Hugging Face's logo

sharren
/
vit-dropout-0.2

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Model card Files
xet
 Metrics Community
sharren commited on
Commit
338634b
·
verified ·
1 Parent(s): 943a7e0

Model save

Browse files
Files changed (2) hide show
  1. README.md +26 -28
  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-dropout-0.2
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: 0.4829
25
- - Accuracy: 0.8440
26
- - Precision: 0.8480
27
- - Recall: 0.8440
28
- - F1: 0.8409
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: 770
54
  - num_epochs: 100
55
  - mixed_precision_training: Native AMP
56
 
@@ -58,26 +57,25 @@ The following hyperparameters were used during training:
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
60
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
61
- | 1.5667 | 1.0 | 321 | 0.8401 | 0.6841 | 0.7945 | 0.6841 | 0.7138 |
62
- | 1.0235 | 2.0 | 642 | 0.8405 | 0.6838 | 0.7960 | 0.6838 | 0.7046 |
63
- | 1.0061 | 3.0 | 963 | 0.6089 | 0.7715 | 0.7852 | 0.7715 | 0.7590 |
64
- | 0.8574 | 4.0 | 1284 | 0.6548 | 0.7080 | 0.8098 | 0.7080 | 0.7353 |
65
- | 0.7849 | 5.0 | 1605 | 0.6220 | 0.7847 | 0.8092 | 0.7847 | 0.7851 |
66
- | 0.7247 | 6.0 | 1926 | 0.5565 | 0.7937 | 0.8135 | 0.7937 | 0.8006 |
67
- | 0.6355 | 7.0 | 2247 | 0.5821 | 0.7767 | 0.8211 | 0.7767 | 0.7857 |
68
- | 0.5745 | 8.0 | 2568 | 0.5514 | 0.7812 | 0.8314 | 0.7812 | 0.7967 |
69
- | 0.5323 | 9.0 | 2889 | 0.4866 | 0.8370 | 0.8431 | 0.8370 | 0.8381 |
70
- | 0.4582 | 10.0 | 3210 | 0.4829 | 0.8440 | 0.8480 | 0.8440 | 0.8409 |
71
- | 0.4188 | 11.0 | 3531 | 0.4901 | 0.8367 | 0.8598 | 0.8367 | 0.8434 |
72
- | 0.3599 | 12.0 | 3852 | 0.5060 | 0.8533 | 0.8610 | 0.8533 | 0.8551 |
73
- | 0.3192 | 13.0 | 4173 | 0.6934 | 0.8322 | 0.8438 | 0.8322 | 0.8281 |
74
- | 0.3145 | 14.0 | 4494 | 0.5187 | 0.8693 | 0.8725 | 0.8693 | 0.8702 |
75
- | 0.2223 | 15.0 | 4815 | 0.5353 | 0.8596 | 0.8621 | 0.8596 | 0.8583 |
76
- | 0.2053 | 16.0 | 5136 | 0.5325 | 0.8651 | 0.8669 | 0.8651 | 0.8648 |
77
- | 0.1557 | 17.0 | 5457 | 0.5371 | 0.8686 | 0.8647 | 0.8686 | 0.8648 |
78
- | 0.1539 | 18.0 | 5778 | 0.5454 | 0.8675 | 0.8677 | 0.8675 | 0.8671 |
79
- | 0.1259 | 19.0 | 6099 | 0.5592 | 0.8707 | 0.8704 | 0.8707 | 0.8699 |
80
- | 0.1362 | 20.0 | 6420 | 0.6169 | 0.8679 | 0.8646 | 0.8679 | 0.8646 |
81
 
82
 
83
  ### 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-dropout-0.2
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: 0.6001
24
+ - Accuracy: 0.8655
25
+ - Precision: 0.8655
26
+ - Recall: 0.8655
27
+ - F1: 0.8643
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: 1219
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
+ | 1.6129 | 1.0 | 321 | 0.8251 | 0.7223 | 0.7708 | 0.7223 | 0.7354 |
61
+ | 0.9753 | 2.0 | 642 | 0.7419 | 0.7115 | 0.7830 | 0.7115 | 0.7320 |
62
+ | 0.9289 | 3.0 | 963 | 0.5421 | 0.7968 | 0.7942 | 0.7968 | 0.7901 |
63
+ | 0.8978 | 4.0 | 1284 | 0.6563 | 0.7410 | 0.8112 | 0.7410 | 0.7569 |
64
+ | 0.8271 | 5.0 | 1605 | 0.5586 | 0.8058 | 0.8090 | 0.8058 | 0.8050 |
65
+ | 0.7757 | 6.0 | 1926 | 0.5340 | 0.8065 | 0.8220 | 0.8065 | 0.8113 |
66
+ | 0.6981 | 7.0 | 2247 | 0.5943 | 0.7791 | 0.8207 | 0.7791 | 0.7911 |
67
+ | 0.5954 | 8.0 | 2568 | 0.5836 | 0.7660 | 0.8270 | 0.7660 | 0.7824 |
68
+ | 0.5804 | 9.0 | 2889 | 0.4888 | 0.8318 | 0.8450 | 0.8318 | 0.8340 |
69
+ | 0.4894 | 10.0 | 3210 | 0.5404 | 0.8037 | 0.8459 | 0.8037 | 0.8145 |
70
+ | 0.4924 | 11.0 | 3531 | 0.4997 | 0.8166 | 0.8530 | 0.8166 | 0.8257 |
71
+ | 0.38 | 12.0 | 3852 | 0.5669 | 0.8356 | 0.8487 | 0.8356 | 0.8404 |
72
+ | 0.3109 | 13.0 | 4173 | 0.5983 | 0.8467 | 0.8492 | 0.8467 | 0.8415 |
73
+ | 0.3445 | 14.0 | 4494 | 0.5060 | 0.8620 | 0.8643 | 0.8620 | 0.8622 |
74
+ | 0.2457 | 15.0 | 4815 | 0.5823 | 0.8547 | 0.8564 | 0.8547 | 0.8520 |
75
+ | 0.2297 | 16.0 | 5136 | 0.5347 | 0.8620 | 0.8647 | 0.8620 | 0.8628 |
76
+ | 0.1701 | 17.0 | 5457 | 0.5561 | 0.8689 | 0.8665 | 0.8689 | 0.8656 |
77
+ | 0.186 | 18.0 | 5778 | 0.5319 | 0.8686 | 0.8688 | 0.8686 | 0.8679 |
78
+ | 0.1258 | 19.0 | 6099 | 0.6001 | 0.8655 | 0.8655 | 0.8655 | 0.8643 |
 
79
 
80
 
81
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ae9f8d0409e63842de234af55b34ad3484e43d98b8a675868e5d2b925d1a209
3
  size 343239356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e930dbd14cdbf4e5176a43258a628642eca8475d06a2774ea3f87cb76a6a53d
3
  size 343239356