diff --git "a/README.md" "b/README.md"
--- "a/README.md"
+++ "b/README.md"
@@ -13,143 +13,143 @@ IoU metric: bbox
  Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
  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 ] = 0.007
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.009
+ 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 ] = 0.000
- Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.009
+ 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 ] = 0.058
- Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.108
- Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.054
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.049
+ Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.083
+ Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.059
  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 ] = 0.019
- Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.051
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.099
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.170
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.192
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.050
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.117
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.204
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.222
  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 ] = 0.046
- Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.177
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.025
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.238
 ```
 
 ## Config
 - dataset: NIH
 - original model: hustvl/yolos-tiny
 - lr: 0.0001
-- dropout_rate: 0.1
-- weight_decay: 0.001
+- dropout_rate: 0.15
+- weight_decay: 0.0005
 - max_epochs: 100
 - train samples: 885
 
 ## Logging
 ### Training process
 ```
-{'validation_loss': tensor(7.2045, device='cuda:0'), 'validation_loss_ce': tensor(2.2968, device='cuda:0'), 'validation_loss_bbox': tensor(0.5672, device='cuda:0'), 'validation_loss_giou': tensor(1.0358, device='cuda:0'), 'validation_cardinality_error': tensor(98.9688, device='cuda:0')}
-{'training_loss': tensor(2.5200, device='cuda:0'), 'train_loss_ce': tensor(0.4957, device='cuda:0'), 'train_loss_bbox': tensor(0.1564, device='cuda:0'), 'train_loss_giou': tensor(0.6212, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2375, device='cuda:0'), 'validation_loss_ce': tensor(0.4545, device='cuda:0'), 'validation_loss_bbox': tensor(0.1507, device='cuda:0'), 'validation_loss_giou': tensor(0.5146, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.2501, device='cuda:0'), 'train_loss_ce': tensor(0.4415, device='cuda:0'), 'train_loss_bbox': tensor(0.1535, device='cuda:0'), 'train_loss_giou': tensor(0.5207, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2336, device='cuda:0'), 'validation_loss_ce': tensor(0.4277, device='cuda:0'), 'validation_loss_bbox': tensor(0.1595, device='cuda:0'), 'validation_loss_giou': tensor(0.5043, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.4403, device='cuda:0'), 'train_loss_ce': tensor(0.3938, device='cuda:0'), 'train_loss_bbox': tensor(0.1813, device='cuda:0'), 'train_loss_giou': tensor(0.5700, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7168, device='cuda:0'), 'validation_loss_ce': tensor(0.4196, device='cuda:0'), 'validation_loss_bbox': tensor(0.2084, device='cuda:0'), 'validation_loss_giou': tensor(0.6275, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.2682, device='cuda:0'), 'train_loss_ce': tensor(0.4668, device='cuda:0'), 'train_loss_bbox': tensor(0.1324, device='cuda:0'), 'train_loss_giou': tensor(0.5698, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.3310, device='cuda:0'), 'validation_loss_ce': tensor(0.4273, device='cuda:0'), 'validation_loss_bbox': tensor(0.1675, device='cuda:0'), 'validation_loss_giou': tensor(0.5331, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.1533, device='cuda:0'), 'train_loss_ce': tensor(0.3045, device='cuda:0'), 'train_loss_bbox': tensor(0.1709, device='cuda:0'), 'train_loss_giou': tensor(0.4971, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1458, device='cuda:0'), 'validation_loss_ce': tensor(0.4185, device='cuda:0'), 'validation_loss_bbox': tensor(0.1446, device='cuda:0'), 'validation_loss_giou': tensor(0.5023, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(1.6247, device='cuda:0'), 'train_loss_ce': tensor(0.2961, device='cuda:0'), 'train_loss_bbox': tensor(0.0975, device='cuda:0'), 'train_loss_giou': tensor(0.4206, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1055, device='cuda:0'), 'validation_loss_ce': tensor(0.4085, device='cuda:0'), 'validation_loss_bbox': tensor(0.1438, device='cuda:0'), 'validation_loss_giou': tensor(0.4889, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(1.5941, device='cuda:0'), 'train_loss_ce': tensor(0.3669, device='cuda:0'), 'train_loss_bbox': tensor(0.0878, device='cuda:0'), 'train_loss_giou': tensor(0.3941, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0741, device='cuda:0'), 'validation_loss_ce': tensor(0.4017, device='cuda:0'), 'validation_loss_bbox': tensor(0.1364, device='cuda:0'), 'validation_loss_giou': tensor(0.4951, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(1.7629, device='cuda:0'), 'train_loss_ce': tensor(0.3858, device='cuda:0'), 'train_loss_bbox': tensor(0.1226, device='cuda:0'), 'train_loss_giou': tensor(0.3820, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0028, device='cuda:0'), 'validation_loss_ce': tensor(0.3956, device='cuda:0'), 'validation_loss_bbox': tensor(0.1363, device='cuda:0'), 'validation_loss_giou': tensor(0.4629, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(1.6581, device='cuda:0'), 'train_loss_ce': tensor(0.3119, device='cuda:0'), 'train_loss_bbox': tensor(0.0921, device='cuda:0'), 'train_loss_giou': tensor(0.4429, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9400, device='cuda:0'), 'validation_loss_ce': tensor(0.3832, device='cuda:0'), 'validation_loss_bbox': tensor(0.1252, device='cuda:0'), 'validation_loss_giou': tensor(0.4655, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(1.3849, device='cuda:0'), 'train_loss_ce': tensor(0.3898, device='cuda:0'), 'train_loss_bbox': tensor(0.0691, device='cuda:0'), 'train_loss_giou': tensor(0.3247, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8570, device='cuda:0'), 'validation_loss_ce': tensor(0.3680, device='cuda:0'), 'validation_loss_bbox': tensor(0.1198, device='cuda:0'), 'validation_loss_giou': tensor(0.4451, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.3841, device='cuda:0'), 'train_loss_ce': tensor(0.4545, device='cuda:0'), 'train_loss_bbox': tensor(0.1736, device='cuda:0'), 'train_loss_giou': tensor(0.5307, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9082, device='cuda:0'), 'validation_loss_ce': tensor(0.3641, device='cuda:0'), 'validation_loss_bbox': tensor(0.1256, device='cuda:0'), 'validation_loss_giou': tensor(0.4582, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(1.6018, device='cuda:0'), 'train_loss_ce': tensor(0.3856, device='cuda:0'), 'train_loss_bbox': tensor(0.0900, device='cuda:0'), 'train_loss_giou': tensor(0.3831, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8398, device='cuda:0'), 'validation_loss_ce': tensor(0.3599, device='cuda:0'), 'validation_loss_bbox': tensor(0.1200, device='cuda:0'), 'validation_loss_giou': tensor(0.4398, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
-{'training_loss': tensor(2.1644, device='cuda:0'), 'train_loss_ce': tensor(0.3639, device='cuda:0'), 'train_loss_bbox': tensor(0.1234, device='cuda:0'), 'train_loss_giou': tensor(0.5917, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8483, device='cuda:0'), 'validation_loss_ce': tensor(0.3541, device='cuda:0'), 'validation_loss_bbox': tensor(0.1239, device='cuda:0'), 'validation_loss_giou': tensor(0.4373, device='cuda:0'), 'validation_cardinality_error': tensor(0.7980, device='cuda:0')}
-{'training_loss': tensor(1.4989, device='cuda:0'), 'train_loss_ce': tensor(0.3999, device='cuda:0'), 'train_loss_bbox': tensor(0.0872, device='cuda:0'), 'train_loss_giou': tensor(0.3315, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.8334, device='cuda:0'), 'validation_loss_ce': tensor(0.3644, device='cuda:0'), 'validation_loss_bbox': tensor(0.1196, device='cuda:0'), 'validation_loss_giou': tensor(0.4356, device='cuda:0'), 'validation_cardinality_error': tensor(0.5354, device='cuda:0')}
-{'training_loss': tensor(1.2876, device='cuda:0'), 'train_loss_ce': tensor(0.3680, device='cuda:0'), 'train_loss_bbox': tensor(0.0884, device='cuda:0'), 'train_loss_giou': tensor(0.2388, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.8002, device='cuda:0'), 'validation_loss_ce': tensor(0.3446, device='cuda:0'), 'validation_loss_bbox': tensor(0.1209, device='cuda:0'), 'validation_loss_giou': tensor(0.4255, device='cuda:0'), 'validation_cardinality_error': tensor(0.7273, device='cuda:0')}
-{'training_loss': tensor(1.8735, device='cuda:0'), 'train_loss_ce': tensor(0.3472, device='cuda:0'), 'train_loss_bbox': tensor(0.1311, device='cuda:0'), 'train_loss_giou': tensor(0.4354, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(2.0753, device='cuda:0'), 'validation_loss_ce': tensor(0.3446, device='cuda:0'), 'validation_loss_bbox': tensor(0.1430, device='cuda:0'), 'validation_loss_giou': tensor(0.5078, device='cuda:0'), 'validation_cardinality_error': tensor(0.4747, device='cuda:0')}
-{'training_loss': tensor(1.9574, device='cuda:0'), 'train_loss_ce': tensor(0.3733, device='cuda:0'), 'train_loss_bbox': tensor(0.1423, device='cuda:0'), 'train_loss_giou': tensor(0.4363, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9587, device='cuda:0'), 'validation_loss_ce': tensor(0.3564, device='cuda:0'), 'validation_loss_bbox': tensor(0.1323, device='cuda:0'), 'validation_loss_giou': tensor(0.4704, device='cuda:0'), 'validation_cardinality_error': tensor(0.8788, device='cuda:0')}
-{'training_loss': tensor(1.4950, device='cuda:0'), 'train_loss_ce': tensor(0.2871, device='cuda:0'), 'train_loss_bbox': tensor(0.0836, device='cuda:0'), 'train_loss_giou': tensor(0.3950, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9386, device='cuda:0'), 'validation_loss_ce': tensor(0.3506, device='cuda:0'), 'validation_loss_bbox': tensor(0.1328, device='cuda:0'), 'validation_loss_giou': tensor(0.4620, device='cuda:0'), 'validation_cardinality_error': tensor(0.7576, device='cuda:0')}
-{'training_loss': tensor(1.1535, device='cuda:0'), 'train_loss_ce': tensor(0.2828, device='cuda:0'), 'train_loss_bbox': tensor(0.0519, device='cuda:0'), 'train_loss_giou': tensor(0.3056, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8730, device='cuda:0'), 'validation_loss_ce': tensor(0.3456, device='cuda:0'), 'validation_loss_bbox': tensor(0.1236, device='cuda:0'), 'validation_loss_giou': tensor(0.4546, device='cuda:0'), 'validation_cardinality_error': tensor(0.6162, device='cuda:0')}
-{'training_loss': tensor(1.4150, device='cuda:0'), 'train_loss_ce': tensor(0.1594, device='cuda:0'), 'train_loss_bbox': tensor(0.1283, device='cuda:0'), 'train_loss_giou': tensor(0.3072, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8677, device='cuda:0'), 'validation_loss_ce': tensor(0.3425, device='cuda:0'), 'validation_loss_bbox': tensor(0.1262, device='cuda:0'), 'validation_loss_giou': tensor(0.4470, device='cuda:0'), 'validation_cardinality_error': tensor(0.5758, device='cuda:0')}
-{'training_loss': tensor(1.1482, device='cuda:0'), 'train_loss_ce': tensor(0.2020, device='cuda:0'), 'train_loss_bbox': tensor(0.0582, device='cuda:0'), 'train_loss_giou': tensor(0.3276, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8096, device='cuda:0'), 'validation_loss_ce': tensor(0.3357, device='cuda:0'), 'validation_loss_bbox': tensor(0.1197, device='cuda:0'), 'validation_loss_giou': tensor(0.4378, device='cuda:0'), 'validation_cardinality_error': tensor(0.5253, device='cuda:0')}
-{'training_loss': tensor(1.5939, device='cuda:0'), 'train_loss_ce': tensor(0.3802, device='cuda:0'), 'train_loss_bbox': tensor(0.0916, device='cuda:0'), 'train_loss_giou': tensor(0.3778, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.9104, device='cuda:0'), 'validation_loss_ce': tensor(0.3441, device='cuda:0'), 'validation_loss_bbox': tensor(0.1264, device='cuda:0'), 'validation_loss_giou': tensor(0.4671, device='cuda:0'), 'validation_cardinality_error': tensor(0.4343, device='cuda:0')}
-{'training_loss': tensor(1.2458, device='cuda:0'), 'train_loss_ce': tensor(0.3179, device='cuda:0'), 'train_loss_bbox': tensor(0.0807, device='cuda:0'), 'train_loss_giou': tensor(0.2623, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.7529, device='cuda:0'), 'validation_loss_ce': tensor(0.3379, device='cuda:0'), 'validation_loss_bbox': tensor(0.1140, device='cuda:0'), 'validation_loss_giou': tensor(0.4224, device='cuda:0'), 'validation_cardinality_error': tensor(0.5354, device='cuda:0')}
