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:

• eval_loss: 0.3951
• eval_accuracy: 0.7997
• eval_f1: 0.5226
• eval_precision: 0.8929
• eval_recall: 0.3695
• eval_runtime: 49.6847
• eval_samples_per_second: 13.767
• eval_steps_per_second: 0.221
• epoch: 0.7674
• step: 33

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: 64
• eval_batch_size: 64
• seed: 42
• 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

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.0+cu121
• Datasets 3.0.2
• Tokenizers 0.20.1