metadata
library_name: transformers
license: apache-2.0
base_model: microsoft/conditional-detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: detr_finetuned_trashify_box_detector_with_data_aug
results: []
detr_finetuned_trashify_box_detector_with_data_aug
This model is a fine-tuned version of microsoft/conditional-detr-resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0875
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 25
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 80.0272 | 1.0 | 50 | 8.2323 |
| 4.2154 | 2.0 | 100 | 2.7596 |
| 2.5841 | 3.0 | 150 | 2.2609 |
| 2.2857 | 4.0 | 200 | 2.1303 |
| 2.1495 | 5.0 | 250 | 1.8199 |
| 1.9145 | 6.0 | 300 | 1.6257 |
| 1.8117 | 7.0 | 350 | 1.4758 |
| 1.6692 | 8.0 | 400 | 1.4397 |
| 1.6048 | 9.0 | 450 | 1.3883 |
| 1.517 | 10.0 | 500 | 1.3472 |
| 1.4842 | 11.0 | 550 | 1.2953 |
| 1.3999 | 12.0 | 600 | 1.2637 |
| 1.3551 | 13.0 | 650 | 1.2034 |
| 1.3283 | 14.0 | 700 | 1.1875 |
| 1.2783 | 15.0 | 750 | 1.1679 |
| 1.2577 | 16.0 | 800 | 1.1578 |
| 1.1815 | 17.0 | 850 | 1.1271 |
| 1.1911 | 18.0 | 900 | 1.1192 |
| 1.1307 | 19.0 | 950 | 1.1172 |
| 1.1604 | 20.0 | 1000 | 1.1065 |
| 1.1365 | 21.0 | 1050 | 1.1013 |
| 1.1287 | 22.0 | 1100 | 1.0867 |
| 1.1201 | 23.0 | 1150 | 1.0822 |
| 1.1075 | 24.0 | 1200 | 1.0890 |
| 1.1138 | 25.0 | 1250 | 1.0875 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu124
- Datasets 2.21.0
- Tokenizers 0.19.1