vietnamese-correction-203

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: 0.1838
• Sacrebleu: 27.6927

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• 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
0.3565	0.7529	2000	0.1943	26.5749
0.1717	1.5059	4000	0.1713	27.1811
0.116	2.2588	6000	0.1705	27.3551
0.076	3.0118	8000	0.1582	27.5668
0.0418	3.7647	10000	0.1674	27.5994
0.0278	4.5176	12000	0.1839	27.6218

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1