Hugging Face's logo

Hemg
/
pneumonia-classification-model

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
Hemg commited on
Commit
7d0413a
·
verified ·
1 Parent(s): d03e986

Model save

Browse files
Files changed (3) hide show
  1. README.md +36 -20
  2. model.safetensors +1 -1
  3. runs/Mar05_08-24-37_734512731fb7/events.out.tfevents.1709627078.734512731fb7.34.1 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9632352941176471
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the chestxrayclassification dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.1081
36
- - Accuracy: 0.9632
37
 
38
  ## Model description
39
 
@@ -61,28 +61,44 @@ The following hyperparameters were used during training:
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
- - num_epochs: 16
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 0.5968 | 0.98 | 25 | 0.4404 | 0.7230 |
71
- | 0.3253 | 2.0 | 51 | 0.2667 | 0.9130 |
72
- | 0.2096 | 2.98 | 76 | 0.2183 | 0.9093 |
73
- | 0.1623 | 4.0 | 102 | 0.1786 | 0.9387 |
74
- | 0.1697 | 4.98 | 127 | 0.1354 | 0.9522 |
75
- | 0.1405 | 6.0 | 153 | 0.1424 | 0.9510 |
76
- | 0.1306 | 6.98 | 178 | 0.1299 | 0.9534 |
77
- | 0.1093 | 8.0 | 204 | 0.1316 | 0.9510 |
78
- | 0.1151 | 8.98 | 229 | 0.1179 | 0.9583 |
79
- | 0.0976 | 10.0 | 255 | 0.1204 | 0.9583 |
80
- | 0.0932 | 10.98 | 280 | 0.1393 | 0.9485 |
81
- | 0.1039 | 12.0 | 306 | 0.1239 | 0.9571 |
82
- | 0.0907 | 12.98 | 331 | 0.1029 | 0.9583 |
83
- | 0.0917 | 14.0 | 357 | 0.1275 | 0.9583 |
84
- | 0.0754 | 14.98 | 382 | 0.1034 | 0.9669 |
85
- | 0.0662 | 15.69 | 400 | 0.1081 | 0.9632 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
86
 
87
 
88
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9656862745098039
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the chestxrayclassification dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.1143
36
+ - Accuracy: 0.9657
37
 
38
  ## Model description
39
 
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 32
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.6297 | 0.98 | 25 | 0.5258 | 0.7230 |
71
+ | 0.3781 | 2.0 | 51 | 0.3011 | 0.9154 |
72
+ | 0.2268 | 2.98 | 76 | 0.1981 | 0.9314 |
73
+ | 0.1827 | 4.0 | 102 | 0.1602 | 0.9473 |
74
+ | 0.1765 | 4.98 | 127 | 0.1446 | 0.9461 |
75
+ | 0.1508 | 6.0 | 153 | 0.1449 | 0.9510 |
76
+ | 0.1332 | 6.98 | 178 | 0.1510 | 0.9375 |
77
+ | 0.1187 | 8.0 | 204 | 0.1169 | 0.9596 |
78
+ | 0.131 | 8.98 | 229 | 0.1315 | 0.9559 |
79
+ | 0.1043 | 10.0 | 255 | 0.1114 | 0.9571 |
80
+ | 0.1022 | 10.98 | 280 | 0.1633 | 0.9375 |
81
+ | 0.0893 | 12.0 | 306 | 0.1167 | 0.9596 |
82
+ | 0.0848 | 12.98 | 331 | 0.0936 | 0.9694 |
83
+ | 0.0885 | 14.0 | 357 | 0.1074 | 0.9608 |
84
+ | 0.0928 | 14.98 | 382 | 0.1052 | 0.9645 |
85
+ | 0.0776 | 16.0 | 408 | 0.1116 | 0.9608 |
86
+ | 0.0895 | 16.98 | 433 | 0.1060 | 0.9645 |
87
+ | 0.0817 | 18.0 | 459 | 0.1107 | 0.9632 |
88
+ | 0.0766 | 18.98 | 484 | 0.0993 | 0.9669 |
89
+ | 0.0697 | 20.0 | 510 | 0.0938 | 0.9681 |
90
+ | 0.0626 | 20.98 | 535 | 0.1199 | 0.9620 |
91
+ | 0.0665 | 22.0 | 561 | 0.1100 | 0.9657 |
92
+ | 0.0613 | 22.98 | 586 | 0.1246 | 0.9620 |
93
+ | 0.054 | 24.0 | 612 | 0.1066 | 0.9645 |
94
+ | 0.0474 | 24.98 | 637 | 0.1100 | 0.9669 |
95
+ | 0.0456 | 26.0 | 663 | 0.1118 | 0.9645 |
96
+ | 0.0473 | 26.98 | 688 | 0.1137 | 0.9645 |
97
+ | 0.0543 | 28.0 | 714 | 0.0955 | 0.9632 |
98
+ | 0.0493 | 28.98 | 739 | 0.1300 | 0.9559 |
99
+ | 0.043 | 30.0 | 765 | 0.1229 | 0.9669 |
100
+ | 0.039 | 30.98 | 790 | 0.1125 | 0.9608 |
101
+ | 0.0398 | 31.37 | 800 | 0.1143 | 0.9657 |
102
 
103
 
104
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bace017d0eb5e21bed2080795dd02536fd213bbae242f7b999a69b64ae03ce55
3
  size 343223968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c874fdfa2b0d8433fa38dc6533799290fdb4ed5e8ba91db52a984aee5240323
3
  size 343223968
runs/Mar05_08-24-37_734512731fb7/events.out.tfevents.1709627078.734512731fb7.34.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b08b5cb1c332e06c034fc93ca00e5affab1e6e3fed794b7735b17293627c2c9
3
- size 21644
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:497d34638e840fbb96cb8ecdcd612a72f1b8dc1e0c714d18fba64dd977d88ce3
3
+ size 21998