convnext-base-8e-5
This model is a fine-tuned version of facebook/convnextv2-base-22k-384 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2713
- Accuracy: 0.9421
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: 8e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5312 | 1.0 | 1099 | 0.4722 | 0.8569 |
| 0.4064 | 2.0 | 2198 | 0.3651 | 0.9026 |
| 0.318 | 3.0 | 3297 | 0.3260 | 0.9145 |
| 0.2725 | 4.0 | 4396 | 0.3165 | 0.9197 |
| 0.212 | 5.0 | 5495 | 0.3330 | 0.9256 |
| 0.1711 | 6.0 | 6594 | 0.3273 | 0.9276 |
| 0.1552 | 7.0 | 7693 | 0.2993 | 0.9304 |
| 0.1039 | 8.0 | 8792 | 0.2773 | 0.9419 |
| 0.0996 | 9.0 | 9891 | 0.2786 | 0.9459 |
| 0.0765 | 10.0 | 10990 | 0.2780 | 0.9475 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2