SWIN_finetuned_frozen_v3_cont
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: 1.9857
- Accuracy: 0.6785
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: 0.0004
- train_batch_size: 512
- eval_batch_size: 512
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15.0
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| 1.6863 | 1.0 | 1313 | 0.5757 | 1.9559 |
| 1.3275 | 2.0 | 2626 | 0.6061 | 1.8276 |
| 1.151 | 3.0 | 3939 | 0.6130 | 1.8857 |
| 1.0336 | 4.0 | 5252 | 0.6322 | 1.8160 |
| 0.947 | 5.0 | 6565 | 0.6317 | 1.8051 |
| 0.8595 | 6.0 | 7878 | 0.6443 | 1.7996 |
| 0.801 | 7.0 | 9191 | 0.6534 | 1.7987 |
| 0.7508 | 8.0 | 10504 | 0.6522 | 1.7864 |
| 0.694 | 9.0 | 11817 | 0.6526 | 1.8871 |
| 0.6523 | 10.0 | 13130 | 0.6648 | 1.8057 |
| 0.5976 | 11.0 | 14443 | 0.6707 | 1.8514 |
| 0.5743 | 12.0 | 15756 | 0.6629 | 1.9271 |
| 0.5426 | 13.0 | 17069 | 0.6692 | 1.9221 |
| 0.5092 | 14.0 | 18382 | 0.6752 | 1.9164 |
| 0.4808 | 15.0 | 19695 | 0.6743 | 1.9259 |
| 0.4611 | 16.0 | 21008 | 0.6785 | 1.9857 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.13.3
- Downloads last month
- 3