-{'training_loss': tensor(1.2705, device='cuda:0'), 'train_loss_ce': tensor(0.2641, device='cuda:0'), 'train_loss_bbox': tensor(0.0617, device='cuda:0'), 'train_loss_giou': tensor(0.3488, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.8156, device='cuda:0'), 'validation_loss_ce': tensor(0.3391, device='cuda:0'), 'validation_loss_bbox': tensor(0.1156, device='cuda:0'), 'validation_loss_giou': tensor(0.4492, device='cuda:0'), 'validation_cardinality_error': tensor(0.7374, device='cuda:0')}
-{'training_loss': tensor(1.3914, device='cuda:0'), 'train_loss_ce': tensor(0.2143, device='cuda:0'), 'train_loss_bbox': tensor(0.0970, device='cuda:0'), 'train_loss_giou': tensor(0.3462, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(1.7497, device='cuda:0'), 'validation_loss_ce': tensor(0.3505, device='cuda:0'), 'validation_loss_bbox': tensor(0.1131, device='cuda:0'), 'validation_loss_giou': tensor(0.4170, device='cuda:0'), 'validation_cardinality_error': tensor(0.5960, device='cuda:0')}
-{'training_loss': tensor(1.6075, device='cuda:0'), 'train_loss_ce': tensor(0.3839, device='cuda:0'), 'train_loss_bbox': tensor(0.0690, device='cuda:0'), 'train_loss_giou': tensor(0.4394, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.6896, device='cuda:0'), 'validation_loss_ce': tensor(0.3293, device='cuda:0'), 'validation_loss_bbox': tensor(0.1059, device='cuda:0'), 'validation_loss_giou': tensor(0.4154, device='cuda:0'), 'validation_cardinality_error': tensor(0.3636, device='cuda:0')}
-{'training_loss': tensor(1.7218, device='cuda:0'), 'train_loss_ce': tensor(0.3454, device='cuda:0'), 'train_loss_bbox': tensor(0.1221, device='cuda:0'), 'train_loss_giou': tensor(0.3830, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.7517, device='cuda:0'), 'validation_loss_ce': tensor(0.3381, device='cuda:0'), 'validation_loss_bbox': tensor(0.1116, device='cuda:0'), 'validation_loss_giou': tensor(0.4279, device='cuda:0'), 'validation_cardinality_error': tensor(0.5859, device='cuda:0')}
-{'training_loss': tensor(1.4428, device='cuda:0'), 'train_loss_ce': tensor(0.2685, device='cuda:0'), 'train_loss_bbox': tensor(0.0879, device='cuda:0'), 'train_loss_giou': tensor(0.3674, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.7905, device='cuda:0'), 'validation_loss_ce': tensor(0.3374, device='cuda:0'), 'validation_loss_bbox': tensor(0.1187, device='cuda:0'), 'validation_loss_giou': tensor(0.4298, device='cuda:0'), 'validation_cardinality_error': tensor(0.6162, device='cuda:0')}
-{'training_loss': tensor(1.3059, device='cuda:0'), 'train_loss_ce': tensor(0.3185, device='cuda:0'), 'train_loss_bbox': tensor(0.0537, device='cuda:0'), 'train_loss_giou': tensor(0.3596, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.7305, device='cuda:0'), 'validation_loss_ce': tensor(0.3429, device='cuda:0'), 'validation_loss_bbox': tensor(0.1116, device='cuda:0'), 'validation_loss_giou': tensor(0.4149, device='cuda:0'), 'validation_cardinality_error': tensor(0.6364, device='cuda:0')}
-{'training_loss': tensor(1.4403, device='cuda:0'), 'train_loss_ce': tensor(0.3263, device='cuda:0'), 'train_loss_bbox': tensor(0.1015, device='cuda:0'), 'train_loss_giou': tensor(0.3034, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.9518, device='cuda:0'), 'validation_loss_ce': tensor(0.3443, device='cuda:0'), 'validation_loss_bbox': tensor(0.1318, device='cuda:0'), 'validation_loss_giou': tensor(0.4743, device='cuda:0'), 'validation_cardinality_error': tensor(0.7172, device='cuda:0')}
-{'training_loss': tensor(1.1981, device='cuda:0'), 'train_loss_ce': tensor(0.2236, device='cuda:0'), 'train_loss_bbox': tensor(0.0807, device='cuda:0'), 'train_loss_giou': tensor(0.2854, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.8668, device='cuda:0'), 'validation_loss_ce': tensor(0.3564, device='cuda:0'), 'validation_loss_bbox': tensor(0.1230, device='cuda:0'), 'validation_loss_giou': tensor(0.4476, device='cuda:0'), 'validation_cardinality_error': tensor(0.7980, device='cuda:0')}
-{'training_loss': tensor(1.5449, device='cuda:0'), 'train_loss_ce': tensor(0.2428, device='cuda:0'), 'train_loss_bbox': tensor(0.0945, device='cuda:0'), 'train_loss_giou': tensor(0.4148, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8501, device='cuda:0'), 'validation_loss_ce': tensor(0.3724, device='cuda:0'), 'validation_loss_bbox': tensor(0.1165, device='cuda:0'), 'validation_loss_giou': tensor(0.4475, device='cuda:0'), 'validation_cardinality_error': tensor(0.5758, device='cuda:0')}
-{'training_loss': tensor(1.7828, device='cuda:0'), 'train_loss_ce': tensor(0.4551, device='cuda:0'), 'train_loss_bbox': tensor(0.1038, device='cuda:0'), 'train_loss_giou': tensor(0.4043, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.8635, device='cuda:0'), 'validation_loss_ce': tensor(0.3396, device='cuda:0'), 'validation_loss_bbox': tensor(0.1237, device='cuda:0'), 'validation_loss_giou': tensor(0.4528, device='cuda:0'), 'validation_cardinality_error': tensor(0.6566, device='cuda:0')}
-{'training_loss': tensor(1.1647, device='cuda:0'), 'train_loss_ce': tensor(0.2744, device='cuda:0'), 'train_loss_bbox': tensor(0.0722, device='cuda:0'), 'train_loss_giou': tensor(0.2647, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.7792, device='cuda:0'), 'validation_loss_ce': tensor(0.3315, device='cuda:0'), 'validation_loss_bbox': tensor(0.1158, device='cuda:0'), 'validation_loss_giou': tensor(0.4344, device='cuda:0'), 'validation_cardinality_error': tensor(0.7980, device='cuda:0')}
-{'training_loss': tensor(1.1196, device='cuda:0'), 'train_loss_ce': tensor(0.1983, device='cuda:0'), 'train_loss_bbox': tensor(0.0853, device='cuda:0'), 'train_loss_giou': tensor(0.2474, device='cuda:0'), 'train_cardinality_error': tensor(1.2000, device='cuda:0'), 'validation_loss': tensor(1.7475, device='cuda:0'), 'validation_loss_ce': tensor(0.3421, device='cuda:0'), 'validation_loss_bbox': tensor(0.1131, device='cuda:0'), 'validation_loss_giou': tensor(0.4200, device='cuda:0'), 'validation_cardinality_error': tensor(0.6768, device='cuda:0')}
-{'training_loss': tensor(1.1440, device='cuda:0'), 'train_loss_ce': tensor(0.1990, device='cuda:0'), 'train_loss_bbox': tensor(0.0908, device='cuda:0'), 'train_loss_giou': tensor(0.2456, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.7808, device='cuda:0'), 'validation_loss_ce': tensor(0.3481, device='cuda:0'), 'validation_loss_bbox': tensor(0.1152, device='cuda:0'), 'validation_loss_giou': tensor(0.4284, device='cuda:0'), 'validation_cardinality_error': tensor(0.7071, device='cuda:0')}
-{'training_loss': tensor(1.2752, device='cuda:0'), 'train_loss_ce': tensor(0.1843, device='cuda:0'), 'train_loss_bbox': tensor(0.1018, device='cuda:0'), 'train_loss_giou': tensor(0.2909, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.8421, device='cuda:0'), 'validation_loss_ce': tensor(0.3465, device='cuda:0'), 'validation_loss_bbox': tensor(0.1200, device='cuda:0'), 'validation_loss_giou': tensor(0.4478, device='cuda:0'), 'validation_cardinality_error': tensor(0.5556, device='cuda:0')}
-{'training_loss': tensor(1.4315, device='cuda:0'), 'train_loss_ce': tensor(0.2973, device='cuda:0'), 'train_loss_bbox': tensor(0.0943, device='cuda:0'), 'train_loss_giou': tensor(0.3314, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.7926, device='cuda:0'), 'validation_loss_ce': tensor(0.3650, device='cuda:0'), 'validation_loss_bbox': tensor(0.1166, device='cuda:0'), 'validation_loss_giou': tensor(0.4223, device='cuda:0'), 'validation_cardinality_error': tensor(0.5455, device='cuda:0')}
-{'training_loss': tensor(1.1553, device='cuda:0'), 'train_loss_ce': tensor(0.2358, device='cuda:0'), 'train_loss_bbox': tensor(0.0676, device='cuda:0'), 'train_loss_giou': tensor(0.2907, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.8522, device='cuda:0'), 'validation_loss_ce': tensor(0.3531, device='cuda:0'), 'validation_loss_bbox': tensor(0.1244, device='cuda:0'), 'validation_loss_giou': tensor(0.4386, device='cuda:0'), 'validation_cardinality_error': tensor(0.6869, device='cuda:0')}
-{'training_loss': tensor(1.1894, device='cuda:0'), 'train_loss_ce': tensor(0.2374, device='cuda:0'), 'train_loss_bbox': tensor(0.0772, device='cuda:0'), 'train_loss_giou': tensor(0.2831, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.8030, device='cuda:0'), 'validation_loss_ce': tensor(0.3644, device='cuda:0'), 'validation_loss_bbox': tensor(0.1184, device='cuda:0'), 'validation_loss_giou': tensor(0.4234, device='cuda:0'), 'validation_cardinality_error': tensor(0.6970, device='cuda:0')}
-{'training_loss': tensor(1.1038, device='cuda:0'), 'train_loss_ce': tensor(0.2761, device='cuda:0'), 'train_loss_bbox': tensor(0.0691, device='cuda:0'), 'train_loss_giou': tensor(0.2410, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.8602, device='cuda:0'), 'validation_loss_ce': tensor(0.3383, device='cuda:0'), 'validation_loss_bbox': tensor(0.1233, device='cuda:0'), 'validation_loss_giou': tensor(0.4526, device='cuda:0'), 'validation_cardinality_error': tensor(0.5657, device='cuda:0')}
-{'training_loss': tensor(1.6817, device='cuda:0'), 'train_loss_ce': tensor(0.3073, device='cuda:0'), 'train_loss_bbox': tensor(0.1129, device='cuda:0'), 'train_loss_giou': tensor(0.4049, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9009, device='cuda:0'), 'validation_loss_ce': tensor(0.3715, device='cuda:0'), 'validation_loss_bbox': tensor(0.1227, device='cuda:0'), 'validation_loss_giou': tensor(0.4580, device='cuda:0'), 'validation_cardinality_error': tensor(0.6162, device='cuda:0')}
-{'training_loss': tensor(1.3429, device='cuda:0'), 'train_loss_ce': tensor(0.2732, device='cuda:0'), 'train_loss_bbox': tensor(0.0755, device='cuda:0'), 'train_loss_giou': tensor(0.3461, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(1.7967, device='cuda:0'), 'validation_loss_ce': tensor(0.3434, device='cuda:0'), 'validation_loss_bbox': tensor(0.1215, device='cuda:0'), 'validation_loss_giou': tensor(0.4229, device='cuda:0'), 'validation_cardinality_error': tensor(0.6061, device='cuda:0')}
-{'training_loss': tensor(1.1241, device='cuda:0'), 'train_loss_ce': tensor(0.2168, device='cuda:0'), 'train_loss_bbox': tensor(0.0621, device='cuda:0'), 'train_loss_giou': tensor(0.2985, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.7612, device='cuda:0'), 'validation_loss_ce': tensor(0.3442, device='cuda:0'), 'validation_loss_bbox': tensor(0.1143, device='cuda:0'), 'validation_loss_giou': tensor(0.4227, device='cuda:0'), 'validation_cardinality_error': tensor(0.6667, device='cuda:0')}
-{'training_loss': tensor(0.9909, device='cuda:0'), 'train_loss_ce': tensor(0.3210, device='cuda:0'), 'train_loss_bbox': tensor(0.0531, device='cuda:0'), 'train_loss_giou': tensor(0.2022, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.8190, device='cuda:0'), 'validation_loss_ce': tensor(0.3695, device='cuda:0'), 'validation_loss_bbox': tensor(0.1170, device='cuda:0'), 'validation_loss_giou': tensor(0.4323, device='cuda:0'), 'validation_cardinality_error': tensor(0.6566, device='cuda:0')}
-{'training_loss': tensor(1.7008, device='cuda:0'), 'train_loss_ce': tensor(0.2614, device='cuda:0'), 'train_loss_bbox': tensor(0.1000, device='cuda:0'), 'train_loss_giou': tensor(0.4698, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9067, device='cuda:0'), 'validation_loss_ce': tensor(0.3768, device='cuda:0'), 'validation_loss_bbox': tensor(0.1280, device='cuda:0'), 'validation_loss_giou': tensor(0.4449, device='cuda:0'), 'validation_cardinality_error': tensor(0.5556, device='cuda:0')}
-{'training_loss': tensor(1.1680, device='cuda:0'), 'train_loss_ce': tensor(0.3623, device='cuda:0'), 'train_loss_bbox': tensor(0.0808, device='cuda:0'), 'train_loss_giou': tensor(0.2009, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8161, device='cuda:0'), 'validation_loss_ce': tensor(0.3561, device='cuda:0'), 'validation_loss_bbox': tensor(0.1127, device='cuda:0'), 'validation_loss_giou': tensor(0.4482, device='cuda:0'), 'validation_cardinality_error': tensor(0.6364, device='cuda:0')}
-{'training_loss': tensor(1.3337, device='cuda:0'), 'train_loss_ce': tensor(0.2750, device='cuda:0'), 'train_loss_bbox': tensor(0.0752, device='cuda:0'), 'train_loss_giou': tensor(0.3413, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9931, device='cuda:0'), 'validation_loss_ce': tensor(0.3794, device='cuda:0'), 'validation_loss_bbox': tensor(0.1348, device='cuda:0'), 'validation_loss_giou': tensor(0.4698, device='cuda:0'), 'validation_cardinality_error': tensor(0.7273, device='cuda:0')}
-{'training_loss': tensor(1.6290, device='cuda:0'), 'train_loss_ce': tensor(0.1759, device='cuda:0'), 'train_loss_bbox': tensor(0.1032, device='cuda:0'), 'train_loss_giou': tensor(0.4685, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8118, device='cuda:0'), 'validation_loss_ce': tensor(0.3543, device='cuda:0'), 'validation_loss_bbox': tensor(0.1188, device='cuda:0'), 'validation_loss_giou': tensor(0.4318, device='cuda:0'), 'validation_cardinality_error': tensor(0.8182, device='cuda:0')}
