bert-finetuned-ner / README.md
ysharma's picture
ysharma HF staff
update model card README.md
edcb7f8
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - conll2003
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-finetuned-ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: conll2003
          type: conll2003
          args: conll2003
        metrics:
          - name: Precision
            type: precision
            value: 0.9327495042961005
          - name: Recall
            type: recall
            value: 0.9500168293503871
          - name: F1
            type: f1
            value: 0.9413039853259965
          - name: Accuracy
            type: accuracy
            value: 0.9860775887443339

bert-finetuned-ner

This model is a fine-tuned version of bert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0634
  • Precision: 0.9327
  • Recall: 0.9500
  • F1: 0.9413
  • Accuracy: 0.9861

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: 8
  • eval_batch_size: 8
  • 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
0.0876 1.0 1756 0.0692 0.9127 0.9355 0.9240 0.9819
0.0316 2.0 3512 0.0651 0.9284 0.9490 0.9386 0.9850
0.0215 3.0 5268 0.0634 0.9327 0.9500 0.9413 0.9861

Framework versions

  • Transformers 4.18.0
  • Pytorch 1.10.0+cu111
  • Datasets 2.1.0
  • Tokenizers 0.12.1