metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-lcbsi-wbc
results: []
swin-tiny-patch4-window7-224-lcbsi-wbc
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0307
- Accuracy: 0.9933
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3668 | 0.98 | 27 | 0.6977 | 0.76 |
| 0.217 | 1.98 | 54 | 0.0992 | 0.972 |
| 0.102 | 2.98 | 81 | 0.0573 | 0.9853 |
| 0.0762 | 3.98 | 108 | 0.1003 | 0.976 |
| 0.0456 | 4.98 | 135 | 0.0307 | 0.9933 |
| 0.0219 | 5.98 | 162 | 0.0497 | 0.9907 |
| 0.0106 | 6.98 | 189 | 0.0568 | 0.9867 |
| 0.0112 | 7.98 | 216 | 0.0532 | 0.9907 |
| 0.0067 | 8.98 | 243 | 0.0528 | 0.9907 |
| 0.008 | 9.98 | 270 | 0.0482 | 0.992 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2