mobilevit_ai_real_classifier – AI Model by songthienll | AlphaNeural AI

You can deploy this model and start earning money today!

songthienll/
mobilevit_ai_real_classifier

like

0

image-classification

generated_from_trainer

apple/mobilevit-small

autotrain_compatible

endpoints_compatible

Views

No views yet

mobilevit_ai_real_classifier

This model is a fine-tuned version of apple/mobilevit-small on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.1279
Accuracy: 0.9567

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: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2617	1.0	219	0.2093	0.918
0.2115	2.0	438	0.1867	0.921
0.1832	3.0	657	0.2291	0.9135
0.1516	4.0	876	0.1993	0.9175
0.1303	5.0	1095	0.1567	0.945
0.1113	6.0	1314	0.1590	0.947
0.0992	7.0	1533	0.1634	0.94
0.0794	8.0	1752	0.1702	0.9445
0.0819	9.0	1971	0.1566	0.949
0.0725	10.0	2190	0.1620	0.949

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1