|
|
--- |
|
|
license: apache-2.0 |
|
|
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: 1.1718 |
|
|
|
|
|
## 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: 32 |
|
|
- 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 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 3.5147 | 0.1 | 32 | 2.4506 | |
|
|
| 2.1248 | 0.2 | 64 | 1.9658 | |
|
|
| 1.8119 | 0.31 | 96 | 1.6541 | |
|
|
| 1.5421 | 0.41 | 128 | 1.4391 | |
|
|
| 1.4124 | 0.51 | 160 | 1.3225 | |
|
|
| 1.3227 | 0.61 | 192 | 1.2518 | |
|
|
| 1.2811 | 0.72 | 224 | 1.2108 | |
|
|
| 1.2499 | 0.82 | 256 | 1.1863 | |
|
|
| 1.2102 | 0.92 | 288 | 1.1718 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.30.2 |
|
|
- Pytorch 2.2.2+cu121 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
