detr-r50-cd45rb-all-4ah-learned
This model is a fine-tuned version of facebook/detr-resnet-50 on the cd45rb dataset. It achieves the following results on the evaluation set:
- Loss: 1.6174
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3714 | 1.0 | 2303 | 1.8496 |
| 2.1897 | 2.0 | 4606 | 1.7683 |
| 2.1158 | 3.0 | 6909 | 1.7291 |
| 2.094 | 4.0 | 9212 | 1.7164 |
| 2.0641 | 5.0 | 11515 | 1.6844 |
| 2.0412 | 6.0 | 13818 | 1.6850 |
| 2.02 | 7.0 | 16121 | 1.6659 |
| 2.0152 | 8.0 | 18424 | 1.6612 |
| 2.0025 | 9.0 | 20727 | 1.6457 |
| 1.9883 | 10.0 | 23030 | 1.6432 |
| 2.0007 | 11.0 | 25333 | 1.6537 |
| 1.9995 | 12.0 | 27636 | 1.6644 |
| 1.9892 | 13.0 | 29939 | 1.6488 |
| 1.9875 | 14.0 | 32242 | 1.6492 |
| 1.9722 | 15.0 | 34545 | 1.6327 |
| 1.969 | 16.0 | 36848 | 1.6258 |
| 1.9571 | 17.0 | 39151 | 1.6252 |
| 1.9524 | 18.0 | 41454 | 1.6218 |
| 1.9415 | 19.0 | 43757 | 1.6195 |
| 1.9433 | 20.0 | 46060 | 1.6174 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3