vit-base-patch16-224-pure-ViT

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

• Loss: 0.3270
• Accuracy: 0.8715

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4676	1.0	202	0.4042	0.8095
0.4605	2.0	404	0.3675	0.8377
0.4012	3.0	606	0.3486	0.8506
0.3727	4.0	808	0.3413	0.8481
0.3482	5.0	1010	0.3339	0.8614
0.354	6.0	1212	0.3436	0.8561
0.3212	7.0	1414	0.3415	0.8534
0.3263	8.0	1616	0.3281	0.8642
0.285	9.0	1818	0.3263	0.8673
0.2779	10.0	2020	0.3270	0.8715

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2