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: 1.2368
• Accuracy: 0.5312

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: 7e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	5	1.2726	0.575
No log	2.0	10	1.3480	0.5062
No log	3.0	15	1.2696	0.5375
No log	4.0	20	1.2715	0.5312
No log	5.0	25	1.2360	0.5687
No log	6.0	30	1.2728	0.5125
No log	7.0	35	1.2374	0.525
No log	8.0	40	1.2484	0.5437
No log	9.0	45	1.2336	0.5563
No log	10.0	50	1.2128	0.6

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3