ALM-AHME's picture
Model save
93baa67
metadata
license: apache-2.0
base_model: microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: >-
      swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-Lesion-Classification-HAM10000-3
    results: []

swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-Lesion-Classification-HAM10000-3

This model is a fine-tuned version of microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0112
  • Accuracy: 0.9951

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.5
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.1885 1.0 114 0.8718 0.6593
0.7037 2.0 228 0.4208 0.8637
0.5085 2.99 342 0.3446 0.8744
0.2874 4.0 457 0.2027 0.9327
0.355 5.0 571 0.1666 0.9401
0.2493 6.0 685 0.0969 0.9655
0.1909 6.99 799 0.0558 0.9836
0.1821 8.0 914 0.0412 0.9901
0.1853 9.0 1028 0.0239 0.9943
0.0666 9.98 1140 0.0112 0.9951

Framework versions

  • Transformers 4.32.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3