detr-r50-cd45rb-8ah-6l-dilation
This model is a fine-tuned version of facebook/detr-resnet-50 on the cd45rb dataset. It achieves the following results on the evaluation set:
- Loss: 1.5806
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.4271 | 1.0 | 4606 | 1.7687 |
| 2.1841 | 2.0 | 9212 | 1.7231 |
| 2.1186 | 3.0 | 13818 | 1.6876 |
| 2.1002 | 4.0 | 18424 | 1.6717 |
| 2.0655 | 5.0 | 23030 | 1.6498 |
| 2.0324 | 6.0 | 27636 | 1.6366 |
| 2.0121 | 7.0 | 32242 | 1.6028 |
| 1.9918 | 8.0 | 36848 | 1.5980 |
| 1.977 | 9.0 | 41454 | 1.5934 |
| 1.9625 | 10.0 | 46060 | 1.5806 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3