Hugging Face's logo

Augusto777
/
swinv2-tiny-patch4-window8-256-DMAE-U2

TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
Augusto777 commited on
Commit
8a0e691
·
verified ·
1 Parent(s): 33aed35

Model save

Browse files
Files changed (3) hide show
  1. README.md +40 -39
  2. model.safetensors +1 -1
  3. runs/Dec03_15-40-48_DESKTOP-SKBE9FB/events.out.tfevents.1733262049.DESKTOP-SKBE9FB.16888.0 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.10869565217391304
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ 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: 7.9210
36
- - Accuracy: 0.1087
37
 
38
  ## Model description
39
 
@@ -52,7 +52,7 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 1.6666666666666667e-05
56
  - train_batch_size: 16
57
  - eval_batch_size: 16
58
  - seed: 42
@@ -60,47 +60,48 @@ The following hyperparameters were used during training:
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 | 7.9210 | 0.1087 |
70
- | No log | 2.0 | 7 | 7.8628 | 0.1087 |
71
- | 7.9205 | 2.86 | 10 | 7.7933 | 0.1087 |
72
- | 7.9205 | 4.0 | 14 | 7.6468 | 0.1087 |
73
- | 7.9205 | 4.86 | 17 | 7.5149 | 0.1087 |
74
- | 7.5974 | 6.0 | 21 | 7.3160 | 0.1087 |
75
- | 7.5974 | 6.86 | 24 | 7.1402 | 0.1087 |
76
- | 7.5974 | 8.0 | 28 | 6.8986 | 0.1087 |
77
- | 6.9785 | 8.86 | 31 | 6.7163 | 0.1087 |
78
- | 6.9785 | 10.0 | 35 | 6.5023 | 0.1087 |
79
- | 6.9785 | 10.86 | 38 | 6.3489 | 0.1087 |
80
- | 6.6592 | 12.0 | 42 | 6.1222 | 0.1087 |
81
- | 6.6592 | 12.86 | 45 | 5.9531 | 0.1087 |
82
- | 6.6592 | 14.0 | 49 | 5.7591 | 0.1087 |
83
- | 5.989 | 14.86 | 52 | 5.6241 | 0.1087 |
84
- | 5.989 | 16.0 | 56 | 5.4473 | 0.1087 |
85
- | 5.989 | 16.86 | 59 | 5.3234 | 0.1087 |
86
- | 5.542 | 18.0 | 63 | 5.1690 | 0.1087 |
87
- | 5.542 | 18.86 | 66 | 5.0607 | 0.1087 |
88
- | 5.2205 | 20.0 | 70 | 4.9247 | 0.1087 |
89
- | 5.2205 | 20.86 | 73 | 4.8281 | 0.1087 |
90
- | 5.2205 | 22.0 | 77 | 4.7096 | 0.1087 |
91
- | 4.8962 | 22.86 | 80 | 4.6283 | 0.1087 |
92
- | 4.8962 | 24.0 | 84 | 4.5298 | 0.1087 |
93
- | 4.8962 | 24.86 | 87 | 4.4619 | 0.1087 |
94
- | 4.6327 | 26.0 | 91 | 4.3810 | 0.1087 |
95
- | 4.6327 | 26.86 | 94 | 4.3274 | 0.1087 |
96
- | 4.6327 | 28.0 | 98 | 4.2649 | 0.1087 |
97
- | 4.3789 | 28.86 | 101 | 4.2249 | 0.1087 |
98
- | 4.3789 | 30.0 | 105 | 4.1806 | 0.1087 |
99
- | 4.3789 | 30.86 | 108 | 4.1541 | 0.1087 |
100
- | 4.3182 | 32.0 | 112 | 4.1275 | 0.1087 |
101
- | 4.3182 | 32.86 | 115 | 4.1142 | 0.1087 |
102
- | 4.3182 | 34.0 | 119 | 4.1054 | 0.1087 |
103
- | 4.254 | 34.29 | 120 | 4.1048 | 0.1087 |
104
 
105
 
106
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.6521739130434783
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
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: 0.8720
36
+ - Accuracy: 0.6522
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 3.5e-05
56
  - train_batch_size: 16
57
  - eval_batch_size: 16
58
  - seed: 42
 
