metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-finetuned_ASL_Isolated_Swin_dataset2
results: []
swin-tiny-patch4-window7-224-finetuned_ASL_Isolated_Swin_dataset2
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the ASL_Isolated_Swin_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.0640
- Accuracy: 0.9846
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.39 | 1.09 | 100 | 1.1827 | 0.6346 |
| 0.8972 | 2.17 | 200 | 0.6287 | 0.7808 |
| 0.4884 | 3.26 | 300 | 0.2927 | 0.8962 |
| 0.4179 | 4.35 | 400 | 0.1795 | 0.9423 |
| 0.4169 | 5.43 | 500 | 0.1564 | 0.95 |
| 0.3427 | 6.52 | 600 | 0.1426 | 0.95 |
| 0.2939 | 7.61 | 700 | 0.1174 | 0.9731 |
| 0.1605 | 8.7 | 800 | 0.0640 | 0.9846 |
| 0.1865 | 9.78 | 900 | 0.0702 | 0.9808 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1