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: 0.1275
Accuracy: 0.9625

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
1.3834	3.9091	10	1.1055	0.7929
0.5606	7.9091	20	0.5141	0.9286
0.13	11.9091	30	0.2629	0.9518
0.0283	15.9091	40	0.1654	0.9464
0.0082	19.9091	50	0.1352	0.9554
0.0043	23.9091	60	0.1337	0.9589
0.0033	27.9091	70	0.1257	0.9607
0.0029	31.9091	80	0.1275	0.9625

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3

griffio/vit-large-patch16-224-in21k-dungeon-geo-morphs-0-4-30Nov24-004

vit-large-patch16-224-in21k-dungeon-geo-morphs-0-4-30Nov24-004

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

griffio/
vit-large-patch16-224-in21k-dungeon-geo-morphs-0-4-30Nov24-004