dinov2-base-finetuned-dermnet
This model is a fine-tuned version of facebook/dinov2-base on the image_folder dataset. It achieves the following results on the evaluation set:
- Loss: 0.7513
- Accuracy: 0.7827
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: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.1078 | 0.99 | 137 | 1.9232 | 0.4213 |
| 1.7287 | 2.0 | 275 | 1.4859 | 0.5665 |
| 1.475 | 3.0 | 413 | 1.3171 | 0.5946 |
| 1.1488 | 4.0 | 551 | 1.1150 | 0.6651 |
| 1.0082 | 4.99 | 688 | 1.0263 | 0.6892 |
| 0.7533 | 6.0 | 826 | 0.9673 | 0.7065 |
| 0.6741 | 7.0 | 964 | 0.9219 | 0.7270 |
| 0.568 | 8.0 | 1102 | 0.8607 | 0.7510 |
| 0.4327 | 8.99 | 1239 | 0.8237 | 0.7643 |
| 0.3464 | 10.0 | 1377 | 0.8143 | 0.7648 |
| 0.2521 | 11.0 | 1515 | 0.7786 | 0.7704 |
| 0.253 | 11.93 | 1644 | 0.7513 | 0.7827 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
- Downloads last month
- 62