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