jaffe_V2_50
This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.7217
- Accuracy: 0.8
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 1 | 1.9638 | 0.2333 |
| No log | 2.0 | 2 | 1.7893 | 0.3333 |
| No log | 3.0 | 3 | 1.8759 | 0.1667 |
| No log | 4.0 | 4 | 1.6759 | 0.3667 |
| No log | 5.0 | 5 | 1.5139 | 0.5 |
| No log | 6.0 | 6 | 1.4280 | 0.5667 |
| No log | 7.0 | 7 | 1.3688 | 0.5667 |
| No log | 8.0 | 8 | 1.2819 | 0.6 |
| No log | 9.0 | 9 | 1.1884 | 0.6 |
| 1.5329 | 10.0 | 10 | 1.1448 | 0.6 |
| 1.5329 | 11.0 | 11 | 1.0732 | 0.7 |
| 1.5329 | 12.0 | 12 | 0.9793 | 0.7333 |
| 1.5329 | 13.0 | 13 | 0.8830 | 0.7333 |
| 1.5329 | 14.0 | 14 | 0.8366 | 0.7667 |
| 1.5329 | 15.0 | 15 | 0.8027 | 0.7333 |
| 1.5329 | 16.0 | 16 | 0.7952 | 0.7333 |
| 1.5329 | 17.0 | 17 | 0.7746 | 0.7333 |
| 1.5329 | 18.0 | 18 | 0.7571 | 0.7667 |
| 1.5329 | 19.0 | 19 | 0.7256 | 0.7667 |
| 0.5232 | 20.0 | 20 | 0.7217 | 0.8 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0