dyu-fr-opus-v2.0

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

• Train Loss: 0.4876
• Validation Loss: 3.7181
• Epoch: 19

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
4.2099	3.6175	0
3.4757	3.4413	1
3.0954	3.3367	2
2.7804	3.2639	3
2.5106	3.2269	4
2.2711	3.2267	5
2.0556	3.2083	6
1.8625	3.2228	7
1.6882	3.2533	8
1.5238	3.2604	9
1.3797	3.2987	10
1.2367	3.3460	11
1.1085	3.3993	12
0.9946	3.4232	13
0.8910	3.4565	14
0.7927	3.5120	15
0.7037	3.5665	16
0.6257	3.6241	17
0.5545	3.6816	18
0.4876	3.7181	19

Framework versions

• Transformers 4.38.2
• TensorFlow 2.15.0
• Datasets 2.18.0
• Tokenizers 0.15.2