metadata
library_name: transformers
license: apache-2.0
base_model: facebook/dinov2-base
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- f1
model-index:
- name: dinov2-Base-finetuned-chest_xray
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: 0.978
- name: F1
type: f1
value: 0.9779992079714871
dinov2-Base-finetuned-chest_xray
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: 0.1155
- Accuracy: 0.978
- F1: 0.9780
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.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 | F1 |
|---|---|---|---|---|---|
| 0.6168 | 1.0 | 500 | 0.3097 | 0.881 | 0.8804 |
| 0.4064 | 2.0 | 1000 | 0.2299 | 0.931 | 0.9309 |
| 0.2011 | 3.0 | 1500 | 0.1904 | 0.943 | 0.9430 |
| 0.148 | 4.0 | 2000 | 0.2213 | 0.94 | 0.9399 |
| 0.2495 | 5.0 | 2500 | 0.2518 | 0.933 | 0.9328 |
| 0.1926 | 6.0 | 3000 | 0.1155 | 0.966 | 0.9660 |
| 0.1565 | 7.0 | 3500 | 0.1711 | 0.959 | 0.9590 |
| 0.1881 | 8.0 | 4000 | 0.1235 | 0.967 | 0.9670 |
| 0.139 | 9.0 | 4500 | 0.1285 | 0.97 | 0.9700 |
| 0.1317 | 10.0 | 5000 | 0.1155 | 0.978 | 0.9780 |
Framework versions
- Transformers 4.51.1
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0