vit-base-patch16-224-finetuned-eurosat
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagenet-1k dataset. It achieves the following results on the evaluation set:
- Loss: 0.6981
- Accuracy: 0.817
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: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.8014 | 1.0 | 10009 | 0.7430 | 0.8052 |
0.6591 | 2.0 | 20018 | 0.7097 | 0.8132 |
0.562 | 3.0 | 30027 | 0.6981 | 0.817 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.1
- Tokenizers 0.15.2
- Downloads last month
- 0
Finetuned from
Dataset used to train chinhang0104/vit-base-patch16-224-finetuned-eurosat
Evaluation results
- Accuracy on imagenet-1kvalidation set self-reported0.817