finetuned_HelsinkiNLP-opus-mt-en-vi_PhoMT

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

• Loss: 1.3069
• Bleu: 42.4251

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
1.4437	1.0	186125	1.3648	40.6353
1.3748	2.0	372250	1.3362	41.4991
1.3182	3.0	558375	1.3224	41.9860
1.2829	4.0	744500	1.3113	42.2649
1.2641	5.0	930625	1.3069	42.4233

Framework versions

• Transformers 4.22.1
• Pytorch 1.10.1+cu113
• Datasets 2.4.0
• Tokenizers 0.12.1