metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
model-index:
  - name: swin-tiny-patch4-window7-224-arty-bg-classifier
    results: []

swin-tiny-patch4-window7-224-arty-bg-classifier

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

eval_loss: 0.0086
eval_accuracy: 0.9975
eval_runtime: 102.2105
eval_samples_per_second: 127.639
eval_steps_per_second: 1.331
epoch: 1.84
step: 250

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: 96
eval_batch_size: 96
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 384
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Framework versions

Transformers 4.29.1
Pytorch 2.0.0+cu118
Datasets 2.12.0
Tokenizers 0.13.3