t5_base-qg-aas-oficial
This model is a fine-tuned version of unicamp-dl/ptt5-base-portuguese-vocab on the tiagoblima/preprocessed-du-qg-squadv1_pt dataset. It achieves the following results on the evaluation set:
- Loss: 2.0362
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1854 | 1.0 | 1386 | 2.0911 |
| 2.048 | 2.0 | 2772 | 2.0533 |
| 1.9295 | 3.0 | 4158 | 2.0422 |
| 1.9142 | 4.0 | 5544 | 2.0362 |
| 1.8512 | 5.0 | 6930 | 2.0399 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.1