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: 1.2333
• Accuracy: 0.55

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	40	1.3397	0.4938
No log	2.0	80	1.3036	0.5312
No log	3.0	120	1.3684	0.5125
No log	4.0	160	1.3877	0.5
No log	5.0	200	1.2441	0.5625
No log	6.0	240	1.3767	0.5
No log	7.0	280	1.2784	0.5437
No log	8.0	320	1.3191	0.5188
No log	9.0	360	1.3417	0.5062
No log	10.0	400	1.3411	0.5125
No log	11.0	440	1.3460	0.5062
No log	12.0	480	1.4155	0.5
0.483	13.0	520	1.2887	0.5375
0.483	14.0	560	1.3648	0.5
0.483	15.0	600	1.3337	0.5

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.1