detr-fashionpedia
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: 1.1716
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: 4
- eval_batch_size: 4
- 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
- lr_scheduler_warmup_steps: 200
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2544 | 1.0 | 375 | 1.9077 |
| 1.7553 | 2.0 | 750 | 1.6923 |
| 1.5305 | 3.0 | 1125 | 1.5401 |
| 1.5791 | 4.0 | 1500 | 1.4498 |
| 1.3828 | 5.0 | 1875 | 1.3846 |
| 1.3269 | 6.0 | 2250 | 1.2931 |
| 1.2617 | 7.0 | 2625 | 1.2597 |
| 1.2426 | 8.0 | 3000 | 1.2500 |
| 1.1980 | 9.0 | 3375 | 1.2199 |
| 1.2260 | 10.0 | 3750 | 1.2089 |
Framework versions
- Transformers 5.5.1
- Pytorch 2.5.1
- Datasets 4.8.4
- Tokenizers 0.22.2