bombshelll's picture
Model save
f908d2e verified
|
raw
history blame
2.46 kB
metadata
library_name: transformers
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: swin-brain-abnormalities-classification
    results: []

swin-brain-abnormalities-classification

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1730
  • Accuracy: 0.9531

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: 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: 15

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.8641 0.9892 23 0.5282 0.7739
0.4526 1.9785 46 0.2441 0.8978
0.271 2.9677 69 0.1764 0.9313
0.2309 4.0 93 0.1976 0.9380
0.1705 4.9892 116 0.1841 0.9414
0.1789 5.9785 139 0.1264 0.9531
0.1442 6.9677 162 0.2048 0.9397
0.1463 8.0 186 0.1362 0.9564
0.122 8.9892 209 0.1399 0.9514
0.1157 9.9785 232 0.1184 0.9615
0.1089 10.9677 255 0.1848 0.9481
0.1062 12.0 279 0.1380 0.9581
0.0969 12.9892 302 0.1658 0.9548
0.0824 13.9785 325 0.1736 0.9548
0.0768 14.8387 345 0.1730 0.9531

Framework versions

  • Transformers 4.45.1
  • Pytorch 2.4.0
  • Datasets 3.0.1
  • Tokenizers 0.20.0