metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: swin-tiny-patch4-window7-224-finetuned-RCC
results: []
swin-tiny-patch4-window7-224-finetuned-RCC
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3565
- Accuracy: 0.9032
- Precision: 0.9032
- Recall: 1.0
- F1: 0.4746
- Auc: 0.5
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Auc |
|---|---|---|---|---|---|---|---|---|
| No log | 0.8571 | 3 | 0.3383 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
| No log | 2.0 | 7 | 0.3654 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
| 0.3833 | 2.8571 | 10 | 0.3422 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
| 0.3833 | 4.0 | 14 | 0.3556 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
| 0.3833 | 4.8571 | 17 | 0.3425 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
| 0.2492 | 6.0 | 21 | 0.3401 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
| 0.2492 | 6.8571 | 24 | 0.3543 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
| 0.2492 | 8.0 | 28 | 0.3572 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
| 0.2304 | 8.5714 | 30 | 0.3565 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.0.0+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1