Hugging Face's logo

sharren
/
vit-lr-0.0001

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
sharren commited on
Commit
4e0ffec
•
1 Parent(s): c4f4ed7

Model save

Browse files
Files changed (2) hide show
  1. README.md +19 -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-0.0001
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: 0.4717
25
- - Accuracy: 0.8284
26
- - Precision: 0.8231
27
- - Recall: 0.8284
28
- - F1: 0.8213
29
 
30
  ## Model description
31
 
@@ -49,7 +48,7 @@ The following hyperparameters were used during training:
49
  - eval_batch_size: 8
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
- - lr_scheduler_type: linear
53
  - num_epochs: 100
54
  - mixed_precision_training: Native AMP
55
 
@@ -57,18 +56,18 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
60
- | 0.682 | 1.0 | 321 | 0.5192 | 0.8100 | 0.8034 | 0.8100 | 0.7981 |
61
- | 0.4386 | 2.0 | 642 | 0.4717 | 0.8284 | 0.8231 | 0.8284 | 0.8213 |
62
- | 0.2621 | 3.0 | 963 | 0.5676 | 0.8350 | 0.8263 | 0.8350 | 0.8201 |
63
- | 0.1891 | 4.0 | 1284 | 0.5022 | 0.8495 | 0.8556 | 0.8495 | 0.8436 |
64
- | 0.1052 | 5.0 | 1605 | 0.6661 | 0.8398 | 0.8483 | 0.8398 | 0.8357 |
65
- | 0.0785 | 6.0 | 1926 | 0.5570 | 0.8592 | 0.8574 | 0.8592 | 0.8574 |
66
- | 0.0481 | 7.0 | 2247 | 0.6496 | 0.8547 | 0.8548 | 0.8547 | 0.8523 |
67
- | 0.0281 | 8.0 | 2568 | 0.7423 | 0.8571 | 0.8570 | 0.8571 | 0.8545 |
68
- | 0.0439 | 9.0 | 2889 | 0.7678 | 0.8540 | 0.8511 | 0.8540 | 0.8518 |
69
- | 0.0297 | 10.0 | 3210 | 0.8648 | 0.8467 | 0.8478 | 0.8467 | 0.8464 |
70
- | 0.037 | 11.0 | 3531 | 0.7683 | 0.8561 | 0.8552 | 0.8561 | 0.8549 |
71
- | 0.0322 | 12.0 | 3852 | 1.0126 | 0.8512 | 0.8561 | 0.8512 | 0.8397 |
72
 
73
 
74
  ### 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-0.0001
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: 1.0203
24
+ - Accuracy: 0.8457
25
+ - Precision: 0.8488
26
+ - Recall: 0.8457
27
+ - F1: 0.8416
28
 
29
  ## Model description
30
 
 
48
  - eval_batch_size: 8
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: cosine
52
  - num_epochs: 100
53
  - mixed_precision_training: Native AMP
54
 
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
59
+ | 0.6718 | 1.0 | 321 | 0.4934 | 0.8242 | 0.8254 | 0.8242 | 0.8163 |
60
+ | 0.4045 | 2.0 | 642 | 0.4778 | 0.8311 | 0.8433 | 0.8311 | 0.8269 |
61
+ | 0.2419 | 3.0 | 963 | 0.5133 | 0.8405 | 0.8525 | 0.8405 | 0.8410 |
62
+ | 0.1267 | 4.0 | 1284 | 0.6154 | 0.8495 | 0.8491 | 0.8495 | 0.8448 |
63
+ | 0.0733 | 5.0 | 1605 | 0.7845 | 0.8422 | 0.8421 | 0.8422 | 0.8361 |
64
+ | 0.0446 | 6.0 | 1926 | 0.8767 | 0.8471 | 0.8407 | 0.8471 | 0.8408 |
65
+ | 0.0523 | 7.0 | 2247 | 0.8674 | 0.8450 | 0.8492 | 0.8450 | 0.8407 |
66
+ | 0.0388 | 8.0 | 2568 | 0.9754 | 0.8398 | 0.8566 | 0.8398 | 0.8387 |
67
+ | 0.0402 | 9.0 | 2889 | 0.9370 | 0.8492 | 0.8547 | 0.8492 | 0.8461 |
68
+ | 0.0283 | 10.0 | 3210 | 0.9218 | 0.8509 | 0.8496 | 0.8509 | 0.8483 |
69
+ | 0.0451 | 11.0 | 3531 | 0.9872 | 0.8474 | 0.8400 | 0.8474 | 0.8401 |
70
+ | 0.0549 | 12.0 | 3852 | 1.0203 | 0.8457 | 0.8488 | 0.8457 | 0.8416 |
71
 
72
 
73
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b7be565243293069d3b7605c2f4daf7549e154fc893f2b0e4cbeaba2087aadc
3
  size 343239356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30757d47a1557a32104ceefac0ee885699d829b7ddd5829e348813c1c372f02e
3
  size 343239356