swin-tiny-patch4-window7-224-uploads-classifier

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: 0.0740
• Accuracy: 0.9669

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.57	0.99	17	1.0733	0.7355
0.5726	1.97	34	0.4882	0.8347
0.213	2.96	51	0.1166	0.9628
0.1528	4.0	69	0.1640	0.9339
0.1243	4.99	86	0.1529	0.9380
0.0985	5.97	103	0.1888	0.9215
0.0838	6.96	120	0.1224	0.9421
0.0667	8.0	138	0.1046	0.9421
0.0455	8.99	155	0.0740	0.9669
0.0469	9.97	172	0.0781	0.9669
0.0472	10.96	189	0.1143	0.9628
0.0378	12.0	207	0.1974	0.9545
0.0386	12.99	224	0.1051	0.9587
0.035	13.97	241	0.0719	0.9545
0.0339	14.96	258	0.1225	0.9504
0.0292	16.0	276	0.0962	0.9587
0.0278	16.99	293	0.1322	0.9463
0.0233	17.97	310	0.1064	0.9545
0.028	18.96	327	0.1207	0.9504
0.0269	19.71	340	0.1161	0.9504

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3