<!-- 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. -->
dinov2-base-finetuned-HAM10000
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: 0.1610
- Accuracy: 0.9391
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.7187 | 0.99 | 70 | 0.5756 | 0.8014 |
0.5567 | 2.0 | 141 | 0.5557 | 0.8074 |
0.4815 | 2.99 | 211 | 0.3852 | 0.8483 |
0.3919 | 4.0 | 282 | 0.3132 | 0.8842 |
0.3898 | 4.99 | 352 | 0.2606 | 0.9042 |
0.2679 | 6.0 | 423 | 0.2422 | 0.9142 |
0.248 | 6.99 | 493 | 0.2498 | 0.9152 |
0.1556 | 8.0 | 564 | 0.1844 | 0.9271 |
0.1314 | 8.99 | 634 | 0.1610 | 0.9391 |
0.0877 | 9.93 | 700 | 0.1704 | 0.9391 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3