vit-base-patch16-224-food101-16-7 – AI Model by PedroSampaio | AlphaNeural AI

You can deploy this model and start earning money today!

PedroSampaio/
vit-base-patch16-224-food101-16-7

like

0

image-classification

generated_from_trainer

google/vit-base-patch16-224

autotrain_compatible

endpoints_compatible

Views

No views yet

vit-base-patch16-224-food101-16-7

This model is a fine-tuned version of google/vit-base-patch16-224 on the food101 dataset. It achieves the following results on the evaluation set:

Loss: 0.3293
Accuracy: 0.9081

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
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9326	1.0	1183	0.5737	0.8566
0.6632	2.0	2367	0.4265	0.884
0.4608	3.0	3551	0.3747	0.8958
0.5356	4.0	4735	0.3557	0.8992
0.483	5.0	5918	0.3431	0.9044
0.3975	6.0	7102	0.3343	0.9071
0.3716	7.0	8281	0.3293	0.9081

Framework versions

Transformers 4.34.1
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1