Edit model card

swinv2-base-patch4-window8-256-isic217

This model is a fine-tuned version of microsoft/swinv2-base-patch4-window8-256 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1588
  • Accuracy: 0.65

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: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • 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
2.1681 0.9888 22 2.0018 0.25
1.9254 1.9775 44 1.7653 0.35
1.6706 2.9663 66 1.6649 0.6
1.2834 4.0 89 1.5579 0.5
1.2039 4.9888 111 1.4087 0.55
0.9395 5.9775 133 1.3115 0.5
0.7532 6.9663 155 1.3599 0.6
0.6573 8.0 178 1.1588 0.65
0.6663 8.9888 200 1.2074 0.6
0.4686 9.8876 220 1.2285 0.6

Framework versions

  • Transformers 4.42.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
0
Safetensors
Model size
86.9M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for vananhle/swinv2-base-patch4-window8-256-isic217

Finetuned
(11)
this model