metadata

license: mit
base_model: neuralmind/bert-base-portuguese-cased
tags:
  - generated_from_trainer
datasets:
  - __main__
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: ner_model
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: __main__
          type: __main__
          config: local
          split: test
          args: local
        metrics:
          - name: Precision
            type: precision
            value: 0.5687651985949743
          - name: Recall
            type: recall
            value: 0.6082935991908683
          - name: F1
            type: f1
            value: 0.5878656705997346
          - name: Accuracy
            type: accuracy
            value: 0.7791311866764413

ner_model

This model is a fine-tuned version of neuralmind/bert-base-portuguese-cased on the main dataset. It achieves the following results on the evaluation set:

Loss: 0.6378
Precision: 0.5688
Recall: 0.6083
F1: 0.5879
Accuracy: 0.7791

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: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.6703	1.0	5737	0.6732	0.5189	0.5700	0.5432	0.7605
0.5251	2.0	11474	0.6378	0.5688	0.6083	0.5879	0.7791

Framework versions

Transformers 4.36.0
Pytorch 2.0.1+cu117
Datasets 2.14.4
Tokenizers 0.15.0