kartashoffv's picture
Training in progress, step 500
2750ef6
raw
history blame
1.36 kB
{
"_name_or_path": "DeepPavlov/rubert-base-cased",
"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": "auto",
"1": "business",
"2": "economics",
"3": "finances",
"4": "lifestyle",
"5": "management",
"6": "opinions",
"7": "politics",
"8": "realty",
"9": "technologies"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"auto": 0,
"business": 1,
"economics": 2,
"finances": 3,
"lifestyle": 4,
"management": 5,
"opinions": 6,
"politics": 7,
"realty": 8,
"technologies": 9
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_past": true,
"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": "4.33.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 119547
}