HCMUS-vietnamese-correction-project-60k – AI Model by pqthinh232 | AlphaNeural AI

You can deploy this model and start earning money today!

pqthinh232/
HCMUS-vietnamese-correction-project-60k

like

0

text2text-generation

generated_from_trainer

vinai/bartpho-syllable

endpoints_compatible

Views

No views yet

HCMUS-vietnamese-correction-project-60k

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: 41.8607
Cer: 0.4352
Wer: 0.4528
F1: 0.8066

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	38.5848	0.4445	0.4752	0.7890
0.0355	2.0	1564	0.0240	40.8109	0.4392	0.4608	0.8004
0.0278	3.0	2346	0.0225	41.5211	0.4360	0.4551	0.8048
0.021	4.0	3128	0.0220	41.6801	0.4350	0.4533	0.8063
0.0187	5.0	3910	0.0213	41.8607	0.4352	0.4528	0.8066

Framework versions

Transformers 4.57.3
Pytorch 2.9.1+cu128
Datasets 4.4.2
Tokenizers 0.22.1