<!-- 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. -->
bearbearchu/mt5-small-finetuned-wikipedia-summarization-jp
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: 0.2757
- Validation Loss: 0.2210
- 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': 7656, '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 |
|---|---|---|
| 1.1713 | 0.3484 | 0 |
| 0.6239 | 0.3156 | 1 |
| 0.4820 | 0.2693 | 2 |
| 0.3973 | 0.2595 | 3 |
| 0.3377 | 0.2480 | 4 |
| 0.3093 | 0.2321 | 5 |
| 0.2843 | 0.2236 | 6 |
| 0.2757 | 0.2210 | 7 |
Framework versions
- Transformers 4.21.1
- TensorFlow 2.8.2
- Datasets 2.4.0
- Tokenizers 0.12.1
