Hugging Face's logo

amanvip2
/
finetuned-breast_cancer_images

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
amanvip2 commited on
Commit
86eaed7
•
1 Parent(s): 4f3ac2d

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +52 -40
README.md CHANGED
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Train Accuracy: 0.9113
20
- - Train Loss: 0.0064
21
- - Accuracy: 0.9620
22
- - Loss: 0.0069
23
 
24
  ## Model description
25
 
@@ -38,48 +38,60 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 0.0002
42
- - train_batch_size: 32
43
- - eval_batch_size: 32
44
  - seed: 42
 
 
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - num_epochs: 75
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Accuracy | Loss | Validation Loss |
52
- |:-------------:|:-----:|:----:|:--------:|:------:|:---------------:|
53
- | No log | 5.0 | 200 | 0.8449 | 0.0173 | 0.0157 |
54
- | No log | 5.0 | 200 | 0.8449 | 0.0173 | 0.0157 |
55
- | No log | 10.0 | 400 | 0.9209 | 0.0135 | 0.0096 |
56
- | No log | 10.0 | 400 | 0.9209 | 0.0135 | 0.0096 |
57
- | No log | 15.0 | 600 | 0.9335 | 0.0126 | 0.0074 |
58
- | No log | 15.0 | 600 | 0.9335 | 0.0126 | 0.0074 |
59
- | No log | 20.0 | 800 | 0.9335 | 0.0101 | 0.0079 |
60
- | No log | 20.0 | 800 | 0.9335 | 0.0101 | 0.0079 |
61
- | No log | 25.0 | 1000 | 0.9335 | 0.0086 | 0.0094 |
62
- | No log | 25.0 | 1000 | 0.9335 | 0.0086 | 0.0094 |
63
- | No log | 30.0 | 1200 | 0.9241 | 0.0096 | 0.0098 |
64
- | No log | 30.0 | 1200 | 0.9241 | 0.0096 | 0.0098 |
65
- | No log | 35.0 | 1400 | 0.9557 | 0.0093 | 0.0080 |
66
- | No log | 35.0 | 1400 | 0.9557 | 0.0093 | 0.0080 |
67
- | No log | 40.0 | 1600 | 0.9462 | 0.0085 | 0.0076 |
68
- | No log | 40.0 | 1600 | 0.9462 | 0.0085 | 0.0076 |
69
- | No log | 45.0 | 1800 | 0.9462 | 0.0073 | 0.0082 |
70
- | No log | 45.0 | 1800 | 0.9462 | 0.0073 | 0.0082 |
71
- | No log | 50.0 | 2000 | 0.9684 | 0.0072 | 0.0067 |
72
- | No log | 50.0 | 2000 | 0.9684 | 0.0072 | 0.0067 |
73
- | No log | 55.0 | 2200 | 0.9525 | 0.0061 | 0.0076 |
74
- | No log | 55.0 | 2200 | 0.9525 | 0.0061 | 0.0076 |
75
- | No log | 60.0 | 2400 | 0.9525 | 0.0065 | 0.0083 |
76
- | No log | 60.0 | 2400 | 0.9525 | 0.0065 | 0.0083 |
77
- | No log | 65.0 | 2600 | 0.9620 | 0.0065 | 0.0066 |
78
- | No log | 65.0 | 2600 | 0.9620 | 0.0065 | 0.0066 |
79
- | No log | 70.0 | 2800 | 0.9557 | 0.0061 | 0.0074 |
80
- | No log | 70.0 | 2800 | 0.9557 | 0.0061 | 0.0074 |
81
- | No log | 75.0 | 3000 | 0.9620 | 0.0064 | 0.0069 |
82
- | No log | 75.0 | 3000 | 0.9620 | 0.0064 | 0.0069 |
 
 
 
 
 
 
 
 
 
