convnext-tiny-224-finetuned-og-dataset-10e
This model is a fine-tuned version of facebook/convnext-tiny-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0571
- Accuracy: 0.9786
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3243 | 1.0 | 2205 | 0.2717 | 0.8910 |
| 0.2524 | 2.0 | 4410 | 0.1613 | 0.9392 |
| 0.2044 | 3.0 | 6615 | 0.1044 | 0.9618 |
| 0.1396 | 4.0 | 8820 | 0.1097 | 0.9577 |
| 0.1177 | 5.0 | 11025 | 0.0650 | 0.9758 |
| 0.143 | 6.0 | 13230 | 0.0571 | 0.9786 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2