metadata
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: detr
results: []
detr
This model is a fine-tuned version of facebook/detr-resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8164
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: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 0.05
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2214 | 0.01 | 25 | 2.3644 |
| 2.21 | 0.01 | 50 | 2.1607 |
| 2.0636 | 0.01 | 75 | 2.1884 |
| 2.1722 | 0.02 | 100 | 2.3081 |
| 2.3687 | 0.03 | 125 | 1.9743 |
| 2.0154 | 0.03 | 150 | 1.9790 |
| 1.8828 | 0.04 | 175 | 1.9207 |
| 1.9719 | 0.04 | 200 | 1.8296 |
| 1.7973 | 0.04 | 225 | 1.8404 |
| 1.687 | 0.05 | 250 | 1.8164 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2