hotel_images_classifier_jd_v4_convnext
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1917
- Accuracy: 0.9366
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3471 | 1.0 | 1147 | 0.2357 | 0.9215 |
| 0.2737 | 2.0 | 2295 | 0.2133 | 0.9280 |
| 0.2743 | 3.0 | 3443 | 0.1934 | 0.9355 |
| 0.276 | 4.0 | 4591 | 0.1982 | 0.9329 |
| 0.2324 | 5.0 | 5735 | 0.1917 | 0.9366 |
Framework versions
- Transformers 4.35.0
- Pytorch 1.12.1+cu113
- Datasets 2.17.1
- Tokenizers 0.14.1