convnextv2-tiny-1k-224-finetuned-pattern-v2
This model is a fine-tuned version of facebook/convnextv2-tiny-1k-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.5496
- Accuracy: 0.8075
- Precision: 0.8151
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: 2e-05
- train_batch_size: 10
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision |
|---|---|---|---|---|---|
| No log | 1.0 | 320 | 0.8829 | 0.7275 | 0.7493 |
| 1.2279 | 2.0 | 640 | 0.7396 | 0.7412 | 0.7517 |
| 1.2279 | 3.0 | 960 | 0.6526 | 0.7775 | 0.7902 |
| 0.6811 | 4.0 | 1280 | 0.5722 | 0.7975 | 0.8076 |
| 0.5073 | 5.0 | 1600 | 0.5496 | 0.8075 | 0.8151 |
| 0.5073 | 6.0 | 1920 | 0.6014 | 0.7887 | 0.7991 |
| 0.4098 | 7.0 | 2240 | 0.5759 | 0.8125 | 0.8171 |
| 0.3357 | 8.0 | 2560 | 0.6241 | 0.7987 | 0.8126 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1