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: 1.4916
• Accuracy: 0.4688

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	20	2.0695	0.1812
No log	2.0	40	2.0566	0.2062
No log	3.0	60	2.0300	0.2625
No log	4.0	80	1.9731	0.3125
No log	5.0	100	1.8858	0.3375
No log	6.0	120	1.7904	0.3438
No log	7.0	140	1.7051	0.3875
No log	8.0	160	1.6312	0.4
No log	9.0	180	1.5429	0.45
No log	10.0	200	1.4916	0.4688

Framework versions

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