swin-base-patch4-window7-224-finetuned-barkley
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0126
- Precision: 1.0
- Recall: 1.0
- F1: 1.0
- Accuracy: 1.0
- Top1 Accuracy: 1.0
- Error Rate: 0.0
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | Top1 Accuracy | Error Rate |
|---|---|---|---|---|---|---|---|---|---|
| 1.6386 | 0.9474 | 9 | 1.2206 | 0.7199 | 0.6842 | 0.6848 | 0.6800 | 0.6842 | 0.3200 |
| 0.7786 | 2.0 | 19 | 0.3487 | 0.9484 | 0.9474 | 0.9467 | 0.9497 | 0.9474 | 0.0503 |
| 0.1763 | 2.9474 | 28 | 0.0609 | 0.9937 | 0.9934 | 0.9934 | 0.9944 | 0.9934 | 0.0056 |
| 0.0472 | 4.0 | 38 | 0.0318 | 0.9871 | 0.9868 | 0.9868 | 0.9878 | 0.9868 | 0.0122 |
| 0.0316 | 4.9474 | 47 | 0.0126 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 0.0 |
| 0.0171 | 6.0 | 57 | 0.0392 | 0.9875 | 0.9868 | 0.9868 | 0.9867 | 0.9868 | 0.0133 |
| 0.0152 | 6.9474 | 66 | 0.0042 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 0.0 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.0+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1