-{'training_loss': tensor(1.0428, device='cuda:0'), 'train_loss_ce': tensor(0.2748, device='cuda:0'), 'train_loss_bbox': tensor(0.0603, device='cuda:0'), 'train_loss_giou': tensor(0.2332, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(1.8947, device='cuda:0'), 'validation_loss_ce': tensor(0.3599, device='cuda:0'), 'validation_loss_bbox': tensor(0.1270, device='cuda:0'), 'validation_loss_giou': tensor(0.4498, device='cuda:0'), 'validation_cardinality_error': tensor(0.7071, device='cuda:0')}
-{'training_loss': tensor(1.3277, device='cuda:0'), 'train_loss_ce': tensor(0.3765, device='cuda:0'), 'train_loss_bbox': tensor(0.0675, device='cuda:0'), 'train_loss_giou': tensor(0.3067, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.8379, device='cuda:0'), 'validation_loss_ce': tensor(0.3622, device='cuda:0'), 'validation_loss_bbox': tensor(0.1199, device='cuda:0'), 'validation_loss_giou': tensor(0.4380, device='cuda:0'), 'validation_cardinality_error': tensor(0.6768, device='cuda:0')}
-{'training_loss': tensor(0.8329, device='cuda:0'), 'train_loss_ce': tensor(0.1931, device='cuda:0'), 'train_loss_bbox': tensor(0.0430, device='cuda:0'), 'train_loss_giou': tensor(0.2123, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8473, device='cuda:0'), 'validation_loss_ce': tensor(0.3623, device='cuda:0'), 'validation_loss_bbox': tensor(0.1220, device='cuda:0'), 'validation_loss_giou': tensor(0.4375, device='cuda:0'), 'validation_cardinality_error': tensor(0.6970, device='cuda:0')}
-{'training_loss': tensor(0.8308, device='cuda:0'), 'train_loss_ce': tensor(0.2576, device='cuda:0'), 'train_loss_bbox': tensor(0.0404, device='cuda:0'), 'train_loss_giou': tensor(0.1856, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8586, device='cuda:0'), 'validation_loss_ce': tensor(0.3569, device='cuda:0'), 'validation_loss_bbox': tensor(0.1232, device='cuda:0'), 'validation_loss_giou': tensor(0.4428, device='cuda:0'), 'validation_cardinality_error': tensor(0.8182, device='cuda:0')}
-{'training_loss': tensor(1.0060, device='cuda:0'), 'train_loss_ce': tensor(0.2221, device='cuda:0'), 'train_loss_bbox': tensor(0.0567, device='cuda:0'), 'train_loss_giou': tensor(0.2502, device='cuda:0'), 'train_cardinality_error': tensor(1.8000, device='cuda:0'), 'validation_loss': tensor(1.8269, device='cuda:0'), 'validation_loss_ce': tensor(0.3623, device='cuda:0'), 'validation_loss_bbox': tensor(0.1209, device='cuda:0'), 'validation_loss_giou': tensor(0.4299, device='cuda:0'), 'validation_cardinality_error': tensor(0.6566, device='cuda:0')}
-{'training_loss': tensor(0.8133, device='cuda:0'), 'train_loss_ce': tensor(0.1912, device='cuda:0'), 'train_loss_bbox': tensor(0.0634, device='cuda:0'), 'train_loss_giou': tensor(0.1526, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.8257, device='cuda:0'), 'validation_loss_ce': tensor(0.3930, device='cuda:0'), 'validation_loss_bbox': tensor(0.1178, device='cuda:0'), 'validation_loss_giou': tensor(0.4218, device='cuda:0'), 'validation_cardinality_error': tensor(0.7475, device='cuda:0')}
-{'training_loss': tensor(0.7469, device='cuda:0'), 'train_loss_ce': tensor(0.1062, device='cuda:0'), 'train_loss_bbox': tensor(0.0483, device='cuda:0'), 'train_loss_giou': tensor(0.1995, device='cuda:0'), 'train_cardinality_error': tensor(1.6000, device='cuda:0'), 'validation_loss': tensor(1.8782, device='cuda:0'), 'validation_loss_ce': tensor(0.3785, device='cuda:0'), 'validation_loss_bbox': tensor(0.1186, device='cuda:0'), 'validation_loss_giou': tensor(0.4534, device='cuda:0'), 'validation_cardinality_error': tensor(0.7172, device='cuda:0')}
-{'training_loss': tensor(0.9501, device='cuda:0'), 'train_loss_ce': tensor(0.1827, device='cuda:0'), 'train_loss_bbox': tensor(0.0738, device='cuda:0'), 'train_loss_giou': tensor(0.1992, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9531, device='cuda:0'), 'validation_loss_ce': tensor(0.3779, device='cuda:0'), 'validation_loss_bbox': tensor(0.1274, device='cuda:0'), 'validation_loss_giou': tensor(0.4690, device='cuda:0'), 'validation_cardinality_error': tensor(0.7677, device='cuda:0')}
-{'training_loss': tensor(0.6456, device='cuda:0'), 'train_loss_ce': tensor(0.1112, device='cuda:0'), 'train_loss_bbox': tensor(0.0401, device='cuda:0'), 'train_loss_giou': tensor(0.1668, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(1.9024, device='cuda:0'), 'validation_loss_ce': tensor(0.3739, device='cuda:0'), 'validation_loss_bbox': tensor(0.1244, device='cuda:0'), 'validation_loss_giou': tensor(0.4531, device='cuda:0'), 'validation_cardinality_error': tensor(0.7071, device='cuda:0')}
-{'training_loss': tensor(0.7231, device='cuda:0'), 'train_loss_ce': tensor(0.2216, device='cuda:0'), 'train_loss_bbox': tensor(0.0425, device='cuda:0'), 'train_loss_giou': tensor(0.1446, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8880, device='cuda:0'), 'validation_loss_ce': tensor(0.3662, device='cuda:0'), 'validation_loss_bbox': tensor(0.1263, device='cuda:0'), 'validation_loss_giou': tensor(0.4451, device='cuda:0'), 'validation_cardinality_error': tensor(0.6667, device='cuda:0')}
-{'training_loss': tensor(0.8083, device='cuda:0'), 'train_loss_ce': tensor(0.1597, device='cuda:0'), 'train_loss_bbox': tensor(0.0396, device='cuda:0'), 'train_loss_giou': tensor(0.2252, device='cuda:0'), 'train_cardinality_error': tensor(1.2000, device='cuda:0'), 'validation_loss': tensor(1.8730, device='cuda:0'), 'validation_loss_ce': tensor(0.3666, device='cuda:0'), 'validation_loss_bbox': tensor(0.1243, device='cuda:0'), 'validation_loss_giou': tensor(0.4424, device='cuda:0'), 'validation_cardinality_error': tensor(0.7677, device='cuda:0')}
-{'training_loss': tensor(0.8300, device='cuda:0'), 'train_loss_ce': tensor(0.1294, device='cuda:0'), 'train_loss_bbox': tensor(0.0581, device='cuda:0'), 'train_loss_giou': tensor(0.2051, device='cuda:0'), 'train_cardinality_error': tensor(2.4000, device='cuda:0'), 'validation_loss': tensor(1.8896, device='cuda:0'), 'validation_loss_ce': tensor(0.3598, device='cuda:0'), 'validation_loss_bbox': tensor(0.1265, device='cuda:0'), 'validation_loss_giou': tensor(0.4486, device='cuda:0'), 'validation_cardinality_error': tensor(1.2020, device='cuda:0')}
-{'training_loss': tensor(0.7547, device='cuda:0'), 'train_loss_ce': tensor(0.1714, device='cuda:0'), 'train_loss_bbox': tensor(0.0385, device='cuda:0'), 'train_loss_giou': tensor(0.1953, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.8844, device='cuda:0'), 'validation_loss_ce': tensor(0.3863, device='cuda:0'), 'validation_loss_bbox': tensor(0.1247, device='cuda:0'), 'validation_loss_giou': tensor(0.4372, device='cuda:0'), 'validation_cardinality_error': tensor(1.0505, device='cuda:0')}
-{'training_loss': tensor(0.6149, device='cuda:0'), 'train_loss_ce': tensor(0.0732, device='cuda:0'), 'train_loss_bbox': tensor(0.0420, device='cuda:0'), 'train_loss_giou': tensor(0.1659, device='cuda:0'), 'train_cardinality_error': tensor(1.6000, device='cuda:0'), 'validation_loss': tensor(1.9739, device='cuda:0'), 'validation_loss_ce': tensor(0.4317, device='cuda:0'), 'validation_loss_bbox': tensor(0.1259, device='cuda:0'), 'validation_loss_giou': tensor(0.4563, device='cuda:0'), 'validation_cardinality_error': tensor(0.9495, device='cuda:0')}
-{'training_loss': tensor(0.7402, device='cuda:0'), 'train_loss_ce': tensor(0.1470, device='cuda:0'), 'train_loss_bbox': tensor(0.0381, device='cuda:0'), 'train_loss_giou': tensor(0.2013, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.9754, device='cuda:0'), 'validation_loss_ce': tensor(0.3963, device='cuda:0'), 'validation_loss_bbox': tensor(0.1296, device='cuda:0'), 'validation_loss_giou': tensor(0.4657, device='cuda:0'), 'validation_cardinality_error': tensor(0.8485, device='cuda:0')}
-{'training_loss': tensor(0.7696, device='cuda:0'), 'train_loss_ce': tensor(0.0860, device='cuda:0'), 'train_loss_bbox': tensor(0.0650, device='cuda:0'), 'train_loss_giou': tensor(0.1794, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(2.0560, device='cuda:0'), 'validation_loss_ce': tensor(0.4615, device='cuda:0'), 'validation_loss_bbox': tensor(0.1319, device='cuda:0'), 'validation_loss_giou': tensor(0.4674, device='cuda:0'), 'validation_cardinality_error': tensor(0.7879, device='cuda:0')}
-{'training_loss': tensor(0.6586, device='cuda:0'), 'train_loss_ce': tensor(0.1435, device='cuda:0'), 'train_loss_bbox': tensor(0.0339, device='cuda:0'), 'train_loss_giou': tensor(0.1727, device='cuda:0'), 'train_cardinality_error': tensor(1.2000, device='cuda:0'), 'validation_loss': tensor(1.9738, device='cuda:0'), 'validation_loss_ce': tensor(0.4302, device='cuda:0'), 'validation_loss_bbox': tensor(0.1304, device='cuda:0'), 'validation_loss_giou': tensor(0.4456, device='cuda:0'), 'validation_cardinality_error': tensor(0.6263, device='cuda:0')}
-{'training_loss': tensor(0.6021, device='cuda:0'), 'train_loss_ce': tensor(0.1640, device='cuda:0'), 'train_loss_bbox': tensor(0.0302, device='cuda:0'), 'train_loss_giou': tensor(0.1435, device='cuda:0'), 'train_cardinality_error': tensor(2.4000, device='cuda:0'), 'validation_loss': tensor(1.9352, device='cuda:0'), 'validation_loss_ce': tensor(0.3988, device='cuda:0'), 'validation_loss_bbox': tensor(0.1245, device='cuda:0'), 'validation_loss_giou': tensor(0.4569, device='cuda:0'), 'validation_cardinality_error': tensor(1.0808, device='cuda:0')}
-{'training_loss': tensor(0.8966, device='cuda:0'), 'train_loss_ce': tensor(0.1546, device='cuda:0'), 'train_loss_bbox': tensor(0.0577, device='cuda:0'), 'train_loss_giou': tensor(0.2268, device='cuda:0'), 'train_cardinality_error': tensor(1.4000, device='cuda:0'), 'validation_loss': tensor(1.9241, device='cuda:0'), 'validation_loss_ce': tensor(0.4078, device='cuda:0'), 'validation_loss_bbox': tensor(0.1259, device='cuda:0'), 'validation_loss_giou': tensor(0.4435, device='cuda:0'), 'validation_cardinality_error': tensor(1.1818, device='cuda:0')}
-{'training_loss': tensor(1.0319, device='cuda:0'), 'train_loss_ce': tensor(0.1619, device='cuda:0'), 'train_loss_bbox': tensor(0.0362, device='cuda:0'), 'train_loss_giou': tensor(0.3445, device='cuda:0'), 'train_cardinality_error': tensor(1.8000, device='cuda:0'), 'validation_loss': tensor(2.0069, device='cuda:0'), 'validation_loss_ce': tensor(0.3800, device='cuda:0'), 'validation_loss_bbox': tensor(0.1369, device='cuda:0'), 'validation_loss_giou': tensor(0.4711, device='cuda:0'), 'validation_cardinality_error': tensor(0.7879, device='cuda:0')}
-{'training_loss': tensor(0.9223, device='cuda:0'), 'train_loss_ce': tensor(0.1558, device='cuda:0'), 'train_loss_bbox': tensor(0.0659, device='cuda:0'), 'train_loss_giou': tensor(0.2184, device='cuda:0'), 'train_cardinality_error': tensor(2.2000, device='cuda:0'), 'validation_loss': tensor(1.9303, device='cuda:0'), 'validation_loss_ce': tensor(0.3612, device='cuda:0'), 'validation_loss_bbox': tensor(0.1333, device='cuda:0'), 'validation_loss_giou': tensor(0.4514, device='cuda:0'), 'validation_cardinality_error': tensor(0.7778, device='cuda:0')}
-{'training_loss': tensor(0.8721, device='cuda:0'), 'train_loss_ce': tensor(0.2239, device='cuda:0'), 'train_loss_bbox': tensor(0.0450, device='cuda:0'), 'train_loss_giou': tensor(0.2117, device='cuda:0'), 'train_cardinality_error': tensor(3., device='cuda:0'), 'validation_loss': tensor(2.0897, device='cuda:0'), 'validation_loss_ce': tensor(0.3954, device='cuda:0'), 'validation_loss_bbox': tensor(0.1372, device='cuda:0'), 'validation_loss_giou': tensor(0.5040, device='cuda:0'), 'validation_cardinality_error': tensor(1.4545, device='cuda:0')}
-{'training_loss': tensor(1.1552, device='cuda:0'), 'train_loss_ce': tensor(0.2509, device='cuda:0'), 'train_loss_bbox': tensor(0.0664, device='cuda:0'), 'train_loss_giou': tensor(0.2862, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0082, device='cuda:0'), 'validation_loss_ce': tensor(0.3658, device='cuda:0'), 'validation_loss_bbox': tensor(0.1394, device='cuda:0'), 'validation_loss_giou': tensor(0.4726, device='cuda:0'), 'validation_cardinality_error': tensor(0.8384, device='cuda:0')}
-{'training_loss': tensor(0.8142, device='cuda:0'), 'train_loss_ce': tensor(0.1869, device='cuda:0'), 'train_loss_bbox': tensor(0.0506, device='cuda:0'), 'train_loss_giou': tensor(0.1872, device='cuda:0'), 'train_cardinality_error': tensor(2.8000, device='cuda:0'), 'validation_loss': tensor(2.0076, device='cuda:0'), 'validation_loss_ce': tensor(0.3652, device='cuda:0'), 'validation_loss_bbox': tensor(0.1318, device='cuda:0'), 'validation_loss_giou': tensor(0.4916, device='cuda:0'), 'validation_cardinality_error': tensor(1.1010, device='cuda:0')}
