---
library_name: transformers
license: apache-2.0
base_model: facebook/deformable-detr-detic
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: fisheye8k_facebook_deformable-detr-detic
  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. -->

# fisheye8k_facebook_deformable-detr-detic

This model is a fine-tuned version of [facebook/deformable-detr-detic](https://huggingface.co/facebook/deformable-detr-detic) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 3.1187

## 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: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 0
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 30
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 2.8068        | 1.0   | 5288  | 3.0866          |
| 2.5985        | 2.0   | 10576 | 2.7970          |
| 2.368         | 3.0   | 15864 | 2.5671          |
| 2.531         | 4.0   | 21152 | 3.0914          |
| 2.2468        | 5.0   | 26440 | 2.8550          |
| 2.3968        | 6.0   | 31728 | 3.0002          |
| 2.2204        | 7.0   | 37016 | 2.4807          |
| 2.0661        | 8.0   | 42304 | 2.4539          |
| 2.2947        | 9.0   | 47592 | 2.7481          |
| 2.3046        | 10.0  | 52880 | 2.9592          |
| 2.5026        | 11.0  | 58168 | 2.9560          |
| 2.4076        | 12.0  | 63456 | 2.9273          |
| 2.4247        | 13.0  | 68744 | 3.1187          |


### Framework versions

- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0