|
|
--- |
|
|
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: 1.3627 |
|
|
|
|
|
## 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: 2e-05 |
|
|
- 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 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 3.4755 | 0.04 | 100 | 3.3282 | |
|
|
| 2.6387 | 0.08 | 200 | 2.5958 | |
|
|
| 2.2721 | 0.12 | 300 | 2.2052 | |
|
|
| 2.0763 | 0.16 | 400 | 2.0273 | |
|
|
| 1.9119 | 0.2 | 500 | 1.9551 | |
|
|
| 1.8762 | 0.24 | 600 | 1.8490 | |
|
|
| 1.7392 | 0.28 | 700 | 1.7626 | |
|
|
| 1.7118 | 0.32 | 800 | 1.6842 | |
|
|
| 1.6537 | 0.36 | 900 | 1.6401 | |
|
|
| 1.5602 | 0.4 | 1000 | 1.5688 | |
|
|
| 1.5637 | 0.44 | 1100 | 1.5510 | |
|
|
| 1.5511 | 0.48 | 1200 | 1.5247 | |
|
|
| 1.5012 | 0.52 | 1300 | 1.5329 | |
|
|
| 1.5139 | 0.56 | 1400 | 1.4959 | |
|
|
| 1.4862 | 0.6 | 1500 | 1.4633 | |
|
|
| 1.4317 | 0.64 | 1600 | 1.4430 | |
|
|
| 1.3776 | 0.68 | 1700 | 1.4082 | |
|
|
| 1.3999 | 0.72 | 1800 | 1.3872 | |
|
|
| 1.4649 | 0.76 | 1900 | 1.3948 | |
|
|
| 1.3576 | 0.8 | 2000 | 1.3961 | |
|
|
| 1.3753 | 0.84 | 2100 | 1.3774 | |
|
|
| 1.3945 | 0.88 | 2200 | 1.3509 | |
|
|
| 1.4045 | 0.92 | 2300 | 1.3592 | |
|
|
| 1.4095 | 0.96 | 2400 | 1.3476 | |
|
|
| 1.3412 | 1.0 | 2500 | 1.3627 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.38.2 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.15.2 |
|
|
|
