model

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: 0.0560
• Accuracy: 0.9867

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: 3
• 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: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1455	0.4279	10000	0.0871	0.9822
0.2997	0.8557	20000	0.0938	0.9748
0.0095	1.2836	30000	0.0787	0.9822
0.0047	1.7114	40000	0.0804	0.9799
0.0025	2.1393	50000	0.0647	0.9848
0.0085	2.5672	60000	0.0577	0.9864
0.0015	2.9950	70000	0.0618	0.9867
0.0996	3.4229	80000	0.0596	0.9869
0.0755	3.8508	90000	0.0560	0.9867

Framework versions

• Transformers 4.48.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0