Hugging Face's logo

cheesebird
/
detr

Object Detection
Transformers
TensorBoard
Safetensors
detr
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
cheesebird commited on
Commit
ebdab88
·
verified ·
1 Parent(s): 678bb9e

End of training

Browse files
Files changed (1) hide show
  1. README.md +27 -12
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.0253
19
 
20
  ## Model description
21
 
@@ -34,7 +34,7 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 0.0001
38
  - train_batch_size: 4
39
  - eval_batch_size: 8
40
  - seed: 42
@@ -47,16 +47,31 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 2.5385 | 0.1 | 250 | 1.9164 |
51
- | 1.952 | 0.2 | 500 | 1.6952 |
52
- | 1.7037 | 0.3 | 750 | 1.6839 |
53
- | 1.5698 | 0.4 | 1000 | 1.4518 |
54
- | 1.4471 | 0.5 | 1250 | 1.4302 |
55
- | 1.3161 | 0.6 | 1500 | 1.2422 |
56
- | 1.2208 | 0.7 | 1750 | 1.1559 |
57
- | 1.1466 | 0.8 | 2000 | 1.0832 |
58
- | 1.1077 | 0.9 | 2250 | 1.0370 |
59
- | 1.0793 | 1.0 | 2500 | 1.0253 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 5.4000
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 0.0005
38
  - train_batch_size: 4
39
  - eval_batch_size: 8
40
  - seed: 42
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 3.4552 | 0.04 | 100 | 5.8812 |
51
+ | 3.0646 | 0.08 | 200 | 6.1299 |
52
+ | 2.8724 | 0.12 | 300 | 5.4912 |
53
+ | 2.7418 | 0.16 | 400 | 6.3882 |
54
+ | 2.6577 | 0.2 | 500 | 5.5691 |
55
+ | 2.5283 | 0.24 | 600 | 5.7357 |
56
+ | 2.4574 | 0.28 | 700 | 5.6403 |
57
+ | 2.3614 | 0.32 | 800 | 5.4325 |
58
+ | 2.342 | 0.36 | 900 | 6.4478 |
59
+ | 2.3154 | 0.4 | 1000 | 5.8527 |
60
+ | 2.3305 | 0.44 | 1100 | 5.8006 |
61
+ | 2.2296 | 0.48 | 1200 | 5.5432 |
62
+ | 2.2821 | 0.52 | 1300 | 5.3882 |
63
+ | 2.2623 | 0.56 | 1400 | 5.3867 |
64
+ | 2.1653 | 0.6 | 1500 | 5.9831 |
65
+ | 2.1729 | 0.64 | 1600 | 5.5752 |
66
+ | 2.1155 | 0.68 | 1700 | 5.4664 |
67
+ | 2.094 | 0.72 | 1800 | 5.5329 |
68
+ | 2.0948 | 0.76 | 1900 | 5.4304 |
69
+ | 1.9956 | 0.8 | 2000 | 5.9376 |
70
+ | 2.0062 | 0.84 | 2100 | 5.7035 |
71
+ | 2.0472 | 0.88 | 2200 | 5.4439 |
72
+ | 2.0699 | 0.92 | 2300 | 5.3537 |
73
+ | 1.9993 | 0.96 | 2400 | 5.3219 |
74
+ | 1.9494 | 1.0 | 2500 | 5.4000 |
75
 
76
 
77
  ### Framework versions