-{'training_loss': tensor(1.4431, device='cuda:0'), 'train_loss_ce': tensor(0.3380, device='cuda:0'), 'train_loss_bbox': tensor(0.0939, device='cuda:0'), 'train_loss_giou': tensor(0.3177, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9940, device='cuda:0'), 'validation_loss_ce': tensor(0.4066, device='cuda:0'), 'validation_loss_bbox': tensor(0.1247, device='cuda:0'), 'validation_loss_giou': tensor(0.4819, device='cuda:0'), 'validation_cardinality_error': tensor(0.8586, device='cuda:0')}
-{'training_loss': tensor(1.0364, device='cuda:0'), 'train_loss_ce': tensor(0.2702, device='cuda:0'), 'train_loss_bbox': tensor(0.0481, device='cuda:0'), 'train_loss_giou': tensor(0.2628, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9175, device='cuda:0'), 'validation_loss_ce': tensor(0.3807, device='cuda:0'), 'validation_loss_bbox': tensor(0.1269, device='cuda:0'), 'validation_loss_giou': tensor(0.4513, device='cuda:0'), 'validation_cardinality_error': tensor(0.8283, device='cuda:0')}
-{'training_loss': tensor(1.0160, device='cuda:0'), 'train_loss_ce': tensor(0.1882, device='cuda:0'), 'train_loss_bbox': tensor(0.0697, device='cuda:0'), 'train_loss_giou': tensor(0.2396, device='cuda:0'), 'train_cardinality_error': tensor(1.4000, device='cuda:0'), 'validation_loss': tensor(2.0068, device='cuda:0'), 'validation_loss_ce': tensor(0.3978, device='cuda:0'), 'validation_loss_bbox': tensor(0.1304, device='cuda:0'), 'validation_loss_giou': tensor(0.4785, device='cuda:0'), 'validation_cardinality_error': tensor(0.6667, device='cuda:0')}
-{'training_loss': tensor(0.7601, device='cuda:0'), 'train_loss_ce': tensor(0.2106, device='cuda:0'), 'train_loss_bbox': tensor(0.0381, device='cuda:0'), 'train_loss_giou': tensor(0.1795, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8925, device='cuda:0'), 'validation_loss_ce': tensor(0.3990, device='cuda:0'), 'validation_loss_bbox': tensor(0.1269, device='cuda:0'), 'validation_loss_giou': tensor(0.4295, device='cuda:0'), 'validation_cardinality_error': tensor(0.6970, device='cuda:0')}
-{'training_loss': tensor(0.6129, device='cuda:0'), 'train_loss_ce': tensor(0.1430, device='cuda:0'), 'train_loss_bbox': tensor(0.0323, device='cuda:0'), 'train_loss_giou': tensor(0.1541, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9653, device='cuda:0'), 'validation_loss_ce': tensor(0.4163, device='cuda:0'), 'validation_loss_bbox': tensor(0.1287, device='cuda:0'), 'validation_loss_giou': tensor(0.4527, device='cuda:0'), 'validation_cardinality_error': tensor(0.7273, device='cuda:0')}
-{'training_loss': tensor(0.6866, device='cuda:0'), 'train_loss_ce': tensor(0.1647, device='cuda:0'), 'train_loss_bbox': tensor(0.0391, device='cuda:0'), 'train_loss_giou': tensor(0.1632, device='cuda:0'), 'train_cardinality_error': tensor(1.2000, device='cuda:0'), 'validation_loss': tensor(1.9499, device='cuda:0'), 'validation_loss_ce': tensor(0.4386, device='cuda:0'), 'validation_loss_bbox': tensor(0.1267, device='cuda:0'), 'validation_loss_giou': tensor(0.4389, device='cuda:0'), 'validation_cardinality_error': tensor(0.9091, device='cuda:0')}
-{'training_loss': tensor(0.6045, device='cuda:0'), 'train_loss_ce': tensor(0.0944, device='cuda:0'), 'train_loss_bbox': tensor(0.0349, device='cuda:0'), 'train_loss_giou': tensor(0.1677, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9993, device='cuda:0'), 'validation_loss_ce': tensor(0.4357, device='cuda:0'), 'validation_loss_bbox': tensor(0.1280, device='cuda:0'), 'validation_loss_giou': tensor(0.4617, device='cuda:0'), 'validation_cardinality_error': tensor(0.8889, device='cuda:0')}
-{'training_loss': tensor(1.3557, device='cuda:0'), 'train_loss_ce': tensor(0.1851, device='cuda:0'), 'train_loss_bbox': tensor(0.0766, device='cuda:0'), 'train_loss_giou': tensor(0.3937, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.9931, device='cuda:0'), 'validation_loss_ce': tensor(0.4444, device='cuda:0'), 'validation_loss_bbox': tensor(0.1335, device='cuda:0'), 'validation_loss_giou': tensor(0.4407, device='cuda:0'), 'validation_cardinality_error': tensor(0.8687, device='cuda:0')}
-{'training_loss': tensor(0.5330, device='cuda:0'), 'train_loss_ce': tensor(0.1816, device='cuda:0'), 'train_loss_bbox': tensor(0.0202, device='cuda:0'), 'train_loss_giou': tensor(0.1252, device='cuda:0'), 'train_cardinality_error': tensor(3., device='cuda:0'), 'validation_loss': tensor(2.0736, device='cuda:0'), 'validation_loss_ce': tensor(0.4412, device='cuda:0'), 'validation_loss_bbox': tensor(0.1370, device='cuda:0'), 'validation_loss_giou': tensor(0.4736, device='cuda:0'), 'validation_cardinality_error': tensor(1.0101, device='cuda:0')}
-{'training_loss': tensor(0.8716, device='cuda:0'), 'train_loss_ce': tensor(0.2841, device='cuda:0'), 'train_loss_bbox': tensor(0.0302, device='cuda:0'), 'train_loss_giou': tensor(0.2181, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(2.0201, device='cuda:0'), 'validation_loss_ce': tensor(0.4935, device='cuda:0'), 'validation_loss_bbox': tensor(0.1270, device='cuda:0'), 'validation_loss_giou': tensor(0.4457, device='cuda:0'), 'validation_cardinality_error': tensor(1.3434, device='cuda:0')}
-{'training_loss': tensor(0.7222, device='cuda:0'), 'train_loss_ce': tensor(0.2035, device='cuda:0'), 'train_loss_bbox': tensor(0.0457, device='cuda:0'), 'train_loss_giou': tensor(0.1452, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9688, device='cuda:0'), 'validation_loss_ce': tensor(0.4381, device='cuda:0'), 'validation_loss_bbox': tensor(0.1307, device='cuda:0'), 'validation_loss_giou': tensor(0.4387, device='cuda:0'), 'validation_cardinality_error': tensor(0.7475, device='cuda:0')}
-{'training_loss': tensor(0.4216, device='cuda:0'), 'train_loss_ce': tensor(0.0884, device='cuda:0'), 'train_loss_bbox': tensor(0.0304, device='cuda:0'), 'train_loss_giou': tensor(0.0907, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.9887, device='cuda:0'), 'validation_loss_ce': tensor(0.4895, device='cuda:0'), 'validation_loss_bbox': tensor(0.1241, device='cuda:0'), 'validation_loss_giou': tensor(0.4392, device='cuda:0'), 'validation_cardinality_error': tensor(0.6263, device='cuda:0')}
-{'training_loss': tensor(0.6335, device='cuda:0'), 'train_loss_ce': tensor(0.1363, device='cuda:0'), 'train_loss_bbox': tensor(0.0188, device='cuda:0'), 'train_loss_giou': tensor(0.2015, device='cuda:0'), 'train_cardinality_error': tensor(1.6000, device='cuda:0'), 'validation_loss': tensor(1.9909, device='cuda:0'), 'validation_loss_ce': tensor(0.4815, device='cuda:0'), 'validation_loss_bbox': tensor(0.1249, device='cuda:0'), 'validation_loss_giou': tensor(0.4424, device='cuda:0'), 'validation_cardinality_error': tensor(0.7879, device='cuda:0')}
-{'training_loss': tensor(0.5883, device='cuda:0'), 'train_loss_ce': tensor(0.0494, device='cuda:0'), 'train_loss_bbox': tensor(0.0409, device='cuda:0'), 'train_loss_giou': tensor(0.1672, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9791, device='cuda:0'), 'validation_loss_ce': tensor(0.4998, device='cuda:0'), 'validation_loss_bbox': tensor(0.1207, device='cuda:0'), 'validation_loss_giou': tensor(0.4379, device='cuda:0'), 'validation_cardinality_error': tensor(0.8586, device='cuda:0')}
-{'training_loss': tensor(0.4353, device='cuda:0'), 'train_loss_ce': tensor(0.0519, device='cuda:0'), 'train_loss_bbox': tensor(0.0218, device='cuda:0'), 'train_loss_giou': tensor(0.1373, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(2.0719, device='cuda:0'), 'validation_loss_ce': tensor(0.5327, device='cuda:0'), 'validation_loss_bbox': tensor(0.1285, device='cuda:0'), 'validation_loss_giou': tensor(0.4484, device='cuda:0'), 'validation_cardinality_error': tensor(0.6667, device='cuda:0')}
-{'training_loss': tensor(0.6419, device='cuda:0'), 'train_loss_ce': tensor(0.1072, device='cuda:0'), 'train_loss_bbox': tensor(0.0320, device='cuda:0'), 'train_loss_giou': tensor(0.1874, device='cuda:0'), 'train_cardinality_error': tensor(1.4000, device='cuda:0'), 'validation_loss': tensor(2.1160, device='cuda:0'), 'validation_loss_ce': tensor(0.5016, device='cuda:0'), 'validation_loss_bbox': tensor(0.1378, device='cuda:0'), 'validation_loss_giou': tensor(0.4628, device='cuda:0'), 'validation_cardinality_error': tensor(0.8889, device='cuda:0')}
-{'training_loss': tensor(0.7383, device='cuda:0'), 'train_loss_ce': tensor(0.0853, device='cuda:0'), 'train_loss_bbox': tensor(0.0365, device='cuda:0'), 'train_loss_giou': tensor(0.2353, device='cuda:0'), 'train_cardinality_error': tensor(1.4000, device='cuda:0'), 'validation_loss': tensor(2.0324, device='cuda:0'), 'validation_loss_ce': tensor(0.5191, device='cuda:0'), 'validation_loss_bbox': tensor(0.1237, device='cuda:0'), 'validation_loss_giou': tensor(0.4473, device='cuda:0'), 'validation_cardinality_error': tensor(1.0909, device='cuda:0')}
-{'training_loss': tensor(0.7048, device='cuda:0'), 'train_loss_ce': tensor(0.1198, device='cuda:0'), 'train_loss_bbox': tensor(0.0352, device='cuda:0'), 'train_loss_giou': tensor(0.2044, device='cuda:0'), 'train_cardinality_error': tensor(1.4000, device='cuda:0'), 'validation_loss': tensor(2.0031, device='cuda:0'), 'validation_loss_ce': tensor(0.5021, device='cuda:0'), 'validation_loss_bbox': tensor(0.1242, device='cuda:0'), 'validation_loss_giou': tensor(0.4400, device='cuda:0'), 'validation_cardinality_error': tensor(0.8586, device='cuda:0')}
-{'training_loss': tensor(0.7183, device='cuda:0'), 'train_loss_ce': tensor(0.0303, device='cuda:0'), 'train_loss_bbox': tensor(0.0404, device='cuda:0'), 'train_loss_giou': tensor(0.2429, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(2.0240, device='cuda:0'), 'validation_loss_ce': tensor(0.5325, device='cuda:0'), 'validation_loss_bbox': tensor(0.1234, device='cuda:0'), 'validation_loss_giou': tensor(0.4374, device='cuda:0'), 'validation_cardinality_error': tensor(0.8990, device='cuda:0')}
-{'training_loss': tensor(0.5812, device='cuda:0'), 'train_loss_ce': tensor(0.0670, device='cuda:0'), 'train_loss_bbox': tensor(0.0321, device='cuda:0'), 'train_loss_giou': tensor(0.1768, device='cuda:0'), 'train_cardinality_error': tensor(1.2000, device='cuda:0'), 'validation_loss': tensor(2.0031, device='cuda:0'), 'validation_loss_ce': tensor(0.5461, device='cuda:0'), 'validation_loss_bbox': tensor(0.1206, device='cuda:0'), 'validation_loss_giou': tensor(0.4271, device='cuda:0'), 'validation_cardinality_error': tensor(0.7172, device='cuda:0')}
-{'training_loss': tensor(0.4142, device='cuda:0'), 'train_loss_ce': tensor(0.0514, device='cuda:0'), 'train_loss_bbox': tensor(0.0342, device='cuda:0'), 'train_loss_giou': tensor(0.0958, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0898, device='cuda:0'), 'validation_loss_ce': tensor(0.5431, device='cuda:0'), 'validation_loss_bbox': tensor(0.1331, device='cuda:0'), 'validation_loss_giou': tensor(0.4406, device='cuda:0'), 'validation_cardinality_error': tensor(0.8283, device='cuda:0')}
-{'training_loss': tensor(0.5866, device='cuda:0'), 'train_loss_ce': tensor(0.0849, device='cuda:0'), 'train_loss_bbox': tensor(0.0300, device='cuda:0'), 'train_loss_giou': tensor(0.1758, device='cuda:0'), 'train_cardinality_error': tensor(2.6000, device='cuda:0'), 'validation_loss': tensor(2.0080, device='cuda:0'), 'validation_loss_ce': tensor(0.4937, device='cuda:0'), 'validation_loss_bbox': tensor(0.1242, device='cuda:0'), 'validation_loss_giou': tensor(0.4467, device='cuda:0'), 'validation_cardinality_error': tensor(0.6465, device='cuda:0')}
-{'training_loss': tensor(0.5337, device='cuda:0'), 'train_loss_ce': tensor(0.0545, device='cuda:0'), 'train_loss_bbox': tensor(0.0357, device='cuda:0'), 'train_loss_giou': tensor(0.1503, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(2.1421, device='cuda:0'), 'validation_loss_ce': tensor(0.5116, device='cuda:0'), 'validation_loss_bbox': tensor(0.1371, device='cuda:0'), 'validation_loss_giou': tensor(0.4725, device='cuda:0'), 'validation_cardinality_error': tensor(0.9192, device='cuda:0')}
-{'training_loss': tensor(0.7298, device='cuda:0'), 'train_loss_ce': tensor(0.0942, device='cuda:0'), 'train_loss_bbox': tensor(0.0284, device='cuda:0'), 'train_loss_giou': tensor(0.2468, device='cuda:0'), 'train_cardinality_error': tensor(2.4000, device='cuda:0'), 'validation_loss': tensor(2.1484, device='cuda:0'), 'validation_loss_ce': tensor(0.5031, device='cuda:0'), 'validation_loss_bbox': tensor(0.1347, device='cuda:0'), 'validation_loss_giou': tensor(0.4860, device='cuda:0'), 'validation_cardinality_error': tensor(0.6768, device='cuda:0')}
-{'training_loss': tensor(0.8502, device='cuda:0'), 'train_loss_ce': tensor(0.0793, device='cuda:0'), 'train_loss_bbox': tensor(0.0461, device='cuda:0'), 'train_loss_giou': tensor(0.2702, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(2.1865, device='cuda:0'), 'validation_loss_ce': tensor(0.5221, device='cuda:0'), 'validation_loss_bbox': tensor(0.1374, device='cuda:0'), 'validation_loss_giou': tensor(0.4888, device='cuda:0'), 'validation_cardinality_error': tensor(0.6667, device='cuda:0')}
