metadata
library_name: transformers
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: results
results: []
results
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: 1.1121
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: 8
- eval_batch_size: 8
- 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5219 | 1.0 | 150 | 1.5095 |
| 1.4556 | 2.0 | 300 | 1.4327 |
| 1.377 | 3.0 | 450 | 1.3390 |
| 1.3398 | 4.0 | 600 | 1.2920 |
| 1.3035 | 5.0 | 750 | 1.2615 |
| 1.2632 | 6.0 | 900 | 1.2491 |
| 1.2236 | 7.0 | 1050 | 1.2270 |
| 1.2066 | 8.0 | 1200 | 1.2137 |
| 1.1853 | 9.0 | 1350 | 1.1804 |
| 1.1686 | 10.0 | 1500 | 1.1939 |
| 1.1531 | 11.0 | 1650 | 1.1614 |
| 1.1388 | 12.0 | 1800 | 1.1582 |
| 1.1157 | 13.0 | 1950 | 1.1663 |
| 1.0953 | 14.0 | 2100 | 1.1516 |
| 1.0903 | 15.0 | 2250 | 1.1507 |
| 1.0834 | 16.0 | 2400 | 1.1479 |
| 1.0779 | 17.0 | 2550 | 1.1305 |
| 1.0651 | 18.0 | 2700 | 1.1332 |
| 1.0607 | 19.0 | 2850 | 1.1350 |
| 1.0567 | 20.0 | 3000 | 1.1380 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1