metadata
library_name: transformers
license: apache-2.0
base_model: facebook/dinov2-base
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: ky-finetuned-skin
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: 0.9543516428392275
ky-finetuned-skin
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: 0.1260
- Accuracy: 0.9544
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4572 | 1.0 | 281 | 0.7687 | 0.7524 |
| 0.7019 | 2.0 | 562 | 0.4615 | 0.8533 |
| 0.5125 | 3.0 | 843 | 0.3146 | 0.8942 |
| 0.4267 | 4.0 | 1124 | 0.2547 | 0.9180 |
| 0.3441 | 5.0 | 1405 | 0.2028 | 0.9333 |
| 0.3034 | 6.0 | 1686 | 0.1992 | 0.9320 |
| 0.2581 | 7.0 | 1967 | 0.1590 | 0.9453 |
| 0.2167 | 8.0 | 2248 | 0.1490 | 0.9468 |
| 0.1879 | 9.0 | 2529 | 0.1318 | 0.9541 |
| 0.16 | 9.9661 | 2800 | 0.1260 | 0.9544 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0