clasificador-reviews-amazon
This model is a fine-tuned version of bert-base-uncased on the amazon_polarity dataset. It achieves the following results on the evaluation set:
- Loss: 0.4642
- Accuracy: 0.926
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
Los conjuntos de train y de test se han reducido respecto al dataset original amazon_polarity para mantener unos tiempos de ejecución relativamente cortos.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-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: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3674 | 1.0 | 625 | 0.2204 | 0.928 |
| 0.1924 | 2.0 | 1250 | 0.3444 | 0.926 |
| 0.0974 | 3.0 | 1875 | 0.4642 | 0.926 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3