metadata
library_name: transformers
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: imgdetection_model
results: []
imgdetection_model
This model is a fine-tuned version of facebook/detr-resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2611
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 17
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.4992 | 1.0 | 75 | 2.4205 |
| 2.0497 | 2.0 | 150 | 1.9037 |
| 1.7749 | 3.0 | 225 | 1.6897 |
| 1.6143 | 4.0 | 300 | 1.5540 |
| 1.5326 | 5.0 | 375 | 1.4655 |
| 1.468 | 6.0 | 450 | 1.3991 |
| 1.4381 | 7.0 | 525 | 1.4099 |
| 1.4019 | 8.0 | 600 | 1.3662 |
| 1.3626 | 9.0 | 675 | 1.3520 |
| 1.3426 | 10.0 | 750 | 1.3188 |
| 1.3249 | 11.0 | 825 | 1.2764 |
| 1.2988 | 12.0 | 900 | 1.2777 |
| 1.288 | 13.0 | 975 | 1.2534 |
| 1.2687 | 14.0 | 1050 | 1.2531 |
| 1.2655 | 15.0 | 1125 | 1.2834 |
| 1.2692 | 16.0 | 1200 | 1.2308 |
| 1.2642 | 17.0 | 1275 | 1.2403 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1