Edit model card

vit-base-patch16-224-finetuned-eurosat

This model is a fine-tuned version of google/vit-base-patch16-224 on the image_folder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3209
  • Accuracy: 0.9072

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: 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
0.5417 0.99 76 0.5556 0.8263
0.4853 1.99 152 0.5319 0.8199
0.4926 2.99 228 0.5133 0.8539
0.4131 3.99 304 0.4481 0.8603
0.4081 4.99 380 0.4280 0.8824
0.3287 5.99 456 0.4330 0.8667
0.3381 6.99 532 0.3549 0.8888
0.3182 7.99 608 0.3382 0.8961
0.3046 8.99 684 0.3790 0.8925
0.3093 9.99 760 0.3209 0.9072

Framework versions

  • Transformers 4.18.0
  • Pytorch 1.11.0+cu113
  • Datasets 2.1.0
  • Tokenizers 0.12.1
Downloads last month
13
Hosted inference API
Drag image file here or click to browse from your device
This model can be loaded on the Inference API on-demand.

Evaluation results