vit-base-beans-demo-v5

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

• Loss: 0.0984
• Accuracy: 0.9762

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: 16
• 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: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1192	0.1764	100	0.1158	0.9692
0.0734	0.3527	200	0.1268	0.9702
0.0701	0.5291	300	0.1057	0.9673
0.1107	0.7055	400	0.1081	0.9722
0.0413	0.8818	500	0.0984	0.9762

Framework versions

• Transformers 4.47.0
• Pytorch 2.4.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0