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: 1.7383
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- 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: 100
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.9049 | 1.0 | 188 | 2.5666 |
| 2.6767 | 2.0 | 376 | 2.3807 |
| 2.3300 | 3.0 | 564 | 2.3843 |
| 2.1809 | 4.0 | 752 | 2.1590 |
| 1.9130 | 5.0 | 940 | 1.9457 |
| 1.8789 | 6.0 | 1128 | 1.8820 |
| 1.8412 | 7.0 | 1316 | 1.8455 |
| 1.7495 | 8.0 | 1504 | 1.8434 |
Framework versions
- Transformers 5.5.4
- Pytorch 2.10.0+cu128
- Datasets 4.8.4
- Tokenizers 0.22.2