Hugging Face's logo

sharren
/
vit-lr-cosine-restarts

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
sharren commited on
Commit
5206769
•
1 Parent(s): a0d01e9

Model save

Browse files
Files changed (2) hide show
  1. README.md +18 -19
  2. model.safetensors +1 -1
README.md CHANGED
@@ -2,7 +2,6 @@
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224
4
  tags:
5
- - image-classification
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
@@ -19,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # vit-lr-cosine-restarts
21
 
22
- This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the skin-cancer dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.5117
25
- - Accuracy: 0.8221
26
- - Precision: 0.8347
27
- - Recall: 0.8221
28
- - F1: 0.8100
29
 
30
  ## Model description
31
 
@@ -58,18 +57,18 @@ The following hyperparameters were used during training:
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
60
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
61
- | 0.86 | 1.0 | 321 | 0.5250 | 0.8141 | 0.8100 | 0.8141 | 0.8011 |
62
- | 0.4517 | 2.0 | 642 | 0.5117 | 0.8221 | 0.8347 | 0.8221 | 0.8100 |
63
- | 0.3462 | 3.0 | 963 | 0.5492 | 0.8318 | 0.8238 | 0.8318 | 0.8146 |
64
- | 0.1884 | 4.0 | 1284 | 0.5316 | 0.8478 | 0.8452 | 0.8478 | 0.8425 |
65
- | 0.0661 | 5.0 | 1605 | 0.5808 | 0.8662 | 0.8632 | 0.8662 | 0.8632 |
66
- | 0.0072 | 6.0 | 1926 | 0.6703 | 0.8714 | 0.8676 | 0.8714 | 0.8685 |
67
- | 0.0005 | 7.0 | 2247 | 0.6641 | 0.8724 | 0.8681 | 0.8724 | 0.8692 |
68
- | 0.0253 | 8.0 | 2568 | 1.1243 | 0.7639 | 0.8425 | 0.7639 | 0.7812 |
69
- | 0.163 | 9.0 | 2889 | 0.7354 | 0.8447 | 0.8560 | 0.8447 | 0.8443 |
70
- | 0.0324 | 10.0 | 3210 | 0.7327 | 0.8641 | 0.8630 | 0.8641 | 0.8609 |
71
- | 0.0014 | 11.0 | 3531 | 0.7243 | 0.8679 | 0.8637 | 0.8679 | 0.8643 |
72
- | 0.0002 | 12.0 | 3852 | 0.7236 | 0.8696 | 0.8655 | 0.8696 | 0.8661 |
73
 
74
 
75
  ### Framework versions
 
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224
4
  tags:
 
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
 
18
 
19
  # vit-lr-cosine-restarts
20
 
21
+ This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.7956
24
+ - Accuracy: 0.8731
25
+ - Precision: 0.8708
26
+ - Recall: 0.8731
27
+ - F1: 0.8699
28
 
29
  ## Model description
30
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
60
+ | 0.5999 | 1.0 | 321 | 0.5250 | 0.8141 | 0.8100 | 0.8141 | 0.8011 |
61
+ | 0.4483 | 2.0 | 642 | 0.5117 | 0.8221 | 0.8347 | 0.8221 | 0.8100 |
62
+ | 0.3425 | 3.0 | 963 | 0.5709 | 0.8270 | 0.8208 | 0.8270 | 0.8107 |
63
+ | 0.176 | 4.0 | 1284 | 0.5579 | 0.8575 | 0.8549 | 0.8575 | 0.8544 |
64
+ | 0.0183 | 5.0 | 1605 | 0.5555 | 0.8773 | 0.8762 | 0.8773 | 0.8759 |
65
+ | 0.0273 | 6.0 | 1926 | 0.8166 | 0.8415 | 0.8369 | 0.8415 | 0.8328 |
66
+ | 0.1186 | 7.0 | 2247 | 0.6380 | 0.8617 | 0.8598 | 0.8617 | 0.8591 |
67
+ | 0.0166 | 8.0 | 2568 | 0.6608 | 0.8731 | 0.8716 | 0.8731 | 0.8709 |
68
+ | 0.0003 | 9.0 | 2889 | 1.0045 | 0.8460 | 0.8438 | 0.8460 | 0.8306 |
69
+ | 0.1258 | 10.0 | 3210 | 0.6712 | 0.8499 | 0.8527 | 0.8499 | 0.8490 |
70
+ | 0.0137 | 11.0 | 3531 | 0.7952 | 0.8738 | 0.8765 | 0.8738 | 0.8740 |
71
+ | 0.0004 | 12.0 | 3852 | 0.7956 | 0.8731 | 0.8708 | 0.8731 | 0.8699 |
72
 
73
 
74
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7971307613f2f97f6fcee8aed9f090d013d782ebb70022b3522d85eeaf60c48b
3
  size 343239356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe2077c2a1cc52d28aeda08ce0a8c3aa4ded851ef06566e68937d1180678c0d2
3
  size 343239356