Hugging Face's logo

system-admin
/
swin-tiny-patch4-window7-224-finetuned-student_two_classes

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
system-admin commited on
Commit
75f2059
•
1 Parent(s): 80a0bb5

Model save

Browse files
Files changed (3) hide show
  1. README.md +26 -18
  2. model.safetensors +1 -1
  3. runs/May01_14-50-35_d6eb9620a945/events.out.tfevents.1714575073.d6eb9620a945.304.0 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.78
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/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.4645
36
- - Accuracy: 0.78
37
 
38
  ## Model description
39
 
@@ -56,27 +56,35 @@ The following hyperparameters were used during training:
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: 10
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
- |:-------------:|:------:|:----:|:---------------:|:--------:|
70
- | No log | 0.9231 | 3 | 0.5091 | 0.79 |
71
- | No log | 1.8462 | 6 | 0.6119 | 0.78 |
72
- | No log | 2.7692 | 9 | 0.5369 | 0.78 |
73
- | 0.5446 | 4.0 | 13 | 0.4780 | 0.78 |
74
- | 0.5446 | 4.9231 | 16 | 0.4721 | 0.78 |
75
- | 0.5446 | 5.8462 | 19 | 0.4750 | 0.78 |
76
- | 0.4041 | 6.7692 | 22 | 0.4746 | 0.78 |
77
- | 0.4041 | 8.0 | 26 | 0.4700 | 0.78 |
78
- | 0.4041 | 8.9231 | 29 | 0.4649 | 0.78 |
79
- | 0.3755 | 9.2308 | 30 | 0.4645 | 0.78 |
 
 
 
 
 
 
 
 
 
 
80
 
81
 
82
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.82
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/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.4187
36
+ - Accuracy: 0.82
37
 
38
  ## Model description
39
 
 
56
  - train_batch_size: 32
57
  - eval_batch_size: 32
58
  - seed: 42
 
 
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
  - lr_scheduler_warmup_ratio: 0.1
62
+ - num_epochs: 20
63
 
64
  ### Training results
65
 
66
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.6951 | 1.0 | 13 | 0.4448 | 0.82 |
69
+ | 0.4292 | 2.0 | 26 | 0.4461 | 0.82 |
70
+ | 0.4246 | 3.0 | 39 | 0.4554 | 0.82 |
71
+ | 0.3983 | 4.0 | 52 | 0.4220 | 0.83 |
72
+ | 0.314 | 5.0 | 65 | 0.4429 | 0.83 |
73
+ | 0.4176 | 6.0 | 78 | 0.4006 | 0.82 |
74
+ | 0.2862 | 7.0 | 91 | 0.4145 | 0.84 |
75
+ | 0.3072 | 8.0 | 104 | 0.3847 | 0.83 |
76
+ | 0.3001 | 9.0 | 117 | 0.4043 | 0.87 |
77
+ | 0.2937 | 10.0 | 130 | 0.4026 | 0.82 |
78
+ | 0.2206 | 11.0 | 143 | 0.3972 | 0.83 |
79
+ | 0.2287 | 12.0 | 156 | 0.3840 | 0.86 |
80
+ | 0.3318 | 13.0 | 169 | 0.3741 | 0.84 |
81
+ | 0.232 | 14.0 | 182 | 0.3850 | 0.85 |
82
+ | 0.2277 | 15.0 | 195 | 0.3989 | 0.85 |
83
+ | 0.2253 | 16.0 | 208 | 0.4071 | 0.85 |
84
+ | 0.2463 | 17.0 | 221 | 0.4027 | 0.85 |
85
+ | 0.2496 | 18.0 | 234 | 0.4146 | 0.83 |
86
+ | 0.1969 | 19.0 | 247 | 0.4104 | 0.83 |
87
+ | 0.2279 | 20.0 | 260 | 0.4187 | 0.82 |
88
 
89
 
90
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b759732ea9b74230e2c60d254b35b4694c7fdbcc7b22c572463080b948ec7fb5
3
  size 110342832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64119251aae881b9f732c9567a2f488f49243d8eed4c21d792eb9755430d1172
3
  size 110342832
runs/May01_14-50-35_d6eb9620a945/events.out.tfevents.1714575073.d6eb9620a945.304.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97e8b33c407033765233c39d1ee686538daee7e448a5f047e38707a0584856dd
3
- size 16302
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d031868d1ebfbd9f82057e35cdd655b95a38722ff7d8e127c45e67056821c79
3
+ size 17401