Gracoy's picture
End of training
e7a130c
|
raw
history blame
2.03 kB
metadata
license: apache-2.0
base_model: microsoft/swinv2-base-patch4-window8-256
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: swinv2-base-patch4-window8-256-Kaggle_test_20231120
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.936830835117773

swinv2-base-patch4-window8-256-Kaggle_test_20231120

This model is a fine-tuned version of microsoft/swinv2-base-patch4-window8-256 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1843
  • Accuracy: 0.9368

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: 0.0001
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.2115 0.99 44 0.1843 0.9368
0.1445 1.99 88 0.1849 0.9368
0.109 2.98 132 0.1720 0.9368

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0