metadata
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: detr-resnet-50_finetuned_swny
results: []
detr-resnet-50_finetuned_swny
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: 1.7504
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.6587 | 4.7619 | 100 | 5.5964 |
| 4.3793 | 9.5238 | 200 | 3.8578 |
| 3.4828 | 14.2857 | 300 | 3.2121 |
| 2.8371 | 19.0476 | 400 | 2.6974 |
| 2.3745 | 23.8095 | 500 | 2.3697 |
| 2.0983 | 28.5714 | 600 | 2.0374 |
| 1.995 | 33.3333 | 700 | 2.0759 |
| 1.8153 | 38.0952 | 800 | 1.9295 |
| 1.7984 | 42.8571 | 900 | 1.8945 |
| 1.6725 | 47.6190 | 1000 | 1.8271 |
| 1.5961 | 52.3810 | 1100 | 1.8709 |
| 1.5454 | 57.1429 | 1200 | 1.8674 |
| 1.4977 | 61.9048 | 1300 | 1.8333 |
| 1.4575 | 66.6667 | 1400 | 1.8387 |
| 1.4784 | 71.4286 | 1500 | 1.8334 |
| 1.4698 | 76.1905 | 1600 | 1.7419 |
| 1.4335 | 80.9524 | 1700 | 1.8332 |
| 1.394 | 85.7143 | 1800 | 1.8329 |
| 1.3992 | 90.4762 | 1900 | 1.7304 |
| 1.3951 | 95.2381 | 2000 | 1.6899 |
| 1.3984 | 100.0 | 2100 | 1.7504 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1