rtdetrv2-floorplancad-doors
This model is a fine-tuned version of PekingU/rtdetr_v2_r18vd on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.2426
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
- num_epochs: 6.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 9.7688 | 0.3444 | 250 | 6.3036 |
| 7.7611 | 0.6887 | 500 | 5.2379 |
| 6.6111 | 1.0331 | 750 | 4.6810 |
| 6.5456 | 1.3774 | 1000 | 4.5544 |
| 6.6030 | 1.7218 | 1250 | 4.5780 |
| 6.0246 | 2.0661 | 1500 | 4.4291 |
| 6.7210 | 2.4105 | 1750 | 4.4532 |
| 5.8983 | 2.7548 | 2000 | 4.4589 |
| 5.5833 | 3.0992 | 2250 | 4.3699 |
| 5.5880 | 3.4435 | 2500 | 4.3238 |
| 5.6837 | 3.7879 | 2750 | 4.3332 |
| 5.4763 | 4.1322 | 3000 | 4.2348 |
| 5.6179 | 4.4766 | 3250 | 4.2787 |
| 5.9673 | 4.8209 | 3500 | 4.2613 |
| 6.1563 | 5.1653 | 3750 | 4.2550 |
| 5.8983 | 5.5096 | 4000 | 4.2712 |
| 5.1829 | 5.8540 | 4250 | 4.2598 |
| 5.8721 | 6.0 | 4356 | 4.2426 |
Framework versions
- Transformers 5.6.2
- Pytorch 2.11.0+cu130
- Datasets 4.8.4
- Tokenizers 0.22.2
- Downloads last month
- 22
Model tree for joshlyman/rtdetrv2-floorplancad-doors
Base model
PekingU/rtdetr_v2_r18vd