swin-large-patch4-window12-384-in22k-finetuned-ADC-4cls-0923

This model is a fine-tuned version of microsoft/swin-large-patch4-window12-384-in22k on the imagefolder dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.5621
• eval_accuracy: 0.8571
• eval_runtime: 6.0148
• eval_samples_per_second: 11.638
• eval_steps_per_second: 0.499
• epoch: 26.4
• step: 99

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 200

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3