This model is a fine-tuned version of google/vit-large-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.0232
Accuracy: 0.9787

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
1.0832	4.4444	10	0.4421	0.9149
0.1422	8.8889	20	0.0481	1.0
0.0055	13.3333	30	0.0213	1.0
0.0007	17.7778	40	0.0223	0.9787
0.0003	22.2222	50	0.0205	0.9787
0.0002	26.6667	60	0.0223	0.9787
0.0002	31.1111	70	0.0232	0.9787

Framework versions

Transformers 4.46.2
Pytorch 2.5.0+cu121
Datasets 3.1.0
Tokenizers 0.20.3

griffio/vit-large-patch16-224-new-dungeon-geo-morphs-002

vit-large-patch16-224-new-dungeon-geo-morphs-002

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

griffio/
vit-large-patch16-224-new-dungeon-geo-morphs-002