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: 0.3057
Accuracy: 0.8971

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.4898	0.9935	38	1.3709	0.4632
0.8902	1.9869	76	0.9261	0.6324
0.9107	2.9804	114	0.8400	0.6397
0.564	4.0	153	0.6937	0.7279
0.5563	4.9935	191	0.5622	0.7647
0.3851	5.9869	229	0.5238	0.8015
0.3327	6.9804	267	0.6382	0.7941
0.2469	8.0	306	0.4330	0.8456
0.2903	8.9935	344	0.4212	0.8309
0.1861	9.9869	382	0.4140	0.8529
0.1533	10.9804	420	0.3810	0.8603
0.1017	12.0	459	0.3565	0.8603
0.1285	12.9935	497	0.3057	0.8971
0.1377	13.9869	535	0.3058	0.8824
0.1033	14.9020	570	0.3140	0.8824

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.19.1

rukundob451/swin-tiny-patch4-window7-224-finetuned-papsmear

swin-tiny-patch4-window7-224-finetuned-papsmear

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

rukundob451/
swin-tiny-patch4-window7-224-finetuned-papsmear