-{'training_loss': tensor(0.5967, device='cuda:0'), 'train_loss_ce': tensor(0.1064, device='cuda:0'), 'train_loss_bbox': tensor(0.0283, device='cuda:0'), 'train_loss_giou': tensor(0.1744, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(2.1303, device='cuda:0'), 'validation_loss_ce': tensor(0.5539, device='cuda:0'), 'validation_loss_bbox': tensor(0.1321, device='cuda:0'), 'validation_loss_giou': tensor(0.4579, device='cuda:0'), 'validation_cardinality_error': tensor(0.6263, device='cuda:0')}
-{'training_loss': tensor(0.6167, device='cuda:0'), 'train_loss_ce': tensor(0.1510, device='cuda:0'), 'train_loss_bbox': tensor(0.0336, device='cuda:0'), 'train_loss_giou': tensor(0.1490, device='cuda:0'), 'train_cardinality_error': tensor(2., device='cuda:0'), 'validation_loss': tensor(2.1606, device='cuda:0'), 'validation_loss_ce': tensor(0.5449, device='cuda:0'), 'validation_loss_bbox': tensor(0.1357, device='cuda:0'), 'validation_loss_giou': tensor(0.4686, device='cuda:0'), 'validation_cardinality_error': tensor(0.8081, device='cuda:0')}
+{'validation_loss': tensor(7.4925, device='cuda:0'), 'validation_loss_ce': tensor(2.5541, device='cuda:0'), 'validation_loss_bbox': tensor(0.5965, device='cuda:0'), 'validation_loss_giou': tensor(0.9779, device='cuda:0'), 'validation_cardinality_error': tensor(99., device='cuda:0')}
+{'training_loss': tensor(2.3264, device='cuda:0'), 'train_loss_ce': tensor(0.4880, device='cuda:0'), 'train_loss_bbox': tensor(0.1570, device='cuda:0'), 'train_loss_giou': tensor(0.5268, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.7121, device='cuda:0'), 'validation_loss_ce': tensor(0.4453, device='cuda:0'), 'validation_loss_bbox': tensor(0.2068, device='cuda:0'), 'validation_loss_giou': tensor(0.6163, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.8342, device='cuda:0'), 'train_loss_ce': tensor(0.4484, device='cuda:0'), 'train_loss_bbox': tensor(0.2176, device='cuda:0'), 'train_loss_giou': tensor(0.6488, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2852, device='cuda:0'), 'validation_loss_ce': tensor(0.4441, device='cuda:0'), 'validation_loss_bbox': tensor(0.1582, device='cuda:0'), 'validation_loss_giou': tensor(0.5250, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.1692, device='cuda:0'), 'train_loss_ce': tensor(0.5057, device='cuda:0'), 'train_loss_bbox': tensor(0.1269, device='cuda:0'), 'train_loss_giou': tensor(0.5145, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.1756, device='cuda:0'), 'validation_loss_ce': tensor(0.4304, device='cuda:0'), 'validation_loss_bbox': tensor(0.1417, device='cuda:0'), 'validation_loss_giou': tensor(0.5182, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.7561, device='cuda:0'), 'train_loss_ce': tensor(0.3625, device='cuda:0'), 'train_loss_bbox': tensor(0.0990, device='cuda:0'), 'train_loss_giou': tensor(0.4493, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0836, device='cuda:0'), 'validation_loss_ce': tensor(0.4193, device='cuda:0'), 'validation_loss_bbox': tensor(0.1388, device='cuda:0'), 'validation_loss_giou': tensor(0.4853, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.2515, device='cuda:0'), 'train_loss_ce': tensor(0.3129, device='cuda:0'), 'train_loss_bbox': tensor(0.1513, device='cuda:0'), 'train_loss_giou': tensor(0.5911, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.2070, device='cuda:0'), 'validation_loss_ce': tensor(0.4197, device='cuda:0'), 'validation_loss_bbox': tensor(0.1543, device='cuda:0'), 'validation_loss_giou': tensor(0.5080, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.8786, device='cuda:0'), 'train_loss_ce': tensor(0.3963, device='cuda:0'), 'train_loss_bbox': tensor(0.1198, device='cuda:0'), 'train_loss_giou': tensor(0.4417, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0831, device='cuda:0'), 'validation_loss_ce': tensor(0.3973, device='cuda:0'), 'validation_loss_bbox': tensor(0.1401, device='cuda:0'), 'validation_loss_giou': tensor(0.4926, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.5512, device='cuda:0'), 'train_loss_ce': tensor(0.2639, device='cuda:0'), 'train_loss_bbox': tensor(0.1068, device='cuda:0'), 'train_loss_giou': tensor(0.3767, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0724, device='cuda:0'), 'validation_loss_ce': tensor(0.3991, device='cuda:0'), 'validation_loss_bbox': tensor(0.1392, device='cuda:0'), 'validation_loss_giou': tensor(0.4886, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(2.2770, device='cuda:0'), 'train_loss_ce': tensor(0.3291, device='cuda:0'), 'train_loss_bbox': tensor(0.1538, device='cuda:0'), 'train_loss_giou': tensor(0.5893, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9589, device='cuda:0'), 'validation_loss_ce': tensor(0.3826, device='cuda:0'), 'validation_loss_bbox': tensor(0.1305, device='cuda:0'), 'validation_loss_giou': tensor(0.4619, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.3441, device='cuda:0'), 'train_loss_ce': tensor(0.2611, device='cuda:0'), 'train_loss_bbox': tensor(0.1015, device='cuda:0'), 'train_loss_giou': tensor(0.2877, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9805, device='cuda:0'), 'validation_loss_ce': tensor(0.3821, device='cuda:0'), 'validation_loss_bbox': tensor(0.1331, device='cuda:0'), 'validation_loss_giou': tensor(0.4666, device='cuda:0'), 'validation_cardinality_error': tensor(0.8788, device='cuda:0')}
+{'training_loss': tensor(2.1461, device='cuda:0'), 'train_loss_ce': tensor(0.4859, device='cuda:0'), 'train_loss_bbox': tensor(0.1561, device='cuda:0'), 'train_loss_giou': tensor(0.4398, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(2.0157, device='cuda:0'), 'validation_loss_ce': tensor(0.3812, device='cuda:0'), 'validation_loss_bbox': tensor(0.1427, device='cuda:0'), 'validation_loss_giou': tensor(0.4606, device='cuda:0'), 'validation_cardinality_error': tensor(0.6364, device='cuda:0')}
+{'training_loss': tensor(1.3417, device='cuda:0'), 'train_loss_ce': tensor(0.3160, device='cuda:0'), 'train_loss_bbox': tensor(0.0713, device='cuda:0'), 'train_loss_giou': tensor(0.3345, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0049, device='cuda:0'), 'validation_loss_ce': tensor(0.3601, device='cuda:0'), 'validation_loss_bbox': tensor(0.1361, device='cuda:0'), 'validation_loss_giou': tensor(0.4822, device='cuda:0'), 'validation_cardinality_error': tensor(0.5657, device='cuda:0')}
+{'training_loss': tensor(1.5425, device='cuda:0'), 'train_loss_ce': tensor(0.2479, device='cuda:0'), 'train_loss_bbox': tensor(0.0981, device='cuda:0'), 'train_loss_giou': tensor(0.4021, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8925, device='cuda:0'), 'validation_loss_ce': tensor(0.3583, device='cuda:0'), 'validation_loss_bbox': tensor(0.1248, device='cuda:0'), 'validation_loss_giou': tensor(0.4552, device='cuda:0'), 'validation_cardinality_error': tensor(0.8687, device='cuda:0')}
+{'training_loss': tensor(1.4850, device='cuda:0'), 'train_loss_ce': tensor(0.3857, device='cuda:0'), 'train_loss_bbox': tensor(0.0768, device='cuda:0'), 'train_loss_giou': tensor(0.3578, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8232, device='cuda:0'), 'validation_loss_ce': tensor(0.3643, device='cuda:0'), 'validation_loss_bbox': tensor(0.1205, device='cuda:0'), 'validation_loss_giou': tensor(0.4282, device='cuda:0'), 'validation_cardinality_error': tensor(0.8687, device='cuda:0')}
+{'training_loss': tensor(1.5018, device='cuda:0'), 'train_loss_ce': tensor(0.3052, device='cuda:0'), 'train_loss_bbox': tensor(0.0905, device='cuda:0'), 'train_loss_giou': tensor(0.3722, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.8548, device='cuda:0'), 'validation_loss_ce': tensor(0.3484, device='cuda:0'), 'validation_loss_bbox': tensor(0.1246, device='cuda:0'), 'validation_loss_giou': tensor(0.4417, device='cuda:0'), 'validation_cardinality_error': tensor(0.5455, device='cuda:0')}
+{'training_loss': tensor(1.8176, device='cuda:0'), 'train_loss_ce': tensor(0.3194, device='cuda:0'), 'train_loss_bbox': tensor(0.0987, device='cuda:0'), 'train_loss_giou': tensor(0.5023, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.9924, device='cuda:0'), 'validation_loss_ce': tensor(0.3666, device='cuda:0'), 'validation_loss_bbox': tensor(0.1335, device='cuda:0'), 'validation_loss_giou': tensor(0.4792, device='cuda:0'), 'validation_cardinality_error': tensor(0.6667, device='cuda:0')}
+{'training_loss': tensor(1.1465, device='cuda:0'), 'train_loss_ce': tensor(0.2934, device='cuda:0'), 'train_loss_bbox': tensor(0.0725, device='cuda:0'), 'train_loss_giou': tensor(0.2453, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.8425, device='cuda:0'), 'validation_loss_ce': tensor(0.3420, device='cuda:0'), 'validation_loss_bbox': tensor(0.1222, device='cuda:0'), 'validation_loss_giou': tensor(0.4447, device='cuda:0'), 'validation_cardinality_error': tensor(0.5051, device='cuda:0')}
+{'training_loss': tensor(1.0657, device='cuda:0'), 'train_loss_ce': tensor(0.3183, device='cuda:0'), 'train_loss_bbox': tensor(0.0595, device='cuda:0'), 'train_loss_giou': tensor(0.2250, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.7772, device='cuda:0'), 'validation_loss_ce': tensor(0.3470, device='cuda:0'), 'validation_loss_bbox': tensor(0.1146, device='cuda:0'), 'validation_loss_giou': tensor(0.4286, device='cuda:0'), 'validation_cardinality_error': tensor(0.4545, device='cuda:0')}
+{'training_loss': tensor(1.9365, device='cuda:0'), 'train_loss_ce': tensor(0.3658, device='cuda:0'), 'train_loss_bbox': tensor(0.1439, device='cuda:0'), 'train_loss_giou': tensor(0.4255, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(1.8952, device='cuda:0'), 'validation_loss_ce': tensor(0.3404, device='cuda:0'), 'validation_loss_bbox': tensor(0.1274, device='cuda:0'), 'validation_loss_giou': tensor(0.4588, device='cuda:0'), 'validation_cardinality_error': tensor(0.4646, device='cuda:0')}
+{'training_loss': tensor(1.4351, device='cuda:0'), 'train_loss_ce': tensor(0.2594, device='cuda:0'), 'train_loss_bbox': tensor(0.0838, device='cuda:0'), 'train_loss_giou': tensor(0.3785, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(1.8806, device='cuda:0'), 'validation_loss_ce': tensor(0.3522, device='cuda:0'), 'validation_loss_bbox': tensor(0.1258, device='cuda:0'), 'validation_loss_giou': tensor(0.4497, device='cuda:0'), 'validation_cardinality_error': tensor(0.3535, device='cuda:0')}
+{'training_loss': tensor(1.5704, device='cuda:0'), 'train_loss_ce': tensor(0.3388, device='cuda:0'), 'train_loss_bbox': tensor(0.0924, device='cuda:0'), 'train_loss_giou': tensor(0.3847, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.9434, device='cuda:0'), 'validation_loss_ce': tensor(0.3550, device='cuda:0'), 'validation_loss_bbox': tensor(0.1306, device='cuda:0'), 'validation_loss_giou': tensor(0.4676, device='cuda:0'), 'validation_cardinality_error': tensor(0.7071, device='cuda:0')}
+{'training_loss': tensor(1.7988, device='cuda:0'), 'train_loss_ce': tensor(0.4468, device='cuda:0'), 'train_loss_bbox': tensor(0.0877, device='cuda:0'), 'train_loss_giou': tensor(0.4567, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.7616, device='cuda:0'), 'validation_loss_ce': tensor(0.3391, device='cuda:0'), 'validation_loss_bbox': tensor(0.1124, device='cuda:0'), 'validation_loss_giou': tensor(0.4302, device='cuda:0'), 'validation_cardinality_error': tensor(0.4040, device='cuda:0')}
+{'training_loss': tensor(1.4750, device='cuda:0'), 'train_loss_ce': tensor(0.3582, device='cuda:0'), 'train_loss_bbox': tensor(0.0899, device='cuda:0'), 'train_loss_giou': tensor(0.3337, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8399, device='cuda:0'), 'validation_loss_ce': tensor(0.3391, device='cuda:0'), 'validation_loss_bbox': tensor(0.1225, device='cuda:0'), 'validation_loss_giou': tensor(0.4442, device='cuda:0'), 'validation_cardinality_error': tensor(0.4040, device='cuda:0')}
+{'training_loss': tensor(1.8876, device='cuda:0'), 'train_loss_ce': tensor(0.3162, device='cuda:0'), 'train_loss_bbox': tensor(0.1306, device='cuda:0'), 'train_loss_giou': tensor(0.4592, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(1.8054, device='cuda:0'), 'validation_loss_ce': tensor(0.3289, device='cuda:0'), 'validation_loss_bbox': tensor(0.1177, device='cuda:0'), 'validation_loss_giou': tensor(0.4439, device='cuda:0'), 'validation_cardinality_error': tensor(0.2626, device='cuda:0')}
+{'training_loss': tensor(1.5214, device='cuda:0'), 'train_loss_ce': tensor(0.4220, device='cuda:0'), 'train_loss_bbox': tensor(0.1034, device='cuda:0'), 'train_loss_giou': tensor(0.2911, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(1.8686, device='cuda:0'), 'validation_loss_ce': tensor(0.3355, device='cuda:0'), 'validation_loss_bbox': tensor(0.1293, device='cuda:0'), 'validation_loss_giou': tensor(0.4434, device='cuda:0'), 'validation_cardinality_error': tensor(0.4040, device='cuda:0')}
