ikram98ai/compliance_verification_ViT

vit-base-beans-demo-v5

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the ikram98ai/compliance_verification dataset. It achieves the following results on the evaluation set:

• Loss: 0.5769
• Accuracy: 0.6585

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: 128
• eval_batch_size: 256
• 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: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5984	0.2459	30	0.5906	0.6400
0.6018	0.4918	60	0.5841	0.6579
0.5816	0.7377	90	0.5819	0.6433
0.594	0.9836	120	0.5769	0.6585

Framework versions

• Transformers 4.51.1
• Pytorch 2.5.1+cu124
• Datasets 3.5.0
• Tokenizers 0.21.0