This model is a fine-tuned version of google/vit-base-patch16-224 on the custom cat dataset dataset. It achieves the following results on the evaluation set:

Loss: 0.6814
Accuracy: 0.96
Precision: 0.97
Recall: 0.96
F1: 0.96

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: 0.0003
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	12	1.0817	0.875	0.9018	0.875	0.8627
1.1512	2.0	24	0.7125	0.9167	0.9278	0.9167	0.9139
1.1512	3.0	36	0.5354	0.9167	0.9278	0.9167	0.9139
0.5336	4.0	48	0.4571	0.9167	0.9278	0.9167	0.9139
0.3465	5.0	60	0.4346	0.9167	0.9219	0.9167	0.9139

Framework versions

Transformers 5.5.0
Pytorch 2.11.0+cpu
Datasets 4.8.4
Tokenizers 0.22.2

DKatheesrupan/cat-vit

cat-vit

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

DKatheesrupan/
cat-vit