README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - conll2003
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: berttest2
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: conll2003
          type: conll2003
          config: conll2003
          split: train
          args: conll2003
        metrics:
          - name: Precision
            type: precision
            value: 0.9137532981530343
          - name: Recall
            type: recall
            value: 0.932514304947829
          - name: F1
            type: f1
            value: 0.9230384807596203
          - name: Accuracy
            type: accuracy
            value: 0.9822805674927886
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: conll2003
          type: conll2003
          config: conll2003
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8984100471155513
            verified: true
          - name: Precision
            type: precision
            value: 0.9270828085377937
            verified: true
          - name: Recall
            type: recall
            value: 0.9152932984050137
            verified: true
          - name: F1
            type: f1
            value: 0.9211503324684426
            verified: true
          - name: loss
            type: loss
            value: 0.7076165080070496
            verified: true

berttest2

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: 0.0674
• Precision: 0.9138
• Recall: 0.9325
• F1: 0.9230
• Accuracy: 0.9823

Model description

Model implemented for CSE 573 Course Project

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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0869	1.0	1756	0.0674	0.9138	0.9325	0.9230	0.9823

Framework versions

• Transformers 4.24.0
• Pytorch 1.13.0+cpu
• Datasets 2.6.1
• Tokenizers 0.13.2