detr-resnet50-cd45rb-subdataset
This model is a fine-tuned version of facebook/detr-resnet-50 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.7267
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.774 | 1.0 | 242 | 2.9629 |
| 3.6768 | 2.0 | 484 | 2.8229 |
| 3.6554 | 3.0 | 726 | 2.8255 |
| 3.5964 | 4.0 | 968 | 2.8284 |
| 3.5668 | 5.0 | 1210 | 2.7503 |
| 3.5733 | 6.0 | 1452 | 2.7553 |
| 3.5197 | 7.0 | 1694 | 2.7467 |
| 3.5313 | 8.0 | 1936 | 2.7521 |
| 3.4862 | 9.0 | 2178 | 2.7275 |
| 3.503 | 10.0 | 2420 | 2.7267 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0
- Datasets 2.10.0
- Tokenizers 0.13.2