Edit model card

nlp-vietnamese

This model is a fine-tuned version of vinai/bartpho-syllable on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0590
  • Sacrebleu: 21.1408

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: 12
  • eval_batch_size: 12
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 48
  • 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 Sacrebleu
No log 1.0 166 0.2705 11.9103
No log 2.0 332 0.0998 18.3922
No log 3.0 498 0.0668 20.3883
No log 4.0 664 0.0611 20.8298
No log 5.0 830 0.0590 21.1408

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
3
Safetensors
Model size
396M params
Tensor type
F32
·

Finetuned from