vit-base-patch16-224-in21k-CDCC
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9010
- Accuracy: 0.6006
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: 3e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 48
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0151 | 1.0 | 586 | 1.0188 | 0.4931 |
| 0.9755 | 2.0 | 1172 | 0.9591 | 0.5558 |
| 0.8769 | 3.0 | 1758 | 0.9301 | 0.5974 |
| 0.8852 | 4.0 | 2345 | 0.9086 | 0.6025 |
| 0.8751 | 5.0 | 2930 | 0.9010 | 0.6006 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1