Hugging Face's logo

ongkn
/
attraction-classifier

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
5
attraction-classifier / README.md
ongkn's picture
ongkn
Training in progress, step 15
362e1bb
preview code
|
raw
history blame
3.43 kB
metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: attraction-classifier
    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: 0.7955974842767296

attraction-classifier

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4691
  • Accuracy: 0.7956

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: 16
  • eval_batch_size: 16
  • seed: 69
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.15
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.6703 0.34 15 0.6354 0.7327
0.5449 0.67 30 0.5836 0.7421
0.5407 1.01 45 0.5594 0.7421
0.5255 1.34 60 0.5294 0.7547
0.5586 1.68 75 0.5171 0.7642
0.5438 2.01 90 0.5212 0.7704
0.4807 2.35 105 0.5181 0.7390
0.6202 2.68 120 0.4972 0.7704
0.5021 3.02 135 0.4566 0.7987
0.4313 3.35 150 0.4852 0.7925
0.3532 3.69 165 0.4378 0.8113
0.3577 4.02 180 0.4515 0.8019
0.4736 4.36 195 0.4498 0.7893
0.3516 4.69 210 0.4408 0.8239
0.4437 5.03 225 0.4611 0.7799
0.3543 5.36 240 0.4294 0.8208
0.4029 5.7 255 0.4155 0.8428
0.3808 6.03 270 0.4116 0.8302
0.3211 6.37 285 0.4009 0.8302
0.2949 6.7 300 0.4321 0.8176
0.2663 7.04 315 0.4229 0.8396
0.3049 7.37 330 0.4110 0.8365
0.1303 7.71 345 0.4288 0.8333
0.2079 8.04 360 0.4218 0.8208
0.208 8.38 375 0.3908 0.8365
0.2067 8.72 390 0.5191 0.7862
0.1635 9.05 405 0.4691 0.7956

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.15.0
  • Tokenizers 0.15.0