swin-tiny-finetuned-dogfood
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the lewtun/dog_food dataset. It achieves the following results on the evaluation set:
- Loss: 0.1959
- Accuracy: 0.988
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: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8198 | 1.0 | 16 | 0.1901 | 0.9822 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1
- Downloads last month
- 13
Dataset used to train sasha/swin-tiny-finetuned-dogfood
Evaluation results
- Accuracy on lewtun/dog_foodself-reported0.988
- Accuracy on lewtun/dog_foodtest set self-reported0.983
- Precision Macro on lewtun/dog_foodtest set self-reported0.982
- Precision Micro on lewtun/dog_foodtest set self-reported0.983
- Precision Weighted on lewtun/dog_foodtest set self-reported0.983
- Recall Macro on lewtun/dog_foodtest set self-reported0.983
- Recall Micro on lewtun/dog_foodtest set self-reported0.983
- Recall Weighted on lewtun/dog_foodtest set self-reported0.983