detr-resnet-101_adagrad_finetuned_food-roboflow
This model is a fine-tuned version of facebook/detr-resnet-101 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 5.9027
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: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.708 | 0.77 | 50 | 6.6090 |
| 6.2622 | 1.54 | 100 | 6.3841 |
| 6.1083 | 2.31 | 150 | 6.3279 |
| 6.1302 | 3.08 | 200 | 6.1396 |
| 6.0668 | 3.85 | 250 | 6.1742 |
| 5.9788 | 4.62 | 300 | 6.1002 |
| 5.9065 | 5.38 | 350 | 6.0478 |
| 5.8597 | 6.15 | 400 | 5.9363 |
| 5.8188 | 6.92 | 450 | 5.9914 |
| 5.7599 | 7.69 | 500 | 5.8783 |
| 5.6732 | 8.46 | 550 | 5.9710 |
| 5.743 | 9.23 | 600 | 6.0130 |
| 5.6341 | 10.0 | 650 | 5.8789 |
| 5.6265 | 10.77 | 700 | 5.8644 |
| 5.7164 | 11.54 | 750 | 5.9142 |
| 5.6104 | 12.31 | 800 | 5.9677 |
| 5.6572 | 13.08 | 850 | 5.8372 |
| 5.7094 | 13.85 | 900 | 5.8269 |
| 5.7456 | 14.62 | 950 | 5.9027 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1