image_classification

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: 1.5032
• Accuracy: 0.5375

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: 0.0003
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0207	1.0	10	1.3284	0.4875
0.9015	2.0	20	1.2407	0.5687
0.7775	3.0	30	1.3203	0.55
0.649	4.0	40	1.2159	0.5312
0.5012	5.0	50	1.4273	0.5
0.546	6.0	60	1.3676	0.5
0.4387	7.0	70	1.4644	0.5062
0.3772	8.0	80	1.3247	0.5563
0.3367	9.0	90	1.5443	0.5125
0.3075	10.0	100	1.3807	0.575
0.3138	11.0	110	1.4366	0.5188
0.2298	12.0	120	1.5350	0.4938
0.2454	13.0	130	1.4485	0.5312
0.2273	14.0	140	1.5771	0.475
0.187	15.0	150	1.4757	0.5312

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0