vit-large-patch16-224-dungeon-geo-morphs-0-4-29Nov24-001
This model is a fine-tuned version of google/vit-large-patch16-224 on the dungeon-geo-morphs dataset. It achieves the following results on the evaluation set:
- Loss: 0.1522
- Accuracy: 0.9946
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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: 35
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6512 | 4.0 | 10 | 1.3078 | 0.4643 |
| 1.0709 | 8.0 | 20 | 0.7778 | 0.8429 |
| 0.6487 | 12.0 | 30 | 0.4804 | 0.9089 |
| 0.4013 | 16.0 | 40 | 0.3228 | 0.9554 |
| 0.264 | 20.0 | 50 | 0.2140 | 0.9839 |
| 0.1821 | 24.0 | 60 | 0.1688 | 0.9857 |
| 0.1711 | 28.0 | 70 | 0.1522 | 0.9946 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3