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: 0.3032
- Accuracy: 0.8941
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8514 | 1.0 | 100 | 0.7862 | 0.7058 |
| 0.631 | 2.0 | 200 | 0.5492 | 0.7886 |
| 0.5516 | 2.99 | 300 | 0.5195 | 0.8079 |
| 0.4597 | 4.0 | 401 | 0.4840 | 0.8229 |
| 0.4094 | 5.0 | 501 | 0.3946 | 0.8597 |
| 0.3289 | 6.0 | 601 | 0.3787 | 0.8573 |
| 0.3145 | 6.99 | 701 | 0.3536 | 0.8773 |
| 0.2911 | 8.0 | 802 | 0.3249 | 0.8853 |
| 0.2487 | 9.0 | 902 | 0.3094 | 0.8938 |
| 0.2291 | 9.98 | 1000 | 0.3032 | 0.8941 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2