mammals_multiclass_classification – AI Model by Tianmu28 | AlphaNeural AI

You can deploy this model and start earning money today!

Tianmu28/
mammals_multiclass_classification

like

0

image-classification

generated_from_trainer

google/vit-base-patch16-224

autotrain_compatible

endpoints_compatible

Views

No views yet

mammals_multiclass_classification

This model is a fine-tuned version of google/vit-base-patch16-224 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.2452
Accuracy: 0.9496

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: 5e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5501	1.0	394	0.3697	0.9207
0.0757	2.0	788	0.2894	0.9311
0.034	3.0	1182	0.2865	0.9304
0.0043	4.0	1576	0.2610	0.9385
0.0024	5.0	1970	0.2526	0.9415
0.0007	6.0	2364	0.2452	0.9496
0.0006	7.0	2758	0.2432	0.9481
0.0004	8.0	3152	0.2442	0.9481
0.0004	9.0	3546	0.2484	0.9496
0.0003	10.0	3940	0.2545	0.9467
0.0003	11.0	4334	0.2543	0.9481

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3