vit-base-patch16-224-cifar10
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the cifar10 dataset.
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Framework versions
- Transformers 4.19.0.dev0
- Pytorch 1.10.1
- Datasets 2.1.0
- Tokenizers 0.12.1
- Downloads last month
- 12
Dataset used to train karthiksv/vit-base-patch16-224-cifar10
Evaluation results
- Accuracy on cifar10test set self-reported0.100
- Precision Macro on cifar10test set self-reported0.077
- Precision Micro on cifar10test set self-reported0.100
- Precision Weighted on cifar10test set self-reported0.077
- Recall Macro on cifar10test set self-reported0.100
- Recall Micro on cifar10test set self-reported0.100
- Recall Weighted on cifar10test set self-reported0.100
- F1 Macro on cifar10test set self-reported0.079