vit-large-patch16-224-dungeon-geo-morphs-0-4-30Nov24-008

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

• Loss: 0.1019
• Accuracy: 0.9732

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 40
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.538	3.9091	10	1.2297	0.5982
0.7675	7.9091	20	0.5668	0.9321
0.2383	11.9091	30	0.2734	0.95
0.0619	15.9091	40	0.1570	0.9643
0.0172	19.9091	50	0.1019	0.9732
0.0058	23.9091	60	0.0944	0.9696
0.0031	27.9091	70	0.0848	0.9714
0.0024	31.9091	80	0.0830	0.9714

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3