Hugging Face's logo

synergyai-jaeung
/
swin-tiny-patch4-window7-224-finetuned-RCC

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
synergyai-jaeung commited on
Commit
db5a405
•
1 Parent(s): 6f94450

Model save

Browse files
Files changed (2) hide show
  1. README.md +21 -20
  2. model.safetensors +1 -1
README.md CHANGED
@@ -20,12 +20,12 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.3261
24
- - Accuracy: 0.9032
25
- - Precision: 0.9032
26
- - Recall: 1.0
27
- - F1: 0.4746
28
- - Auc: 0.5
29
 
30
  ## Model description
31
 
@@ -45,11 +45,11 @@ More information needed
45
 
46
  The following hyperparameters were used during training:
47
  - learning_rate: 5e-05
48
- - train_batch_size: 64
49
- - eval_batch_size: 64
50
  - seed: 42
51
  - gradient_accumulation_steps: 4
52
- - total_train_batch_size: 256
53
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
  - lr_scheduler_type: linear
55
  - lr_scheduler_warmup_ratio: 0.1
@@ -57,17 +57,18 @@ The following hyperparameters were used during training:
57
 
58
  ### Training results
59
 
60
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Auc |
61
- |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:---:|
62
- | No log | 0.8571 | 3 | 0.3023 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
63
- | No log | 2.0 | 7 | 0.3677 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
64
- | 0.4028 | 2.8571 | 10 | 0.3276 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
65
- | 0.4028 | 4.0 | 14 | 0.3286 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
66
- | 0.4028 | 4.8571 | 17 | 0.3271 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
67
- | 0.2494 | 6.0 | 21 | 0.3259 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
68
- | 0.2494 | 6.8571 | 24 | 0.3279 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
69
- | 0.2494 | 8.0 | 28 | 0.3267 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
70
- | 0.2351 | 8.5714 | 30 | 0.3261 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
 
71
 
72
 
73
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.3526
24
+ - Accuracy: 0.8226
25
+ - Precision: 0.9245
26
+ - Recall: 0.875
27
+ - F1: 0.5829
28
+ - Auc: 0.6042
29
 
30
  ## Model description
31
 
 
45
 
46
  The following hyperparameters were used during training:
47
  - learning_rate: 5e-05
48
+ - train_batch_size: 32
49
+ - eval_batch_size: 32
50
  - seed: 42
51
  - gradient_accumulation_steps: 4
52
+ - total_train_batch_size: 128
53
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
  - lr_scheduler_type: linear
55
  - lr_scheduler_warmup_ratio: 0.1
 
57
 
58
  ### Training results
59
 
60
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Auc |
61
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
62
+ | No log | 1.0 | 7 | 0.3296 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
63
+ | 0.4795 | 2.0 | 14 | 0.3129 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
64
+ | 0.2503 | 3.0 | 21 | 0.3182 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
65
+ | 0.2503 | 4.0 | 28 | 0.2973 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
66
+ | 0.2231 | 5.0 | 35 | 0.3275 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
67
+ | 0.1791 | 6.0 | 42 | 0.3147 | 0.9032 | 0.9032 | 1.0 | 0.4746 | 0.5 |
68
+ | 0.1791 | 7.0 | 49 | 0.3401 | 0.8978 | 0.9071 | 0.9881 | 0.5206 | 0.5218 |
69
+ | 0.1361 | 8.0 | 56 | 0.3885 | 0.7849 | 0.9211 | 0.8333 | 0.5529 | 0.5833 |
70
+ | 0.1245 | 9.0 | 63 | 0.3192 | 0.8817 | 0.9195 | 0.9524 | 0.6012 | 0.5873 |
71
+ | 0.0902 | 10.0 | 70 | 0.3526 | 0.8226 | 0.9245 | 0.875 | 0.5829 | 0.6042 |
72
 
73
 
74
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:206ebeb891a78686dba6fdf8aa27f49bb54f66a14360a90d49d548d28bc62f4d
3
  size 110342832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d07e7c41d6e3d022c28c3c64002a95b5a168904c992038f6dda631436efb1a4
3
  size 110342832