Edit model card

swin-tiny-patch4-window7-224-finetuned-teeth_dataset-finetuned-teeth_dataset-V2

This model is a fine-tuned version of Dhyey8/swin-tiny-patch4-window7-224-finetuned-teeth_dataset on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3081
  • Accuracy: 0.9261

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: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 0.8 3 1.1267 0.8391
No log 1.87 7 1.0719 0.8304
0.5709 2.93 11 0.9447 0.8478
0.5709 4.0 15 0.8442 0.8652
0.5709 4.8 18 0.7065 0.8826
0.3317 5.87 22 0.6930 0.8891
0.3317 6.93 26 0.5630 0.8978
0.1576 8.0 30 0.5882 0.8826
0.1576 8.8 33 0.5198 0.9087
0.1576 9.87 37 0.4425 0.9043
0.0883 10.93 41 0.4727 0.8978
0.0883 12.0 45 0.4314 0.9022
0.0883 12.8 48 0.4011 0.9022
0.051 13.87 52 0.4045 0.9174
0.051 14.93 56 0.3745 0.9109
0.0415 16.0 60 0.3597 0.9152
0.0415 16.8 63 0.4016 0.9065
0.0415 17.87 67 0.3804 0.9152
0.0307 18.93 71 0.3519 0.9217
0.0307 20.0 75 0.4131 0.8935
0.0307 20.8 78 0.4047 0.9
0.0262 21.87 82 0.3450 0.9174
0.0262 22.93 86 0.3639 0.9109
0.0208 24.0 90 0.3843 0.9043
0.0208 24.8 93 0.3797 0.8978
0.0208 25.87 97 0.3660 0.9152
0.0141 26.93 101 0.3445 0.9152
0.0141 28.0 105 0.3131 0.9239
0.0141 28.8 108 0.3069 0.9196
0.0114 29.87 112 0.3006 0.9196
0.0114 30.93 116 0.3097 0.9239
0.014 32.0 120 0.3121 0.9174
0.014 32.8 123 0.3242 0.9174
0.014 33.87 127 0.3291 0.9217
0.016 34.93 131 0.3156 0.9217
0.016 36.0 135 0.3081 0.9261
0.016 36.8 138 0.3084 0.9261
0.0114 37.87 142 0.3148 0.9196
0.0114 38.93 146 0.3191 0.9174
0.0091 40.0 150 0.3191 0.9174

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
25
Safetensors
Model size
27.6M params
Tensor type
I64
·
F32
·

Finetuned from

Evaluation results