metadata
license: mit
base_model: neuralmind/bert-base-portuguese-cased
tags:
- generated_from_trainer
datasets:
- glue-ptpt
metrics:
- accuracy
- f1
model-index:
- name: paraphrase-bert-portuguese
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue-ptpt
type: glue-ptpt
config: mrpc
split: validation
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.8848039215686274
- name: F1
type: f1
value: 0.919104991394148
paraphrase-bert-portuguese
This model is a fine-tuned version of neuralmind/bert-base-portuguese-cased on the glue-ptpt dataset. It achieves the following results on the evaluation set:
- Loss: 0.7884
- Accuracy: 0.8848
- F1: 0.9191
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: 8
- eval_batch_size: 8
- 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 | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.1866 | 1.09 | 500 | 0.5935 | 0.8775 | 0.9104 |
| 0.1791 | 2.18 | 1000 | 0.6557 | 0.8676 | 0.9062 |
| 0.0676 | 3.27 | 1500 | 0.7884 | 0.8848 | 0.9191 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3