<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
convnext-tiny-224-wikiart
This model is a fine-tuned version of facebook/convnext-tiny-224 on the huggan/wikiart dataset. It achieves the following results on the evaluation set:
- Loss: 0.8022
- Accuracy: 0.7140
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: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9779 | 1.0 | 8654 | 0.9191 | 0.6743 |
| 0.9959 | 2.0 | 17308 | 0.8523 | 0.6941 |
| 1.0344 | 3.0 | 25962 | 0.8277 | 0.7023 |
| 0.8853 | 4.0 | 34616 | 0.8126 | 0.7100 |
| 0.9557 | 5.0 | 43270 | 0.8022 | 0.7140 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2
