Edit model card

dental_classification_model_010424

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

  • Loss: 0.5797
  • Accuracy: 0.8354

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: 20

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.8845 0.99 40 1.8553 0.3106
1.6458 1.99 80 1.6211 0.4363
1.4423 2.98 120 1.4076 0.5202
1.2767 4.0 161 1.2806 0.5714
1.0687 4.99 201 1.0996 0.6537
0.9687 5.99 241 1.0288 0.6677
0.8714 6.98 281 0.9370 0.7252
0.7841 8.0 322 0.8287 0.7484
0.6814 8.99 362 0.8141 0.7376
0.5964 9.99 402 0.7433 0.7919
0.5995 10.98 442 0.7075 0.7904
0.5222 12.0 483 0.6613 0.8043
0.5173 12.99 523 0.6485 0.8090
0.4776 13.99 563 0.6196 0.8230
0.4679 14.98 603 0.5795 0.8416
0.4123 16.0 644 0.6202 0.8168
0.4179 16.99 684 0.6037 0.8230
0.4139 17.99 724 0.5797 0.8354

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
2
Safetensors
Model size
85.8M params
Tensor type
F32
·

Finetuned from