opus-mt-vi-en-finetuned-ba-to-en

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

• Loss: 4.9806
• Bleu: 0.5733
• Gen Len: 32.227

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: 1e-05
• train_batch_size: 64
• eval_batch_size: 16
• seed: 42
• optimizer: Use 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: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
3.5162	1.0	360	4.9645	0.4174	36.227
3.0009	2.0	720	4.9700	0.6196	31.905
2.7889	3.0	1080	4.9772	0.6215	32.137
2.6722	4.0	1440	4.9654	0.6355	32.077
2.6167	5.0	1800	4.9806	0.5733	32.227

Framework versions

• Transformers 4.46.3
• Pytorch 2.4.0
• Datasets 3.1.0
• Tokenizers 0.20.3