+{'training_loss': tensor(1.6568, device='cuda:0'), 'train_loss_ce': tensor(0.3218, device='cuda:0'), 'train_loss_bbox': tensor(0.0998, device='cuda:0'), 'train_loss_giou': tensor(0.4181, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9430, device='cuda:0'), 'validation_loss_ce': tensor(0.3508, device='cuda:0'), 'validation_loss_bbox': tensor(0.1318, device='cuda:0'), 'validation_loss_giou': tensor(0.4665, device='cuda:0'), 'validation_cardinality_error': tensor(0.9293, device='cuda:0')}
+{'training_loss': tensor(1.7328, device='cuda:0'), 'train_loss_ce': tensor(0.4156, device='cuda:0'), 'train_loss_bbox': tensor(0.0824, device='cuda:0'), 'train_loss_giou': tensor(0.4527, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(1.8903, device='cuda:0'), 'validation_loss_ce': tensor(0.3503, device='cuda:0'), 'validation_loss_bbox': tensor(0.1208, device='cuda:0'), 'validation_loss_giou': tensor(0.4681, device='cuda:0'), 'validation_cardinality_error': tensor(0.3737, device='cuda:0')}
+{'training_loss': tensor(1.5311, device='cuda:0'), 'train_loss_ce': tensor(0.3013, device='cuda:0'), 'train_loss_bbox': tensor(0.1027, device='cuda:0'), 'train_loss_giou': tensor(0.3582, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(2.0567, device='cuda:0'), 'validation_loss_ce': tensor(0.3694, device='cuda:0'), 'validation_loss_bbox': tensor(0.1428, device='cuda:0'), 'validation_loss_giou': tensor(0.4867, device='cuda:0'), 'validation_cardinality_error': tensor(0.2525, device='cuda:0')}
+{'training_loss': tensor(2.6274, device='cuda:0'), 'train_loss_ce': tensor(0.3244, device='cuda:0'), 'train_loss_bbox': tensor(0.1597, device='cuda:0'), 'train_loss_giou': tensor(0.7522, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.7862, device='cuda:0'), 'validation_loss_ce': tensor(0.3303, device='cuda:0'), 'validation_loss_bbox': tensor(0.1217, device='cuda:0'), 'validation_loss_giou': tensor(0.4238, device='cuda:0'), 'validation_cardinality_error': tensor(0.6263, device='cuda:0')}
+{'training_loss': tensor(1.2280, device='cuda:0'), 'train_loss_ce': tensor(0.3173, device='cuda:0'), 'train_loss_bbox': tensor(0.0821, device='cuda:0'), 'train_loss_giou': tensor(0.2502, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(1.7541, device='cuda:0'), 'validation_loss_ce': tensor(0.3245, device='cuda:0'), 'validation_loss_bbox': tensor(0.1159, device='cuda:0'), 'validation_loss_giou': tensor(0.4251, device='cuda:0'), 'validation_cardinality_error': tensor(0.5758, device='cuda:0')}
+{'training_loss': tensor(2.1156, device='cuda:0'), 'train_loss_ce': tensor(0.3874, device='cuda:0'), 'train_loss_bbox': tensor(0.1171, device='cuda:0'), 'train_loss_giou': tensor(0.5713, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.7310, device='cuda:0'), 'validation_loss_ce': tensor(0.3306, device='cuda:0'), 'validation_loss_bbox': tensor(0.1136, device='cuda:0'), 'validation_loss_giou': tensor(0.4161, device='cuda:0'), 'validation_cardinality_error': tensor(0.7677, device='cuda:0')}
+{'training_loss': tensor(1.5396, device='cuda:0'), 'train_loss_ce': tensor(0.2611, device='cuda:0'), 'train_loss_bbox': tensor(0.1037, device='cuda:0'), 'train_loss_giou': tensor(0.3800, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8486, device='cuda:0'), 'validation_loss_ce': tensor(0.3286, device='cuda:0'), 'validation_loss_bbox': tensor(0.1257, device='cuda:0'), 'validation_loss_giou': tensor(0.4458, device='cuda:0'), 'validation_cardinality_error': tensor(0.2929, device='cuda:0')}
+{'training_loss': tensor(1.4614, device='cuda:0'), 'train_loss_ce': tensor(0.3526, device='cuda:0'), 'train_loss_bbox': tensor(0.0802, device='cuda:0'), 'train_loss_giou': tensor(0.3538, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.9545, device='cuda:0'), 'validation_loss_ce': tensor(0.3581, device='cuda:0'), 'validation_loss_bbox': tensor(0.1326, device='cuda:0'), 'validation_loss_giou': tensor(0.4668, device='cuda:0'), 'validation_cardinality_error': tensor(0.8788, device='cuda:0')}
+{'training_loss': tensor(1.9016, device='cuda:0'), 'train_loss_ce': tensor(0.3195, device='cuda:0'), 'train_loss_bbox': tensor(0.1198, device='cuda:0'), 'train_loss_giou': tensor(0.4916, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(1.8477, device='cuda:0'), 'validation_loss_ce': tensor(0.3207, device='cuda:0'), 'validation_loss_bbox': tensor(0.1241, device='cuda:0'), 'validation_loss_giou': tensor(0.4532, device='cuda:0'), 'validation_cardinality_error': tensor(0.4040, device='cuda:0')}
+{'training_loss': tensor(1.8817, device='cuda:0'), 'train_loss_ce': tensor(0.3269, device='cuda:0'), 'train_loss_bbox': tensor(0.1378, device='cuda:0'), 'train_loss_giou': tensor(0.4330, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.9073, device='cuda:0'), 'validation_loss_ce': tensor(0.3216, device='cuda:0'), 'validation_loss_bbox': tensor(0.1274, device='cuda:0'), 'validation_loss_giou': tensor(0.4743, device='cuda:0'), 'validation_cardinality_error': tensor(0.7778, device='cuda:0')}
+{'training_loss': tensor(2.4130, device='cuda:0'), 'train_loss_ce': tensor(0.3232, device='cuda:0'), 'train_loss_bbox': tensor(0.1843, device='cuda:0'), 'train_loss_giou': tensor(0.5841, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8564, device='cuda:0'), 'validation_loss_ce': tensor(0.3216, device='cuda:0'), 'validation_loss_bbox': tensor(0.1274, device='cuda:0'), 'validation_loss_giou': tensor(0.4490, device='cuda:0'), 'validation_cardinality_error': tensor(0.5758, device='cuda:0')}
+{'training_loss': tensor(1.7000, device='cuda:0'), 'train_loss_ce': tensor(0.3662, device='cuda:0'), 'train_loss_bbox': tensor(0.0844, device='cuda:0'), 'train_loss_giou': tensor(0.4558, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8421, device='cuda:0'), 'validation_loss_ce': tensor(0.3481, device='cuda:0'), 'validation_loss_bbox': tensor(0.1201, device='cuda:0'), 'validation_loss_giou': tensor(0.4467, device='cuda:0'), 'validation_cardinality_error': tensor(0.4646, device='cuda:0')}
+{'training_loss': tensor(1.7469, device='cuda:0'), 'train_loss_ce': tensor(0.2118, device='cuda:0'), 'train_loss_bbox': tensor(0.1563, device='cuda:0'), 'train_loss_giou': tensor(0.3767, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.8326, device='cuda:0'), 'validation_loss_ce': tensor(0.3209, device='cuda:0'), 'validation_loss_bbox': tensor(0.1240, device='cuda:0'), 'validation_loss_giou': tensor(0.4458, device='cuda:0'), 'validation_cardinality_error': tensor(0.4141, device='cuda:0')}
+{'training_loss': tensor(1.7565, device='cuda:0'), 'train_loss_ce': tensor(0.1709, device='cuda:0'), 'train_loss_bbox': tensor(0.0879, device='cuda:0'), 'train_loss_giou': tensor(0.5730, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.8730, device='cuda:0'), 'validation_loss_ce': tensor(0.3249, device='cuda:0'), 'validation_loss_bbox': tensor(0.1275, device='cuda:0'), 'validation_loss_giou': tensor(0.4553, device='cuda:0'), 'validation_cardinality_error': tensor(0.3838, device='cuda:0')}
+{'training_loss': tensor(1.5408, device='cuda:0'), 'train_loss_ce': tensor(0.3118, device='cuda:0'), 'train_loss_bbox': tensor(0.0859, device='cuda:0'), 'train_loss_giou': tensor(0.3999, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.7961, device='cuda:0'), 'validation_loss_ce': tensor(0.3173, device='cuda:0'), 'validation_loss_bbox': tensor(0.1208, device='cuda:0'), 'validation_loss_giou': tensor(0.4375, device='cuda:0'), 'validation_cardinality_error': tensor(0.4545, device='cuda:0')}
+{'training_loss': tensor(1.3644, device='cuda:0'), 'train_loss_ce': tensor(0.2795, device='cuda:0'), 'train_loss_bbox': tensor(0.0769, device='cuda:0'), 'train_loss_giou': tensor(0.3502, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.8532, device='cuda:0'), 'validation_loss_ce': tensor(0.3439, device='cuda:0'), 'validation_loss_bbox': tensor(0.1287, device='cuda:0'), 'validation_loss_giou': tensor(0.4328, device='cuda:0'), 'validation_cardinality_error': tensor(0.5657, device='cuda:0')}
+{'training_loss': tensor(1.1239, device='cuda:0'), 'train_loss_ce': tensor(0.3182, device='cuda:0'), 'train_loss_bbox': tensor(0.0746, device='cuda:0'), 'train_loss_giou': tensor(0.2163, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(2.0984, device='cuda:0'), 'validation_loss_ce': tensor(0.3335, device='cuda:0'), 'validation_loss_bbox': tensor(0.1464, device='cuda:0'), 'validation_loss_giou': tensor(0.5165, device='cuda:0'), 'validation_cardinality_error': tensor(0.3636, device='cuda:0')}
+{'training_loss': tensor(1.4970, device='cuda:0'), 'train_loss_ce': tensor(0.3141, device='cuda:0'), 'train_loss_bbox': tensor(0.0944, device='cuda:0'), 'train_loss_giou': tensor(0.3555, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.9576, device='cuda:0'), 'validation_loss_ce': tensor(0.3247, device='cuda:0'), 'validation_loss_bbox': tensor(0.1342, device='cuda:0'), 'validation_loss_giou': tensor(0.4810, device='cuda:0'), 'validation_cardinality_error': tensor(0.5455, device='cuda:0')}
+{'training_loss': tensor(1.4003, device='cuda:0'), 'train_loss_ce': tensor(0.2166, device='cuda:0'), 'train_loss_bbox': tensor(0.0724, device='cuda:0'), 'train_loss_giou': tensor(0.4108, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(1.9156, device='cuda:0'), 'validation_loss_ce': tensor(0.3234, device='cuda:0'), 'validation_loss_bbox': tensor(0.1337, device='cuda:0'), 'validation_loss_giou': tensor(0.4619, device='cuda:0'), 'validation_cardinality_error': tensor(0.5152, device='cuda:0')}
+{'training_loss': tensor(1.2544, device='cuda:0'), 'train_loss_ce': tensor(0.2942, device='cuda:0'), 'train_loss_bbox': tensor(0.0794, device='cuda:0'), 'train_loss_giou': tensor(0.2815, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(2.0829, device='cuda:0'), 'validation_loss_ce': tensor(0.3535, device='cuda:0'), 'validation_loss_bbox': tensor(0.1463, device='cuda:0'), 'validation_loss_giou': tensor(0.4990, device='cuda:0'), 'validation_cardinality_error': tensor(0.5960, device='cuda:0')}
+{'training_loss': tensor(1.9876, device='cuda:0'), 'train_loss_ce': tensor(0.2309, device='cuda:0'), 'train_loss_bbox': tensor(0.1941, device='cuda:0'), 'train_loss_giou': tensor(0.3930, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(2.0909, device='cuda:0'), 'validation_loss_ce': tensor(0.3460, device='cuda:0'), 'validation_loss_bbox': tensor(0.1507, device='cuda:0'), 'validation_loss_giou': tensor(0.4957, device='cuda:0'), 'validation_cardinality_error': tensor(0.4949, device='cuda:0')}
+{'training_loss': tensor(1.7261, device='cuda:0'), 'train_loss_ce': tensor(0.2997, device='cuda:0'), 'train_loss_bbox': tensor(0.1047, device='cuda:0'), 'train_loss_giou': tensor(0.4515, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(1.9829, device='cuda:0'), 'validation_loss_ce': tensor(0.3362, device='cuda:0'), 'validation_loss_bbox': tensor(0.1342, device='cuda:0'), 'validation_loss_giou': tensor(0.4878, device='cuda:0'), 'validation_cardinality_error': tensor(0.6465, device='cuda:0')}
+{'training_loss': tensor(1.1098, device='cuda:0'), 'train_loss_ce': tensor(0.2768, device='cuda:0'), 'train_loss_bbox': tensor(0.0634, device='cuda:0'), 'train_loss_giou': tensor(0.2579, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(2.1523, device='cuda:0'), 'validation_loss_ce': tensor(0.3616, device='cuda:0'), 'validation_loss_bbox': tensor(0.1435, device='cuda:0'), 'validation_loss_giou': tensor(0.5365, device='cuda:0'), 'validation_cardinality_error': tensor(0.6768, device='cuda:0')}
+{'training_loss': tensor(1.1501, device='cuda:0'), 'train_loss_ce': tensor(0.2511, device='cuda:0'), 'train_loss_bbox': tensor(0.1015, device='cuda:0'), 'train_loss_giou': tensor(0.1957, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(1.9119, device='cuda:0'), 'validation_loss_ce': tensor(0.3425, device='cuda:0'), 'validation_loss_bbox': tensor(0.1300, device='cuda:0'), 'validation_loss_giou': tensor(0.4596, device='cuda:0'), 'validation_cardinality_error': tensor(0.4848, device='cuda:0')}
+{'training_loss': tensor(2.2693, device='cuda:0'), 'train_loss_ce': tensor(0.2723, device='cuda:0'), 'train_loss_bbox': tensor(0.1527, device='cuda:0'), 'train_loss_giou': tensor(0.6168, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9472, device='cuda:0'), 'validation_loss_ce': tensor(0.3583, device='cuda:0'), 'validation_loss_bbox': tensor(0.1320, device='cuda:0'), 'validation_loss_giou': tensor(0.4644, device='cuda:0'), 'validation_cardinality_error': tensor(0.6667, device='cuda:0')}
+{'training_loss': tensor(0.9290, device='cuda:0'), 'train_loss_ce': tensor(0.2324, device='cuda:0'), 'train_loss_bbox': tensor(0.0654, device='cuda:0'), 'train_loss_giou': tensor(0.1847, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(2.1173, device='cuda:0'), 'validation_loss_ce': tensor(0.3557, device='cuda:0'), 'validation_loss_bbox': tensor(0.1476, device='cuda:0'), 'validation_loss_giou': tensor(0.5119, device='cuda:0'), 'validation_cardinality_error': tensor(0.7172, device='cuda:0')}
