Nguyen Tien
vuihocrnd/teacher-status-van-tiny-256
b31ca8b
metadata
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-256-2
    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: 0.9759358288770054
          - name: Recall
            type: recall
            value: 0.9756944444444444
          - name: Precision
            type: precision
            value: 0.9929328621908127

teacher-status-van-tiny-256-2

This model is a fine-tuned version of Visual-Attention-Network/van-tiny on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0916
  • Accuracy: 0.9759
  • F1 Score: 0.9842
  • Recall: 0.9757
  • Precision: 0.9929

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: 30

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Score Recall Precision
0.6896 0.99 26 0.6707 0.7701 0.8701 1.0 0.7701
0.5438 1.98 52 0.4302 0.7701 0.8701 1.0 0.7701
0.3756 2.97 78 0.2762 0.8850 0.9285 0.9688 0.8914
0.3017 4.0 105 0.2002 0.9225 0.9503 0.9618 0.9390
0.257 4.99 131 0.1794 0.9385 0.9605 0.9722 0.9492
0.2345 5.98 157 0.1485 0.9358 0.9582 0.9549 0.9615
0.2318 6.97 183 0.1302 0.9439 0.9631 0.9514 0.9751
0.2173 8.0 210 0.1277 0.9519 0.9689 0.9722 0.9655
0.2058 8.99 236 0.1269 0.9572 0.9722 0.9722 0.9722
0.1955 9.98 262 0.1146 0.9572 0.9724 0.9792 0.9658
0.2083 10.97 288 0.1083 0.9652 0.9772 0.9688 0.9859
0.1886 12.0 315 0.1048 0.9599 0.9741 0.9792 0.9691
0.1618 12.99 341 0.1033 0.9626 0.9757 0.9757 0.9757
0.1908 13.98 367 0.1044 0.9599 0.9739 0.9722 0.9756
0.1594 14.97 393 0.0915 0.9626 0.9758 0.9792 0.9724
0.1474 16.0 420 0.0916 0.9759 0.9842 0.9757 0.9929
0.1734 16.99 446 0.0951 0.9652 0.9773 0.9722 0.9825
0.1484 17.98 472 0.1049 0.9706 0.9809 0.9792 0.9826
0.1495 18.97 498 0.0930 0.9679 0.9791 0.9757 0.9825
0.1385 20.0 525 0.0955 0.9626 0.9759 0.9826 0.9692
0.1492 20.99 551 0.0911 0.9599 0.9741 0.9792 0.9691
0.1401 21.98 577 0.0927 0.9706 0.9809 0.9792 0.9826
0.1288 22.97 603 0.0940 0.9706 0.9809 0.9792 0.9826
0.1304 24.0 630 0.0913 0.9652 0.9775 0.9826 0.9725
0.14 24.99 656 0.0979 0.9652 0.9776 0.9861 0.9693
0.1461 25.98 682 0.0874 0.9706 0.9810 0.9861 0.9759
0.1429 26.97 708 0.0837 0.9706 0.9808 0.9757 0.9860
0.1444 28.0 735 0.0876 0.9679 0.9792 0.9792 0.9792
0.145 28.99 761 0.0903 0.9706 0.9809 0.9792 0.9826
0.1445 29.71 780 0.0882 0.9679 0.9791 0.9757 0.9825

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.0
  • Tokenizers 0.15.0