learning_rate: 2e-05
train_batch_size: 128
eval_batch_size: 128
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	6	0.4001	0.5696	0.625	0.5960	0.864
No log	2.0	12	0.0797	0.9722	0.9722	0.9722	0.997
No log	3.0	18	0.0153	0.9861	0.9861	0.9861	0.999
No log	4.0	24	0.0042	1.0	1.0	1.0	1.0
No log	5.0	30	0.0029	1.0	1.0	1.0	1.0
No log	6.0	36	0.0017	1.0	1.0	1.0	1.0
No log	7.0	42	0.0034	0.9726	0.9861	0.9793	0.999
No log	8.0	48	0.0017	1.0	1.0	1.0	1.0
No log	9.0	54	0.0013	1.0	1.0	1.0	1.0
No log	10.0	60	0.0012	1.0	1.0	1.0	1.0

luohuashijieyoufengjun/ner_based_bert-base-chinese-only-phone

ner_based_bert-base-chinese-only-phone