|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- imagefolder |
|
|
metrics: |
|
|
- accuracy |
|
|
- f1 |
|
|
model-index: |
|
|
- name: dit-base-finetuned-brs |
|
|
results: |
|
|
- task: |
|
|
name: Image Classification |
|
|
type: image-classification |
|
|
dataset: |
|
|
name: imagefolder |
|
|
type: imagefolder |
|
|
config: default |
|
|
split: train |
|
|
args: default |
|
|
metrics: |
|
|
- name: Accuracy |
|
|
type: accuracy |
|
|
value: 0.8823529411764706 |
|
|
- name: F1 |
|
|
type: f1 |
|
|
value: 0.8571428571428571 |
|
|
--- |
|
|
|
|
|
<!-- 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. --> |
|
|
|
|
|
# dit-base-finetuned-brs |
|
|
|
|
|
This model is a fine-tuned version of [microsoft/dit-base](https://huggingface.co/microsoft/dit-base) on the imagefolder dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.8748 |
|
|
- Accuracy: 0.8824 |
|
|
- F1: 0.8571 |
|
|
- Precision (ppv): 0.8571 |
|
|
- Recall (sensitivity): 0.8571 |
|
|
- Specificity: 0.9 |
|
|
- Npv: 0.9 |
|
|
- Auc: 0.8786 |
|
|
|
|
|
## 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: 1e-05 |
|
|
- train_batch_size: 1 |
|
|
- eval_batch_size: 1 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 4 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 100 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision (ppv) | Recall (sensitivity) | Specificity | Npv | Auc | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------------:|:--------------------:|:-----------:|:------:|:------:| |
|
|
| 0.6624 | 6.25 | 100 | 0.5548 | 0.8235 | 0.7692 | 0.8333 | 0.7143 | 0.9 | 0.8182 | 0.8071 | |
|
|
| 0.5201 | 12.49 | 200 | 0.4617 | 0.8824 | 0.8571 | 0.8571 | 0.8571 | 0.9 | 0.9 | 0.8786 | |
|
|
| 0.5172 | 18.74 | 300 | 0.4249 | 0.8235 | 0.8000 | 0.75 | 0.8571 | 0.8 | 0.8889 | 0.8286 | |
|
|
| 0.4605 | 24.98 | 400 | 0.3172 | 0.8235 | 0.7692 | 0.8333 | 0.7143 | 0.9 | 0.8182 | 0.8071 | |
|
|
| 0.4894 | 31.25 | 500 | 0.4466 | 0.8235 | 0.7692 | 0.8333 | 0.7143 | 0.9 | 0.8182 | 0.8071 | |
|
|
| 0.3694 | 37.49 | 600 | 0.5077 | 0.8235 | 0.7692 | 0.8333 | 0.7143 | 0.9 | 0.8182 | 0.8071 | |
|
|
| 0.6172 | 43.74 | 700 | 0.5722 | 0.7647 | 0.7143 | 0.7143 | 0.7143 | 0.8 | 0.8 | 0.7571 | |
|
|
| 0.3671 | 49.98 | 800 | 0.7006 | 0.7647 | 0.6667 | 0.8 | 0.5714 | 0.9 | 0.75 | 0.7357 | |
|
|
| 0.4109 | 56.25 | 900 | 0.4410 | 0.8235 | 0.7692 | 0.8333 | 0.7143 | 0.9 | 0.8182 | 0.8071 | |
|
|
| 0.3198 | 62.49 | 1000 | 0.7226 | 0.8235 | 0.7692 | 0.8333 | 0.7143 | 0.9 | 0.8182 | 0.8071 | |
|
|
| 0.4283 | 68.74 | 1100 | 0.8089 | 0.8235 | 0.7692 | 0.8333 | 0.7143 | 0.9 | 0.8182 | 0.8071 | |
|
|
| 0.3273 | 74.98 | 1200 | 0.9059 | 0.7647 | 0.6667 | 0.8 | 0.5714 | 0.9 | 0.75 | 0.7357 | |
|
|
| 0.3237 | 81.25 | 1300 | 0.8520 | 0.8235 | 0.7692 | 0.8333 | 0.7143 | 0.9 | 0.8182 | 0.8071 | |
|
|
| 0.2014 | 87.49 | 1400 | 0.9183 | 0.7647 | 0.6667 | 0.8 | 0.5714 | 0.9 | 0.75 | 0.7357 | |
|
|
| 0.3204 | 93.74 | 1500 | 0.6769 | 0.8824 | 0.8571 | 0.8571 | 0.8571 | 0.9 | 0.9 | 0.8786 | |
|
|
| 0.1786 | 99.98 | 1600 | 0.8748 | 0.8824 | 0.8571 | 0.8571 | 0.8571 | 0.9 | 0.9 | 0.8786 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.23.1 |
|
|
- Pytorch 1.12.1+cu113 |
|
|
- Datasets 2.6.1 |
|
|
- Tokenizers 0.13.1 |
|
|
|
