Hugging Face's logo

Augusto777
/
swinv2-tiny-patch4-window8-256-DMAE-ex

TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results
Model card Files Metrics Community
Augusto777 commited on
Commit
b7284ed
·
verified ·
1 Parent(s): 6be06f3

Model save

Browse files
Files changed (3) hide show
  1. README.md +40 -29
  2. model.safetensors +1 -1
  3. runs/Dec02_15-11-10_DESKTOP-SKBE9FB/events.out.tfevents.1733173871.DESKTOP-SKBE9FB.10128.0 +2 -2
README.md CHANGED
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.3825
36
  - Accuracy: 0.4565
37
 
38
  ## Model description
@@ -52,44 +52,55 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 4e-05
56
- - train_batch_size: 32
57
- - eval_batch_size: 32
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
- - total_train_batch_size: 128
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
- - lr_scheduler_warmup_ratio: 0.1
64
  - num_epochs: 40
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 0.57 | 1 | 1.3863 | 0.1087 |
71
- | No log | 1.71 | 3 | 1.3825 | 0.4565 |
72
- | No log | 2.86 | 5 | 1.3677 | 0.4565 |
73
- | No log | 4.0 | 7 | 1.3405 | 0.4565 |
74
- | No log | 4.57 | 8 | 1.3229 | 0.4565 |
75
- | 1.3605 | 5.71 | 10 | 1.2859 | 0.4565 |
76
- | 1.3605 | 6.86 | 12 | 1.2580 | 0.4565 |
77
- | 1.3605 | 8.0 | 14 | 1.2332 | 0.4565 |
78
- | 1.3605 | 8.57 | 15 | 1.2239 | 0.4565 |
79
- | 1.3605 | 9.71 | 17 | 1.2128 | 0.4565 |
80
- | 1.3605 | 10.86 | 19 | 1.2086 | 0.4565 |
81
- | 1.2105 | 12.0 | 21 | 1.2092 | 0.4565 |
82
- | 1.2105 | 12.57 | 22 | 1.2098 | 0.4565 |
83
- | 1.2105 | 13.71 | 24 | 1.2100 | 0.4565 |
84
- | 1.2105 | 14.86 | 26 | 1.2062 | 0.4565 |
85
- | 1.2105 | 16.0 | 28 | 1.2015 | 0.4565 |
86
- | 1.2105 | 16.57 | 29 | 1.1986 | 0.4565 |
87
- | 1.1785 | 17.71 | 31 | 1.1926 | 0.4565 |
88
- | 1.1785 | 18.86 | 33 | 1.1902 | 0.4565 |
89
- | 1.1785 | 20.0 | 35 | 1.1885 | 0.4565 |
90
- | 1.1785 | 20.57 | 36 | 1.1878 | 0.4565 |
91
- | 1.1785 | 21.71 | 38 | 1.1870 | 0.4565 |
92
- | 1.1615 | 22.86 | 40 | 1.1869 | 0.4565 |
 
 
 
 
 
 
 
 
 
 
 
 
93
 
94
 
95
  ### Framework versions
 
32
 
33
  This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.2080
36
  - Accuracy: 0.4565
37
 
38
  ## Model description
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 0.02
56
+ - train_batch_size: 16
57
+ - eval_batch_size: 16
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 64
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
 
63
  - num_epochs: 40
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 0.86 | 3 | 26.2016 | 0.1739 |
70
+ | No log | 2.0 | 7 | 1.3785 | 0.4565 |
71
+ | 12.975 | 2.86 | 10 | 2.2855 | 0.4565 |
72
+ | 12.975 | 4.0 | 14 | 1.5437 | 0.4565 |
73
+ | 12.975 | 4.86 | 17 | 1.5017 | 0.3261 |
74
+ | 2.1282 | 6.0 | 21 | 1.5409 | 0.1087 |
75
+ | 2.1282 | 6.86 | 24 | 1.4040 | 0.4565 |
76
+ | 2.1282 | 8.0 | 28 | 1.2780 | 0.4565 |
77
+ | 1.554 | 8.86 | 31 | 1.2300 | 0.3261 |
78
+ | 1.554 | 10.0 | 35 | 1.3228 | 0.3261 |
79
+ | 1.554 | 10.86 | 38 | 1.2745 | 0.4565 |
80
+ | 1.3748 | 12.0 | 42 | 1.3724 | 0.3261 |
81
+ | 1.3748 | 12.86 | 45 | 1.3726 | 0.4565 |
82
+ | 1.3748 | 14.0 | 49 | 1.2891 | 0.3261 |
83
+ | 1.5315 | 14.86 | 52 | 1.2979 | 0.4565 |
84
+ | 1.5315 | 16.0 | 56 | 1.2272 | 0.4565 |
85
+ | 1.5315 | 16.86 | 59 | 1.2749 | 0.3261 |
86
+ | 1.351 | 18.0 | 63 | 1.2219 | 0.4565 |
87
+ | 1.351 | 18.86 | 66 | 1.2200 | 0.4565 |
88
+ | 1.2678 | 20.0 | 70 | 1.2278 | 0.3261 |
89
+ | 1.2678 | 20.86 | 73 | 1.2318 | 0.4565 |
90
+ | 1.2678 | 22.0 | 77 | 1.2102 | 0.4565 |
91
+ | 1.244 | 22.86 | 80 | 1.2466 | 0.3261 |
92
+ | 1.244 | 24.0 | 84 | 1.2103 | 0.4565 |
93
+ | 1.244 | 24.86 | 87 | 1.2067 | 0.4565 |
94
+ | 1.2585 | 26.0 | 91 | 1.2129 | 0.4565 |
95
+ | 1.2585 | 26.86 | 94 | 1.2110 | 0.4565 |
96
+ | 1.2585 | 28.0 | 98 | 1.2131 | 0.4565 |
97
+ | 1.2405 | 28.86 | 101 | 1.2072 | 0.4565 |
98
+ | 1.2405 | 30.0 | 105 | 1.2099 | 0.4565 |
99
+ | 1.2405 | 30.86 | 108 | 1.2115 | 0.4565 |
100
+ | 1.2134 | 32.0 | 112 | 1.2138 | 0.4565 |
101
+ | 1.2134 | 32.86 | 115 | 1.2095 | 0.4565 |
102
+ | 1.2134 | 34.0 | 119 | 1.2081 | 0.4565 |
103
+ | 1.1982 | 34.29 | 120 | 1.2080 | 0.4565 |
104
 
105
 
106
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c717cf970c45f8dd0bab1d0bd8e41d5ee362d43529c5ef016b7ed742730e2cfc
3
  size 110356296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06147d48db0c7f00cd736879677bab6e594f99a3f0855e92050e33709b349e93
3
  size 110356296
runs/Dec02_15-11-10_DESKTOP-SKBE9FB/events.out.tfevents.1733173871.DESKTOP-SKBE9FB.10128.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c54767f736e76d4f078ec01a31321a6e2eebc484ece909eaf4b728e2d28f020
3
- size 16635
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90d3a0b310da1b344af4d6783724838e9a3b5259432d83f15940022eeccb7cee
3
+ size 18088