swin-tiny-patch4-window7-224-finetuned-eurosat

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: 0.6177
• Accuracy: 0.8182

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: 1e-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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	0.7459	0.3636
No log	2.0	2	0.7104	0.5455
No log	3.0	3	0.6824	0.4545
No log	4.0	4	0.6597	0.4545
No log	5.0	5	0.6421	0.5455
No log	6.0	6	0.6285	0.7273
No log	7.0	7	0.6177	0.8182
No log	8.0	8	0.6101	0.8182
No log	9.0	9	0.6053	0.8182
0.5108	10.0	10	0.6029	0.8182

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2