metadata
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: detr-resnet-50_finetuned_detect-waste
results: []
detr-resnet-50_finetuned_detect-waste
This model is a fine-tuned version of facebook/detr-resnet-50 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5678
- Dummy: 1
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Dummy |
|---|---|---|---|---|
| 2.4218 | 5.26 | 500 | 2.0445 | 1 |
| 2.269 | 10.53 | 1000 | 1.9227 | 1 |
| 1.9898 | 15.79 | 1500 | 1.7609 | 1 |
| 2.0422 | 21.05 | 2000 | 1.6763 | 1 |
| 2.1387 | 26.32 | 2500 | 1.7746 | 1 |
| 1.8163 | 31.58 | 3000 | 1.6525 | 1 |
| 1.7993 | 36.84 | 3500 | 1.6010 | 1 |
| 1.8009 | 42.11 | 4000 | 1.5959 | 1 |
| 1.8148 | 47.37 | 4500 | 1.5332 | 1 |
| 1.7837 | 52.63 | 5000 | 1.5525 | 1 |
| 1.5934 | 57.89 | 5500 | 1.5409 | 1 |
| 1.5357 | 63.16 | 6000 | 1.5678 | 1 |
Framework versions
- Transformers 4.33.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3