val-vit-kitchen-shapes

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: 1.4589
• Accuracy: 0.3925

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: 2e-05
• train_batch_size: 10
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	60	1.4294	0.4393
No log	2.0	120	1.4529	0.4019
No log	3.0	180	1.4798	0.4112
No log	4.0	240	1.4490	0.4206
No log	5.0	300	1.4589	0.3925

Framework versions

• Transformers 4.39.0
• Pytorch 2.1.0
• Datasets 2.18.0
• Tokenizers 0.15.2