metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_keras_callback
model-index:
- name: pijarcandra22/t5Indo2Jawa
results: []
pijarcandra22/t5Indo2Jawa
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 2.5224
- Validation Loss: 2.2750
- Epoch: 21
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': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 3.5149 | 3.1567 | 0 |
| 3.3816 | 3.0397 | 1 |
| 3.2812 | 2.9518 | 2 |
| 3.1977 | 2.8751 | 3 |
| 3.1223 | 2.8078 | 4 |
| 3.0599 | 2.7507 | 5 |
| 3.0019 | 2.6979 | 6 |
| 2.9517 | 2.6513 | 7 |
| 2.9034 | 2.6121 | 8 |
| 2.8638 | 2.5756 | 9 |
| 2.8232 | 2.5391 | 10 |
| 2.7856 | 2.5089 | 11 |
| 2.7541 | 2.4786 | 12 |
| 2.7219 | 2.4499 | 13 |
| 2.6935 | 2.4256 | 14 |
| 2.6658 | 2.4010 | 15 |
| 2.6389 | 2.3762 | 16 |
| 2.6143 | 2.3550 | 17 |
| 2.5899 | 2.3313 | 18 |
| 2.5665 | 2.3156 | 19 |
| 2.5445 | 2.2939 | 20 |
| 2.5224 | 2.2750 | 21 |
Framework versions
- Transformers 4.35.2
- TensorFlow 2.14.0
- Datasets 2.15.0
- Tokenizers 0.15.0