Dhyey8 commited on
Commit
0b15979
1 Parent(s): 8dc18b2

Model save

Browse files
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8673913043478261
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 [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.6580
36
- - Accuracy: 0.8674
37
 
38
  ## Model description
39
 
@@ -67,46 +67,46 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 0.8 | 3 | 1.1515 | 0.7913 |
71
- | No log | 1.87 | 7 | 1.1546 | 0.7630 |
72
- | 0.6441 | 2.93 | 11 | 1.0708 | 0.8065 |
73
- | 0.6441 | 4.0 | 15 | 0.9925 | 0.8217 |
74
- | 0.6441 | 4.8 | 18 | 0.9926 | 0.8109 |
75
- | 0.6042 | 5.87 | 22 | 1.0165 | 0.7935 |
76
- | 0.6042 | 6.93 | 26 | 0.8680 | 0.8348 |
77
- | 0.4293 | 8.0 | 30 | 0.8361 | 0.8348 |
78
- | 0.4293 | 8.8 | 33 | 0.8076 | 0.8565 |
79
- | 0.4293 | 9.87 | 37 | 0.7548 | 0.8565 |
80
- | 0.4471 | 10.93 | 41 | 0.7901 | 0.8370 |
81
- | 0.4471 | 12.0 | 45 | 0.7327 | 0.8543 |
82
- | 0.4471 | 12.8 | 48 | 0.7485 | 0.8478 |
83
- | 0.3436 | 13.87 | 52 | 0.7844 | 0.8348 |
84
- | 0.3436 | 14.93 | 56 | 0.6645 | 0.8630 |
85
- | 0.2813 | 16.0 | 60 | 0.7370 | 0.8391 |
86
- | 0.2813 | 16.8 | 63 | 0.7598 | 0.8348 |
87
- | 0.2813 | 17.87 | 67 | 0.6580 | 0.8674 |
88
- | 0.275 | 18.93 | 71 | 0.7026 | 0.8457 |
89
- | 0.275 | 20.0 | 75 | 0.7056 | 0.8370 |
90
- | 0.275 | 20.8 | 78 | 0.6517 | 0.8543 |
91
- | 0.2674 | 21.87 | 82 | 0.5931 | 0.8609 |
92
- | 0.2674 | 22.93 | 86 | 0.5986 | 0.8609 |
93
- | 0.2278 | 24.0 | 90 | 0.5982 | 0.8609 |
94
- | 0.2278 | 24.8 | 93 | 0.6043 | 0.8543 |
95
- | 0.2278 | 25.87 | 97 | 0.6148 | 0.8522 |
96
- | 0.2034 | 26.93 | 101 | 0.6160 | 0.85 |
97
- | 0.2034 | 28.0 | 105 | 0.5904 | 0.8522 |
98
- | 0.2034 | 28.8 | 108 | 0.5825 | 0.8609 |
99
- | 0.2207 | 29.87 | 112 | 0.6132 | 0.8478 |
100
- | 0.2207 | 30.93 | 116 | 0.6181 | 0.8391 |
101
- | 0.1701 | 32.0 | 120 | 0.5689 | 0.85 |
102
- | 0.1701 | 32.8 | 123 | 0.5634 | 0.8609 |
103
- | 0.1701 | 33.87 | 127 | 0.5659 | 0.8652 |
104
- | 0.1681 | 34.93 | 131 | 0.5895 | 0.8565 |
105
- | 0.1681 | 36.0 | 135 | 0.6095 | 0.85 |
106
- | 0.1681 | 36.8 | 138 | 0.6145 | 0.8457 |
107
- | 0.1435 | 37.87 | 142 | 0.6112 | 0.8478 |
108
- | 0.1435 | 38.93 | 146 | 0.5997 | 0.8457 |
109
- | 0.1586 | 40.0 | 150 | 0.5966 | 0.85 |
110
 
111
 
112
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8391304347826087
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 [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.0631
36
+ - Accuracy: 0.8391
37
 
