f\u0437\u0432\u0438\u043c\u043e\u0441\u0442\u0438": 4,
"\u0444\u0438\u043d\u0430\u043d\u0441\u044b_\u0438_\u0431\u0438\u0437\u043d\u0435\u0441": 9
},
"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": "multi_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.30.2",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 119547
}