swin-tiny-patch4-window7-224-finetuned-eurosat-leukemia-3000-finetuned-leukemia-1000

This model is a fine-tuned version of DouglasBraga/swin-tiny-patch4-window7-224-finetuned-eurosat-leukemia-3000 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.0056
• Accuracy: 1.0

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
0.5471	0.9825	14	0.1240	0.955
0.1792	1.9649	28	0.0493	0.985
0.0936	2.9474	42	0.1210	0.965
0.0907	4.0	57	0.0056	1.0
0.0441	4.9825	71	0.0165	0.995
0.0341	5.9649	85	0.0059	0.995
0.0406	6.9474	99	0.0018	1.0
0.013	8.0	114	0.0200	0.995
0.0342	8.9825	128	0.0030	1.0
0.0246	9.8246	140	0.0026	1.0

Framework versions

• Transformers 4.40.0.dev0
• Pytorch 2.2.2+cpu
• Datasets 2.19.0
• Tokenizers 0.15.2