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
+ - lr_scheduler_warmup_ratio: 0.05
64
  - num_epochs: 40
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.86 | 3 | 1.3843 | 0.4783 |
71
+ | No log | 2.0 | 7 | 1.3617 | 0.4565 |
72
+ | 1.3721 | 2.86 | 10 | 1.3211 | 0.4565 |
73
+ | 1.3721 | 4.0 | 14 | 1.2598 | 0.4565 |
74
+ | 1.3721 | 4.86 | 17 | 1.2251 | 0.4565 |
75
+ | 1.25 | 6.0 | 21 | 1.2094 | 0.4565 |
76
+ | 1.25 | 6.86 | 24 | 1.2127 | 0.4565 |
77
+ | 1.25 | 8.0 | 28 | 1.2118 | 0.4565 |
78
+ | 1.1902 | 8.86 | 31 | 1.2031 | 0.4565 |
79
+ | 1.1902 | 10.0 | 35 | 1.1936 | 0.4565 |
80
+ | 1.1902 | 10.86 | 38 | 1.1829 | 0.4565 |
81
+ | 1.1472 | 12.0 | 42 | 1.1569 | 0.4565 |
82
+ | 1.1472 | 12.86 | 45 | 1.1432 | 0.4565 |
83
+ | 1.1472 | 14.0 | 49 | 1.1357 | 0.4783 |
84
+ | 1.1495 | 14.86 | 52 | 1.1178 | 0.5 |
85
+ | 1.1495 | 16.0 | 56 | 1.0903 | 0.5217 |
86
+ | 1.1495 | 16.86 | 59 | 1.0714 | 0.6304 |
87
+ | 1.0824 | 18.0 | 63 | 1.0453 | 0.6522 |
88
+ | 1.0824 | 18.86 | 66 | 1.0150 | 0.6522 |
89
+ | 1.0535 | 20.0 | 70 | 0.9925 | 0.6522 |
90
+ | 1.0535 | 20.86 | 73 | 0.9778 | 0.6304 |
91
+ | 1.0535 | 22.0 | 77 | 0.9570 | 0.6522 |
92
+ | 0.994 | 22.86 | 80 | 0.9441 | 0.6304 |
93
+ | 0.994 | 24.0 | 84 | 0.9246 | 0.6304 |
94
+ | 0.994 | 24.86 | 87 | 0.9095 | 0.6304 |
95
+ | 0.9554 | 26.0 | 91 | 0.8937 | 0.6304 |
96
+ | 0.9554 | 26.86 | 94 | 0.8925 | 0.6522 |
97
+ | 0.9554 | 28.0 | 98 | 0.8886 | 0.6522 |
98
+ | 0.953 | 28.86 | 101 | 0.8804 | 0.6522 |
99
+ | 0.953 | 30.0 | 105 | 0.8744 | 0.6522 |
100
+ | 0.953 | 30.86 | 108 | 0.8754 | 0.6522 |
101
+ | 0.9092 | 32.0 | 112 | 0.8733 | 0.6522 |
102
+ | 0.9092 | 32.86 | 115 | 0.8725 | 0.6522 |
103
+ | 0.9092 | 34.0 | 119 | 0.8722 | 0.6522 |
104
+ | 0.9247 | 34.29 | 120 | 0.8720 | 0.6522 |
105
 
106
 
107
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5762929538f1e79eb4dcd5a67af2b1dcb16ccf9c4452cc894ecb67fa01378670
3
  size 110356296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97e64e64886aca534c5d2a1887d06f3f64a266ed42f760ee5a5a5e6d0d3fa678
3
  size 110356296
runs/Dec03_15-40-48_DESKTOP-SKBE9FB/events.out.tfevents.1733262049.DESKTOP-SKBE9FB.16888.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8a349b956d9ee1598612b450a0d63c9b53c7fee640f497e9a17cef4651bc107
3
- size 17275
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3c606b04f56f22e9532d4914e6e3178ce654c85348c8c37a8d9c7ad71e663c2
3
+ size 18094