Hugging Face's logo

sharren
/
vit-lr-cosine-warmup

Image Classification
Transformers
TensorBoard
Safetensors
vit
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
sharren commited on
Commit
5eec375
•
1 Parent(s): 9acd403

Model save

Browse files
Files changed (2) hide show
  1. README.md +20 -20
  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-warmup
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: 0.4682
25
- - Accuracy: 0.8298
26
- - Precision: 0.8308
27
- - Recall: 0.8298
28
- - F1: 0.8194
29
 
30
  ## Model description
31
 
@@ -50,7 +49,7 @@ The following hyperparameters were used during training:
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: cosine
53
- - lr_scheduler_warmup_steps: 192
54
  - num_epochs: 100
55
  - mixed_precision_training: Native AMP
56
 
@@ -58,18 +57,19 @@ The following hyperparameters were used during training:
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
60
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
61
- | 0.7736 | 1.0 | 321 | 0.5478 | 0.8096 | 0.8060 | 0.8096 | 0.7907 |
62
- | 0.4267 | 2.0 | 642 | 0.4682 | 0.8298 | 0.8308 | 0.8298 | 0.8194 |
63
- | 0.2634 | 3.0 | 963 | 0.6987 | 0.8187 | 0.8195 | 0.8187 | 0.7978 |
64
- | 0.1465 | 4.0 | 1284 | 0.7699 | 0.8162 | 0.8059 | 0.8162 | 0.7919 |
65
- | 0.067 | 5.0 | 1605 | 0.7295 | 0.8478 | 0.8406 | 0.8478 | 0.8402 |
66
- | 0.0486 | 6.0 | 1926 | 0.8328 | 0.8450 | 0.8447 | 0.8450 | 0.8347 |
67
- | 0.0193 | 7.0 | 2247 | 0.8354 | 0.8509 | 0.8604 | 0.8509 | 0.8526 |
68
- | 0.0144 | 8.0 | 2568 | 0.9953 | 0.8464 | 0.8410 | 0.8464 | 0.8374 |
69
- | 0.0207 | 9.0 | 2889 | 1.0263 | 0.8526 | 0.8504 | 0.8526 | 0.8463 |
70
- | 0.0127 | 10.0 | 3210 | 1.0858 | 0.8395 | 0.8538 | 0.8395 | 0.8385 |
71
- | 0.026 | 11.0 | 3531 | 0.9576 | 0.8395 | 0.8568 | 0.8395 | 0.8441 |
72
- | 0.0199 | 12.0 | 3852 | 0.9899 | 0.8575 | 0.8529 | 0.8575 | 0.8523 |
 
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-warmup
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: 1.2992
24
+ - Accuracy: 0.8398
25
+ - Precision: 0.8396
26
+ - Recall: 0.8398
27
+ - F1: 0.8243
28
 
29
  ## Model description
30
 
 
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: cosine
52
+ - lr_scheduler_warmup_steps: 770
53
  - num_epochs: 100
54
  - mixed_precision_training: Native AMP
55
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
60
+ | 0.86 | 1.0 | 321 | 0.5250 | 0.8141 | 0.8100 | 0.8141 | 0.8011 |
61
+ | 0.4517 | 2.0 | 642 | 0.5117 | 0.8221 | 0.8347 | 0.8221 | 0.8100 |
62
+ | 0.3512 | 3.0 | 963 | 0.4736 | 0.8395 | 0.8318 | 0.8395 | 0.8308 |
63
+ | 0.2184 | 4.0 | 1284 | 0.4797 | 0.8568 | 0.8536 | 0.8568 | 0.8505 |
64
+ | 0.1264 | 5.0 | 1605 | 0.6212 | 0.8547 | 0.8552 | 0.8547 | 0.8530 |
65
+ | 0.0687 | 6.0 | 1926 | 0.7659 | 0.8464 | 0.8476 | 0.8464 | 0.8402 |
66
+ | 0.0463 | 7.0 | 2247 | 0.8237 | 0.8519 | 0.8546 | 0.8519 | 0.8469 |
67
+ | 0.0373 | 8.0 | 2568 | 0.8712 | 0.8377 | 0.8493 | 0.8377 | 0.8415 |
68
+ | 0.0347 | 9.0 | 2889 | 0.8181 | 0.8568 | 0.8550 | 0.8568 | 0.8534 |
69
+ | 0.0263 | 10.0 | 3210 | 1.0705 | 0.8447 | 0.8389 | 0.8447 | 0.8308 |
70
+ | 0.0289 | 11.0 | 3531 | 0.9376 | 0.8589 | 0.8606 | 0.8589 | 0.8550 |
71
+ | 0.0164 | 12.0 | 3852 | 0.9714 | 0.8634 | 0.8611 | 0.8634 | 0.8611 |
72
+ | 0.0077 | 13.0 | 4173 | 1.2992 | 0.8398 | 0.8396 | 0.8398 | 0.8243 |
73
 
74
 
75
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1257ff61a4d537cb0e242491479d3cf591c031880bc16f85f971f2223437f5a
3
  size 343239356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b0e30553cf81e43dc309c47bf0eace343c1cd6dc7f06da0004b22feb8a103b
3
  size 343239356