convnext-tiny-224_album_vit
This model is a fine-tuned version of facebook/convnext-tiny-224 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3898
- Accuracy: 0.4912
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.6659 | 1.0 | 944 | 3.5335 | 0.2607 |
| 2.8174 | 2.0 | 1888 | 2.6391 | 0.4418 |
| 2.4959 | 3.0 | 2832 | 2.3898 | 0.4912 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2