vit-large-patch16-224-dungeon-geo-morphs-0-4-28Nov24-003
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: 0.1086
- Accuracy: 0.9875
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: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4912 | 4.0 | 10 | 1.1069 | 0.6786 |
| 0.6967 | 8.0 | 20 | 0.5143 | 0.9232 |
| 0.2492 | 12.0 | 30 | 0.2546 | 0.9768 |
| 0.0819 | 16.0 | 40 | 0.1649 | 0.975 |
| 0.0326 | 20.0 | 50 | 0.1086 | 0.9875 |
| 0.0167 | 24.0 | 60 | 0.0943 | 0.9857 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3