Hugging Face's logo

mcity-data-engine
/
fisheye8k_hustvl_yolos-base

Object Detection
Transformers
PyTorch
TensorBoard
yolos
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Daniel Bogdoll commited on
Commit
c3d4788
·
verified ·
1 Parent(s): ae5592c

End of training

Browse files
Files changed (2) hide show
  1. README.md +11 -17
  2. runs/Feb15_20-32-10_mcity-rtx-4090/events.out.tfevents.1739669530.mcity-rtx-4090.1139582.23 +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 [hustvl/yolos-base](https://huggingface.co/hustvl/yolos-base) on the generator dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 2.4259
22
 
23
  ## Model description
24
 
@@ -38,32 +38,26 @@ 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
- | 1.869 | 1.0 | 2644 | 2.4719 |
54
- | 1.7653 | 2.0 | 5288 | 2.4479 |
55
- | 1.6713 | 3.0 | 7932 | 2.4587 |
56
- | 1.6485 | 4.0 | 10576 | 2.4582 |
57
- | 1.5246 | 5.0 | 13220 | 2.3657 |
58
- | 1.6017 | 6.0 | 15864 | 2.5125 |
59
- | 1.4199 | 7.0 | 18508 | 2.5242 |
60
- | 1.5472 | 8.0 | 21152 | 2.5324 |
61
- | 1.4067 | 9.0 | 23796 | 2.2619 |
62
- | 1.3167 | 10.0 | 26440 | 2.2793 |
63
- | 1.1909 | 11.0 | 29084 | 2.4237 |
64
- | 1.1875 | 12.0 | 31728 | 2.3808 |
65
- | 1.2329 | 13.0 | 34372 | 2.3562 |
66
- | 1.1447 | 14.0 | 37016 | 2.4259 |
67
 
68
 
69
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [hustvl/yolos-base](https://huggingface.co/hustvl/yolos-base) on the generator dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 2.6653
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
+ | 1.9357 | 1.0 | 5288 | 2.7182 |
54
+ | 1.8095 | 2.0 | 10576 | 2.6559 |
55
+ | 1.6565 | 3.0 | 15864 | 2.5114 |
56
+ | 1.5912 | 4.0 | 21152 | 2.6875 |
57
+ | 1.6169 | 5.0 | 26440 | 2.7796 |
58
+ | 1.5075 | 6.0 | 31728 | 2.6514 |
59
+ | 1.4073 | 7.0 | 37016 | 2.7649 |
60
+ | 1.3617 | 8.0 | 42304 | 2.6653 |
 
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
runs/Feb15_20-32-10_mcity-rtx-4090/events.out.tfevents.1739669530.mcity-rtx-4090.1139582.23 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0affe90db5837f6ff4a11124fb5d8689880acc27bfff46b25ca9cfae6c654022
3
- size 12899
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a8beaf4ad90192ee22ea2e030e0fd3e19a3e9c5d151be8821d73b6e0b8b08b4
3
+ size 26030