--- library_name: transformers license: apache-2.0 base_model: facebook/detr-resnet-50 tags: - generated_from_trainer model-index: - name: chickens results: [] --- # chickens This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.6675 ## 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: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - num_epochs: 30 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | No log | 1.0 | 13 | 0.9785 | | No log | 2.0 | 26 | 0.9392 | | 1.1336 | 3.0 | 39 | 0.8768 | | 1.1336 | 4.0 | 52 | 0.8375 | | 0.9422 | 5.0 | 65 | 0.8428 | | 0.9422 | 6.0 | 78 | 0.8161 | | 0.8703 | 7.0 | 91 | 0.7947 | | 0.8703 | 8.0 | 104 | 0.7691 | | 0.8703 | 9.0 | 117 | 0.7788 | | 0.8332 | 10.0 | 130 | 0.7683 | | 0.8332 | 11.0 | 143 | 0.7432 | | 0.7978 | 12.0 | 156 | 0.7431 | | 0.7978 | 13.0 | 169 | 0.7229 | | 0.7796 | 14.0 | 182 | 0.7483 | | 0.7796 | 15.0 | 195 | 0.7237 | | 0.7796 | 16.0 | 208 | 0.7092 | | 0.7763 | 17.0 | 221 | 0.7036 | | 0.7763 | 18.0 | 234 | 0.7014 | | 0.749 | 19.0 | 247 | 0.6938 | | 0.749 | 20.0 | 260 | 0.6885 | | 0.742 | 21.0 | 273 | 0.6886 | | 0.742 | 22.0 | 286 | 0.6793 | | 0.742 | 23.0 | 299 | 0.6723 | | 0.7268 | 24.0 | 312 | 0.6708 | | 0.7268 | 25.0 | 325 | 0.6694 | | 0.7258 | 26.0 | 338 | 0.6672 | | 0.7258 | 27.0 | 351 | 0.6674 | | 0.7074 | 28.0 | 364 | 0.6673 | | 0.7074 | 29.0 | 377 | 0.6671 | | 0.7168 | 30.0 | 390 | 0.6675 | ### Framework versions - Transformers 4.44.2 - Pytorch 2.4.1+cu121 - Datasets 2.14.4 - Tokenizers 0.19.1