| | --- |
| | license: apache-2.0 |
| | tags: |
| | - image-classification |
| | - generated_from_trainer |
| | metrics: |
| | - accuracy |
| | - recall |
| | - f1 |
| | - precision |
| | model-index: |
| | - name: vit-huge-binary-isic-sharpened-patch-14 |
| | results: [] |
| | --- |
| | |
| | <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| | should probably proofread and complete it, then remove this comment. --> |
| |
|
| | # vit-huge-binary-isic-sharpened-patch-14 |
| |
|
| | This model is a fine-tuned version of [google/vit-huge-patch14-224-in21k](https://huggingface.co/google/vit-huge-patch14-224-in21k) on the ahishamm/isic_binary_sharpened dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.2129 |
| | - Accuracy: 0.9336 |
| | - Recall: 0.9336 |
| | - F1: 0.9336 |
| | - Precision: 0.9336 |
| |
|
| | ## 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: 0.0002 |
| | - train_batch_size: 16 |
| | - eval_batch_size: 8 |
| | - seed: 42 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: linear |
| | - num_epochs: 4 |
| |
|
| | ### Training results |
| |
|
| | | Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | F1 | Precision | |
| | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:| |
| | | 0.3116 | 0.09 | 100 | 0.3191 | 0.8553 | 0.8553 | 0.8553 | 0.8553 | |
| | | 0.3328 | 0.18 | 200 | 0.3595 | 0.8152 | 0.8152 | 0.8152 | 0.8152 | |
| | | 0.2597 | 0.28 | 300 | 0.2901 | 0.8733 | 0.8733 | 0.8733 | 0.8733 | |
| | | 0.2037 | 0.37 | 400 | 0.2478 | 0.8912 | 0.8912 | 0.8912 | 0.8912 | |
| | | 0.2415 | 0.46 | 500 | 0.2488 | 0.8966 | 0.8966 | 0.8966 | 0.8966 | |
| | | 0.1483 | 0.55 | 600 | 0.2943 | 0.8844 | 0.8844 | 0.8844 | 0.8844 | |
| | | 0.1126 | 0.65 | 700 | 0.3269 | 0.8752 | 0.8752 | 0.8752 | 0.8752 | |
| | | 0.207 | 0.74 | 800 | 0.2984 | 0.8869 | 0.8869 | 0.8869 | 0.8869 | |
| | | 0.234 | 0.83 | 900 | 0.2394 | 0.8857 | 0.8857 | 0.8857 | 0.8857 | |
| | | 0.1625 | 0.92 | 1000 | 0.2706 | 0.8930 | 0.8930 | 0.8930 | 0.8930 | |
| | | 0.1131 | 1.02 | 1100 | 0.2156 | 0.9208 | 0.9208 | 0.9208 | 0.9208 | |
| | | 0.048 | 1.11 | 1200 | 0.2676 | 0.9026 | 0.9026 | 0.9026 | 0.9026 | |
| | | 0.1235 | 1.2 | 1300 | 0.3326 | 0.9025 | 0.9025 | 0.9025 | 0.9025 | |
| | | 0.0093 | 1.29 | 1400 | 0.3239 | 0.9107 | 0.9107 | 0.9107 | 0.9107 | |
| | | 0.0851 | 1.39 | 1500 | 0.3067 | 0.8971 | 0.8971 | 0.8971 | 0.8971 | |
| | | 0.0962 | 1.48 | 1600 | 0.3164 | 0.8998 | 0.8998 | 0.8998 | 0.8998 | |
| | | 0.0143 | 1.57 | 1700 | 0.2269 | 0.9266 | 0.9266 | 0.9266 | 0.9266 | |
| | | 0.071 | 1.66 | 1800 | 0.3436 | 0.9118 | 0.9118 | 0.9118 | 0.9118 | |
| | | 0.0594 | 1.76 | 1900 | 0.3813 | 0.8997 | 0.8997 | 0.8997 | 0.8997 | |
| | | 0.0406 | 1.85 | 2000 | 0.2129 | 0.9336 | 0.9336 | 0.9336 | 0.9336 | |
| | | 0.048 | 1.94 | 2100 | 0.3117 | 0.9161 | 0.9161 | 0.9161 | 0.9161 | |
| | | 0.0071 | 2.03 | 2200 | 0.2732 | 0.9247 | 0.9247 | 0.9247 | 0.9247 | |
| | | 0.0021 | 2.13 | 2300 | 0.3055 | 0.9275 | 0.9275 | 0.9275 | 0.9275 | |
| | | 0.0722 | 2.22 | 2400 | 0.3442 | 0.9250 | 0.9250 | 0.9250 | 0.9250 | |
| | | 0.0146 | 2.31 | 2500 | 0.2984 | 0.9314 | 0.9314 | 0.9314 | 0.9314 | |
| | | 0.0031 | 2.4 | 2600 | 0.3212 | 0.9298 | 0.9298 | 0.9298 | 0.9298 | |
| | | 0.0167 | 2.5 | 2700 | 0.3111 | 0.9320 | 0.9320 | 0.9320 | 0.9320 | |
| | | 0.0017 | 2.59 | 2800 | 0.2883 | 0.9307 | 0.9307 | 0.9307 | 0.9307 | |
| | | 0.0007 | 2.68 | 2900 | 0.3189 | 0.9321 | 0.9321 | 0.9321 | 0.9321 | |
| | | 0.0012 | 2.77 | 3000 | 0.2996 | 0.9384 | 0.9384 | 0.9384 | 0.9384 | |
| | | 0.0006 | 2.87 | 3100 | 0.3553 | 0.9281 | 0.9281 | 0.9281 | 0.9281 | |
| | | 0.0007 | 2.96 | 3200 | 0.3595 | 0.9285 | 0.9285 | 0.9285 | 0.9285 | |
| | | 0.0238 | 3.05 | 3300 | 0.3351 | 0.9349 | 0.9349 | 0.9349 | 0.9349 | |
| | | 0.0065 | 3.14 | 3400 | 0.3166 | 0.9376 | 0.9376 | 0.9376 | 0.9376 | |
| | | 0.0009 | 3.23 | 3500 | 0.3304 | 0.9331 | 0.9331 | 0.9331 | 0.9331 | |
| | | 0.0006 | 3.33 | 3600 | 0.3215 | 0.9348 | 0.9348 | 0.9348 | 0.9348 | |
| | | 0.0005 | 3.42 | 3700 | 0.3414 | 0.9353 | 0.9353 | 0.9353 | 0.9353 | |
| | | 0.0006 | 3.51 | 3800 | 0.3321 | 0.9350 | 0.9350 | 0.9350 | 0.9350 | |
| | | 0.0006 | 3.6 | 3900 | 0.3306 | 0.9379 | 0.9379 | 0.9379 | 0.9379 | |
| | | 0.0411 | 3.7 | 4000 | 0.3226 | 0.9375 | 0.9375 | 0.9375 | 0.9375 | |
| | | 0.0006 | 3.79 | 4100 | 0.3235 | 0.9377 | 0.9377 | 0.9377 | 0.9377 | |
| | | 0.0354 | 3.88 | 4200 | 0.3268 | 0.9357 | 0.9357 | 0.9357 | 0.9357 | |
| | | 0.0328 | 3.97 | 4300 | 0.3264 | 0.9358 | 0.9358 | 0.9358 | 0.9358 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.30.2 |
| | - Pytorch 2.0.1+cu118 |
| | - Datasets 2.13.1 |
| | - Tokenizers 0.13.3 |
| |
|
