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

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

• Loss: 0.0977
• Accuracy: 0.9678

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: 128
• eval_batch_size: 128
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 512
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3971	0.99	47	0.2025	0.9367
0.2313	1.99	94	0.1240	0.9578
0.1881	2.99	141	0.0977	0.9678

Framework versions

• Transformers 4.18.0
• Pytorch 1.10.0a0+3fd9dcf
• Datasets 2.1.0
• Tokenizers 0.12.1