Hugging Face's logo

mrdbourke
/
detr_finetuned_trashify_box_detector_with_data_aug

Object Detection
Transformers
Safetensors
conditional_detr
Generated from Trainer
Inference Endpoints
Model card Files Community
mrdbourke commited on
Commit
03d2ead
•
1 Parent(s): 8b7b946

upload trashify object detection model with data augmentation

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: 1.0749
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
- | 36.0329 | 1.0 | 50 | 3.4510 |
52
- | 2.8564 | 2.0 | 100 | 2.2827 |
53
- | 2.3323 | 3.0 | 150 | 2.1028 |
54
- | 2.1202 | 4.0 | 200 | 1.8915 |
55
- | 1.9452 | 5.0 | 250 | 1.6696 |
56
- | 1.7582 | 6.0 | 300 | 1.5181 |
57
- | 1.6291 | 7.0 | 350 | 1.4310 |
58
- | 1.5394 | 8.0 | 400 | 1.3669 |
59
- | 1.4751 | 9.0 | 450 | 1.3164 |
60
- | 1.3906 | 10.0 | 500 | 1.2860 |
61
- | 1.394 | 11.0 | 550 | 1.2915 |
62
- | 1.338 | 12.0 | 600 | 1.2461 |
63
- | 1.3071 | 13.0 | 650 | 1.2300 |
64
- | 1.2772 | 14.0 | 700 | 1.2059 |
65
- | 1.2363 | 15.0 | 750 | 1.1639 |
66
- | 1.2213 | 16.0 | 800 | 1.1547 |
67
- | 1.1372 | 17.0 | 850 | 1.1213 |
68
- | 1.1423 | 18.0 | 900 | 1.1322 |
69
- | 1.0991 | 19.0 | 950 | 1.1069 |
70
- | 1.1041 | 20.0 | 1000 | 1.1001 |
71
- | 1.0921 | 21.0 | 1050 | 1.0869 |
72
- | 1.063 | 22.0 | 1100 | 1.0760 |
73
- | 1.0561 | 23.0 | 1150 | 1.0775 |
74
- | 1.0373 | 24.0 | 1200 | 1.0799 |
75
- | 1.0325 | 25.0 | 1250 | 1.0749 |
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: 1.0325
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
+ | 88.5164 | 1.0 | 50 | 7.1501 |
53
+ | 3.8056 | 2.0 | 100 | 2.5905 |
54
+ | 2.4603 | 3.0 | 150 | 2.1159 |
55
+ | 2.1947 | 4.0 | 200 | 1.9162 |
56
+ | 1.9644 | 5.0 | 250 | 1.6812 |
57
+ | 1.7886 | 6.0 | 300 | 1.5471 |
58
+ | 1.6914 | 7.0 | 350 | 1.4803 |
59
+ | 1.5788 | 8.0 | 400 | 1.3945 |
60
+ | 1.53 | 9.0 | 450 | 1.2992 |
61
+ | 1.4044 | 10.0 | 500 | 1.2839 |
62
+ | 1.4037 | 11.0 | 550 | 1.2180 |
63
+ | 1.3311 | 12.0 | 600 | 1.1833 |
64
+ | 1.3008 | 13.0 | 650 | 1.1693 |
65
+ | 1.2501 | 14.0 | 700 | 1.1408 |
66
+ | 1.2194 | 15.0 | 750 | 1.1292 |
67
+ | 1.2088 | 16.0 | 800 | 1.1160 |
68
+ | 1.1337 | 17.0 | 850 | 1.1234 |
69
+ | 1.1451 | 18.0 | 900 | 1.0815 |
70
+ | 1.0759 | 19.0 | 950 | 1.0609 |
71
+ | 1.0866 | 20.0 | 1000 | 1.0670 |
72
+ | 1.0732 | 21.0 | 1050 | 1.0553 |
73
+ | 1.0442 | 22.0 | 1100 | 1.0460 |
74
+ | 1.0339 | 23.0 | 1150 | 1.0389 |
75
+ | 1.0185 | 24.0 | 1200 | 1.0337 |
76
+ | 1.0179 | 25.0 | 1250 | 1.0325 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe0684c55e44bd02e61048c6a12912d159e5370547f518c354fcae901301532e
3
  size 174081852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a53c6d697ecca739eae45e43cf03e270a43ed5c36e2e6ef2068d1ebc7df90be
3
  size 174081852
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f66c68bea1d5455cab041a87da03b15d66801c6130700b0c1ebd0179639024df
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ca1a18b7409cd78f599b23cbe3dd7b331101da59eb65760719249d490dfc6d4
3
  size 5240