kaishih/bert-tzh-med-ner

test-ner

This model is a fine-tuned version of bert-base-chinese on an CMeEE-V2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4423
• Precision: 0.5197
• Recall: 0.6287
• F1: 0.5690
• Accuracy: 0.8492

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.6791	1.0	938	0.4600	0.5031	0.6096	0.5513	0.8435
0.3969	2.0	1876	0.4423	0.5197	0.6287	0.5690	0.8492

Framework versions

• Transformers 4.42.4
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1