metadata
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: detr-resnet-50_adamw_hf_epoch_finetuned_food-roboflow
results: []
detr-resnet-50_adamw_hf_epoch_finetuned_food-roboflow
This model is a fine-tuned version of facebook/detr-resnet-50 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 2.9613
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 33 | 3.4739 |
| 4.5266 | 2.0 | 66 | 3.4064 |
| 4.5266 | 3.0 | 99 | 3.2739 |
| 3.2133 | 4.0 | 132 | 3.3611 |
| 3.3196 | 5.0 | 165 | 3.1082 |
| 3.3196 | 6.0 | 198 | 3.2548 |
| 2.9882 | 7.0 | 231 | 3.2691 |
| 3.1559 | 8.0 | 264 | 3.2925 |
| 3.1559 | 9.0 | 297 | 3.1214 |
| 2.9855 | 10.0 | 330 | 3.0595 |
| 2.8269 | 11.0 | 363 | 3.0367 |
| 2.8269 | 12.0 | 396 | 3.0276 |
| 2.7938 | 13.0 | 429 | 3.0012 |
| 2.7678 | 14.0 | 462 | 2.9559 |
| 2.7678 | 15.0 | 495 | 2.9613 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1