vit-base-travel-document-classification

This model is a fine-tuned version of google/vit-base-patch16-224 on the TianZhou621/travel-document-dataset dataset. It achieves the following results on the evaluation set:

• Loss: 0.4433
• Accuracy: 1.0

Model description

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: 0.0003
• train_batch_size: 4
• eval_batch_size: 8
• 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	Accuracy
No log	1.0	8	0.6273	0.5
No log	2.0	16	0.5903	0.75
No log	3.0	24	0.5776	0.75

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.1
• Tokenizers 0.21.1