|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: facebook/detr-resnet-50 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: detr |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# detr |
|
|
|
|
|
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.7117 |
|
|
|
|
|
## 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: 4 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
|
| 2.0345 | 0.08 | 200 | 1.8447 | |
|
|
| 1.5511 | 0.16 | 400 | 1.4217 | |
|
|
| 1.444 | 0.24 | 600 | 1.3814 | |
|
|
| 1.3746 | 0.32 | 800 | 1.3241 | |
|
|
| 1.2361 | 0.4 | 1000 | 1.2589 | |
|
|
| 1.3506 | 0.48 | 1200 | 1.2441 | |
|
|
| 1.2833 | 0.56 | 1400 | 1.2052 | |
|
|
| 1.1051 | 0.64 | 1600 | 1.0607 | |
|
|
| 1.1091 | 0.72 | 1800 | 1.0610 | |
|
|
| 1.0295 | 0.8 | 2000 | 1.0241 | |
|
|
| 1.1376 | 0.88 | 2200 | 1.0846 | |
|
|
| 1.1172 | 0.96 | 2400 | 1.1095 | |
|
|
| 1.0186 | 1.04 | 2600 | 0.9978 | |
|
|
| 1.0775 | 1.12 | 2800 | 1.0225 | |
|
|
| 0.9973 | 1.2 | 3000 | 0.9934 | |
|
|
| 1.006 | 1.28 | 3200 | 0.9886 | |
|
|
| 0.9814 | 1.36 | 3400 | 0.9256 | |
|
|
| 1.0253 | 1.44 | 3600 | 0.9209 | |
|
|
| 0.9932 | 1.52 | 3800 | 0.9159 | |
|
|
| 0.9307 | 1.6 | 4000 | 0.9058 | |
|
|
| 0.9103 | 1.68 | 4200 | 0.9049 | |
|
|
| 0.9034 | 1.76 | 4400 | 0.8643 | |
|
|
| 0.9544 | 1.84 | 4600 | 0.9114 | |
|
|
| 0.889 | 1.92 | 4800 | 0.8880 | |
|
|
| 0.8888 | 2.0 | 5000 | 0.8515 | |
|
|
| 0.8877 | 2.08 | 5200 | 0.8707 | |
|
|
| 0.8799 | 2.16 | 5400 | 0.8458 | |
|
|
| 0.8398 | 2.24 | 5600 | 0.8292 | |
|
|
| 0.8181 | 2.32 | 5800 | 0.8226 | |
|
|
| 0.8876 | 2.4 | 6000 | 0.8021 | |
|
|
| 0.8893 | 2.48 | 6200 | 0.8173 | |
|
|
| 0.8497 | 2.56 | 6400 | 0.7870 | |
|
|
| 0.8369 | 2.64 | 6600 | 0.7719 | |
|
|
| 0.8213 | 2.72 | 6800 | 0.7877 | |
|
|
| 0.8044 | 2.8 | 7000 | 0.7763 | |
|
|
| 0.8087 | 2.88 | 7200 | 0.7702 | |
|
|
| 0.7616 | 2.96 | 7400 | 0.7570 | |
|
|
| 0.7901 | 3.04 | 7600 | 0.7451 | |
|
|
| 0.8454 | 3.12 | 7800 | 0.7560 | |
|
|
| 0.7428 | 3.2 | 8000 | 0.7455 | |
|
|
| 0.822 | 3.28 | 8200 | 0.7390 | |
|
|
| 0.8293 | 3.36 | 8400 | 0.7324 | |
|
|
| 0.7196 | 3.44 | 8600 | 0.7270 | |
|
|
| 0.7508 | 3.52 | 8800 | 0.7357 | |
|
|
| 0.783 | 3.6 | 9000 | 0.7293 | |
|
|
| 0.7094 | 3.68 | 9200 | 0.7276 | |
|
|
| 0.7811 | 3.76 | 9400 | 0.7178 | |
|
|
| 0.7765 | 3.84 | 9600 | 0.7129 | |
|
|
| 0.7542 | 3.92 | 9800 | 0.7165 | |
|
|
| 0.756 | 4.0 | 10000 | 0.7117 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.39.3 |
|
|
- Pytorch 2.1.2 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.15.2 |
|
|
|
