metadata
library_name: transformers
license: apache-2.0
base_model: microsoft/conditional-detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: detr_finetuned_trashify_box_detector
results: []
detr_finetuned_trashify_box_detector
This model is a fine-tuned version of microsoft/conditional-detr-resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0728
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 25
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.6374 | 1.0 | 25 | 2.2767 |
| 2.3806 | 2.0 | 50 | 2.0779 |
| 2.17 | 3.0 | 75 | 1.8047 |
| 1.9959 | 4.0 | 100 | 1.7031 |
| 1.9129 | 5.0 | 125 | 1.6561 |
| 1.7917 | 6.0 | 150 | 1.5245 |
| 1.6619 | 7.0 | 175 | 1.4002 |
| 1.5913 | 8.0 | 200 | 1.3501 |
| 1.4466 | 9.0 | 225 | 1.2675 |
| 1.3785 | 10.0 | 250 | 1.2594 |
| 1.3542 | 11.0 | 275 | 1.2620 |
| 1.349 | 12.0 | 300 | 1.1957 |
| 1.3055 | 13.0 | 325 | 1.1818 |
| 1.1731 | 14.0 | 350 | 1.1466 |
| 1.1585 | 15.0 | 375 | 1.1627 |
| 1.0614 | 16.0 | 400 | 1.1615 |
| 1.0144 | 17.0 | 425 | 1.1411 |
| 0.967 | 18.0 | 450 | 1.1193 |
| 0.9114 | 19.0 | 475 | 1.1043 |
| 0.9031 | 20.0 | 500 | 1.1005 |
| 0.8719 | 21.0 | 525 | 1.1000 |
| 0.8505 | 22.0 | 550 | 1.0800 |
| 0.8314 | 23.0 | 575 | 1.0739 |
| 0.8178 | 24.0 | 600 | 1.0757 |
| 0.804 | 25.0 | 625 | 1.0728 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu124
- Datasets 2.21.0
- Tokenizers 0.19.1