Bert-NER / README.md
Kriyans's picture
End of training
4fcd887
|
raw
history blame
2.45 kB
metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - indian_names
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: my_awesome_wnut_model
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: indian_names
          type: indian_names
          config: indian_names
          split: train
          args: indian_names
        metrics:
          - name: Precision
            type: precision
            value: 0.9905686167304538
          - name: Recall
            type: recall
            value: 0.910427135678392
          - name: F1
            type: f1
            value: 0.9488085886357684
          - name: Accuracy
            type: accuracy
            value: 0.983080223080223

my_awesome_wnut_model

This model is a fine-tuned version of distilbert-base-uncased on the indian_names dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0679
  • Precision: 0.9906
  • Recall: 0.9104
  • F1: 0.9488
  • Accuracy: 0.9831

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: 5e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 66 0.1499 0.7872 0.7281 0.7565 0.9557
No log 2.0 132 0.1338 0.8289 0.7524 0.7888 0.9612
No log 3.0 198 0.0884 0.9959 0.9053 0.9484 0.9820
No log 4.0 264 0.0750 0.9964 0.9070 0.9496 0.9826
No log 5.0 330 0.0679 0.9906 0.9104 0.9488 0.9831

Framework versions

  • Transformers 4.33.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3