metadata

library_name: transformers
tags:
  - translation
  - generated_from_trainer
datasets:
  - tatoeba
metrics:
  - bleu
model-index:
  - name: opus-mt-en-ro
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: tatoeba
          type: tatoeba
          config: en-ro
          split: train
          args: en-ro
        metrics:
          - name: Bleu
            type: bleu
            value: 56.051440475882075

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