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: 0.0367
• Accuracy: 0.9879

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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
0.1993	0.9904	77	0.0961	0.9617
0.1729	1.9936	155	0.1151	0.9486
0.1509	2.9968	233	0.0603	0.9748
0.1081	4.0	311	0.0367	0.9879
0.1195	4.9904	388	0.0936	0.9627
0.0674	5.9936	466	0.0370	0.9849
0.0629	6.9968	544	0.0400	0.9839
0.0718	8.0	622	0.0496	0.9839
0.0335	8.9904	699	0.0533	0.9819
0.0843	9.9035	770	0.0550	0.9809

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1