---
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: 5.4000

## 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: 0.0005
- 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: 1
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.4552        | 0.04  | 100  | 5.8812          |
| 3.0646        | 0.08  | 200  | 6.1299          |
| 2.8724        | 0.12  | 300  | 5.4912          |
| 2.7418        | 0.16  | 400  | 6.3882          |
| 2.6577        | 0.2   | 500  | 5.5691          |
| 2.5283        | 0.24  | 600  | 5.7357          |
| 2.4574        | 0.28  | 700  | 5.6403          |
| 2.3614        | 0.32  | 800  | 5.4325          |
| 2.342         | 0.36  | 900  | 6.4478          |
| 2.3154        | 0.4   | 1000 | 5.8527          |
| 2.3305        | 0.44  | 1100 | 5.8006          |
| 2.2296        | 0.48  | 1200 | 5.5432          |
| 2.2821        | 0.52  | 1300 | 5.3882          |
| 2.2623        | 0.56  | 1400 | 5.3867          |
| 2.1653        | 0.6   | 1500 | 5.9831          |
| 2.1729        | 0.64  | 1600 | 5.5752          |
| 2.1155        | 0.68  | 1700 | 5.4664          |
| 2.094         | 0.72  | 1800 | 5.5329          |
| 2.0948        | 0.76  | 1900 | 5.4304          |
| 1.9956        | 0.8   | 2000 | 5.9376          |
| 2.0062        | 0.84  | 2100 | 5.7035          |
| 2.0472        | 0.88  | 2200 | 5.4439          |
| 2.0699        | 0.92  | 2300 | 5.3537          |
| 1.9993        | 0.96  | 2400 | 5.3219          |
| 1.9494        | 1.0   | 2500 | 5.4000          |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2