ChingizA commited on
Commit
e3763f6
·
verified ·
1 Parent(s): b96aad3

End of training

Browse files
Files changed (1) hide show
  1. README.md +28 -28
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: 1.9733
19
 
20
  ## Model description
21
 
@@ -47,36 +47,36 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 2.3967 | 0.08 | 200 | 2.5516 |
51
- | 2.3043 | 0.16 | 400 | 2.2766 |
52
- | 2.2959 | 0.24 | 600 | 2.3239 |
53
- | 2.2428 | 0.32 | 800 | 2.1433 |
54
- | 2.2565 | 0.4 | 1000 | 2.1595 |
55
- | 2.1795 | 0.48 | 1200 | 2.1772 |
56
- | 2.1432 | 0.56 | 1400 | 2.1102 |
57
- | 2.226 | 0.64 | 1600 | 2.5041 |
58
- | 2.1588 | 0.72 | 1800 | 2.1281 |
59
- | 2.0289 | 0.8 | 2000 | 2.0285 |
60
- | 2.0329 | 0.88 | 2200 | 2.2104 |
61
- | 2.0465 | 0.96 | 2400 | 2.0112 |
62
- | 1.9734 | 1.04 | 2600 | 2.0137 |
63
- | 1.9412 | 1.12 | 2800 | 2.1651 |
64
- | 2.015 | 1.2 | 3000 | 2.0066 |
65
- | 1.9244 | 1.28 | 3200 | 1.9237 |
66
- | 1.9236 | 1.36 | 3400 | 2.0830 |
67
- | 1.9466 | 1.44 | 3600 | 2.0800 |
68
- | 1.8694 | 1.52 | 3800 | 1.9643 |
69
- | 1.9207 | 1.6 | 4000 | 2.0302 |
70
- | 1.9522 | 1.68 | 4200 | 2.1183 |
71
- | 1.9719 | 1.76 | 4400 | 2.0455 |
72
- | 1.8371 | 1.84 | 4600 | 1.9370 |
73
- | 1.8939 | 1.92 | 4800 | 1.9784 |
74
- | 1.8951 | 2.0 | 5000 | 1.9733 |
75
 
76
 
77
  ### Framework versions
78
 
79
- - Transformers 4.38.2
80
- - Pytorch 2.2.1+cu121
81
  - Datasets 2.18.0
82
  - Tokenizers 0.15.2
 
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: 0.8513
19
 
20
  ## Model description
21
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 2.235 | 0.08 | 200 | 2.0882 |
51
+ | 2.0278 | 0.16 | 400 | 2.0542 |
52
+ | 1.7003 | 0.24 | 600 | 1.6411 |
53
+ | 1.7188 | 0.32 | 800 | 1.6111 |
54
+ | 1.4488 | 0.4 | 1000 | 1.3552 |
55
+ | 1.4492 | 0.48 | 1200 | 1.4768 |
56
+ | 1.3457 | 0.56 | 1400 | 1.3206 |
57
+ | 1.3914 | 0.64 | 1600 | 1.3176 |
58
+ | 1.2392 | 0.72 | 1800 | 1.1918 |
59
+ | 1.1335 | 0.8 | 2000 | 1.1535 |
60
+ | 1.1321 | 0.88 | 2200 | 1.1134 |
61
+ | 1.1088 | 0.96 | 2400 | 1.0808 |
62
+ | 1.0792 | 1.04 | 2600 | 1.0290 |
63
+ | 1.0801 | 1.12 | 2800 | 1.0240 |
64
+ | 0.9925 | 1.2 | 3000 | 0.9858 |
65
+ | 1.001 | 1.28 | 3200 | 0.9476 |
66
+ | 0.9654 | 1.36 | 3400 | 0.9389 |
67
+ | 0.9802 | 1.44 | 3600 | 0.9158 |
68
+ | 0.947 | 1.52 | 3800 | 0.9130 |
69
+ | 0.9489 | 1.6 | 4000 | 0.9004 |
70
+ | 0.8446 | 1.68 | 4200 | 0.8881 |
71
+ | 0.8854 | 1.76 | 4400 | 0.8774 |
72
+ | 0.9502 | 1.84 | 4600 | 0.8606 |
73
+ | 0.8816 | 1.92 | 4800 | 0.8616 |
74
+ | 0.8936 | 2.0 | 5000 | 0.8513 |
75
 
76
 
77
  ### Framework versions
78
 
79
+ - Transformers 4.39.3
80
+ - Pytorch 2.1.2
81
  - Datasets 2.18.0
82
  - Tokenizers 0.15.2