bert-base-chinese-finetuned-ner-food

This model is a fine-tuned version of bert-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0039
• F1: 1.0

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	F1
3.0829	1.0	3	1.6749	0.0
1.5535	2.0	6	1.0327	0.6354
1.0573	3.0	9	0.6295	0.7097
0.5854	4.0	12	0.3763	0.8271
0.4292	5.0	15	0.2165	0.9059
0.2235	6.0	18	0.1121	0.9836
0.1535	7.0	21	0.0597	0.9975
0.0846	8.0	24	0.0337	0.9975
0.0613	9.0	27	0.0214	1.0
0.0365	10.0	30	0.0144	1.0
0.0302	11.0	33	0.0103	1.0
0.0182	12.0	36	0.0078	1.0
0.0175	13.0	39	0.0064	1.0
0.0115	14.0	42	0.0055	1.0
0.0124	15.0	45	0.0049	1.0
0.0117	16.0	48	0.0045	1.0
0.0111	17.0	51	0.0042	1.0
0.0102	18.0	54	0.0041	1.0
0.0096	19.0	57	0.0040	1.0
0.0095	20.0	60	0.0039	1.0

Framework versions

• Transformers 4.18.0
• Pytorch 1.12.0+cu102
• Datasets 1.18.4
• Tokenizers 0.12.1