mbti-career / config.json
theta's picture
Training in progress, step 100
6b26170
{
"_name_or_path": "theta/mbti-career",
"architectures": [
"XLMRobertaForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "\u5718\u9ad4\u4e3b\u7fa9\u884c\u52d5",
"1": "\u500b\u4eba\u4e3b\u7fa9\u884c\u52d5",
"2": "\u76f4\u89ba\u7d71\u6574\u8a8d\u77e5",
"3": "\u89c0\u5bdf\u611f\u53d7\u8a8d\u77e5",
"4": "\u7406\u6027\u5f15\u5c0e\u6c7a\u7b56",
"5": "\u611f\u6027\u5f15\u5c0e\u6c7a\u7b56",
"6": "\u5b89\u5168\u7a69\u5b9a\u56ae\u5f80",
"7": "\u6a5f\u6703\u8b8a\u5316\u56ae\u5f80"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": null,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "xlm-roberta",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"problem_type": "multi_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.26.0",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 250002
}