nlewins/mt5-small-finetuned-ceb-to-en-tfG
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: 5.1913
- Validation Loss: 3.3805
- Train Bleu: 0.7692
- Train Gen Len: 59.0253
- Epoch: 1
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': {'module': 'keras.optimizers.schedules', 'class_name': 'ExponentialDecay', 'config': {'initial_learning_rate': 0.0001, 'decay_steps': 10000, 'decay_rate': 0.6, 'staircase': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.0001}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Bleu | Train Gen Len | Epoch |
|---|---|---|---|---|
| 8.1364 | 3.7729 | 0.4430 | 65.2191 | 0 |
| 5.1913 | 3.3805 | 0.7692 | 59.0253 | 1 |
Framework versions
- Transformers 4.34.0
- TensorFlow 2.14.0
- Datasets 2.14.5
- Tokenizers 0.14.1