training_results / config.json
logiczmaksimka's picture
Training in progress, epoch 1
e9455d1
{
"_name_or_path": "ai-forever/ruElectra-medium",
"architectures": [
"ElectraForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"embedding_size": 576,
"generator_size": "0.25",
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 576,
"id2label": {
"0": "appreciation",
"1": "positive answer",
"2": "other answer",
"3": "command",
"4": "opinion question",
"5": "negative answer",
"6": "fact",
"7": "factual question",
"8": "opinion",
"9": "yes/no question"
},
"initializer_range": 0.02,
"intermediate_size": 2304,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2,
"LABEL_3": 3,
"LABEL_4": 4,
"LABEL_5": 5,
"LABEL_6": 6,
"LABEL_7": 7,
"LABEL_8": 8,
"LABEL_9": 9
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "electra",
"num_attention_heads": 9,
"num_hidden_layers": 12,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"problem_type": "single_label_classification",
"summary_activation": "gelu",
"summary_last_dropout": 0.1,
"summary_type": "first",
"summary_use_proj": true,
"torch_dtype": "float32",
"transformers_version": "4.34.0",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 64000
}