swin-tiny-patch4-window7-224-swin-tiny-patch4-window7-224-finetuned-leukemia.v2.1

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:

• Loss: 0.1379
• Accuracy: 0.954

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: 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4215	0.9991	281	0.3880	0.8293
0.3137	1.9982	562	0.2898	0.8788
0.2631	2.9973	843	0.2382	0.907
0.2338	4.0	1125	0.4090	0.8575
0.1834	4.9991	1406	0.2477	0.8985
0.2065	5.9982	1687	0.1331	0.9513
0.1555	6.9973	1968	0.1304	0.9473
0.1521	8.0	2250	0.1837	0.9293
0.1512	8.9991	2531	0.1708	0.9405
0.119	9.9911	2810	0.1379	0.954

Framework versions

• Transformers 4.45.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.1