skincare-detection / README.md
tuphamdf's picture
Upload ViTForImageClassification
784cdfd verified
metadata
license: apache-2.0
tags:
  - generated_from_trainer
  - image-classification
  - vision
base_model: google/vit-base-patch16-224-in21k
metrics:
  - accuracy
model-index:
  - name: skincare-detection
    results: []

skincare-detection

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4840
  • Accuracy: 0.8648

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: 0.0002
  • 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: 12

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.3961 0.99 61 0.5629 0.7725
0.4982 2.0 123 0.3991 0.8435
0.3563 2.99 184 0.4330 0.8272
0.2314 4.0 246 0.3969 0.8554
0.1815 4.99 307 0.4492 0.8435
0.1332 6.0 369 0.4474 0.8580
0.0869 6.99 430 0.4520 0.8631
0.0844 8.0 492 0.4469 0.8640
0.0681 8.99 553 0.4533 0.8717
0.0574 10.0 615 0.4952 0.8597
0.0477 10.99 676 0.4772 0.8674
0.0454 11.9 732 0.4840 0.8648

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.2
  • Datasets 2.17.1
  • Tokenizers 0.15.2