swin-transformer

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.7366
• Accuracy: 0.39
• F1: 0.2753

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.7273	2	2.0766	0.3	0.2161
No log	1.8182	5	1.7687	0.37	0.2461
No log	2.1818	6	1.7366	0.39	0.2753

Framework versions

• Transformers 4.45.2
• Pytorch 2.4.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.1