metadata

license: mit
tags:
  - generated_from_trainer
datasets:
  - tapaco
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: punctuation-taboa-bert
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: tapaco
          type: tapaco
          config: all_languages
          split: train
          args: all_languages
        metrics:
          - name: Precision
            type: precision
            value: 0.9849559686888454
          - name: Recall
            type: recall
            value: 0.9836325882496642
          - name: F1
            type: f1
            value: 0.9842938336490864
          - name: Accuracy
            type: accuracy
            value: 0.9945622875893589

punctuation-taboa-bert

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

Loss: 0.0181
Precision: 0.9850
Recall: 0.9836
F1: 0.9843
Accuracy: 0.9946

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0272	1.0	17438	0.0181	0.9850	0.9836	0.9843	0.9946
0.0234	2.0	34876	0.0196	0.9870	0.9853	0.9862	0.9948
0.0092	3.0	52314	0.0233	0.9874	0.9853	0.9864	0.9950

Framework versions

Transformers 4.23.1
Pytorch 1.12.1+cu113
Datasets 2.5.2
Tokenizers 0.13.1