bert-base-chinese-finetuned-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: 0.0044
• 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
3.2163	1.0	3	1.7446	0.0201
1.5263	2.0	6	1.1179	0.6113
1.1837	3.0	9	0.7233	0.75
0.6987	4.0	12	0.4377	0.8766
0.5036	5.0	15	0.2544	0.9154
0.2602	6.0	18	0.1495	0.9598
0.1998	7.0	21	0.0834	0.9836
0.1182	8.0	24	0.0484	0.9911
0.0815	9.0	27	0.0280	1.0
0.05	10.0	30	0.0177	1.0
0.0375	11.0	33	0.0124	1.0
0.0244	12.0	36	0.0094	1.0
0.0213	13.0	39	0.0075	1.0
0.0163	14.0	42	0.0063	1.0
0.0147	15.0	45	0.0056	1.0
0.0124	16.0	48	0.0051	1.0
0.0125	17.0	51	0.0047	1.0
0.0115	18.0	54	0.0045	1.0
0.0116	19.0	57	0.0044	1.0
0.0102	20.0	60	0.0044	1.0

Framework versions

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