ZycckZ/Zk1-QA-VN-test

VieModTest

This model is a fine-tuned version of KoichiYasuoka/bert-base-vietnamese-ud-goeswith model and taidng/UIT-ViQuAD2 dataset. It achieves the following results on the evaluation set:

• Loss: 1.6558
• Exact Match (EM): 50.28
• F1 Score: 70.75

Model description

• This model maybe not too bad and not is the best 😁 maybe 😅
• Trained total 115,354,368 parameters

Intended uses & limitations

• Create a simple chatbot 🤗
• Maybe just understand Vietnamese

Training and evaluation data

• taidng/UIT-ViQuAD2.0 - "train"
• taidng/UIT-ViQuAD2.0 - "validation"

Training procedure

Based on Question Answering HuggingFace 🤗

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.8987	1.0	1423	1.6217
1.3346	2.0	2846	1.5800
1.0633	3.0	4269	1.6558

Framework versions

• Transformers 4.51.1
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1