kabelomalapane/Helsinki-NLP-opus-finetuned-en-to-zu

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-mul on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 1.5907
• Validation Loss: 1.6321
• Epoch: 2

Model description

More information needed

Intended uses & limitations

This model is to be used to translate English into Zulu. But there are still some problems in running this model, so it's still to be modified.

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 783, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Epoch
2.1622	1.7379	0
1.7292	1.6529	1
1.5907	1.6321	2

Framework versions

• Transformers 4.16.2
• TensorFlow 2.8.0
• Datasets 1.18.3
• Tokenizers 0.11.0