|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: facebook/detr-resnet-50 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: detr |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# detr |
|
|
|
|
|
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.0196 |
|
|
|
|
|
## 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: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 1 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 3.8584 | 0.02 | 50 | 3.3010 | |
|
|
| 2.7538 | 0.04 | 100 | 2.5486 | |
|
|
| 2.2986 | 0.06 | 150 | 2.2761 | |
|
|
| 2.0637 | 0.08 | 200 | 2.0595 | |
|
|
| 1.9565 | 0.1 | 250 | 1.9289 | |
|
|
| 1.9208 | 0.12 | 300 | 1.9521 | |
|
|
| 1.9024 | 0.14 | 350 | 1.8841 | |
|
|
| 1.8294 | 0.16 | 400 | 1.7362 | |
|
|
| 1.7064 | 0.18 | 450 | 1.6461 | |
|
|
| 1.6336 | 0.2 | 500 | 1.5706 | |
|
|
| 1.5009 | 0.22 | 550 | 1.5610 | |
|
|
| 1.639 | 0.24 | 600 | 1.5916 | |
|
|
| 1.4837 | 0.26 | 650 | 1.4572 | |
|
|
| 1.4384 | 0.28 | 700 | 1.4170 | |
|
|
| 1.4366 | 0.3 | 750 | 1.4112 | |
|
|
| 1.4204 | 0.32 | 800 | 1.3324 | |
|
|
| 1.2496 | 0.34 | 850 | 1.2658 | |
|
|
| 1.313 | 0.36 | 900 | 1.2854 | |
|
|
| 1.2573 | 0.38 | 950 | 1.2485 | |
|
|
| 1.2961 | 0.4 | 1000 | 1.2550 | |
|
|
| 1.2419 | 0.42 | 1050 | 1.2334 | |
|
|
| 1.2132 | 0.44 | 1100 | 1.2097 | |
|
|
| 1.237 | 0.46 | 1150 | 1.1870 | |
|
|
| 1.2395 | 0.48 | 1200 | 1.2277 | |
|
|
| 1.2789 | 0.5 | 1250 | 1.2159 | |
|
|
| 1.2264 | 0.52 | 1300 | 1.1848 | |
|
|
| 1.2875 | 0.54 | 1350 | 1.1683 | |
|
|
| 1.1939 | 0.56 | 1400 | 1.1437 | |
|
|
| 1.1407 | 0.58 | 1450 | 1.1325 | |
|
|
| 1.1727 | 0.6 | 1500 | 1.1204 | |
|
|
| 1.1618 | 0.62 | 1550 | 1.1065 | |
|
|
| 1.1374 | 0.64 | 1600 | 1.0942 | |
|
|
| 1.1241 | 0.66 | 1650 | 1.0965 | |
|
|
| 1.0826 | 0.68 | 1700 | 1.0910 | |
|
|
| 1.1185 | 0.7 | 1750 | 1.0853 | |
|
|
| 1.1238 | 0.72 | 1800 | 1.0656 | |
|
|
| 1.1146 | 0.74 | 1850 | 1.0486 | |
|
|
| 1.1339 | 0.76 | 1900 | 1.0652 | |
|
|
| 1.0464 | 0.78 | 1950 | 1.0542 | |
|
|
| 1.0563 | 0.8 | 2000 | 1.0534 | |
|
|
| 1.0896 | 0.82 | 2050 | 1.0510 | |
|
|
| 1.0753 | 0.84 | 2100 | 1.0300 | |
|
|
| 1.0979 | 0.86 | 2150 | 1.0408 | |
|
|
| 1.0831 | 0.88 | 2200 | 1.0328 | |
|
|
| 1.0936 | 0.9 | 2250 | 1.0215 | |
|
|
| 1.1161 | 0.92 | 2300 | 1.0238 | |
|
|
| 1.0251 | 0.94 | 2350 | 1.0109 | |
|
|
| 1.0676 | 0.96 | 2400 | 1.0147 | |
|
|
| 1.0461 | 0.98 | 2450 | 1.0109 | |
|
|
| 1.0386 | 1.0 | 2500 | 1.0196 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.39.3 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.15.2 |
|
|
|
