metadata
library_name: transformers
license: apache-2.0
base_model: facebook/dinov2-small-imagenet1k-1-layer
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: dinov2-small-imagenet1k-1-layer-finetuned-eurosat
results: []
dinov2-small-imagenet1k-1-layer-finetuned-eurosat
This model is a fine-tuned version of facebook/dinov2-small-imagenet1k-1-layer on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2994
- Accuracy: 0.9212
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: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.9886 | 1.0 | 26 | 0.8828 | 0.7717 |
0.645 | 2.0 | 52 | 0.4112 | 0.8859 |
0.4834 | 3.0 | 78 | 0.2994 | 0.9212 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3