my_wr / config.json
AIYIYA's picture
Training in progress epoch 0
887a2dc
{
"_name_or_path": "bert-base-chinese",
"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": "\u5176\u4ed6",
"1": "\u59d3\u540d",
"2": "\u8eab\u4efd\u8bc1\u53f7",
"3": "\u624b\u673a\u53f7",
"4": "\u5730\u5740",
"5": "\u90ae\u7bb1",
"6": "QQ",
"7": "\u82f1\u6587\u59d3",
"8": "\u516c\u53f8\u540d\u79f0",
"9": "\u8054\u7cfb\u4eba\u59d3\u540d",
"10": "\u7edf\u4e00\u793e\u4f1a\u4fe1\u7528\u4ee3\u7801",
"11": "\u90ae\u7f16",
"12": "\u5b57\u6bcd",
"13": "\u6c49\u5b57",
"14": "\u786e\u8ba4\u5bc6\u7801",
"15": "\u7528\u6237\u540d",
"16": "\u5bc6\u7801",
"17": "\u524d\u7aef\u9a8c\u8bc1\u7801",
"18": "\u52a8\u6001\u9a8c\u8bc1\u7801",
"19": "\u4f20\u771f",
"20": "\u6635\u79f0"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"QQ": 6,
"\u4f20\u771f": 19,
"\u516c\u53f8\u540d\u79f0": 8,
"\u5176\u4ed6": 0,
"\u524d\u7aef\u9a8c\u8bc1\u7801": 17,
"\u52a8\u6001\u9a8c\u8bc1\u7801": 18,
"\u5730\u5740": 4,
"\u59d3\u540d": 1,
"\u5b57\u6bcd": 12,
"\u5bc6\u7801": 16,
"\u624b\u673a\u53f7": 3,
"\u6635\u79f0": 20,
"\u6c49\u5b57": 13,
"\u7528\u6237\u540d": 15,
"\u786e\u8ba4\u5bc6\u7801": 14,
"\u7edf\u4e00\u793e\u4f1a\u4fe1\u7528\u4ee3\u7801": 10,
"\u8054\u7cfb\u4eba\u59d3\u540d": 9,
"\u82f1\u6587\u59d3": 7,
"\u8eab\u4efd\u8bc1\u53f7": 2,
"\u90ae\u7bb1": 5,
"\u90ae\u7f16": 11
},
"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",
"transformers_version": "4.31.0",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 21128
}