mbart_VietnameseToEnglish_60k

This model is a fine-tuned version of NghiemAbe/mbart_VietnameseToEnglish on the None dataset. It achieves the following results on the evaluation set (size 1000):

• 'eval_loss': 1.2711644172668457,
• 'eval_bleu': 32.5607,
• 'eval_gen_len': 21.2096,
• 'eval_runtime': 952.3829,
• 'eval_samples_per_second': 5.25,
• 'eval_steps_per_second': 0.329

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
1.1212	1.0	3750	1.4557	27.1385	33.638

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1