cards-vit-base-patch16-224-finetuned-v1

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: 1.9972
• Accuracy: 0.3170

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: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• 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
1.7068	0.9993	378	1.9533	0.2753
1.6691	1.9987	756	1.9642	0.2864
1.6278	2.9980	1134	1.9935	0.3018
1.5837	4.0	1513	2.0155	0.3077
1.5263	4.9993	1891	2.0283	0.3063
1.4969	5.9987	2269	2.0026	0.3081
1.5088	6.9980	2647	2.0275	0.3098
1.4623	8.0	3026	2.0096	0.3137
1.4305	8.9993	3404	2.0239	0.3154
1.3895	9.9934	3780	1.9972	0.3170

Framework versions

• Transformers 4.40.1
• Pytorch 2.0.1+cu117
• Datasets 2.19.1
• Tokenizers 0.19.1