<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
MUmairAB/mt5-small-finetuned-en-and-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: 3.8111
- Validation Loss: 3.3450
- Epoch: 9
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': 12090, '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: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 9.8080 | 4.2830 | 0 |
| 5.9101 | 3.8003 | 1 |
| 5.1453 | 3.6062 | 2 |
| 4.7005 | 3.5052 | 3 |
| 4.4095 | 3.4904 | 4 |
| 4.2204 | 3.3996 | 5 |
| 4.0501 | 3.3842 | 6 |
| 3.9260 | 3.3963 | 7 |
| 3.8527 | 3.3267 | 8 |
| 3.8111 | 3.3450 | 9 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.12.0
- Datasets 2.14.0
- Tokenizers 0.13.3
