<!-- 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. -->
nlewins/mt5-small-finetuned-ceb-to-en-tf
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: 7.3346
- Validation Loss: 4.8338
- Train Bleu: 0.0137
- Train Gen Len: 456.0278
- Epoch: 5
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 | Train Bleu | Train Gen Len | Epoch |
|---|---|---|---|---|
| 17.6758 | 8.8679 | 0.0526 | 11.1630 | 0 |
| 11.7748 | 6.7158 | 0.0312 | 177.5556 | 1 |
| 9.5327 | 5.8409 | 0.0425 | 381.0870 | 2 |
| 8.4461 | 5.3506 | 0.0335 | 439.6315 | 3 |
| 7.8033 | 5.0206 | 0.0192 | 450.5741 | 4 |
| 7.3346 | 4.8338 | 0.0137 | 456.0278 | 5 |
Framework versions
- Transformers 4.33.3
- TensorFlow 2.14.0
- Datasets 2.14.5
- Tokenizers 0.13.3
