pvt-small-224-finetuned-papsmear

This model is a fine-tuned version of Xrenya/pvt-small-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: nan
• Accuracy: 0.2426

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
0.0	0.9935	38	nan	0.2426
0.0	1.9869	76	nan	0.2426
0.0	2.9804	114	nan	0.2426
0.0	4.0	153	nan	0.2426
0.0	4.9935	191	nan	0.2426
0.0	5.9869	229	nan	0.2426
0.0	6.9804	267	nan	0.2426
0.0	8.0	306	nan	0.2426
0.0	8.9935	344	nan	0.2426
0.0	9.9869	382	nan	0.2426
0.0	10.9804	420	nan	0.2426
0.0	12.0	459	nan	0.2426
0.0	12.9935	497	nan	0.2426
0.0	13.9869	535	nan	0.2426
0.0	14.9020	570	nan	0.2426

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1