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

Loss: 0.3879
Accuracy: 0.8901

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: 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: cosine
lr_scheduler_warmup_steps: 0.1
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.4838	1.0	48	1.0466	0.7225
0.6587	2.0	96	0.4952	0.8534
0.3246	3.0	144	0.3935	0.8848
0.2179	4.0	192	0.3825	0.9058
0.1602	5.0	240	0.3896	0.8953
0.1212	6.0	288	0.3723	0.8953
0.1028	7.0	336	0.3793	0.8796
0.0767	8.0	384	0.3885	0.8953
0.0682	9.0	432	0.3887	0.8901
0.0827	10.0	480	0.3879	0.8901

Framework versions

Transformers 5.9.0
Pytorch 2.12.0
Datasets 4.8.5
Tokenizers 0.22.2

jaime168/hf_cat_breed_classifier-vit-base-patch16-224

hf_cat_breed_classifier-vit-base-patch16-224

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jaime168/
hf_cat_breed_classifier-vit-base-patch16-224