EhtashamNQ/mt5-small-finetuned-amazon-en-es
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 2.5396
- Validation Loss: 2.8061
- Epoch: 5
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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 5208, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 20.5300 | 7.1775 | 0 |
| 5.5220 | 3.7545 | 1 |
| 3.4137 | 3.5929 | 2 |
| 2.9827 | 3.0892 | 3 |
| 2.7228 | 2.8718 | 4 |
| 2.5396 | 2.8061 | 5 |
Framework versions
- Transformers 4.24.0
- TensorFlow 2.9.2
- Datasets 2.6.1
- Tokenizers 0.13.2