+{'training_loss': tensor(1.2413, device='cuda:0'), 'train_loss_ce': tensor(0.3473, device='cuda:0'), 'train_loss_bbox': tensor(0.0458, device='cuda:0'), 'train_loss_giou': tensor(0.3324, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8865, device='cuda:0'), 'validation_loss_ce': tensor(0.3591, device='cuda:0'), 'validation_loss_bbox': tensor(0.1217, device='cuda:0'), 'validation_loss_giou': tensor(0.4593, device='cuda:0'), 'validation_cardinality_error': tensor(0.6667, device='cuda:0')}
+{'training_loss': tensor(1.4967, device='cuda:0'), 'train_loss_ce': tensor(0.4218, device='cuda:0'), 'train_loss_bbox': tensor(0.0720, device='cuda:0'), 'train_loss_giou': tensor(0.3574, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0452, device='cuda:0'), 'validation_loss_ce': tensor(0.3850, device='cuda:0'), 'validation_loss_bbox': tensor(0.1376, device='cuda:0'), 'validation_loss_giou': tensor(0.4861, device='cuda:0'), 'validation_cardinality_error': tensor(0.9192, device='cuda:0')}
+{'training_loss': tensor(1.3397, device='cuda:0'), 'train_loss_ce': tensor(0.2367, device='cuda:0'), 'train_loss_bbox': tensor(0.1158, device='cuda:0'), 'train_loss_giou': tensor(0.2620, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.9833, device='cuda:0'), 'validation_loss_ce': tensor(0.3665, device='cuda:0'), 'validation_loss_bbox': tensor(0.1364, device='cuda:0'), 'validation_loss_giou': tensor(0.4673, device='cuda:0'), 'validation_cardinality_error': tensor(0.8889, device='cuda:0')}
+{'training_loss': tensor(1.6956, device='cuda:0'), 'train_loss_ce': tensor(0.3173, device='cuda:0'), 'train_loss_bbox': tensor(0.0916, device='cuda:0'), 'train_loss_giou': tensor(0.4601, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(1.9618, device='cuda:0'), 'validation_loss_ce': tensor(0.3245, device='cuda:0'), 'validation_loss_bbox': tensor(0.1386, device='cuda:0'), 'validation_loss_giou': tensor(0.4720, device='cuda:0'), 'validation_cardinality_error': tensor(0.5354, device='cuda:0')}
+{'training_loss': tensor(1.1396, device='cuda:0'), 'train_loss_ce': tensor(0.2333, device='cuda:0'), 'train_loss_bbox': tensor(0.0721, device='cuda:0'), 'train_loss_giou': tensor(0.2730, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8328, device='cuda:0'), 'validation_loss_ce': tensor(0.3425, device='cuda:0'), 'validation_loss_bbox': tensor(0.1240, device='cuda:0'), 'validation_loss_giou': tensor(0.4352, device='cuda:0'), 'validation_cardinality_error': tensor(0.4747, device='cuda:0')}
+{'training_loss': tensor(1.0871, device='cuda:0'), 'train_loss_ce': tensor(0.2299, device='cuda:0'), 'train_loss_bbox': tensor(0.0565, device='cuda:0'), 'train_loss_giou': tensor(0.2873, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(1.8545, device='cuda:0'), 'validation_loss_ce': tensor(0.3696, device='cuda:0'), 'validation_loss_bbox': tensor(0.1226, device='cuda:0'), 'validation_loss_giou': tensor(0.4359, device='cuda:0'), 'validation_cardinality_error': tensor(0.2727, device='cuda:0')}
+{'training_loss': tensor(1.3639, device='cuda:0'), 'train_loss_ce': tensor(0.1798, device='cuda:0'), 'train_loss_bbox': tensor(0.1214, device='cuda:0'), 'train_loss_giou': tensor(0.2885, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.9228, device='cuda:0'), 'validation_loss_ce': tensor(0.3585, device='cuda:0'), 'validation_loss_bbox': tensor(0.1256, device='cuda:0'), 'validation_loss_giou': tensor(0.4682, device='cuda:0'), 'validation_cardinality_error': tensor(0.6869, device='cuda:0')}
+{'training_loss': tensor(1.7393, device='cuda:0'), 'train_loss_ce': tensor(0.2350, device='cuda:0'), 'train_loss_bbox': tensor(0.1224, device='cuda:0'), 'train_loss_giou': tensor(0.4462, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9342, device='cuda:0'), 'validation_loss_ce': tensor(0.3558, device='cuda:0'), 'validation_loss_bbox': tensor(0.1307, device='cuda:0'), 'validation_loss_giou': tensor(0.4625, device='cuda:0'), 'validation_cardinality_error': tensor(0.7475, device='cuda:0')}
+{'training_loss': tensor(1.7079, device='cuda:0'), 'train_loss_ce': tensor(0.1986, device='cuda:0'), 'train_loss_bbox': tensor(0.1289, device='cuda:0'), 'train_loss_giou': tensor(0.4323, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0021, device='cuda:0'), 'validation_loss_ce': tensor(0.3432, device='cuda:0'), 'validation_loss_bbox': tensor(0.1376, device='cuda:0'), 'validation_loss_giou': tensor(0.4854, device='cuda:0'), 'validation_cardinality_error': tensor(0.6566, device='cuda:0')}
+{'training_loss': tensor(1.5813, device='cuda:0'), 'train_loss_ce': tensor(0.2767, device='cuda:0'), 'train_loss_bbox': tensor(0.0934, device='cuda:0'), 'train_loss_giou': tensor(0.4187, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9703, device='cuda:0'), 'validation_loss_ce': tensor(0.3368, device='cuda:0'), 'validation_loss_bbox': tensor(0.1375, device='cuda:0'), 'validation_loss_giou': tensor(0.4731, device='cuda:0'), 'validation_cardinality_error': tensor(0.5556, device='cuda:0')}
+{'training_loss': tensor(1.5485, device='cuda:0'), 'train_loss_ce': tensor(0.2712, device='cuda:0'), 'train_loss_bbox': tensor(0.0982, device='cuda:0'), 'train_loss_giou': tensor(0.3931, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.8743, device='cuda:0'), 'validation_loss_ce': tensor(0.3535, device='cuda:0'), 'validation_loss_bbox': tensor(0.1231, device='cuda:0'), 'validation_loss_giou': tensor(0.4527, device='cuda:0'), 'validation_cardinality_error': tensor(0.5657, device='cuda:0')}
+{'training_loss': tensor(1.0340, device='cuda:0'), 'train_loss_ce': tensor(0.2134, device='cuda:0'), 'train_loss_bbox': tensor(0.0602, device='cuda:0'), 'train_loss_giou': tensor(0.2598, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.9241, device='cuda:0'), 'validation_loss_ce': tensor(0.3598, device='cuda:0'), 'validation_loss_bbox': tensor(0.1284, device='cuda:0'), 'validation_loss_giou': tensor(0.4612, device='cuda:0'), 'validation_cardinality_error': tensor(0.6869, device='cuda:0')}
+{'training_loss': tensor(1.3158, device='cuda:0'), 'train_loss_ce': tensor(0.3823, device='cuda:0'), 'train_loss_bbox': tensor(0.0984, device='cuda:0'), 'train_loss_giou': tensor(0.2209, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.8715, device='cuda:0'), 'validation_loss_ce': tensor(0.3522, device='cuda:0'), 'validation_loss_bbox': tensor(0.1257, device='cuda:0'), 'validation_loss_giou': tensor(0.4454, device='cuda:0'), 'validation_cardinality_error': tensor(0.4444, device='cuda:0')}
+{'training_loss': tensor(0.9308, device='cuda:0'), 'train_loss_ce': tensor(0.1364, device='cuda:0'), 'train_loss_bbox': tensor(0.0530, device='cuda:0'), 'train_loss_giou': tensor(0.2648, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9659, device='cuda:0'), 'validation_loss_ce': tensor(0.3548, device='cuda:0'), 'validation_loss_bbox': tensor(0.1373, device='cuda:0'), 'validation_loss_giou': tensor(0.4622, device='cuda:0'), 'validation_cardinality_error': tensor(0.2424, device='cuda:0')}
+{'training_loss': tensor(1.3534, device='cuda:0'), 'train_loss_ce': tensor(0.3225, device='cuda:0'), 'train_loss_bbox': tensor(0.1003, device='cuda:0'), 'train_loss_giou': tensor(0.2646, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(2.0871, device='cuda:0'), 'validation_loss_ce': tensor(0.3548, device='cuda:0'), 'validation_loss_bbox': tensor(0.1477, device='cuda:0'), 'validation_loss_giou': tensor(0.4969, device='cuda:0'), 'validation_cardinality_error': tensor(0.6869, device='cuda:0')}
+{'training_loss': tensor(1.7097, device='cuda:0'), 'train_loss_ce': tensor(0.3047, device='cuda:0'), 'train_loss_bbox': tensor(0.1078, device='cuda:0'), 'train_loss_giou': tensor(0.4329, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(2.1222, device='cuda:0'), 'validation_loss_ce': tensor(0.3638, device='cuda:0'), 'validation_loss_bbox': tensor(0.1531, device='cuda:0'), 'validation_loss_giou': tensor(0.4965, device='cuda:0'), 'validation_cardinality_error': tensor(0.5455, device='cuda:0')}
+{'training_loss': tensor(2.0316, device='cuda:0'), 'train_loss_ce': tensor(0.2812, device='cuda:0'), 'train_loss_bbox': tensor(0.0919, device='cuda:0'), 'train_loss_giou': tensor(0.6455, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.9983, device='cuda:0'), 'validation_loss_ce': tensor(0.3696, device='cuda:0'), 'validation_loss_bbox': tensor(0.1388, device='cuda:0'), 'validation_loss_giou': tensor(0.4675, device='cuda:0'), 'validation_cardinality_error': tensor(0.4545, device='cuda:0')}
+{'training_loss': tensor(1.2256, device='cuda:0'), 'train_loss_ce': tensor(0.2159, device='cuda:0'), 'train_loss_bbox': tensor(0.0824, device='cuda:0'), 'train_loss_giou': tensor(0.2988, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.8724, device='cuda:0'), 'validation_loss_ce': tensor(0.3637, device='cuda:0'), 'validation_loss_bbox': tensor(0.1269, device='cuda:0'), 'validation_loss_giou': tensor(0.4371, device='cuda:0'), 'validation_cardinality_error': tensor(0.6162, device='cuda:0')}
+{'training_loss': tensor(1.3514, device='cuda:0'), 'train_loss_ce': tensor(0.1869, device='cuda:0'), 'train_loss_bbox': tensor(0.0742, device='cuda:0'), 'train_loss_giou': tensor(0.3967, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8816, device='cuda:0'), 'validation_loss_ce': tensor(0.3441, device='cuda:0'), 'validation_loss_bbox': tensor(0.1223, device='cuda:0'), 'validation_loss_giou': tensor(0.4629, device='cuda:0'), 'validation_cardinality_error': tensor(0.3636, device='cuda:0')}
+{'training_loss': tensor(0.9221, device='cuda:0'), 'train_loss_ce': tensor(0.2315, device='cuda:0'), 'train_loss_bbox': tensor(0.0492, device='cuda:0'), 'train_loss_giou': tensor(0.2223, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.8565, device='cuda:0'), 'validation_loss_ce': tensor(0.3535, device='cuda:0'), 'validation_loss_bbox': tensor(0.1233, device='cuda:0'), 'validation_loss_giou': tensor(0.4433, device='cuda:0'), 'validation_cardinality_error': tensor(0.6364, device='cuda:0')}
+{'training_loss': tensor(1.3560, device='cuda:0'), 'train_loss_ce': tensor(0.2082, device='cuda:0'), 'train_loss_bbox': tensor(0.0960, device='cuda:0'), 'train_loss_giou': tensor(0.3339, device='cuda:0'), 'train_cardinality_error': tensor(0.2000, device='cuda:0'), 'validation_loss': tensor(1.8503, device='cuda:0'), 'validation_loss_ce': tensor(0.3596, device='cuda:0'), 'validation_loss_bbox': tensor(0.1204, device='cuda:0'), 'validation_loss_giou': tensor(0.4442, device='cuda:0'), 'validation_cardinality_error': tensor(0.6768, device='cuda:0')}
+{'training_loss': tensor(0.9772, device='cuda:0'), 'train_loss_ce': tensor(0.1904, device='cuda:0'), 'train_loss_bbox': tensor(0.0466, device='cuda:0'), 'train_loss_giou': tensor(0.2768, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9169, device='cuda:0'), 'validation_loss_ce': tensor(0.3756, device='cuda:0'), 'validation_loss_bbox': tensor(0.1270, device='cuda:0'), 'validation_loss_giou': tensor(0.4532, device='cuda:0'), 'validation_cardinality_error': tensor(0.5455, device='cuda:0')}
+{'training_loss': tensor(0.8828, device='cuda:0'), 'train_loss_ce': tensor(0.2542, device='cuda:0'), 'train_loss_bbox': tensor(0.0487, device='cuda:0'), 'train_loss_giou': tensor(0.1926, device='cuda:0'), 'train_cardinality_error': tensor(1.4000, device='cuda:0'), 'validation_loss': tensor(1.9725, device='cuda:0'), 'validation_loss_ce': tensor(0.3896, device='cuda:0'), 'validation_loss_bbox': tensor(0.1291, device='cuda:0'), 'validation_loss_giou': tensor(0.4686, device='cuda:0'), 'validation_cardinality_error': tensor(0.6566, device='cuda:0')}
+{'training_loss': tensor(0.9948, device='cuda:0'), 'train_loss_ce': tensor(0.2190, device='cuda:0'), 'train_loss_bbox': tensor(0.0838, device='cuda:0'), 'train_loss_giou': tensor(0.1785, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.9232, device='cuda:0'), 'validation_loss_ce': tensor(0.4014, device='cuda:0'), 'validation_loss_bbox': tensor(0.1273, device='cuda:0'), 'validation_loss_giou': tensor(0.4426, device='cuda:0'), 'validation_cardinality_error': tensor(0.5455, device='cuda:0')}
+{'training_loss': tensor(1.0668, device='cuda:0'), 'train_loss_ce': tensor(0.2886, device='cuda:0'), 'train_loss_bbox': tensor(0.0481, device='cuda:0'), 'train_loss_giou': tensor(0.2687, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.8897, device='cuda:0'), 'validation_loss_ce': tensor(0.3733, device='cuda:0'), 'validation_loss_bbox': tensor(0.1231, device='cuda:0'), 'validation_loss_giou': tensor(0.4506, device='cuda:0'), 'validation_cardinality_error': tensor(0.9091, device='cuda:0')}
+{'training_loss': tensor(0.9408, device='cuda:0'), 'train_loss_ce': tensor(0.2310, device='cuda:0'), 'train_loss_bbox': tensor(0.0689, device='cuda:0'), 'train_loss_giou': tensor(0.1827, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9338, device='cuda:0'), 'validation_loss_ce': tensor(0.3668, device='cuda:0'), 'validation_loss_bbox': tensor(0.1320, device='cuda:0'), 'validation_loss_giou': tensor(0.4536, device='cuda:0'), 'validation_cardinality_error': tensor(0.7778, device='cuda:0')}
