metadata
library_name: transformers
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: raccoon_detector
results: []
raccoon_detector
This model is a fine-tuned version of facebook/detr-resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4696
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 40 | 1.2814 |
| No log | 2.0 | 80 | 1.1424 |
| No log | 3.0 | 120 | 0.9869 |
| No log | 4.0 | 160 | 0.9042 |
| No log | 5.0 | 200 | 0.7036 |
| No log | 6.0 | 240 | 0.7302 |
| No log | 7.0 | 280 | 0.6320 |
| No log | 8.0 | 320 | 0.5814 |
| No log | 9.0 | 360 | 0.5468 |
| No log | 10.0 | 400 | 0.5419 |
| No log | 11.0 | 440 | 0.5130 |
| No log | 12.0 | 480 | 0.5220 |
| 0.8899 | 13.0 | 520 | 0.5162 |
| 0.8899 | 14.0 | 560 | 0.5061 |
| 0.8899 | 15.0 | 600 | 0.5066 |
| 0.8899 | 16.0 | 640 | 0.4785 |
| 0.8899 | 17.0 | 680 | 0.4817 |
| 0.8899 | 18.0 | 720 | 0.4782 |
| 0.8899 | 19.0 | 760 | 0.4873 |
| 0.8899 | 20.0 | 800 | 0.4696 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1