metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-classification
results: []
swin-tiny-patch4-window7-224-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: 0.2780
- Accuracy: 0.9264
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1469 | 1.0 | 100 | 0.3027 | 0.9127 |
| 0.1677 | 2.0 | 200 | 0.3351 | 0.9001 |
| 0.167 | 2.99 | 300 | 0.3875 | 0.8931 |
| 0.1556 | 4.0 | 401 | 0.3814 | 0.8969 |
| 0.1328 | 5.0 | 501 | 0.3281 | 0.9046 |
| 0.1 | 6.0 | 601 | 0.3726 | 0.9004 |
| 0.1188 | 6.99 | 701 | 0.3736 | 0.9046 |
| 0.1257 | 8.0 | 802 | 0.3381 | 0.9102 |
| 0.1017 | 9.0 | 902 | 0.2872 | 0.9215 |
| 0.0987 | 10.0 | 1002 | 0.3067 | 0.9176 |
| 0.0874 | 10.99 | 1102 | 0.2919 | 0.9165 |
| 0.0901 | 12.0 | 1203 | 0.2942 | 0.9229 |
| 0.0831 | 13.0 | 1303 | 0.2974 | 0.9232 |
| 0.0838 | 14.0 | 1403 | 0.2787 | 0.9264 |
| 0.0603 | 14.96 | 1500 | 0.2780 | 0.9264 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2