Hugging Face's logo

mcity-data-engine
/
fisheye8k_SenseTime_deformable-detr

Object Detection
Transformers
PyTorch
TensorBoard
deformable_detr
Generated from Trainer
Model card Files Metrics Community
1
Daniel Bogdoll commited on
Commit
6c5379d
·
verified ·
1 Parent(s): e0f02a8

End of training

Browse files
Files changed (2) hide show
  1. README.md +12 -18
  2. runs/Feb15_04-53-41_mcity-rtx-4090/events.out.tfevents.1739613221.mcity-rtx-4090.1139582.13 +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 [SenseTime/deformable-detr](https://huggingface.co/SenseTime/deformable-detr) on the generator dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.2359
22
 
23
  ## Model description
24
 
@@ -38,33 +38,27 @@ 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
- | 0.8578 | 1.0 | 5288 | 1.4569 |
54
- | 0.7252 | 2.0 | 10576 | 1.2005 |
55
- | 0.6929 | 3.0 | 15864 | 1.1937 |
56
- | 0.6535 | 4.0 | 21152 | 1.2539 |
57
- | 0.6191 | 5.0 | 26440 | 1.2350 |
58
- | 0.5987 | 6.0 | 31728 | 1.2300 |
59
- | 0.5677 | 7.0 | 37016 | 1.1897 |
60
- | 0.558 | 8.0 | 42304 | 1.2451 |
61
- | 0.5338 | 9.0 | 47592 | 1.1865 |
62
- | 0.5054 | 10.0 | 52880 | 1.1585 |
63
- | 0.4795 | 11.0 | 58168 | 1.2366 |
64
- | 0.4809 | 12.0 | 63456 | 1.2193 |
65
- | 0.4825 | 13.0 | 68744 | 1.2375 |
66
- | 0.4535 | 14.0 | 74032 | 1.2542 |
67
- | 0.4357 | 15.0 | 79320 | 1.2359 |
68
 
69
 
70
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [SenseTime/deformable-detr](https://huggingface.co/SenseTime/deformable-detr) on the generator dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.2335
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
+ | 0.8943 | 1.0 | 5288 | 1.5330 |
54
+ | 0.7865 | 2.0 | 10576 | 1.4108 |
55
+ | 0.7238 | 3.0 | 15864 | 1.2660 |
56
+ | 0.6657 | 4.0 | 21152 | 1.2084 |
57
+ | 0.646 | 5.0 | 26440 | 1.2666 |
58
+ | 0.6269 | 6.0 | 31728 | 1.2555 |
59
+ | 0.6049 | 7.0 | 37016 | 1.2350 |
60
+ | 0.5894 | 8.0 | 42304 | 1.2940 |
61
+ | 0.5484 | 9.0 | 47592 | 1.2335 |
 
 
 
 
 
 
62
 
63
 
64
  ### Framework versions
runs/Feb15_04-53-41_mcity-rtx-4090/events.out.tfevents.1739613221.mcity-rtx-4090.1139582.13 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:451b2dda3986fb116db49ff9ce87622c75e352d7b1f4fc3956b3f62c151ecc90
3
- size 16221
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93de94cc75d18269d165cd9faf7c20ffd5808e146a29556ad9ad2e22ca94fbe6
3
+ size 29356