metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - ner
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: Bert-NER
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: ner
          type: ner
          config: indian_names
          split: test
          args: indian_names
        metrics:
          - name: Precision
            type: precision
            value: 0.7254647322919372
          - name: Recall
            type: recall
            value: 0.8467001558981465
          - name: F1
            type: f1
            value: 0.7814079891293488
          - name: Accuracy
            type: accuracy
            value: 0.8557099199430039

Bert-NER

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

Loss: 0.9081
Precision: 0.7255
Recall: 0.8467
F1: 0.7814
Accuracy: 0.8557

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
0.0934	1.0	501	0.6938	0.7190	0.8536	0.7805	0.8502
0.035	2.0	1002	0.7709	0.7087	0.8383	0.7681	0.8446
0.0196	3.0	1503	0.7814	0.7130	0.8439	0.7729	0.8477
0.0109	4.0	2004	0.8572	0.7206	0.8467	0.7786	0.8526
0.0065	5.0	2505	0.9081	0.7255	0.8467	0.7814	0.8557

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3