vit-cifar10-fine-tuned – AI Model by shivrajbadu | AlphaNeural AI

You can deploy this model and start earning money today!

shivrajbadu/
vit-cifar10-fine-tuned

like

0

image-classification

generated_from_trainer

google/vit-base-patch16-224

autotrain_compatible

endpoints_compatible

Views

No views yet

vit-cifar10-fine-tuned

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

Loss: 0.0603

Model description

Made few prediction tests on following classes during self study.

airplane
automobile
bird
cat
deer
dog
frog
horse
ship
truck

image/png

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: 8
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
lr_scheduler_warmup_steps: 500
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.1156	0.16	500	0.1052
0.0768	0.32	1000	0.0869
0.0552	0.48	1500	0.0761
0.0533	0.64	2000	0.0614
0.0441	0.8	2500	0.0712
0.0567	0.96	3000	0.0699
0.0101	1.12	3500	0.0583
0.0075	1.28	4000	0.0630
0.0091	1.44	4500	0.0617
0.0122	1.6	5000	0.0611
0.0153	1.76	5500	0.0589
0.0173	1.92	6000	0.0716
0.0018	2.08	6500	0.0586
0.0062	2.24	7000	0.0610
0.0061	2.4	7500	0.0578
0.0005	2.56	8000	0.0555
0.0006	2.7200	8500	0.0591
0.0003	2.88	9000	0.0603

Framework versions

Transformers 4.48.3
Pytorch 2.6.0
Datasets 3.3.0
Tokenizers 0.21.0