metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- cd45rb
model-index:
- name: detr-r50-cd45rb-all-1ah
results: []
detr-r50-cd45rb-all-1ah
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: 1.6472
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.4098 | 1.0 | 2303 | 1.8950 |
| 2.1885 | 2.0 | 4606 | 1.8041 |
| 2.1283 | 3.0 | 6909 | 1.7426 |
| 2.0899 | 4.0 | 9212 | 1.7135 |
| 2.0724 | 5.0 | 11515 | 1.6893 |
| 2.0495 | 6.0 | 13818 | 1.6910 |
| 2.0379 | 7.0 | 16121 | 1.6886 |
| 2.0203 | 8.0 | 18424 | 1.6616 |
| 2.0067 | 9.0 | 20727 | 1.6534 |
| 1.9953 | 10.0 | 23030 | 1.6472 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3