ViNormT5

This model is a fine-tuned version of VietAI/vit5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2580
• Bleu Score: 79.3456
• Precision: 57.4671
• Recall: 57.4671
• Gen Len: 12.7694
• Err: 57.4671

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: 0.0002
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu Score	Precision	Recall	Gen Len	Err
0.5544	1.0	838	0.2951	75.8053	45.9976	45.9976	12.6918	45.9976
0.2306	2.0	1676	0.2519	77.9908	51.9713	51.9713	12.7515	51.9713
0.1091	3.0	2514	0.2437	78.935	54.9582	54.9582	12.7778	54.9582
0.0435	4.0	3352	0.2580	79.3456	57.4671	57.4671	12.7694	57.4671

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.0