vit-base-patch16-224-in21k-finetuned-eurosat
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the image_folder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3648
- Accuracy: 0.9017
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.91 | 5 | 0.5982 | 0.7492 |
| 0.645 | 1.91 | 10 | 0.4862 | 0.7593 |
| 0.645 | 2.91 | 15 | 0.4191 | 0.7966 |
| 0.465 | 3.91 | 20 | 0.3803 | 0.8780 |
| 0.465 | 4.91 | 25 | 0.3648 | 0.9017 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.11.0+cpu
- Datasets 2.2.0
- Tokenizers 0.12.1