Hugging Face's logo

Augusto777
/
swiftformer-xs-DMAE

TensorBoard
Safetensors
swiftformer
Generated from Trainer
Eval Results
Model card Files Metrics Community
Augusto777 commited on
Commit
67f0759
·
verified ·
1 Parent(s): 9afad14

Model save

Browse files
Files changed (3) hide show
  1. README.md +40 -40
  2. model.safetensors +1 -1
  3. runs/Dec02_12-51-56_DESKTOP-SKBE9FB/events.out.tfevents.1733165517.DESKTOP-SKBE9FB.7092.0 +2 -2
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.6521739130434783
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 1.3719
35
- - Accuracy: 0.6522
36
 
37
  ## Model description
38
 
@@ -51,7 +51,7 @@ More information needed
51
  ### Training hyperparameters
52
 
53
  The following hyperparameters were used during training:
54
- - learning_rate: 1.5e-05
55
  - train_batch_size: 16
56
  - eval_batch_size: 16
57
  - seed: 42
@@ -59,48 +59,48 @@ The following hyperparameters were used during training:
59
  - total_train_batch_size: 64
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
- - lr_scheduler_warmup_ratio: 0.01
63
  - num_epochs: 40
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | No log | 0.86 | 3 | 1.3862 | 0.3261 |
70
- | No log | 2.0 | 7 | 1.3857 | 0.4783 |
71
- | 1.3859 | 2.86 | 10 | 1.3849 | 0.5435 |
72
- | 1.3859 | 4.0 | 14 | 1.3839 | 0.6087 |
73
- | 1.3859 | 4.86 | 17 | 1.3834 | 0.6087 |
74
- | 1.3844 | 6.0 | 21 | 1.3825 | 0.6087 |
75
- | 1.3844 | 6.86 | 24 | 1.3820 | 0.5870 |
76
- | 1.3844 | 8.0 | 28 | 1.3812 | 0.5870 |
77
- | 1.3831 | 8.86 | 31 | 1.3804 | 0.6304 |
78
- | 1.3831 | 10.0 | 35 | 1.3793 | 0.6087 |
79
- | 1.3831 | 10.86 | 38 | 1.3787 | 0.6087 |
80
- | 1.3815 | 12.0 | 42 | 1.3778 | 0.6087 |
81
- | 1.3815 | 12.86 | 45 | 1.3767 | 0.6087 |
82
- | 1.3815 | 14.0 | 49 | 1.3757 | 0.6087 |
83
- | 1.3794 | 14.86 | 52 | 1.3748 | 0.6087 |
84
- | 1.3794 | 16.0 | 56 | 1.3738 | 0.6304 |
85
- | 1.3794 | 16.86 | 59 | 1.3730 | 0.6087 |
86
- | 1.3766 | 18.0 | 63 | 1.3719 | 0.6522 |
87
- | 1.3766 | 18.86 | 66 | 1.3708 | 0.6087 |
88
- | 1.3748 | 20.0 | 70 | 1.3699 | 0.6304 |
89
- | 1.3748 | 20.86 | 73 | 1.3687 | 0.6304 |
90
- | 1.3748 | 22.0 | 77 | 1.3677 | 0.5870 |
91
- | 1.372 | 22.86 | 80 | 1.3664 | 0.6304 |
92
- | 1.372 | 24.0 | 84 | 1.3655 | 0.5870 |
93
- | 1.372 | 24.86 | 87 | 1.3648 | 0.6304 |
94
- | 1.3693 | 26.0 | 91 | 1.3640 | 0.6087 |
95
- | 1.3693 | 26.86 | 94 | 1.3637 | 0.6087 |
96
- | 1.3693 | 28.0 | 98 | 1.3627 | 0.6304 |
97
- | 1.3685 | 28.86 | 101 | 1.3624 | 0.5870 |
98
- | 1.3685 | 30.0 | 105 | 1.3622 | 0.6087 |
99
- | 1.3685 | 30.86 | 108 | 1.3610 | 0.6087 |
100
- | 1.3675 | 32.0 | 112 | 1.3605 | 0.6087 |
101
- | 1.3675 | 32.86 | 115 | 1.3605 | 0.6087 |
102
- | 1.3675 | 34.0 | 119 | 1.3611 | 0.5870 |
103
- | 1.3663 | 34.29 | 120 | 1.3608 | 0.6087 |
104
 
