Hugging Face's logo

zeenfts
/
output_dir

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
2
output_dir / README.md
zeenfts's picture
zeenfts
End of training
6e115f9
preview code
|
raw
history blame
3.75 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: output_dir
    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: 0.5875

output_dir

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: 1.2119
  • Accuracy: 0.5875

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: 64
  • eval_batch_size: 64
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: reduce_lr_on_plateau
  • num_epochs: 41

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 0.8 2 2.0638 0.1562
No log 2.0 5 2.0353 0.2
No log 2.8 7 1.9965 0.2687
1.9968 4.0 10 1.9289 0.3937
1.9968 4.8 12 1.8942 0.3125
1.9968 6.0 15 1.8054 0.4562
1.9968 6.8 17 1.7626 0.4313
1.7555 8.0 20 1.7078 0.4562
1.7555 8.8 22 1.6608 0.45
1.7555 10.0 25 1.6121 0.425
1.7555 10.8 27 1.5759 0.4813
1.5214 12.0 30 1.5340 0.4562
1.5214 12.8 32 1.5006 0.5062
1.5214 14.0 35 1.4956 0.4313
1.5214 14.8 37 1.4418 0.5125
1.3342 16.0 40 1.4236 0.525
1.3342 16.8 42 1.3784 0.55
1.3342 18.0 45 1.4367 0.4938
1.3342 18.8 47 1.3665 0.525
1.1553 20.0 50 1.3867 0.4813
1.1553 20.8 52 1.3536 0.5312
1.1553 22.0 55 1.3391 0.5125
1.1553 22.8 57 1.2930 0.5563
0.9972 24.0 60 1.2894 0.5375
0.9972 24.8 62 1.2802 0.5625
0.9972 26.0 65 1.2671 0.5687
0.9972 26.8 67 1.2491 0.5625
0.838 28.0 70 1.2907 0.5437
0.838 28.8 72 1.2806 0.5563
0.838 30.0 75 1.2228 0.5687
0.838 30.8 77 1.2485 0.575
0.7226 32.0 80 1.2777 0.5437
0.7226 32.8 82 1.2106 0.6

Framework versions

  • Transformers 4.33.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3