Hugging Face's logo

distill-io
/
detr-amzss3-v2

Object Detection
Transformers
PyTorch
detr
Generated from Trainer
Inference Endpoints
Model card Files Community
pallavJha commited on
Commit
3abbb02
·
1 Parent(s): c7f9b21

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +102 -0
README.md ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-amzss3-v2
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-amzss3-v2
15
+
16
+ This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.5846
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: 1e-05
38
+ - train_batch_size: 8
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: 25
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:-----:|:---------------:|
49
+ | No log | 0.54 | 1000 | 2.5308 |
50
+ | 2.824 | 1.08 | 2000 | 2.0484 |
51
+ | 2.824 | 1.62 | 3000 | 1.7408 |
52
+ | 1.8911 | 2.16 | 4000 | 1.5862 |
53
+ | 1.8911 | 2.7 | 5000 | 1.4858 |
54
+ | 1.594 | 3.24 | 6000 | 1.3551 |
55
+ | 1.594 | 3.78 | 7000 | 1.2802 |
56
+ | 1.4147 | 4.32 | 8000 | 1.2439 |
57
+ | 1.4147 | 4.86 | 9000 | 1.1548 |
58
+ | 1.2978 | 5.4 | 10000 | 1.1031 |
59
+ | 1.2978 | 5.94 | 11000 | 1.0674 |
60
+ | 1.1984 | 6.48 | 12000 | 1.0380 |
61
+ | 1.1086 | 7.02 | 13000 | 0.9949 |
62
+ | 1.1086 | 7.56 | 14000 | 0.9393 |
63
+ | 1.0383 | 8.1 | 15000 | 0.9204 |
64
+ | 1.0383 | 8.64 | 16000 | 0.8921 |
65
+ | 0.9817 | 9.18 | 17000 | 0.8670 |
66
+ | 0.9817 | 9.72 | 18000 | 0.8250 |
67
+ | 0.9277 | 10.26 | 19000 | 0.8084 |
68
+ | 0.9277 | 10.8 | 20000 | 0.7968 |
69
+ | 0.8864 | 11.34 | 21000 | 0.7928 |
70
+ | 0.8864 | 11.88 | 22000 | 0.7605 |
71
+ | 0.8525 | 12.42 | 23000 | 0.7602 |
72
+ | 0.8525 | 12.96 | 24000 | 0.7406 |
73
+ | 0.8197 | 13.5 | 25000 | 0.7224 |
74
+ | 0.7975 | 14.04 | 26000 | 0.7060 |
75
+ | 0.7975 | 14.58 | 27000 | 0.6893 |
76
+ | 0.7733 | 15.12 | 28000 | 0.6940 |
77
+ | 0.7733 | 15.66 | 29000 | 0.6836 |
78
+ | 0.7534 | 16.2 | 30000 | 0.6620 |
79
+ | 0.7534 | 16.74 | 31000 | 0.6584 |
80
+ | 0.7376 | 17.28 | 32000 | 0.6552 |
81
+ | 0.7376 | 17.82 | 33000 | 0.6487 |
82
+ | 0.7242 | 18.36 | 34000 | 0.6334 |
83
+ | 0.7242 | 18.9 | 35000 | 0.6319 |
84
+ | 0.7052 | 19.44 | 36000 | 0.6223 |
85
+ | 0.7052 | 19.98 | 37000 | 0.6155 |
86
+ | 0.6935 | 20.52 | 38000 | 0.6092 |
87
+ | 0.6816 | 21.06 | 39000 | 0.6079 |
88
+ | 0.6816 | 21.6 | 40000 | 0.6045 |
89
+ | 0.6747 | 22.14 | 41000 | 0.5997 |
90
+ | 0.6747 | 22.68 | 42000 | 0.6002 |
91
+ | 0.6693 | 23.22 | 43000 | 0.5924 |
92
+ | 0.6693 | 23.76 | 44000 | 0.5922 |
93
+ | 0.6608 | 24.3 | 45000 | 0.5861 |
94
+ | 0.6608 | 24.84 | 46000 | 0.5846 |
95
+
96
+
97
+ ### Framework versions
98
+
99
+ - Transformers 4.31.0
100
+ - Pytorch 2.0.1+cu118
101
+ - Datasets 2.13.1
102
+ - Tokenizers 0.13.3