vit-large-patch16-224-dungeon-geo-morphs-0-4-30Nov24-012

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: 0.0763
• Accuracy: 0.9929

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: 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: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.4699	3.9091	10	0.9471	0.7821
0.5263	7.9091	20	0.3796	0.9214
0.1867	11.9091	30	0.2458	0.9357
0.0908	15.9091	40	0.1267	0.9857
0.0436	19.9091	50	0.0763	0.9929
0.0256	23.9091	60	0.0681	0.9929

Framework versions

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