Hugging Face's logo

Injardav
/
detr

Object Detection
Transformers
TensorBoard
Safetensors
detr
Generated from Trainer
Model card Files
xet
Metrics Community
Injardav commited on
Commit
1839193
·
verified ·
1 Parent(s): 6348fad

End of training

Browse files
Files changed (1) hide show
  1. README.md +107 -0
README.md ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/detr-resnet-50
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: detr
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # detr
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: 1.0196
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 1
44
+ - mixed_precision_training: Native AMP
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:----:|:---------------:|
50
+ | 3.8584 | 0.02 | 50 | 3.3010 |
51
+ | 2.7538 | 0.04 | 100 | 2.5486 |
52
+ | 2.2986 | 0.06 | 150 | 2.2761 |
53
+ | 2.0637 | 0.08 | 200 | 2.0595 |
54
+ | 1.9565 | 0.1 | 250 | 1.9289 |
55
+ | 1.9208 | 0.12 | 300 | 1.9521 |
56
+ | 1.9024 | 0.14 | 350 | 1.8841 |
57
+ | 1.8294 | 0.16 | 400 | 1.7362 |
58
+ | 1.7064 | 0.18 | 450 | 1.6461 |
59
+ | 1.6336 | 0.2 | 500 | 1.5706 |
60
+ | 1.5009 | 0.22 | 550 | 1.5610 |
61
+ | 1.639 | 0.24 | 600 | 1.5916 |
62
+ | 1.4837 | 0.26 | 650 | 1.4572 |
63
+ | 1.4384 | 0.28 | 700 | 1.4170 |
64
+ | 1.4366 | 0.3 | 750 | 1.4112 |
65
+ | 1.4204 | 0.32 | 800 | 1.3324 |
66
+ | 1.2496 | 0.34 | 850 | 1.2658 |
67
+ | 1.313 | 0.36 | 900 | 1.2854 |
68
+ | 1.2573 | 0.38 | 950 | 1.2485 |
69
+ | 1.2961 | 0.4 | 1000 | 1.2550 |
70
+ | 1.2419 | 0.42 | 1050 | 1.2334 |
71
+ | 1.2132 | 0.44 | 1100 | 1.2097 |
72
+ | 1.237 | 0.46 | 1150 | 1.1870 |
73
+ | 1.2395 | 0.48 | 1200 | 1.2277 |
74
+ | 1.2789 | 0.5 | 1250 | 1.2159 |
75
+ | 1.2264 | 0.52 | 1300 | 1.1848 |
76
+ | 1.2875 | 0.54 | 1350 | 1.1683 |
77
+ | 1.1939 | 0.56 | 1400 | 1.1437 |
78
+ | 1.1407 | 0.58 | 1450 | 1.1325 |
79
+ | 1.1727 | 0.6 | 1500 | 1.1204 |
80
+ | 1.1618 | 0.62 | 1550 | 1.1065 |
81
+ | 1.1374 | 0.64 | 1600 | 1.0942 |
82
+ | 1.1241 | 0.66 | 1650 | 1.0965 |
83
+ | 1.0826 | 0.68 | 1700 | 1.0910 |
84
+ | 1.1185 | 0.7 | 1750 | 1.0853 |
85
+ | 1.1238 | 0.72 | 1800 | 1.0656 |
86
+ | 1.1146 | 0.74 | 1850 | 1.0486 |
87
+ | 1.1339 | 0.76 | 1900 | 1.0652 |
88
+ | 1.0464 | 0.78 | 1950 | 1.0542 |
89
+ | 1.0563 | 0.8 | 2000 | 1.0534 |
90
+ | 1.0896 | 0.82 | 2050 | 1.0510 |
91
+ | 1.0753 | 0.84 | 2100 | 1.0300 |
92
+ | 1.0979 | 0.86 | 2150 | 1.0408 |
93
+ | 1.0831 | 0.88 | 2200 | 1.0328 |
94
+ | 1.0936 | 0.9 | 2250 | 1.0215 |
95
+ | 1.1161 | 0.92 | 2300 | 1.0238 |
96
+ | 1.0251 | 0.94 | 2350 | 1.0109 |
97
+ | 1.0676 | 0.96 | 2400 | 1.0147 |
98
+ | 1.0461 | 0.98 | 2450 | 1.0109 |
99
+ | 1.0386 | 1.0 | 2500 | 1.0196 |
100
+
101
+
102
+ ### Framework versions
103
+
104
+ - Transformers 4.39.3
105
+ - Pytorch 2.2.1+cu121
106
+ - Datasets 2.18.0
107
+ - Tokenizers 0.15.2