Hugging Face's logo

joe611
/
chickens

Object Detection
Transformers
TensorBoard
Safetensors
detr
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
joe611 commited on
Commit
f8326ac
·
verified ·
1 Parent(s): ad49322

End of training

Browse files
Files changed (1) hide show
  1. README.md +63 -34
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 None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.6675
20
 
21
  ## Model description
22
 
@@ -35,49 +35,78 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 1e-05
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
- - num_epochs: 30
45
- - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | No log | 1.0 | 13 | 0.9785 |
52
- | No log | 2.0 | 26 | 0.9392 |
53
- | 1.1336 | 3.0 | 39 | 0.8768 |
54
- | 1.1336 | 4.0 | 52 | 0.8375 |
55
- | 0.9422 | 5.0 | 65 | 0.8428 |
56
- | 0.9422 | 6.0 | 78 | 0.8161 |
57
- | 0.8703 | 7.0 | 91 | 0.7947 |
58
- | 0.8703 | 8.0 | 104 | 0.7691 |
59
- | 0.8703 | 9.0 | 117 | 0.7788 |
60
- | 0.8332 | 10.0 | 130 | 0.7683 |
61
- | 0.8332 | 11.0 | 143 | 0.7432 |
62
- | 0.7978 | 12.0 | 156 | 0.7431 |
63
- | 0.7978 | 13.0 | 169 | 0.7229 |
64
- | 0.7796 | 14.0 | 182 | 0.7483 |
65
- | 0.7796 | 15.0 | 195 | 0.7237 |
66
- | 0.7796 | 16.0 | 208 | 0.7092 |
67
- | 0.7763 | 17.0 | 221 | 0.7036 |
68
- | 0.7763 | 18.0 | 234 | 0.7014 |
69
- | 0.749 | 19.0 | 247 | 0.6938 |
70
- | 0.749 | 20.0 | 260 | 0.6885 |
71
- | 0.742 | 21.0 | 273 | 0.6886 |
72
- | 0.742 | 22.0 | 286 | 0.6793 |
73
- | 0.742 | 23.0 | 299 | 0.6723 |
74
- | 0.7268 | 24.0 | 312 | 0.6708 |
75
- | 0.7268 | 25.0 | 325 | 0.6694 |
76
- | 0.7258 | 26.0 | 338 | 0.6672 |
77
- | 0.7258 | 27.0 | 351 | 0.6674 |
78
- | 0.7074 | 28.0 | 364 | 0.6673 |
79
- | 0.7074 | 29.0 | 377 | 0.6671 |
80
- | 0.7168 | 30.0 | 390 | 0.6675 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
81
 
82
 
83
  ### 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 None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.2325
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
+ - num_epochs: 60
 
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | No log | 1.0 | 13 | 1.1435 |
51
+ | No log | 2.0 | 26 | 0.9264 |
52
+ | 1.1679 | 3.0 | 39 | 0.8999 |
53
+ | 1.1679 | 4.0 | 52 | 0.7677 |
54
+ | 0.8695 | 5.0 | 65 | 0.6625 |
55
+ | 0.8695 | 6.0 | 78 | 0.6801 |
56
+ | 0.733 | 7.0 | 91 | 0.7046 |
57
+ | 0.733 | 8.0 | 104 | 0.6163 |
58
+ | 0.733 | 9.0 | 117 | 0.4858 |
59
+ | 0.6456 | 10.0 | 130 | 0.6188 |
60
+ | 0.6456 | 11.0 | 143 | 0.4342 |
61
+ | 0.5509 | 12.0 | 156 | 0.4561 |
62
+ | 0.5509 | 13.0 | 169 | 0.4610 |
63
+ | 0.5194 | 14.0 | 182 | 0.4872 |
64
+ | 0.5194 | 15.0 | 195 | 0.3929 |
65
+ | 0.5194 | 16.0 | 208 | 0.3746 |
66
+ | 0.4818 | 17.0 | 221 | 0.4183 |
67
+ | 0.4818 | 18.0 | 234 | 0.3301 |
68
+ | 0.4491 | 19.0 | 247 | 0.3647 |
69
+ | 0.4491 | 20.0 | 260 | 0.3881 |
70
+ | 0.4108 | 21.0 | 273 | 0.3070 |
71
+ | 0.4108 | 22.0 | 286 | 0.3409 |
72
+ | 0.4108 | 23.0 | 299 | 0.3500 |
73
+ | 0.3873 | 24.0 | 312 | 0.3143 |
74
+ | 0.3873 | 25.0 | 325 | 0.3314 |
75
+ | 0.385 | 26.0 | 338 | 0.2909 |
76
+ | 0.385 | 27.0 | 351 | 0.2874 |
77
+ | 0.3735 | 28.0 | 364 | 0.3362 |
78
+ | 0.3735 | 29.0 | 377 | 0.2828 |
79
+ | 0.3794 | 30.0 | 390 | 0.2709 |
80
+ | 0.3794 | 31.0 | 403 | 0.3035 |
81
+ | 0.3794 | 32.0 | 416 | 0.3283 |
82
+ | 0.3591 | 33.0 | 429 | 0.2983 |
83
+ | 0.3591 | 34.0 | 442 | 0.3207 |
84
+ | 0.3412 | 35.0 | 455 | 0.2782 |
85
+ | 0.3412 | 36.0 | 468 | 0.2417 |
86
+ | 0.3264 | 37.0 | 481 | 0.2604 |
87
+ | 0.3264 | 38.0 | 494 | 0.2783 |
88
+ | 0.3264 | 39.0 | 507 | 0.2813 |
89
+ | 0.3106 | 40.0 | 520 | 0.2569 |
90
+ | 0.3106 | 41.0 | 533 | 0.2442 |
91
+ | 0.3 | 42.0 | 546 | 0.2540 |
92
+ | 0.3 | 43.0 | 559 | 0.2532 |
93
+ | 0.2936 | 44.0 | 572 | 0.2696 |
94
+ | 0.2936 | 45.0 | 585 | 0.2516 |
95
+ | 0.2936 | 46.0 | 598 | 0.2359 |
96
+ | 0.283 | 47.0 | 611 | 0.2418 |
97
+ | 0.283 | 48.0 | 624 | 0.2594 |
98
+ | 0.2723 | 49.0 | 637 | 0.2364 |
99
+ | 0.2723 | 50.0 | 650 | 0.2518 |
100
+ | 0.2686 | 51.0 | 663 | 0.2533 |
101
+ | 0.2686 | 52.0 | 676 | 0.2393 |
102
+ | 0.2686 | 53.0 | 689 | 0.2391 |
103
+ | 0.2665 | 54.0 | 702 | 0.2346 |
104
+ | 0.2665 | 55.0 | 715 | 0.2319 |
105
+ | 0.2687 | 56.0 | 728 | 0.2321 |
106
+ | 0.2687 | 57.0 | 741 | 0.2333 |
107
+ | 0.266 | 58.0 | 754 | 0.2333 |
108
+ | 0.266 | 59.0 | 767 | 0.2342 |
109
+ | 0.2719 | 60.0 | 780 | 0.2325 |
110
 
111
 
112
  ### Framework versions