README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - conll2003
metrics:
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-finetuned-ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: conll2003
          type: conll2003
          config: conll2003
          split: train
          args: conll2003
        metrics:
          - name: Recall
            type: recall
            value: 0.9522046449007069
          - name: F1
            type: f1
            value: 0.9441802252816022
          - name: Accuracy
            type: accuracy
            value: 0.9866221227997881
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: conll2003
          type: conll2003
          config: conll2003
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9000173334804052
            verified: true
          - name: Precision
            type: precision
            value: 0.9290209672533908
            verified: true
          - name: Recall
            type: recall
            value: 0.9153430381006068
            verified: true
          - name: F1
            type: f1
            value: 0.9221312844496409
            verified: true
          - name: loss
            type: loss
            value: 1.0536952018737793
            verified: true

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: 0.0858
• Precition: 0.9363
• Recall: 0.9522
• F1: 0.9442
• Accuracy: 0.9866

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	Precition	Recall	F1	Accuracy
0.0081	1.0	1756	0.0914	0.9273	0.9446	0.9359	0.9848
0.012	2.0	3512	0.0852	0.9321	0.9478	0.9399	0.9857
0.0036	3.0	5268	0.0858	0.9363	0.9522	0.9442	0.9866

Framework versions

• Transformers 4.21.2
• Pytorch 1.12.1+cu113
• Datasets 2.4.0
• Tokenizers 0.12.1