Hugging Face's logo

polejowska
/
detr-r50-cd45rb-8ah-6l-gelu-corrected

Object Detection
Transformers
PyTorch
detr
Generated from Trainer
Inference Endpoints
Model card Files Community
2
polejowska commited on
Commit
277babb
•
1 Parent(s): d4be0bc

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +29 -24
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the cd45rb dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.5992
20
 
21
  ## Model description
22
 
@@ -41,33 +41,38 @@ The following hyperparameters were used during training:
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
- - num_epochs: 20
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss |
50
- |:-------------:|:-----:|:-----:|:---------------:|
51
- | 3.0438 | 1.0 | 4606 | 1.9413 |
52
- | 2.3933 | 2.0 | 9212 | 1.8238 |
53
- | 2.2782 | 3.0 | 13818 | 1.7718 |
54
- | 2.2383 | 4.0 | 18424 | 1.7528 |
55
- | 2.2046 | 5.0 | 23030 | 1.7265 |
56
- | 2.1659 | 6.0 | 27636 | 1.7125 |
57
- | 2.1457 | 7.0 | 32242 | 1.6760 |
58
- | 2.1111 | 8.0 | 36848 | 1.6622 |
59
- | 2.0959 | 9.0 | 41454 | 1.6467 |
60
- | 2.0826 | 10.0 | 46060 | 1.6392 |
61
- | 2.1132 | 11.0 | 50666 | 1.6875 |
62
- | 2.1145 | 12.0 | 55272 | 1.6863 |
63
- | 2.0947 | 13.0 | 59878 | 1.6528 |
64
- | 2.0777 | 14.0 | 64484 | 1.6669 |
65
- | 2.0551 | 15.0 | 69090 | 1.6241 |
66
- | 2.0567 | 16.0 | 73696 | 1.6241 |
67
- | 2.042 | 17.0 | 78302 | 1.6171 |
68
- | 2.0306 | 18.0 | 82908 | 1.6062 |
69
- | 2.015 | 19.0 | 87514 | 1.5989 |
70
- | 2.0084 | 20.0 | 92120 | 1.5992 |
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the cd45rb dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.5861
20
 
21
  ## Model description
22
 
 
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
+ - num_epochs: 25
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:------:|:---------------:|
51
+ | 3.0438 | 1.0 | 4606 | 1.9413 |
52
+ | 2.3933 | 2.0 | 9212 | 1.8238 |
53
+ | 2.2782 | 3.0 | 13818 | 1.7718 |
54
+ | 2.2383 | 4.0 | 18424 | 1.7528 |
55
+ | 2.2046 | 5.0 | 23030 | 1.7265 |
56
+ | 2.1659 | 6.0 | 27636 | 1.7125 |
57
+ | 2.1457 | 7.0 | 32242 | 1.6760 |
58
+ | 2.1111 | 8.0 | 36848 | 1.6622 |
59
+ | 2.0959 | 9.0 | 41454 | 1.6467 |
60
+ | 2.0826 | 10.0 | 46060 | 1.6392 |
61
+ | 2.1132 | 11.0 | 50666 | 1.6875 |
62
+ | 2.1145 | 12.0 | 55272 | 1.6863 |
63
+ | 2.0947 | 13.0 | 59878 | 1.6528 |
64
+ | 2.0777 | 14.0 | 64484 | 1.6669 |
65
+ | 2.0551 | 15.0 | 69090 | 1.6241 |
66
+ | 2.0567 | 16.0 | 73696 | 1.6241 |
67
+ | 2.042 | 17.0 | 78302 | 1.6171 |
68
+ | 2.0306 | 18.0 | 82908 | 1.6062 |
69
+ | 2.015 | 19.0 | 87514 | 1.5989 |
70
+ | 2.0206 | 20.0 | 92120 | 1.6168 |
71
+ | 2.026 | 21.0 | 96726 | 1.6022 |
72
+ | 2.0109 | 22.0 | 101332 | 1.5996 |
73
+ | 2.0133 | 23.0 | 105938 | 1.5983 |
74
+ | 2.0081 | 24.0 | 110544 | 1.5888 |
75
+ | 1.9975 | 25.0 | 115150 | 1.5861 |
76
 
77
 
78
  ### Framework versions