<!-- 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-all-2ah
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: 1.6025
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.4038 | 1.0 | 2303 | 1.8661 |
| 2.1781 | 2.0 | 4606 | 1.7985 |
| 2.1368 | 3.0 | 6909 | 1.8164 |
| 2.1048 | 4.0 | 9212 | 1.7115 |
| 2.0891 | 5.0 | 11515 | 1.7121 |
| 2.0525 | 6.0 | 13818 | 1.7282 |
| 2.0546 | 7.0 | 16121 | 1.6930 |
| 2.0401 | 8.0 | 18424 | 1.6876 |
| 2.019 | 9.0 | 20727 | 1.6599 |
| 2.011 | 10.0 | 23030 | 1.6661 |
| 1.9971 | 11.0 | 25333 | 1.6714 |
| 1.9929 | 12.0 | 27636 | 1.6486 |
| 1.9805 | 13.0 | 29939 | 1.6352 |
| 1.9738 | 14.0 | 32242 | 1.6336 |
| 1.9625 | 15.0 | 34545 | 1.6401 |
| 1.9645 | 16.0 | 36848 | 1.6302 |
| 1.9459 | 17.0 | 39151 | 1.6107 |
| 1.9364 | 18.0 | 41454 | 1.6078 |
| 1.9271 | 19.0 | 43757 | 1.6064 |
| 1.9301 | 20.0 | 46060 | 1.6025 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
