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: 1.0801
• Accuracy: 0.675

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: 6e-05
• 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
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	23	1.0917	0.625
No log	2.0	46	1.1605	0.6125
No log	3.0	69	1.0543	0.6375
No log	4.0	92	1.1663	0.6
No log	5.0	115	1.2546	0.5875
No log	6.0	138	1.0580	0.6
No log	7.0	161	1.1193	0.6125
No log	8.0	184	1.2297	0.525
No log	9.0	207	1.2295	0.55
No log	10.0	230	1.0842	0.6125

Framework versions

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