youssefabdelmottaleb's picture
Model save
ebf87dd verified
metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: Garbage-Classification-SWIN-Transformer
    results: []

Garbage-Classification-SWIN-Transformer

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: 0.0440
  • Accuracy: 0.9900

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: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.1969 0.9973 280 0.1740 0.9409
0.1014 1.9982 561 0.0752 0.9755
0.0333 2.9991 842 0.0551 0.9824
0.0332 4.0 1123 0.0526 0.9845
0.0218 4.9973 1403 0.0511 0.9866
0.0086 5.9982 1684 0.0515 0.9873
0.0057 6.9991 1965 0.0462 0.9875
0.0043 8.0 2246 0.0453 0.9891
0.0012 8.9973 2526 0.0460 0.9888
0.0017 9.9733 2800 0.0440 0.9900

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.1.2
  • Datasets 2.19.2
  • Tokenizers 0.19.1