 
83
 
84
 
85
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Train Accuracy: 0.9025
20
+ - Train Loss: 0.0125
21
+ - Accuracy: 0.9589
22
+ - Loss: 0.0175
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 0.0001
42
+ - train_batch_size: 16
43
+ - eval_batch_size: 16
44
  - seed: 42
45
+ - gradient_accumulation_steps: 2
46
+ - total_train_batch_size: 32
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
+ - num_epochs: 103
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Accuracy | Loss | Validation Loss |
54
+ |:-------------:|:------:|:----:|:--------:|:------:|:---------------:|
55
+ | No log | 5.06 | 200 | 0.9114 | 0.0241 | 0.0172 |
56
+ | No log | 5.06 | 200 | 0.9114 | 0.0241 | 0.0172 |
57
+ | No log | 10.13 | 400 | 0.9335 | 0.0209 | 0.0157 |
58
+ | No log | 10.13 | 400 | 0.9335 | 0.0209 | 0.0157 |
59
+ | No log | 15.19 | 600 | 0.9241 | 0.0189 | 0.0172 |
60
+ | No log | 15.19 | 600 | 0.9241 | 0.0189 | 0.0172 |
61
+ | No log | 20.25 | 800 | 0.9430 | 0.0182 | 0.0161 |
62
+ | No log | 20.25 | 800 | 0.9430 | 0.0182 | 0.0161 |
63
+ | No log | 25.32 | 1000 | 0.9399 | 0.0165 | 0.0186 |
64
+ | No log | 25.32 | 1000 | 0.9399 | 0.0165 | 0.0186 |
65
+ | No log | 30.38 | 1200 | 0.9557 | 0.0155 | 0.0137 |
66
+ | No log | 30.38 | 1200 | 0.9557 | 0.0155 | 0.0137 |
67
+ | No log | 35.44 | 1400 | 0.9335 | 0.0136 | 0.0180 |
68
+ | No log | 35.44 | 1400 | 0.9335 | 0.0136 | 0.0180 |
69
+ | No log | 40.51 | 1600 | 0.9525 | 0.0152 | 0.0139 |
70
+ | No log | 40.51 | 1600 | 0.9525 | 0.0152 | 0.0139 |
71
+ | No log | 45.57 | 1800 | 0.9494 | 0.0144 | 0.0149 |
72
+ | No log | 45.57 | 1800 | 0.9494 | 0.0144 | 0.0149 |
73
+ | No log | 50.63 | 2000 | 0.9430 | 0.0153 | 0.0187 |
74
+ | No log | 50.63 | 2000 | 0.9430 | 0.0153 | 0.0187 |
75
+ | No log | 55.7 | 2200 | 0.9557 | 0.0132 | 0.0149 |
76
+ | No log | 55.7 | 2200 | 0.9557 | 0.0132 | 0.0149 |
77
+ | No log | 60.76 | 2400 | 0.9430 | 0.0124 | 0.0149 |
78
+ | No log | 60.76 | 2400 | 0.9430 | 0.0124 | 0.0149 |
79
+ | No log | 65.82 | 2600 | 0.9525 | 0.0134 | 0.0164 |
80
+ | No log | 65.82 | 2600 | 0.9525 | 0.0134 | 0.0164 |
81
+ | No log | 70.89 | 2800 | 0.9557 | 0.0117 | 0.0143 |
82
+ | No log | 70.89 | 2800 | 0.9557 | 0.0117 | 0.0143 |
83
+ | No log | 75.95 | 3000 | 0.9557 | 0.0112 | 0.0166 |
84
+ | No log | 75.95 | 3000 | 0.9557 | 0.0112 | 0.0166 |
85
+ | No log | 81.01 | 3200 | 0.9589 | 0.0118 | 0.0163 |
86
+ | No log | 81.01 | 3200 | 0.9589 | 0.0118 | 0.0163 |
87
+ | No log | 86.08 | 3400 | 0.9494 | 0.0106 | 0.0188 |
88
+ | No log | 86.08 | 3400 | 0.9494 | 0.0106 | 0.0188 |
89
+ | No log | 91.14 | 3600 | 0.9462 | 0.0121 | 0.0186 |
90
+ | No log | 91.14 | 3600 | 0.9462 | 0.0121 | 0.0186 |
91
+ | No log | 96.2 | 3800 | 0.9525 | 0.0129 | 0.0171 |
92
+ | No log | 96.2 | 3800 | 0.9525 | 0.0129 | 0.0171 |
93
+ | No log | 101.27 | 4000 | 0.9589 | 0.0125 | 0.0175 |
94
+ | No log | 101.27 | 4000 | 0.9589 | 0.0125 | 0.0175 |
95
 
96
 
97
  ### Framework versions