vit-base-patch16-224-finetuned-flowers

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: 0.1542
• Accuracy: 0.9728

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-06
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9927	0.5376	50	0.7656	0.8828
0.6638	1.0753	100	0.4909	0.9292
0.4344	1.6129	150	0.3344	0.9482
0.3479	2.1505	200	0.2529	0.9646
0.2803	2.6882	250	0.2076	0.9673
0.2208	3.2258	300	0.1812	0.9673
0.2083	3.7634	350	0.1662	0.9728
0.1948	4.3011	400	0.1576	0.9728
0.1855	4.8387	450	0.1542	0.9728

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1