detr-r50-cd45rb-8ah-4l-attdrop02
This model is a fine-tuned version of facebook/detr-resnet-50 on the cd45rb_nan_xywh dataset. It achieves the following results on the evaluation set:
- Loss: 2.3955
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 |
---|---|---|---|
3.6528 | 1.0 | 4606 | 2.7772 |
3.3969 | 2.0 | 9212 | 2.6612 |
3.2937 | 3.0 | 13818 | 2.5696 |
3.2385 | 4.0 | 18424 | 2.5185 |
3.1884 | 5.0 | 23030 | 2.4789 |
3.1504 | 6.0 | 27636 | 2.4483 |
3.1188 | 7.0 | 32242 | 2.4247 |
3.0975 | 8.0 | 36848 | 2.4002 |
3.0858 | 9.0 | 41454 | 2.3913 |
3.0788 | 10.0 | 46060 | 2.3955 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 31
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.