deta-cd45rb-4ah-4l
This model is a fine-tuned version of jozhang97/deta-swin-large on the cd45rb_nan_xywh dataset. It achieves the following results on the evaluation set:
- Loss: 4.3723
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-06
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.8838 | 1.0 | 4606 | 5.5818 |
| 4.3326 | 2.0 | 9212 | 5.5327 |
| 4.3118 | 3.0 | 13818 | 5.3539 |
| 4.1978 | 4.0 | 18424 | 5.1552 |
| 4.0235 | 5.0 | 23030 | 4.9679 |
| 3.9038 | 6.0 | 27636 | 4.7824 |
| 3.8628 | 7.0 | 32242 | 4.5919 |
| 3.7967 | 8.0 | 36848 | 4.4415 |
| 3.7638 | 9.0 | 41454 | 4.4006 |
| 3.7538 | 10.0 | 46060 | 4.3723 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 5