JEdward7777 commited on
Commit
67f4317
1 Parent(s): debf40c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -7
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.4
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 [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 1.4366
35
- - Accuracy: 0.4
36
 
37
  ## Model description
38
 
@@ -60,15 +60,22 @@ The following hyperparameters were used during training:
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: 3
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | No log | 1.0 | 1 | 1.6357 | 0.4 |
70
- | No log | 2.0 | 2 | 1.5019 | 0.4 |
71
- | No log | 3.0 | 3 | 1.4366 | 0.4 |
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.8
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 [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 1.0377
35
+ - Accuracy: 0.8
36
 
37
  ## Model description
38
 
 
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: 10
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 1.0 | 1 | 1.6117 | 0.6 |
70
+ | No log | 2.0 | 2 | 1.5290 | 0.6 |
71
+ | No log | 3.0 | 3 | 1.4318 | 0.8 |
72
+ | No log | 4.0 | 4 | 1.3328 | 0.8 |
73
+ | No log | 5.0 | 5 | 1.2356 | 0.8 |
74
+ | No log | 6.0 | 6 | 1.1691 | 0.8 |
75
+ | No log | 7.0 | 7 | 1.1160 | 0.8 |
76
+ | No log | 8.0 | 8 | 1.0754 | 0.8 |
77
+ | No log | 9.0 | 9 | 1.0506 | 0.8 |
78
+ | No log | 10.0 | 10 | 1.0377 | 0.8 |
79
 
80
 
81
  ### Framework versions