vit-large-patch16-224-dungeon-geo-morphs-0-4-30Nov24-001

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: 0.1078
• Accuracy: 0.9821

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
1.5783	4.3636	10	1.2305	0.65
0.6956	8.7273	20	0.5841	0.8946
0.1959	13.2727	30	0.3096	0.9554
0.0443	17.6364	40	0.1980	0.9589
0.0116	22.1818	50	0.1434	0.9679
0.005	26.5455	60	0.1169	0.9786
0.0026	31.0909	70	0.1078	0.9821
0.0022	35.4545	80	0.1072	0.9804

Framework versions

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