swin-tiny-patch4-window7-224-finetuned-aiornot-baseline
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2231
- Accuracy: 0.9119
- F1: 0.9086
- Log Loss: 3.0422
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Log Loss |
|---|---|---|---|---|---|---|
| 0.2538 | 0.98 | 32 | 0.2327 | 0.9055 | 0.9018 | 3.2647 |
| 0.1735 | 1.98 | 64 | 0.2029 | 0.9151 | 0.9122 | 2.9309 |
| 0.1562 | 2.98 | 96 | 0.2231 | 0.9119 | 0.9086 | 3.0422 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1