metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: swin-tiny-patch4-window7-224-finetunedo
results: []
swin-tiny-patch4-window7-224-finetunedo
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6095
- Roc Auc: 0.6579
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: 4e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Roc Auc |
|---|---|---|---|---|
| No log | 1.0 | 3 | 0.8088 | 0.5 |
| No log | 2.0 | 6 | 0.7896 | 0.5 |
| No log | 3.0 | 9 | 0.6320 | 0.6316 |
| 0.5949 | 4.0 | 12 | 0.5968 | 0.6579 |
| 0.5949 | 5.0 | 15 | 0.6095 | 0.6579 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1