results

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: 1.3098
• Accuracy: 0.575

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	10	1.8622	0.2875
1.7517	2.0	20	1.6548	0.45
1.7517	3.0	30	1.4987	0.4688
0.8128	4.0	40	1.3997	0.5125
0.8128	5.0	50	1.3707	0.5125
0.2863	6.0	60	1.3209	0.525
0.2863	7.0	70	1.3131	0.55
0.0776	8.0	80	1.2887	0.5563
0.0776	9.0	90	1.2996	0.5687
0.0267	10.0	100	1.3032	0.5563
0.0267	11.0	110	1.3003	0.5625
0.0156	12.0	120	1.3069	0.5625
0.0156	13.0	130	1.3039	0.5687
0.0117	14.0	140	1.3037	0.5687
0.0117	15.0	150	1.3059	0.5687
0.0098	16.0	160	1.3098	0.575
0.0098	17.0	170	1.3095	0.5625
0.0088	18.0	180	1.3107	0.5625
0.0088	19.0	190	1.3112	0.5687
0.0083	20.0	200	1.3112	0.5687

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1