metadata

language:
  - zh
tags:
  - generated_from_trainer
datasets:
  - gyr66/privacy_detection
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-base-chinese-finetuned-ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: gyr66/privacy_detection
          type: gyr66/privacy_detection
          config: privacy_detection
          split: train
          args: privacy_detection
        metrics:
          - name: Precision
            type: precision
            value: 0.3840122394339262
          - name: Recall
            type: recall
            value: 0.5055387713997986
          - name: F1
            type: f1
            value: 0.43647429627214435
          - name: Accuracy
            type: accuracy
            value: 0.8564247370217519

bert-base-chinese-finetuned-ner

This model is a fine-tuned version of Danielwei0214/bert-base-chinese-finetuned-ner on the gyr66/privacy_detection dataset. It achieves the following results on the evaluation set:

Loss: 0.4895
Precision: 0.3840
Recall: 0.5055
F1: 0.4365
Accuracy: 0.8564

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: 2e-05
train_batch_size: 56
eval_batch_size: 56
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
1.3112	1.0	36	0.7305	0.2062	0.2535	0.2274	0.8028
0.6083	2.0	72	0.5295	0.3598	0.4668	0.4064	0.8451
0.4782	3.0	108	0.4895	0.3840	0.5055	0.4365	0.8564

Framework versions

Transformers 4.27.3
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.2