Edit model card

Psoriasis-M-vit-large-patch16-224-in21k

This model is a fine-tuned version of google/vit-large-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1464
  • Accuracy: 0.9792

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: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 0.92 6 1.1103 0.6667
1.4249 2.0 13 0.5429 0.875
1.4249 2.92 19 0.3529 0.9167
0.3823 4.0 26 0.2861 0.9375
0.1072 4.62 30 0.2801 0.9375
No log 0.92 6 0.2647 0.9167
0.0527 2.0 13 0.1843 0.9792
0.0527 2.92 19 0.1604 0.9792
0.0138 4.0 26 0.1480 0.9792
0.0074 4.62 30 0.1464 0.9792

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
0
Safetensors
Model size
303M params
Tensor type
F32
·

Finetuned from