Bert-NER / README.md
Kriyans's picture
update model card README.md
d0f8270
|
raw
history blame
2.18 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - ner
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: my_awesome_wnut_model
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: ner
          type: ner
          config: indian_names
          split: train
          args: indian_names
        metrics:
          - name: Precision
            type: precision
            value: 0.999537251272559
          - name: Recall
            type: recall
            value: 0.999537251272559
          - name: F1
            type: f1
            value: 0.999537251272559
          - name: Accuracy
            type: accuracy
            value: 0.9997335485246202

my_awesome_wnut_model

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

  • Loss: 0.0003
  • Precision: 0.9995
  • Recall: 0.9995
  • F1: 0.9995
  • Accuracy: 0.9997

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: 3

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.0364 1.0 688 0.0026 0.9964 0.9965 0.9964 0.9979
0.0088 2.0 1376 0.0008 0.9991 0.9988 0.9990 0.9994
0.0017 3.0 2064 0.0003 0.9995 0.9995 0.9995 0.9997

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.13.1
  • Tokenizers 0.13.3