Adeptschneider/opus-mt-dyu-fr

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: 0.4349
• Validation Loss: 3.7720
• Epoch: 20

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
4.2081	3.6259	0
3.4679	3.4347	1
3.0948	3.3176	2
2.7833	3.2584	3
2.5063	3.2218	4
2.2673	3.2113	5
2.0584	3.2196	6
1.8604	3.2329	7
1.6837	3.2526	8
1.5233	3.2799	9
1.3768	3.3051	10
1.2342	3.3325	11
1.1145	3.3796	12
0.9931	3.4345	13
0.8911	3.4657	14
0.7914	3.5177	15
0.7034	3.5688	16
0.6226	3.6150	17
0.5546	3.6662	18
0.4875	3.7227	19
0.4349	3.7720	20

Framework versions

• Transformers 4.38.2
• TensorFlow 2.15.1
• Datasets 2.18.0
• Tokenizers 0.15.2