cdetr-cd45rb-s
This model is a fine-tuned version of microsoft/conditional-detr-resnet-50 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0136
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 |
|---|---|---|---|
| 2.6006 | 1.0 | 242 | 2.2146 |
| 2.2409 | 2.0 | 484 | 2.1106 |
| 2.2027 | 3.0 | 726 | 2.1456 |
| 2.183 | 4.0 | 968 | 2.0863 |
| 2.0628 | 5.0 | 1210 | 2.0294 |
| 2.1588 | 6.0 | 1452 | 2.0859 |
| 2.1731 | 7.0 | 1694 | 2.0731 |
| 2.1041 | 8.0 | 1936 | 2.1052 |
| 2.0383 | 9.0 | 2178 | 2.0378 |
| 1.967 | 10.0 | 2420 | 2.0136 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3