+{'training_loss': tensor(1.2902, device='cuda:0'), 'train_loss_ce': tensor(0.3665, device='cuda:0'), 'train_loss_bbox': tensor(0.0679, device='cuda:0'), 'train_loss_giou': tensor(0.2921, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(2.0078, device='cuda:0'), 'validation_loss_ce': tensor(0.3995, device='cuda:0'), 'validation_loss_bbox': tensor(0.1352, device='cuda:0'), 'validation_loss_giou': tensor(0.4661, device='cuda:0'), 'validation_cardinality_error': tensor(0.7879, device='cuda:0')}
+{'training_loss': tensor(0.8218, device='cuda:0'), 'train_loss_ce': tensor(0.1780, device='cuda:0'), 'train_loss_bbox': tensor(0.0415, device='cuda:0'), 'train_loss_giou': tensor(0.2182, device='cuda:0'), 'train_cardinality_error': tensor(1.2000, device='cuda:0'), 'validation_loss': tensor(2.0702, device='cuda:0'), 'validation_loss_ce': tensor(0.3784, device='cuda:0'), 'validation_loss_bbox': tensor(0.1394, device='cuda:0'), 'validation_loss_giou': tensor(0.4975, device='cuda:0'), 'validation_cardinality_error': tensor(0.9394, device='cuda:0')}
+{'training_loss': tensor(1.8621, device='cuda:0'), 'train_loss_ce': tensor(0.1998, device='cuda:0'), 'train_loss_bbox': tensor(0.1682, device='cuda:0'), 'train_loss_giou': tensor(0.4107, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(2.1440, device='cuda:0'), 'validation_loss_ce': tensor(0.3787, device='cuda:0'), 'validation_loss_bbox': tensor(0.1599, device='cuda:0'), 'validation_loss_giou': tensor(0.4829, device='cuda:0'), 'validation_cardinality_error': tensor(0.6869, device='cuda:0')}
+{'training_loss': tensor(1.0829, device='cuda:0'), 'train_loss_ce': tensor(0.1853, device='cuda:0'), 'train_loss_bbox': tensor(0.0629, device='cuda:0'), 'train_loss_giou': tensor(0.2914, device='cuda:0'), 'train_cardinality_error': tensor(1.2000, device='cuda:0'), 'validation_loss': tensor(2.0309, device='cuda:0'), 'validation_loss_ce': tensor(0.3553, device='cuda:0'), 'validation_loss_bbox': tensor(0.1472, device='cuda:0'), 'validation_loss_giou': tensor(0.4698, device='cuda:0'), 'validation_cardinality_error': tensor(0.7980, device='cuda:0')}
+{'training_loss': tensor(1.1420, device='cuda:0'), 'train_loss_ce': tensor(0.1532, device='cuda:0'), 'train_loss_bbox': tensor(0.0691, device='cuda:0'), 'train_loss_giou': tensor(0.3217, device='cuda:0'), 'train_cardinality_error': tensor(1.4000, device='cuda:0'), 'validation_loss': tensor(1.9761, device='cuda:0'), 'validation_loss_ce': tensor(0.4083, device='cuda:0'), 'validation_loss_bbox': tensor(0.1330, device='cuda:0'), 'validation_loss_giou': tensor(0.4513, device='cuda:0'), 'validation_cardinality_error': tensor(0.7677, device='cuda:0')}
+{'training_loss': tensor(0.9070, device='cuda:0'), 'train_loss_ce': tensor(0.1499, device='cuda:0'), 'train_loss_bbox': tensor(0.0561, device='cuda:0'), 'train_loss_giou': tensor(0.2384, device='cuda:0'), 'train_cardinality_error': tensor(1.2000, device='cuda:0'), 'validation_loss': tensor(1.9902, device='cuda:0'), 'validation_loss_ce': tensor(0.4400, device='cuda:0'), 'validation_loss_bbox': tensor(0.1289, device='cuda:0'), 'validation_loss_giou': tensor(0.4528, device='cuda:0'), 'validation_cardinality_error': tensor(0.9293, device='cuda:0')}
+{'training_loss': tensor(0.8739, device='cuda:0'), 'train_loss_ce': tensor(0.1929, device='cuda:0'), 'train_loss_bbox': tensor(0.0761, device='cuda:0'), 'train_loss_giou': tensor(0.1502, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(1.9908, device='cuda:0'), 'validation_loss_ce': tensor(0.3882, device='cuda:0'), 'validation_loss_bbox': tensor(0.1339, device='cuda:0'), 'validation_loss_giou': tensor(0.4667, device='cuda:0'), 'validation_cardinality_error': tensor(0.7677, device='cuda:0')}
+{'training_loss': tensor(0.9192, device='cuda:0'), 'train_loss_ce': tensor(0.1021, device='cuda:0'), 'train_loss_bbox': tensor(0.0766, device='cuda:0'), 'train_loss_giou': tensor(0.2171, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.9334, device='cuda:0'), 'validation_loss_ce': tensor(0.4008, device='cuda:0'), 'validation_loss_bbox': tensor(0.1271, device='cuda:0'), 'validation_loss_giou': tensor(0.4486, device='cuda:0'), 'validation_cardinality_error': tensor(0.7374, device='cuda:0')}
+{'training_loss': tensor(0.7223, device='cuda:0'), 'train_loss_ce': tensor(0.1821, device='cuda:0'), 'train_loss_bbox': tensor(0.0433, device='cuda:0'), 'train_loss_giou': tensor(0.1619, device='cuda:0'), 'train_cardinality_error': tensor(1.4000, device='cuda:0'), 'validation_loss': tensor(1.9307, device='cuda:0'), 'validation_loss_ce': tensor(0.4025, device='cuda:0'), 'validation_loss_bbox': tensor(0.1261, device='cuda:0'), 'validation_loss_giou': tensor(0.4488, device='cuda:0'), 'validation_cardinality_error': tensor(0.5960, device='cuda:0')}
+{'training_loss': tensor(1.1063, device='cuda:0'), 'train_loss_ce': tensor(0.2344, device='cuda:0'), 'train_loss_bbox': tensor(0.0529, device='cuda:0'), 'train_loss_giou': tensor(0.3037, device='cuda:0'), 'train_cardinality_error': tensor(0.8000, device='cuda:0'), 'validation_loss': tensor(2.0237, device='cuda:0'), 'validation_loss_ce': tensor(0.4271, device='cuda:0'), 'validation_loss_bbox': tensor(0.1298, device='cuda:0'), 'validation_loss_giou': tensor(0.4738, device='cuda:0'), 'validation_cardinality_error': tensor(0.7273, device='cuda:0')}
+{'training_loss': tensor(0.6276, device='cuda:0'), 'train_loss_ce': tensor(0.1232, device='cuda:0'), 'train_loss_bbox': tensor(0.0523, device='cuda:0'), 'train_loss_giou': tensor(0.1214, device='cuda:0'), 'train_cardinality_error': tensor(1.8000, device='cuda:0'), 'validation_loss': tensor(1.8591, device='cuda:0'), 'validation_loss_ce': tensor(0.4162, device='cuda:0'), 'validation_loss_bbox': tensor(0.1148, device='cuda:0'), 'validation_loss_giou': tensor(0.4345, device='cuda:0'), 'validation_cardinality_error': tensor(0.8788, device='cuda:0')}
+{'training_loss': tensor(0.7868, device='cuda:0'), 'train_loss_ce': tensor(0.2419, device='cuda:0'), 'train_loss_bbox': tensor(0.0478, device='cuda:0'), 'train_loss_giou': tensor(0.1529, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.9230, device='cuda:0'), 'validation_loss_ce': tensor(0.4118, device='cuda:0'), 'validation_loss_bbox': tensor(0.1236, device='cuda:0'), 'validation_loss_giou': tensor(0.4466, device='cuda:0'), 'validation_cardinality_error': tensor(0.9697, device='cuda:0')}
+{'training_loss': tensor(1.2211, device='cuda:0'), 'train_loss_ce': tensor(0.2328, device='cuda:0'), 'train_loss_bbox': tensor(0.0655, device='cuda:0'), 'train_loss_giou': tensor(0.3305, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(1.9071, device='cuda:0'), 'validation_loss_ce': tensor(0.4175, device='cuda:0'), 'validation_loss_bbox': tensor(0.1238, device='cuda:0'), 'validation_loss_giou': tensor(0.4354, device='cuda:0'), 'validation_cardinality_error': tensor(0.7879, device='cuda:0')}
+{'training_loss': tensor(0.8082, device='cuda:0'), 'train_loss_ce': tensor(0.2394, device='cuda:0'), 'train_loss_bbox': tensor(0.0311, device='cuda:0'), 'train_loss_giou': tensor(0.2066, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(1.8883, device='cuda:0'), 'validation_loss_ce': tensor(0.4144, device='cuda:0'), 'validation_loss_bbox': tensor(0.1211, device='cuda:0'), 'validation_loss_giou': tensor(0.4341, device='cuda:0'), 'validation_cardinality_error': tensor(0.8485, device='cuda:0')}
+{'training_loss': tensor(0.9011, device='cuda:0'), 'train_loss_ce': tensor(0.1563, device='cuda:0'), 'train_loss_bbox': tensor(0.0334, device='cuda:0'), 'train_loss_giou': tensor(0.2890, device='cuda:0'), 'train_cardinality_error': tensor(1.8000, device='cuda:0'), 'validation_loss': tensor(1.9627, device='cuda:0'), 'validation_loss_ce': tensor(0.4335, device='cuda:0'), 'validation_loss_bbox': tensor(0.1267, device='cuda:0'), 'validation_loss_giou': tensor(0.4479, device='cuda:0'), 'validation_cardinality_error': tensor(0.8788, device='cuda:0')}
+{'training_loss': tensor(0.8532, device='cuda:0'), 'train_loss_ce': tensor(0.2237, device='cuda:0'), 'train_loss_bbox': tensor(0.0629, device='cuda:0'), 'train_loss_giou': tensor(0.1576, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(2.1048, device='cuda:0'), 'validation_loss_ce': tensor(0.4781, device='cuda:0'), 'validation_loss_bbox': tensor(0.1330, device='cuda:0'), 'validation_loss_giou': tensor(0.4809, device='cuda:0'), 'validation_cardinality_error': tensor(0.9697, device='cuda:0')}
+{'training_loss': tensor(0.8224, device='cuda:0'), 'train_loss_ce': tensor(0.1048, device='cuda:0'), 'train_loss_bbox': tensor(0.0370, device='cuda:0'), 'train_loss_giou': tensor(0.2662, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(2.0275, device='cuda:0'), 'validation_loss_ce': tensor(0.4637, device='cuda:0'), 'validation_loss_bbox': tensor(0.1276, device='cuda:0'), 'validation_loss_giou': tensor(0.4630, device='cuda:0'), 'validation_cardinality_error': tensor(0.8182, device='cuda:0')}
+{'training_loss': tensor(0.9030, device='cuda:0'), 'train_loss_ce': tensor(0.2146, device='cuda:0'), 'train_loss_bbox': tensor(0.0558, device='cuda:0'), 'train_loss_giou': tensor(0.2047, device='cuda:0'), 'train_cardinality_error': tensor(4., device='cuda:0'), 'validation_loss': tensor(2.0526, device='cuda:0'), 'validation_loss_ce': tensor(0.4696, device='cuda:0'), 'validation_loss_bbox': tensor(0.1312, device='cuda:0'), 'validation_loss_giou': tensor(0.4635, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(0.6652, device='cuda:0'), 'train_loss_ce': tensor(0.2014, device='cuda:0'), 'train_loss_bbox': tensor(0.0383, device='cuda:0'), 'train_loss_giou': tensor(0.1362, device='cuda:0'), 'train_cardinality_error': tensor(4.4000, device='cuda:0'), 'validation_loss': tensor(1.9326, device='cuda:0'), 'validation_loss_ce': tensor(0.4480, device='cuda:0'), 'validation_loss_bbox': tensor(0.1194, device='cuda:0'), 'validation_loss_giou': tensor(0.4438, device='cuda:0'), 'validation_cardinality_error': tensor(1.0101, device='cuda:0')}
+{'training_loss': tensor(1.1147, device='cuda:0'), 'train_loss_ce': tensor(0.3158, device='cuda:0'), 'train_loss_bbox': tensor(0.0584, device='cuda:0'), 'train_loss_giou': tensor(0.2536, device='cuda:0'), 'train_cardinality_error': tensor(3.6000, device='cuda:0'), 'validation_loss': tensor(2.0196, device='cuda:0'), 'validation_loss_ce': tensor(0.4547, device='cuda:0'), 'validation_loss_bbox': tensor(0.1329, device='cuda:0'), 'validation_loss_giou': tensor(0.4501, device='cuda:0'), 'validation_cardinality_error': tensor(1., device='cuda:0')}
+{'training_loss': tensor(1.0267, device='cuda:0'), 'train_loss_ce': tensor(0.1566, device='cuda:0'), 'train_loss_bbox': tensor(0.0750, device='cuda:0'), 'train_loss_giou': tensor(0.2475, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(2.0730, device='cuda:0'), 'validation_loss_ce': tensor(0.4747, device='cuda:0'), 'validation_loss_bbox': tensor(0.1282, device='cuda:0'), 'validation_loss_giou': tensor(0.4787, device='cuda:0'), 'validation_cardinality_error': tensor(0.8182, device='cuda:0')}
+{'training_loss': tensor(0.7079, device='cuda:0'), 'train_loss_ce': tensor(0.0955, device='cuda:0'), 'train_loss_bbox': tensor(0.0404, device='cuda:0'), 'train_loss_giou': tensor(0.2051, device='cuda:0'), 'train_cardinality_error': tensor(2.8000, device='cuda:0'), 'validation_loss': tensor(2.0235, device='cuda:0'), 'validation_loss_ce': tensor(0.4538, device='cuda:0'), 'validation_loss_bbox': tensor(0.1329, device='cuda:0'), 'validation_loss_giou': tensor(0.4525, device='cuda:0'), 'validation_cardinality_error': tensor(0.8182, device='cuda:0')}
+{'training_loss': tensor(0.5221, device='cuda:0'), 'train_loss_ce': tensor(0.1109, device='cuda:0'), 'train_loss_bbox': tensor(0.0314, device='cuda:0'), 'train_loss_giou': tensor(0.1271, device='cuda:0'), 'train_cardinality_error': tensor(0.4000, device='cuda:0'), 'validation_loss': tensor(2.0294, device='cuda:0'), 'validation_loss_ce': tensor(0.4754, device='cuda:0'), 'validation_loss_bbox': tensor(0.1272, device='cuda:0'), 'validation_loss_giou': tensor(0.4590, device='cuda:0'), 'validation_cardinality_error': tensor(0.7980, device='cuda:0')}
+{'training_loss': tensor(0.7147, device='cuda:0'), 'train_loss_ce': tensor(0.1476, device='cuda:0'), 'train_loss_bbox': tensor(0.0458, device='cuda:0'), 'train_loss_giou': tensor(0.1690, device='cuda:0'), 'train_cardinality_error': tensor(0.6000, device='cuda:0'), 'validation_loss': tensor(2.0873, device='cuda:0'), 'validation_loss_ce': tensor(0.4671, device='cuda:0'), 'validation_loss_bbox': tensor(0.1382, device='cuda:0'), 'validation_loss_giou': tensor(0.4647, device='cuda:0'), 'validation_cardinality_error': tensor(0.7980, device='cuda:0')}
 ```
 
 ## Examples