metadata
library_name: transformers
license: apache-2.0
base_model: facebook/dinov2-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
model-index:
- name: output_dinov2_baseline
results: []
output_dinov2_baseline
This model is a fine-tuned version of facebook/dinov2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0350
- Precision: 0.9820
- Recall: 0.9748
- F1: 0.9784
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-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use 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 | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 0.3192 | 1.0 | 145 | 0.0417 | 0.9532 | 0.9632 | 0.9582 |
| 0.1286 | 2.0 | 290 | 0.0304 | 0.9698 | 0.9769 | 0.9733 |
| 0.0635 | 3.0 | 435 | 0.0370 | 0.9579 | 0.9790 | 0.9683 |
| 0.0970 | 4.0 | 580 | 0.0326 | 0.9738 | 0.9758 | 0.9748 |
| 0.1622 | 5.0 | 725 | 0.0305 | 0.9810 | 0.9779 | 0.9795 |
| 0.0427 | 6.0 | 870 | 0.0369 | 0.9789 | 0.9737 | 0.9763 |
| 0.0301 | 7.0 | 1015 | 0.0356 | 0.9810 | 0.9748 | 0.9779 |
| 0.0523 | 8.0 | 1160 | 0.0346 | 0.9841 | 0.9748 | 0.9794 |
| 0.0112 | 9.0 | 1305 | 0.0345 | 0.9820 | 0.9758 | 0.9789 |
| 0.0094 | 10.0 | 1450 | 0.0350 | 0.9820 | 0.9748 | 0.9784 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2