metadata
license: apache-2.0
base_model: qgyd2021/detr_cppe5_object_detection
tags:
- generated_from_trainer
datasets:
- cppe5
model-index:
- name: detr_cppe5_object_detection
results: []
detr_cppe5_object_detection
This model is a fine-tuned version of qgyd2021/detr_cppe5_object_detection on the cppe5 dataset. It achieves the following results on the evaluation set:
- Loss: 1.0498
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
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 16
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9924 | 3.17 | 200 | 1.0855 |
| 0.9863 | 6.35 | 400 | 1.1051 |
| 0.9099 | 9.52 | 600 | 1.1780 |
| 0.8853 | 12.7 | 800 | 1.0780 |
| 0.907 | 15.87 | 1000 | 1.0617 |
| 0.8919 | 19.05 | 1200 | 1.0444 |
| 0.8687 | 22.22 | 1400 | 1.0967 |
| 0.8559 | 25.4 | 1600 | 1.0865 |
| 0.8158 | 28.57 | 1800 | 1.0498 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3