<!-- 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-tfA
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: 5.5525
- Validation Loss: 4.0997
- Train Bleu: 0.1041
- Train Gen Len: 201.1370
- Epoch: 4
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': 0.9, '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': 0.001}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Bleu | Train Gen Len | Epoch |
|---|---|---|---|---|
| 11.6054 | 6.6077 | 0.0114 | 14.7389 | 0 |
| 7.1266 | 5.0863 | 0.0067 | 257.6037 | 1 |
| 6.3089 | 4.7488 | 0.0951 | 72.3407 | 2 |
| 5.8855 | 4.4007 | 0.0793 | 112.35 | 3 |
| 5.5525 | 4.0997 | 0.1041 | 201.1370 | 4 |
Framework versions
- Transformers 4.33.3
- TensorFlow 2.14.0
- Datasets 2.14.5
- Tokenizers 0.13.3
