<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
detr-r50-cd45rb-8ah-6l-128d
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: 3.4100
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 |
|---|---|---|---|
| 4.1894 | 1.0 | 4606 | 3.9730 |
| 3.4275 | 2.0 | 9212 | 3.5463 |
| 3.3617 | 3.0 | 13818 | 3.6702 |
| 3.3349 | 4.0 | 18424 | 3.2565 |
| 3.3174 | 5.0 | 23030 | 3.3137 |
| 3.2912 | 6.0 | 27636 | 3.6149 |
| 3.2733 | 7.0 | 32242 | 3.5332 |
| 3.2614 | 8.0 | 36848 | 3.5219 |
| 3.2479 | 9.0 | 41454 | 3.4650 |
| 3.2358 | 10.0 | 46060 | 3.4100 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
