|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: Visual-Attention-Network/van-tiny |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- imagefolder |
|
|
metrics: |
|
|
- accuracy |
|
|
- recall |
|
|
- precision |
|
|
model-index: |
|
|
- name: teacher-status-van-tiny-256-1-2 |
|
|
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: 0.9716684155299056 |
|
|
- name: Recall |
|
|
type: recall |
|
|
value: 0.9754098360655737 |
|
|
- name: Precision |
|
|
type: precision |
|
|
value: 0.9802306425041186 |
|
|
--- |
|
|
|
|
|
<!-- 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. --> |
|
|
|
|
|
# teacher-status-van-tiny-256-1-2 |
|
|
|
|
|
This model is a fine-tuned version of [Visual-Attention-Network/van-tiny](https://huggingface.co/Visual-Attention-Network/van-tiny) on the imagefolder dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0859 |
|
|
- Accuracy: 0.9717 |
|
|
- F1 Score: 0.9778 |
|
|
- Recall: 0.9754 |
|
|
- Precision: 0.9802 |
|
|
|
|
|
## 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: 128 |
|
|
- eval_batch_size: 128 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 2 |
|
|
- total_train_batch_size: 256 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 30 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Score | Recall | Precision | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:------:|:---------:| |
|
|
| 0.6722 | 0.99 | 33 | 0.6499 | 0.6401 | 0.7806 | 1.0 | 0.6401 | |
|
|
| 0.5431 | 2.0 | 67 | 0.4164 | 0.7817 | 0.8531 | 0.9902 | 0.7494 | |
|
|
| 0.393 | 2.99 | 100 | 0.2833 | 0.8877 | 0.9078 | 0.8639 | 0.9564 | |
|
|
| 0.354 | 4.0 | 134 | 0.1930 | 0.9276 | 0.9436 | 0.9459 | 0.9413 | |
|
|
| 0.3007 | 4.99 | 167 | 0.1585 | 0.9370 | 0.9511 | 0.9557 | 0.9464 | |
|
|
| 0.2898 | 6.0 | 201 | 0.1445 | 0.9465 | 0.9581 | 0.9557 | 0.9605 | |
|
|
| 0.2824 | 6.99 | 234 | 0.1353 | 0.9465 | 0.9580 | 0.9525 | 0.9635 | |
|
|
| 0.2763 | 8.0 | 268 | 0.1359 | 0.9486 | 0.9603 | 0.9721 | 0.9488 | |
|
|
| 0.2473 | 8.99 | 301 | 0.1213 | 0.9570 | 0.9664 | 0.9672 | 0.9656 | |
|
|
| 0.2598 | 10.0 | 335 | 0.1091 | 0.9570 | 0.9665 | 0.9705 | 0.9626 | |
|
|
| 0.2476 | 10.99 | 368 | 0.1041 | 0.9633 | 0.9714 | 0.9754 | 0.9675 | |
|
|
| 0.2376 | 12.0 | 402 | 0.0997 | 0.9601 | 0.9686 | 0.9623 | 0.9751 | |
|
|
| 0.2402 | 12.99 | 435 | 0.0972 | 0.9622 | 0.9704 | 0.9672 | 0.9736 | |
|
|
| 0.2324 | 14.0 | 469 | 0.0950 | 0.9664 | 0.9739 | 0.9803 | 0.9676 | |
|
|
| 0.2256 | 14.99 | 502 | 0.0909 | 0.9706 | 0.9770 | 0.9754 | 0.9786 | |
|
|
| 0.21 | 16.0 | 536 | 0.0922 | 0.9622 | 0.9703 | 0.9656 | 0.9752 | |
|
|
| 0.217 | 16.99 | 569 | 0.0933 | 0.9612 | 0.9695 | 0.9656 | 0.9736 | |
|
|
| 0.2092 | 18.0 | 603 | 0.0891 | 0.9664 | 0.9738 | 0.9754 | 0.9722 | |
|
|
| 0.2063 | 18.99 | 636 | 0.0913 | 0.9654 | 0.9730 | 0.9738 | 0.9722 | |
|
|
| 0.2217 | 20.0 | 670 | 0.0917 | 0.9643 | 0.9720 | 0.9672 | 0.9768 | |
|
|
| 0.1952 | 20.99 | 703 | 0.0859 | 0.9717 | 0.9778 | 0.9754 | 0.9802 | |
|
|
| 0.2068 | 22.0 | 737 | 0.0907 | 0.9685 | 0.9755 | 0.9770 | 0.9739 | |
|
|
| 0.1914 | 22.99 | 770 | 0.0847 | 0.9696 | 0.9763 | 0.9787 | 0.9739 | |
|
|
| 0.1961 | 24.0 | 804 | 0.0870 | 0.9685 | 0.9755 | 0.9770 | 0.9739 | |
|
|
| 0.1911 | 24.99 | 837 | 0.0884 | 0.9664 | 0.9739 | 0.9770 | 0.9707 | |
|
|
| 0.1961 | 26.0 | 871 | 0.0870 | 0.9685 | 0.9754 | 0.9738 | 0.9770 | |
|
|
| 0.1978 | 26.99 | 904 | 0.0871 | 0.9685 | 0.9754 | 0.9754 | 0.9754 | |
|
|
| 0.1854 | 28.0 | 938 | 0.0858 | 0.9685 | 0.9755 | 0.9770 | 0.9739 | |
|
|
| 0.1733 | 28.99 | 971 | 0.0860 | 0.9685 | 0.9754 | 0.9738 | 0.9770 | |
|
|
| 0.1762 | 29.55 | 990 | 0.0858 | 0.9664 | 0.9738 | 0.9738 | 0.9738 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.36.2 |
|
|
- Pytorch 2.1.0+cu121 |
|
|
- Datasets 2.16.1 |
|
|
- Tokenizers 0.15.0 |
|
|
|
