Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
This model is a fine-tuned version of facebook/dinov2-base on the imagefolder dataset. It achieves the following results on the evaluation set: Loss: 0.4141 Accuracy: 0.8724
Model source
Source description
This model is a fine-tuned version of facebook/dinov2-base on the imagefolder dataset. It achieves the following results on the evaluation set:
More information needed
Sources
1 sourceVerified Sep 17
Model artifacts
1 artifactSource excerpts
2 excerptsMore information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.1724 | 1.0 | 14 | 1.9875 | 0.3776 |
| 1.9233 | 2.0 | 28 | 1.2796 | 0.5995 |
| 0.9913 | 3.0 | 42 | 0.8862 | 0.7168 |
| 0.7552 | 4.0 | 56 | 0.7308 | 0.7577 |
| 0.5114 | 5.0 | 70 | 0.5880 | 0.8163 |
--- library_name: transformers license: apache-2.0 base_model: facebook/dinov2-base tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: dinov2-base-rawdata-finetuned-SkinDisease results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.8724489795918368 --- <!-- 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-rawdata-finetuned-SkinDisease This model is a fine-tuned version of [facebook/dinov2-base](https://huggingface.co/facebook/dinov2-base) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.4141 - Accuracy: 0.8724 ## 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: 64 - eval_batch_size: 64 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 256 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 0.1 - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 3.1724 | 1.0 | 14 | 1.9875 | 0.3776 | | 1.9233 | 2.0 | 28 | 1.2796 | 0.5995 | | 0.9913 | 3.0 | 42 | 0.8862 | 0.7168 | | 0.7552 | 4.0 | 56 | 0.7308 | 0.7577 | | 0.5114 | 5.0 | 70 | 0.5880 | 0.8163 | | 0.4078 | 6.0 | 84 | 0.6009 | 0.8265 | | 0.3522 | 7.0 | 98 | 0.5508 | 0.8393 | | 0.3091 | 8.0 | 112 | 0.4744 | 0.8520 | | 0.2232 | 9.0 | 126 | 0.4141 | 0.8724 | | 0.1817 | 10.0 | 140 | 0.4219 | 0.8699 | ### Framework versions - Transformers 5.10.2 - Pytorch 2.10.0+cu128 - Datasets 4.8.5 - Tokenizers 0.22.2
Source context: 8 downloads · 0 likes · Pipeline image-classification · Library transformers · Repo RushnaFathima/dinov2-base-rawdata-finetuned-SkinDisease
| 0.4078 | 6.0 | 84 | 0.6009 | 0.8265 |
| 0.3522 | 7.0 | 98 | 0.5508 | 0.8393 |
| 0.3091 | 8.0 | 112 | 0.4744 | 0.8520 |
| 0.2232 | 9.0 | 126 | 0.4141 | 0.8724 |
| 0.1817 | 10.0 | 140 | 0.4219 | 0.8699 |