38
  ## Model description
39
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.8 | 3 | 4.5796 | 0.0152 |
71
+ | No log | 1.87 | 7 | 4.5200 | 0.0261 |
72
+ | 4.5616 | 2.93 | 11 | 4.4705 | 0.0326 |
73
+ | 4.5616 | 4.0 | 15 | 4.4127 | 0.0674 |
74
+ | 4.5616 | 4.8 | 18 | 4.3493 | 0.0804 |
75
+ | 4.44 | 5.87 | 22 | 4.2425 | 0.1130 |
76
+ | 4.44 | 6.93 | 26 | 4.1107 | 0.1370 |
77
+ | 4.1823 | 8.0 | 30 | 3.9340 | 0.1609 |
78
+ | 4.1823 | 8.8 | 33 | 3.7821 | 0.1935 |
79
+ | 4.1823 | 9.87 | 37 | 3.5314 | 0.2783 |
80
+ | 3.6357 | 10.93 | 41 | 3.2857 | 0.3043 |
81
+ | 3.6357 | 12.0 | 45 | 3.1064 | 0.3696 |
82
+ | 3.6357 | 12.8 | 48 | 2.9713 | 0.3826 |
83
+ | 3.0041 | 13.87 | 52 | 2.7172 | 0.4870 |
84
+ | 3.0041 | 14.93 | 56 | 2.5111 | 0.5435 |
85
+ | 2.4604 | 16.0 | 60 | 2.3561 | 0.5696 |
86
+ | 2.4604 | 16.8 | 63 | 2.2684 | 0.5717 |
87
+ | 2.4604 | 17.87 | 67 | 2.0961 | 0.6348 |
88
+ | 1.971 | 18.93 | 71 | 1.9555 | 0.6783 |
89
+ | 1.971 | 20.0 | 75 | 1.8400 | 0.6891 |
90
+ | 1.971 | 20.8 | 78 | 1.7856 | 0.7239 |
91
+ | 1.651 | 21.87 | 82 | 1.6797 | 0.7370 |
92
+ | 1.651 | 22.93 | 86 | 1.6007 | 0.7717 |
93
+ | 1.3665 | 24.0 | 90 | 1.5256 | 0.7739 |
94
+ | 1.3665 | 24.8 | 93 | 1.4876 | 0.7652 |
95
+ | 1.3665 | 25.87 | 97 | 1.4395 | 0.7783 |
96
+ | 1.1954 | 26.93 | 101 | 1.3679 | 0.7870 |
97
+ | 1.1954 | 28.0 | 105 | 1.3043 | 0.8022 |
98
+ | 1.1954 | 28.8 | 108 | 1.2906 | 0.8022 |
99
+ | 0.9886 | 29.87 | 112 | 1.2313 | 0.8109 |
100
+ | 0.9886 | 30.93 | 116 | 1.1829 | 0.8348 |
101
+ | 0.8803 | 32.0 | 120 | 1.1564 | 0.8391 |
102
+ | 0.8803 | 32.8 | 123 | 1.1421 | 0.8304 |
103
+ | 0.8803 | 33.87 | 127 | 1.1144 | 0.8326 |
104
+ | 0.815 | 34.93 | 131 | 1.1074 | 0.8304 |
105
+ | 0.815 | 36.0 | 135 | 1.0919 | 0.8283 |
106
+ | 0.815 | 36.8 | 138 | 1.0821 | 0.8326 |
107
+ | 0.7619 | 37.87 | 142 | 1.0701 | 0.8348 |
108
+ | 0.7619 | 38.93 | 146 | 1.0642 | 0.8348 |
109
+ | 0.6991 | 40.0 | 150 | 1.0631 | 0.8391 |
110
 
111
 
112
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5bd5a564cd98283c5f7f91c9d93153d893c91448e99f700a4430c4c21f3c0d3
3
  size 110619696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dccff25e8bb4b2cf484d2592ae424539097f2d72b6ca5074a3f1dfec1cb43d6
3
  size 110619696
runs/Apr04_09-11-23_fe56890e08d0/events.out.tfevents.1712221884.fe56890e08d0.1029.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2761eb00123d51fa6622ca497a87796052cf82d879a3a399bee1c80f9e3dfc14
3
- size 22996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71ec63366c23a2f3755148756af64e1eabd8bb23d06f8ccb63ace91d92bd2b47
3
+ size 23884