metadata
library_name: transformers
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: results
results: []
results
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: 1.1423
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: 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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 2 | 5.4207 |
| No log | 2.0 | 4 | 3.5959 |
| No log | 3.0 | 6 | 2.6546 |
| No log | 4.0 | 8 | 2.5924 |
| 4.7135 | 5.0 | 10 | 2.4246 |
| 4.7135 | 6.0 | 12 | 2.3156 |
| 4.7135 | 7.0 | 14 | 2.0630 |
| 4.7135 | 8.0 | 16 | 1.8700 |
| 4.7135 | 9.0 | 18 | 1.9057 |
| 1.9751 | 10.0 | 20 | 1.8555 |
| 1.9751 | 11.0 | 22 | 1.7879 |
| 1.9751 | 12.0 | 24 | 1.6941 |
| 1.9751 | 13.0 | 26 | 1.6313 |
| 1.9751 | 14.0 | 28 | 1.5788 |
| 1.6067 | 15.0 | 30 | 1.5095 |
| 1.6067 | 16.0 | 32 | 1.4926 |
| 1.6067 | 17.0 | 34 | 1.3962 |
| 1.6067 | 18.0 | 36 | 1.3799 |
| 1.6067 | 19.0 | 38 | 1.4024 |
| 1.3628 | 20.0 | 40 | 1.3731 |
| 1.3628 | 21.0 | 42 | 1.3351 |
| 1.3628 | 22.0 | 44 | 1.2939 |
| 1.3628 | 23.0 | 46 | 1.3056 |
| 1.3628 | 24.0 | 48 | 1.2118 |
| 1.2051 | 25.0 | 50 | 1.1925 |
| 1.2051 | 26.0 | 52 | 1.1810 |
| 1.2051 | 27.0 | 54 | 1.1621 |
| 1.2051 | 28.0 | 56 | 1.1491 |
| 1.2051 | 29.0 | 58 | 1.1433 |
| 1.0991 | 30.0 | 60 | 1.1423 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1