metadata
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: my-finetuned-mt5-class0
results: []
my-finetuned-mt5-class0
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: 2.0505
- Validation Loss: 1.7733
- Epoch: 7
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': 107192, '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 |
|---|---|---|
| 3.5536 | 2.1181 | 0 |
| 2.4769 | 1.9296 | 1 |
| 2.2865 | 1.8569 | 2 |
| 2.1928 | 1.8241 | 3 |
| 2.1344 | 1.8022 | 4 |
| 2.0953 | 1.7880 | 5 |
| 2.0671 | 1.7811 | 6 |
| 2.0505 | 1.7733 | 7 |
Framework versions
- Transformers 4.24.0
- TensorFlow 2.9.2
- Datasets 2.7.1
- Tokenizers 0.13.2