Hugging Face's logo

salmu
/
output

Object Detection
Transformers
Safetensors
detr
Generated from Trainer
Model card Files Community
salmu commited on
Commit
743cb0d
·
verified ·
1 Parent(s): 0d09af6

End of training

Browse files
Files changed (3) hide show
  1. README.md +38 -28
  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 [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 6.3818
20
 
21
  ## Model description
22
 
@@ -35,40 +35,50 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.001
39
- - train_batch_size: 8
40
- - eval_batch_size: 8
41
  - seed: 42
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: cosine
44
- - lr_scheduler_warmup_steps: 200
45
- - num_epochs: 20
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss |
51
- |:-------------:|:-----:|:-----:|:---------------:|
52
- | 3.9549 | 1.0 | 500 | 8.6487 |
53
- | 3.7386 | 2.0 | 1000 | 6.6653 |
54
- | 3.2303 | 3.0 | 1500 | 6.5420 |
55
- | 3.0704 | 4.0 | 2000 | 6.6156 |
56
- | 3.0275 | 5.0 | 2500 | 6.9053 |
57
- | 3.0644 | 6.0 | 3000 | 6.4292 |
58
- | 2.9575 | 7.0 | 3500 | 6.4167 |
59
- | 3.0707 | 8.0 | 4000 | 7.0283 |
60
- | 2.8764 | 9.0 | 4500 | 6.4162 |
61
- | 2.9142 | 10.0 | 5000 | 6.7128 |
62
- | 2.8474 | 11.0 | 5500 | 6.7765 |
63
- | 2.9095 | 12.0 | 6000 | 6.6026 |
64
- | 2.8555 | 13.0 | 6500 | 6.6679 |
65
- | 2.8619 | 14.0 | 7000 | 6.6986 |
66
- | 2.8407 | 15.0 | 7500 | 6.6944 |
67
- | 2.8214 | 16.0 | 8000 | 6.6572 |
68
- | 2.8244 | 17.0 | 8500 | 6.6596 |
69
- | 2.8092 | 18.0 | 9000 | 6.6372 |
70
- | 2.8896 | 19.0 | 9500 | 6.6237 |
71
- | 2.8422 | 20.0 | 10000 | 6.6249 |
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.9020
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 16
40
+ - eval_batch_size: 16
41
  - seed: 42
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: cosine
44
+ - lr_scheduler_warmup_steps: 375
45
+ - num_epochs: 30
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 1.8809 | 1.0 | 250 | 1.6853 |
53
+ | 1.4938 | 2.0 | 500 | 1.3327 |
54
+ | 1.3403 | 3.0 | 750 | 1.2940 |
55
+ | 1.3485 | 4.0 | 1000 | 1.2512 |
56
+ | 1.2645 | 5.0 | 1250 | 1.2189 |
57
+ | 1.2061 | 6.0 | 1500 | 1.1517 |
58
+ | 1.1632 | 7.0 | 1750 | 1.1042 |
59
+ | 1.179 | 8.0 | 2000 | 1.0796 |
60
+ | 1.1558 | 9.0 | 2250 | 1.0567 |
61
+ | 1.1294 | 10.0 | 2500 | 1.0661 |
62
+ | 1.0644 | 11.0 | 2750 | 1.0214 |
63
+ | 1.0545 | 12.0 | 3000 | 1.0508 |
64
+ | 1.0455 | 13.0 | 3250 | 0.9904 |
65
+ | 1.0242 | 14.0 | 3500 | 0.9863 |
66
+ | 1.0021 | 15.0 | 3750 | 0.9897 |
67
+ | 0.9947 | 16.0 | 4000 | 0.9774 |
68
+ | 0.9456 | 17.0 | 4250 | 0.9485 |
69
+ | 0.9339 | 18.0 | 4500 | 0.9553 |
70
+ | 0.9481 | 19.0 | 4750 | 0.9431 |
71
+ | 0.8992 | 20.0 | 5000 | 0.9348 |
72
+ | 0.8792 | 21.0 | 5250 | 0.9265 |
73
+ | 0.8946 | 22.0 | 5500 | 0.9271 |
74
+ | 0.8913 | 23.0 | 5750 | 0.9249 |
75
+ | 0.8813 | 24.0 | 6000 | 0.9072 |
76
+ | 0.885 | 25.0 | 6250 | 0.9115 |
77
+ | 0.8477 | 26.0 | 6500 | 0.9091 |
78
+ | 0.8792 | 27.0 | 6750 | 0.9045 |
79
+ | 0.8816 | 28.0 | 7000 | 0.9034 |
80
+ | 0.8633 | 29.0 | 7250 | 0.9005 |
81
+ | 0.8921 | 30.0 | 7500 | 0.9102 |
82
 
83
 
84
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a99e93e280570147d6fd73e076c4ce9d842de2ebe797639287a07966b2ebab1d
3
  size 166506812
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcae5dab708ea3d5427d71b346ebc33e03c1ef8eb095a37afe0beb3a8880d8db
3
  size 166506812
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bf0ac20604c79c87894c1c0c46b5a7c70ffe0a05a74ed7b5ffeb17108a284ac
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a71ca2f1ee7c3cc899a4be580fd764fae8e5cf69aee631cdd96d0874ae166d83
3
  size 5304