vit-large-patch16-224-new-dungeon-geo-morphs-025

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: 0.5643
• Accuracy: 0.9434

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: 35
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0	3.6364	10	0.5643	0.9434
0.0	7.2727	20	0.6440	0.9434
0.0	10.9091	30	0.6484	0.9434
0.0	14.5455	40	0.6491	0.9434
0.0	18.1818	50	0.6515	0.9434
0.0	21.8182	60	0.6539	0.9434
0.0	25.4545	70	0.6547	0.9434

Framework versions

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