metadata
library_name: transformers
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: swin-brain-abnormalities-classification
results: []
swin-brain-abnormalities-classification
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2291
- Accuracy: 0.9262
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: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2609 | 1.0 | 6 | 0.9906 | 0.6779 |
| 0.8038 | 2.0 | 12 | 0.6710 | 0.7718 |
| 0.7211 | 3.0 | 18 | 0.5718 | 0.7785 |
| 0.5931 | 4.0 | 24 | 0.4404 | 0.8255 |
| 0.4773 | 5.0 | 30 | 0.3184 | 0.8859 |
| 0.4233 | 6.0 | 36 | 0.2672 | 0.9396 |
| 0.3331 | 7.0 | 42 | 0.2489 | 0.9262 |
| 0.2819 | 8.0 | 48 | 0.2307 | 0.9396 |
| 0.2437 | 9.0 | 54 | 0.2180 | 0.9262 |
| 0.2231 | 10.0 | 60 | 0.2301 | 0.9128 |
| 0.2023 | 11.0 | 66 | 0.1972 | 0.9262 |
| 0.1873 | 12.0 | 72 | 0.2396 | 0.9128 |
| 0.1627 | 13.0 | 78 | 0.1933 | 0.9262 |
| 0.1372 | 14.0 | 84 | 0.2708 | 0.9195 |
| 0.1559 | 15.0 | 90 | 0.2443 | 0.9128 |
| 0.1455 | 16.0 | 96 | 0.2369 | 0.9195 |
| 0.1064 | 17.0 | 102 | 0.2470 | 0.9128 |
| 0.1152 | 18.0 | 108 | 0.2397 | 0.9128 |
| 0.0994 | 19.0 | 114 | 0.2626 | 0.9128 |
| 0.1046 | 20.0 | 120 | 0.2738 | 0.9195 |
| 0.1056 | 21.0 | 126 | 0.2384 | 0.9195 |
| 0.0902 | 22.0 | 132 | 0.2373 | 0.9195 |
| 0.0735 | 23.0 | 138 | 0.2268 | 0.9329 |
| 0.096 | 24.0 | 144 | 0.2240 | 0.9329 |
| 0.1087 | 25.0 | 150 | 0.2291 | 0.9262 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0