detr-resnet-50_adafactor_finetuned_food-roboflow
This model is a fine-tuned version of facebook/detr-resnet-50 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 2.5062
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|
| 6.4038 | 1.52 | 50 | 5.7574 |
| 5.3942 | 3.03 | 100 | 4.7285 |
| 4.5081 | 4.55 | 150 | 3.8652 |
| 3.6495 | 6.06 | 200 | 3.0781 |
| 3.2792 | 7.58 | 250 | 2.8378 |
| 3.0286 | 9.09 | 300 | 2.6613 |
| 2.948 | 10.61 | 350 | 2.6172 |
| 2.8826 | 12.12 | 400 | 2.5483 |
| 2.7976 | 13.64 | 450 | 2.5062 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1