<!-- 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. -->
vit-huge-augmented-ph2-patch-14
This model is a fine-tuned version of google/vit-huge-patch14-224-in21k on the ahishamm/Augmented_PH2_db_sharpened dataset. It achieves the following results on the evaluation set:
- Loss: 0.5005
- Accuracy: 0.8581
- Recall: 0.8581
- F1: 0.8581
- Precision: 0.8581
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | F1 | Precision |
|---|---|---|---|---|---|---|---|
| 0.0835 | 0.36 | 50 | 0.5005 | 0.8581 | 0.8581 | 0.8581 | 0.8581 |
| 0.0168 | 0.72 | 100 | 0.5818 | 0.8564 | 0.8564 | 0.8564 | 0.8564 |
| 0.0205 | 1.09 | 150 | 0.5220 | 0.8479 | 0.8479 | 0.8479 | 0.8479 |
| 0.0125 | 1.45 | 200 | 0.6188 | 0.8513 | 0.8513 | 0.8513 | 0.8513 |
| 0.0029 | 1.81 | 250 | 0.6046 | 0.8769 | 0.8769 | 0.8769 | 0.8769 |
| 0.0021 | 2.17 | 300 | 0.6408 | 0.8803 | 0.8803 | 0.8803 | 0.8803 |
| 0.0018 | 2.54 | 350 | 0.6588 | 0.8803 | 0.8803 | 0.8803 | 0.8803 |
| 0.0015 | 2.9 | 400 | 0.6720 | 0.8803 | 0.8803 | 0.8803 | 0.8803 |
| 0.0014 | 3.26 | 450 | 0.6803 | 0.8803 | 0.8803 | 0.8803 | 0.8803 |
| 0.0014 | 3.62 | 500 | 0.6861 | 0.8803 | 0.8803 | 0.8803 | 0.8803 |
| 0.0014 | 3.99 | 550 | 0.6879 | 0.8803 | 0.8803 | 0.8803 | 0.8803 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
