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: 1.1048
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 50
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2940 | 1.0 | 75 | 1.2525 |
| 1.2645 | 2.0 | 150 | 1.1964 |
| 1.2238 | 3.0 | 225 | 1.1464 |
| 1.1928 | 4.0 | 300 | 1.1165 |
| 1.2381 | 5.0 | 375 | 1.1464 |
| 1.1490 | 6.0 | 450 | 1.0756 |
| 1.1375 | 7.0 | 525 | 1.1150 |
| 1.1097 | 8.0 | 600 | 1.0882 |
| 1.1072 | 9.0 | 675 | 1.0612 |
| 1.0850 | 10.0 | 750 | 1.0515 |
| 1.0477 | 11.0 | 825 | 1.0348 |
| 1.0293 | 12.0 | 900 | 1.0370 |
| 1.0273 | 13.0 | 975 | 1.0373 |
| 1.0246 | 14.0 | 1050 | 1.0337 |
| 1.0298 | 15.0 | 1125 | 1.0270 |
Framework versions
- Transformers 5.5.4
- Pytorch 2.10.0+cu128
- Datasets 4.8.4
- Tokenizers 0.22.2