vit-base-patch16-224-MSC-dmae
This model is a fine-tuned version of google/vit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6300
- Accuracy: 0.95
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.67 | 1 | 1.2258 | 0.5 |
| No log | 2.0 | 3 | 1.0536 | 0.7 |
| No log | 2.67 | 4 | 0.9143 | 0.75 |
| No log | 4.0 | 6 | 0.6899 | 0.9 |
| No log | 4.67 | 7 | 0.6300 | 0.95 |
| No log | 6.0 | 9 | 0.5069 | 0.9 |
| 0.8554 | 6.67 | 10 | 0.4671 | 0.9 |
| 0.8554 | 8.0 | 12 | 0.4312 | 0.9 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3