vit-large-patch16-224-in21k-dungeon-geo-morphs-0-4-30Nov24-002
This model is a fine-tuned version of google/vit-large-patch16-224-in21k on the dungeon-geo-morphs dataset. It achieves the following results on the evaluation set:
- Loss: 0.2581
- Accuracy: 0.9661
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: 40
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.517 | 3.9091 | 10 | 1.3386 | 0.6768 |
| 0.8959 | 7.9091 | 20 | 0.8879 | 0.9089 |
| 0.4053 | 11.9091 | 30 | 0.5939 | 0.9375 |
| 0.173 | 15.9091 | 40 | 0.4381 | 0.95 |
| 0.0766 | 19.9091 | 50 | 0.3394 | 0.9589 |
| 0.0395 | 23.9091 | 60 | 0.2854 | 0.9643 |
| 0.0243 | 27.9091 | 70 | 0.2581 | 0.9661 |
| 0.0186 | 31.9091 | 80 | 0.2486 | 0.9661 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3