vit-large-patch16-224-in21k-dungeon-geo-morphs-denoised-04Dec24-003

This model is a fine-tuned version of google/vit-large-patch16-224-in21k on the dungeon-geo-morphs dataset. It achieves the following results on the evaluation set:

• Loss: 0.0725
• Accuracy: 1.0

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: 40
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.5126	4.0	10	1.3321	0.6384
1.049	8.0	20	0.7613	0.8444
0.5397	12.0	30	0.4086	0.9434
0.2381	16.0	40	0.2025	0.9899
0.1152	20.0	50	0.1160	0.9899
0.058	24.0	60	0.0725	1.0
0.0392	28.0	70	0.0678	0.9899
0.026	32.0	80	0.0444	0.9960

Framework versions

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