This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.9305
Accuracy: 0.8765
Precision: 0.8810
Recall: 0.8765
F1: 0.8766

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: 5e-05
train_batch_size: 4
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine_with_restarts
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	160	0.3941	0.8519	0.8562	0.8519	0.8519
No log	2.0	320	0.9611	0.7901	0.8162	0.7901	0.7880
No log	3.0	480	0.8992	0.8272	0.8505	0.8272	0.8258
0.3748	4.0	640	0.9305	0.8765	0.8810	0.8765	0.8766

Framework versions

Transformers 4.57.1
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1

akuazzam/swin-tiny-bmr-tuned

swin-tiny-bmr-tuned

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

akuazzam/
swin-tiny-bmr-tuned