<!-- 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. -->
bedus-creation/t5-small-dataset-i-eng-lim-001
This model is a fine-tuned version of bedus-creation/t5-small-dataset-i-eng-lim on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 3.7583
- Validation Loss: 3.7411
- Epoch: 13
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 |
|---|---|---|
| 4.4846 | 4.2595 | 0 |
| 4.2055 | 4.1211 | 1 |
| 4.1093 | 4.0275 | 2 |
| 4.0398 | 3.9973 | 3 |
| 3.9791 | 3.9362 | 4 |
| 3.9739 | 3.8901 | 5 |
| 3.9283 | 3.8724 | 6 |
| 3.9120 | 3.8307 | 7 |
| 3.8557 | 3.8131 | 8 |
| 3.8460 | 3.7868 | 9 |
| 3.7961 | 3.7668 | 10 |
| 3.8028 | 3.7454 | 11 |
| 3.7628 | 3.7471 | 12 |
| 3.7583 | 3.7411 | 13 |
Framework versions
- Transformers 4.33.2
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.13.3
