train problem 卡在以下最后一行内容current training loss is : 0.01826123334467411 不动

[gjy-code]

train_zh_onto.sh: line 7: EXP-ID=22_1: command not found
Better speed can be achieved with apex installed from https://www.github.com/nvidia/apex.
Better speed can be achieved with apex installed from https://www.github.com/nvidia/apex.
Please notice that merge the args_dict and json_config ... ...
{
"bert_frozen": "false",
"hidden_size": 768,
"hidden_dropout_prob": 0.2,
"classifier_sign": "multi_nonlinear",
"clip_grad": 1,
"bert_config": {
"attention_probs_dropout_prob": 0.1,
"directionality": "bidi",
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"max_position_embeddings": 512,
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pooler_fc_size": 768,
"pooler_num_attention_heads": 12,
"pooler_num_fc_layers": 3,
"pooler_size_per_head": 128,
"pooler_type": "first_token_transform",
"type_vocab_size": 2,
"vocab_size": 21128
},
"config_path": "/home/amax/work/gjy/mrcc/config/zh_bert.json",
"data_dir": "/home/amax/work/gjy/mrcc/data_preprocess/example/zh_ontonotes4",
"bert_model": "/home/amax/work/gjy/Bert-Ner-Demo-master/chinese_L-12_H-768_A-12",
"task_name": null,
"max_seq_length": 100,
"train_batch_size": 16,
"dev_batch_size": 16,
"test_batch_size": 16,
"checkpoint": 600,
"learning_rate": 8e-06,
"num_train_epochs": 10,
"warmup_proportion": -1.0,
"local_rank": -1,
"gradient_accumulation_steps": 1,
"seed": 2333,
"export_model": true,
"output_dir": "/home/amax/work/gjy/mrcc/export/zh_onto/mrc-ner-zh_onto-2020-05-12--100-8e-6-16-0.3",
"data_sign": "zh_onto",
"weight_start": 1.0,
"weight_end": 1.0,
"weight_span": 1.0,
"entity_sign": "flat",
"n_gpu": 1,
"dropout": 0.3,
"entity_threshold": 0.5,
"data_cache": true
}
--------------------
current data_sign: zh_onto
====================
loading train data ... ...
62896
62896 train data loaded
====================
loading dev data ... ...
17204
17204 dev data loaded
====================
loading test data ... ...
17384
17384 test data loaded
数据已加载完毕！
load_model模型已加载完毕！
######################################################################
EPOCH: 0
-----------------------------*-
current training loss is :
0.01826123334467411