Hemg's picture
Model save
c8f2f2c verified
|
raw
history blame
3.44 kB
metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: Wound-Image-classification
    results: []

Wound-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: 0.2278
  • Accuracy: 0.9524

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 32

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.8831 1.0 147 1.2970 0.6531
0.9115 2.0 294 0.8685 0.7143
0.6506 3.0 441 0.7251 0.7653
0.5561 4.0 588 0.6598 0.7959
0.4606 5.0 735 0.6454 0.7806
0.3946 6.0 882 0.5916 0.8282
0.3433 7.0 1029 0.5672 0.8265
0.281 8.0 1176 0.6194 0.8265
0.2735 9.0 1323 0.4681 0.8571
0.2452 10.0 1470 0.4842 0.8673
0.2358 11.0 1617 0.4283 0.8776
0.1693 12.0 1764 0.4548 0.8759
0.1715 13.0 1911 0.5153 0.8724
0.159 14.0 2058 0.3161 0.9184
0.1557 15.0 2205 0.4901 0.8861
0.1137 16.0 2352 0.4257 0.9031
0.1239 17.0 2499 0.3844 0.9031
0.1426 18.0 2646 0.3769 0.8980
0.128 19.0 2793 0.3641 0.9082
0.1168 20.0 2940 0.3241 0.9133
0.1139 21.0 3087 0.2318 0.9320
0.0975 22.0 3234 0.3019 0.9286
0.0989 23.0 3381 0.2984 0.9269
0.0847 24.0 3528 0.2930 0.9201
0.0659 25.0 3675 0.3112 0.9371
0.0789 26.0 3822 0.2835 0.9354
0.0432 27.0 3969 0.3100 0.9303
0.0438 28.0 4116 0.3168 0.9320
0.0371 29.0 4263 0.2361 0.9490
0.039 30.0 4410 0.2714 0.9473
0.0435 31.0 4557 0.2547 0.9524
0.0512 32.0 4704 0.2278 0.9524

Framework versions

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