vit-base-patch16-224-rotated-dungeons-v103

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

• Loss: 0.8291
• Accuracy: 0.8333

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.522	3.3333	20	0.8489	0.6667
0.0346	6.6667	40	2.3103	0.6667
0.019	10.0	60	1.4623	0.75
0.017	13.3333	80	0.8291	0.8333

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1