105
 
106
  ### Framework versions
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.6956521739130435
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 1.2611
35
+ - Accuracy: 0.6957
36
 
37
  ## Model description
38
 
 
51
  ### Training hyperparameters
52
 
53
  The following hyperparameters were used during training:
54
+ - learning_rate: 0.0015
55
  - train_batch_size: 16
56
  - eval_batch_size: 16
57
  - seed: 42
 
59
  - total_train_batch_size: 64
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_ratio: 0.1
63
  - num_epochs: 40
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 0.86 | 3 | 1.3836 | 0.4565 |
70
+ | No log | 2.0 | 7 | 1.3327 | 0.6522 |
71
+ | 1.3567 | 2.86 | 10 | 1.1681 | 0.6522 |
72
+ | 1.3567 | 4.0 | 14 | 1.0440 | 0.5652 |
73
+ | 1.3567 | 4.86 | 17 | 1.0462 | 0.6304 |
74
+ | 1.0903 | 6.0 | 21 | 0.9294 | 0.5870 |
75
+ | 1.0903 | 6.86 | 24 | 0.9572 | 0.6522 |
76
+ | 1.0903 | 8.0 | 28 | 0.9286 | 0.6739 |
77
+ | 1.0969 | 8.86 | 31 | 0.9229 | 0.6304 |
78
+ | 1.0969 | 10.0 | 35 | 0.9061 | 0.6522 |
79
+ | 1.0969 | 10.86 | 38 | 0.8341 | 0.6739 |
80
+ | 0.8923 | 12.0 | 42 | 0.8786 | 0.6739 |
81
+ | 0.8923 | 12.86 | 45 | 0.8596 | 0.7391 |
82
+ | 0.8923 | 14.0 | 49 | 0.8902 | 0.7174 |
83
+ | 0.7289 | 14.86 | 52 | 0.8024 | 0.6739 |
84
+ | 0.7289 | 16.0 | 56 | 0.9341 | 0.7174 |
85
+ | 0.7289 | 16.86 | 59 | 1.0464 | 0.7174 |
86
+ | 0.6609 | 18.0 | 63 | 0.9923 | 0.6087 |
87
+ | 0.6609 | 18.86 | 66 | 0.8225 | 0.7174 |
88
+ | 0.6527 | 20.0 | 70 | 0.8748 | 0.6957 |
89
+ | 0.6527 | 20.86 | 73 | 0.8052 | 0.6739 |
90
+ | 0.6527 | 22.0 | 77 | 0.8861 | 0.6957 |
91
+ | 0.493 | 22.86 | 80 | 0.9555 | 0.6957 |
92
+ | 0.493 | 24.0 | 84 | 1.0336 | 0.6739 |
93
+ | 0.493 | 24.86 | 87 | 0.9961 | 0.6957 |
94
+ | 0.4088 | 26.0 | 91 | 1.0400 | 0.6957 |
95
+ | 0.4088 | 26.86 | 94 | 1.0536 | 0.6957 |
96
+ | 0.4088 | 28.0 | 98 | 1.1388 | 0.6739 |
97
+ | 0.4047 | 28.86 | 101 | 1.2295 | 0.6522 |
98
+ | 0.4047 | 30.0 | 105 | 1.2627 | 0.6522 |
99
+ | 0.4047 | 30.86 | 108 | 1.2372 | 0.6739 |
100
+ | 0.3681 | 32.0 | 112 | 1.2919 | 0.6522 |
101
+ | 0.3681 | 32.86 | 115 | 1.2453 | 0.6522 |
102
+ | 0.3681 | 34.0 | 119 | 1.2612 | 0.6739 |
103
+ | 0.353 | 34.29 | 120 | 1.2611 | 0.6957 |
104
 
105
 
106
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3101846c0e92c529c2b7c0b1894ce811d68cc4f4c11e92330f21ca976625aa1a
3
  size 12203648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ba64d5c606918d9facce594789c42c8daaf78f6a7160d3ee4424b3e3043a7a5
3
  size 12203648
runs/Dec02_12-51-56_DESKTOP-SKBE9FB/events.out.tfevents.1733165517.DESKTOP-SKBE9FB.7092.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c079f61580d1f547d61bfeebd81fff91d6a053a5f3160fd4dc7fb97062486726
3
- size 17014
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9011a4cdaeeff055011a15687a24e43d64ae7357cf6de5a97cdcce0ab4d50344
3
+ size 17833