detr_finetuned_roadsigns_poisoned
This model is a fine-tuned version of Jesse020202/detr_finetuned_roadsigns on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7780
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: 8
- eval_batch_size: 8
- 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: 25
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 35 | 1.0743 |
| No log | 2.0 | 70 | 1.0560 |
| No log | 3.0 | 105 | 0.9479 |
| No log | 4.0 | 140 | 0.8907 |
| No log | 5.0 | 175 | 0.9357 |
| No log | 6.0 | 210 | 0.9149 |
| No log | 7.0 | 245 | 0.9574 |
| No log | 8.0 | 280 | 0.9942 |
| No log | 9.0 | 315 | 0.8970 |
| No log | 10.0 | 350 | 0.8994 |
| No log | 11.0 | 385 | 0.8997 |
| No log | 12.0 | 420 | 0.8442 |
| No log | 13.0 | 455 | 0.8805 |
| No log | 14.0 | 490 | 0.8440 |
| 0.9464 | 15.0 | 525 | 0.8098 |
| 0.9464 | 16.0 | 560 | 0.8108 |
| 0.9464 | 17.0 | 595 | 0.8385 |
| 0.9464 | 18.0 | 630 | 0.8016 |
| 0.9464 | 19.0 | 665 | 0.8070 |
| 0.9464 | 20.0 | 700 | 0.7925 |
| 0.9464 | 21.0 | 735 | 0.7861 |
| 0.9464 | 22.0 | 770 | 0.7869 |
| 0.9464 | 23.0 | 805 | 0.7721 |
| 0.9464 | 24.0 | 840 | 0.7776 |
| 0.9464 | 25.0 | 875 | 0.7780 |
Framework versions
- Transformers 4.56.2
- Pytorch 2.8.0
- Datasets 4.1.1
- Tokenizers 0.22.1