mt5_base-qg-aap-oficial
This model is a fine-tuned version of google/mt5-base on the tiagoblima/preprocessed-du-qg-squadv1_pt dataset. It achieves the following results on the evaluation set:
- Loss: 1.0870
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 |
|---|---|---|---|
| 1.7144 | 1.0 | 1386 | 1.3310 |
| 1.5556 | 2.0 | 2772 | 1.2120 |
| 1.4427 | 3.0 | 4158 | 1.1406 |
| 1.3878 | 4.0 | 5544 | 1.0971 |
| 1.3626 | 5.0 | 6930 | 1.0870 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.1