Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
organa-swin-large-finetuned
This model is a fine-tuned version of microsoft/swin-large-patch4-window7-224-in22k on the medmnist_v2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2172
- Accuracy: 0.9353
- Precision: 0.9395
- Recall: 0.9294
- F1: 0.9336
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: 0.005
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
0.5593 | 1.0 | 324 | 0.1527 | 0.9430 | 0.9543 | 0.9418 | 0.9458 |
0.5689 | 2.0 | 648 | 0.1009 | 0.9646 | 0.9691 | 0.9700 | 0.9682 |
0.6306 | 3.0 | 972 | 0.0859 | 0.9692 | 0.9779 | 0.9751 | 0.9754 |
0.5282 | 4.0 | 1297 | 0.0719 | 0.9738 | 0.9779 | 0.9759 | 0.9759 |
0.5392 | 5.0 | 1621 | 0.1056 | 0.9569 | 0.9719 | 0.9640 | 0.9656 |
0.4461 | 6.0 | 1945 | 0.0446 | 0.9892 | 0.9884 | 0.9911 | 0.9896 |
0.461 | 7.0 | 2269 | 0.0582 | 0.9800 | 0.9849 | 0.9825 | 0.9831 |
0.4002 | 8.0 | 2594 | 0.0561 | 0.9846 | 0.9869 | 0.9866 | 0.9863 |
0.3409 | 9.0 | 2918 | 0.0405 | 0.9815 | 0.9873 | 0.9860 | 0.9862 |
0.2874 | 9.99 | 3240 | 0.0561 | 0.9769 | 0.9865 | 0.9833 | 0.9842 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2
- Downloads last month
- 400
Unable to determine this model’s pipeline type. Check the
docs
.