HCMUS-vietnamese-correction-project

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: 0.0213
• Bleu: 89.3574
• Cer: 0.0196
• Wer: 0.0563
• F1: 0.9826

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: 3e-05
• train_batch_size: 32
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Cer	Wer	F1
0.3907	1.0	782	0.0338	83.8387	0.0343	0.0892	0.9626
0.0355	2.0	1564	0.0240	87.6565	0.0244	0.0669	0.9763
0.0278	3.0	2346	0.0225	88.6311	0.0216	0.0605	0.9804
0.021	4.0	3128	0.0220	88.8898	0.0200	0.0580	0.9821
0.0187	5.0	3910	0.0213	89.3574	0.0196	0.0563	0.9826

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.1+cu128
• Datasets 4.4.2
• Tokenizers 0.22.1