|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
base_model: microsoft/swin-large-patch4-window7-224-in22k |
|
model-index: |
|
- name: chest-swin-large-finetuned |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# chest-swin-large-finetuned |
|
|
|
This model is a fine-tuned version of [microsoft/swin-large-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-large-patch4-window7-224-in22k) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1159 |
|
- Accuracy: 0.9588 |
|
- Precision: 0.9599 |
|
- Recall: 0.9401 |
|
- F1: 0.9492 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| 0.3305 | 0.99 | 63 | 0.1600 | 0.9365 | 0.9478 | 0.8868 | 0.9119 | |
|
| 0.2335 | 1.99 | 127 | 0.1552 | 0.9313 | 0.8968 | 0.9472 | 0.9166 | |
|
| 0.1977 | 3.0 | 191 | 0.0855 | 0.9734 | 0.9608 | 0.9714 | 0.9659 | |
|
| 0.1746 | 4.0 | 255 | 0.0870 | 0.9794 | 0.9794 | 0.9669 | 0.9729 | |
|
| 0.1797 | 4.99 | 318 | 0.0829 | 0.9700 | 0.9549 | 0.9690 | 0.9617 | |
|
| 0.1436 | 5.99 | 382 | 0.0797 | 0.9708 | 0.9556 | 0.9707 | 0.9628 | |
|
| 0.1632 | 7.0 | 446 | 0.0816 | 0.9700 | 0.9508 | 0.9754 | 0.9621 | |
|
| 0.1125 | 8.0 | 510 | 0.1007 | 0.9614 | 0.9365 | 0.9717 | 0.9519 | |
|
| 0.1076 | 8.99 | 573 | 0.0900 | 0.9691 | 0.9482 | 0.9770 | 0.9612 | |
|
| 0.1188 | 9.88 | 630 | 0.1064 | 0.9622 | 0.9377 | 0.9723 | 0.9530 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.9.0 |
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |