README.md

---
library_name: transformers
tags: []
---

## Original result
```
IoU metric: bbox
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000
```

## After training result
```
IoU metric: bbox
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.900
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 1.000
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.900
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.900
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.900
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.900
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.900
```

## Config
- dataset: NIH
- original model: hustvl/yolos-tiny
- lr: 0.0001
- dropout_rate: 0.1
- weight_decay: 0.0001
- max_epochs: 300
- train samples: 2

## Logging
### Training process
```
{'validation_loss': tensor(8.4415, device='cuda:0'), 'validation_loss_ce': tensor(2.1892, device='cuda:0'), 'validation_loss_bbox': tensor(0.7321, device='cuda:0'), 'validation_loss_giou': tensor(1.2958, device='cuda:0'), 'validation_cardinality_error': tensor(97.5000, device='cuda:0')}
{'training_loss': tensor(8.4415, device='cuda:0'), 'train_loss_ce': tensor(2.1892, device='cuda:0'), 'train_loss_bbox': tensor(0.7321, device='cuda:0'), 'train_loss_giou': tensor(1.2958, device='cuda:0'), 'train_cardinality_error': tensor(97.5000, device='cuda:0'), 'validation_loss': tensor(6.8429, device='cuda:0'), 'validation_loss_ce': tensor(1.7903, device='cuda:0'), 'validation_loss_bbox': tensor(0.4391, device='cuda:0'), 'validation_loss_giou': tensor(1.4286, device='cuda:0'), 'validation_cardinality_error': tensor(38., device='cuda:0')}
{'training_loss': tensor(6.8429, device='cuda:0'), 'train_loss_ce': tensor(1.7903, device='cuda:0'), 'train_loss_bbox': tensor(0.4391, device='cuda:0'), 'train_loss_giou': tensor(1.4286, device='cuda:0'), 'train_cardinality_error': tensor(38., device='cuda:0'), 'validation_loss': tensor(4.6954, device='cuda:0'), 'validation_loss_ce': tensor(1.6042, device='cuda:0'), 'validation_loss_bbox': tensor(0.2544, device='cuda:0'), 'validation_loss_giou': tensor(0.9095, device='cuda:0'), 'validation_cardinality_error': tensor(21., device='cuda:0')}
{'training_loss': tensor(4.6954, device='cuda:0'), 'train_loss_ce': tensor(1.6042, device='cuda:0'), 'train_loss_bbox': tensor(0.2544, device='cuda:0'), 'train_loss_giou': tensor(0.9095, device='cuda:0'), 'train_cardinality_error': tensor(21., device='cuda:0'), 'validation_loss': tensor(4.3832, device='cuda:0'), 'validation_loss_ce': tensor(1.4586, device='cuda:0'), 'validation_loss_bbox': tensor(0.1827, device='cuda:0'), 'validation_loss_giou': tensor(1.0055, device='cuda:0'), 'validation_cardinality_error': tensor(10.5000, device='cuda:0')}
{'training_loss': tensor(4.3832, device='cuda:0'), 'train_loss_ce': tensor(1.4586, device='cuda:0'), 'train_loss_bbox': tensor(0.1827, device='cuda:0'), 'train_loss_giou': tensor(1.0055, device='cuda:0'), 'train_cardinality_error': tensor(10.5000, device='cuda:0'), 'validation_loss': tensor(2.5910, device='cuda:0'), 'validation_loss_ce': tensor(1.3605, device='cuda:0'), 'validation_loss_bbox': tensor(0.0772, device='cuda:0'), 'validation_loss_giou': tensor(0.4223, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(2.5910, device='cuda:0'), 'train_loss_ce': tensor(1.3605, device='cuda:0'), 'train_loss_bbox': tensor(0.0772, device='cuda:0'), 'train_loss_giou': tensor(0.4223, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(2.2764, device='cuda:0'), 'validation_loss_ce': tensor(1.2621, device='cuda:0'), 'validation_loss_bbox': tensor(0.0533, device='cuda:0'), 'validation_loss_giou': tensor(0.3738, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.2764, device='cuda:0'), 'train_loss_ce': tensor(1.2621, device='cuda:0'), 'train_loss_bbox': tensor(0.0533, device='cuda:0'), 'train_loss_giou': tensor(0.3738, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2869, device='cuda:0'), 'validation_loss_ce': tensor(1.1396, device='cuda:0'), 'validation_loss_bbox': tensor(0.0631, device='cuda:0'), 'validation_loss_giou': tensor(0.4159, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.2869, device='cuda:0'), 'train_loss_ce': tensor(1.1396, device='cuda:0'), 'train_loss_bbox': tensor(0.0631, device='cuda:0'), 'train_loss_giou': tensor(0.4159, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.7317, device='cuda:0'), 'validation_loss_ce': tensor(1.0187, device='cuda:0'), 'validation_loss_bbox': tensor(0.0306, device='cuda:0'), 'validation_loss_giou': tensor(0.2799, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.7317, device='cuda:0'), 'train_loss_ce': tensor(1.0187, device='cuda:0'), 'train_loss_bbox': tensor(0.0306, device='cuda:0'), 'train_loss_giou': tensor(0.2799, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.5695, device='cuda:0'), 'validation_loss_ce': tensor(0.9265, device='cuda:0'), 'validation_loss_bbox': tensor(0.0909, device='cuda:0'), 'validation_loss_giou': tensor(0.5943, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.5695, device='cuda:0'), 'train_loss_ce': tensor(0.9265, device='cuda:0'), 'train_loss_bbox': tensor(0.0909, device='cuda:0'), 'train_loss_giou': tensor(0.5943, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.4328, device='cuda:0'), 'validation_loss_ce': tensor(0.8355, device='cuda:0'), 'validation_loss_bbox': tensor(0.0930, device='cuda:0'), 'validation_loss_giou': tensor(0.5662, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(2.4328, device='cuda:0'), 'train_loss_ce': tensor(0.8355, device='cuda:0'), 'train_loss_bbox': tensor(0.0930, device='cuda:0'), 'train_loss_giou': tensor(0.5662, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9397, device='cuda:0'), 'validation_loss_ce': tensor(0.7566, device='cuda:0'), 'validation_loss_bbox': tensor(0.0739, device='cuda:0'), 'validation_loss_giou': tensor(0.4067, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.9397, device='cuda:0'), 'train_loss_ce': tensor(0.7566, device='cuda:0'), 'train_loss_bbox': tensor(0.0739, device='cuda:0'), 'train_loss_giou': tensor(0.4067, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8813, device='cuda:0'), 'validation_loss_ce': tensor(0.6895, device='cuda:0'), 'validation_loss_bbox': tensor(0.0686, device='cuda:0'), 'validation_loss_giou': tensor(0.4244, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.8813, device='cuda:0'), 'train_loss_ce': tensor(0.6895, device='cuda:0'), 'train_loss_bbox': tensor(0.0686, device='cuda:0'), 'train_loss_giou': tensor(0.4244, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.6956, device='cuda:0'), 'validation_loss_ce': tensor(0.6046, device='cuda:0'), 'validation_loss_bbox': tensor(0.0604, device='cuda:0'), 'validation_loss_giou': tensor(0.3946, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.6956, device='cuda:0'), 'train_loss_ce': tensor(0.6046, device='cuda:0'), 'train_loss_bbox': tensor(0.0604, device='cuda:0'), 'train_loss_giou': tensor(0.3946, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.5624, device='cuda:0'), 'validation_loss_ce': tensor(0.5391, device='cuda:0'), 'validation_loss_bbox': tensor(0.0615, device='cuda:0'), 'validation_loss_giou': tensor(0.3580, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.5624, device='cuda:0'), 'train_loss_ce': tensor(0.5391, device='cuda:0'), 'train_loss_bbox': tensor(0.0615, device='cuda:0'), 'train_loss_giou': tensor(0.3580, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.0563, device='cuda:0'), 'validation_loss_ce': tensor(0.4887, device='cuda:0'), 'validation_loss_bbox': tensor(0.0301, device='cuda:0'), 'validation_loss_giou': tensor(0.2084, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.0563, device='cuda:0'), 'train_loss_ce': tensor(0.4887, device='cuda:0'), 'train_loss_bbox': tensor(0.0301, device='cuda:0'), 'train_loss_giou': tensor(0.2084, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.4984, device='cuda:0'), 'validation_loss_ce': tensor(0.4608, device='cuda:0'), 'validation_loss_bbox': tensor(0.0831, device='cuda:0'), 'validation_loss_giou': tensor(0.3111, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.4984, device='cuda:0'), 'train_loss_ce': tensor(0.4608, device='cuda:0'), 'train_loss_bbox': tensor(0.0831, device='cuda:0'), 'train_loss_giou': tensor(0.3111, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.2211, device='cuda:0'), 'validation_loss_ce': tensor(0.4321, device='cuda:0'), 'validation_loss_bbox': tensor(0.0592, device='cuda:0'), 'validation_loss_giou': tensor(0.2466, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.2211, device='cuda:0'), 'train_loss_ce': tensor(0.4321, device='cuda:0'), 'train_loss_bbox': tensor(0.0592, device='cuda:0'), 'train_loss_giou': tensor(0.2466, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.3553, device='cuda:0'), 'validation_loss_ce': tensor(0.3998, device='cuda:0'), 'validation_loss_bbox': tensor(0.0638, device='cuda:0'), 'validation_loss_giou': tensor(0.3182, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.3553, device='cuda:0'), 'train_loss_ce': tensor(0.3998, device='cuda:0'), 'train_loss_bbox': tensor(0.0638, device='cuda:0'), 'train_loss_giou': tensor(0.3182, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.1320, device='cuda:0'), 'validation_loss_ce': tensor(0.3978, device='cuda:0'), 'validation_loss_bbox': tensor(0.0442, device='cuda:0'), 'validation_loss_giou': tensor(0.2565, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(1.1320, device='cuda:0'), 'train_loss_ce': tensor(0.3978, device='cuda:0'), 'train_loss_bbox': tensor(0.0442, device='cuda:0'), 'train_loss_giou': tensor(0.2565, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.8688, device='cuda:0'), 'validation_loss_ce': tensor(0.4125, device='cuda:0'), 'validation_loss_bbox': tensor(0.0229, device='cuda:0'), 'validation_loss_giou': tensor(0.1709, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.8688, device='cuda:0'), 'train_loss_ce': tensor(0.4125, device='cuda:0'), 'train_loss_bbox': tensor(0.0229, device='cuda:0'), 'train_loss_giou': tensor(0.1709, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5925, device='cuda:0'), 'validation_loss_ce': tensor(0.4242, device='cuda:0'), 'validation_loss_bbox': tensor(0.0075, device='cuda:0'), 'validation_loss_giou': tensor(0.0653, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5925, device='cuda:0'), 'train_loss_ce': tensor(0.4242, device='cuda:0'), 'train_loss_bbox': tensor(0.0075, device='cuda:0'), 'train_loss_giou': tensor(0.0653, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.9919, device='cuda:0'), 'validation_loss_ce': tensor(0.4179, device='cuda:0'), 'validation_loss_bbox': tensor(0.0315, device='cuda:0'), 'validation_loss_giou': tensor(0.2082, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.9919, device='cuda:0'), 'train_loss_ce': tensor(0.4179, device='cuda:0'), 'train_loss_bbox': tensor(0.0315, device='cuda:0'), 'train_loss_giou': tensor(0.2082, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.9607, device='cuda:0'), 'validation_loss_ce': tensor(0.4075, device='cuda:0'), 'validation_loss_bbox': tensor(0.0330, device='cuda:0'), 'validation_loss_giou': tensor(0.1941, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.9607, device='cuda:0'), 'train_loss_ce': tensor(0.4075, device='cuda:0'), 'train_loss_bbox': tensor(0.0330, device='cuda:0'), 'train_loss_giou': tensor(0.1941, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.8104, device='cuda:0'), 'validation_loss_ce': tensor(0.3983, device='cuda:0'), 'validation_loss_bbox': tensor(0.0237, device='cuda:0'), 'validation_loss_giou': tensor(0.1467, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.8104, device='cuda:0'), 'train_loss_ce': tensor(0.3983, device='cuda:0'), 'train_loss_bbox': tensor(0.0237, device='cuda:0'), 'train_loss_giou': tensor(0.1467, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6995, device='cuda:0'), 'validation_loss_ce': tensor(0.3888, device='cuda:0'), 'validation_loss_bbox': tensor(0.0181, device='cuda:0'), 'validation_loss_giou': tensor(0.1101, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6995, device='cuda:0'), 'train_loss_ce': tensor(0.3888, device='cuda:0'), 'train_loss_bbox': tensor(0.0181, device='cuda:0'), 'train_loss_giou': tensor(0.1101, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.8095, device='cuda:0'), 'validation_loss_ce': tensor(0.3818, device='cuda:0'), 'validation_loss_bbox': tensor(0.0239, device='cuda:0'), 'validation_loss_giou': tensor(0.1540, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.8095, device='cuda:0'), 'train_loss_ce': tensor(0.3818, device='cuda:0'), 'train_loss_bbox': tensor(0.0239, device='cuda:0'), 'train_loss_giou': tensor(0.1540, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.8350, device='cuda:0'), 'validation_loss_ce': tensor(0.3689, device='cuda:0'), 'validation_loss_bbox': tensor(0.0254, device='cuda:0'), 'validation_loss_giou': tensor(0.1695, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.8350, device='cuda:0'), 'train_loss_ce': tensor(0.3689, device='cuda:0'), 'train_loss_bbox': tensor(0.0254, device='cuda:0'), 'train_loss_giou': tensor(0.1695, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.7958, device='cuda:0'), 'validation_loss_ce': tensor(0.3573, device='cuda:0'), 'validation_loss_bbox': tensor(0.0241, device='cuda:0'), 'validation_loss_giou': tensor(0.1590, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.7958, device='cuda:0'), 'train_loss_ce': tensor(0.3573, device='cuda:0'), 'train_loss_bbox': tensor(0.0241, device='cuda:0'), 'train_loss_giou': tensor(0.1590, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.9031, device='cuda:0'), 'validation_loss_ce': tensor(0.3476, device='cuda:0'), 'validation_loss_bbox': tensor(0.0276, device='cuda:0'), 'validation_loss_giou': tensor(0.2087, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.9031, device='cuda:0'), 'train_loss_ce': tensor(0.3476, device='cuda:0'), 'train_loss_bbox': tensor(0.0276, device='cuda:0'), 'train_loss_giou': tensor(0.2087, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.7674, device='cuda:0'), 'validation_loss_ce': tensor(0.3367, device='cuda:0'), 'validation_loss_bbox': tensor(0.0211, device='cuda:0'), 'validation_loss_giou': tensor(0.1627, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.7674, device='cuda:0'), 'train_loss_ce': tensor(0.3367, device='cuda:0'), 'train_loss_bbox': tensor(0.0211, device='cuda:0'), 'train_loss_giou': tensor(0.1627, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5935, device='cuda:0'), 'validation_loss_ce': tensor(0.3245, device='cuda:0'), 'validation_loss_bbox': tensor(0.0132, device='cuda:0'), 'validation_loss_giou': tensor(0.1014, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5935, device='cuda:0'), 'train_loss_ce': tensor(0.3245, device='cuda:0'), 'train_loss_bbox': tensor(0.0132, device='cuda:0'), 'train_loss_giou': tensor(0.1014, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5668, device='cuda:0'), 'validation_loss_ce': tensor(0.3225, device='cuda:0'), 'validation_loss_bbox': tensor(0.0136, device='cuda:0'), 'validation_loss_giou': tensor(0.0881, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5668, device='cuda:0'), 'train_loss_ce': tensor(0.3225, device='cuda:0'), 'train_loss_bbox': tensor(0.0136, device='cuda:0'), 'train_loss_giou': tensor(0.0881, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6651, device='cuda:0'), 'validation_loss_ce': tensor(0.3124, device='cuda:0'), 'validation_loss_bbox': tensor(0.0177, device='cuda:0'), 'validation_loss_giou': tensor(0.1322, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6651, device='cuda:0'), 'train_loss_ce': tensor(0.3124, device='cuda:0'), 'train_loss_bbox': tensor(0.0177, device='cuda:0'), 'train_loss_giou': tensor(0.1322, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6747, device='cuda:0'), 'validation_loss_ce': tensor(0.3028, device='cuda:0'), 'validation_loss_bbox': tensor(0.0200, device='cuda:0'), 'validation_loss_giou': tensor(0.1358, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6747, device='cuda:0'), 'train_loss_ce': tensor(0.3028, device='cuda:0'), 'train_loss_bbox': tensor(0.0200, device='cuda:0'), 'train_loss_giou': tensor(0.1358, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.7654, device='cuda:0'), 'validation_loss_ce': tensor(0.2944, device='cuda:0'), 'validation_loss_bbox': tensor(0.0258, device='cuda:0'), 'validation_loss_giou': tensor(0.1710, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.7654, device='cuda:0'), 'train_loss_ce': tensor(0.2944, device='cuda:0'), 'train_loss_bbox': tensor(0.0258, device='cuda:0'), 'train_loss_giou': tensor(0.1710, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6377, device='cuda:0'), 'validation_loss_ce': tensor(0.2869, device='cuda:0'), 'validation_loss_bbox': tensor(0.0198, device='cuda:0'), 'validation_loss_giou': tensor(0.1259, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6377, device='cuda:0'), 'train_loss_ce': tensor(0.2869, device='cuda:0'), 'train_loss_bbox': tensor(0.0198, device='cuda:0'), 'train_loss_giou': tensor(0.1259, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5517, device='cuda:0'), 'validation_loss_ce': tensor(0.2820, device='cuda:0'), 'validation_loss_bbox': tensor(0.0146, device='cuda:0'), 'validation_loss_giou': tensor(0.0984, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5517, device='cuda:0'), 'train_loss_ce': tensor(0.2820, device='cuda:0'), 'train_loss_bbox': tensor(0.0146, device='cuda:0'), 'train_loss_giou': tensor(0.0984, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6360, device='cuda:0'), 'validation_loss_ce': tensor(0.2759, device='cuda:0'), 'validation_loss_bbox': tensor(0.0216, device='cuda:0'), 'validation_loss_giou': tensor(0.1261, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6360, device='cuda:0'), 'train_loss_ce': tensor(0.2759, device='cuda:0'), 'train_loss_bbox': tensor(0.0216, device='cuda:0'), 'train_loss_giou': tensor(0.1261, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5860, device='cuda:0'), 'validation_loss_ce': tensor(0.2692, device='cuda:0'), 'validation_loss_bbox': tensor(0.0175, device='cuda:0'), 'validation_loss_giou': tensor(0.1147, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5860, device='cuda:0'), 'train_loss_ce': tensor(0.2692, device='cuda:0'), 'train_loss_bbox': tensor(0.0175, device='cuda:0'), 'train_loss_giou': tensor(0.1147, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4671, device='cuda:0'), 'validation_loss_ce': tensor(0.2624, device='cuda:0'), 'validation_loss_bbox': tensor(0.0115, device='cuda:0'), 'validation_loss_giou': tensor(0.0736, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4671, device='cuda:0'), 'train_loss_ce': tensor(0.2624, device='cuda:0'), 'train_loss_bbox': tensor(0.0115, device='cuda:0'), 'train_loss_giou': tensor(0.0736, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6358, device='cuda:0'), 'validation_loss_ce': tensor(0.2559, device='cuda:0'), 'validation_loss_bbox': tensor(0.0212, device='cuda:0'), 'validation_loss_giou': tensor(0.1369, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6358, device='cuda:0'), 'train_loss_ce': tensor(0.2559, device='cuda:0'), 'train_loss_bbox': tensor(0.0212, device='cuda:0'), 'train_loss_giou': tensor(0.1369, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.7122, device='cuda:0'), 'validation_loss_ce': tensor(0.2498, device='cuda:0'), 'validation_loss_bbox': tensor(0.0253, device='cuda:0'), 'validation_loss_giou': tensor(0.1680, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.7122, device='cuda:0'), 'train_loss_ce': tensor(0.2498, device='cuda:0'), 'train_loss_bbox': tensor(0.0253, device='cuda:0'), 'train_loss_giou': tensor(0.1680, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6051, device='cuda:0'), 'validation_loss_ce': tensor(0.2438, device='cuda:0'), 'validation_loss_bbox': tensor(0.0173, device='cuda:0'), 'validation_loss_giou': tensor(0.1375, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6051, device='cuda:0'), 'train_loss_ce': tensor(0.2438, device='cuda:0'), 'train_loss_bbox': tensor(0.0173, device='cuda:0'), 'train_loss_giou': tensor(0.1375, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5448, device='cuda:0'), 'validation_loss_ce': tensor(0.2378, device='cuda:0'), 'validation_loss_bbox': tensor(0.0146, device='cuda:0'), 'validation_loss_giou': tensor(0.1169, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5448, device='cuda:0'), 'train_loss_ce': tensor(0.2378, device='cuda:0'), 'train_loss_bbox': tensor(0.0146, device='cuda:0'), 'train_loss_giou': tensor(0.1169, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6503, device='cuda:0'), 'validation_loss_ce': tensor(0.2314, device='cuda:0'), 'validation_loss_bbox': tensor(0.0230, device='cuda:0'), 'validation_loss_giou': tensor(0.1519, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6503, device='cuda:0'), 'train_loss_ce': tensor(0.2314, device='cuda:0'), 'train_loss_bbox': tensor(0.0230, device='cuda:0'), 'train_loss_giou': tensor(0.1519, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.6441, device='cuda:0'), 'validation_loss_ce': tensor(0.2251, device='cuda:0'), 'validation_loss_bbox': tensor(0.0237, device='cuda:0'), 'validation_loss_giou': tensor(0.1502, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.6441, device='cuda:0'), 'train_loss_ce': tensor(0.2251, device='cuda:0'), 'train_loss_bbox': tensor(0.0237, device='cuda:0'), 'train_loss_giou': tensor(0.1502, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5166, device='cuda:0'), 'validation_loss_ce': tensor(0.2191, device='cuda:0'), 'validation_loss_bbox': tensor(0.0144, device='cuda:0'), 'validation_loss_giou': tensor(0.1129, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5166, device='cuda:0'), 'train_loss_ce': tensor(0.2191, device='cuda:0'), 'train_loss_bbox': tensor(0.0144, device='cuda:0'), 'train_loss_giou': tensor(0.1129, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4642, device='cuda:0'), 'validation_loss_ce': tensor(0.2135, device='cuda:0'), 'validation_loss_bbox': tensor(0.0131, device='cuda:0'), 'validation_loss_giou': tensor(0.0925, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4642, device='cuda:0'), 'train_loss_ce': tensor(0.2135, device='cuda:0'), 'train_loss_bbox': tensor(0.0131, device='cuda:0'), 'train_loss_giou': tensor(0.0925, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5538, device='cuda:0'), 'validation_loss_ce': tensor(0.2082, device='cuda:0'), 'validation_loss_bbox': tensor(0.0205, device='cuda:0'), 'validation_loss_giou': tensor(0.1215, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5538, device='cuda:0'), 'train_loss_ce': tensor(0.2082, device='cuda:0'), 'train_loss_bbox': tensor(0.0205, device='cuda:0'), 'train_loss_giou': tensor(0.1215, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5844, device='cuda:0'), 'validation_loss_ce': tensor(0.2029, device='cuda:0'), 'validation_loss_bbox': tensor(0.0202, device='cuda:0'), 'validation_loss_giou': tensor(0.1402, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5844, device='cuda:0'), 'train_loss_ce': tensor(0.2029, device='cuda:0'), 'train_loss_bbox': tensor(0.0202, device='cuda:0'), 'train_loss_giou': tensor(0.1402, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4431, device='cuda:0'), 'validation_loss_ce': tensor(0.1975, device='cuda:0'), 'validation_loss_bbox': tensor(0.0111, device='cuda:0'), 'validation_loss_giou': tensor(0.0950, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4431, device='cuda:0'), 'train_loss_ce': tensor(0.1975, device='cuda:0'), 'train_loss_bbox': tensor(0.0111, device='cuda:0'), 'train_loss_giou': tensor(0.0950, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4185, device='cuda:0'), 'validation_loss_ce': tensor(0.1922, device='cuda:0'), 'validation_loss_bbox': tensor(0.0124, device='cuda:0'), 'validation_loss_giou': tensor(0.0821, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4185, device='cuda:0'), 'train_loss_ce': tensor(0.1922, device='cuda:0'), 'train_loss_bbox': tensor(0.0124, device='cuda:0'), 'train_loss_giou': tensor(0.0821, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5260, device='cuda:0'), 'validation_loss_ce': tensor(0.1868, device='cuda:0'), 'validation_loss_bbox': tensor(0.0183, device='cuda:0'), 'validation_loss_giou': tensor(0.1239, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5260, device='cuda:0'), 'train_loss_ce': tensor(0.1868, device='cuda:0'), 'train_loss_bbox': tensor(0.0183, device='cuda:0'), 'train_loss_giou': tensor(0.1239, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4616, device='cuda:0'), 'validation_loss_ce': tensor(0.1816, device='cuda:0'), 'validation_loss_bbox': tensor(0.0166, device='cuda:0'), 'validation_loss_giou': tensor(0.0985, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4616, device='cuda:0'), 'train_loss_ce': tensor(0.1816, device='cuda:0'), 'train_loss_bbox': tensor(0.0166, device='cuda:0'), 'train_loss_giou': tensor(0.0985, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4940, device='cuda:0'), 'validation_loss_ce': tensor(0.1762, device='cuda:0'), 'validation_loss_bbox': tensor(0.0163, device='cuda:0'), 'validation_loss_giou': tensor(0.1182, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4940, device='cuda:0'), 'train_loss_ce': tensor(0.1762, device='cuda:0'), 'train_loss_bbox': tensor(0.0163, device='cuda:0'), 'train_loss_giou': tensor(0.1182, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4763, device='cuda:0'), 'validation_loss_ce': tensor(0.1710, device='cuda:0'), 'validation_loss_bbox': tensor(0.0155, device='cuda:0'), 'validation_loss_giou': tensor(0.1139, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4763, device='cuda:0'), 'train_loss_ce': tensor(0.1710, device='cuda:0'), 'train_loss_bbox': tensor(0.0155, device='cuda:0'), 'train_loss_giou': tensor(0.1139, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4972, device='cuda:0'), 'validation_loss_ce': tensor(0.1658, device='cuda:0'), 'validation_loss_bbox': tensor(0.0189, device='cuda:0'), 'validation_loss_giou': tensor(0.1183, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4972, device='cuda:0'), 'train_loss_ce': tensor(0.1658, device='cuda:0'), 'train_loss_bbox': tensor(0.0189, device='cuda:0'), 'train_loss_giou': tensor(0.1183, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4801, device='cuda:0'), 'validation_loss_ce': tensor(0.1608, device='cuda:0'), 'validation_loss_bbox': tensor(0.0173, device='cuda:0'), 'validation_loss_giou': tensor(0.1165, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4801, device='cuda:0'), 'train_loss_ce': tensor(0.1608, device='cuda:0'), 'train_loss_bbox': tensor(0.0173, device='cuda:0'), 'train_loss_giou': tensor(0.1165, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4167, device='cuda:0'), 'validation_loss_ce': tensor(0.1564, device='cuda:0'), 'validation_loss_bbox': tensor(0.0091, device='cuda:0'), 'validation_loss_giou': tensor(0.1074, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4167, device='cuda:0'), 'train_loss_ce': tensor(0.1564, device='cuda:0'), 'train_loss_bbox': tensor(0.0091, device='cuda:0'), 'train_loss_giou': tensor(0.1074, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.3448, device='cuda:0'), 'validation_loss_ce': tensor(0.1525, device='cuda:0'), 'validation_loss_bbox': tensor(0.0115, device='cuda:0'), 'validation_loss_giou': tensor(0.0674, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.3448, device='cuda:0'), 'train_loss_ce': tensor(0.1525, device='cuda:0'), 'train_loss_bbox': tensor(0.0115, device='cuda:0'), 'train_loss_giou': tensor(0.0674, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4019, device='cuda:0'), 'validation_loss_ce': tensor(0.1483, device='cuda:0'), 'validation_loss_bbox': tensor(0.0140, device='cuda:0'), 'validation_loss_giou': tensor(0.0918, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.4019, device='cuda:0'), 'train_loss_ce': tensor(0.1483, device='cuda:0'), 'train_loss_bbox': tensor(0.0140, device='cuda:0'), 'train_loss_giou': tensor(0.0918, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.3806, device='cuda:0'), 'validation_loss_ce': tensor(0.1439, device='cuda:0'), 'validation_loss_bbox': tensor(0.0112, device='cuda:0'), 'validation_loss_giou': tensor(0.0903, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.3806, device='cuda:0'), 'train_loss_ce': tensor(0.1439, device='cuda:0'), 'train_loss_bbox': tensor(0.0112, device='cuda:0'), 'train_loss_giou': tensor(0.0903, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4055, device='cuda:0'), 'validation_loss_ce': tensor(0.1394, device='cuda:0'), 'validation_loss_bbox': tensor(0.0108, device='cuda:0'), 'validation_loss_giou': tensor(0.1061, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.4055, device='cuda:0'), 'train_loss_ce': tensor(0.1394, device='cuda:0'), 'train_loss_bbox': tensor(0.0108, device='cuda:0'), 'train_loss_giou': tensor(0.1061, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.3380, device='cuda:0'), 'validation_loss_ce': tensor(0.1345, device='cuda:0'), 'validation_loss_bbox': tensor(0.0114, device='cuda:0'), 'validation_loss_giou': tensor(0.0732, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.3380, device='cuda:0'), 'train_loss_ce': tensor(0.1345, device='cuda:0'), 'train_loss_bbox': tensor(0.0114, device='cuda:0'), 'train_loss_giou': tensor(0.0732, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.3690, device='cuda:0'), 'validation_loss_ce': tensor(0.1303, device='cuda:0'), 'validation_loss_bbox': tensor(0.0118, device='cuda:0'), 'validation_loss_giou': tensor(0.0898, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.3690, device='cuda:0'), 'train_loss_ce': tensor(0.1303, device='cuda:0'), 'train_loss_bbox': tensor(0.0118, device='cuda:0'), 'train_loss_giou': tensor(0.0898, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.3661, device='cuda:0'), 'validation_loss_ce': tensor(0.1265, device='cuda:0'), 'validation_loss_bbox': tensor(0.0095, device='cuda:0'), 'validation_loss_giou': tensor(0.0960, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.3661, device='cuda:0'), 'train_loss_ce': tensor(0.1265, device='cuda:0'), 'train_loss_bbox': tensor(0.0095, device='cuda:0'), 'train_loss_giou': tensor(0.0960, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.3483, device='cuda:0'), 'validation_loss_ce': tensor(0.1225, device='cuda:0'), 'validation_loss_bbox': tensor(0.0088, device='cuda:0'), 'validation_loss_giou': tensor(0.0909, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.3483, device='cuda:0'), 'train_loss_ce': tensor(0.1225, device='cuda:0'), 'train_loss_bbox': tensor(0.0088, device='cuda:0'), 'train_loss_giou': tensor(0.0909, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.2951, device='cuda:0'), 'validation_loss_ce': tensor(0.1182, device='cuda:0'), 'validation_loss_bbox': tensor(0.0103, device='cuda:0'), 'validation_loss_giou': tensor(0.0627, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.2951, device='cuda:0'), 'train_loss_ce': tensor(0.1182, device='cuda:0'), 'train_loss_bbox': tensor(0.0103, device='cuda:0'), 'train_loss_giou': tensor(0.0627, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.3811, device='cuda:0'), 'validation_loss_ce': tensor(0.1145, device='cuda:0'), 'validation_loss_bbox': tensor(0.0148, device='cuda:0'), 'validation_loss_giou': tensor(0.0963, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.3811, device='cuda:0'), 'train_loss_ce': tensor(0.1145, device='cuda:0'), 'train_loss_bbox': tensor(0.0148, device='cuda:0'), 'train_loss_giou': tensor(0.0963, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.4378, device='cuda:0'), 'validation_loss_ce': tensor(0.1108, device='cuda:0'), 'validation_loss_bbox': tensor(0.0171, device='cuda:0'), 'validation_loss_giou': tensor(0.1207, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.4378, device='cuda:0'), 'train_loss_ce': tensor(0.1108, device='cuda:0'), 'train_loss_bbox': tensor(0.0171, device='cuda:0'), 'train_loss_giou': tensor(0.1207, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.3757, device='cuda:0'), 'validation_loss_ce': tensor(0.1069, device='cuda:0'), 'validation_loss_bbox': tensor(0.0129, device='cuda:0'), 'validation_loss_giou': tensor(0.1021, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.3757, device='cuda:0'), 'train_loss_ce': tensor(0.1069, device='cuda:0'), 'train_loss_bbox': tensor(0.0129, device='cuda:0'), 'train_loss_giou': tensor(0.1021, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.3717, device='cuda:0'), 'validation_loss_ce': tensor(0.1029, device='cuda:0'), 'validation_loss_bbox': tensor(0.0127, device='cuda:0'), 'validation_loss_giou': tensor(0.1026, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.3717, device='cuda:0'), 'train_loss_ce': tensor(0.1029, device='cuda:0'), 'train_loss_bbox': tensor(0.0127, device='cuda:0'), 'train_loss_giou': tensor(0.1026, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.3644, device='cuda:0'), 'validation_loss_ce': tensor(0.0999, device='cuda:0'), 'validation_loss_bbox': tensor(0.0122, device='cuda:0'), 'validation_loss_giou': tensor(0.1017, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3644, device='cuda:0'), 'train_loss_ce': tensor(0.0999, device='cuda:0'), 'train_loss_bbox': tensor(0.0122, device='cuda:0'), 'train_loss_giou': tensor(0.1017, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2506, device='cuda:0'), 'validation_loss_ce': tensor(0.0973, device='cuda:0'), 'validation_loss_bbox': tensor(0.0066, device='cuda:0'), 'validation_loss_giou': tensor(0.0600, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2506, device='cuda:0'), 'train_loss_ce': tensor(0.0973, device='cuda:0'), 'train_loss_bbox': tensor(0.0066, device='cuda:0'), 'train_loss_giou': tensor(0.0600, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.4763, device='cuda:0'), 'validation_loss_ce': tensor(0.0953, device='cuda:0'), 'validation_loss_bbox': tensor(0.0164, device='cuda:0'), 'validation_loss_giou': tensor(0.1494, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.4763, device='cuda:0'), 'train_loss_ce': tensor(0.0953, device='cuda:0'), 'train_loss_bbox': tensor(0.0164, device='cuda:0'), 'train_loss_giou': tensor(0.1494, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.5612, device='cuda:0'), 'validation_loss_ce': tensor(0.0930, device='cuda:0'), 'validation_loss_bbox': tensor(0.0188, device='cuda:0'), 'validation_loss_giou': tensor(0.1871, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.5612, device='cuda:0'), 'train_loss_ce': tensor(0.0930, device='cuda:0'), 'train_loss_bbox': tensor(0.0188, device='cuda:0'), 'train_loss_giou': tensor(0.1871, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.4405, device='cuda:0'), 'validation_loss_ce': tensor(0.0902, device='cuda:0'), 'validation_loss_bbox': tensor(0.0139, device='cuda:0'), 'validation_loss_giou': tensor(0.1405, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.4405, device='cuda:0'), 'train_loss_ce': tensor(0.0902, device='cuda:0'), 'train_loss_bbox': tensor(0.0139, device='cuda:0'), 'train_loss_giou': tensor(0.1405, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2879, device='cuda:0'), 'validation_loss_ce': tensor(0.0873, device='cuda:0'), 'validation_loss_bbox': tensor(0.0097, device='cuda:0'), 'validation_loss_giou': tensor(0.0760, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2879, device='cuda:0'), 'train_loss_ce': tensor(0.0873, device='cuda:0'), 'train_loss_bbox': tensor(0.0097, device='cuda:0'), 'train_loss_giou': tensor(0.0760, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.4814, device='cuda:0'), 'validation_loss_ce': tensor(0.0842, device='cuda:0'), 'validation_loss_bbox': tensor(0.0182, device='cuda:0'), 'validation_loss_giou': tensor(0.1530, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.4814, device='cuda:0'), 'train_loss_ce': tensor(0.0842, device='cuda:0'), 'train_loss_bbox': tensor(0.0182, device='cuda:0'), 'train_loss_giou': tensor(0.1530, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.5626, device='cuda:0'), 'validation_loss_ce': tensor(0.0817, device='cuda:0'), 'validation_loss_bbox': tensor(0.0193, device='cuda:0'), 'validation_loss_giou': tensor(0.1921, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5626, device='cuda:0'), 'train_loss_ce': tensor(0.0817, device='cuda:0'), 'train_loss_bbox': tensor(0.0193, device='cuda:0'), 'train_loss_giou': tensor(0.1921, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.3903, device='cuda:0'), 'validation_loss_ce': tensor(0.0794, device='cuda:0'), 'validation_loss_bbox': tensor(0.0099, device='cuda:0'), 'validation_loss_giou': tensor(0.1308, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.3903, device='cuda:0'), 'train_loss_ce': tensor(0.0794, device='cuda:0'), 'train_loss_bbox': tensor(0.0099, device='cuda:0'), 'train_loss_giou': tensor(0.1308, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.3352, device='cuda:0'), 'validation_loss_ce': tensor(0.0774, device='cuda:0'), 'validation_loss_bbox': tensor(0.0103, device='cuda:0'), 'validation_loss_giou': tensor(0.1032, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.3352, device='cuda:0'), 'train_loss_ce': tensor(0.0774, device='cuda:0'), 'train_loss_bbox': tensor(0.0103, device='cuda:0'), 'train_loss_giou': tensor(0.1032, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.3630, device='cuda:0'), 'validation_loss_ce': tensor(0.0987, device='cuda:0'), 'validation_loss_bbox': tensor(0.0135, device='cuda:0'), 'validation_loss_giou': tensor(0.0983, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.3630, device='cuda:0'), 'train_loss_ce': tensor(0.0987, device='cuda:0'), 'train_loss_bbox': tensor(0.0135, device='cuda:0'), 'train_loss_giou': tensor(0.0983, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5952, device='cuda:0'), 'validation_loss_ce': tensor(0.0961, device='cuda:0'), 'validation_loss_bbox': tensor(0.0205, device='cuda:0'), 'validation_loss_giou': tensor(0.1984, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5952, device='cuda:0'), 'train_loss_ce': tensor(0.0961, device='cuda:0'), 'train_loss_bbox': tensor(0.0205, device='cuda:0'), 'train_loss_giou': tensor(0.1984, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.5618, device='cuda:0'), 'validation_loss_ce': tensor(0.0946, device='cuda:0'), 'validation_loss_bbox': tensor(0.0177, device='cuda:0'), 'validation_loss_giou': tensor(0.1893, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.5618, device='cuda:0'), 'train_loss_ce': tensor(0.0946, device='cuda:0'), 'train_loss_bbox': tensor(0.0177, device='cuda:0'), 'train_loss_giou': tensor(0.1893, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2575, device='cuda:0'), 'validation_loss_ce': tensor(0.0950, device='cuda:0'), 'validation_loss_bbox': tensor(0.0090, device='cuda:0'), 'validation_loss_giou': tensor(0.0587, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.2575, device='cuda:0'), 'train_loss_ce': tensor(0.0950, device='cuda:0'), 'train_loss_bbox': tensor(0.0090, device='cuda:0'), 'train_loss_giou': tensor(0.0587, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.3741, device='cuda:0'), 'validation_loss_ce': tensor(0.0681, device='cuda:0'), 'validation_loss_bbox': tensor(0.0146, device='cuda:0'), 'validation_loss_giou': tensor(0.1164, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.3741, device='cuda:0'), 'train_loss_ce': tensor(0.0681, device='cuda:0'), 'train_loss_bbox': tensor(0.0146, device='cuda:0'), 'train_loss_giou': tensor(0.1164, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.3804, device='cuda:0'), 'validation_loss_ce': tensor(0.0672, device='cuda:0'), 'validation_loss_bbox': tensor(0.0145, device='cuda:0'), 'validation_loss_giou': tensor(0.1203, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.3804, device='cuda:0'), 'train_loss_ce': tensor(0.0672, device='cuda:0'), 'train_loss_bbox': tensor(0.0145, device='cuda:0'), 'train_loss_giou': tensor(0.1203, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.4510, device='cuda:0'), 'validation_loss_ce': tensor(0.0661, device='cuda:0'), 'validation_loss_bbox': tensor(0.0164, device='cuda:0'), 'validation_loss_giou': tensor(0.1514, device='cuda:0'), 'validation_cardinality_error': tensor(1.5000, device='cuda:0')}
{'training_loss': tensor(0.4510, device='cuda:0'), 'train_loss_ce': tensor(0.0661, device='cuda:0'), 'train_loss_bbox': tensor(0.0164, device='cuda:0'), 'train_loss_giou': tensor(0.1514, device='cuda:0'), 'train_cardinality_error': tensor(1.5000, device='cuda:0'), 'validation_loss': tensor(0.4518, device='cuda:0'), 'validation_loss_ce': tensor(0.0644, device='cuda:0'), 'validation_loss_bbox': tensor(0.0157, device='cuda:0'), 'validation_loss_giou': tensor(0.1545, device='cuda:0'), 'validation_cardinality_error': tensor(1.5000, device='cuda:0')}
{'training_loss': tensor(0.4518, device='cuda:0'), 'train_loss_ce': tensor(0.0644, device='cuda:0'), 'train_loss_bbox': tensor(0.0157, device='cuda:0'), 'train_loss_giou': tensor(0.1545, device='cuda:0'), 'train_cardinality_error': tensor(1.5000, device='cuda:0'), 'validation_loss': tensor(0.3655, device='cuda:0'), 'validation_loss_ce': tensor(0.0634, device='cuda:0'), 'validation_loss_bbox': tensor(0.0132, device='cuda:0'), 'validation_loss_giou': tensor(0.1181, device='cuda:0'), 'validation_cardinality_error': tensor(1.5000, device='cuda:0')}
{'training_loss': tensor(0.3655, device='cuda:0'), 'train_loss_ce': tensor(0.0634, device='cuda:0'), 'train_loss_bbox': tensor(0.0132, device='cuda:0'), 'train_loss_giou': tensor(0.1181, device='cuda:0'), 'train_cardinality_error': tensor(1.5000, device='cuda:0'), 'validation_loss': tensor(0.2913, device='cuda:0'), 'validation_loss_ce': tensor(0.0632, device='cuda:0'), 'validation_loss_bbox': tensor(0.0085, device='cuda:0'), 'validation_loss_giou': tensor(0.0927, device='cuda:0'), 'validation_cardinality_error': tensor(1.5000, device='cuda:0')}
{'training_loss': tensor(0.2913, device='cuda:0'), 'train_loss_ce': tensor(0.0632, device='cuda:0'), 'train_loss_bbox': tensor(0.0085, device='cuda:0'), 'train_loss_giou': tensor(0.0927, device='cuda:0'), 'train_cardinality_error': tensor(1.5000, device='cuda:0'), 'validation_loss': tensor(0.3692, device='cuda:0'), 'validation_loss_ce': tensor(0.0632, device='cuda:0'), 'validation_loss_bbox': tensor(0.0130, device='cuda:0'), 'validation_loss_giou': tensor(0.1204, device='cuda:0'), 'validation_cardinality_error': tensor(2., device='cuda:0')}
{'training_loss': tensor(0.3692, device='cuda:0'), 'train_loss_ce': tensor(0.0632, device='cuda:0'), 'train_loss_bbox': tensor(0.0130, device='cuda:0'), 'train_loss_giou': tensor(0.1204, device='cuda:0'), 'train_cardinality_error': tensor(2., device='cuda:0'), 'validation_loss': tensor(0.3340, device='cuda:0'), 'validation_loss_ce': tensor(0.0623, device='cuda:0'), 'validation_loss_bbox': tensor(0.0146, device='cuda:0'), 'validation_loss_giou': tensor(0.0994, device='cuda:0'), 'validation_cardinality_error': tensor(2., device='cuda:0')}
{'training_loss': tensor(0.3340, device='cuda:0'), 'train_loss_ce': tensor(0.0623, device='cuda:0'), 'train_loss_bbox': tensor(0.0146, device='cuda:0'), 'train_loss_giou': tensor(0.0994, device='cuda:0'), 'train_cardinality_error': tensor(2., device='cuda:0'), 'validation_loss': tensor(0.2792, device='cuda:0'), 'validation_loss_ce': tensor(0.0603, device='cuda:0'), 'validation_loss_bbox': tensor(0.0124, device='cuda:0'), 'validation_loss_giou': tensor(0.0784, device='cuda:0'), 'validation_cardinality_error': tensor(1.5000, device='cuda:0')}
{'training_loss': tensor(0.2792, device='cuda:0'), 'train_loss_ce': tensor(0.0603, device='cuda:0'), 'train_loss_bbox': tensor(0.0124, device='cuda:0'), 'train_loss_giou': tensor(0.0784, device='cuda:0'), 'train_cardinality_error': tensor(1.5000, device='cuda:0'), 'validation_loss': tensor(0.2597, device='cuda:0'), 'validation_loss_ce': tensor(0.0582, device='cuda:0'), 'validation_loss_bbox': tensor(0.0103, device='cuda:0'), 'validation_loss_giou': tensor(0.0751, device='cuda:0'), 'validation_cardinality_error': tensor(1.5000, device='cuda:0')}
{'training_loss': tensor(0.2597, device='cuda:0'), 'train_loss_ce': tensor(0.0582, device='cuda:0'), 'train_loss_bbox': tensor(0.0103, device='cuda:0'), 'train_loss_giou': tensor(0.0751, device='cuda:0'), 'train_cardinality_error': tensor(1.5000, device='cuda:0'), 'validation_loss': tensor(0.1822, device='cuda:0'), 'validation_loss_ce': tensor(0.0560, device='cuda:0'), 'validation_loss_bbox': tensor(0.0070, device='cuda:0'), 'validation_loss_giou': tensor(0.0456, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.1822, device='cuda:0'), 'train_loss_ce': tensor(0.0560, device='cuda:0'), 'train_loss_bbox': tensor(0.0070, device='cuda:0'), 'train_loss_giou': tensor(0.0456, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.1763, device='cuda:0'), 'validation_loss_ce': tensor(0.0536, device='cuda:0'), 'validation_loss_bbox': tensor(0.0054, device='cuda:0'), 'validation_loss_giou': tensor(0.0479, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.1763, device='cuda:0'), 'train_loss_ce': tensor(0.0536, device='cuda:0'), 'train_loss_bbox': tensor(0.0054, device='cuda:0'), 'train_loss_giou': tensor(0.0479, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.1416, device='cuda:0'), 'validation_loss_ce': tensor(0.0507, device='cuda:0'), 'validation_loss_bbox': tensor(0.0052, device='cuda:0'), 'validation_loss_giou': tensor(0.0324, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.1416, device='cuda:0'), 'train_loss_ce': tensor(0.0507, device='cuda:0'), 'train_loss_bbox': tensor(0.0052, device='cuda:0'), 'train_loss_giou': tensor(0.0324, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2995, device='cuda:0'), 'validation_loss_ce': tensor(0.0473, device='cuda:0'), 'validation_loss_bbox': tensor(0.0116, device='cuda:0'), 'validation_loss_giou': tensor(0.0972, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.2995, device='cuda:0'), 'train_loss_ce': tensor(0.0473, device='cuda:0'), 'train_loss_bbox': tensor(0.0116, device='cuda:0'), 'train_loss_giou': tensor(0.0972, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2813, device='cuda:0'), 'validation_loss_ce': tensor(0.0460, device='cuda:0'), 'validation_loss_bbox': tensor(0.0098, device='cuda:0'), 'validation_loss_giou': tensor(0.0932, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.2813, device='cuda:0'), 'train_loss_ce': tensor(0.0460, device='cuda:0'), 'train_loss_bbox': tensor(0.0098, device='cuda:0'), 'train_loss_giou': tensor(0.0932, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2491, device='cuda:0'), 'validation_loss_ce': tensor(0.0447, device='cuda:0'), 'validation_loss_bbox': tensor(0.0094, device='cuda:0'), 'validation_loss_giou': tensor(0.0785, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.2491, device='cuda:0'), 'train_loss_ce': tensor(0.0447, device='cuda:0'), 'train_loss_bbox': tensor(0.0094, device='cuda:0'), 'train_loss_giou': tensor(0.0785, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.3269, device='cuda:0'), 'validation_loss_ce': tensor(0.0435, device='cuda:0'), 'validation_loss_bbox': tensor(0.0138, device='cuda:0'), 'validation_loss_giou': tensor(0.1072, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.3269, device='cuda:0'), 'train_loss_ce': tensor(0.0435, device='cuda:0'), 'train_loss_bbox': tensor(0.0138, device='cuda:0'), 'train_loss_giou': tensor(0.1072, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.3899, device='cuda:0'), 'validation_loss_ce': tensor(0.0423, device='cuda:0'), 'validation_loss_bbox': tensor(0.0150, device='cuda:0'), 'validation_loss_giou': tensor(0.1362, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.3899, device='cuda:0'), 'train_loss_ce': tensor(0.0423, device='cuda:0'), 'train_loss_bbox': tensor(0.0150, device='cuda:0'), 'train_loss_giou': tensor(0.1362, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2593, device='cuda:0'), 'validation_loss_ce': tensor(0.0412, device='cuda:0'), 'validation_loss_bbox': tensor(0.0090, device='cuda:0'), 'validation_loss_giou': tensor(0.0866, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.2593, device='cuda:0'), 'train_loss_ce': tensor(0.0412, device='cuda:0'), 'train_loss_bbox': tensor(0.0090, device='cuda:0'), 'train_loss_giou': tensor(0.0866, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2396, device='cuda:0'), 'validation_loss_ce': tensor(0.0404, device='cuda:0'), 'validation_loss_bbox': tensor(0.0082, device='cuda:0'), 'validation_loss_giou': tensor(0.0791, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.2396, device='cuda:0'), 'train_loss_ce': tensor(0.0404, device='cuda:0'), 'train_loss_bbox': tensor(0.0082, device='cuda:0'), 'train_loss_giou': tensor(0.0791, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2881, device='cuda:0'), 'validation_loss_ce': tensor(0.0394, device='cuda:0'), 'validation_loss_bbox': tensor(0.0101, device='cuda:0'), 'validation_loss_giou': tensor(0.0992, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.2881, device='cuda:0'), 'train_loss_ce': tensor(0.0394, device='cuda:0'), 'train_loss_bbox': tensor(0.0101, device='cuda:0'), 'train_loss_giou': tensor(0.0992, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.1705, device='cuda:0'), 'validation_loss_ce': tensor(0.0383, device='cuda:0'), 'validation_loss_bbox': tensor(0.0079, device='cuda:0'), 'validation_loss_giou': tensor(0.0464, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.1705, device='cuda:0'), 'train_loss_ce': tensor(0.0383, device='cuda:0'), 'train_loss_bbox': tensor(0.0079, device='cuda:0'), 'train_loss_giou': tensor(0.0464, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2659, device='cuda:0'), 'validation_loss_ce': tensor(0.0371, device='cuda:0'), 'validation_loss_bbox': tensor(0.0100, device='cuda:0'), 'validation_loss_giou': tensor(0.0895, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.2659, device='cuda:0'), 'train_loss_ce': tensor(0.0371, device='cuda:0'), 'train_loss_bbox': tensor(0.0100, device='cuda:0'), 'train_loss_giou': tensor(0.0895, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2592, device='cuda:0'), 'validation_loss_ce': tensor(0.0363, device='cuda:0'), 'validation_loss_bbox': tensor(0.0107, device='cuda:0'), 'validation_loss_giou': tensor(0.0846, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.2592, device='cuda:0'), 'train_loss_ce': tensor(0.0363, device='cuda:0'), 'train_loss_bbox': tensor(0.0107, device='cuda:0'), 'train_loss_giou': tensor(0.0846, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.1584, device='cuda:0'), 'validation_loss_ce': tensor(0.0354, device='cuda:0'), 'validation_loss_bbox': tensor(0.0064, device='cuda:0'), 'validation_loss_giou': tensor(0.0456, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.1584, device='cuda:0'), 'train_loss_ce': tensor(0.0354, device='cuda:0'), 'train_loss_bbox': tensor(0.0064, device='cuda:0'), 'train_loss_giou': tensor(0.0456, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2545, device='cuda:0'), 'validation_loss_ce': tensor(0.0346, device='cuda:0'), 'validation_loss_bbox': tensor(0.0073, device='cuda:0'), 'validation_loss_giou': tensor(0.0916, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.2545, device='cuda:0'), 'train_loss_ce': tensor(0.0346, device='cuda:0'), 'train_loss_bbox': tensor(0.0073, device='cuda:0'), 'train_loss_giou': tensor(0.0916, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.3034, device='cuda:0'), 'validation_loss_ce': tensor(0.0338, device='cuda:0'), 'validation_loss_bbox': tensor(0.0113, device='cuda:0'), 'validation_loss_giou': tensor(0.1066, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.3034, device='cuda:0'), 'train_loss_ce': tensor(0.0338, device='cuda:0'), 'train_loss_bbox': tensor(0.0113, device='cuda:0'), 'train_loss_giou': tensor(0.1066, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2192, device='cuda:0'), 'validation_loss_ce': tensor(0.0331, device='cuda:0'), 'validation_loss_bbox': tensor(0.0084, device='cuda:0'), 'validation_loss_giou': tensor(0.0720, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.2192, device='cuda:0'), 'train_loss_ce': tensor(0.0331, device='cuda:0'), 'train_loss_bbox': tensor(0.0084, device='cuda:0'), 'train_loss_giou': tensor(0.0720, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2407, device='cuda:0'), 'validation_loss_ce': tensor(0.0325, device='cuda:0'), 'validation_loss_bbox': tensor(0.0104, device='cuda:0'), 'validation_loss_giou': tensor(0.0780, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.2407, device='cuda:0'), 'train_loss_ce': tensor(0.0325, device='cuda:0'), 'train_loss_bbox': tensor(0.0104, device='cuda:0'), 'train_loss_giou': tensor(0.0780, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2686, device='cuda:0'), 'validation_loss_ce': tensor(0.0318, device='cuda:0'), 'validation_loss_bbox': tensor(0.0110, device='cuda:0'), 'validation_loss_giou': tensor(0.0909, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.2686, device='cuda:0'), 'train_loss_ce': tensor(0.0318, device='cuda:0'), 'train_loss_bbox': tensor(0.0110, device='cuda:0'), 'train_loss_giou': tensor(0.0909, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.1828, device='cuda:0'), 'validation_loss_ce': tensor(0.0310, device='cuda:0'), 'validation_loss_bbox': tensor(0.0067, device='cuda:0'), 'validation_loss_giou': tensor(0.0593, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.1828, device='cuda:0'), 'train_loss_ce': tensor(0.0310, device='cuda:0'), 'train_loss_bbox': tensor(0.0067, device='cuda:0'), 'train_loss_giou': tensor(0.0593, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2056, device='cuda:0'), 'validation_loss_ce': tensor(0.0303, device='cuda:0'), 'validation_loss_bbox': tensor(0.0090, device='cuda:0'), 'validation_loss_giou': tensor(0.0651, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.2056, device='cuda:0'), 'train_loss_ce': tensor(0.0303, device='cuda:0'), 'train_loss_bbox': tensor(0.0090, device='cuda:0'), 'train_loss_giou': tensor(0.0651, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2310, device='cuda:0'), 'validation_loss_ce': tensor(0.0294, device='cuda:0'), 'validation_loss_bbox': tensor(0.0096, device='cuda:0'), 'validation_loss_giou': tensor(0.0768, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.2310, device='cuda:0'), 'train_loss_ce': tensor(0.0294, device='cuda:0'), 'train_loss_bbox': tensor(0.0096, device='cuda:0'), 'train_loss_giou': tensor(0.0768, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.1602, device='cuda:0'), 'validation_loss_ce': tensor(0.0286, device='cuda:0'), 'validation_loss_bbox': tensor(0.0074, device='cuda:0'), 'validation_loss_giou': tensor(0.0473, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.1602, device='cuda:0'), 'train_loss_ce': tensor(0.0286, device='cuda:0'), 'train_loss_bbox': tensor(0.0074, device='cuda:0'), 'train_loss_giou': tensor(0.0473, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2294, device='cuda:0'), 'validation_loss_ce': tensor(0.0280, device='cuda:0'), 'validation_loss_bbox': tensor(0.0083, device='cuda:0'), 'validation_loss_giou': tensor(0.0800, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.2294, device='cuda:0'), 'train_loss_ce': tensor(0.0280, device='cuda:0'), 'train_loss_bbox': tensor(0.0083, device='cuda:0'), 'train_loss_giou': tensor(0.0800, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2559, device='cuda:0'), 'validation_loss_ce': tensor(0.0274, device='cuda:0'), 'validation_loss_bbox': tensor(0.0113, device='cuda:0'), 'validation_loss_giou': tensor(0.0859, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.2559, device='cuda:0'), 'train_loss_ce': tensor(0.0274, device='cuda:0'), 'train_loss_bbox': tensor(0.0113, device='cuda:0'), 'train_loss_giou': tensor(0.0859, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.1676, device='cuda:0'), 'validation_loss_ce': tensor(0.0266, device='cuda:0'), 'validation_loss_bbox': tensor(0.0074, device='cuda:0'), 'validation_loss_giou': tensor(0.0521, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.1676, device='cuda:0'), 'train_loss_ce': tensor(0.0266, device='cuda:0'), 'train_loss_bbox': tensor(0.0074, device='cuda:0'), 'train_loss_giou': tensor(0.0521, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.1977, device='cuda:0'), 'validation_loss_ce': tensor(0.0254, device='cuda:0'), 'validation_loss_bbox': tensor(0.0088, device='cuda:0'), 'validation_loss_giou': tensor(0.0642, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.1977, device='cuda:0'), 'train_loss_ce': tensor(0.0254, device='cuda:0'), 'train_loss_bbox': tensor(0.0088, device='cuda:0'), 'train_loss_giou': tensor(0.0642, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.1807, device='cuda:0'), 'validation_loss_ce': tensor(0.0242, device='cuda:0'), 'validation_loss_bbox': tensor(0.0086, device='cuda:0'), 'validation_loss_giou': tensor(0.0567, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.1807, device='cuda:0'), 'train_loss_ce': tensor(0.0242, device='cuda:0'), 'train_loss_bbox': tensor(0.0086, device='cuda:0'), 'train_loss_giou': tensor(0.0567, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.2037, device='cuda:0'), 'validation_loss_ce': tensor(0.0235, device='cuda:0'), 'validation_loss_bbox': tensor(0.0083, device='cuda:0'), 'validation_loss_giou': tensor(0.0693, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
{'training_loss': tensor(0.2037, device='cuda:0'), 'train_loss_ce': tensor(0.0235, device='cuda:0'), 'train_loss_bbox': tensor(0.0083, device='cuda:0'), 'train_loss_giou': tensor(0.0693, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.1670, device='cuda:0'), 'validation_loss_ce': tensor(0.0232, device='cuda:0'), 'validation_loss_bbox': tensor(0.0078, device='cuda:0'), 'validation_loss_giou': tensor(0.0525, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.1670, device='cuda:0'), 'train_loss_ce': tensor(0.0232, device='cuda:0'), 'train_loss_bbox': tensor(0.0078, device='cuda:0'), 'train_loss_giou': tensor(0.0525, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.1765, device='cuda:0'), 'validation_loss_ce': tensor(0.0229, device='cuda:0'), 'validation_loss_bbox': tensor(0.0091, device='cuda:0'), 'validation_loss_giou': tensor(0.0541, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.1765, device='cuda:0'), 'train_loss_ce': tensor(0.0229, device='cuda:0'), 'train_loss_bbox': tensor(0.0091, device='cuda:0'), 'train_loss_giou': tensor(0.0541, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.2228, device='cuda:0'), 'validation_loss_ce': tensor(0.0225, device='cuda:0'), 'validation_loss_bbox': tensor(0.0089, device='cuda:0'), 'validation_loss_giou': tensor(0.0779, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.2228, device='cuda:0'), 'train_loss_ce': tensor(0.0225, device='cuda:0'), 'train_loss_bbox': tensor(0.0089, device='cuda:0'), 'train_loss_giou': tensor(0.0779, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.1548, device='cuda:0'), 'validation_loss_ce': tensor(0.0218, device='cuda:0'), 'validation_loss_bbox': tensor(0.0060, device='cuda:0'), 'validation_loss_giou': tensor(0.0515, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1548, device='cuda:0'), 'train_loss_ce': tensor(0.0218, device='cuda:0'), 'train_loss_bbox': tensor(0.0060, device='cuda:0'), 'train_loss_giou': tensor(0.0515, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2298, device='cuda:0'), 'validation_loss_ce': tensor(0.0208, device='cuda:0'), 'validation_loss_bbox': tensor(0.0131, device='cuda:0'), 'validation_loss_giou': tensor(0.0717, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.2298, device='cuda:0'), 'train_loss_ce': tensor(0.0208, device='cuda:0'), 'train_loss_bbox': tensor(0.0131, device='cuda:0'), 'train_loss_giou': tensor(0.0717, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.2543, device='cuda:0'), 'validation_loss_ce': tensor(0.0200, device='cuda:0'), 'validation_loss_bbox': tensor(0.0151, device='cuda:0'), 'validation_loss_giou': tensor(0.0793, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.2543, device='cuda:0'), 'train_loss_ce': tensor(0.0200, device='cuda:0'), 'train_loss_bbox': tensor(0.0151, device='cuda:0'), 'train_loss_giou': tensor(0.0793, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.1557, device='cuda:0'), 'validation_loss_ce': tensor(0.0194, device='cuda:0'), 'validation_loss_bbox': tensor(0.0081, device='cuda:0'), 'validation_loss_giou': tensor(0.0480, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1557, device='cuda:0'), 'train_loss_ce': tensor(0.0194, device='cuda:0'), 'train_loss_bbox': tensor(0.0081, device='cuda:0'), 'train_loss_giou': tensor(0.0480, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1749, device='cuda:0'), 'validation_loss_ce': tensor(0.0190, device='cuda:0'), 'validation_loss_bbox': tensor(0.0081, device='cuda:0'), 'validation_loss_giou': tensor(0.0577, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1749, device='cuda:0'), 'train_loss_ce': tensor(0.0190, device='cuda:0'), 'train_loss_bbox': tensor(0.0081, device='cuda:0'), 'train_loss_giou': tensor(0.0577, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2357, device='cuda:0'), 'validation_loss_ce': tensor(0.0184, device='cuda:0'), 'validation_loss_bbox': tensor(0.0119, device='cuda:0'), 'validation_loss_giou': tensor(0.0790, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2357, device='cuda:0'), 'train_loss_ce': tensor(0.0184, device='cuda:0'), 'train_loss_bbox': tensor(0.0119, device='cuda:0'), 'train_loss_giou': tensor(0.0790, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2063, device='cuda:0'), 'validation_loss_ce': tensor(0.0177, device='cuda:0'), 'validation_loss_bbox': tensor(0.0090, device='cuda:0'), 'validation_loss_giou': tensor(0.0719, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2063, device='cuda:0'), 'train_loss_ce': tensor(0.0177, device='cuda:0'), 'train_loss_bbox': tensor(0.0090, device='cuda:0'), 'train_loss_giou': tensor(0.0719, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1656, device='cuda:0'), 'validation_loss_ce': tensor(0.0170, device='cuda:0'), 'validation_loss_bbox': tensor(0.0068, device='cuda:0'), 'validation_loss_giou': tensor(0.0572, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.1656, device='cuda:0'), 'train_loss_ce': tensor(0.0170, device='cuda:0'), 'train_loss_bbox': tensor(0.0068, device='cuda:0'), 'train_loss_giou': tensor(0.0572, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.1819, device='cuda:0'), 'validation_loss_ce': tensor(0.0165, device='cuda:0'), 'validation_loss_bbox': tensor(0.0086, device='cuda:0'), 'validation_loss_giou': tensor(0.0613, device='cuda:0'), 'validation_cardinality_error': tensor(0.5000, device='cuda:0')}
{'training_loss': tensor(0.1819, device='cuda:0'), 'train_loss_ce': tensor(0.0165, device='cuda:0'), 'train_loss_bbox': tensor(0.0086, device='cuda:0'), 'train_loss_giou': tensor(0.0613, device='cuda:0'), 'train_cardinality_error': tensor(0.5000, device='cuda:0'), 'validation_loss': tensor(0.1635, device='cuda:0'), 'validation_loss_ce': tensor(0.0159, device='cuda:0'), 'validation_loss_bbox': tensor(0.0073, device='cuda:0'), 'validation_loss_giou': tensor(0.0554, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1635, device='cuda:0'), 'train_loss_ce': tensor(0.0159, device='cuda:0'), 'train_loss_bbox': tensor(0.0073, device='cuda:0'), 'train_loss_giou': tensor(0.0554, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1871, device='cuda:0'), 'validation_loss_ce': tensor(0.0153, device='cuda:0'), 'validation_loss_bbox': tensor(0.0074, device='cuda:0'), 'validation_loss_giou': tensor(0.0675, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1871, device='cuda:0'), 'train_loss_ce': tensor(0.0153, device='cuda:0'), 'train_loss_bbox': tensor(0.0074, device='cuda:0'), 'train_loss_giou': tensor(0.0675, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1836, device='cuda:0'), 'validation_loss_ce': tensor(0.0150, device='cuda:0'), 'validation_loss_bbox': tensor(0.0098, device='cuda:0'), 'validation_loss_giou': tensor(0.0598, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1836, device='cuda:0'), 'train_loss_ce': tensor(0.0150, device='cuda:0'), 'train_loss_bbox': tensor(0.0098, device='cuda:0'), 'train_loss_giou': tensor(0.0598, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1827, device='cuda:0'), 'validation_loss_ce': tensor(0.0145, device='cuda:0'), 'validation_loss_bbox': tensor(0.0093, device='cuda:0'), 'validation_loss_giou': tensor(0.0608, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1827, device='cuda:0'), 'train_loss_ce': tensor(0.0145, device='cuda:0'), 'train_loss_bbox': tensor(0.0093, device='cuda:0'), 'train_loss_giou': tensor(0.0608, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2484, device='cuda:0'), 'validation_loss_ce': tensor(0.0142, device='cuda:0'), 'validation_loss_bbox': tensor(0.0118, device='cuda:0'), 'validation_loss_giou': tensor(0.0876, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2484, device='cuda:0'), 'train_loss_ce': tensor(0.0142, device='cuda:0'), 'train_loss_bbox': tensor(0.0118, device='cuda:0'), 'train_loss_giou': tensor(0.0876, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3151, device='cuda:0'), 'validation_loss_ce': tensor(0.0138, device='cuda:0'), 'validation_loss_bbox': tensor(0.0142, device='cuda:0'), 'validation_loss_giou': tensor(0.1152, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3151, device='cuda:0'), 'train_loss_ce': tensor(0.0138, device='cuda:0'), 'train_loss_bbox': tensor(0.0142, device='cuda:0'), 'train_loss_giou': tensor(0.1152, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2890, device='cuda:0'), 'validation_loss_ce': tensor(0.0135, device='cuda:0'), 'validation_loss_bbox': tensor(0.0115, device='cuda:0'), 'validation_loss_giou': tensor(0.1091, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2890, device='cuda:0'), 'train_loss_ce': tensor(0.0135, device='cuda:0'), 'train_loss_bbox': tensor(0.0115, device='cuda:0'), 'train_loss_giou': tensor(0.1091, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1245, device='cuda:0'), 'validation_loss_ce': tensor(0.0137, device='cuda:0'), 'validation_loss_bbox': tensor(0.0055, device='cuda:0'), 'validation_loss_giou': tensor(0.0416, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1245, device='cuda:0'), 'train_loss_ce': tensor(0.0137, device='cuda:0'), 'train_loss_bbox': tensor(0.0055, device='cuda:0'), 'train_loss_giou': tensor(0.0416, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2204, device='cuda:0'), 'validation_loss_ce': tensor(0.0151, device='cuda:0'), 'validation_loss_bbox': tensor(0.0096, device='cuda:0'), 'validation_loss_giou': tensor(0.0786, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2204, device='cuda:0'), 'train_loss_ce': tensor(0.0151, device='cuda:0'), 'train_loss_bbox': tensor(0.0096, device='cuda:0'), 'train_loss_giou': tensor(0.0786, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2524, device='cuda:0'), 'validation_loss_ce': tensor(0.0153, device='cuda:0'), 'validation_loss_bbox': tensor(0.0121, device='cuda:0'), 'validation_loss_giou': tensor(0.0883, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2524, device='cuda:0'), 'train_loss_ce': tensor(0.0153, device='cuda:0'), 'train_loss_bbox': tensor(0.0121, device='cuda:0'), 'train_loss_giou': tensor(0.0883, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2031, device='cuda:0'), 'validation_loss_ce': tensor(0.0142, device='cuda:0'), 'validation_loss_bbox': tensor(0.0106, device='cuda:0'), 'validation_loss_giou': tensor(0.0679, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2031, device='cuda:0'), 'train_loss_ce': tensor(0.0142, device='cuda:0'), 'train_loss_bbox': tensor(0.0106, device='cuda:0'), 'train_loss_giou': tensor(0.0679, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1970, device='cuda:0'), 'validation_loss_ce': tensor(0.0131, device='cuda:0'), 'validation_loss_bbox': tensor(0.0084, device='cuda:0'), 'validation_loss_giou': tensor(0.0709, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1970, device='cuda:0'), 'train_loss_ce': tensor(0.0131, device='cuda:0'), 'train_loss_bbox': tensor(0.0084, device='cuda:0'), 'train_loss_giou': tensor(0.0709, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2780, device='cuda:0'), 'validation_loss_ce': tensor(0.0125, device='cuda:0'), 'validation_loss_bbox': tensor(0.0110, device='cuda:0'), 'validation_loss_giou': tensor(0.1054, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2780, device='cuda:0'), 'train_loss_ce': tensor(0.0125, device='cuda:0'), 'train_loss_bbox': tensor(0.0110, device='cuda:0'), 'train_loss_giou': tensor(0.1054, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2422, device='cuda:0'), 'validation_loss_ce': tensor(0.0124, device='cuda:0'), 'validation_loss_bbox': tensor(0.0117, device='cuda:0'), 'validation_loss_giou': tensor(0.0858, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2422, device='cuda:0'), 'train_loss_ce': tensor(0.0124, device='cuda:0'), 'train_loss_bbox': tensor(0.0117, device='cuda:0'), 'train_loss_giou': tensor(0.0858, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2422, device='cuda:0'), 'validation_loss_ce': tensor(0.0120, device='cuda:0'), 'validation_loss_bbox': tensor(0.0123, device='cuda:0'), 'validation_loss_giou': tensor(0.0842, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2422, device='cuda:0'), 'train_loss_ce': tensor(0.0120, device='cuda:0'), 'train_loss_bbox': tensor(0.0123, device='cuda:0'), 'train_loss_giou': tensor(0.0842, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2694, device='cuda:0'), 'validation_loss_ce': tensor(0.0121, device='cuda:0'), 'validation_loss_bbox': tensor(0.0123, device='cuda:0'), 'validation_loss_giou': tensor(0.0979, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2694, device='cuda:0'), 'train_loss_ce': tensor(0.0121, device='cuda:0'), 'train_loss_bbox': tensor(0.0123, device='cuda:0'), 'train_loss_giou': tensor(0.0979, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2531, device='cuda:0'), 'validation_loss_ce': tensor(0.0126, device='cuda:0'), 'validation_loss_bbox': tensor(0.0122, device='cuda:0'), 'validation_loss_giou': tensor(0.0898, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2531, device='cuda:0'), 'train_loss_ce': tensor(0.0126, device='cuda:0'), 'train_loss_bbox': tensor(0.0122, device='cuda:0'), 'train_loss_giou': tensor(0.0898, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2334, device='cuda:0'), 'validation_loss_ce': tensor(0.0128, device='cuda:0'), 'validation_loss_bbox': tensor(0.0122, device='cuda:0'), 'validation_loss_giou': tensor(0.0797, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2334, device='cuda:0'), 'train_loss_ce': tensor(0.0128, device='cuda:0'), 'train_loss_bbox': tensor(0.0122, device='cuda:0'), 'train_loss_giou': tensor(0.0797, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2111, device='cuda:0'), 'validation_loss_ce': tensor(0.0122, device='cuda:0'), 'validation_loss_bbox': tensor(0.0119, device='cuda:0'), 'validation_loss_giou': tensor(0.0698, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2111, device='cuda:0'), 'train_loss_ce': tensor(0.0122, device='cuda:0'), 'train_loss_bbox': tensor(0.0119, device='cuda:0'), 'train_loss_giou': tensor(0.0698, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2438, device='cuda:0'), 'validation_loss_ce': tensor(0.0113, device='cuda:0'), 'validation_loss_bbox': tensor(0.0092, device='cuda:0'), 'validation_loss_giou': tensor(0.0932, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2438, device='cuda:0'), 'train_loss_ce': tensor(0.0113, device='cuda:0'), 'train_loss_bbox': tensor(0.0092, device='cuda:0'), 'train_loss_giou': tensor(0.0932, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1562, device='cuda:0'), 'validation_loss_ce': tensor(0.0111, device='cuda:0'), 'validation_loss_bbox': tensor(0.0076, device='cuda:0'), 'validation_loss_giou': tensor(0.0536, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1562, device='cuda:0'), 'train_loss_ce': tensor(0.0111, device='cuda:0'), 'train_loss_bbox': tensor(0.0076, device='cuda:0'), 'train_loss_giou': tensor(0.0536, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2693, device='cuda:0'), 'validation_loss_ce': tensor(0.0111, device='cuda:0'), 'validation_loss_bbox': tensor(0.0125, device='cuda:0'), 'validation_loss_giou': tensor(0.0977, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2693, device='cuda:0'), 'train_loss_ce': tensor(0.0111, device='cuda:0'), 'train_loss_bbox': tensor(0.0125, device='cuda:0'), 'train_loss_giou': tensor(0.0977, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2538, device='cuda:0'), 'validation_loss_ce': tensor(0.0104, device='cuda:0'), 'validation_loss_bbox': tensor(0.0110, device='cuda:0'), 'validation_loss_giou': tensor(0.0943, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2538, device='cuda:0'), 'train_loss_ce': tensor(0.0104, device='cuda:0'), 'train_loss_bbox': tensor(0.0110, device='cuda:0'), 'train_loss_giou': tensor(0.0943, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.0871, device='cuda:0'), 'validation_loss_ce': tensor(0.0097, device='cuda:0'), 'validation_loss_bbox': tensor(0.0044, device='cuda:0'), 'validation_loss_giou': tensor(0.0277, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.0871, device='cuda:0'), 'train_loss_ce': tensor(0.0097, device='cuda:0'), 'train_loss_bbox': tensor(0.0044, device='cuda:0'), 'train_loss_giou': tensor(0.0277, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3141, device='cuda:0'), 'validation_loss_ce': tensor(0.0100, device='cuda:0'), 'validation_loss_bbox': tensor(0.0112, device='cuda:0'), 'validation_loss_giou': tensor(0.1241, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3141, device='cuda:0'), 'train_loss_ce': tensor(0.0100, device='cuda:0'), 'train_loss_bbox': tensor(0.0112, device='cuda:0'), 'train_loss_giou': tensor(0.1241, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3379, device='cuda:0'), 'validation_loss_ce': tensor(0.0102, device='cuda:0'), 'validation_loss_bbox': tensor(0.0139, device='cuda:0'), 'validation_loss_giou': tensor(0.1290, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3379, device='cuda:0'), 'train_loss_ce': tensor(0.0102, device='cuda:0'), 'train_loss_bbox': tensor(0.0139, device='cuda:0'), 'train_loss_giou': tensor(0.1290, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3033, device='cuda:0'), 'validation_loss_ce': tensor(0.0098, device='cuda:0'), 'validation_loss_bbox': tensor(0.0128, device='cuda:0'), 'validation_loss_giou': tensor(0.1148, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3033, device='cuda:0'), 'train_loss_ce': tensor(0.0098, device='cuda:0'), 'train_loss_bbox': tensor(0.0128, device='cuda:0'), 'train_loss_giou': tensor(0.1148, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2814, device='cuda:0'), 'validation_loss_ce': tensor(0.0091, device='cuda:0'), 'validation_loss_bbox': tensor(0.0104, device='cuda:0'), 'validation_loss_giou': tensor(0.1102, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2814, device='cuda:0'), 'train_loss_ce': tensor(0.0091, device='cuda:0'), 'train_loss_bbox': tensor(0.0104, device='cuda:0'), 'train_loss_giou': tensor(0.1102, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2810, device='cuda:0'), 'validation_loss_ce': tensor(0.0088, device='cuda:0'), 'validation_loss_bbox': tensor(0.0104, device='cuda:0'), 'validation_loss_giou': tensor(0.1101, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2810, device='cuda:0'), 'train_loss_ce': tensor(0.0088, device='cuda:0'), 'train_loss_bbox': tensor(0.0104, device='cuda:0'), 'train_loss_giou': tensor(0.1101, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2601, device='cuda:0'), 'validation_loss_ce': tensor(0.0087, device='cuda:0'), 'validation_loss_bbox': tensor(0.0126, device='cuda:0'), 'validation_loss_giou': tensor(0.0941, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2601, device='cuda:0'), 'train_loss_ce': tensor(0.0087, device='cuda:0'), 'train_loss_bbox': tensor(0.0126, device='cuda:0'), 'train_loss_giou': tensor(0.0941, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2376, device='cuda:0'), 'validation_loss_ce': tensor(0.0087, device='cuda:0'), 'validation_loss_bbox': tensor(0.0122, device='cuda:0'), 'validation_loss_giou': tensor(0.0840, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2376, device='cuda:0'), 'train_loss_ce': tensor(0.0087, device='cuda:0'), 'train_loss_bbox': tensor(0.0122, device='cuda:0'), 'train_loss_giou': tensor(0.0840, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2287, device='cuda:0'), 'validation_loss_ce': tensor(0.0087, device='cuda:0'), 'validation_loss_bbox': tensor(0.0116, device='cuda:0'), 'validation_loss_giou': tensor(0.0811, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2287, device='cuda:0'), 'train_loss_ce': tensor(0.0087, device='cuda:0'), 'train_loss_bbox': tensor(0.0116, device='cuda:0'), 'train_loss_giou': tensor(0.0811, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2307, device='cuda:0'), 'validation_loss_ce': tensor(0.0086, device='cuda:0'), 'validation_loss_bbox': tensor(0.0084, device='cuda:0'), 'validation_loss_giou': tensor(0.0901, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2307, device='cuda:0'), 'train_loss_ce': tensor(0.0086, device='cuda:0'), 'train_loss_bbox': tensor(0.0084, device='cuda:0'), 'train_loss_giou': tensor(0.0901, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1298, device='cuda:0'), 'validation_loss_ce': tensor(0.0083, device='cuda:0'), 'validation_loss_bbox': tensor(0.0054, device='cuda:0'), 'validation_loss_giou': tensor(0.0473, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1298, device='cuda:0'), 'train_loss_ce': tensor(0.0083, device='cuda:0'), 'train_loss_bbox': tensor(0.0054, device='cuda:0'), 'train_loss_giou': tensor(0.0473, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2433, device='cuda:0'), 'validation_loss_ce': tensor(0.0082, device='cuda:0'), 'validation_loss_bbox': tensor(0.0095, device='cuda:0'), 'validation_loss_giou': tensor(0.0938, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2433, device='cuda:0'), 'train_loss_ce': tensor(0.0082, device='cuda:0'), 'train_loss_bbox': tensor(0.0095, device='cuda:0'), 'train_loss_giou': tensor(0.0938, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3300, device='cuda:0'), 'validation_loss_ce': tensor(0.0080, device='cuda:0'), 'validation_loss_bbox': tensor(0.0145, device='cuda:0'), 'validation_loss_giou': tensor(0.1247, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3300, device='cuda:0'), 'train_loss_ce': tensor(0.0080, device='cuda:0'), 'train_loss_bbox': tensor(0.0145, device='cuda:0'), 'train_loss_giou': tensor(0.1247, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2760, device='cuda:0'), 'validation_loss_ce': tensor(0.0077, device='cuda:0'), 'validation_loss_bbox': tensor(0.0123, device='cuda:0'), 'validation_loss_giou': tensor(0.1034, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2760, device='cuda:0'), 'train_loss_ce': tensor(0.0077, device='cuda:0'), 'train_loss_bbox': tensor(0.0123, device='cuda:0'), 'train_loss_giou': tensor(0.1034, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1365, device='cuda:0'), 'validation_loss_ce': tensor(0.0074, device='cuda:0'), 'validation_loss_bbox': tensor(0.0073, device='cuda:0'), 'validation_loss_giou': tensor(0.0463, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1365, device='cuda:0'), 'train_loss_ce': tensor(0.0074, device='cuda:0'), 'train_loss_bbox': tensor(0.0073, device='cuda:0'), 'train_loss_giou': tensor(0.0463, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3019, device='cuda:0'), 'validation_loss_ce': tensor(0.0070, device='cuda:0'), 'validation_loss_bbox': tensor(0.0121, device='cuda:0'), 'validation_loss_giou': tensor(0.1171, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3019, device='cuda:0'), 'train_loss_ce': tensor(0.0070, device='cuda:0'), 'train_loss_bbox': tensor(0.0121, device='cuda:0'), 'train_loss_giou': tensor(0.1171, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3336, device='cuda:0'), 'validation_loss_ce': tensor(0.0069, device='cuda:0'), 'validation_loss_bbox': tensor(0.0149, device='cuda:0'), 'validation_loss_giou': tensor(0.1260, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3336, device='cuda:0'), 'train_loss_ce': tensor(0.0069, device='cuda:0'), 'train_loss_bbox': tensor(0.0149, device='cuda:0'), 'train_loss_giou': tensor(0.1260, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2558, device='cuda:0'), 'validation_loss_ce': tensor(0.0069, device='cuda:0'), 'validation_loss_bbox': tensor(0.0107, device='cuda:0'), 'validation_loss_giou': tensor(0.0976, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2558, device='cuda:0'), 'train_loss_ce': tensor(0.0069, device='cuda:0'), 'train_loss_bbox': tensor(0.0107, device='cuda:0'), 'train_loss_giou': tensor(0.0976, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1840, device='cuda:0'), 'validation_loss_ce': tensor(0.0069, device='cuda:0'), 'validation_loss_bbox': tensor(0.0093, device='cuda:0'), 'validation_loss_giou': tensor(0.0654, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1840, device='cuda:0'), 'train_loss_ce': tensor(0.0069, device='cuda:0'), 'train_loss_bbox': tensor(0.0093, device='cuda:0'), 'train_loss_giou': tensor(0.0654, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2434, device='cuda:0'), 'validation_loss_ce': tensor(0.0068, device='cuda:0'), 'validation_loss_bbox': tensor(0.0102, device='cuda:0'), 'validation_loss_giou': tensor(0.0928, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2434, device='cuda:0'), 'train_loss_ce': tensor(0.0068, device='cuda:0'), 'train_loss_bbox': tensor(0.0102, device='cuda:0'), 'train_loss_giou': tensor(0.0928, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2289, device='cuda:0'), 'validation_loss_ce': tensor(0.0067, device='cuda:0'), 'validation_loss_bbox': tensor(0.0098, device='cuda:0'), 'validation_loss_giou': tensor(0.0865, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2289, device='cuda:0'), 'train_loss_ce': tensor(0.0067, device='cuda:0'), 'train_loss_bbox': tensor(0.0098, device='cuda:0'), 'train_loss_giou': tensor(0.0865, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2336, device='cuda:0'), 'validation_loss_ce': tensor(0.0066, device='cuda:0'), 'validation_loss_bbox': tensor(0.0135, device='cuda:0'), 'validation_loss_giou': tensor(0.0798, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2336, device='cuda:0'), 'train_loss_ce': tensor(0.0066, device='cuda:0'), 'train_loss_bbox': tensor(0.0135, device='cuda:0'), 'train_loss_giou': tensor(0.0798, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3234, device='cuda:0'), 'validation_loss_ce': tensor(0.0063, device='cuda:0'), 'validation_loss_bbox': tensor(0.0172, device='cuda:0'), 'validation_loss_giou': tensor(0.1155, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3234, device='cuda:0'), 'train_loss_ce': tensor(0.0063, device='cuda:0'), 'train_loss_bbox': tensor(0.0172, device='cuda:0'), 'train_loss_giou': tensor(0.1155, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3425, device='cuda:0'), 'validation_loss_ce': tensor(0.0062, device='cuda:0'), 'validation_loss_bbox': tensor(0.0176, device='cuda:0'), 'validation_loss_giou': tensor(0.1242, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3425, device='cuda:0'), 'train_loss_ce': tensor(0.0062, device='cuda:0'), 'train_loss_bbox': tensor(0.0176, device='cuda:0'), 'train_loss_giou': tensor(0.1242, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2623, device='cuda:0'), 'validation_loss_ce': tensor(0.0061, device='cuda:0'), 'validation_loss_bbox': tensor(0.0116, device='cuda:0'), 'validation_loss_giou': tensor(0.0992, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2623, device='cuda:0'), 'train_loss_ce': tensor(0.0061, device='cuda:0'), 'train_loss_bbox': tensor(0.0116, device='cuda:0'), 'train_loss_giou': tensor(0.0992, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1937, device='cuda:0'), 'validation_loss_ce': tensor(0.0060, device='cuda:0'), 'validation_loss_bbox': tensor(0.0077, device='cuda:0'), 'validation_loss_giou': tensor(0.0745, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1937, device='cuda:0'), 'train_loss_ce': tensor(0.0060, device='cuda:0'), 'train_loss_bbox': tensor(0.0077, device='cuda:0'), 'train_loss_giou': tensor(0.0745, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3438, device='cuda:0'), 'validation_loss_ce': tensor(0.0060, device='cuda:0'), 'validation_loss_bbox': tensor(0.0149, device='cuda:0'), 'validation_loss_giou': tensor(0.1316, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3438, device='cuda:0'), 'train_loss_ce': tensor(0.0060, device='cuda:0'), 'train_loss_bbox': tensor(0.0149, device='cuda:0'), 'train_loss_giou': tensor(0.1316, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3953, device='cuda:0'), 'validation_loss_ce': tensor(0.0059, device='cuda:0'), 'validation_loss_bbox': tensor(0.0194, device='cuda:0'), 'validation_loss_giou': tensor(0.1463, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3953, device='cuda:0'), 'train_loss_ce': tensor(0.0059, device='cuda:0'), 'train_loss_bbox': tensor(0.0194, device='cuda:0'), 'train_loss_giou': tensor(0.1463, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3053, device='cuda:0'), 'validation_loss_ce': tensor(0.0058, device='cuda:0'), 'validation_loss_bbox': tensor(0.0172, device='cuda:0'), 'validation_loss_giou': tensor(0.1067, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3053, device='cuda:0'), 'train_loss_ce': tensor(0.0058, device='cuda:0'), 'train_loss_bbox': tensor(0.0172, device='cuda:0'), 'train_loss_giou': tensor(0.1067, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3345, device='cuda:0'), 'validation_loss_ce': tensor(0.0058, device='cuda:0'), 'validation_loss_bbox': tensor(0.0153, device='cuda:0'), 'validation_loss_giou': tensor(0.1262, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3345, device='cuda:0'), 'train_loss_ce': tensor(0.0058, device='cuda:0'), 'train_loss_bbox': tensor(0.0153, device='cuda:0'), 'train_loss_giou': tensor(0.1262, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2791, device='cuda:0'), 'validation_loss_ce': tensor(0.0057, device='cuda:0'), 'validation_loss_bbox': tensor(0.0118, device='cuda:0'), 'validation_loss_giou': tensor(0.1072, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2791, device='cuda:0'), 'train_loss_ce': tensor(0.0057, device='cuda:0'), 'train_loss_bbox': tensor(0.0118, device='cuda:0'), 'train_loss_giou': tensor(0.1072, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2469, device='cuda:0'), 'validation_loss_ce': tensor(0.0056, device='cuda:0'), 'validation_loss_bbox': tensor(0.0097, device='cuda:0'), 'validation_loss_giou': tensor(0.0963, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2469, device='cuda:0'), 'train_loss_ce': tensor(0.0056, device='cuda:0'), 'train_loss_bbox': tensor(0.0097, device='cuda:0'), 'train_loss_giou': tensor(0.0963, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2663, device='cuda:0'), 'validation_loss_ce': tensor(0.0055, device='cuda:0'), 'validation_loss_bbox': tensor(0.0143, device='cuda:0'), 'validation_loss_giou': tensor(0.0945, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2663, device='cuda:0'), 'train_loss_ce': tensor(0.0055, device='cuda:0'), 'train_loss_bbox': tensor(0.0143, device='cuda:0'), 'train_loss_giou': tensor(0.0945, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3384, device='cuda:0'), 'validation_loss_ce': tensor(0.0054, device='cuda:0'), 'validation_loss_bbox': tensor(0.0148, device='cuda:0'), 'validation_loss_giou': tensor(0.1294, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3384, device='cuda:0'), 'train_loss_ce': tensor(0.0054, device='cuda:0'), 'train_loss_bbox': tensor(0.0148, device='cuda:0'), 'train_loss_giou': tensor(0.1294, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2651, device='cuda:0'), 'validation_loss_ce': tensor(0.0053, device='cuda:0'), 'validation_loss_bbox': tensor(0.0140, device='cuda:0'), 'validation_loss_giou': tensor(0.0949, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2651, device='cuda:0'), 'train_loss_ce': tensor(0.0053, device='cuda:0'), 'train_loss_bbox': tensor(0.0140, device='cuda:0'), 'train_loss_giou': tensor(0.0949, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3123, device='cuda:0'), 'validation_loss_ce': tensor(0.0052, device='cuda:0'), 'validation_loss_bbox': tensor(0.0126, device='cuda:0'), 'validation_loss_giou': tensor(0.1220, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3123, device='cuda:0'), 'train_loss_ce': tensor(0.0052, device='cuda:0'), 'train_loss_bbox': tensor(0.0126, device='cuda:0'), 'train_loss_giou': tensor(0.1220, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2979, device='cuda:0'), 'validation_loss_ce': tensor(0.0051, device='cuda:0'), 'validation_loss_bbox': tensor(0.0098, device='cuda:0'), 'validation_loss_giou': tensor(0.1218, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2979, device='cuda:0'), 'train_loss_ce': tensor(0.0051, device='cuda:0'), 'train_loss_bbox': tensor(0.0098, device='cuda:0'), 'train_loss_giou': tensor(0.1218, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2771, device='cuda:0'), 'validation_loss_ce': tensor(0.0051, device='cuda:0'), 'validation_loss_bbox': tensor(0.0111, device='cuda:0'), 'validation_loss_giou': tensor(0.1082, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2771, device='cuda:0'), 'train_loss_ce': tensor(0.0051, device='cuda:0'), 'train_loss_bbox': tensor(0.0111, device='cuda:0'), 'train_loss_giou': tensor(0.1082, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2593, device='cuda:0'), 'validation_loss_ce': tensor(0.0051, device='cuda:0'), 'validation_loss_bbox': tensor(0.0118, device='cuda:0'), 'validation_loss_giou': tensor(0.0976, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2593, device='cuda:0'), 'train_loss_ce': tensor(0.0051, device='cuda:0'), 'train_loss_bbox': tensor(0.0118, device='cuda:0'), 'train_loss_giou': tensor(0.0976, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2314, device='cuda:0'), 'validation_loss_ce': tensor(0.0051, device='cuda:0'), 'validation_loss_bbox': tensor(0.0113, device='cuda:0'), 'validation_loss_giou': tensor(0.0849, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2314, device='cuda:0'), 'train_loss_ce': tensor(0.0051, device='cuda:0'), 'train_loss_bbox': tensor(0.0113, device='cuda:0'), 'train_loss_giou': tensor(0.0849, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2144, device='cuda:0'), 'validation_loss_ce': tensor(0.0051, device='cuda:0'), 'validation_loss_bbox': tensor(0.0086, device='cuda:0'), 'validation_loss_giou': tensor(0.0831, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2144, device='cuda:0'), 'train_loss_ce': tensor(0.0051, device='cuda:0'), 'train_loss_bbox': tensor(0.0086, device='cuda:0'), 'train_loss_giou': tensor(0.0831, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2268, device='cuda:0'), 'validation_loss_ce': tensor(0.0051, device='cuda:0'), 'validation_loss_bbox': tensor(0.0099, device='cuda:0'), 'validation_loss_giou': tensor(0.0860, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2268, device='cuda:0'), 'train_loss_ce': tensor(0.0051, device='cuda:0'), 'train_loss_bbox': tensor(0.0099, device='cuda:0'), 'train_loss_giou': tensor(0.0860, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2667, device='cuda:0'), 'validation_loss_ce': tensor(0.0050, device='cuda:0'), 'validation_loss_bbox': tensor(0.0122, device='cuda:0'), 'validation_loss_giou': tensor(0.1003, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2667, device='cuda:0'), 'train_loss_ce': tensor(0.0050, device='cuda:0'), 'train_loss_bbox': tensor(0.0122, device='cuda:0'), 'train_loss_giou': tensor(0.1003, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1828, device='cuda:0'), 'validation_loss_ce': tensor(0.0049, device='cuda:0'), 'validation_loss_bbox': tensor(0.0103, device='cuda:0'), 'validation_loss_giou': tensor(0.0632, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1828, device='cuda:0'), 'train_loss_ce': tensor(0.0049, device='cuda:0'), 'train_loss_bbox': tensor(0.0103, device='cuda:0'), 'train_loss_giou': tensor(0.0632, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2312, device='cuda:0'), 'validation_loss_ce': tensor(0.0048, device='cuda:0'), 'validation_loss_bbox': tensor(0.0107, device='cuda:0'), 'validation_loss_giou': tensor(0.0864, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2312, device='cuda:0'), 'train_loss_ce': tensor(0.0048, device='cuda:0'), 'train_loss_bbox': tensor(0.0107, device='cuda:0'), 'train_loss_giou': tensor(0.0864, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2423, device='cuda:0'), 'validation_loss_ce': tensor(0.0047, device='cuda:0'), 'validation_loss_bbox': tensor(0.0090, device='cuda:0'), 'validation_loss_giou': tensor(0.0964, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2423, device='cuda:0'), 'train_loss_ce': tensor(0.0047, device='cuda:0'), 'train_loss_bbox': tensor(0.0090, device='cuda:0'), 'train_loss_giou': tensor(0.0964, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.0665, device='cuda:0'), 'validation_loss_ce': tensor(0.0046, device='cuda:0'), 'validation_loss_bbox': tensor(0.0034, device='cuda:0'), 'validation_loss_giou': tensor(0.0224, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.0665, device='cuda:0'), 'train_loss_ce': tensor(0.0046, device='cuda:0'), 'train_loss_bbox': tensor(0.0034, device='cuda:0'), 'train_loss_giou': tensor(0.0224, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1930, device='cuda:0'), 'validation_loss_ce': tensor(0.0046, device='cuda:0'), 'validation_loss_bbox': tensor(0.0081, device='cuda:0'), 'validation_loss_giou': tensor(0.0740, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1930, device='cuda:0'), 'train_loss_ce': tensor(0.0046, device='cuda:0'), 'train_loss_bbox': tensor(0.0081, device='cuda:0'), 'train_loss_giou': tensor(0.0740, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2849, device='cuda:0'), 'validation_loss_ce': tensor(0.0045, device='cuda:0'), 'validation_loss_bbox': tensor(0.0112, device='cuda:0'), 'validation_loss_giou': tensor(0.1122, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2849, device='cuda:0'), 'train_loss_ce': tensor(0.0045, device='cuda:0'), 'train_loss_bbox': tensor(0.0112, device='cuda:0'), 'train_loss_giou': tensor(0.1122, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1956, device='cuda:0'), 'validation_loss_ce': tensor(0.0044, device='cuda:0'), 'validation_loss_bbox': tensor(0.0075, device='cuda:0'), 'validation_loss_giou': tensor(0.0769, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1956, device='cuda:0'), 'train_loss_ce': tensor(0.0044, device='cuda:0'), 'train_loss_bbox': tensor(0.0075, device='cuda:0'), 'train_loss_giou': tensor(0.0769, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1454, device='cuda:0'), 'validation_loss_ce': tensor(0.0044, device='cuda:0'), 'validation_loss_bbox': tensor(0.0061, device='cuda:0'), 'validation_loss_giou': tensor(0.0553, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1454, device='cuda:0'), 'train_loss_ce': tensor(0.0044, device='cuda:0'), 'train_loss_bbox': tensor(0.0061, device='cuda:0'), 'train_loss_giou': tensor(0.0553, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2098, device='cuda:0'), 'validation_loss_ce': tensor(0.0043, device='cuda:0'), 'validation_loss_bbox': tensor(0.0072, device='cuda:0'), 'validation_loss_giou': tensor(0.0848, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2098, device='cuda:0'), 'train_loss_ce': tensor(0.0043, device='cuda:0'), 'train_loss_bbox': tensor(0.0072, device='cuda:0'), 'train_loss_giou': tensor(0.0848, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1164, device='cuda:0'), 'validation_loss_ce': tensor(0.0043, device='cuda:0'), 'validation_loss_bbox': tensor(0.0050, device='cuda:0'), 'validation_loss_giou': tensor(0.0436, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1164, device='cuda:0'), 'train_loss_ce': tensor(0.0043, device='cuda:0'), 'train_loss_bbox': tensor(0.0050, device='cuda:0'), 'train_loss_giou': tensor(0.0436, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2209, device='cuda:0'), 'validation_loss_ce': tensor(0.0043, device='cuda:0'), 'validation_loss_bbox': tensor(0.0085, device='cuda:0'), 'validation_loss_giou': tensor(0.0871, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2209, device='cuda:0'), 'train_loss_ce': tensor(0.0043, device='cuda:0'), 'train_loss_bbox': tensor(0.0085, device='cuda:0'), 'train_loss_giou': tensor(0.0871, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2499, device='cuda:0'), 'validation_loss_ce': tensor(0.0042, device='cuda:0'), 'validation_loss_bbox': tensor(0.0091, device='cuda:0'), 'validation_loss_giou': tensor(0.1000, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2499, device='cuda:0'), 'train_loss_ce': tensor(0.0042, device='cuda:0'), 'train_loss_bbox': tensor(0.0091, device='cuda:0'), 'train_loss_giou': tensor(0.1000, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1557, device='cuda:0'), 'validation_loss_ce': tensor(0.0041, device='cuda:0'), 'validation_loss_bbox': tensor(0.0064, device='cuda:0'), 'validation_loss_giou': tensor(0.0597, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1557, device='cuda:0'), 'train_loss_ce': tensor(0.0041, device='cuda:0'), 'train_loss_bbox': tensor(0.0064, device='cuda:0'), 'train_loss_giou': tensor(0.0597, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1533, device='cuda:0'), 'validation_loss_ce': tensor(0.0040, device='cuda:0'), 'validation_loss_bbox': tensor(0.0069, device='cuda:0'), 'validation_loss_giou': tensor(0.0575, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1533, device='cuda:0'), 'train_loss_ce': tensor(0.0040, device='cuda:0'), 'train_loss_bbox': tensor(0.0069, device='cuda:0'), 'train_loss_giou': tensor(0.0575, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1770, device='cuda:0'), 'validation_loss_ce': tensor(0.0040, device='cuda:0'), 'validation_loss_bbox': tensor(0.0069, device='cuda:0'), 'validation_loss_giou': tensor(0.0693, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1770, device='cuda:0'), 'train_loss_ce': tensor(0.0040, device='cuda:0'), 'train_loss_bbox': tensor(0.0069, device='cuda:0'), 'train_loss_giou': tensor(0.0693, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1144, device='cuda:0'), 'validation_loss_ce': tensor(0.0039, device='cuda:0'), 'validation_loss_bbox': tensor(0.0054, device='cuda:0'), 'validation_loss_giou': tensor(0.0419, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1144, device='cuda:0'), 'train_loss_ce': tensor(0.0039, device='cuda:0'), 'train_loss_bbox': tensor(0.0054, device='cuda:0'), 'train_loss_giou': tensor(0.0419, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1907, device='cuda:0'), 'validation_loss_ce': tensor(0.0037, device='cuda:0'), 'validation_loss_bbox': tensor(0.0073, device='cuda:0'), 'validation_loss_giou': tensor(0.0752, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1907, device='cuda:0'), 'train_loss_ce': tensor(0.0037, device='cuda:0'), 'train_loss_bbox': tensor(0.0073, device='cuda:0'), 'train_loss_giou': tensor(0.0752, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2450, device='cuda:0'), 'validation_loss_ce': tensor(0.0036, device='cuda:0'), 'validation_loss_bbox': tensor(0.0087, device='cuda:0'), 'validation_loss_giou': tensor(0.0990, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2450, device='cuda:0'), 'train_loss_ce': tensor(0.0036, device='cuda:0'), 'train_loss_bbox': tensor(0.0087, device='cuda:0'), 'train_loss_giou': tensor(0.0990, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2099, device='cuda:0'), 'validation_loss_ce': tensor(0.0035, device='cuda:0'), 'validation_loss_bbox': tensor(0.0074, device='cuda:0'), 'validation_loss_giou': tensor(0.0848, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2099, device='cuda:0'), 'train_loss_ce': tensor(0.0035, device='cuda:0'), 'train_loss_bbox': tensor(0.0074, device='cuda:0'), 'train_loss_giou': tensor(0.0848, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.0943, device='cuda:0'), 'validation_loss_ce': tensor(0.0036, device='cuda:0'), 'validation_loss_bbox': tensor(0.0045, device='cuda:0'), 'validation_loss_giou': tensor(0.0341, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.0943, device='cuda:0'), 'train_loss_ce': tensor(0.0036, device='cuda:0'), 'train_loss_bbox': tensor(0.0045, device='cuda:0'), 'train_loss_giou': tensor(0.0341, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1894, device='cuda:0'), 'validation_loss_ce': tensor(0.0036, device='cuda:0'), 'validation_loss_bbox': tensor(0.0064, device='cuda:0'), 'validation_loss_giou': tensor(0.0768, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1894, device='cuda:0'), 'train_loss_ce': tensor(0.0036, device='cuda:0'), 'train_loss_bbox': tensor(0.0064, device='cuda:0'), 'train_loss_giou': tensor(0.0768, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1661, device='cuda:0'), 'validation_loss_ce': tensor(0.0036, device='cuda:0'), 'validation_loss_bbox': tensor(0.0062, device='cuda:0'), 'validation_loss_giou': tensor(0.0657, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1661, device='cuda:0'), 'train_loss_ce': tensor(0.0036, device='cuda:0'), 'train_loss_bbox': tensor(0.0062, device='cuda:0'), 'train_loss_giou': tensor(0.0657, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.0847, device='cuda:0'), 'validation_loss_ce': tensor(0.0035, device='cuda:0'), 'validation_loss_bbox': tensor(0.0029, device='cuda:0'), 'validation_loss_giou': tensor(0.0332, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.0847, device='cuda:0'), 'train_loss_ce': tensor(0.0035, device='cuda:0'), 'train_loss_bbox': tensor(0.0029, device='cuda:0'), 'train_loss_giou': tensor(0.0332, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1978, device='cuda:0'), 'validation_loss_ce': tensor(0.0034, device='cuda:0'), 'validation_loss_bbox': tensor(0.0062, device='cuda:0'), 'validation_loss_giou': tensor(0.0818, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1978, device='cuda:0'), 'train_loss_ce': tensor(0.0034, device='cuda:0'), 'train_loss_bbox': tensor(0.0062, device='cuda:0'), 'train_loss_giou': tensor(0.0818, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2746, device='cuda:0'), 'validation_loss_ce': tensor(0.0034, device='cuda:0'), 'validation_loss_bbox': tensor(0.0093, device='cuda:0'), 'validation_loss_giou': tensor(0.1123, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2746, device='cuda:0'), 'train_loss_ce': tensor(0.0034, device='cuda:0'), 'train_loss_bbox': tensor(0.0093, device='cuda:0'), 'train_loss_giou': tensor(0.1123, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1926, device='cuda:0'), 'validation_loss_ce': tensor(0.0033, device='cuda:0'), 'validation_loss_bbox': tensor(0.0082, device='cuda:0'), 'validation_loss_giou': tensor(0.0741, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1926, device='cuda:0'), 'train_loss_ce': tensor(0.0033, device='cuda:0'), 'train_loss_bbox': tensor(0.0082, device='cuda:0'), 'train_loss_giou': tensor(0.0741, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1713, device='cuda:0'), 'validation_loss_ce': tensor(0.0032, device='cuda:0'), 'validation_loss_bbox': tensor(0.0070, device='cuda:0'), 'validation_loss_giou': tensor(0.0665, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1713, device='cuda:0'), 'train_loss_ce': tensor(0.0032, device='cuda:0'), 'train_loss_bbox': tensor(0.0070, device='cuda:0'), 'train_loss_giou': tensor(0.0665, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3369, device='cuda:0'), 'validation_loss_ce': tensor(0.0032, device='cuda:0'), 'validation_loss_bbox': tensor(0.0115, device='cuda:0'), 'validation_loss_giou': tensor(0.1381, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3369, device='cuda:0'), 'train_loss_ce': tensor(0.0032, device='cuda:0'), 'train_loss_bbox': tensor(0.0115, device='cuda:0'), 'train_loss_giou': tensor(0.1381, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3359, device='cuda:0'), 'validation_loss_ce': tensor(0.0031, device='cuda:0'), 'validation_loss_bbox': tensor(0.0110, device='cuda:0'), 'validation_loss_giou': tensor(0.1390, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3359, device='cuda:0'), 'train_loss_ce': tensor(0.0031, device='cuda:0'), 'train_loss_bbox': tensor(0.0110, device='cuda:0'), 'train_loss_giou': tensor(0.1390, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2050, device='cuda:0'), 'validation_loss_ce': tensor(0.0031, device='cuda:0'), 'validation_loss_bbox': tensor(0.0079, device='cuda:0'), 'validation_loss_giou': tensor(0.0811, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2050, device='cuda:0'), 'train_loss_ce': tensor(0.0031, device='cuda:0'), 'train_loss_bbox': tensor(0.0079, device='cuda:0'), 'train_loss_giou': tensor(0.0811, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1934, device='cuda:0'), 'validation_loss_ce': tensor(0.0031, device='cuda:0'), 'validation_loss_bbox': tensor(0.0093, device='cuda:0'), 'validation_loss_giou': tensor(0.0720, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1934, device='cuda:0'), 'train_loss_ce': tensor(0.0031, device='cuda:0'), 'train_loss_bbox': tensor(0.0093, device='cuda:0'), 'train_loss_giou': tensor(0.0720, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2651, device='cuda:0'), 'validation_loss_ce': tensor(0.0031, device='cuda:0'), 'validation_loss_bbox': tensor(0.0106, device='cuda:0'), 'validation_loss_giou': tensor(0.1044, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2651, device='cuda:0'), 'train_loss_ce': tensor(0.0031, device='cuda:0'), 'train_loss_bbox': tensor(0.0106, device='cuda:0'), 'train_loss_giou': tensor(0.1044, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1370, device='cuda:0'), 'validation_loss_ce': tensor(0.0031, device='cuda:0'), 'validation_loss_bbox': tensor(0.0061, device='cuda:0'), 'validation_loss_giou': tensor(0.0518, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1370, device='cuda:0'), 'train_loss_ce': tensor(0.0031, device='cuda:0'), 'train_loss_bbox': tensor(0.0061, device='cuda:0'), 'train_loss_giou': tensor(0.0518, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2645, device='cuda:0'), 'validation_loss_ce': tensor(0.0032, device='cuda:0'), 'validation_loss_bbox': tensor(0.0081, device='cuda:0'), 'validation_loss_giou': tensor(0.1105, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2645, device='cuda:0'), 'train_loss_ce': tensor(0.0032, device='cuda:0'), 'train_loss_bbox': tensor(0.0081, device='cuda:0'), 'train_loss_giou': tensor(0.1105, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3578, device='cuda:0'), 'validation_loss_ce': tensor(0.0032, device='cuda:0'), 'validation_loss_bbox': tensor(0.0117, device='cuda:0'), 'validation_loss_giou': tensor(0.1480, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3578, device='cuda:0'), 'train_loss_ce': tensor(0.0032, device='cuda:0'), 'train_loss_bbox': tensor(0.0117, device='cuda:0'), 'train_loss_giou': tensor(0.1480, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.3293, device='cuda:0'), 'validation_loss_ce': tensor(0.0031, device='cuda:0'), 'validation_loss_bbox': tensor(0.0117, device='cuda:0'), 'validation_loss_giou': tensor(0.1338, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.3293, device='cuda:0'), 'train_loss_ce': tensor(0.0031, device='cuda:0'), 'train_loss_bbox': tensor(0.0117, device='cuda:0'), 'train_loss_giou': tensor(0.1338, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1457, device='cuda:0'), 'validation_loss_ce': tensor(0.0031, device='cuda:0'), 'validation_loss_bbox': tensor(0.0057, device='cuda:0'), 'validation_loss_giou': tensor(0.0571, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1457, device='cuda:0'), 'train_loss_ce': tensor(0.0031, device='cuda:0'), 'train_loss_bbox': tensor(0.0057, device='cuda:0'), 'train_loss_giou': tensor(0.0571, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1852, device='cuda:0'), 'validation_loss_ce': tensor(0.0029, device='cuda:0'), 'validation_loss_bbox': tensor(0.0069, device='cuda:0'), 'validation_loss_giou': tensor(0.0739, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1852, device='cuda:0'), 'train_loss_ce': tensor(0.0029, device='cuda:0'), 'train_loss_bbox': tensor(0.0069, device='cuda:0'), 'train_loss_giou': tensor(0.0739, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2342, device='cuda:0'), 'validation_loss_ce': tensor(0.0028, device='cuda:0'), 'validation_loss_bbox': tensor(0.0089, device='cuda:0'), 'validation_loss_giou': tensor(0.0934, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2342, device='cuda:0'), 'train_loss_ce': tensor(0.0028, device='cuda:0'), 'train_loss_bbox': tensor(0.0089, device='cuda:0'), 'train_loss_giou': tensor(0.0934, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1252, device='cuda:0'), 'validation_loss_ce': tensor(0.0028, device='cuda:0'), 'validation_loss_bbox': tensor(0.0065, device='cuda:0'), 'validation_loss_giou': tensor(0.0449, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1252, device='cuda:0'), 'train_loss_ce': tensor(0.0028, device='cuda:0'), 'train_loss_bbox': tensor(0.0065, device='cuda:0'), 'train_loss_giou': tensor(0.0449, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1787, device='cuda:0'), 'validation_loss_ce': tensor(0.0028, device='cuda:0'), 'validation_loss_bbox': tensor(0.0084, device='cuda:0'), 'validation_loss_giou': tensor(0.0670, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1787, device='cuda:0'), 'train_loss_ce': tensor(0.0028, device='cuda:0'), 'train_loss_bbox': tensor(0.0084, device='cuda:0'), 'train_loss_giou': tensor(0.0670, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2583, device='cuda:0'), 'validation_loss_ce': tensor(0.0028, device='cuda:0'), 'validation_loss_bbox': tensor(0.0120, device='cuda:0'), 'validation_loss_giou': tensor(0.0979, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2583, device='cuda:0'), 'train_loss_ce': tensor(0.0028, device='cuda:0'), 'train_loss_bbox': tensor(0.0120, device='cuda:0'), 'train_loss_giou': tensor(0.0979, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2179, device='cuda:0'), 'validation_loss_ce': tensor(0.0027, device='cuda:0'), 'validation_loss_bbox': tensor(0.0094, device='cuda:0'), 'validation_loss_giou': tensor(0.0842, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2179, device='cuda:0'), 'train_loss_ce': tensor(0.0027, device='cuda:0'), 'train_loss_bbox': tensor(0.0094, device='cuda:0'), 'train_loss_giou': tensor(0.0842, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1052, device='cuda:0'), 'validation_loss_ce': tensor(0.0027, device='cuda:0'), 'validation_loss_bbox': tensor(0.0044, device='cuda:0'), 'validation_loss_giou': tensor(0.0403, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1052, device='cuda:0'), 'train_loss_ce': tensor(0.0027, device='cuda:0'), 'train_loss_bbox': tensor(0.0044, device='cuda:0'), 'train_loss_giou': tensor(0.0403, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2141, device='cuda:0'), 'validation_loss_ce': tensor(0.0027, device='cuda:0'), 'validation_loss_bbox': tensor(0.0079, device='cuda:0'), 'validation_loss_giou': tensor(0.0861, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2141, device='cuda:0'), 'train_loss_ce': tensor(0.0027, device='cuda:0'), 'train_loss_bbox': tensor(0.0079, device='cuda:0'), 'train_loss_giou': tensor(0.0861, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2502, device='cuda:0'), 'validation_loss_ce': tensor(0.0027, device='cuda:0'), 'validation_loss_bbox': tensor(0.0094, device='cuda:0'), 'validation_loss_giou': tensor(0.1002, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2502, device='cuda:0'), 'train_loss_ce': tensor(0.0027, device='cuda:0'), 'train_loss_bbox': tensor(0.0094, device='cuda:0'), 'train_loss_giou': tensor(0.1002, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1387, device='cuda:0'), 'validation_loss_ce': tensor(0.0027, device='cuda:0'), 'validation_loss_bbox': tensor(0.0069, device='cuda:0'), 'validation_loss_giou': tensor(0.0507, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1387, device='cuda:0'), 'train_loss_ce': tensor(0.0027, device='cuda:0'), 'train_loss_bbox': tensor(0.0069, device='cuda:0'), 'train_loss_giou': tensor(0.0507, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1273, device='cuda:0'), 'validation_loss_ce': tensor(0.0027, device='cuda:0'), 'validation_loss_bbox': tensor(0.0051, device='cuda:0'), 'validation_loss_giou': tensor(0.0496, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1273, device='cuda:0'), 'train_loss_ce': tensor(0.0027, device='cuda:0'), 'train_loss_bbox': tensor(0.0051, device='cuda:0'), 'train_loss_giou': tensor(0.0496, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1621, device='cuda:0'), 'validation_loss_ce': tensor(0.0027, device='cuda:0'), 'validation_loss_bbox': tensor(0.0073, device='cuda:0'), 'validation_loss_giou': tensor(0.0613, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1621, device='cuda:0'), 'train_loss_ce': tensor(0.0027, device='cuda:0'), 'train_loss_bbox': tensor(0.0073, device='cuda:0'), 'train_loss_giou': tensor(0.0613, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1434, device='cuda:0'), 'validation_loss_ce': tensor(0.0027, device='cuda:0'), 'validation_loss_bbox': tensor(0.0075, device='cuda:0'), 'validation_loss_giou': tensor(0.0515, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1434, device='cuda:0'), 'train_loss_ce': tensor(0.0027, device='cuda:0'), 'train_loss_bbox': tensor(0.0075, device='cuda:0'), 'train_loss_giou': tensor(0.0515, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1542, device='cuda:0'), 'validation_loss_ce': tensor(0.0028, device='cuda:0'), 'validation_loss_bbox': tensor(0.0087, device='cuda:0'), 'validation_loss_giou': tensor(0.0540, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1542, device='cuda:0'), 'train_loss_ce': tensor(0.0028, device='cuda:0'), 'train_loss_bbox': tensor(0.0087, device='cuda:0'), 'train_loss_giou': tensor(0.0540, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2351, device='cuda:0'), 'validation_loss_ce': tensor(0.0028, device='cuda:0'), 'validation_loss_bbox': tensor(0.0105, device='cuda:0'), 'validation_loss_giou': tensor(0.0900, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2351, device='cuda:0'), 'train_loss_ce': tensor(0.0028, device='cuda:0'), 'train_loss_bbox': tensor(0.0105, device='cuda:0'), 'train_loss_giou': tensor(0.0900, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1805, device='cuda:0'), 'validation_loss_ce': tensor(0.0027, device='cuda:0'), 'validation_loss_bbox': tensor(0.0087, device='cuda:0'), 'validation_loss_giou': tensor(0.0672, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1805, device='cuda:0'), 'train_loss_ce': tensor(0.0027, device='cuda:0'), 'train_loss_bbox': tensor(0.0087, device='cuda:0'), 'train_loss_giou': tensor(0.0672, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1407, device='cuda:0'), 'validation_loss_ce': tensor(0.0026, device='cuda:0'), 'validation_loss_bbox': tensor(0.0061, device='cuda:0'), 'validation_loss_giou': tensor(0.0538, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1407, device='cuda:0'), 'train_loss_ce': tensor(0.0026, device='cuda:0'), 'train_loss_bbox': tensor(0.0061, device='cuda:0'), 'train_loss_giou': tensor(0.0538, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1305, device='cuda:0'), 'validation_loss_ce': tensor(0.0026, device='cuda:0'), 'validation_loss_bbox': tensor(0.0074, device='cuda:0'), 'validation_loss_giou': tensor(0.0455, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1305, device='cuda:0'), 'train_loss_ce': tensor(0.0026, device='cuda:0'), 'train_loss_bbox': tensor(0.0074, device='cuda:0'), 'train_loss_giou': tensor(0.0455, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1796, device='cuda:0'), 'validation_loss_ce': tensor(0.0026, device='cuda:0'), 'validation_loss_bbox': tensor(0.0093, device='cuda:0'), 'validation_loss_giou': tensor(0.0653, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1796, device='cuda:0'), 'train_loss_ce': tensor(0.0026, device='cuda:0'), 'train_loss_bbox': tensor(0.0093, device='cuda:0'), 'train_loss_giou': tensor(0.0653, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1812, device='cuda:0'), 'validation_loss_ce': tensor(0.0026, device='cuda:0'), 'validation_loss_bbox': tensor(0.0105, device='cuda:0'), 'validation_loss_giou': tensor(0.0630, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1812, device='cuda:0'), 'train_loss_ce': tensor(0.0026, device='cuda:0'), 'train_loss_bbox': tensor(0.0105, device='cuda:0'), 'train_loss_giou': tensor(0.0630, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1530, device='cuda:0'), 'validation_loss_ce': tensor(0.0025, device='cuda:0'), 'validation_loss_bbox': tensor(0.0085, device='cuda:0'), 'validation_loss_giou': tensor(0.0540, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1530, device='cuda:0'), 'train_loss_ce': tensor(0.0025, device='cuda:0'), 'train_loss_bbox': tensor(0.0085, device='cuda:0'), 'train_loss_giou': tensor(0.0540, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1584, device='cuda:0'), 'validation_loss_ce': tensor(0.0025, device='cuda:0'), 'validation_loss_bbox': tensor(0.0068, device='cuda:0'), 'validation_loss_giou': tensor(0.0610, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1584, device='cuda:0'), 'train_loss_ce': tensor(0.0025, device='cuda:0'), 'train_loss_bbox': tensor(0.0068, device='cuda:0'), 'train_loss_giou': tensor(0.0610, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1358, device='cuda:0'), 'validation_loss_ce': tensor(0.0024, device='cuda:0'), 'validation_loss_bbox': tensor(0.0051, device='cuda:0'), 'validation_loss_giou': tensor(0.0540, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1358, device='cuda:0'), 'train_loss_ce': tensor(0.0024, device='cuda:0'), 'train_loss_bbox': tensor(0.0051, device='cuda:0'), 'train_loss_giou': tensor(0.0540, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1468, device='cuda:0'), 'validation_loss_ce': tensor(0.0024, device='cuda:0'), 'validation_loss_bbox': tensor(0.0072, device='cuda:0'), 'validation_loss_giou': tensor(0.0542, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1468, device='cuda:0'), 'train_loss_ce': tensor(0.0024, device='cuda:0'), 'train_loss_bbox': tensor(0.0072, device='cuda:0'), 'train_loss_giou': tensor(0.0542, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1805, device='cuda:0'), 'validation_loss_ce': tensor(0.0024, device='cuda:0'), 'validation_loss_bbox': tensor(0.0089, device='cuda:0'), 'validation_loss_giou': tensor(0.0668, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1805, device='cuda:0'), 'train_loss_ce': tensor(0.0024, device='cuda:0'), 'train_loss_bbox': tensor(0.0089, device='cuda:0'), 'train_loss_giou': tensor(0.0668, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1439, device='cuda:0'), 'validation_loss_ce': tensor(0.0024, device='cuda:0'), 'validation_loss_bbox': tensor(0.0071, device='cuda:0'), 'validation_loss_giou': tensor(0.0530, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1439, device='cuda:0'), 'train_loss_ce': tensor(0.0024, device='cuda:0'), 'train_loss_bbox': tensor(0.0071, device='cuda:0'), 'train_loss_giou': tensor(0.0530, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2011, device='cuda:0'), 'validation_loss_ce': tensor(0.0024, device='cuda:0'), 'validation_loss_bbox': tensor(0.0104, device='cuda:0'), 'validation_loss_giou': tensor(0.0734, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2011, device='cuda:0'), 'train_loss_ce': tensor(0.0024, device='cuda:0'), 'train_loss_bbox': tensor(0.0104, device='cuda:0'), 'train_loss_giou': tensor(0.0734, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2137, device='cuda:0'), 'validation_loss_ce': tensor(0.0023, device='cuda:0'), 'validation_loss_bbox': tensor(0.0114, device='cuda:0'), 'validation_loss_giou': tensor(0.0772, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2137, device='cuda:0'), 'train_loss_ce': tensor(0.0023, device='cuda:0'), 'train_loss_bbox': tensor(0.0114, device='cuda:0'), 'train_loss_giou': tensor(0.0772, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1350, device='cuda:0'), 'validation_loss_ce': tensor(0.0024, device='cuda:0'), 'validation_loss_bbox': tensor(0.0070, device='cuda:0'), 'validation_loss_giou': tensor(0.0487, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1350, device='cuda:0'), 'train_loss_ce': tensor(0.0024, device='cuda:0'), 'train_loss_bbox': tensor(0.0070, device='cuda:0'), 'train_loss_giou': tensor(0.0487, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1804, device='cuda:0'), 'validation_loss_ce': tensor(0.0025, device='cuda:0'), 'validation_loss_bbox': tensor(0.0100, device='cuda:0'), 'validation_loss_giou': tensor(0.0640, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1804, device='cuda:0'), 'train_loss_ce': tensor(0.0025, device='cuda:0'), 'train_loss_bbox': tensor(0.0100, device='cuda:0'), 'train_loss_giou': tensor(0.0640, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2193, device='cuda:0'), 'validation_loss_ce': tensor(0.0025, device='cuda:0'), 'validation_loss_bbox': tensor(0.0123, device='cuda:0'), 'validation_loss_giou': tensor(0.0776, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2193, device='cuda:0'), 'train_loss_ce': tensor(0.0025, device='cuda:0'), 'train_loss_bbox': tensor(0.0123, device='cuda:0'), 'train_loss_giou': tensor(0.0776, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1465, device='cuda:0'), 'validation_loss_ce': tensor(0.0025, device='cuda:0'), 'validation_loss_bbox': tensor(0.0090, device='cuda:0'), 'validation_loss_giou': tensor(0.0496, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1465, device='cuda:0'), 'train_loss_ce': tensor(0.0025, device='cuda:0'), 'train_loss_bbox': tensor(0.0090, device='cuda:0'), 'train_loss_giou': tensor(0.0496, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1465, device='cuda:0'), 'validation_loss_ce': tensor(0.0024, device='cuda:0'), 'validation_loss_bbox': tensor(0.0071, device='cuda:0'), 'validation_loss_giou': tensor(0.0544, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1465, device='cuda:0'), 'train_loss_ce': tensor(0.0024, device='cuda:0'), 'train_loss_bbox': tensor(0.0071, device='cuda:0'), 'train_loss_giou': tensor(0.0544, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1179, device='cuda:0'), 'validation_loss_ce': tensor(0.0023, device='cuda:0'), 'validation_loss_bbox': tensor(0.0066, device='cuda:0'), 'validation_loss_giou': tensor(0.0414, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1179, device='cuda:0'), 'train_loss_ce': tensor(0.0023, device='cuda:0'), 'train_loss_bbox': tensor(0.0066, device='cuda:0'), 'train_loss_giou': tensor(0.0414, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1842, device='cuda:0'), 'validation_loss_ce': tensor(0.0023, device='cuda:0'), 'validation_loss_bbox': tensor(0.0074, device='cuda:0'), 'validation_loss_giou': tensor(0.0724, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1842, device='cuda:0'), 'train_loss_ce': tensor(0.0023, device='cuda:0'), 'train_loss_bbox': tensor(0.0074, device='cuda:0'), 'train_loss_giou': tensor(0.0724, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1665, device='cuda:0'), 'validation_loss_ce': tensor(0.0023, device='cuda:0'), 'validation_loss_bbox': tensor(0.0064, device='cuda:0'), 'validation_loss_giou': tensor(0.0661, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1665, device='cuda:0'), 'train_loss_ce': tensor(0.0023, device='cuda:0'), 'train_loss_bbox': tensor(0.0064, device='cuda:0'), 'train_loss_giou': tensor(0.0661, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2244, device='cuda:0'), 'validation_loss_ce': tensor(0.0023, device='cuda:0'), 'validation_loss_bbox': tensor(0.0076, device='cuda:0'), 'validation_loss_giou': tensor(0.0920, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2244, device='cuda:0'), 'train_loss_ce': tensor(0.0023, device='cuda:0'), 'train_loss_bbox': tensor(0.0076, device='cuda:0'), 'train_loss_giou': tensor(0.0920, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2112, device='cuda:0'), 'validation_loss_ce': tensor(0.0023, device='cuda:0'), 'validation_loss_bbox': tensor(0.0082, device='cuda:0'), 'validation_loss_giou': tensor(0.0839, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2112, device='cuda:0'), 'train_loss_ce': tensor(0.0023, device='cuda:0'), 'train_loss_bbox': tensor(0.0082, device='cuda:0'), 'train_loss_giou': tensor(0.0839, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1813, device='cuda:0'), 'validation_loss_ce': tensor(0.0022, device='cuda:0'), 'validation_loss_bbox': tensor(0.0075, device='cuda:0'), 'validation_loss_giou': tensor(0.0707, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1813, device='cuda:0'), 'train_loss_ce': tensor(0.0022, device='cuda:0'), 'train_loss_bbox': tensor(0.0075, device='cuda:0'), 'train_loss_giou': tensor(0.0707, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.2024, device='cuda:0'), 'validation_loss_ce': tensor(0.0022, device='cuda:0'), 'validation_loss_bbox': tensor(0.0074, device='cuda:0'), 'validation_loss_giou': tensor(0.0815, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.2024, device='cuda:0'), 'train_loss_ce': tensor(0.0022, device='cuda:0'), 'train_loss_bbox': tensor(0.0074, device='cuda:0'), 'train_loss_giou': tensor(0.0815, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1581, device='cuda:0'), 'validation_loss_ce': tensor(0.0023, device='cuda:0'), 'validation_loss_bbox': tensor(0.0055, device='cuda:0'), 'validation_loss_giou': tensor(0.0642, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1581, device='cuda:0'), 'train_loss_ce': tensor(0.0023, device='cuda:0'), 'train_loss_bbox': tensor(0.0055, device='cuda:0'), 'train_loss_giou': tensor(0.0642, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1893, device='cuda:0'), 'validation_loss_ce': tensor(0.0023, device='cuda:0'), 'validation_loss_bbox': tensor(0.0069, device='cuda:0'), 'validation_loss_giou': tensor(0.0763, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1893, device='cuda:0'), 'train_loss_ce': tensor(0.0023, device='cuda:0'), 'train_loss_bbox': tensor(0.0069, device='cuda:0'), 'train_loss_giou': tensor(0.0763, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1946, device='cuda:0'), 'validation_loss_ce': tensor(0.0023, device='cuda:0'), 'validation_loss_bbox': tensor(0.0078, device='cuda:0'), 'validation_loss_giou': tensor(0.0766, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1946, device='cuda:0'), 'train_loss_ce': tensor(0.0023, device='cuda:0'), 'train_loss_bbox': tensor(0.0078, device='cuda:0'), 'train_loss_giou': tensor(0.0766, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1593, device='cuda:0'), 'validation_loss_ce': tensor(0.0022, device='cuda:0'), 'validation_loss_bbox': tensor(0.0068, device='cuda:0'), 'validation_loss_giou': tensor(0.0616, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1593, device='cuda:0'), 'train_loss_ce': tensor(0.0022, device='cuda:0'), 'train_loss_bbox': tensor(0.0068, device='cuda:0'), 'train_loss_giou': tensor(0.0616, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1564, device='cuda:0'), 'validation_loss_ce': tensor(0.0022, device='cuda:0'), 'validation_loss_bbox': tensor(0.0057, device='cuda:0'), 'validation_loss_giou': tensor(0.0629, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1564, device='cuda:0'), 'train_loss_ce': tensor(0.0022, device='cuda:0'), 'train_loss_bbox': tensor(0.0057, device='cuda:0'), 'train_loss_giou': tensor(0.0629, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.0987, device='cuda:0'), 'validation_loss_ce': tensor(0.0021, device='cuda:0'), 'validation_loss_bbox': tensor(0.0048, device='cuda:0'), 'validation_loss_giou': tensor(0.0364, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.0987, device='cuda:0'), 'train_loss_ce': tensor(0.0021, device='cuda:0'), 'train_loss_bbox': tensor(0.0048, device='cuda:0'), 'train_loss_giou': tensor(0.0364, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1400, device='cuda:0'), 'validation_loss_ce': tensor(0.0021, device='cuda:0'), 'validation_loss_bbox': tensor(0.0048, device='cuda:0'), 'validation_loss_giou': tensor(0.0569, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1400, device='cuda:0'), 'train_loss_ce': tensor(0.0021, device='cuda:0'), 'train_loss_bbox': tensor(0.0048, device='cuda:0'), 'train_loss_giou': tensor(0.0569, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1314, device='cuda:0'), 'validation_loss_ce': tensor(0.0020, device='cuda:0'), 'validation_loss_bbox': tensor(0.0045, device='cuda:0'), 'validation_loss_giou': tensor(0.0533, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1314, device='cuda:0'), 'train_loss_ce': tensor(0.0020, device='cuda:0'), 'train_loss_bbox': tensor(0.0045, device='cuda:0'), 'train_loss_giou': tensor(0.0533, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1424, device='cuda:0'), 'validation_loss_ce': tensor(0.0020, device='cuda:0'), 'validation_loss_bbox': tensor(0.0049, device='cuda:0'), 'validation_loss_giou': tensor(0.0580, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1424, device='cuda:0'), 'train_loss_ce': tensor(0.0020, device='cuda:0'), 'train_loss_bbox': tensor(0.0049, device='cuda:0'), 'train_loss_giou': tensor(0.0580, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.0753, device='cuda:0'), 'validation_loss_ce': tensor(0.0020, device='cuda:0'), 'validation_loss_bbox': tensor(0.0030, device='cuda:0'), 'validation_loss_giou': tensor(0.0290, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.0753, device='cuda:0'), 'train_loss_ce': tensor(0.0020, device='cuda:0'), 'train_loss_bbox': tensor(0.0030, device='cuda:0'), 'train_loss_giou': tensor(0.0290, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.0889, device='cuda:0'), 'validation_loss_ce': tensor(0.0021, device='cuda:0'), 'validation_loss_bbox': tensor(0.0032, device='cuda:0'), 'validation_loss_giou': tensor(0.0353, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.0889, device='cuda:0'), 'train_loss_ce': tensor(0.0021, device='cuda:0'), 'train_loss_bbox': tensor(0.0032, device='cuda:0'), 'train_loss_giou': tensor(0.0353, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1552, device='cuda:0'), 'validation_loss_ce': tensor(0.0021, device='cuda:0'), 'validation_loss_bbox': tensor(0.0051, device='cuda:0'), 'validation_loss_giou': tensor(0.0639, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1552, device='cuda:0'), 'train_loss_ce': tensor(0.0021, device='cuda:0'), 'train_loss_bbox': tensor(0.0051, device='cuda:0'), 'train_loss_giou': tensor(0.0639, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1461, device='cuda:0'), 'validation_loss_ce': tensor(0.0021, device='cuda:0'), 'validation_loss_bbox': tensor(0.0058, device='cuda:0'), 'validation_loss_giou': tensor(0.0576, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1461, device='cuda:0'), 'train_loss_ce': tensor(0.0021, device='cuda:0'), 'train_loss_bbox': tensor(0.0058, device='cuda:0'), 'train_loss_giou': tensor(0.0576, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1026, device='cuda:0'), 'validation_loss_ce': tensor(0.0020, device='cuda:0'), 'validation_loss_bbox': tensor(0.0048, device='cuda:0'), 'validation_loss_giou': tensor(0.0382, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1026, device='cuda:0'), 'train_loss_ce': tensor(0.0020, device='cuda:0'), 'train_loss_bbox': tensor(0.0048, device='cuda:0'), 'train_loss_giou': tensor(0.0382, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1504, device='cuda:0'), 'validation_loss_ce': tensor(0.0020, device='cuda:0'), 'validation_loss_bbox': tensor(0.0065, device='cuda:0'), 'validation_loss_giou': tensor(0.0581, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1504, device='cuda:0'), 'train_loss_ce': tensor(0.0020, device='cuda:0'), 'train_loss_bbox': tensor(0.0065, device='cuda:0'), 'train_loss_giou': tensor(0.0581, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1370, device='cuda:0'), 'validation_loss_ce': tensor(0.0020, device='cuda:0'), 'validation_loss_bbox': tensor(0.0042, device='cuda:0'), 'validation_loss_giou': tensor(0.0570, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1370, device='cuda:0'), 'train_loss_ce': tensor(0.0020, device='cuda:0'), 'train_loss_bbox': tensor(0.0042, device='cuda:0'), 'train_loss_giou': tensor(0.0570, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1498, device='cuda:0'), 'validation_loss_ce': tensor(0.0020, device='cuda:0'), 'validation_loss_bbox': tensor(0.0076, device='cuda:0'), 'validation_loss_giou': tensor(0.0550, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1498, device='cuda:0'), 'train_loss_ce': tensor(0.0020, device='cuda:0'), 'train_loss_bbox': tensor(0.0076, device='cuda:0'), 'train_loss_giou': tensor(0.0550, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1961, device='cuda:0'), 'validation_loss_ce': tensor(0.0020, device='cuda:0'), 'validation_loss_bbox': tensor(0.0111, device='cuda:0'), 'validation_loss_giou': tensor(0.0693, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1961, device='cuda:0'), 'train_loss_ce': tensor(0.0020, device='cuda:0'), 'train_loss_bbox': tensor(0.0111, device='cuda:0'), 'train_loss_giou': tensor(0.0693, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1626, device='cuda:0'), 'validation_loss_ce': tensor(0.0021, device='cuda:0'), 'validation_loss_bbox': tensor(0.0083, device='cuda:0'), 'validation_loss_giou': tensor(0.0594, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
{'training_loss': tensor(0.1626, device='cuda:0'), 'train_loss_ce': tensor(0.0021, device='cuda:0'), 'train_loss_bbox': tensor(0.0083, device='cuda:0'), 'train_loss_giou': tensor(0.0594, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.1654, device='cuda:0'), 'validation_loss_ce': tensor(0.0021, device='cuda:0'), 'validation_loss_bbox': tensor(0.0094, device='cuda:0'), 'validation_loss_giou': tensor(0.0582, device='cuda:0'), 'validation_cardinality_error': tensor(0., device='cuda:0')}
```

## Examples
{'size': tensor([512, 512]), 'image_id': tensor([735]), 'class_labels': tensor([5]), 'boxes': tensor([[0.7651, 0.5307, 0.0952, 0.0942]]), 'area': tensor([2351.3042]), 'iscrowd': tensor([0]), 'orig_size': tensor([1024, 1024])}

![Example](./example.png)