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: 1.5137
• Accuracy: 0.45

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	40	1.5946	0.4062
No log	2.0	80	1.5868	0.4062
No log	3.0	120	1.5588	0.425
No log	4.0	160	1.5516	0.425
No log	5.0	200	1.5479	0.4313
No log	6.0	240	1.5150	0.4813
No log	7.0	280	1.5037	0.4625
No log	8.0	320	1.5131	0.475
No log	9.0	360	1.5091	0.425
No log	10.0	400	1.5117	0.4125

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.2