vit-base-patch16-224-cl-v1

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: 2.4053
• Accuracy: 0.5027

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.6762	1.0	353	3.4472	0.3691
2.8516	2.0	706	2.5892	0.4738
2.6887	3.0	1059	2.4053	0.5027

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.0
• Datasets 2.14.4
• Tokenizers 0.13.3