metadata
library_name: transformers
license: other
base_model: timm/vit_base_patch16_dinov3.lvd1689m
tags:
- image-classification
- vision
- timm
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: openscene-vit-dinov3
results: []
openscene-vit-dinov3
This model is a fine-tuned version of timm/vit_base_patch16_dinov3.lvd1689m on the prithivMLmods/OpenScene-Classification dataset. It achieves the following results on the evaluation set:
- Loss: 0.1190
- Accuracy: 0.9673
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
- 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: 5.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4400 | 1.0 | 44 | 0.2700 | 0.9429 |
| 0.3791 | 2.0 | 88 | 0.1623 | 0.9510 |
| 0.2094 | 3.0 | 132 | 0.1398 | 0.9551 |
| 0.1632 | 4.0 | 176 | 0.1410 | 0.9510 |
| 0.1688 | 5.0 | 220 | 0.1190 | 0.9673 |
Framework versions
- Transformers 5.3.0.dev0
- Pytorch 2.10.0+cu128
- Datasets 4.6.1
- Tokenizers 0.22.2