This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the cifar10 dataset. It achieves the following results on the evaluation set:

Loss: 0.4714
Accuracy: 0.883

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.7956	0.99	62	1.6395	0.817
0.8981	2.0	125	0.8510	0.858
0.6049	2.99	187	0.6666	0.878
0.5427	4.0	250	0.5796	0.88
0.4318	4.99	312	0.5110	0.889
0.3952	6.0	375	0.4339	0.907
0.3544	6.99	437	0.4432	0.902
0.3612	8.0	500	0.4213	0.898
0.3522	8.99	562	0.4474	0.884
0.3096	9.92	620	0.4714	0.883

Framework versions

Transformers 4.28.0
Pytorch 2.0.1+cu118
Datasets 2.12.0
Tokenizers 0.13.3

vhurryharry/cifar

cifar

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

vhurryharry/
cifar