vit-large-patch16-224-dungeon-geo-morphs-0-4-30Nov24-005

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: 0.1439
• Accuracy: 0.9875

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
1.5645	4.3636	10	1.2976	0.525
1.0147	8.7273	20	0.7672	0.8393
0.5992	13.2727	30	0.4470	0.9446
0.343	17.6364	40	0.2926	0.9589
0.2065	22.1818	50	0.1980	0.9786
0.1286	26.5455	60	0.1439	0.9875
0.082	31.0909	70	0.1141	0.9857
0.0649	35.4545	80	0.1032	0.9839

Framework versions

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