Hemg's picture
Model save
fca5583 verified
metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: Melanoma-Cancer-Image-Classification
    results: []

Melanoma-Cancer-Image-Classification

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

  • Loss: 0.1954
  • Accuracy: 0.9395

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: 3e-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: 16
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.5451 0.99 68 0.2960 0.8936
0.2488 1.99 137 0.2254 0.9105
0.1986 3.0 206 0.1913 0.9282
0.1714 4.0 275 0.1906 0.9264
0.1576 4.99 343 0.1825 0.9323
0.1359 5.99 412 0.1973 0.9318
0.1193 7.0 481 0.1756 0.9368
0.1062 8.0 550 0.1743 0.9382
0.0983 8.99 618 0.1885 0.9395
0.0797 9.99 687 0.1931 0.9309
0.0698 11.0 756 0.1895 0.9359
0.0657 12.0 825 0.1861 0.9368
0.0587 12.99 893 0.1837 0.9414
0.056 13.99 962 0.1936 0.9377
0.0592 15.0 1031 0.1958 0.935
0.0508 15.83 1088 0.1954 0.9395

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2