README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - bird-data
metrics:
  - accuracy
model-index:
  - name: swin-tiny-patch4-window7-224-finetuned-birds-finetuned-birds
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: bird-data
          type: bird-data
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6918896321070234

swin-tiny-patch4-window7-224-finetuned-birds-finetuned-birds

This model is a fine-tuned version of gjuggler/swin-tiny-patch4-window7-224-finetuned-birds on the bird-data dataset. It achieves the following results on the evaluation set:

• Loss: 1.2646
• Accuracy: 0.6919

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0629	1.0	84	1.5111	0.6455
1.8561	2.0	168	1.3206	0.6747
1.686	3.0	252	1.2646	0.6919

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2