vit_cifar10_classification_tmp

This model is a fine-tuned version of againeureka/vit_cifar10_classification_tmp on the cifar10 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0945
• Accuracy: 0.9781

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: 0.0002
• train_batch_size: 128
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2199	0.26	100	0.1853	0.9678
0.0999	0.51	200	0.1270	0.9713
0.0944	0.77	300	0.0945	0.9781

Framework versions

• Transformers 4.29.1
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.2