marian-finetuned-kde4-en-to-fr

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-fr on the kde4 dataset. It achieves the following results on the evaluation set:

• Loss: 0.7609
• Bleu: 41.9091

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:

• learning_rate: 2e-05
• train_batch_size: 32
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
No log	1.0	282	0.7520	39.7427
0.7807	2.0	564	0.7585	35.7192
0.7807	3.0	846	0.7609	37.1767

Framework versions

• Transformers 4.50.2
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1