README.md

metadata

language:
  - en
license: apache-2.0
datasets:
  - conll2003
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-large-uncased
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: conll2003
          type: conll2003
          args: default
        metrics:
          - name: precision
            type: precision
            value: 0.9504719600222099
          - name: recall
            type: recall
            value: 0.9574896520863632
          - name: f1
            type: f1
            value: 0.9539679001337494
          - name: accuracy
            type: accuracy
            value: 0.9885618059637473

bert-large-uncased

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

• precision: 0.9505
• recall: 0.9575
• f1: 0.9540
• accuracy: 0.9886

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:

• num_train_epochs: 10
• train_batch_size: 4
• learning_rate: 2e-05
• weight_decay_rate: 0.01
• num_warmup_steps: 0
• fp16: True

Framework versions

• Transformers 4.16.2
• Pytorch 1.8.1+cu111
• Datasets 1.18.3
• Tokenizers 0.11.0