resnet-50-finetuned-eurosat
This model is a fine-tuned version of microsoft/resnet-50 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6309
- Accuracy: 0.5625
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 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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 3 | 0.6749 | 0.5625 |
| No log | 2.0 | 6 | 0.6746 | 0.5625 |
| No log | 3.0 | 9 | 0.6696 | 0.5625 |
| 2.1049 | 4.0 | 12 | 0.6614 | 0.5312 |
| 2.1049 | 5.0 | 15 | 0.6552 | 0.5625 |
| 2.1049 | 6.0 | 18 | 0.6494 | 0.5625 |
| 2.0436 | 7.0 | 21 | 0.6427 | 0.5625 |
| 2.0436 | 8.0 | 24 | 0.6399 | 0.5625 |
| 2.0436 | 9.0 | 27 | 0.6325 | 0.5625 |
| 1.7828 | 10.0 | 30 | 0.6314 | 0.5625 |
| 1.7828 | 11.0 | 33 | 0.6309 | 0.5625 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0