results
This model is a fine-tuned version of pierreguillou/gpt2-small-portuguese on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.1675
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.0373 | 1.0 | 38 | 4.1597 |
| 3.8691 | 2.0 | 76 | 4.1378 |
| 3.8037 | 3.0 | 114 | 4.1324 |
| 3.6804 | 4.0 | 152 | 4.1340 |
| 3.5658 | 5.0 | 190 | 4.1411 |
| 3.4923 | 6.0 | 228 | 4.1479 |
| 3.3789 | 7.0 | 266 | 4.1537 |
| 3.4002 | 8.0 | 304 | 4.1621 |
| 3.3624 | 9.0 | 342 | 4.1654 |
| 3.3 | 10.0 | 380 | 4.1675 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 2
Model tree for eudesfilho/results
Base model
pierreguillou/gpt2-small-portuguese