resnet-50-finetuned-eurosat
This model is a fine-tuned version of microsoft/resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9696
- Accuracy: 0.757
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 5.0195 | 1.0 | 704 | 4.8949 | 0.1813 |
| 3.2267 | 2.0 | 1408 | 2.2076 | 0.5449 |
| 2.5469 | 3.0 | 2112 | 1.5307 | 0.6525 |
| 2.3148 | 4.0 | 2816 | 1.2637 | 0.7025 |
| 2.0595 | 5.0 | 3520 | 1.1327 | 0.7218 |
| 2.0319 | 6.0 | 4224 | 1.0622 | 0.7373 |
| 2.0039 | 7.0 | 4928 | 1.0171 | 0.7454 |
| 2.0365 | 8.0 | 5632 | 0.9957 | 0.7527 |
| 1.9755 | 9.0 | 6336 | 0.9780 | 0.7539 |
| 1.8816 | 9.9868 | 7030 | 0.9696 | 0.757 |
Framework versions
- Transformers 4.51.1
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1