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: 0.5783305117853887
          - name: Recall
            type: recall
            value: 0.6134825252106645
          - name: F1
            type: f1
            value: 0.5953881217321357
          - name: Accuracy
            type: accuracy
            value: 0.7670984455958549

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: 1.5136
Precision: 0.5783
Recall: 0.6135
F1: 0.5954
Accuracy: 0.7671

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.7447	1.0	5905	0.7678	0.4966	0.5209	0.5085	0.7409
0.6153	2.0	11810	0.7378	0.5628	0.5600	0.5614	0.7624
0.4623	3.0	17715	0.7959	0.5449	0.5836	0.5636	0.7573
0.3629	4.0	23620	0.8921	0.5679	0.6017	0.5843	0.7631
0.246	5.0	29525	1.0286	0.5878	0.5955	0.5916	0.7685
0.1923	6.0	35430	1.2142	0.5926	0.5957	0.5941	0.7689
0.1477	7.0	41335	1.3019	0.5681	0.6091	0.5879	0.7591
0.1214	8.0	47240	1.4101	0.5834	0.6110	0.5969	0.7659
0.0793	9.0	53145	1.4745	0.5848	0.6136	0.5989	0.7688
0.0733	10.0	59050	1.5136	0.5783	0.6135	0.5954	0.7671

Framework versions

Transformers 4.36.0
Pytorch 2.0.1+cu117
Datasets 2.14.4
Tokenizers 0.15.0