Hugging Face's logo

Hemg
/
Wound-Image-classification

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Model card Files
xet
Metrics Community
Hemg commited on
Commit
7f4e02e
·
verified ·
1 Parent(s): b1c873e

Model save

Browse files
Files changed (2) hide show
  1. README.md +15 -22
  2. runs/Mar11_09-13-38_33467ebf2898/events.out.tfevents.1710148419.33467ebf2898.370.3 +2 -2
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.1183
21
- - Accuracy: 0.7356
22
 
23
  ## Model description
24
 
@@ -37,36 +37,29 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 4e-05
41
- - train_batch_size: 16
42
- - eval_batch_size: 16
43
  - seed: 42
44
  - gradient_accumulation_steps: 4
45
- - total_train_batch_size: 64
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
- - num_epochs: 16
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
- | 2.1311 | 0.91 | 5 | 1.9292 | 0.2529 |
56
- | 1.7051 | 2.0 | 11 | 1.8199 | 0.3678 |
57
- | 1.8849 | 2.91 | 16 | 1.6945 | 0.5172 |
58
- | 1.4484 | 4.0 | 22 | 1.5908 | 0.5287 |
59
- | 1.6081 | 4.91 | 27 | 1.4990 | 0.5747 |
60
- | 1.2273 | 6.0 | 33 | 1.4064 | 0.5977 |
61
- | 1.3761 | 6.91 | 38 | 1.3142 | 0.7011 |
62
- | 1.0694 | 8.0 | 44 | 1.2471 | 0.6897 |
63
- | 1.2311 | 8.91 | 49 | 1.1874 | 0.7241 |
64
- | 0.9412 | 10.0 | 55 | 1.1786 | 0.7011 |
65
- | 1.097 | 10.91 | 60 | 1.1551 | 0.7126 |
66
- | 0.8663 | 12.0 | 66 | 1.1174 | 0.7356 |
67
- | 1.0139 | 12.91 | 71 | 1.0850 | 0.7586 |
68
- | 0.8313 | 14.0 | 77 | 1.0856 | 0.7586 |
69
- | 0.9011 | 14.55 | 80 | 1.1183 | 0.7356 |
70
 
71
 
72
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.4970
21
+ - Accuracy: 0.5402
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
  - seed: 42
44
  - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 32
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 8
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | 2.0669 | 0.93 | 10 | 1.8739 | 0.4483 |
56
+ | 1.7779 | 1.95 | 21 | 1.7844 | 0.4253 |
57
+ | 1.6468 | 2.98 | 32 | 1.6641 | 0.5172 |
58
+ | 1.5619 | 4.0 | 43 | 1.6033 | 0.5517 |
59
+ | 1.6159 | 4.93 | 53 | 1.5406 | 0.5402 |
60
+ | 1.4169 | 5.95 | 64 | 1.5055 | 0.5517 |
61
+ | 1.3861 | 6.98 | 75 | 1.4805 | 0.5632 |
62
+ | 1.3713 | 7.44 | 80 | 1.4970 | 0.5402 |
 
 
 
 
 
 
 
63
 
64
 
65
  ### Framework versions
runs/Mar11_09-13-38_33467ebf2898/events.out.tfevents.1710148419.33467ebf2898.370.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba494e101d5f6c1506b9753f5e666ef7a7d983b6e04264c09d9475e434248328
3
- size 8473
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb3e8909cf0ac0e31163f9f2e569f43dd85c6daa7abaa925316d6cac7de504a5
3
+ size 9345