| | --- |
| | license: apache-2.0 |
| | tags: |
| | - image-classification |
| | - generated_from_trainer |
| | metrics: |
| | - accuracy |
| | - recall |
| | - f1 |
| | - precision |
| | model-index: |
| | - name: vit-base-binary-isic-patch-16 |
| | 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-base-binary-isic-patch-16 |
| |
|
| | This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the ahishamm/isic_binary_augmented dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.2665 |
| | - Accuracy: 0.8799 |
| | - Recall: 0.8799 |
| | - F1: 0.8799 |
| | - Precision: 0.8799 |
| |
|
| | ## 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 | |
| | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:| |
| | | 0.3887 | 0.09 | 100 | 0.3201 | 0.8539 | 0.8539 | 0.8539 | 0.8539 | |
| | | 0.2725 | 0.19 | 200 | 0.3208 | 0.8526 | 0.8526 | 0.8526 | 0.8526 | |
| | | 0.2653 | 0.28 | 300 | 0.3113 | 0.8532 | 0.8532 | 0.8532 | 0.8532 | |
| | | 0.2439 | 0.37 | 400 | 0.3156 | 0.8749 | 0.8749 | 0.8749 | 0.8749 | |
| | | 0.2183 | 0.46 | 500 | 0.3145 | 0.8391 | 0.8391 | 0.8391 | 0.8391 | |
| | | 0.2233 | 0.56 | 600 | 0.3083 | 0.8543 | 0.8543 | 0.8543 | 0.8543 | |
| | | 0.2234 | 0.65 | 700 | 0.3757 | 0.8598 | 0.8598 | 0.8598 | 0.8598 | |
| | | 0.1825 | 0.74 | 800 | 0.2665 | 0.8799 | 0.8799 | 0.8799 | 0.8799 | |
| | | 0.1244 | 0.84 | 900 | 0.3088 | 0.8886 | 0.8886 | 0.8886 | 0.8886 | |
| | | 0.1454 | 0.93 | 1000 | 0.4594 | 0.8544 | 0.8544 | 0.8544 | 0.8544 | |
| | | 0.043 | 1.02 | 1100 | 0.3424 | 0.8820 | 0.8820 | 0.8820 | 0.8820 | |
| | | 0.1911 | 1.12 | 1200 | 0.4268 | 0.8630 | 0.8630 | 0.8630 | 0.8630 | |
| | | 0.1091 | 1.21 | 1300 | 0.2940 | 0.8779 | 0.8779 | 0.8779 | 0.8779 | |
| | | 0.0426 | 1.3 | 1400 | 0.3423 | 0.8915 | 0.8915 | 0.8915 | 0.8915 | |
| | | 0.0831 | 1.39 | 1500 | 0.4086 | 0.8625 | 0.8625 | 0.8625 | 0.8625 | |
| | | 0.106 | 1.49 | 1600 | 0.3020 | 0.8972 | 0.8972 | 0.8972 | 0.8972 | |
| | | 0.0717 | 1.58 | 1700 | 0.3971 | 0.8875 | 0.8875 | 0.8875 | 0.8875 | |
| | | 0.1134 | 1.67 | 1800 | 0.3530 | 0.8924 | 0.8924 | 0.8924 | 0.8924 | |
| | | 0.0702 | 1.77 | 1900 | 0.3878 | 0.8888 | 0.8888 | 0.8888 | 0.8888 | |
| | | 0.0828 | 1.86 | 2000 | 0.3822 | 0.8852 | 0.8852 | 0.8852 | 0.8852 | |
| | | 0.0497 | 1.95 | 2100 | 0.3364 | 0.8992 | 0.8992 | 0.8992 | 0.8992 | |
| | | 0.0191 | 2.04 | 2200 | 0.4042 | 0.8925 | 0.8925 | 0.8925 | 0.8925 | |
| | | 0.0388 | 2.14 | 2300 | 0.4485 | 0.8970 | 0.8970 | 0.8970 | 0.8970 | |
| | | 0.0273 | 2.23 | 2400 | 0.3862 | 0.8953 | 0.8953 | 0.8953 | 0.8953 | |
| | | 0.0032 | 2.32 | 2500 | 0.4710 | 0.8949 | 0.8949 | 0.8949 | 0.8949 | |
| | | 0.0242 | 2.42 | 2600 | 0.4859 | 0.8938 | 0.8938 | 0.8938 | 0.8938 | |
| | | 0.065 | 2.51 | 2700 | 0.4446 | 0.8983 | 0.8983 | 0.8983 | 0.8983 | |
| | | 0.0258 | 2.6 | 2800 | 0.5354 | 0.8925 | 0.8925 | 0.8925 | 0.8925 | |
| | | 0.001 | 2.7 | 2900 | 0.5201 | 0.8958 | 0.8958 | 0.8958 | 0.8958 | |
| | | 0.0336 | 2.79 | 3000 | 0.5137 | 0.8924 | 0.8924 | 0.8924 | 0.8924 | |
| | | 0.0205 | 2.88 | 3100 | 0.5251 | 0.8972 | 0.8972 | 0.8972 | 0.8972 | |
| | | 0.0033 | 2.97 | 3200 | 0.5083 | 0.8907 | 0.8907 | 0.8907 | 0.8907 | |
| | | 0.0009 | 3.07 | 3300 | 0.4909 | 0.9007 | 0.9007 | 0.9007 | 0.9007 | |
| | | 0.0465 | 3.16 | 3400 | 0.5176 | 0.8984 | 0.8984 | 0.8984 | 0.8984 | |
| | | 0.0007 | 3.25 | 3500 | 0.5411 | 0.8977 | 0.8977 | 0.8977 | 0.8977 | |
| | | 0.0406 | 3.35 | 3600 | 0.4929 | 0.9008 | 0.9008 | 0.9008 | 0.9008 | |
| | | 0.0016 | 3.44 | 3700 | 0.5065 | 0.8993 | 0.8993 | 0.8993 | 0.8993 | |
| | | 0.0006 | 3.53 | 3800 | 0.5403 | 0.8985 | 0.8985 | 0.8985 | 0.8985 | |
| | | 0.0272 | 3.62 | 3900 | 0.5399 | 0.8992 | 0.8992 | 0.8992 | 0.8992 | |
| | | 0.0223 | 3.72 | 4000 | 0.5075 | 0.9044 | 0.9044 | 0.9044 | 0.9044 | |
| | | 0.0006 | 3.81 | 4100 | 0.5432 | 0.8993 | 0.8993 | 0.8993 | 0.8993 | |
| | | 0.0153 | 3.9 | 4200 | 0.5263 | 0.9021 | 0.9021 | 0.9021 | 0.9021 | |
| | | 0.0273 | 4.0 | 4300 | 0.5242 | 0.9029 | 0.9029 | 0.9029 | 0.9029 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.30.2 |
| | - Pytorch 2.0.1+cu118 |
| | - Datasets 2.13.1 |
| | - Tokenizers 0.13.3 |
| |
|
