detr-fashionpedia-finetune
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: 1.0765
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: 4
- eval_batch_size: 4
- seed: 42
- 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: cosine
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1505 | 1.0 | 375 | 1.8976 |
| 1.6779 | 2.0 | 750 | 1.6688 |
| 1.6621 | 3.0 | 1125 | 1.5830 |
| 1.4466 | 4.0 | 1500 | 1.4593 |
| 1.3566 | 5.0 | 1875 | 1.3623 |
| 1.2979 | 6.0 | 2250 | 1.2112 |
| 1.1717 | 7.0 | 2625 | 1.1591 |
| 1.1899 | 8.0 | 3000 | 1.1542 |
Framework versions
- Transformers 5.5.4
- Pytorch 2.10.0+cu128
- Datasets 4.8.4
- Tokenizers 0.22.2