convnext-base-224-finetuned-eurosat
This model is a fine-tuned version of facebook/convnext-base-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.8160
- Accuracy: 0.5862
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- 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 |
|---|---|---|---|---|
| 1.4118 | 1.0 | 65 | 1.3980 | 0.4483 |
| 0.703 | 2.0 | 130 | 0.9538 | 0.5862 |
| 0.6892 | 3.0 | 195 | 0.8160 | 0.5862 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.12.1
- Datasets 2.12.0
- Tokenizers 0.13.3