Hugging Face's logo

mrdbourke
/
detr_finetuned_trashify_box_detector

Object Detection
Transformers
Safetensors
conditional_detr
Generated from Trainer
Inference Endpoints
Model card Files Community
mrdbourke commited on
Commit
ab273ce
•
1 Parent(s): 7913fe9

upload trashify object detection model

Browse files
Files changed (3) hide show
  1. README.md +27 -26
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
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 [microsoft/conditional-detr-resnet-50](https://huggingface.co/microsoft/conditional-detr-resnet-50) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.1024
20
 
21
  ## Model description
22
 
@@ -41,6 +41,7 @@ The following hyperparameters were used during training:
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
 
44
  - num_epochs: 25
45
  - mixed_precision_training: Native AMP
46
 
@@ -48,31 +49,31 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 47.984 | 1.0 | 50 | 3.3624 |
52
- | 2.7348 | 2.0 | 100 | 2.3693 |
53
- | 2.2463 | 3.0 | 150 | 1.9785 |
54
- | 2.1473 | 4.0 | 200 | 1.9305 |
55
- | 1.9375 | 5.0 | 250 | 1.7268 |
56
- | 1.7557 | 6.0 | 300 | 1.5692 |
57
- | 1.6032 | 7.0 | 350 | 1.4597 |
58
- | 1.5135 | 8.0 | 400 | 1.3900 |
59
- | 1.4173 | 9.0 | 450 | 1.3377 |
60
- | 1.3089 | 10.0 | 500 | 1.2696 |
61
- | 1.2517 | 11.0 | 550 | 1.2276 |
62
- | 1.1837 | 12.0 | 600 | 1.2114 |
63
- | 1.136 | 13.0 | 650 | 1.1715 |
64
- | 1.0892 | 14.0 | 700 | 1.1834 |
65
- | 1.046 | 15.0 | 750 | 1.1676 |
66
- | 0.986 | 16.0 | 800 | 1.1197 |
67
- | 0.912 | 17.0 | 850 | 1.1203 |
68
- | 0.8765 | 18.0 | 900 | 1.1224 |
69
- | 0.836 | 19.0 | 950 | 1.0934 |
70
- | 0.8173 | 20.0 | 1000 | 1.1082 |
71
- | 0.7742 | 21.0 | 1050 | 1.0997 |
72
- | 0.7471 | 22.0 | 1100 | 1.0991 |
73
- | 0.7351 | 23.0 | 1150 | 1.1083 |
74
- | 0.7151 | 24.0 | 1200 | 1.0987 |
75
- | 0.7052 | 25.0 | 1250 | 1.1024 |
76
 
77
 
78
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [microsoft/conditional-detr-resnet-50](https://huggingface.co/microsoft/conditional-detr-resnet-50) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.1302
20
 
21
  ## Model description
22
 
 
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_ratio: 0.05
45
  - num_epochs: 25
46
  - mixed_precision_training: Native AMP
47
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | 101.8783 | 1.0 | 50 | 7.5132 |
53
+ | 4.1455 | 2.0 | 100 | 3.0556 |
54
+ | 2.5964 | 3.0 | 150 | 2.2737 |
55
+ | 2.2773 | 4.0 | 200 | 2.0691 |
56
+ | 2.0818 | 5.0 | 250 | 1.8494 |
57
+ | 1.9253 | 6.0 | 300 | 1.6872 |
58
+ | 1.7802 | 7.0 | 350 | 1.6033 |
59
+ | 1.675 | 8.0 | 400 | 1.4511 |
60
+ | 1.5263 | 9.0 | 450 | 1.4097 |
61
+ | 1.4322 | 10.0 | 500 | 1.3397 |
62
+ | 1.386 | 11.0 | 550 | 1.2897 |
63
+ | 1.3098 | 12.0 | 600 | 1.2813 |
64
+ | 1.248 | 13.0 | 650 | 1.2096 |
65
+ | 1.209 | 14.0 | 700 | 1.2200 |
66
+ | 1.1757 | 15.0 | 750 | 1.1987 |
67
+ | 1.144 | 16.0 | 800 | 1.1757 |
68
+ | 1.0732 | 17.0 | 850 | 1.1935 |
69
+ | 1.0501 | 18.0 | 900 | 1.1531 |
70
+ | 0.9864 | 19.0 | 950 | 1.1576 |
71
+ | 0.9941 | 20.0 | 1000 | 1.1513 |
72
+ | 0.9589 | 21.0 | 1050 | 1.1450 |
73
+ | 0.9279 | 22.0 | 1100 | 1.1355 |
74
+ | 0.9071 | 23.0 | 1150 | 1.1233 |
75
+ | 0.8851 | 24.0 | 1200 | 1.1338 |
76
+ | 0.8709 | 25.0 | 1250 | 1.1302 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b4234f8bddb6b3aa5a9fc5e8667b9883bb3955d0c50f06a57c7063fb639e7d0
3
  size 174081852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dfea14c4904d7f941a9f08b43e18bd8ac3346c526ac36ba012ab191bd2d06ff
3
  size 174081852
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff66dec1f16d86504daf9ec3819bf3beda20cd5534543cdb6bb247a59a4090ae
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd08c3f5c4928f5d84d7e17c6522b545e5cbf5e0fd759853eb1d0cf6d3d2bbe2
3
  size 5240