Train-Test-Augmentation-NO-UPNormal-swinv2-base
This model is a fine-tuned version of microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5452
- Accuracy: 0.9030
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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 |
---|---|---|---|---|
0.4905 | 1.0 | 86 | 0.5127 | 0.8252 |
0.2148 | 2.0 | 172 | 0.5452 | 0.8445 |
0.1355 | 3.0 | 258 | 0.5205 | 0.8608 |
0.0472 | 4.0 | 344 | 0.4481 | 0.8921 |
0.0229 | 5.0 | 430 | 0.5671 | 0.8782 |
0.0505 | 6.0 | 516 | 0.6136 | 0.8837 |
0.0254 | 7.0 | 602 | 0.6037 | 0.8891 |
0.0009 | 8.0 | 688 | 0.6371 | 0.8819 |
0.0034 | 9.0 | 774 | 0.5569 | 0.8981 |
0.0019 | 10.0 | 860 | 0.5452 | 0.9030 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.15.2
- Downloads last month
- 9
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.