opus-mt-en-ro

This model was trained from scratch on the tatoeba dataset. It achieves the following results on the evaluation set:

• Loss: 0.5128
• Model Preparation Time: 0.0032
• Bleu: 56.0514

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	Model Preparation Time	Bleu
0.5958	1.0	427	0.5168	0.0032	56.1356
0.4699	2.0	854	0.5128	0.0032	56.0514
0.4118	3.0	1281	0.5130	0.0032	56.6443

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1