bartpho-word-base-question-answering

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

bartpho-word-base-question-answering

This model is a fine-tuned version of vinai/bartpho-word-base on UIT-ViQuAD2.0 dataset.

Model description

This model is the fine-tuned version of vinai/bartpho-word-base model on UIT-ViQuAD2.0 dataset.

Intended uses & limitations

The model can be used for Vietnamese Machine Reading Comprehensive (MRC) task to answer a question of a given context.

Training and evaluation data

UIT-ViQuAD2.0 dataset.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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: 7

Training results

F1-Score: 71.1

EM: 49.2

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0