vit-large-patch16-224-in21k-dungeon-geo-morphs-denoised-04Dec24-004

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: 0.0486
• 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
1.4428	4.0	10	1.0774	0.7192
0.8313	8.0	20	0.5764	0.9010
0.3864	12.0	30	0.2752	0.9576
0.164	16.0	40	0.1299	0.9879
0.08	20.0	50	0.0736	0.9960
0.046	24.0	60	0.0486	1.0
0.0243	28.0	70	0.0369	0.9939
0.0194	32.0	80	0.0254	1.0

Framework versions

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