land-type-classification-pro_2

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

• Loss: 0.5273
• Accuracy: 0.9889

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: 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: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7867	1.0	405	0.6712	0.9383
0.698	2.0	810	0.5838	0.9735
0.669	3.0	1215	0.5638	0.9735
0.6739	4.0	1620	0.5576	0.9793
0.6016	5.0	2025	0.5527	0.9793
0.6183	6.0	2430	0.5412	0.9833
0.6063	7.0	2835	0.5556	0.9759
0.5916	8.0	3240	0.5392	0.9846
0.6016	9.0	3645	0.5429	0.9858
0.5973	10.0	4050	0.5330	0.9880
0.6503	11.0	4455	0.5325	0.9880
0.5924	12.0	4860	0.5407	0.9849
0.6405	13.0	5265	0.5342	0.9870
0.5706	14.0	5670	0.5311	0.9873
0.5609	15.0	6075	0.5273	0.9889

Framework versions

• Transformers 4.57.1
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1