detr-resnet-50-base-coco
This model is a fine-tuned version of facebook/detr-resnet-50 on the detection-datasets/coco dataset. It achieves the following results on the evaluation set:
- Loss: 5.2641
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 4 | 5.5331 |
| No log | 2.0 | 8 | 5.5277 |
| 5.4377 | 3.0 | 12 | 5.4450 |
| 5.4377 | 4.0 | 16 | 5.3960 |
| 5.1582 | 5.0 | 20 | 5.3349 |
| 5.1582 | 6.0 | 24 | 5.3144 |
| 5.1582 | 7.0 | 28 | 5.2738 |
| 5.0556 | 8.0 | 32 | 5.2641 |
| 5.0556 | 9.0 | 36 | 5.2848 |
| 4.9784 | 10.0 | 40 | 5.2792 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.0+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 13