<!-- 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. -->
VANBase-finetuned-brs-finetuned-brs
This model is a fine-tuned version of Visual-Attention-Network/van-base on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.7056
- Accuracy: 0.5882
- F1: 0.6957
- Precision (ppv): 0.6154
- Recall (sensitivity): 0.8
- Specificity: 0.2857
- Npv: 0.5
- Auc: 0.5429
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision (ppv) | Recall (sensitivity) | Specificity | Npv | Auc |
|---|---|---|---|---|---|---|---|---|---|---|
| 0.6589 | 6.25 | 100 | 0.6655 | 0.5882 | 0.6316 | 0.6667 | 0.6 | 0.5714 | 0.5 | 0.5857 |
| 0.6262 | 12.49 | 200 | 0.6917 | 0.5294 | 0.6364 | 0.5833 | 0.7 | 0.2857 | 0.4 | 0.4929 |
| 0.4706 | 18.74 | 300 | 0.6776 | 0.5882 | 0.6957 | 0.6154 | 0.8 | 0.2857 | 0.5 | 0.5429 |
| 0.5202 | 24.98 | 400 | 0.7018 | 0.5294 | 0.6 | 0.6 | 0.6 | 0.4286 | 0.4286 | 0.5143 |
| 0.4628 | 31.25 | 500 | 0.6903 | 0.6471 | 0.75 | 0.6429 | 0.9 | 0.2857 | 0.6667 | 0.5929 |
| 0.3525 | 37.49 | 600 | 0.7241 | 0.5294 | 0.6667 | 0.5714 | 0.8 | 0.1429 | 0.3333 | 0.4714 |
| 0.2877 | 43.74 | 700 | 0.8262 | 0.5882 | 0.7407 | 0.5882 | 1.0 | 0.0 | nan | 0.5 |
| 0.2921 | 49.98 | 800 | 0.8058 | 0.4706 | 0.64 | 0.5333 | 0.8 | 0.0 | 0.0 | 0.4 |
| 0.3834 | 56.25 | 900 | 0.7864 | 0.5882 | 0.7407 | 0.5882 | 1.0 | 0.0 | nan | 0.5 |
| 0.2267 | 62.49 | 1000 | 0.5520 | 0.7647 | 0.8182 | 0.75 | 0.9 | 0.5714 | 0.8 | 0.7357 |
| 0.3798 | 68.74 | 1100 | 0.8722 | 0.4706 | 0.64 | 0.5333 | 0.8 | 0.0 | 0.0 | 0.4 |
| 0.2633 | 74.98 | 1200 | 0.7260 | 0.6471 | 0.7273 | 0.6667 | 0.8 | 0.4286 | 0.6 | 0.6143 |
| 0.3439 | 81.25 | 1300 | 1.0187 | 0.4118 | 0.5455 | 0.5 | 0.6 | 0.1429 | 0.2 | 0.3714 |
| 0.2532 | 87.49 | 1400 | 0.8812 | 0.5882 | 0.7407 | 0.5882 | 1.0 | 0.0 | nan | 0.5 |
| 0.0841 | 93.74 | 1500 | 0.8717 | 0.5294 | 0.6923 | 0.5625 | 0.9 | 0.0 | 0.0 | 0.45 |
| 0.3409 | 99.98 | 1600 | 0.7056 | 0.5882 | 0.6957 | 0.6154 | 0.8 | 0.2857 | 0.5 | 0.5429 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1
