Hugging Face's logo

mcity-data-engine
/
fisheye8k_facebook_deformable-detr-detic

Zero-Shot Object Detection
Transformers
PyTorch
TensorBoard
deformable_detr
object-detection
Generated from Trainer
zero-shot
Model card Files
xet
Metrics Community
4
Daniel Bogdoll commited on
Commit
b2bdc9c
·
verified ·
1 Parent(s): 2de8952

End of training

Browse files
Files changed (2) hide show
  1. README.md +19 -16
  2. runs/Feb13_02-17-37_mcity-rtx-4090/events.out.tfevents.1739431058.mcity-rtx-4090.11129.20 +2 -2
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [facebook/deformable-detr-detic](https://huggingface.co/facebook/deformable-detr-detic) on the generator dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 3.1187
22
 
23
  ## Model description
24
 
@@ -38,31 +38,34 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
- - train_batch_size: 32
42
  - eval_batch_size: 8
43
  - seed: 0
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: cosine
46
- - num_epochs: 30
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:-----:|:---------------:|
53
- | 2.8068 | 1.0 | 5288 | 3.0866 |
54
- | 2.5985 | 2.0 | 10576 | 2.7970 |
55
- | 2.368 | 3.0 | 15864 | 2.5671 |
56
- | 2.531 | 4.0 | 21152 | 3.0914 |
57
- | 2.2468 | 5.0 | 26440 | 2.8550 |
58
- | 2.3968 | 6.0 | 31728 | 3.0002 |
59
- | 2.2204 | 7.0 | 37016 | 2.4807 |
60
- | 2.0661 | 8.0 | 42304 | 2.4539 |
61
- | 2.2947 | 9.0 | 47592 | 2.7481 |
62
- | 2.3046 | 10.0 | 52880 | 2.9592 |
63
- | 2.5026 | 11.0 | 58168 | 2.9560 |
64
- | 2.4076 | 12.0 | 63456 | 2.9273 |
65
- | 2.4247 | 13.0 | 68744 | 3.1187 |
 
 
 
66
 
67
 
68
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [facebook/deformable-detr-detic](https://huggingface.co/facebook/deformable-detr-detic) on the generator dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 3.2039
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
+ - train_batch_size: 1
42
  - eval_batch_size: 8
43
  - seed: 0
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: cosine
46
+ - num_epochs: 36
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:-----:|:---------------:|
53
+ | 3.0392 | 1.0 | 5288 | 3.5259 |
54
+ | 3.0592 | 2.0 | 10576 | 3.4599 |
55
+ | 3.1633 | 3.0 | 15864 | 3.5487 |
56
+ | 3.1245 | 4.0 | 21152 | 3.5904 |
57
+ | 3.0262 | 5.0 | 26440 | 3.2672 |
58
+ | 2.7331 | 6.0 | 31728 | 3.1167 |
59
+ | 2.9657 | 7.0 | 37016 | 3.4212 |
60
+ | 2.8438 | 8.0 | 42304 | 3.2879 |
61
+ | 2.7125 | 9.0 | 47592 | 3.0869 |
62
+ | 2.6851 | 10.0 | 52880 | 3.2923 |
63
+ | 2.5917 | 11.0 | 58168 | 3.0151 |
64
+ | 2.8082 | 12.0 | 63456 | 3.1771 |
65
+ | 2.6767 | 13.0 | 68744 | 3.2470 |
66
+ | 2.5765 | 14.0 | 74032 | 3.0629 |
67
+ | 2.6197 | 15.0 | 79320 | 3.1206 |
68
+ | 2.4499 | 16.0 | 84608 | 3.2039 |
69
 
70
 
71
  ### Framework versions
runs/Feb13_02-17-37_mcity-rtx-4090/events.out.tfevents.1739431058.mcity-rtx-4090.11129.20 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df0d823ad3cdbd79e9d1497e034aaaeb64db920969a175d3e33380588a798ccc
3
- size 36239
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e33d8f3cd9bb3bfeb18d59561e4863e6e7d3809a8e106604c1d521f40bb41651
3
+ size 49374