|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: detr-resnet50-cd45rb |
|
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-resnet50-cd45rb |
|
|
|
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.7418 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 3.8886 | 1.0 | 242 | 2.8754 | |
|
| 3.6406 | 2.0 | 484 | 2.7956 | |
|
| 3.6109 | 3.0 | 726 | 2.8412 | |
|
| 3.5724 | 4.0 | 968 | 2.7906 | |
|
| 3.5492 | 5.0 | 1210 | 2.7473 | |
|
| 3.5595 | 6.0 | 1452 | 2.7594 | |
|
| 3.5249 | 7.0 | 1694 | 2.7396 | |
|
| 3.524 | 8.0 | 1936 | 2.7562 | |
|
| 3.4908 | 9.0 | 2178 | 2.7345 | |
|
| 3.5149 | 10.0 | 2420 | 2.7418 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.10.0 |
|
- Tokenizers 0.13.2 |
|
|
