serhii-korobchenko/mt5-small_poetry_test-2024-02-23-11-37-04
This model is a fine-tuned version of serhii-korobchenko/mt5-small_poetry_test-2024-02-23-09-44-03 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 4.2334
- Validation Loss: 3.3547
- Epoch: 16
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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 2400, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.0001}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 6.6604 | 4.1654 | 0 |
| 6.0975 | 3.9769 | 1 |
| 5.7642 | 3.8194 | 2 |
| 5.5421 | 3.7233 | 3 |
| 5.5621 | 3.6724 | 4 |
| 5.2110 | 3.6284 | 5 |
| 5.0164 | 3.5796 | 6 |
| 4.9996 | 3.5401 | 7 |
| 4.8020 | 3.4781 | 8 |
| 4.7490 | 3.4661 | 9 |
| 4.6101 | 3.4544 | 10 |
| 4.4780 | 3.4371 | 11 |
| 4.4204 | 3.4310 | 12 |
| 4.3121 | 3.3932 | 13 |
| 4.2895 | 3.3719 | 14 |
| 4.2082 | 3.3649 | 15 |
| 4.2334 | 3.3547 | 16 |
Framework versions
- Transformers 4.37.2
- TensorFlow 2.15.0
- Datasets 2.17.1
- Tokenizers 0.15.2