swinv2-base
This model is a fine-tuned version of microsoft/swinv2-base-patch4-window12-192-22k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1570
- Accuracy: 0.9577
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 |
|---|---|---|---|---|
| 1.1001 | 1.0 | 240 | 1.0510 | 0.5701 |
| 0.7709 | 2.0 | 480 | 0.7516 | 0.7091 |
| 0.5077 | 3.0 | 720 | 0.5670 | 0.7953 |
| 0.2908 | 4.0 | 960 | 0.3946 | 0.8650 |
| 0.1676 | 5.0 | 1200 | 0.2796 | 0.9038 |
| 0.117 | 6.0 | 1440 | 0.2322 | 0.9275 |
| 0.0634 | 7.0 | 1680 | 0.2433 | 0.9306 |
| 0.0425 | 8.0 | 1920 | 0.1843 | 0.9490 |
| 0.0252 | 9.0 | 2160 | 0.1653 | 0.9543 |
| 0.0147 | 10.0 | 2400 | 0.1570 | 0.9577 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Tokenizers 0.19.1
- Downloads last month
- 45
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.