|
|
--- |
|
|
library_name: transformers |
|
|
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 |
|
|
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. --> |
|
|
|
|
|
# swin-tiny-patch4-window7-224-finetuned |
|
|
|
|
|
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.9034 |
|
|
- Accuracy: 0.6660 |
|
|
- Precision: 0.6546 |
|
|
- Recall: 0.6660 |
|
|
- F1: 0.6519 |
|
|
|
|
|
## 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: 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: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
|
| 1.0809 | 0.9846 | 32 | 1.0485 | 0.5833 | 0.5506 | 0.5833 | 0.5627 | |
|
|
| 1.0052 | 2.0 | 65 | 1.0600 | 0.5727 | 0.5941 | 0.5727 | 0.5170 | |
|
|
| 0.9429 | 2.9846 | 97 | 0.9755 | 0.6160 | 0.5878 | 0.6160 | 0.5837 | |
|
|
| 0.9497 | 4.0 | 130 | 0.9318 | 0.6497 | 0.6458 | 0.6497 | 0.6313 | |
|
|
| 0.8807 | 4.9846 | 162 | 0.9541 | 0.6304 | 0.6321 | 0.6304 | 0.6200 | |
|
|
| 0.8089 | 6.0 | 195 | 0.9556 | 0.6266 | 0.6270 | 0.6266 | 0.6150 | |
|
|
| 0.801 | 6.9846 | 227 | 0.9050 | 0.6603 | 0.6512 | 0.6603 | 0.6472 | |
|
|
| 0.7753 | 8.0 | 260 | 0.9134 | 0.6506 | 0.6440 | 0.6506 | 0.6440 | |
|
|
| 0.6986 | 8.9846 | 292 | 0.9138 | 0.6554 | 0.6468 | 0.6554 | 0.6436 | |
|
|
| 0.7107 | 9.8462 | 320 | 0.9034 | 0.6660 | 0.6546 | 0.6660 | 0.6519 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.44.2 |
|
|
- Pytorch 2.4.0+cu121 |
|
|
- Datasets 3.0.0 |
|
|
- Tokenizers 0.19.1 |
|
|
|
