swin-tiny-patch4-window7-224-finetuned-ginger

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: 0.6161
• Accuracy: 0.7112

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Use OptimizerNames.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: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2795	0.9973	275	0.8344	0.7773
0.1696	1.9982	551	1.2580	0.6245
0.1425	2.9991	827	1.0643	0.5959
0.1329	4.0	1103	0.8342	0.6281
0.1237	4.9973	1378	1.4786	0.6110
0.0743	5.9982	1654	1.1068	0.6283
0.1083	6.9991	1930	0.8262	0.8321
0.0667	8.0	2206	0.6214	0.7564
0.0743	8.9973	2481	0.7777	0.7342
0.0527	9.9982	2757	0.6794	0.6985
0.076	10.9991	3033	0.7436	0.6429
0.0423	11.9674	3300	0.6161	0.7112

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3